diff options
Diffstat (limited to 'app/openssl/crypto/sha/asm')
40 files changed, 0 insertions, 35509 deletions
diff --git a/app/openssl/crypto/sha/asm/README b/app/openssl/crypto/sha/asm/README deleted file mode 100644 index b7e75576..00000000 --- a/app/openssl/crypto/sha/asm/README +++ /dev/null @@ -1 +0,0 @@ -C2.pl works diff --git a/app/openssl/crypto/sha/asm/sha1-586.S b/app/openssl/crypto/sha/asm/sha1-586.S deleted file mode 100644 index 47bef2a9..00000000 --- a/app/openssl/crypto/sha/asm/sha1-586.S +++ /dev/null @@ -1,2639 +0,0 @@ -.file "sha1-586.s" -.text -.globl sha1_block_data_order -.type sha1_block_data_order,@function -.align 16 -sha1_block_data_order: -.L_sha1_block_data_order_begin: - pushl %ebp - pushl %ebx - pushl %esi - pushl %edi - call .L000pic_point -.L000pic_point: - popl %ebp - leal _GLOBAL_OFFSET_TABLE_+[.-.L000pic_point](%ebp),%esi - movl OPENSSL_ia32cap_P@GOT(%esi),%esi - leal .LK_XX_XX-.L000pic_point(%ebp),%ebp - movl (%esi),%eax - movl 4(%esi),%edx - testl $512,%edx - jz .L001x86 - testl $16777216,%eax - jz .L001x86 - jmp .Lssse3_shortcut -.align 16 -.L001x86: - movl 20(%esp),%ebp - movl 24(%esp),%esi - movl 28(%esp),%eax - subl $76,%esp - shll $6,%eax - addl %esi,%eax - movl %eax,104(%esp) - movl 16(%ebp),%edi - jmp .L002loop -.align 16 -.L002loop: - movl (%esi),%eax - movl 4(%esi),%ebx - movl 8(%esi),%ecx - movl 12(%esi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - movl %eax,(%esp) - movl %ebx,4(%esp) - movl %ecx,8(%esp) - movl %edx,12(%esp) - movl 16(%esi),%eax - movl 20(%esi),%ebx - movl 24(%esi),%ecx - movl 28(%esi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - movl %eax,16(%esp) - movl %ebx,20(%esp) - movl %ecx,24(%esp) - movl %edx,28(%esp) - movl 32(%esi),%eax - movl 36(%esi),%ebx - movl 40(%esi),%ecx - movl 44(%esi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - movl %eax,32(%esp) - movl %ebx,36(%esp) - movl %ecx,40(%esp) - movl %edx,44(%esp) - movl 48(%esi),%eax - movl 52(%esi),%ebx - movl 56(%esi),%ecx - movl 60(%esi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - movl %eax,48(%esp) - movl %ebx,52(%esp) - movl %ecx,56(%esp) - movl %edx,60(%esp) - movl %esi,100(%esp) - movl (%ebp),%eax - movl 4(%ebp),%ebx - movl 8(%ebp),%ecx - movl 12(%ebp),%edx - - movl %ecx,%esi - movl %eax,%ebp - roll $5,%ebp - xorl %edx,%esi - addl %edi,%ebp - movl (%esp),%edi - andl %ebx,%esi - rorl $2,%ebx - xorl %edx,%esi - leal 1518500249(%ebp,%edi,1),%ebp - addl %esi,%ebp - - movl %ebx,%edi - movl %ebp,%esi - roll $5,%ebp - xorl %ecx,%edi - addl %edx,%ebp - movl 4(%esp),%edx - andl %eax,%edi - rorl $2,%eax - xorl %ecx,%edi - leal 1518500249(%ebp,%edx,1),%ebp - addl %edi,%ebp - - movl %eax,%edx - movl %ebp,%edi - roll $5,%ebp - xorl %ebx,%edx - addl %ecx,%ebp - movl 8(%esp),%ecx - andl %esi,%edx - rorl $2,%esi - xorl %ebx,%edx - leal 1518500249(%ebp,%ecx,1),%ebp - addl %edx,%ebp - - movl %esi,%ecx - movl %ebp,%edx - roll $5,%ebp - xorl %eax,%ecx - addl %ebx,%ebp - movl 12(%esp),%ebx - andl %edi,%ecx - rorl $2,%edi - xorl %eax,%ecx - leal 1518500249(%ebp,%ebx,1),%ebp - addl %ecx,%ebp - - movl %edi,%ebx - movl %ebp,%ecx - roll $5,%ebp - xorl %esi,%ebx - addl %eax,%ebp - movl 16(%esp),%eax - andl %edx,%ebx - rorl $2,%edx - xorl %esi,%ebx - leal 1518500249(%ebp,%eax,1),%ebp - addl %ebx,%ebp - - movl %edx,%eax - movl %ebp,%ebx - roll $5,%ebp - xorl %edi,%eax - addl %esi,%ebp - movl 20(%esp),%esi - andl %ecx,%eax - rorl $2,%ecx - xorl %edi,%eax - leal 1518500249(%ebp,%esi,1),%ebp - addl %eax,%ebp - - movl %ecx,%esi - movl %ebp,%eax - roll $5,%ebp - xorl %edx,%esi - addl %edi,%ebp - movl 24(%esp),%edi - andl %ebx,%esi - rorl $2,%ebx - xorl %edx,%esi - leal 1518500249(%ebp,%edi,1),%ebp - addl %esi,%ebp - - movl %ebx,%edi - movl %ebp,%esi - roll $5,%ebp - xorl %ecx,%edi - addl %edx,%ebp - movl 28(%esp),%edx - andl %eax,%edi - rorl $2,%eax - xorl %ecx,%edi - leal 1518500249(%ebp,%edx,1),%ebp - addl %edi,%ebp - - movl %eax,%edx - movl %ebp,%edi - roll $5,%ebp - xorl %ebx,%edx - addl %ecx,%ebp - movl 32(%esp),%ecx - andl %esi,%edx - rorl $2,%esi - xorl %ebx,%edx - leal 1518500249(%ebp,%ecx,1),%ebp - addl %edx,%ebp - - movl %esi,%ecx - movl %ebp,%edx - roll $5,%ebp - xorl %eax,%ecx - addl %ebx,%ebp - movl 36(%esp),%ebx - andl %edi,%ecx - rorl $2,%edi - xorl %eax,%ecx - leal 1518500249(%ebp,%ebx,1),%ebp - addl %ecx,%ebp - - movl %edi,%ebx - movl %ebp,%ecx - roll $5,%ebp - xorl %esi,%ebx - addl %eax,%ebp - movl 40(%esp),%eax - andl %edx,%ebx - rorl $2,%edx - xorl %esi,%ebx - leal 1518500249(%ebp,%eax,1),%ebp - addl %ebx,%ebp - - movl %edx,%eax - movl %ebp,%ebx - roll $5,%ebp - xorl %edi,%eax - addl %esi,%ebp - movl 44(%esp),%esi - andl %ecx,%eax - rorl $2,%ecx - xorl %edi,%eax - leal 1518500249(%ebp,%esi,1),%ebp - addl %eax,%ebp - - movl %ecx,%esi - movl %ebp,%eax - roll $5,%ebp - xorl %edx,%esi - addl %edi,%ebp - movl 48(%esp),%edi - andl %ebx,%esi - rorl $2,%ebx - xorl %edx,%esi - leal 1518500249(%ebp,%edi,1),%ebp - addl %esi,%ebp - - movl %ebx,%edi - movl %ebp,%esi - roll $5,%ebp - xorl %ecx,%edi - addl %edx,%ebp - movl 52(%esp),%edx - andl %eax,%edi - rorl $2,%eax - xorl %ecx,%edi - leal 1518500249(%ebp,%edx,1),%ebp - addl %edi,%ebp - - movl %eax,%edx - movl %ebp,%edi - roll $5,%ebp - xorl %ebx,%edx - addl %ecx,%ebp - movl 56(%esp),%ecx - andl %esi,%edx - rorl $2,%esi - xorl %ebx,%edx - leal 1518500249(%ebp,%ecx,1),%ebp - addl %edx,%ebp - - movl %esi,%ecx - movl %ebp,%edx - roll $5,%ebp - xorl %eax,%ecx - addl %ebx,%ebp - movl 60(%esp),%ebx - andl %edi,%ecx - rorl $2,%edi - xorl %eax,%ecx - leal 1518500249(%ebp,%ebx,1),%ebp - movl (%esp),%ebx - addl %ebp,%ecx - - movl %edi,%ebp - xorl 8(%esp),%ebx - xorl %esi,%ebp - xorl 32(%esp),%ebx - andl %edx,%ebp - xorl 52(%esp),%ebx - roll $1,%ebx - xorl %esi,%ebp - addl %ebp,%eax - movl %ecx,%ebp - rorl $2,%edx - movl %ebx,(%esp) - roll $5,%ebp - leal 1518500249(%ebx,%eax,1),%ebx - movl 4(%esp),%eax - addl %ebp,%ebx - - movl %edx,%ebp - xorl 12(%esp),%eax - xorl %edi,%ebp - xorl 36(%esp),%eax - andl %ecx,%ebp - xorl 56(%esp),%eax - roll $1,%eax - xorl %edi,%ebp - addl %ebp,%esi - movl %ebx,%ebp - rorl $2,%ecx - movl %eax,4(%esp) - roll $5,%ebp - leal 1518500249(%eax,%esi,1),%eax - movl 8(%esp),%esi - addl %ebp,%eax - - movl %ecx,%ebp - xorl 16(%esp),%esi - xorl %edx,%ebp - xorl 40(%esp),%esi - andl %ebx,%ebp - xorl 60(%esp),%esi - roll $1,%esi - xorl %edx,%ebp - addl %ebp,%edi - movl %eax,%ebp - rorl $2,%ebx - movl %esi,8(%esp) - roll $5,%ebp - leal 1518500249(%esi,%edi,1),%esi - movl 12(%esp),%edi - addl %ebp,%esi - - movl %ebx,%ebp - xorl 20(%esp),%edi - xorl %ecx,%ebp - xorl 44(%esp),%edi - andl %eax,%ebp - xorl (%esp),%edi - roll $1,%edi - xorl %ecx,%ebp - addl %ebp,%edx - movl %esi,%ebp - rorl $2,%eax - movl %edi,12(%esp) - roll $5,%ebp - leal 1518500249(%edi,%edx,1),%edi - movl 16(%esp),%edx - addl %ebp,%edi - - movl %esi,%ebp - xorl 24(%esp),%edx - xorl %eax,%ebp - xorl 48(%esp),%edx - xorl %ebx,%ebp - xorl 4(%esp),%edx - roll $1,%edx - addl %ebp,%ecx - rorl $2,%esi - movl %edi,%ebp - roll $5,%ebp - movl %edx,16(%esp) - leal 1859775393(%edx,%ecx,1),%edx - movl 20(%esp),%ecx - addl %ebp,%edx - - movl %edi,%ebp - xorl 28(%esp),%ecx - xorl %esi,%ebp - xorl 52(%esp),%ecx - xorl %eax,%ebp - xorl 8(%esp),%ecx - roll $1,%ecx - addl %ebp,%ebx - rorl $2,%edi - movl %edx,%ebp - roll $5,%ebp - movl %ecx,20(%esp) - leal 1859775393(%ecx,%ebx,1),%ecx - movl 24(%esp),%ebx - addl %ebp,%ecx - - movl %edx,%ebp - xorl 32(%esp),%ebx - xorl %edi,%ebp - xorl 56(%esp),%ebx - xorl %esi,%ebp - xorl 12(%esp),%ebx - roll $1,%ebx - addl %ebp,%eax - rorl $2,%edx - movl %ecx,%ebp - roll $5,%ebp - movl %ebx,24(%esp) - leal 1859775393(%ebx,%eax,1),%ebx - movl 28(%esp),%eax - addl %ebp,%ebx - - movl %ecx,%ebp - xorl 36(%esp),%eax - xorl %edx,%ebp - xorl 60(%esp),%eax - xorl %edi,%ebp - xorl 16(%esp),%eax - roll $1,%eax - addl %ebp,%esi - rorl $2,%ecx - movl %ebx,%ebp - roll $5,%ebp - movl %eax,28(%esp) - leal 1859775393(%eax,%esi,1),%eax - movl 32(%esp),%esi - addl %ebp,%eax - - movl %ebx,%ebp - xorl 40(%esp),%esi - xorl %ecx,%ebp - xorl (%esp),%esi - xorl %edx,%ebp - xorl 20(%esp),%esi - roll $1,%esi - addl %ebp,%edi - rorl $2,%ebx - movl %eax,%ebp - roll $5,%ebp - movl %esi,32(%esp) - leal 1859775393(%esi,%edi,1),%esi - movl 36(%esp),%edi - addl %ebp,%esi - - movl %eax,%ebp - xorl 44(%esp),%edi - xorl %ebx,%ebp - xorl 4(%esp),%edi - xorl %ecx,%ebp - xorl 24(%esp),%edi - roll $1,%edi - addl %ebp,%edx - rorl $2,%eax - movl %esi,%ebp - roll $5,%ebp - movl %edi,36(%esp) - leal 1859775393(%edi,%edx,1),%edi - movl 40(%esp),%edx - addl %ebp,%edi - - movl %esi,%ebp - xorl 48(%esp),%edx - xorl %eax,%ebp - xorl 8(%esp),%edx - xorl %ebx,%ebp - xorl 28(%esp),%edx - roll $1,%edx - addl %ebp,%ecx - rorl $2,%esi - movl %edi,%ebp - roll $5,%ebp - movl %edx,40(%esp) - leal 1859775393(%edx,%ecx,1),%edx - movl 44(%esp),%ecx - addl %ebp,%edx - - movl %edi,%ebp - xorl 52(%esp),%ecx - xorl %esi,%ebp - xorl 12(%esp),%ecx - xorl %eax,%ebp - xorl 32(%esp),%ecx - roll $1,%ecx - addl %ebp,%ebx - rorl $2,%edi - movl %edx,%ebp - roll $5,%ebp - movl %ecx,44(%esp) - leal 1859775393(%ecx,%ebx,1),%ecx - movl 48(%esp),%ebx - addl %ebp,%ecx - - movl %edx,%ebp - xorl 56(%esp),%ebx - xorl %edi,%ebp - xorl 16(%esp),%ebx - xorl %esi,%ebp - xorl 36(%esp),%ebx - roll $1,%ebx - addl %ebp,%eax - rorl $2,%edx - movl %ecx,%ebp - roll $5,%ebp - movl %ebx,48(%esp) - leal 1859775393(%ebx,%eax,1),%ebx - movl 52(%esp),%eax - addl %ebp,%ebx - - movl %ecx,%ebp - xorl 60(%esp),%eax - xorl %edx,%ebp - xorl 20(%esp),%eax - xorl %edi,%ebp - xorl 40(%esp),%eax - roll $1,%eax - addl %ebp,%esi - rorl $2,%ecx - movl %ebx,%ebp - roll $5,%ebp - movl %eax,52(%esp) - leal 1859775393(%eax,%esi,1),%eax - movl 56(%esp),%esi - addl %ebp,%eax - - movl %ebx,%ebp - xorl (%esp),%esi - xorl %ecx,%ebp - xorl 24(%esp),%esi - xorl %edx,%ebp - xorl 44(%esp),%esi - roll $1,%esi - addl %ebp,%edi - rorl $2,%ebx - movl %eax,%ebp - roll $5,%ebp - movl %esi,56(%esp) - leal 1859775393(%esi,%edi,1),%esi - movl 60(%esp),%edi - addl %ebp,%esi - - movl %eax,%ebp - xorl 4(%esp),%edi - xorl %ebx,%ebp - xorl 28(%esp),%edi - xorl %ecx,%ebp - xorl 48(%esp),%edi - roll $1,%edi - addl %ebp,%edx - rorl $2,%eax - movl %esi,%ebp - roll $5,%ebp - movl %edi,60(%esp) - leal 1859775393(%edi,%edx,1),%edi - movl (%esp),%edx - addl %ebp,%edi - - movl %esi,%ebp - xorl 8(%esp),%edx - xorl %eax,%ebp - xorl 32(%esp),%edx - xorl %ebx,%ebp - xorl 52(%esp),%edx - roll $1,%edx - addl %ebp,%ecx - rorl $2,%esi - movl %edi,%ebp - roll $5,%ebp - movl %edx,(%esp) - leal 1859775393(%edx,%ecx,1),%edx - movl 4(%esp),%ecx - addl %ebp,%edx - - movl %edi,%ebp - xorl 12(%esp),%ecx - xorl %esi,%ebp - xorl 36(%esp),%ecx - xorl %eax,%ebp - xorl 56(%esp),%ecx - roll $1,%ecx - addl %ebp,%ebx - rorl $2,%edi - movl %edx,%ebp - roll $5,%ebp - movl %ecx,4(%esp) - leal 1859775393(%ecx,%ebx,1),%ecx - movl 8(%esp),%ebx - addl %ebp,%ecx - - movl %edx,%ebp - xorl 16(%esp),%ebx - xorl %edi,%ebp - xorl 40(%esp),%ebx - xorl %esi,%ebp - xorl 60(%esp),%ebx - roll $1,%ebx - addl %ebp,%eax - rorl $2,%edx - movl %ecx,%ebp - roll $5,%ebp - movl %ebx,8(%esp) - leal 1859775393(%ebx,%eax,1),%ebx - movl 12(%esp),%eax - addl %ebp,%ebx - - movl %ecx,%ebp - xorl 20(%esp),%eax - xorl %edx,%ebp - xorl 44(%esp),%eax - xorl %edi,%ebp - xorl (%esp),%eax - roll $1,%eax - addl %ebp,%esi - rorl $2,%ecx - movl %ebx,%ebp - roll $5,%ebp - movl %eax,12(%esp) - leal 1859775393(%eax,%esi,1),%eax - movl 16(%esp),%esi - addl %ebp,%eax - - movl %ebx,%ebp - xorl 24(%esp),%esi - xorl %ecx,%ebp - xorl 48(%esp),%esi - xorl %edx,%ebp - xorl 4(%esp),%esi - roll $1,%esi - addl %ebp,%edi - rorl $2,%ebx - movl %eax,%ebp - roll $5,%ebp - movl %esi,16(%esp) - leal 1859775393(%esi,%edi,1),%esi - movl 20(%esp),%edi - addl %ebp,%esi - - movl %eax,%ebp - xorl 28(%esp),%edi - xorl %ebx,%ebp - xorl 52(%esp),%edi - xorl %ecx,%ebp - xorl 8(%esp),%edi - roll $1,%edi - addl %ebp,%edx - rorl $2,%eax - movl %esi,%ebp - roll $5,%ebp - movl %edi,20(%esp) - leal 1859775393(%edi,%edx,1),%edi - movl 24(%esp),%edx - addl %ebp,%edi - - movl %esi,%ebp - xorl 32(%esp),%edx - xorl %eax,%ebp - xorl 56(%esp),%edx - xorl %ebx,%ebp - xorl 12(%esp),%edx - roll $1,%edx - addl %ebp,%ecx - rorl $2,%esi - movl %edi,%ebp - roll $5,%ebp - movl %edx,24(%esp) - leal 1859775393(%edx,%ecx,1),%edx - movl 28(%esp),%ecx - addl %ebp,%edx - - movl %edi,%ebp - xorl 36(%esp),%ecx - xorl %esi,%ebp - xorl 60(%esp),%ecx - xorl %eax,%ebp - xorl 16(%esp),%ecx - roll $1,%ecx - addl %ebp,%ebx - rorl $2,%edi - movl %edx,%ebp - roll $5,%ebp - movl %ecx,28(%esp) - leal 1859775393(%ecx,%ebx,1),%ecx - movl 32(%esp),%ebx - addl %ebp,%ecx - - movl %edi,%ebp - xorl 40(%esp),%ebx - xorl %esi,%ebp - xorl (%esp),%ebx - andl %edx,%ebp - xorl 20(%esp),%ebx - roll $1,%ebx - addl %eax,%ebp - rorl $2,%edx - movl %ecx,%eax - roll $5,%eax - movl %ebx,32(%esp) - leal 2400959708(%ebx,%ebp,1),%ebx - movl %edi,%ebp - addl %eax,%ebx - andl %esi,%ebp - movl 36(%esp),%eax - addl %ebp,%ebx - - movl %edx,%ebp - xorl 44(%esp),%eax - xorl %edi,%ebp - xorl 4(%esp),%eax - andl %ecx,%ebp - xorl 24(%esp),%eax - roll $1,%eax - addl %esi,%ebp - rorl $2,%ecx - movl %ebx,%esi - roll $5,%esi - movl %eax,36(%esp) - leal 2400959708(%eax,%ebp,1),%eax - movl %edx,%ebp - addl %esi,%eax - andl %edi,%ebp - movl 40(%esp),%esi - addl %ebp,%eax - - movl %ecx,%ebp - xorl 48(%esp),%esi - xorl %edx,%ebp - xorl 8(%esp),%esi - andl %ebx,%ebp - xorl 28(%esp),%esi - roll $1,%esi - addl %edi,%ebp - rorl $2,%ebx - movl %eax,%edi - roll $5,%edi - movl %esi,40(%esp) - leal 2400959708(%esi,%ebp,1),%esi - movl %ecx,%ebp - addl %edi,%esi - andl %edx,%ebp - movl 44(%esp),%edi - addl %ebp,%esi - - movl %ebx,%ebp - xorl 52(%esp),%edi - xorl %ecx,%ebp - xorl 12(%esp),%edi - andl %eax,%ebp - xorl 32(%esp),%edi - roll $1,%edi - addl %edx,%ebp - rorl $2,%eax - movl %esi,%edx - roll $5,%edx - movl %edi,44(%esp) - leal 2400959708(%edi,%ebp,1),%edi - movl %ebx,%ebp - addl %edx,%edi - andl %ecx,%ebp - movl 48(%esp),%edx - addl %ebp,%edi - - movl %eax,%ebp - xorl 56(%esp),%edx - xorl %ebx,%ebp - xorl 16(%esp),%edx - andl %esi,%ebp - xorl 36(%esp),%edx - roll $1,%edx - addl %ecx,%ebp - rorl $2,%esi - movl %edi,%ecx - roll $5,%ecx - movl %edx,48(%esp) - leal 2400959708(%edx,%ebp,1),%edx - movl %eax,%ebp - addl %ecx,%edx - andl %ebx,%ebp - movl 52(%esp),%ecx - addl %ebp,%edx - - movl %esi,%ebp - xorl 60(%esp),%ecx - xorl %eax,%ebp - xorl 20(%esp),%ecx - andl %edi,%ebp - xorl 40(%esp),%ecx - roll $1,%ecx - addl %ebx,%ebp - rorl $2,%edi - movl %edx,%ebx - roll $5,%ebx - movl %ecx,52(%esp) - leal 2400959708(%ecx,%ebp,1),%ecx - movl %esi,%ebp - addl %ebx,%ecx - andl %eax,%ebp - movl 56(%esp),%ebx - addl %ebp,%ecx - - movl %edi,%ebp - xorl (%esp),%ebx - xorl %esi,%ebp - xorl 24(%esp),%ebx - andl %edx,%ebp - xorl 44(%esp),%ebx - roll $1,%ebx - addl %eax,%ebp - rorl $2,%edx - movl %ecx,%eax - roll $5,%eax - movl %ebx,56(%esp) - leal 2400959708(%ebx,%ebp,1),%ebx - movl %edi,%ebp - addl %eax,%ebx - andl %esi,%ebp - movl 60(%esp),%eax - addl %ebp,%ebx - - movl %edx,%ebp - xorl 4(%esp),%eax - xorl %edi,%ebp - xorl 28(%esp),%eax - andl %ecx,%ebp - xorl 48(%esp),%eax - roll $1,%eax - addl %esi,%ebp - rorl $2,%ecx - movl %ebx,%esi - roll $5,%esi - movl %eax,60(%esp) - leal 2400959708(%eax,%ebp,1),%eax - movl %edx,%ebp - addl %esi,%eax - andl %edi,%ebp - movl (%esp),%esi - addl %ebp,%eax - - movl %ecx,%ebp - xorl 8(%esp),%esi - xorl %edx,%ebp - xorl 32(%esp),%esi - andl %ebx,%ebp - xorl 52(%esp),%esi - roll $1,%esi - addl %edi,%ebp - rorl $2,%ebx - movl %eax,%edi - roll $5,%edi - movl %esi,(%esp) - leal 2400959708(%esi,%ebp,1),%esi - movl %ecx,%ebp - addl %edi,%esi - andl %edx,%ebp - movl 4(%esp),%edi - addl %ebp,%esi - - movl %ebx,%ebp - xorl 12(%esp),%edi - xorl %ecx,%ebp - xorl 36(%esp),%edi - andl %eax,%ebp - xorl 56(%esp),%edi - roll $1,%edi - addl %edx,%ebp - rorl $2,%eax - movl %esi,%edx - roll $5,%edx - movl %edi,4(%esp) - leal 2400959708(%edi,%ebp,1),%edi - movl %ebx,%ebp - addl %edx,%edi - andl %ecx,%ebp - movl 8(%esp),%edx - addl %ebp,%edi - - movl %eax,%ebp - xorl 16(%esp),%edx - xorl %ebx,%ebp - xorl 40(%esp),%edx - andl %esi,%ebp - xorl 60(%esp),%edx - roll $1,%edx - addl %ecx,%ebp - rorl $2,%esi - movl %edi,%ecx - roll $5,%ecx - movl %edx,8(%esp) - leal 2400959708(%edx,%ebp,1),%edx - movl %eax,%ebp - addl %ecx,%edx - andl %ebx,%ebp - movl 12(%esp),%ecx - addl %ebp,%edx - - movl %esi,%ebp - xorl 20(%esp),%ecx - xorl %eax,%ebp - xorl 44(%esp),%ecx - andl %edi,%ebp - xorl (%esp),%ecx - roll $1,%ecx - addl %ebx,%ebp - rorl $2,%edi - movl %edx,%ebx - roll $5,%ebx - movl %ecx,12(%esp) - leal 2400959708(%ecx,%ebp,1),%ecx - movl %esi,%ebp - addl %ebx,%ecx - andl %eax,%ebp - movl 16(%esp),%ebx - addl %ebp,%ecx - - movl %edi,%ebp - xorl 24(%esp),%ebx - xorl %esi,%ebp - xorl 48(%esp),%ebx - andl %edx,%ebp - xorl 4(%esp),%ebx - roll $1,%ebx - addl %eax,%ebp - rorl $2,%edx - movl %ecx,%eax - roll $5,%eax - movl %ebx,16(%esp) - leal 2400959708(%ebx,%ebp,1),%ebx - movl %edi,%ebp - addl %eax,%ebx - andl %esi,%ebp - movl 20(%esp),%eax - addl %ebp,%ebx - - movl %edx,%ebp - xorl 28(%esp),%eax - xorl %edi,%ebp - xorl 52(%esp),%eax - andl %ecx,%ebp - xorl 8(%esp),%eax - roll $1,%eax - addl %esi,%ebp - rorl $2,%ecx - movl %ebx,%esi - roll $5,%esi - movl %eax,20(%esp) - leal 2400959708(%eax,%ebp,1),%eax - movl %edx,%ebp - addl %esi,%eax - andl %edi,%ebp - movl 24(%esp),%esi - addl %ebp,%eax - - movl %ecx,%ebp - xorl 32(%esp),%esi - xorl %edx,%ebp - xorl 56(%esp),%esi - andl %ebx,%ebp - xorl 12(%esp),%esi - roll $1,%esi - addl %edi,%ebp - rorl $2,%ebx - movl %eax,%edi - roll $5,%edi - movl %esi,24(%esp) - leal 2400959708(%esi,%ebp,1),%esi - movl %ecx,%ebp - addl %edi,%esi - andl %edx,%ebp - movl 28(%esp),%edi - addl %ebp,%esi - - movl %ebx,%ebp - xorl 36(%esp),%edi - xorl %ecx,%ebp - xorl 60(%esp),%edi - andl %eax,%ebp - xorl 16(%esp),%edi - roll $1,%edi - addl %edx,%ebp - rorl $2,%eax - movl %esi,%edx - roll $5,%edx - movl %edi,28(%esp) - leal 2400959708(%edi,%ebp,1),%edi - movl %ebx,%ebp - addl %edx,%edi - andl %ecx,%ebp - movl 32(%esp),%edx - addl %ebp,%edi - - movl %eax,%ebp - xorl 40(%esp),%edx - xorl %ebx,%ebp - xorl (%esp),%edx - andl %esi,%ebp - xorl 20(%esp),%edx - roll $1,%edx - addl %ecx,%ebp - rorl $2,%esi - movl %edi,%ecx - roll $5,%ecx - movl %edx,32(%esp) - leal 2400959708(%edx,%ebp,1),%edx - movl %eax,%ebp - addl %ecx,%edx - andl %ebx,%ebp - movl 36(%esp),%ecx - addl %ebp,%edx - - movl %esi,%ebp - xorl 44(%esp),%ecx - xorl %eax,%ebp - xorl 4(%esp),%ecx - andl %edi,%ebp - xorl 24(%esp),%ecx - roll $1,%ecx - addl %ebx,%ebp - rorl $2,%edi - movl %edx,%ebx - roll $5,%ebx - movl %ecx,36(%esp) - leal 2400959708(%ecx,%ebp,1),%ecx - movl %esi,%ebp - addl %ebx,%ecx - andl %eax,%ebp - movl 40(%esp),%ebx - addl %ebp,%ecx - - movl %edi,%ebp - xorl 48(%esp),%ebx - xorl %esi,%ebp - xorl 8(%esp),%ebx - andl %edx,%ebp - xorl 28(%esp),%ebx - roll $1,%ebx - addl %eax,%ebp - rorl $2,%edx - movl %ecx,%eax - roll $5,%eax - movl %ebx,40(%esp) - leal 2400959708(%ebx,%ebp,1),%ebx - movl %edi,%ebp - addl %eax,%ebx - andl %esi,%ebp - movl 44(%esp),%eax - addl %ebp,%ebx - - movl %edx,%ebp - xorl 52(%esp),%eax - xorl %edi,%ebp - xorl 12(%esp),%eax - andl %ecx,%ebp - xorl 32(%esp),%eax - roll $1,%eax - addl %esi,%ebp - rorl $2,%ecx - movl %ebx,%esi - roll $5,%esi - movl %eax,44(%esp) - leal 2400959708(%eax,%ebp,1),%eax - movl %edx,%ebp - addl %esi,%eax - andl %edi,%ebp - movl 48(%esp),%esi - addl %ebp,%eax - - movl %ebx,%ebp - xorl 56(%esp),%esi - xorl %ecx,%ebp - xorl 16(%esp),%esi - xorl %edx,%ebp - xorl 36(%esp),%esi - roll $1,%esi - addl %ebp,%edi - rorl $2,%ebx - movl %eax,%ebp - roll $5,%ebp - movl %esi,48(%esp) - leal 3395469782(%esi,%edi,1),%esi - movl 52(%esp),%edi - addl %ebp,%esi - - movl %eax,%ebp - xorl 60(%esp),%edi - xorl %ebx,%ebp - xorl 20(%esp),%edi - xorl %ecx,%ebp - xorl 40(%esp),%edi - roll $1,%edi - addl %ebp,%edx - rorl $2,%eax - movl %esi,%ebp - roll $5,%ebp - movl %edi,52(%esp) - leal 3395469782(%edi,%edx,1),%edi - movl 56(%esp),%edx - addl %ebp,%edi - - movl %esi,%ebp - xorl (%esp),%edx - xorl %eax,%ebp - xorl 24(%esp),%edx - xorl %ebx,%ebp - xorl 44(%esp),%edx - roll $1,%edx - addl %ebp,%ecx - rorl $2,%esi - movl %edi,%ebp - roll $5,%ebp - movl %edx,56(%esp) - leal 3395469782(%edx,%ecx,1),%edx - movl 60(%esp),%ecx - addl %ebp,%edx - - movl %edi,%ebp - xorl 4(%esp),%ecx - xorl %esi,%ebp - xorl 28(%esp),%ecx - xorl %eax,%ebp - xorl 48(%esp),%ecx - roll $1,%ecx - addl %ebp,%ebx - rorl $2,%edi - movl %edx,%ebp - roll $5,%ebp - movl %ecx,60(%esp) - leal 3395469782(%ecx,%ebx,1),%ecx - movl (%esp),%ebx - addl %ebp,%ecx - - movl %edx,%ebp - xorl 8(%esp),%ebx - xorl %edi,%ebp - xorl 32(%esp),%ebx - xorl %esi,%ebp - xorl 52(%esp),%ebx - roll $1,%ebx - addl %ebp,%eax - rorl $2,%edx - movl %ecx,%ebp - roll $5,%ebp - movl %ebx,(%esp) - leal 3395469782(%ebx,%eax,1),%ebx - movl 4(%esp),%eax - addl %ebp,%ebx - - movl %ecx,%ebp - xorl 12(%esp),%eax - xorl %edx,%ebp - xorl 36(%esp),%eax - xorl %edi,%ebp - xorl 56(%esp),%eax - roll $1,%eax - addl %ebp,%esi - rorl $2,%ecx - movl %ebx,%ebp - roll $5,%ebp - movl %eax,4(%esp) - leal 3395469782(%eax,%esi,1),%eax - movl 8(%esp),%esi - addl %ebp,%eax - - movl %ebx,%ebp - xorl 16(%esp),%esi - xorl %ecx,%ebp - xorl 40(%esp),%esi - xorl %edx,%ebp - xorl 60(%esp),%esi - roll $1,%esi - addl %ebp,%edi - rorl $2,%ebx - movl %eax,%ebp - roll $5,%ebp - movl %esi,8(%esp) - leal 3395469782(%esi,%edi,1),%esi - movl 12(%esp),%edi - addl %ebp,%esi - - movl %eax,%ebp - xorl 20(%esp),%edi - xorl %ebx,%ebp - xorl 44(%esp),%edi - xorl %ecx,%ebp - xorl (%esp),%edi - roll $1,%edi - addl %ebp,%edx - rorl $2,%eax - movl %esi,%ebp - roll $5,%ebp - movl %edi,12(%esp) - leal 3395469782(%edi,%edx,1),%edi - movl 16(%esp),%edx - addl %ebp,%edi - - movl %esi,%ebp - xorl 24(%esp),%edx - xorl %eax,%ebp - xorl 48(%esp),%edx - xorl %ebx,%ebp - xorl 4(%esp),%edx - roll $1,%edx - addl %ebp,%ecx - rorl $2,%esi - movl %edi,%ebp - roll $5,%ebp - movl %edx,16(%esp) - leal 3395469782(%edx,%ecx,1),%edx - movl 20(%esp),%ecx - addl %ebp,%edx - - movl %edi,%ebp - xorl 28(%esp),%ecx - xorl %esi,%ebp - xorl 52(%esp),%ecx - xorl %eax,%ebp - xorl 8(%esp),%ecx - roll $1,%ecx - addl %ebp,%ebx - rorl $2,%edi - movl %edx,%ebp - roll $5,%ebp - movl %ecx,20(%esp) - leal 3395469782(%ecx,%ebx,1),%ecx - movl 24(%esp),%ebx - addl %ebp,%ecx - - movl %edx,%ebp - xorl 32(%esp),%ebx - xorl %edi,%ebp - xorl 56(%esp),%ebx - xorl %esi,%ebp - xorl 12(%esp),%ebx - roll $1,%ebx - addl %ebp,%eax - rorl $2,%edx - movl %ecx,%ebp - roll $5,%ebp - movl %ebx,24(%esp) - leal 3395469782(%ebx,%eax,1),%ebx - movl 28(%esp),%eax - addl %ebp,%ebx - - movl %ecx,%ebp - xorl 36(%esp),%eax - xorl %edx,%ebp - xorl 60(%esp),%eax - xorl %edi,%ebp - xorl 16(%esp),%eax - roll $1,%eax - addl %ebp,%esi - rorl $2,%ecx - movl %ebx,%ebp - roll $5,%ebp - movl %eax,28(%esp) - leal 3395469782(%eax,%esi,1),%eax - movl 32(%esp),%esi - addl %ebp,%eax - - movl %ebx,%ebp - xorl 40(%esp),%esi - xorl %ecx,%ebp - xorl (%esp),%esi - xorl %edx,%ebp - xorl 20(%esp),%esi - roll $1,%esi - addl %ebp,%edi - rorl $2,%ebx - movl %eax,%ebp - roll $5,%ebp - movl %esi,32(%esp) - leal 3395469782(%esi,%edi,1),%esi - movl 36(%esp),%edi - addl %ebp,%esi - - movl %eax,%ebp - xorl 44(%esp),%edi - xorl %ebx,%ebp - xorl 4(%esp),%edi - xorl %ecx,%ebp - xorl 24(%esp),%edi - roll $1,%edi - addl %ebp,%edx - rorl $2,%eax - movl %esi,%ebp - roll $5,%ebp - movl %edi,36(%esp) - leal 3395469782(%edi,%edx,1),%edi - movl 40(%esp),%edx - addl %ebp,%edi - - movl %esi,%ebp - xorl 48(%esp),%edx - xorl %eax,%ebp - xorl 8(%esp),%edx - xorl %ebx,%ebp - xorl 28(%esp),%edx - roll $1,%edx - addl %ebp,%ecx - rorl $2,%esi - movl %edi,%ebp - roll $5,%ebp - movl %edx,40(%esp) - leal 3395469782(%edx,%ecx,1),%edx - movl 44(%esp),%ecx - addl %ebp,%edx - - movl %edi,%ebp - xorl 52(%esp),%ecx - xorl %esi,%ebp - xorl 12(%esp),%ecx - xorl %eax,%ebp - xorl 32(%esp),%ecx - roll $1,%ecx - addl %ebp,%ebx - rorl $2,%edi - movl %edx,%ebp - roll $5,%ebp - movl %ecx,44(%esp) - leal 3395469782(%ecx,%ebx,1),%ecx - movl 48(%esp),%ebx - addl %ebp,%ecx - - movl %edx,%ebp - xorl 56(%esp),%ebx - xorl %edi,%ebp - xorl 16(%esp),%ebx - xorl %esi,%ebp - xorl 36(%esp),%ebx - roll $1,%ebx - addl %ebp,%eax - rorl $2,%edx - movl %ecx,%ebp - roll $5,%ebp - movl %ebx,48(%esp) - leal 3395469782(%ebx,%eax,1),%ebx - movl 52(%esp),%eax - addl %ebp,%ebx - - movl %ecx,%ebp - xorl 60(%esp),%eax - xorl %edx,%ebp - xorl 20(%esp),%eax - xorl %edi,%ebp - xorl 40(%esp),%eax - roll $1,%eax - addl %ebp,%esi - rorl $2,%ecx - movl %ebx,%ebp - roll $5,%ebp - leal 3395469782(%eax,%esi,1),%eax - movl 56(%esp),%esi - addl %ebp,%eax - - movl %ebx,%ebp - xorl (%esp),%esi - xorl %ecx,%ebp - xorl 24(%esp),%esi - xorl %edx,%ebp - xorl 44(%esp),%esi - roll $1,%esi - addl %ebp,%edi - rorl $2,%ebx - movl %eax,%ebp - roll $5,%ebp - leal 3395469782(%esi,%edi,1),%esi - movl 60(%esp),%edi - addl %ebp,%esi - - movl %eax,%ebp - xorl 4(%esp),%edi - xorl %ebx,%ebp - xorl 28(%esp),%edi - xorl %ecx,%ebp - xorl 48(%esp),%edi - roll $1,%edi - addl %ebp,%edx - rorl $2,%eax - movl %esi,%ebp - roll $5,%ebp - leal 3395469782(%edi,%edx,1),%edi - addl %ebp,%edi - movl 96(%esp),%ebp - movl 100(%esp),%edx - addl (%ebp),%edi - addl 4(%ebp),%esi - addl 8(%ebp),%eax - addl 12(%ebp),%ebx - addl 16(%ebp),%ecx - movl %edi,(%ebp) - addl $64,%edx - movl %esi,4(%ebp) - cmpl 104(%esp),%edx - movl %eax,8(%ebp) - movl %ecx,%edi - movl %ebx,12(%ebp) - movl %edx,%esi - movl %ecx,16(%ebp) - jb .L002loop - addl $76,%esp - popl %edi - popl %esi - popl %ebx - popl %ebp - ret -.size sha1_block_data_order,.-.L_sha1_block_data_order_begin -.type _sha1_block_data_order_ssse3,@function -.align 16 -_sha1_block_data_order_ssse3: - pushl %ebp - pushl %ebx - pushl %esi - pushl %edi - call .L003pic_point -.L003pic_point: - popl %ebp - leal .LK_XX_XX-.L003pic_point(%ebp),%ebp -.Lssse3_shortcut: - movdqa (%ebp),%xmm7 - movdqa 16(%ebp),%xmm0 - movdqa 32(%ebp),%xmm1 - movdqa 48(%ebp),%xmm2 - movdqa 64(%ebp),%xmm6 - movl 20(%esp),%edi - movl 24(%esp),%ebp - movl 28(%esp),%edx - movl %esp,%esi - subl $208,%esp - andl $-64,%esp - movdqa %xmm0,112(%esp) - movdqa %xmm1,128(%esp) - movdqa %xmm2,144(%esp) - shll $6,%edx - movdqa %xmm7,160(%esp) - addl %ebp,%edx - movdqa %xmm6,176(%esp) - addl $64,%ebp - movl %edi,192(%esp) - movl %ebp,196(%esp) - movl %edx,200(%esp) - movl %esi,204(%esp) - movl (%edi),%eax - movl 4(%edi),%ebx - movl 8(%edi),%ecx - movl 12(%edi),%edx - movl 16(%edi),%edi - movl %ebx,%esi - movdqu -64(%ebp),%xmm0 - movdqu -48(%ebp),%xmm1 - movdqu -32(%ebp),%xmm2 - movdqu -16(%ebp),%xmm3 -.byte 102,15,56,0,198 -.byte 102,15,56,0,206 -.byte 102,15,56,0,214 - movdqa %xmm7,96(%esp) -.byte 102,15,56,0,222 - paddd %xmm7,%xmm0 - paddd %xmm7,%xmm1 - paddd %xmm7,%xmm2 - movdqa %xmm0,(%esp) - psubd %xmm7,%xmm0 - movdqa %xmm1,16(%esp) - psubd %xmm7,%xmm1 - movdqa %xmm2,32(%esp) - psubd %xmm7,%xmm2 - movdqa %xmm1,%xmm4 - jmp .L004loop -.align 16 -.L004loop: - addl (%esp),%edi - xorl %edx,%ecx -.byte 102,15,58,15,224,8 - movdqa %xmm3,%xmm6 - movl %eax,%ebp - roll $5,%eax - paddd %xmm3,%xmm7 - movdqa %xmm0,64(%esp) - andl %ecx,%esi - xorl %edx,%ecx - psrldq $4,%xmm6 - xorl %edx,%esi - addl %eax,%edi - pxor %xmm0,%xmm4 - rorl $2,%ebx - addl %esi,%edi - pxor %xmm2,%xmm6 - addl 4(%esp),%edx - xorl %ecx,%ebx - movl %edi,%esi - roll $5,%edi - pxor %xmm6,%xmm4 - andl %ebx,%ebp - xorl %ecx,%ebx - movdqa %xmm7,48(%esp) - xorl %ecx,%ebp - addl %edi,%edx - movdqa %xmm4,%xmm0 - movdqa %xmm4,%xmm6 - rorl $7,%eax - addl %ebp,%edx - addl 8(%esp),%ecx - xorl %ebx,%eax - pslldq $12,%xmm0 - paddd %xmm4,%xmm4 - movl %edx,%ebp - roll $5,%edx - andl %eax,%esi - xorl %ebx,%eax - psrld $31,%xmm6 - xorl %ebx,%esi - addl %edx,%ecx - movdqa %xmm0,%xmm7 - rorl $7,%edi - addl %esi,%ecx - psrld $30,%xmm0 - por %xmm6,%xmm4 - addl 12(%esp),%ebx - xorl %eax,%edi - movl %ecx,%esi - roll $5,%ecx - pslld $2,%xmm7 - pxor %xmm0,%xmm4 - andl %edi,%ebp - xorl %eax,%edi - movdqa 96(%esp),%xmm0 - xorl %eax,%ebp - addl %ecx,%ebx - pxor %xmm7,%xmm4 - movdqa %xmm2,%xmm5 - rorl $7,%edx - addl %ebp,%ebx - addl 16(%esp),%eax - xorl %edi,%edx -.byte 102,15,58,15,233,8 - movdqa %xmm4,%xmm7 - movl %ebx,%ebp - roll $5,%ebx - paddd %xmm4,%xmm0 - movdqa %xmm1,80(%esp) - andl %edx,%esi - xorl %edi,%edx - psrldq $4,%xmm7 - xorl %edi,%esi - addl %ebx,%eax - pxor %xmm1,%xmm5 - rorl $7,%ecx - addl %esi,%eax - pxor %xmm3,%xmm7 - addl 20(%esp),%edi - xorl %edx,%ecx - movl %eax,%esi - roll $5,%eax - pxor %xmm7,%xmm5 - andl %ecx,%ebp - xorl %edx,%ecx - movdqa %xmm0,(%esp) - xorl %edx,%ebp - addl %eax,%edi - movdqa %xmm5,%xmm1 - movdqa %xmm5,%xmm7 - rorl $7,%ebx - addl %ebp,%edi - addl 24(%esp),%edx - xorl %ecx,%ebx - pslldq $12,%xmm1 - paddd %xmm5,%xmm5 - movl %edi,%ebp - roll $5,%edi - andl %ebx,%esi - xorl %ecx,%ebx - psrld $31,%xmm7 - xorl %ecx,%esi - addl %edi,%edx - movdqa %xmm1,%xmm0 - rorl $7,%eax - addl %esi,%edx - psrld $30,%xmm1 - por %xmm7,%xmm5 - addl 28(%esp),%ecx - xorl %ebx,%eax - movl %edx,%esi - roll $5,%edx - pslld $2,%xmm0 - pxor %xmm1,%xmm5 - andl %eax,%ebp - xorl %ebx,%eax - movdqa 112(%esp),%xmm1 - xorl %ebx,%ebp - addl %edx,%ecx - pxor %xmm0,%xmm5 - movdqa %xmm3,%xmm6 - rorl $7,%edi - addl %ebp,%ecx - addl 32(%esp),%ebx - xorl %eax,%edi -.byte 102,15,58,15,242,8 - movdqa %xmm5,%xmm0 - movl %ecx,%ebp - roll $5,%ecx - paddd %xmm5,%xmm1 - movdqa %xmm2,96(%esp) - andl %edi,%esi - xorl %eax,%edi - psrldq $4,%xmm0 - xorl %eax,%esi - addl %ecx,%ebx - pxor %xmm2,%xmm6 - rorl $7,%edx - addl %esi,%ebx - pxor %xmm4,%xmm0 - addl 36(%esp),%eax - xorl %edi,%edx - movl %ebx,%esi - roll $5,%ebx - pxor %xmm0,%xmm6 - andl %edx,%ebp - xorl %edi,%edx - movdqa %xmm1,16(%esp) - xorl %edi,%ebp - addl %ebx,%eax - movdqa %xmm6,%xmm2 - movdqa %xmm6,%xmm0 - rorl $7,%ecx - addl %ebp,%eax - addl 40(%esp),%edi - xorl %edx,%ecx - pslldq $12,%xmm2 - paddd %xmm6,%xmm6 - movl %eax,%ebp - roll $5,%eax - andl %ecx,%esi - xorl %edx,%ecx - psrld $31,%xmm0 - xorl %edx,%esi - addl %eax,%edi - movdqa %xmm2,%xmm1 - rorl $7,%ebx - addl %esi,%edi - psrld $30,%xmm2 - por %xmm0,%xmm6 - addl 44(%esp),%edx - xorl %ecx,%ebx - movdqa 64(%esp),%xmm0 - movl %edi,%esi - roll $5,%edi - pslld $2,%xmm1 - pxor %xmm2,%xmm6 - andl %ebx,%ebp - xorl %ecx,%ebx - movdqa 112(%esp),%xmm2 - xorl %ecx,%ebp - addl %edi,%edx - pxor %xmm1,%xmm6 - movdqa %xmm4,%xmm7 - rorl $7,%eax - addl %ebp,%edx - addl 48(%esp),%ecx - xorl %ebx,%eax -.byte 102,15,58,15,251,8 - movdqa %xmm6,%xmm1 - movl %edx,%ebp - roll $5,%edx - paddd %xmm6,%xmm2 - movdqa %xmm3,64(%esp) - andl %eax,%esi - xorl %ebx,%eax - psrldq $4,%xmm1 - xorl %ebx,%esi - addl %edx,%ecx - pxor %xmm3,%xmm7 - rorl $7,%edi - addl %esi,%ecx - pxor %xmm5,%xmm1 - addl 52(%esp),%ebx - xorl %eax,%edi - movl %ecx,%esi - roll $5,%ecx - pxor %xmm1,%xmm7 - andl %edi,%ebp - xorl %eax,%edi - movdqa %xmm2,32(%esp) - xorl %eax,%ebp - addl %ecx,%ebx - movdqa %xmm7,%xmm3 - movdqa %xmm7,%xmm1 - rorl $7,%edx - addl %ebp,%ebx - addl 56(%esp),%eax - xorl %edi,%edx - pslldq $12,%xmm3 - paddd %xmm7,%xmm7 - movl %ebx,%ebp - roll $5,%ebx - andl %edx,%esi - xorl %edi,%edx - psrld $31,%xmm1 - xorl %edi,%esi - addl %ebx,%eax - movdqa %xmm3,%xmm2 - rorl $7,%ecx - addl %esi,%eax - psrld $30,%xmm3 - por %xmm1,%xmm7 - addl 60(%esp),%edi - xorl %edx,%ecx - movdqa 80(%esp),%xmm1 - movl %eax,%esi - roll $5,%eax - pslld $2,%xmm2 - pxor %xmm3,%xmm7 - andl %ecx,%ebp - xorl %edx,%ecx - movdqa 112(%esp),%xmm3 - xorl %edx,%ebp - addl %eax,%edi - pxor %xmm2,%xmm7 - rorl $7,%ebx - addl %ebp,%edi - movdqa %xmm7,%xmm2 - addl (%esp),%edx - pxor %xmm4,%xmm0 -.byte 102,15,58,15,214,8 - xorl %ecx,%ebx - movl %edi,%ebp - roll $5,%edi - pxor %xmm1,%xmm0 - movdqa %xmm4,80(%esp) - andl %ebx,%esi - xorl %ecx,%ebx - movdqa %xmm3,%xmm4 - paddd %xmm7,%xmm3 - xorl %ecx,%esi - addl %edi,%edx - pxor %xmm2,%xmm0 - rorl $7,%eax - addl %esi,%edx - addl 4(%esp),%ecx - xorl %ebx,%eax - movdqa %xmm0,%xmm2 - movdqa %xmm3,48(%esp) - movl %edx,%esi - roll $5,%edx - andl %eax,%ebp - xorl %ebx,%eax - pslld $2,%xmm0 - xorl %ebx,%ebp - addl %edx,%ecx - psrld $30,%xmm2 - rorl $7,%edi - addl %ebp,%ecx - addl 8(%esp),%ebx - xorl %eax,%edi - movl %ecx,%ebp - roll $5,%ecx - por %xmm2,%xmm0 - andl %edi,%esi - xorl %eax,%edi - movdqa 96(%esp),%xmm2 - xorl %eax,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 12(%esp),%eax - movdqa %xmm0,%xmm3 - xorl %edi,%edx - movl %ebx,%esi - roll $5,%ebx - andl %edx,%ebp - xorl %edi,%edx - xorl %edi,%ebp - addl %ebx,%eax - rorl $7,%ecx - addl %ebp,%eax - addl 16(%esp),%edi - pxor %xmm5,%xmm1 -.byte 102,15,58,15,223,8 - xorl %edx,%esi - movl %eax,%ebp - roll $5,%eax - pxor %xmm2,%xmm1 - movdqa %xmm5,96(%esp) - xorl %ecx,%esi - addl %eax,%edi - movdqa %xmm4,%xmm5 - paddd %xmm0,%xmm4 - rorl $7,%ebx - addl %esi,%edi - pxor %xmm3,%xmm1 - addl 20(%esp),%edx - xorl %ecx,%ebp - movl %edi,%esi - roll $5,%edi - movdqa %xmm1,%xmm3 - movdqa %xmm4,(%esp) - xorl %ebx,%ebp - addl %edi,%edx - rorl $7,%eax - addl %ebp,%edx - pslld $2,%xmm1 - addl 24(%esp),%ecx - xorl %ebx,%esi - psrld $30,%xmm3 - movl %edx,%ebp - roll $5,%edx - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%edi - addl %esi,%ecx - por %xmm3,%xmm1 - addl 28(%esp),%ebx - xorl %eax,%ebp - movdqa 64(%esp),%xmm3 - movl %ecx,%esi - roll $5,%ecx - xorl %edi,%ebp - addl %ecx,%ebx - rorl $7,%edx - movdqa %xmm1,%xmm4 - addl %ebp,%ebx - addl 32(%esp),%eax - pxor %xmm6,%xmm2 -.byte 102,15,58,15,224,8 - xorl %edi,%esi - movl %ebx,%ebp - roll $5,%ebx - pxor %xmm3,%xmm2 - movdqa %xmm6,64(%esp) - xorl %edx,%esi - addl %ebx,%eax - movdqa 128(%esp),%xmm6 - paddd %xmm1,%xmm5 - rorl $7,%ecx - addl %esi,%eax - pxor %xmm4,%xmm2 - addl 36(%esp),%edi - xorl %edx,%ebp - movl %eax,%esi - roll $5,%eax - movdqa %xmm2,%xmm4 - movdqa %xmm5,16(%esp) - xorl %ecx,%ebp - addl %eax,%edi - rorl $7,%ebx - addl %ebp,%edi - pslld $2,%xmm2 - addl 40(%esp),%edx - xorl %ecx,%esi - psrld $30,%xmm4 - movl %edi,%ebp - roll $5,%edi - xorl %ebx,%esi - addl %edi,%edx - rorl $7,%eax - addl %esi,%edx - por %xmm4,%xmm2 - addl 44(%esp),%ecx - xorl %ebx,%ebp - movdqa 80(%esp),%xmm4 - movl %edx,%esi - roll $5,%edx - xorl %eax,%ebp - addl %edx,%ecx - rorl $7,%edi - movdqa %xmm2,%xmm5 - addl %ebp,%ecx - addl 48(%esp),%ebx - pxor %xmm7,%xmm3 -.byte 102,15,58,15,233,8 - xorl %eax,%esi - movl %ecx,%ebp - roll $5,%ecx - pxor %xmm4,%xmm3 - movdqa %xmm7,80(%esp) - xorl %edi,%esi - addl %ecx,%ebx - movdqa %xmm6,%xmm7 - paddd %xmm2,%xmm6 - rorl $7,%edx - addl %esi,%ebx - pxor %xmm5,%xmm3 - addl 52(%esp),%eax - xorl %edi,%ebp - movl %ebx,%esi - roll $5,%ebx - movdqa %xmm3,%xmm5 - movdqa %xmm6,32(%esp) - xorl %edx,%ebp - addl %ebx,%eax - rorl $7,%ecx - addl %ebp,%eax - pslld $2,%xmm3 - addl 56(%esp),%edi - xorl %edx,%esi - psrld $30,%xmm5 - movl %eax,%ebp - roll $5,%eax - xorl %ecx,%esi - addl %eax,%edi - rorl $7,%ebx - addl %esi,%edi - por %xmm5,%xmm3 - addl 60(%esp),%edx - xorl %ecx,%ebp - movdqa 96(%esp),%xmm5 - movl %edi,%esi - roll $5,%edi - xorl %ebx,%ebp - addl %edi,%edx - rorl $7,%eax - movdqa %xmm3,%xmm6 - addl %ebp,%edx - addl (%esp),%ecx - pxor %xmm0,%xmm4 -.byte 102,15,58,15,242,8 - xorl %ebx,%esi - movl %edx,%ebp - roll $5,%edx - pxor %xmm5,%xmm4 - movdqa %xmm0,96(%esp) - xorl %eax,%esi - addl %edx,%ecx - movdqa %xmm7,%xmm0 - paddd %xmm3,%xmm7 - rorl $7,%edi - addl %esi,%ecx - pxor %xmm6,%xmm4 - addl 4(%esp),%ebx - xorl %eax,%ebp - movl %ecx,%esi - roll $5,%ecx - movdqa %xmm4,%xmm6 - movdqa %xmm7,48(%esp) - xorl %edi,%ebp - addl %ecx,%ebx - rorl $7,%edx - addl %ebp,%ebx - pslld $2,%xmm4 - addl 8(%esp),%eax - xorl %edi,%esi - psrld $30,%xmm6 - movl %ebx,%ebp - roll $5,%ebx - xorl %edx,%esi - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - por %xmm6,%xmm4 - addl 12(%esp),%edi - xorl %edx,%ebp - movdqa 64(%esp),%xmm6 - movl %eax,%esi - roll $5,%eax - xorl %ecx,%ebp - addl %eax,%edi - rorl $7,%ebx - movdqa %xmm4,%xmm7 - addl %ebp,%edi - addl 16(%esp),%edx - pxor %xmm1,%xmm5 -.byte 102,15,58,15,251,8 - xorl %ecx,%esi - movl %edi,%ebp - roll $5,%edi - pxor %xmm6,%xmm5 - movdqa %xmm1,64(%esp) - xorl %ebx,%esi - addl %edi,%edx - movdqa %xmm0,%xmm1 - paddd %xmm4,%xmm0 - rorl $7,%eax - addl %esi,%edx - pxor %xmm7,%xmm5 - addl 20(%esp),%ecx - xorl %ebx,%ebp - movl %edx,%esi - roll $5,%edx - movdqa %xmm5,%xmm7 - movdqa %xmm0,(%esp) - xorl %eax,%ebp - addl %edx,%ecx - rorl $7,%edi - addl %ebp,%ecx - pslld $2,%xmm5 - addl 24(%esp),%ebx - xorl %eax,%esi - psrld $30,%xmm7 - movl %ecx,%ebp - roll $5,%ecx - xorl %edi,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - por %xmm7,%xmm5 - addl 28(%esp),%eax - xorl %edi,%ebp - movdqa 80(%esp),%xmm7 - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%ebp - addl %ebx,%eax - rorl $7,%ecx - movdqa %xmm5,%xmm0 - addl %ebp,%eax - movl %ecx,%ebp - pxor %xmm2,%xmm6 -.byte 102,15,58,15,196,8 - xorl %edx,%ecx - addl 32(%esp),%edi - andl %edx,%ebp - pxor %xmm7,%xmm6 - movdqa %xmm2,80(%esp) - andl %ecx,%esi - rorl $7,%ebx - movdqa %xmm1,%xmm2 - paddd %xmm5,%xmm1 - addl %ebp,%edi - movl %eax,%ebp - pxor %xmm0,%xmm6 - roll $5,%eax - addl %esi,%edi - xorl %edx,%ecx - addl %eax,%edi - movdqa %xmm6,%xmm0 - movdqa %xmm1,16(%esp) - movl %ebx,%esi - xorl %ecx,%ebx - addl 36(%esp),%edx - andl %ecx,%esi - pslld $2,%xmm6 - andl %ebx,%ebp - rorl $7,%eax - psrld $30,%xmm0 - addl %esi,%edx - movl %edi,%esi - roll $5,%edi - addl %ebp,%edx - xorl %ecx,%ebx - addl %edi,%edx - por %xmm0,%xmm6 - movl %eax,%ebp - xorl %ebx,%eax - movdqa 96(%esp),%xmm0 - addl 40(%esp),%ecx - andl %ebx,%ebp - andl %eax,%esi - rorl $7,%edi - addl %ebp,%ecx - movdqa %xmm6,%xmm1 - movl %edx,%ebp - roll $5,%edx - addl %esi,%ecx - xorl %ebx,%eax - addl %edx,%ecx - movl %edi,%esi - xorl %eax,%edi - addl 44(%esp),%ebx - andl %eax,%esi - andl %edi,%ebp - rorl $7,%edx - addl %esi,%ebx - movl %ecx,%esi - roll $5,%ecx - addl %ebp,%ebx - xorl %eax,%edi - addl %ecx,%ebx - movl %edx,%ebp - pxor %xmm3,%xmm7 -.byte 102,15,58,15,205,8 - xorl %edi,%edx - addl 48(%esp),%eax - andl %edi,%ebp - pxor %xmm0,%xmm7 - movdqa %xmm3,96(%esp) - andl %edx,%esi - rorl $7,%ecx - movdqa 144(%esp),%xmm3 - paddd %xmm6,%xmm2 - addl %ebp,%eax - movl %ebx,%ebp - pxor %xmm1,%xmm7 - roll $5,%ebx - addl %esi,%eax - xorl %edi,%edx - addl %ebx,%eax - movdqa %xmm7,%xmm1 - movdqa %xmm2,32(%esp) - movl %ecx,%esi - xorl %edx,%ecx - addl 52(%esp),%edi - andl %edx,%esi - pslld $2,%xmm7 - andl %ecx,%ebp - rorl $7,%ebx - psrld $30,%xmm1 - addl %esi,%edi - movl %eax,%esi - roll $5,%eax - addl %ebp,%edi - xorl %edx,%ecx - addl %eax,%edi - por %xmm1,%xmm7 - movl %ebx,%ebp - xorl %ecx,%ebx - movdqa 64(%esp),%xmm1 - addl 56(%esp),%edx - andl %ecx,%ebp - andl %ebx,%esi - rorl $7,%eax - addl %ebp,%edx - movdqa %xmm7,%xmm2 - movl %edi,%ebp - roll $5,%edi - addl %esi,%edx - xorl %ecx,%ebx - addl %edi,%edx - movl %eax,%esi - xorl %ebx,%eax - addl 60(%esp),%ecx - andl %ebx,%esi - andl %eax,%ebp - rorl $7,%edi - addl %esi,%ecx - movl %edx,%esi - roll $5,%edx - addl %ebp,%ecx - xorl %ebx,%eax - addl %edx,%ecx - movl %edi,%ebp - pxor %xmm4,%xmm0 -.byte 102,15,58,15,214,8 - xorl %eax,%edi - addl (%esp),%ebx - andl %eax,%ebp - pxor %xmm1,%xmm0 - movdqa %xmm4,64(%esp) - andl %edi,%esi - rorl $7,%edx - movdqa %xmm3,%xmm4 - paddd %xmm7,%xmm3 - addl %ebp,%ebx - movl %ecx,%ebp - pxor %xmm2,%xmm0 - roll $5,%ecx - addl %esi,%ebx - xorl %eax,%edi - addl %ecx,%ebx - movdqa %xmm0,%xmm2 - movdqa %xmm3,48(%esp) - movl %edx,%esi - xorl %edi,%edx - addl 4(%esp),%eax - andl %edi,%esi - pslld $2,%xmm0 - andl %edx,%ebp - rorl $7,%ecx - psrld $30,%xmm2 - addl %esi,%eax - movl %ebx,%esi - roll $5,%ebx - addl %ebp,%eax - xorl %edi,%edx - addl %ebx,%eax - por %xmm2,%xmm0 - movl %ecx,%ebp - xorl %edx,%ecx - movdqa 80(%esp),%xmm2 - addl 8(%esp),%edi - andl %edx,%ebp - andl %ecx,%esi - rorl $7,%ebx - addl %ebp,%edi - movdqa %xmm0,%xmm3 - movl %eax,%ebp - roll $5,%eax - addl %esi,%edi - xorl %edx,%ecx - addl %eax,%edi - movl %ebx,%esi - xorl %ecx,%ebx - addl 12(%esp),%edx - andl %ecx,%esi - andl %ebx,%ebp - rorl $7,%eax - addl %esi,%edx - movl %edi,%esi - roll $5,%edi - addl %ebp,%edx - xorl %ecx,%ebx - addl %edi,%edx - movl %eax,%ebp - pxor %xmm5,%xmm1 -.byte 102,15,58,15,223,8 - xorl %ebx,%eax - addl 16(%esp),%ecx - andl %ebx,%ebp - pxor %xmm2,%xmm1 - movdqa %xmm5,80(%esp) - andl %eax,%esi - rorl $7,%edi - movdqa %xmm4,%xmm5 - paddd %xmm0,%xmm4 - addl %ebp,%ecx - movl %edx,%ebp - pxor %xmm3,%xmm1 - roll $5,%edx - addl %esi,%ecx - xorl %ebx,%eax - addl %edx,%ecx - movdqa %xmm1,%xmm3 - movdqa %xmm4,(%esp) - movl %edi,%esi - xorl %eax,%edi - addl 20(%esp),%ebx - andl %eax,%esi - pslld $2,%xmm1 - andl %edi,%ebp - rorl $7,%edx - psrld $30,%xmm3 - addl %esi,%ebx - movl %ecx,%esi - roll $5,%ecx - addl %ebp,%ebx - xorl %eax,%edi - addl %ecx,%ebx - por %xmm3,%xmm1 - movl %edx,%ebp - xorl %edi,%edx - movdqa 96(%esp),%xmm3 - addl 24(%esp),%eax - andl %edi,%ebp - andl %edx,%esi - rorl $7,%ecx - addl %ebp,%eax - movdqa %xmm1,%xmm4 - movl %ebx,%ebp - roll $5,%ebx - addl %esi,%eax - xorl %edi,%edx - addl %ebx,%eax - movl %ecx,%esi - xorl %edx,%ecx - addl 28(%esp),%edi - andl %edx,%esi - andl %ecx,%ebp - rorl $7,%ebx - addl %esi,%edi - movl %eax,%esi - roll $5,%eax - addl %ebp,%edi - xorl %edx,%ecx - addl %eax,%edi - movl %ebx,%ebp - pxor %xmm6,%xmm2 -.byte 102,15,58,15,224,8 - xorl %ecx,%ebx - addl 32(%esp),%edx - andl %ecx,%ebp - pxor %xmm3,%xmm2 - movdqa %xmm6,96(%esp) - andl %ebx,%esi - rorl $7,%eax - movdqa %xmm5,%xmm6 - paddd %xmm1,%xmm5 - addl %ebp,%edx - movl %edi,%ebp - pxor %xmm4,%xmm2 - roll $5,%edi - addl %esi,%edx - xorl %ecx,%ebx - addl %edi,%edx - movdqa %xmm2,%xmm4 - movdqa %xmm5,16(%esp) - movl %eax,%esi - xorl %ebx,%eax - addl 36(%esp),%ecx - andl %ebx,%esi - pslld $2,%xmm2 - andl %eax,%ebp - rorl $7,%edi - psrld $30,%xmm4 - addl %esi,%ecx - movl %edx,%esi - roll $5,%edx - addl %ebp,%ecx - xorl %ebx,%eax - addl %edx,%ecx - por %xmm4,%xmm2 - movl %edi,%ebp - xorl %eax,%edi - movdqa 64(%esp),%xmm4 - addl 40(%esp),%ebx - andl %eax,%ebp - andl %edi,%esi - rorl $7,%edx - addl %ebp,%ebx - movdqa %xmm2,%xmm5 - movl %ecx,%ebp - roll $5,%ecx - addl %esi,%ebx - xorl %eax,%edi - addl %ecx,%ebx - movl %edx,%esi - xorl %edi,%edx - addl 44(%esp),%eax - andl %edi,%esi - andl %edx,%ebp - rorl $7,%ecx - addl %esi,%eax - movl %ebx,%esi - roll $5,%ebx - addl %ebp,%eax - xorl %edi,%edx - addl %ebx,%eax - addl 48(%esp),%edi - pxor %xmm7,%xmm3 -.byte 102,15,58,15,233,8 - xorl %edx,%esi - movl %eax,%ebp - roll $5,%eax - pxor %xmm4,%xmm3 - movdqa %xmm7,64(%esp) - xorl %ecx,%esi - addl %eax,%edi - movdqa %xmm6,%xmm7 - paddd %xmm2,%xmm6 - rorl $7,%ebx - addl %esi,%edi - pxor %xmm5,%xmm3 - addl 52(%esp),%edx - xorl %ecx,%ebp - movl %edi,%esi - roll $5,%edi - movdqa %xmm3,%xmm5 - movdqa %xmm6,32(%esp) - xorl %ebx,%ebp - addl %edi,%edx - rorl $7,%eax - addl %ebp,%edx - pslld $2,%xmm3 - addl 56(%esp),%ecx - xorl %ebx,%esi - psrld $30,%xmm5 - movl %edx,%ebp - roll $5,%edx - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%edi - addl %esi,%ecx - por %xmm5,%xmm3 - addl 60(%esp),%ebx - xorl %eax,%ebp - movl %ecx,%esi - roll $5,%ecx - xorl %edi,%ebp - addl %ecx,%ebx - rorl $7,%edx - addl %ebp,%ebx - addl (%esp),%eax - paddd %xmm3,%xmm7 - xorl %edi,%esi - movl %ebx,%ebp - roll $5,%ebx - xorl %edx,%esi - movdqa %xmm7,48(%esp) - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - addl 4(%esp),%edi - xorl %edx,%ebp - movl %eax,%esi - roll $5,%eax - xorl %ecx,%ebp - addl %eax,%edi - rorl $7,%ebx - addl %ebp,%edi - addl 8(%esp),%edx - xorl %ecx,%esi - movl %edi,%ebp - roll $5,%edi - xorl %ebx,%esi - addl %edi,%edx - rorl $7,%eax - addl %esi,%edx - addl 12(%esp),%ecx - xorl %ebx,%ebp - movl %edx,%esi - roll $5,%edx - xorl %eax,%ebp - addl %edx,%ecx - rorl $7,%edi - addl %ebp,%ecx - movl 196(%esp),%ebp - cmpl 200(%esp),%ebp - je .L005done - movdqa 160(%esp),%xmm7 - movdqa 176(%esp),%xmm6 - movdqu (%ebp),%xmm0 - movdqu 16(%ebp),%xmm1 - movdqu 32(%ebp),%xmm2 - movdqu 48(%ebp),%xmm3 - addl $64,%ebp -.byte 102,15,56,0,198 - movl %ebp,196(%esp) - movdqa %xmm7,96(%esp) - addl 16(%esp),%ebx - xorl %eax,%esi -.byte 102,15,56,0,206 - movl %ecx,%ebp - roll $5,%ecx - paddd %xmm7,%xmm0 - xorl %edi,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - movdqa %xmm0,(%esp) - addl 20(%esp),%eax - xorl %edi,%ebp - psubd %xmm7,%xmm0 - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%ebp - addl %ebx,%eax - rorl $7,%ecx - addl %ebp,%eax - addl 24(%esp),%edi - xorl %edx,%esi - movl %eax,%ebp - roll $5,%eax - xorl %ecx,%esi - addl %eax,%edi - rorl $7,%ebx - addl %esi,%edi - addl 28(%esp),%edx - xorl %ecx,%ebp - movl %edi,%esi - roll $5,%edi - xorl %ebx,%ebp - addl %edi,%edx - rorl $7,%eax - addl %ebp,%edx - addl 32(%esp),%ecx - xorl %ebx,%esi -.byte 102,15,56,0,214 - movl %edx,%ebp - roll $5,%edx - paddd %xmm7,%xmm1 - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%edi - addl %esi,%ecx - movdqa %xmm1,16(%esp) - addl 36(%esp),%ebx - xorl %eax,%ebp - psubd %xmm7,%xmm1 - movl %ecx,%esi - roll $5,%ecx - xorl %edi,%ebp - addl %ecx,%ebx - rorl $7,%edx - addl %ebp,%ebx - addl 40(%esp),%eax - xorl %edi,%esi - movl %ebx,%ebp - roll $5,%ebx - xorl %edx,%esi - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - addl 44(%esp),%edi - xorl %edx,%ebp - movl %eax,%esi - roll $5,%eax - xorl %ecx,%ebp - addl %eax,%edi - rorl $7,%ebx - addl %ebp,%edi - addl 48(%esp),%edx - xorl %ecx,%esi -.byte 102,15,56,0,222 - movl %edi,%ebp - roll $5,%edi - paddd %xmm7,%xmm2 - xorl %ebx,%esi - addl %edi,%edx - rorl $7,%eax - addl %esi,%edx - movdqa %xmm2,32(%esp) - addl 52(%esp),%ecx - xorl %ebx,%ebp - psubd %xmm7,%xmm2 - movl %edx,%esi - roll $5,%edx - xorl %eax,%ebp - addl %edx,%ecx - rorl $7,%edi - addl %ebp,%ecx - addl 56(%esp),%ebx - xorl %eax,%esi - movl %ecx,%ebp - roll $5,%ecx - xorl %edi,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 60(%esp),%eax - xorl %edi,%ebp - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%ebp - addl %ebx,%eax - rorl $7,%ecx - addl %ebp,%eax - movl 192(%esp),%ebp - addl (%ebp),%eax - addl 4(%ebp),%esi - addl 8(%ebp),%ecx - movl %eax,(%ebp) - addl 12(%ebp),%edx - movl %esi,4(%ebp) - addl 16(%ebp),%edi - movl %ecx,8(%ebp) - movl %esi,%ebx - movl %edx,12(%ebp) - movl %edi,16(%ebp) - movdqa %xmm1,%xmm4 - jmp .L004loop -.align 16 -.L005done: - addl 16(%esp),%ebx - xorl %eax,%esi - movl %ecx,%ebp - roll $5,%ecx - xorl %edi,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 20(%esp),%eax - xorl %edi,%ebp - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%ebp - addl %ebx,%eax - rorl $7,%ecx - addl %ebp,%eax - addl 24(%esp),%edi - xorl %edx,%esi - movl %eax,%ebp - roll $5,%eax - xorl %ecx,%esi - addl %eax,%edi - rorl $7,%ebx - addl %esi,%edi - addl 28(%esp),%edx - xorl %ecx,%ebp - movl %edi,%esi - roll $5,%edi - xorl %ebx,%ebp - addl %edi,%edx - rorl $7,%eax - addl %ebp,%edx - addl 32(%esp),%ecx - xorl %ebx,%esi - movl %edx,%ebp - roll $5,%edx - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%edi - addl %esi,%ecx - addl 36(%esp),%ebx - xorl %eax,%ebp - movl %ecx,%esi - roll $5,%ecx - xorl %edi,%ebp - addl %ecx,%ebx - rorl $7,%edx - addl %ebp,%ebx - addl 40(%esp),%eax - xorl %edi,%esi - movl %ebx,%ebp - roll $5,%ebx - xorl %edx,%esi - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - addl 44(%esp),%edi - xorl %edx,%ebp - movl %eax,%esi - roll $5,%eax - xorl %ecx,%ebp - addl %eax,%edi - rorl $7,%ebx - addl %ebp,%edi - addl 48(%esp),%edx - xorl %ecx,%esi - movl %edi,%ebp - roll $5,%edi - xorl %ebx,%esi - addl %edi,%edx - rorl $7,%eax - addl %esi,%edx - addl 52(%esp),%ecx - xorl %ebx,%ebp - movl %edx,%esi - roll $5,%edx - xorl %eax,%ebp - addl %edx,%ecx - rorl $7,%edi - addl %ebp,%ecx - addl 56(%esp),%ebx - xorl %eax,%esi - movl %ecx,%ebp - roll $5,%ecx - xorl %edi,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 60(%esp),%eax - xorl %edi,%ebp - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%ebp - addl %ebx,%eax - rorl $7,%ecx - addl %ebp,%eax - movl 192(%esp),%ebp - addl (%ebp),%eax - movl 204(%esp),%esp - addl 4(%ebp),%esi - addl 8(%ebp),%ecx - movl %eax,(%ebp) - addl 12(%ebp),%edx - movl %esi,4(%ebp) - addl 16(%ebp),%edi - movl %ecx,8(%ebp) - movl %edx,12(%ebp) - movl %edi,16(%ebp) - popl %edi - popl %esi - popl %ebx - popl %ebp - ret -.size _sha1_block_data_order_ssse3,.-_sha1_block_data_order_ssse3 -.align 64 -.LK_XX_XX: -.long 1518500249,1518500249,1518500249,1518500249 -.long 1859775393,1859775393,1859775393,1859775393 -.long 2400959708,2400959708,2400959708,2400959708 -.long 3395469782,3395469782,3395469782,3395469782 -.long 66051,67438087,134810123,202182159 -.byte 83,72,65,49,32,98,108,111,99,107,32,116,114,97,110,115 -.byte 102,111,114,109,32,102,111,114,32,120,56,54,44,32,67,82 -.byte 89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112 -.byte 114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0 -.comm OPENSSL_ia32cap_P,8,4 diff --git a/app/openssl/crypto/sha/asm/sha1-586.pl b/app/openssl/crypto/sha/asm/sha1-586.pl deleted file mode 100644 index 2b119ffa..00000000 --- a/app/openssl/crypto/sha/asm/sha1-586.pl +++ /dev/null @@ -1,1229 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# [Re]written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# "[Re]written" was achieved in two major overhauls. In 2004 BODY_* -# functions were re-implemented to address P4 performance issue [see -# commentary below], and in 2006 the rest was rewritten in order to -# gain freedom to liberate licensing terms. - -# January, September 2004. -# -# It was noted that Intel IA-32 C compiler generates code which -# performs ~30% *faster* on P4 CPU than original *hand-coded* -# SHA1 assembler implementation. To address this problem (and -# prove that humans are still better than machines:-), the -# original code was overhauled, which resulted in following -# performance changes: -# -# compared with original compared with Intel cc -# assembler impl. generated code -# Pentium -16% +48% -# PIII/AMD +8% +16% -# P4 +85%(!) +45% -# -# As you can see Pentium came out as looser:-( Yet I reckoned that -# improvement on P4 outweights the loss and incorporate this -# re-tuned code to 0.9.7 and later. -# ---------------------------------------------------------------- -# <appro@fy.chalmers.se> - -# August 2009. -# -# George Spelvin has tipped that F_40_59(b,c,d) can be rewritten as -# '(c&d) + (b&(c^d))', which allows to accumulate partial results -# and lighten "pressure" on scratch registers. This resulted in -# >12% performance improvement on contemporary AMD cores (with no -# degradation on other CPUs:-). Also, the code was revised to maximize -# "distance" between instructions producing input to 'lea' instruction -# and the 'lea' instruction itself, which is essential for Intel Atom -# core and resulted in ~15% improvement. - -# October 2010. -# -# Add SSSE3, Supplemental[!] SSE3, implementation. The idea behind it -# is to offload message schedule denoted by Wt in NIST specification, -# or Xupdate in OpenSSL source, to SIMD unit. The idea is not novel, -# and in SSE2 context was first explored by Dean Gaudet in 2004, see -# http://arctic.org/~dean/crypto/sha1.html. Since then several things -# have changed that made it interesting again: -# -# a) XMM units became faster and wider; -# b) instruction set became more versatile; -# c) an important observation was made by Max Locktykhin, which made -# it possible to reduce amount of instructions required to perform -# the operation in question, for further details see -# http://software.intel.com/en-us/articles/improving-the-performance-of-the-secure-hash-algorithm-1/. - -# April 2011. -# -# Add AVX code path, probably most controversial... The thing is that -# switch to AVX alone improves performance by as little as 4% in -# comparison to SSSE3 code path. But below result doesn't look like -# 4% improvement... Trouble is that Sandy Bridge decodes 'ro[rl]' as -# pair of µ-ops, and it's the additional µ-ops, two per round, that -# make it run slower than Core2 and Westmere. But 'sh[rl]d' is decoded -# as single µ-op by Sandy Bridge and it's replacing 'ro[rl]' with -# equivalent 'sh[rl]d' that is responsible for the impressive 5.1 -# cycles per processed byte. But 'sh[rl]d' is not something that used -# to be fast, nor does it appear to be fast in upcoming Bulldozer -# [according to its optimization manual]. Which is why AVX code path -# is guarded by *both* AVX and synthetic bit denoting Intel CPUs. -# One can argue that it's unfair to AMD, but without 'sh[rl]d' it -# makes no sense to keep the AVX code path. If somebody feels that -# strongly, it's probably more appropriate to discuss possibility of -# using vector rotate XOP on AMD... - -###################################################################### -# Current performance is summarized in following table. Numbers are -# CPU clock cycles spent to process single byte (less is better). -# -# x86 SSSE3 AVX -# Pentium 15.7 - -# PIII 11.5 - -# P4 10.6 - -# AMD K8 7.1 - -# Core2 7.3 6.1/+20% - -# Atom 12.5 9.5(*)/+32% - -# Westmere 7.3 5.6/+30% - -# Sandy Bridge 8.8 6.2/+40% 5.1(**)/+70% -# -# (*) Loop is 1056 instructions long and expected result is ~8.25. -# It remains mystery [to me] why ILP is limited to 1.7. -# -# (**) As per above comment, the result is for AVX *plus* sh[rl]d. - -$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; -push(@INC,"${dir}","${dir}../../perlasm"); -require "x86asm.pl"; - -&asm_init($ARGV[0],"sha1-586.pl",$ARGV[$#ARGV] eq "386"); - -$xmm=$ymm=0; -for (@ARGV) { $xmm=1 if (/-DOPENSSL_IA32_SSE2/); } - -$ymm=1 if ($xmm && - `$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1` - =~ /GNU assembler version ([2-9]\.[0-9]+)/ && - $1>=2.19); # first version supporting AVX - -$ymm=1 if ($xmm && !$ymm && $ARGV[0] eq "win32n" && - `nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)/ && - $1>=2.03); # first version supporting AVX - -&external_label("OPENSSL_ia32cap_P") if ($xmm); - - -$A="eax"; -$B="ebx"; -$C="ecx"; -$D="edx"; -$E="edi"; -$T="esi"; -$tmp1="ebp"; - -@V=($A,$B,$C,$D,$E,$T); - -$alt=0; # 1 denotes alternative IALU implementation, which performs - # 8% *worse* on P4, same on Westmere and Atom, 2% better on - # Sandy Bridge... - -sub BODY_00_15 - { - local($n,$a,$b,$c,$d,$e,$f)=@_; - - &comment("00_15 $n"); - - &mov($f,$c); # f to hold F_00_19(b,c,d) - if ($n==0) { &mov($tmp1,$a); } - else { &mov($a,$tmp1); } - &rotl($tmp1,5); # tmp1=ROTATE(a,5) - &xor($f,$d); - &add($tmp1,$e); # tmp1+=e; - &mov($e,&swtmp($n%16)); # e becomes volatile and is loaded - # with xi, also note that e becomes - # f in next round... - &and($f,$b); - &rotr($b,2); # b=ROTATE(b,30) - &xor($f,$d); # f holds F_00_19(b,c,d) - &lea($tmp1,&DWP(0x5a827999,$tmp1,$e)); # tmp1+=K_00_19+xi - - if ($n==15) { &mov($e,&swtmp(($n+1)%16));# pre-fetch f for next round - &add($f,$tmp1); } # f+=tmp1 - else { &add($tmp1,$f); } # f becomes a in next round - &mov($tmp1,$a) if ($alt && $n==15); - } - -sub BODY_16_19 - { - local($n,$a,$b,$c,$d,$e,$f)=@_; - - &comment("16_19 $n"); - -if ($alt) { - &xor($c,$d); - &xor($f,&swtmp(($n+2)%16)); # f to hold Xupdate(xi,xa,xb,xc,xd) - &and($tmp1,$c); # tmp1 to hold F_00_19(b,c,d), b&=c^d - &xor($f,&swtmp(($n+8)%16)); - &xor($tmp1,$d); # tmp1=F_00_19(b,c,d) - &xor($f,&swtmp(($n+13)%16)); # f holds xa^xb^xc^xd - &rotl($f,1); # f=ROTATE(f,1) - &add($e,$tmp1); # e+=F_00_19(b,c,d) - &xor($c,$d); # restore $c - &mov($tmp1,$a); # b in next round - &rotr($b,$n==16?2:7); # b=ROTATE(b,30) - &mov(&swtmp($n%16),$f); # xi=f - &rotl($a,5); # ROTATE(a,5) - &lea($f,&DWP(0x5a827999,$f,$e));# f+=F_00_19(b,c,d)+e - &mov($e,&swtmp(($n+1)%16)); # pre-fetch f for next round - &add($f,$a); # f+=ROTATE(a,5) -} else { - &mov($tmp1,$c); # tmp1 to hold F_00_19(b,c,d) - &xor($f,&swtmp(($n+2)%16)); # f to hold Xupdate(xi,xa,xb,xc,xd) - &xor($tmp1,$d); - &xor($f,&swtmp(($n+8)%16)); - &and($tmp1,$b); - &xor($f,&swtmp(($n+13)%16)); # f holds xa^xb^xc^xd - &rotl($f,1); # f=ROTATE(f,1) - &xor($tmp1,$d); # tmp1=F_00_19(b,c,d) - &add($e,$tmp1); # e+=F_00_19(b,c,d) - &mov($tmp1,$a); - &rotr($b,2); # b=ROTATE(b,30) - &mov(&swtmp($n%16),$f); # xi=f - &rotl($tmp1,5); # ROTATE(a,5) - &lea($f,&DWP(0x5a827999,$f,$e));# f+=F_00_19(b,c,d)+e - &mov($e,&swtmp(($n+1)%16)); # pre-fetch f for next round - &add($f,$tmp1); # f+=ROTATE(a,5) -} - } - -sub BODY_20_39 - { - local($n,$a,$b,$c,$d,$e,$f)=@_; - local $K=($n<40)?0x6ed9eba1:0xca62c1d6; - - &comment("20_39 $n"); - -if ($alt) { - &xor($tmp1,$c); # tmp1 to hold F_20_39(b,c,d), b^=c - &xor($f,&swtmp(($n+2)%16)); # f to hold Xupdate(xi,xa,xb,xc,xd) - &xor($tmp1,$d); # tmp1 holds F_20_39(b,c,d) - &xor($f,&swtmp(($n+8)%16)); - &add($e,$tmp1); # e+=F_20_39(b,c,d) - &xor($f,&swtmp(($n+13)%16)); # f holds xa^xb^xc^xd - &rotl($f,1); # f=ROTATE(f,1) - &mov($tmp1,$a); # b in next round - &rotr($b,7); # b=ROTATE(b,30) - &mov(&swtmp($n%16),$f) if($n<77);# xi=f - &rotl($a,5); # ROTATE(a,5) - &xor($b,$c) if($n==39);# warm up for BODY_40_59 - &and($tmp1,$b) if($n==39); - &lea($f,&DWP($K,$f,$e)); # f+=e+K_XX_YY - &mov($e,&swtmp(($n+1)%16)) if($n<79);# pre-fetch f for next round - &add($f,$a); # f+=ROTATE(a,5) - &rotr($a,5) if ($n==79); -} else { - &mov($tmp1,$b); # tmp1 to hold F_20_39(b,c,d) - &xor($f,&swtmp(($n+2)%16)); # f to hold Xupdate(xi,xa,xb,xc,xd) - &xor($tmp1,$c); - &xor($f,&swtmp(($n+8)%16)); - &xor($tmp1,$d); # tmp1 holds F_20_39(b,c,d) - &xor($f,&swtmp(($n+13)%16)); # f holds xa^xb^xc^xd - &rotl($f,1); # f=ROTATE(f,1) - &add($e,$tmp1); # e+=F_20_39(b,c,d) - &rotr($b,2); # b=ROTATE(b,30) - &mov($tmp1,$a); - &rotl($tmp1,5); # ROTATE(a,5) - &mov(&swtmp($n%16),$f) if($n<77);# xi=f - &lea($f,&DWP($K,$f,$e)); # f+=e+K_XX_YY - &mov($e,&swtmp(($n+1)%16)) if($n<79);# pre-fetch f for next round - &add($f,$tmp1); # f+=ROTATE(a,5) -} - } - -sub BODY_40_59 - { - local($n,$a,$b,$c,$d,$e,$f)=@_; - - &comment("40_59 $n"); - -if ($alt) { - &add($e,$tmp1); # e+=b&(c^d) - &xor($f,&swtmp(($n+2)%16)); # f to hold Xupdate(xi,xa,xb,xc,xd) - &mov($tmp1,$d); - &xor($f,&swtmp(($n+8)%16)); - &xor($c,$d); # restore $c - &xor($f,&swtmp(($n+13)%16)); # f holds xa^xb^xc^xd - &rotl($f,1); # f=ROTATE(f,1) - &and($tmp1,$c); - &rotr($b,7); # b=ROTATE(b,30) - &add($e,$tmp1); # e+=c&d - &mov($tmp1,$a); # b in next round - &mov(&swtmp($n%16),$f); # xi=f - &rotl($a,5); # ROTATE(a,5) - &xor($b,$c) if ($n<59); - &and($tmp1,$b) if ($n<59);# tmp1 to hold F_40_59(b,c,d) - &lea($f,&DWP(0x8f1bbcdc,$f,$e));# f+=K_40_59+e+(b&(c^d)) - &mov($e,&swtmp(($n+1)%16)); # pre-fetch f for next round - &add($f,$a); # f+=ROTATE(a,5) -} else { - &mov($tmp1,$c); # tmp1 to hold F_40_59(b,c,d) - &xor($f,&swtmp(($n+2)%16)); # f to hold Xupdate(xi,xa,xb,xc,xd) - &xor($tmp1,$d); - &xor($f,&swtmp(($n+8)%16)); - &and($tmp1,$b); - &xor($f,&swtmp(($n+13)%16)); # f holds xa^xb^xc^xd - &rotl($f,1); # f=ROTATE(f,1) - &add($tmp1,$e); # b&(c^d)+=e - &rotr($b,2); # b=ROTATE(b,30) - &mov($e,$a); # e becomes volatile - &rotl($e,5); # ROTATE(a,5) - &mov(&swtmp($n%16),$f); # xi=f - &lea($f,&DWP(0x8f1bbcdc,$f,$tmp1));# f+=K_40_59+e+(b&(c^d)) - &mov($tmp1,$c); - &add($f,$e); # f+=ROTATE(a,5) - &and($tmp1,$d); - &mov($e,&swtmp(($n+1)%16)); # pre-fetch f for next round - &add($f,$tmp1); # f+=c&d -} - } - -&function_begin("sha1_block_data_order"); -if ($xmm) { - &static_label("ssse3_shortcut"); - &static_label("avx_shortcut") if ($ymm); - &static_label("K_XX_XX"); - - &call (&label("pic_point")); # make it PIC! - &set_label("pic_point"); - &blindpop($tmp1); - &picmeup($T,"OPENSSL_ia32cap_P",$tmp1,&label("pic_point")); - &lea ($tmp1,&DWP(&label("K_XX_XX")."-".&label("pic_point"),$tmp1)); - - &mov ($A,&DWP(0,$T)); - &mov ($D,&DWP(4,$T)); - &test ($D,1<<9); # check SSSE3 bit - &jz (&label("x86")); - &test ($A,1<<24); # check FXSR bit - &jz (&label("x86")); - if ($ymm) { - &and ($D,1<<28); # mask AVX bit - &and ($A,1<<30); # mask "Intel CPU" bit - &or ($A,$D); - &cmp ($A,1<<28|1<<30); - &je (&label("avx_shortcut")); - } - &jmp (&label("ssse3_shortcut")); - &set_label("x86",16); -} - &mov($tmp1,&wparam(0)); # SHA_CTX *c - &mov($T,&wparam(1)); # const void *input - &mov($A,&wparam(2)); # size_t num - &stack_push(16+3); # allocate X[16] - &shl($A,6); - &add($A,$T); - &mov(&wparam(2),$A); # pointer beyond the end of input - &mov($E,&DWP(16,$tmp1));# pre-load E - &jmp(&label("loop")); - -&set_label("loop",16); - - # copy input chunk to X, but reversing byte order! - for ($i=0; $i<16; $i+=4) - { - &mov($A,&DWP(4*($i+0),$T)); - &mov($B,&DWP(4*($i+1),$T)); - &mov($C,&DWP(4*($i+2),$T)); - &mov($D,&DWP(4*($i+3),$T)); - &bswap($A); - &bswap($B); - &bswap($C); - &bswap($D); - &mov(&swtmp($i+0),$A); - &mov(&swtmp($i+1),$B); - &mov(&swtmp($i+2),$C); - &mov(&swtmp($i+3),$D); - } - &mov(&wparam(1),$T); # redundant in 1st spin - - &mov($A,&DWP(0,$tmp1)); # load SHA_CTX - &mov($B,&DWP(4,$tmp1)); - &mov($C,&DWP(8,$tmp1)); - &mov($D,&DWP(12,$tmp1)); - # E is pre-loaded - - for($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); } - for(;$i<20;$i++) { &BODY_16_19($i,@V); unshift(@V,pop(@V)); } - for(;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } - for(;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } - for(;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } - - (($V[5] eq $D) and ($V[0] eq $E)) or die; # double-check - - &mov($tmp1,&wparam(0)); # re-load SHA_CTX* - &mov($D,&wparam(1)); # D is last "T" and is discarded - - &add($E,&DWP(0,$tmp1)); # E is last "A"... - &add($T,&DWP(4,$tmp1)); - &add($A,&DWP(8,$tmp1)); - &add($B,&DWP(12,$tmp1)); - &add($C,&DWP(16,$tmp1)); - - &mov(&DWP(0,$tmp1),$E); # update SHA_CTX - &add($D,64); # advance input pointer - &mov(&DWP(4,$tmp1),$T); - &cmp($D,&wparam(2)); # have we reached the end yet? - &mov(&DWP(8,$tmp1),$A); - &mov($E,$C); # C is last "E" which needs to be "pre-loaded" - &mov(&DWP(12,$tmp1),$B); - &mov($T,$D); # input pointer - &mov(&DWP(16,$tmp1),$C); - &jb(&label("loop")); - - &stack_pop(16+3); -&function_end("sha1_block_data_order"); - -if ($xmm) { -###################################################################### -# The SSSE3 implementation. -# -# %xmm[0-7] are used as ring @X[] buffer containing quadruples of last -# 32 elements of the message schedule or Xupdate outputs. First 4 -# quadruples are simply byte-swapped input, next 4 are calculated -# according to method originally suggested by Dean Gaudet (modulo -# being implemented in SSSE3). Once 8 quadruples or 32 elements are -# collected, it switches to routine proposed by Max Locktyukhin. -# -# Calculations inevitably require temporary reqisters, and there are -# no %xmm registers left to spare. For this reason part of the ring -# buffer, X[2..4] to be specific, is offloaded to 3 quadriples ring -# buffer on the stack. Keep in mind that X[2] is alias X[-6], X[3] - -# X[-5], and X[4] - X[-4]... -# -# Another notable optimization is aggressive stack frame compression -# aiming to minimize amount of 9-byte instructions... -# -# Yet another notable optimization is "jumping" $B variable. It means -# that there is no register permanently allocated for $B value. This -# allowed to eliminate one instruction from body_20_39... -# -my $Xi=4; # 4xSIMD Xupdate round, start pre-seeded -my @X=map("xmm$_",(4..7,0..3)); # pre-seeded for $Xi=4 -my @V=($A,$B,$C,$D,$E); -my $j=0; # hash round -my @T=($T,$tmp1); -my $inp; - -my $_rol=sub { &rol(@_) }; -my $_ror=sub { &ror(@_) }; - -&function_begin("_sha1_block_data_order_ssse3"); - &call (&label("pic_point")); # make it PIC! - &set_label("pic_point"); - &blindpop($tmp1); - &lea ($tmp1,&DWP(&label("K_XX_XX")."-".&label("pic_point"),$tmp1)); -&set_label("ssse3_shortcut"); - - &movdqa (@X[3],&QWP(0,$tmp1)); # K_00_19 - &movdqa (@X[4],&QWP(16,$tmp1)); # K_20_39 - &movdqa (@X[5],&QWP(32,$tmp1)); # K_40_59 - &movdqa (@X[6],&QWP(48,$tmp1)); # K_60_79 - &movdqa (@X[2],&QWP(64,$tmp1)); # pbswap mask - - &mov ($E,&wparam(0)); # load argument block - &mov ($inp=@T[1],&wparam(1)); - &mov ($D,&wparam(2)); - &mov (@T[0],"esp"); - - # stack frame layout - # - # +0 X[0]+K X[1]+K X[2]+K X[3]+K # XMM->IALU xfer area - # X[4]+K X[5]+K X[6]+K X[7]+K - # X[8]+K X[9]+K X[10]+K X[11]+K - # X[12]+K X[13]+K X[14]+K X[15]+K - # - # +64 X[0] X[1] X[2] X[3] # XMM->XMM backtrace area - # X[4] X[5] X[6] X[7] - # X[8] X[9] X[10] X[11] # even borrowed for K_00_19 - # - # +112 K_20_39 K_20_39 K_20_39 K_20_39 # constants - # K_40_59 K_40_59 K_40_59 K_40_59 - # K_60_79 K_60_79 K_60_79 K_60_79 - # K_00_19 K_00_19 K_00_19 K_00_19 - # pbswap mask - # - # +192 ctx # argument block - # +196 inp - # +200 end - # +204 esp - &sub ("esp",208); - &and ("esp",-64); - - &movdqa (&QWP(112+0,"esp"),@X[4]); # copy constants - &movdqa (&QWP(112+16,"esp"),@X[5]); - &movdqa (&QWP(112+32,"esp"),@X[6]); - &shl ($D,6); # len*64 - &movdqa (&QWP(112+48,"esp"),@X[3]); - &add ($D,$inp); # end of input - &movdqa (&QWP(112+64,"esp"),@X[2]); - &add ($inp,64); - &mov (&DWP(192+0,"esp"),$E); # save argument block - &mov (&DWP(192+4,"esp"),$inp); - &mov (&DWP(192+8,"esp"),$D); - &mov (&DWP(192+12,"esp"),@T[0]); # save original %esp - - &mov ($A,&DWP(0,$E)); # load context - &mov ($B,&DWP(4,$E)); - &mov ($C,&DWP(8,$E)); - &mov ($D,&DWP(12,$E)); - &mov ($E,&DWP(16,$E)); - &mov (@T[0],$B); # magic seed - - &movdqu (@X[-4&7],&QWP(-64,$inp)); # load input to %xmm[0-3] - &movdqu (@X[-3&7],&QWP(-48,$inp)); - &movdqu (@X[-2&7],&QWP(-32,$inp)); - &movdqu (@X[-1&7],&QWP(-16,$inp)); - &pshufb (@X[-4&7],@X[2]); # byte swap - &pshufb (@X[-3&7],@X[2]); - &pshufb (@X[-2&7],@X[2]); - &movdqa (&QWP(112-16,"esp"),@X[3]); # borrow last backtrace slot - &pshufb (@X[-1&7],@X[2]); - &paddd (@X[-4&7],@X[3]); # add K_00_19 - &paddd (@X[-3&7],@X[3]); - &paddd (@X[-2&7],@X[3]); - &movdqa (&QWP(0,"esp"),@X[-4&7]); # X[]+K xfer to IALU - &psubd (@X[-4&7],@X[3]); # restore X[] - &movdqa (&QWP(0+16,"esp"),@X[-3&7]); - &psubd (@X[-3&7],@X[3]); - &movdqa (&QWP(0+32,"esp"),@X[-2&7]); - &psubd (@X[-2&7],@X[3]); - &movdqa (@X[0],@X[-3&7]); - &jmp (&label("loop")); - -###################################################################### -# SSE instruction sequence is first broken to groups of indepentent -# instructions, independent in respect to their inputs and shifter -# (not all architectures have more than one). Then IALU instructions -# are "knitted in" between the SSE groups. Distance is maintained for -# SSE latency of 2 in hope that it fits better upcoming AMD Bulldozer -# [which allegedly also implements SSSE3]... -# -# Temporary registers usage. X[2] is volatile at the entry and at the -# end is restored from backtrace ring buffer. X[3] is expected to -# contain current K_XX_XX constant and is used to caclulate X[-1]+K -# from previous round, it becomes volatile the moment the value is -# saved to stack for transfer to IALU. X[4] becomes volatile whenever -# X[-4] is accumulated and offloaded to backtrace ring buffer, at the -# end it is loaded with next K_XX_XX [which becomes X[3] in next -# round]... -# -sub Xupdate_ssse3_16_31() # recall that $Xi starts wtih 4 -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 40 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - eval(shift(@insns)); - &palignr(@X[0],@X[-4&7],8); # compose "X[-14]" in "X[0]" - &movdqa (@X[2],@X[-1&7]); - eval(shift(@insns)); - eval(shift(@insns)); - - &paddd (@X[3],@X[-1&7]); - &movdqa (&QWP(64+16*(($Xi-4)%3),"esp"),@X[-4&7]);# save X[] to backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); - &psrldq (@X[2],4); # "X[-3]", 3 dwords - eval(shift(@insns)); - eval(shift(@insns)); - &pxor (@X[0],@X[-4&7]); # "X[0]"^="X[-16]" - eval(shift(@insns)); - eval(shift(@insns)); - - &pxor (@X[2],@X[-2&7]); # "X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &pxor (@X[0],@X[2]); # "X[0]"^="X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (&QWP(0+16*(($Xi-1)&3),"esp"),@X[3]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - - &movdqa (@X[4],@X[0]); - &movdqa (@X[2],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &pslldq (@X[4],12); # "X[0]"<<96, extract one dword - &paddd (@X[0],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &psrld (@X[2],31); - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (@X[3],@X[4]); - eval(shift(@insns)); - eval(shift(@insns)); - - &psrld (@X[4],30); - &por (@X[0],@X[2]); # "X[0]"<<<=1 - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (@X[2],&QWP(64+16*(($Xi-6)%3),"esp")) if ($Xi>5); # restore X[] from backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); - - &pslld (@X[3],2); - &pxor (@X[0],@X[4]); - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (@X[4],&QWP(112-16+16*(($Xi)/5),"esp")); # K_XX_XX - eval(shift(@insns)); - eval(shift(@insns)); - - &pxor (@X[0],@X[3]); # "X[0]"^=("X[0]"<<96)<<<2 - &movdqa (@X[1],@X[-2&7]) if ($Xi<7); - eval(shift(@insns)); - eval(shift(@insns)); - - foreach (@insns) { eval; } # remaining instructions [if any] - - $Xi++; push(@X,shift(@X)); # "rotate" X[] -} - -sub Xupdate_ssse3_32_79() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 to 48 instructions - my ($a,$b,$c,$d,$e); - - &movdqa (@X[2],@X[-1&7]) if ($Xi==8); - eval(shift(@insns)); # body_20_39 - &pxor (@X[0],@X[-4&7]); # "X[0]"="X[-32]"^"X[-16]" - &palignr(@X[2],@X[-2&7],8); # compose "X[-6]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &pxor (@X[0],@X[-7&7]); # "X[0]"^="X[-28]" - &movdqa (&QWP(64+16*(($Xi-4)%3),"esp"),@X[-4&7]); # save X[] to backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); - if ($Xi%5) { - &movdqa (@X[4],@X[3]); # "perpetuate" K_XX_XX... - } else { # ... or load next one - &movdqa (@X[4],&QWP(112-16+16*($Xi/5),"esp")); - } - &paddd (@X[3],@X[-1&7]); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &pxor (@X[0],@X[2]); # "X[0]"^="X[-6]" - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &movdqa (@X[2],@X[0]); - &movdqa (&QWP(0+16*(($Xi-1)&3),"esp"),@X[3]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &pslld (@X[0],2); - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - &psrld (@X[2],30); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &por (@X[0],@X[2]); # "X[0]"<<<=2 - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - &movdqa (@X[2],&QWP(64+16*(($Xi-6)%3),"esp")) if($Xi<19); # restore X[] from backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - &movdqa (@X[3],@X[0]) if ($Xi<19); - eval(shift(@insns)); - - foreach (@insns) { eval; } # remaining instructions - - $Xi++; push(@X,shift(@X)); # "rotate" X[] -} - -sub Xuplast_ssse3_80() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - &paddd (@X[3],@X[-1&7]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &movdqa (&QWP(0+16*(($Xi-1)&3),"esp"),@X[3]); # X[]+K xfer IALU - - foreach (@insns) { eval; } # remaining instructions - - &mov ($inp=@T[1],&DWP(192+4,"esp")); - &cmp ($inp,&DWP(192+8,"esp")); - &je (&label("done")); - - &movdqa (@X[3],&QWP(112+48,"esp")); # K_00_19 - &movdqa (@X[2],&QWP(112+64,"esp")); # pbswap mask - &movdqu (@X[-4&7],&QWP(0,$inp)); # load input - &movdqu (@X[-3&7],&QWP(16,$inp)); - &movdqu (@X[-2&7],&QWP(32,$inp)); - &movdqu (@X[-1&7],&QWP(48,$inp)); - &add ($inp,64); - &pshufb (@X[-4&7],@X[2]); # byte swap - &mov (&DWP(192+4,"esp"),$inp); - &movdqa (&QWP(112-16,"esp"),@X[3]); # borrow last backtrace slot - - $Xi=0; -} - -sub Xloop_ssse3() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - eval(shift(@insns)); - &pshufb (@X[($Xi-3)&7],@X[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &paddd (@X[($Xi-4)&7],@X[3]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (&QWP(0+16*$Xi,"esp"),@X[($Xi-4)&7]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - &psubd (@X[($Xi-4)&7],@X[3]); - - foreach (@insns) { eval; } - $Xi++; -} - -sub Xtail_ssse3() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - foreach (@insns) { eval; } -} - -sub body_00_19 () { - ( - '($a,$b,$c,$d,$e)=@V;'. - '&add ($e,&DWP(4*($j&15),"esp"));', # X[]+K xfer - '&xor ($c,$d);', - '&mov (@T[1],$a);', # $b in next round - '&$_rol ($a,5);', - '&and (@T[0],$c);', # ($b&($c^$d)) - '&xor ($c,$d);', # restore $c - '&xor (@T[0],$d);', - '&add ($e,$a);', - '&$_ror ($b,$j?7:2);', # $b>>>2 - '&add ($e,@T[0]);' .'$j++; unshift(@V,pop(@V)); unshift(@T,pop(@T));' - ); -} - -sub body_20_39 () { - ( - '($a,$b,$c,$d,$e)=@V;'. - '&add ($e,&DWP(4*($j++&15),"esp"));', # X[]+K xfer - '&xor (@T[0],$d);', # ($b^$d) - '&mov (@T[1],$a);', # $b in next round - '&$_rol ($a,5);', - '&xor (@T[0],$c);', # ($b^$d^$c) - '&add ($e,$a);', - '&$_ror ($b,7);', # $b>>>2 - '&add ($e,@T[0]);' .'unshift(@V,pop(@V)); unshift(@T,pop(@T));' - ); -} - -sub body_40_59 () { - ( - '($a,$b,$c,$d,$e)=@V;'. - '&mov (@T[1],$c);', - '&xor ($c,$d);', - '&add ($e,&DWP(4*($j++&15),"esp"));', # X[]+K xfer - '&and (@T[1],$d);', - '&and (@T[0],$c);', # ($b&($c^$d)) - '&$_ror ($b,7);', # $b>>>2 - '&add ($e,@T[1]);', - '&mov (@T[1],$a);', # $b in next round - '&$_rol ($a,5);', - '&add ($e,@T[0]);', - '&xor ($c,$d);', # restore $c - '&add ($e,$a);' .'unshift(@V,pop(@V)); unshift(@T,pop(@T));' - ); -} - -&set_label("loop",16); - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_32_79(\&body_00_19); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xuplast_ssse3_80(\&body_20_39); # can jump to "done" - - $saved_j=$j; @saved_V=@V; - - &Xloop_ssse3(\&body_20_39); - &Xloop_ssse3(\&body_20_39); - &Xloop_ssse3(\&body_20_39); - - &mov (@T[1],&DWP(192,"esp")); # update context - &add ($A,&DWP(0,@T[1])); - &add (@T[0],&DWP(4,@T[1])); # $b - &add ($C,&DWP(8,@T[1])); - &mov (&DWP(0,@T[1]),$A); - &add ($D,&DWP(12,@T[1])); - &mov (&DWP(4,@T[1]),@T[0]); - &add ($E,&DWP(16,@T[1])); - &mov (&DWP(8,@T[1]),$C); - &mov ($B,@T[0]); - &mov (&DWP(12,@T[1]),$D); - &mov (&DWP(16,@T[1]),$E); - &movdqa (@X[0],@X[-3&7]); - - &jmp (&label("loop")); - -&set_label("done",16); $j=$saved_j; @V=@saved_V; - - &Xtail_ssse3(\&body_20_39); - &Xtail_ssse3(\&body_20_39); - &Xtail_ssse3(\&body_20_39); - - &mov (@T[1],&DWP(192,"esp")); # update context - &add ($A,&DWP(0,@T[1])); - &mov ("esp",&DWP(192+12,"esp")); # restore %esp - &add (@T[0],&DWP(4,@T[1])); # $b - &add ($C,&DWP(8,@T[1])); - &mov (&DWP(0,@T[1]),$A); - &add ($D,&DWP(12,@T[1])); - &mov (&DWP(4,@T[1]),@T[0]); - &add ($E,&DWP(16,@T[1])); - &mov (&DWP(8,@T[1]),$C); - &mov (&DWP(12,@T[1]),$D); - &mov (&DWP(16,@T[1]),$E); - -&function_end("_sha1_block_data_order_ssse3"); - -if ($ymm) { -my $Xi=4; # 4xSIMD Xupdate round, start pre-seeded -my @X=map("xmm$_",(4..7,0..3)); # pre-seeded for $Xi=4 -my @V=($A,$B,$C,$D,$E); -my $j=0; # hash round -my @T=($T,$tmp1); -my $inp; - -my $_rol=sub { &shld(@_[0],@_) }; -my $_ror=sub { &shrd(@_[0],@_) }; - -&function_begin("_sha1_block_data_order_avx"); - &call (&label("pic_point")); # make it PIC! - &set_label("pic_point"); - &blindpop($tmp1); - &lea ($tmp1,&DWP(&label("K_XX_XX")."-".&label("pic_point"),$tmp1)); -&set_label("avx_shortcut"); - &vzeroall(); - - &vmovdqa(@X[3],&QWP(0,$tmp1)); # K_00_19 - &vmovdqa(@X[4],&QWP(16,$tmp1)); # K_20_39 - &vmovdqa(@X[5],&QWP(32,$tmp1)); # K_40_59 - &vmovdqa(@X[6],&QWP(48,$tmp1)); # K_60_79 - &vmovdqa(@X[2],&QWP(64,$tmp1)); # pbswap mask - - &mov ($E,&wparam(0)); # load argument block - &mov ($inp=@T[1],&wparam(1)); - &mov ($D,&wparam(2)); - &mov (@T[0],"esp"); - - # stack frame layout - # - # +0 X[0]+K X[1]+K X[2]+K X[3]+K # XMM->IALU xfer area - # X[4]+K X[5]+K X[6]+K X[7]+K - # X[8]+K X[9]+K X[10]+K X[11]+K - # X[12]+K X[13]+K X[14]+K X[15]+K - # - # +64 X[0] X[1] X[2] X[3] # XMM->XMM backtrace area - # X[4] X[5] X[6] X[7] - # X[8] X[9] X[10] X[11] # even borrowed for K_00_19 - # - # +112 K_20_39 K_20_39 K_20_39 K_20_39 # constants - # K_40_59 K_40_59 K_40_59 K_40_59 - # K_60_79 K_60_79 K_60_79 K_60_79 - # K_00_19 K_00_19 K_00_19 K_00_19 - # pbswap mask - # - # +192 ctx # argument block - # +196 inp - # +200 end - # +204 esp - &sub ("esp",208); - &and ("esp",-64); - - &vmovdqa(&QWP(112+0,"esp"),@X[4]); # copy constants - &vmovdqa(&QWP(112+16,"esp"),@X[5]); - &vmovdqa(&QWP(112+32,"esp"),@X[6]); - &shl ($D,6); # len*64 - &vmovdqa(&QWP(112+48,"esp"),@X[3]); - &add ($D,$inp); # end of input - &vmovdqa(&QWP(112+64,"esp"),@X[2]); - &add ($inp,64); - &mov (&DWP(192+0,"esp"),$E); # save argument block - &mov (&DWP(192+4,"esp"),$inp); - &mov (&DWP(192+8,"esp"),$D); - &mov (&DWP(192+12,"esp"),@T[0]); # save original %esp - - &mov ($A,&DWP(0,$E)); # load context - &mov ($B,&DWP(4,$E)); - &mov ($C,&DWP(8,$E)); - &mov ($D,&DWP(12,$E)); - &mov ($E,&DWP(16,$E)); - &mov (@T[0],$B); # magic seed - - &vmovdqu(@X[-4&7],&QWP(-64,$inp)); # load input to %xmm[0-3] - &vmovdqu(@X[-3&7],&QWP(-48,$inp)); - &vmovdqu(@X[-2&7],&QWP(-32,$inp)); - &vmovdqu(@X[-1&7],&QWP(-16,$inp)); - &vpshufb(@X[-4&7],@X[-4&7],@X[2]); # byte swap - &vpshufb(@X[-3&7],@X[-3&7],@X[2]); - &vpshufb(@X[-2&7],@X[-2&7],@X[2]); - &vmovdqa(&QWP(112-16,"esp"),@X[3]); # borrow last backtrace slot - &vpshufb(@X[-1&7],@X[-1&7],@X[2]); - &vpaddd (@X[0],@X[-4&7],@X[3]); # add K_00_19 - &vpaddd (@X[1],@X[-3&7],@X[3]); - &vpaddd (@X[2],@X[-2&7],@X[3]); - &vmovdqa(&QWP(0,"esp"),@X[0]); # X[]+K xfer to IALU - &vmovdqa(&QWP(0+16,"esp"),@X[1]); - &vmovdqa(&QWP(0+32,"esp"),@X[2]); - &jmp (&label("loop")); - -sub Xupdate_avx_16_31() # recall that $Xi starts wtih 4 -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 40 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - eval(shift(@insns)); - &vpalignr(@X[0],@X[-3&7],@X[-4&7],8); # compose "X[-14]" in "X[0]" - eval(shift(@insns)); - eval(shift(@insns)); - - &vpaddd (@X[3],@X[3],@X[-1&7]); - &vmovdqa (&QWP(64+16*(($Xi-4)%3),"esp"),@X[-4&7]);# save X[] to backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); - &vpsrldq(@X[2],@X[-1&7],4); # "X[-3]", 3 dwords - eval(shift(@insns)); - eval(shift(@insns)); - &vpxor (@X[0],@X[0],@X[-4&7]); # "X[0]"^="X[-16]" - eval(shift(@insns)); - eval(shift(@insns)); - - &vpxor (@X[2],@X[2],@X[-2&7]); # "X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - &vmovdqa (&QWP(0+16*(($Xi-1)&3),"esp"),@X[3]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - - &vpxor (@X[0],@X[0],@X[2]); # "X[0]"^="X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpsrld (@X[2],@X[0],31); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpslldq(@X[4],@X[0],12); # "X[0]"<<96, extract one dword - &vpaddd (@X[0],@X[0],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpsrld (@X[3],@X[4],30); - &vpor (@X[0],@X[0],@X[2]); # "X[0]"<<<=1 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpslld (@X[4],@X[4],2); - &vmovdqa (@X[2],&QWP(64+16*(($Xi-6)%3),"esp")) if ($Xi>5); # restore X[] from backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); - &vpxor (@X[0],@X[0],@X[3]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpxor (@X[0],@X[0],@X[4]); # "X[0]"^=("X[0]"<<96)<<<2 - eval(shift(@insns)); - eval(shift(@insns)); - &vmovdqa (@X[4],&QWP(112-16+16*(($Xi)/5),"esp")); # K_XX_XX - eval(shift(@insns)); - eval(shift(@insns)); - - foreach (@insns) { eval; } # remaining instructions [if any] - - $Xi++; push(@X,shift(@X)); # "rotate" X[] -} - -sub Xupdate_avx_32_79() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 to 48 instructions - my ($a,$b,$c,$d,$e); - - &vpalignr(@X[2],@X[-1&7],@X[-2&7],8); # compose "X[-6]" - &vpxor (@X[0],@X[0],@X[-4&7]); # "X[0]"="X[-32]"^"X[-16]" - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &vpxor (@X[0],@X[0],@X[-7&7]); # "X[0]"^="X[-28]" - &vmovdqa (&QWP(64+16*(($Xi-4)%3),"esp"),@X[-4&7]); # save X[] to backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); - if ($Xi%5) { - &vmovdqa (@X[4],@X[3]); # "perpetuate" K_XX_XX... - } else { # ... or load next one - &vmovdqa (@X[4],&QWP(112-16+16*($Xi/5),"esp")); - } - &vpaddd (@X[3],@X[3],@X[-1&7]); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &vpxor (@X[0],@X[0],@X[2]); # "X[0]"^="X[-6]" - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &vpsrld (@X[2],@X[0],30); - &vmovdqa (&QWP(0+16*(($Xi-1)&3),"esp"),@X[3]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &vpslld (@X[0],@X[0],2); - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &vpor (@X[0],@X[0],@X[2]); # "X[0]"<<<=2 - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - &vmovdqa (@X[2],&QWP(64+16*(($Xi-6)%3),"esp")) if($Xi<19); # restore X[] from backtrace buffer - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - foreach (@insns) { eval; } # remaining instructions - - $Xi++; push(@X,shift(@X)); # "rotate" X[] -} - -sub Xuplast_avx_80() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - &vpaddd (@X[3],@X[3],@X[-1&7]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vmovdqa (&QWP(0+16*(($Xi-1)&3),"esp"),@X[3]); # X[]+K xfer IALU - - foreach (@insns) { eval; } # remaining instructions - - &mov ($inp=@T[1],&DWP(192+4,"esp")); - &cmp ($inp,&DWP(192+8,"esp")); - &je (&label("done")); - - &vmovdqa(@X[3],&QWP(112+48,"esp")); # K_00_19 - &vmovdqa(@X[2],&QWP(112+64,"esp")); # pbswap mask - &vmovdqu(@X[-4&7],&QWP(0,$inp)); # load input - &vmovdqu(@X[-3&7],&QWP(16,$inp)); - &vmovdqu(@X[-2&7],&QWP(32,$inp)); - &vmovdqu(@X[-1&7],&QWP(48,$inp)); - &add ($inp,64); - &vpshufb(@X[-4&7],@X[-4&7],@X[2]); # byte swap - &mov (&DWP(192+4,"esp"),$inp); - &vmovdqa(&QWP(112-16,"esp"),@X[3]); # borrow last backtrace slot - - $Xi=0; -} - -sub Xloop_avx() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - eval(shift(@insns)); - &vpshufb (@X[($Xi-3)&7],@X[($Xi-3)&7],@X[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &vpaddd (@X[$Xi&7],@X[($Xi-4)&7],@X[3]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vmovdqa (&QWP(0+16*$Xi,"esp"),@X[$Xi&7]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - - foreach (@insns) { eval; } - $Xi++; -} - -sub Xtail_avx() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - foreach (@insns) { eval; } -} - -&set_label("loop",16); - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_32_79(\&body_00_19); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_20_39); - &Xuplast_avx_80(\&body_20_39); # can jump to "done" - - $saved_j=$j; @saved_V=@V; - - &Xloop_avx(\&body_20_39); - &Xloop_avx(\&body_20_39); - &Xloop_avx(\&body_20_39); - - &mov (@T[1],&DWP(192,"esp")); # update context - &add ($A,&DWP(0,@T[1])); - &add (@T[0],&DWP(4,@T[1])); # $b - &add ($C,&DWP(8,@T[1])); - &mov (&DWP(0,@T[1]),$A); - &add ($D,&DWP(12,@T[1])); - &mov (&DWP(4,@T[1]),@T[0]); - &add ($E,&DWP(16,@T[1])); - &mov (&DWP(8,@T[1]),$C); - &mov ($B,@T[0]); - &mov (&DWP(12,@T[1]),$D); - &mov (&DWP(16,@T[1]),$E); - - &jmp (&label("loop")); - -&set_label("done",16); $j=$saved_j; @V=@saved_V; - - &Xtail_avx(\&body_20_39); - &Xtail_avx(\&body_20_39); - &Xtail_avx(\&body_20_39); - - &vzeroall(); - - &mov (@T[1],&DWP(192,"esp")); # update context - &add ($A,&DWP(0,@T[1])); - &mov ("esp",&DWP(192+12,"esp")); # restore %esp - &add (@T[0],&DWP(4,@T[1])); # $b - &add ($C,&DWP(8,@T[1])); - &mov (&DWP(0,@T[1]),$A); - &add ($D,&DWP(12,@T[1])); - &mov (&DWP(4,@T[1]),@T[0]); - &add ($E,&DWP(16,@T[1])); - &mov (&DWP(8,@T[1]),$C); - &mov (&DWP(12,@T[1]),$D); - &mov (&DWP(16,@T[1]),$E); -&function_end("_sha1_block_data_order_avx"); -} -&set_label("K_XX_XX",64); -&data_word(0x5a827999,0x5a827999,0x5a827999,0x5a827999); # K_00_19 -&data_word(0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1); # K_20_39 -&data_word(0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc); # K_40_59 -&data_word(0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6); # K_60_79 -&data_word(0x00010203,0x04050607,0x08090a0b,0x0c0d0e0f); # pbswap mask -} -&asciz("SHA1 block transform for x86, CRYPTOGAMS by <appro\@openssl.org>"); - -&asm_finish(); diff --git a/app/openssl/crypto/sha/asm/sha1-alpha.pl b/app/openssl/crypto/sha/asm/sha1-alpha.pl deleted file mode 100644 index 6c4b9251..00000000 --- a/app/openssl/crypto/sha/asm/sha1-alpha.pl +++ /dev/null @@ -1,322 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA1 block procedure for Alpha. - -# On 21264 performance is 33% better than code generated by vendor -# compiler, and 75% better than GCC [3.4], and in absolute terms is -# 8.7 cycles per processed byte. Implementation features vectorized -# byte swap, but not Xupdate. - -@X=( "\$0", "\$1", "\$2", "\$3", "\$4", "\$5", "\$6", "\$7", - "\$8", "\$9", "\$10", "\$11", "\$12", "\$13", "\$14", "\$15"); -$ctx="a0"; # $16 -$inp="a1"; -$num="a2"; -$A="a3"; -$B="a4"; # 20 -$C="a5"; -$D="t8"; -$E="t9"; @V=($A,$B,$C,$D,$E); -$t0="t10"; # 24 -$t1="t11"; -$t2="ra"; -$t3="t12"; -$K="AT"; # 28 - -sub BODY_00_19 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if ($i==0); - ldq_u @X[0],0+0($inp) - ldq_u @X[1],0+7($inp) -___ -$code.=<<___ if (!($i&1) && $i<14); - ldq_u @X[$i+2],($i+2)*4+0($inp) - ldq_u @X[$i+3],($i+2)*4+7($inp) -___ -$code.=<<___ if (!($i&1) && $i<15); - extql @X[$i],$inp,@X[$i] - extqh @X[$i+1],$inp,@X[$i+1] - - or @X[$i+1],@X[$i],@X[$i] # pair of 32-bit values are fetched - - srl @X[$i],24,$t0 # vectorized byte swap - srl @X[$i],8,$t2 - - sll @X[$i],8,$t3 - sll @X[$i],24,@X[$i] - zapnot $t0,0x11,$t0 - zapnot $t2,0x22,$t2 - - zapnot @X[$i],0x88,@X[$i] - or $t0,$t2,$t0 - zapnot $t3,0x44,$t3 - sll $a,5,$t1 - - or @X[$i],$t0,@X[$i] - addl $K,$e,$e - and $b,$c,$t2 - zapnot $a,0xf,$a - - or @X[$i],$t3,@X[$i] - srl $a,27,$t0 - bic $d,$b,$t3 - sll $b,30,$b - - extll @X[$i],4,@X[$i+1] # extract upper half - or $t2,$t3,$t2 - addl @X[$i],$e,$e - - addl $t1,$e,$e - srl $b,32,$t3 - zapnot @X[$i],0xf,@X[$i] - - addl $t0,$e,$e - addl $t2,$e,$e - or $t3,$b,$b -___ -$code.=<<___ if (($i&1) && $i<15); - sll $a,5,$t1 - addl $K,$e,$e - and $b,$c,$t2 - zapnot $a,0xf,$a - - srl $a,27,$t0 - addl @X[$i%16],$e,$e - bic $d,$b,$t3 - sll $b,30,$b - - or $t2,$t3,$t2 - addl $t1,$e,$e - srl $b,32,$t3 - zapnot @X[$i],0xf,@X[$i] - - addl $t0,$e,$e - addl $t2,$e,$e - or $t3,$b,$b -___ -$code.=<<___ if ($i>=15); # with forward Xupdate - sll $a,5,$t1 - addl $K,$e,$e - and $b,$c,$t2 - xor @X[($j+2)%16],@X[$j%16],@X[$j%16] - - zapnot $a,0xf,$a - addl @X[$i%16],$e,$e - bic $d,$b,$t3 - xor @X[($j+8)%16],@X[$j%16],@X[$j%16] - - srl $a,27,$t0 - addl $t1,$e,$e - or $t2,$t3,$t2 - xor @X[($j+13)%16],@X[$j%16],@X[$j%16] - - sll $b,30,$b - addl $t0,$e,$e - srl @X[$j%16],31,$t1 - - addl $t2,$e,$e - srl $b,32,$t3 - addl @X[$j%16],@X[$j%16],@X[$j%16] - - or $t3,$b,$b - zapnot @X[$i%16],0xf,@X[$i%16] - or $t1,@X[$j%16],@X[$j%16] -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if ($i<79); # with forward Xupdate - sll $a,5,$t1 - addl $K,$e,$e - zapnot $a,0xf,$a - xor @X[($j+2)%16],@X[$j%16],@X[$j%16] - - sll $b,30,$t3 - addl $t1,$e,$e - xor $b,$c,$t2 - xor @X[($j+8)%16],@X[$j%16],@X[$j%16] - - srl $b,2,$b - addl @X[$i%16],$e,$e - xor $d,$t2,$t2 - xor @X[($j+13)%16],@X[$j%16],@X[$j%16] - - srl @X[$j%16],31,$t1 - addl $t2,$e,$e - srl $a,27,$t0 - addl @X[$j%16],@X[$j%16],@X[$j%16] - - or $t3,$b,$b - addl $t0,$e,$e - or $t1,@X[$j%16],@X[$j%16] -___ -$code.=<<___ if ($i<77); - zapnot @X[$i%16],0xf,@X[$i%16] -___ -$code.=<<___ if ($i==79); # with context fetch - sll $a,5,$t1 - addl $K,$e,$e - zapnot $a,0xf,$a - ldl @X[0],0($ctx) - - sll $b,30,$t3 - addl $t1,$e,$e - xor $b,$c,$t2 - ldl @X[1],4($ctx) - - srl $b,2,$b - addl @X[$i%16],$e,$e - xor $d,$t2,$t2 - ldl @X[2],8($ctx) - - srl $a,27,$t0 - addl $t2,$e,$e - ldl @X[3],12($ctx) - - or $t3,$b,$b - addl $t0,$e,$e - ldl @X[4],16($ctx) -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___; # with forward Xupdate - sll $a,5,$t1 - addl $K,$e,$e - zapnot $a,0xf,$a - xor @X[($j+2)%16],@X[$j%16],@X[$j%16] - - srl $a,27,$t0 - and $b,$c,$t2 - and $b,$d,$t3 - xor @X[($j+8)%16],@X[$j%16],@X[$j%16] - - sll $b,30,$b - addl $t1,$e,$e - xor @X[($j+13)%16],@X[$j%16],@X[$j%16] - - srl @X[$j%16],31,$t1 - addl $t0,$e,$e - or $t2,$t3,$t2 - and $c,$d,$t3 - - or $t2,$t3,$t2 - srl $b,32,$t3 - addl @X[$i%16],$e,$e - addl @X[$j%16],@X[$j%16],@X[$j%16] - - or $t3,$b,$b - addl $t2,$e,$e - or $t1,@X[$j%16],@X[$j%16] - zapnot @X[$i%16],0xf,@X[$i%16] -___ -} - -$code=<<___; -#ifdef __linux__ -#include <asm/regdef.h> -#else -#include <asm.h> -#include <regdef.h> -#endif - -.text - -.set noat -.set noreorder -.globl sha1_block_data_order -.align 5 -.ent sha1_block_data_order -sha1_block_data_order: - lda sp,-64(sp) - stq ra,0(sp) - stq s0,8(sp) - stq s1,16(sp) - stq s2,24(sp) - stq s3,32(sp) - stq s4,40(sp) - stq s5,48(sp) - stq fp,56(sp) - .mask 0x0400fe00,-64 - .frame sp,64,ra - .prologue 0 - - ldl $A,0($ctx) - ldl $B,4($ctx) - sll $num,6,$num - ldl $C,8($ctx) - ldl $D,12($ctx) - ldl $E,16($ctx) - addq $inp,$num,$num - -.Lloop: - .set noreorder - ldah $K,23170(zero) - zapnot $B,0xf,$B - lda $K,31129($K) # K_00_19 -___ -for ($i=0;$i<20;$i++) { &BODY_00_19($i,@V); unshift(@V,pop(@V)); } - -$code.=<<___; - ldah $K,28378(zero) - lda $K,-5215($K) # K_20_39 -___ -for (;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } - -$code.=<<___; - ldah $K,-28900(zero) - lda $K,-17188($K) # K_40_59 -___ -for (;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } - -$code.=<<___; - ldah $K,-13725(zero) - lda $K,-15914($K) # K_60_79 -___ -for (;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } - -$code.=<<___; - addl @X[0],$A,$A - addl @X[1],$B,$B - addl @X[2],$C,$C - addl @X[3],$D,$D - addl @X[4],$E,$E - stl $A,0($ctx) - stl $B,4($ctx) - addq $inp,64,$inp - stl $C,8($ctx) - stl $D,12($ctx) - stl $E,16($ctx) - cmpult $inp,$num,$t1 - bne $t1,.Lloop - - .set noreorder - ldq ra,0(sp) - ldq s0,8(sp) - ldq s1,16(sp) - ldq s2,24(sp) - ldq s3,32(sp) - ldq s4,40(sp) - ldq s5,48(sp) - ldq fp,56(sp) - lda sp,64(sp) - ret (ra) -.end sha1_block_data_order -.ascii "SHA1 block transform for Alpha, CRYPTOGAMS by <appro\@openssl.org>" -.align 2 -___ -$output=shift and open STDOUT,">$output"; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-armv4-large.S b/app/openssl/crypto/sha/asm/sha1-armv4-large.S deleted file mode 100644 index a1562883..00000000 --- a/app/openssl/crypto/sha/asm/sha1-armv4-large.S +++ /dev/null @@ -1,1450 +0,0 @@ -#include "arm_arch.h" - -.text -.code 32 - -.global sha1_block_data_order -.type sha1_block_data_order,%function - -.align 5 -sha1_block_data_order: -#if __ARM_ARCH__>=7 - sub r3,pc,#8 @ sha1_block_data_order - ldr r12,.LOPENSSL_armcap - ldr r12,[r3,r12] @ OPENSSL_armcap_P - tst r12,#ARMV8_SHA1 - bne .LARMv8 - tst r12,#ARMV7_NEON - bne .LNEON -#endif - stmdb sp!,{r4-r12,lr} - add r2,r1,r2,lsl#6 @ r2 to point at the end of r1 - ldmia r0,{r3,r4,r5,r6,r7} -.Lloop: - ldr r8,.LK_00_19 - mov r14,sp - sub sp,sp,#15*4 - mov r5,r5,ror#30 - mov r6,r6,ror#30 - mov r7,r7,ror#30 @ [6] -.L_00_15: -#if __ARM_ARCH__<7 - ldrb r10,[r1,#2] - ldrb r9,[r1,#3] - ldrb r11,[r1,#1] - add r7,r8,r7,ror#2 @ E+=K_00_19 - ldrb r12,[r1],#4 - orr r9,r9,r10,lsl#8 - eor r10,r5,r6 @ F_xx_xx - orr r9,r9,r11,lsl#16 - add r7,r7,r3,ror#27 @ E+=ROR(A,27) - orr r9,r9,r12,lsl#24 -#else - ldr r9,[r1],#4 @ handles unaligned - add r7,r8,r7,ror#2 @ E+=K_00_19 - eor r10,r5,r6 @ F_xx_xx - add r7,r7,r3,ror#27 @ E+=ROR(A,27) -#ifdef __ARMEL__ - rev r9,r9 @ byte swap -#endif -#endif - and r10,r4,r10,ror#2 - add r7,r7,r9 @ E+=X[i] - eor r10,r10,r6,ror#2 @ F_00_19(B,C,D) - str r9,[r14,#-4]! - add r7,r7,r10 @ E+=F_00_19(B,C,D) -#if __ARM_ARCH__<7 - ldrb r10,[r1,#2] - ldrb r9,[r1,#3] - ldrb r11,[r1,#1] - add r6,r8,r6,ror#2 @ E+=K_00_19 - ldrb r12,[r1],#4 - orr r9,r9,r10,lsl#8 - eor r10,r4,r5 @ F_xx_xx - orr r9,r9,r11,lsl#16 - add r6,r6,r7,ror#27 @ E+=ROR(A,27) - orr r9,r9,r12,lsl#24 -#else - ldr r9,[r1],#4 @ handles unaligned - add r6,r8,r6,ror#2 @ E+=K_00_19 - eor r10,r4,r5 @ F_xx_xx - add r6,r6,r7,ror#27 @ E+=ROR(A,27) -#ifdef __ARMEL__ - rev r9,r9 @ byte swap -#endif -#endif - and r10,r3,r10,ror#2 - add r6,r6,r9 @ E+=X[i] - eor r10,r10,r5,ror#2 @ F_00_19(B,C,D) - str r9,[r14,#-4]! - add r6,r6,r10 @ E+=F_00_19(B,C,D) -#if __ARM_ARCH__<7 - ldrb r10,[r1,#2] - ldrb r9,[r1,#3] - ldrb r11,[r1,#1] - add r5,r8,r5,ror#2 @ E+=K_00_19 - ldrb r12,[r1],#4 - orr r9,r9,r10,lsl#8 - eor r10,r3,r4 @ F_xx_xx - orr r9,r9,r11,lsl#16 - add r5,r5,r6,ror#27 @ E+=ROR(A,27) - orr r9,r9,r12,lsl#24 -#else - ldr r9,[r1],#4 @ handles unaligned - add r5,r8,r5,ror#2 @ E+=K_00_19 - eor r10,r3,r4 @ F_xx_xx - add r5,r5,r6,ror#27 @ E+=ROR(A,27) -#ifdef __ARMEL__ - rev r9,r9 @ byte swap -#endif -#endif - and r10,r7,r10,ror#2 - add r5,r5,r9 @ E+=X[i] - eor r10,r10,r4,ror#2 @ F_00_19(B,C,D) - str r9,[r14,#-4]! - add r5,r5,r10 @ E+=F_00_19(B,C,D) -#if __ARM_ARCH__<7 - ldrb r10,[r1,#2] - ldrb r9,[r1,#3] - ldrb r11,[r1,#1] - add r4,r8,r4,ror#2 @ E+=K_00_19 - ldrb r12,[r1],#4 - orr r9,r9,r10,lsl#8 - eor r10,r7,r3 @ F_xx_xx - orr r9,r9,r11,lsl#16 - add r4,r4,r5,ror#27 @ E+=ROR(A,27) - orr r9,r9,r12,lsl#24 -#else - ldr r9,[r1],#4 @ handles unaligned - add r4,r8,r4,ror#2 @ E+=K_00_19 - eor r10,r7,r3 @ F_xx_xx - add r4,r4,r5,ror#27 @ E+=ROR(A,27) -#ifdef __ARMEL__ - rev r9,r9 @ byte swap -#endif -#endif - and r10,r6,r10,ror#2 - add r4,r4,r9 @ E+=X[i] - eor r10,r10,r3,ror#2 @ F_00_19(B,C,D) - str r9,[r14,#-4]! - add r4,r4,r10 @ E+=F_00_19(B,C,D) -#if __ARM_ARCH__<7 - ldrb r10,[r1,#2] - ldrb r9,[r1,#3] - ldrb r11,[r1,#1] - add r3,r8,r3,ror#2 @ E+=K_00_19 - ldrb r12,[r1],#4 - orr r9,r9,r10,lsl#8 - eor r10,r6,r7 @ F_xx_xx - orr r9,r9,r11,lsl#16 - add r3,r3,r4,ror#27 @ E+=ROR(A,27) - orr r9,r9,r12,lsl#24 -#else - ldr r9,[r1],#4 @ handles unaligned - add r3,r8,r3,ror#2 @ E+=K_00_19 - eor r10,r6,r7 @ F_xx_xx - add r3,r3,r4,ror#27 @ E+=ROR(A,27) -#ifdef __ARMEL__ - rev r9,r9 @ byte swap -#endif -#endif - and r10,r5,r10,ror#2 - add r3,r3,r9 @ E+=X[i] - eor r10,r10,r7,ror#2 @ F_00_19(B,C,D) - str r9,[r14,#-4]! - add r3,r3,r10 @ E+=F_00_19(B,C,D) - teq r14,sp - bne .L_00_15 @ [((11+4)*5+2)*3] - sub sp,sp,#25*4 -#if __ARM_ARCH__<7 - ldrb r10,[r1,#2] - ldrb r9,[r1,#3] - ldrb r11,[r1,#1] - add r7,r8,r7,ror#2 @ E+=K_00_19 - ldrb r12,[r1],#4 - orr r9,r9,r10,lsl#8 - eor r10,r5,r6 @ F_xx_xx - orr r9,r9,r11,lsl#16 - add r7,r7,r3,ror#27 @ E+=ROR(A,27) - orr r9,r9,r12,lsl#24 -#else - ldr r9,[r1],#4 @ handles unaligned - add r7,r8,r7,ror#2 @ E+=K_00_19 - eor r10,r5,r6 @ F_xx_xx - add r7,r7,r3,ror#27 @ E+=ROR(A,27) -#ifdef __ARMEL__ - rev r9,r9 @ byte swap -#endif -#endif - and r10,r4,r10,ror#2 - add r7,r7,r9 @ E+=X[i] - eor r10,r10,r6,ror#2 @ F_00_19(B,C,D) - str r9,[r14,#-4]! - add r7,r7,r10 @ E+=F_00_19(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r6,r8,r6,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r4,r5 @ F_xx_xx - mov r9,r9,ror#31 - add r6,r6,r7,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r3,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r6,r6,r9 @ E+=X[i] - eor r10,r10,r5,ror#2 @ F_00_19(B,C,D) - add r6,r6,r10 @ E+=F_00_19(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r5,r8,r5,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r3,r4 @ F_xx_xx - mov r9,r9,ror#31 - add r5,r5,r6,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r7,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r5,r5,r9 @ E+=X[i] - eor r10,r10,r4,ror#2 @ F_00_19(B,C,D) - add r5,r5,r10 @ E+=F_00_19(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r4,r8,r4,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r7,r3 @ F_xx_xx - mov r9,r9,ror#31 - add r4,r4,r5,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r6,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r4,r4,r9 @ E+=X[i] - eor r10,r10,r3,ror#2 @ F_00_19(B,C,D) - add r4,r4,r10 @ E+=F_00_19(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r3,r8,r3,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r6,r7 @ F_xx_xx - mov r9,r9,ror#31 - add r3,r3,r4,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r5,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r3,r3,r9 @ E+=X[i] - eor r10,r10,r7,ror#2 @ F_00_19(B,C,D) - add r3,r3,r10 @ E+=F_00_19(B,C,D) - - ldr r8,.LK_20_39 @ [+15+16*4] - cmn sp,#0 @ [+3], clear carry to denote 20_39 -.L_20_39_or_60_79: - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r7,r8,r7,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r5,r6 @ F_xx_xx - mov r9,r9,ror#31 - add r7,r7,r3,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - eor r10,r4,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r7,r7,r9 @ E+=X[i] - add r7,r7,r10 @ E+=F_20_39(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r6,r8,r6,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r4,r5 @ F_xx_xx - mov r9,r9,ror#31 - add r6,r6,r7,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - eor r10,r3,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r6,r6,r9 @ E+=X[i] - add r6,r6,r10 @ E+=F_20_39(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r5,r8,r5,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r3,r4 @ F_xx_xx - mov r9,r9,ror#31 - add r5,r5,r6,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - eor r10,r7,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r5,r5,r9 @ E+=X[i] - add r5,r5,r10 @ E+=F_20_39(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r4,r8,r4,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r7,r3 @ F_xx_xx - mov r9,r9,ror#31 - add r4,r4,r5,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - eor r10,r6,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r4,r4,r9 @ E+=X[i] - add r4,r4,r10 @ E+=F_20_39(B,C,D) - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r3,r8,r3,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r6,r7 @ F_xx_xx - mov r9,r9,ror#31 - add r3,r3,r4,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - eor r10,r5,r10,ror#2 @ F_xx_xx - @ F_xx_xx - add r3,r3,r9 @ E+=X[i] - add r3,r3,r10 @ E+=F_20_39(B,C,D) - teq r14,sp @ preserve carry - bne .L_20_39_or_60_79 @ [+((12+3)*5+2)*4] - bcs .L_done @ [+((12+3)*5+2)*4], spare 300 bytes - - ldr r8,.LK_40_59 - sub sp,sp,#20*4 @ [+2] -.L_40_59: - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r7,r8,r7,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r5,r6 @ F_xx_xx - mov r9,r9,ror#31 - add r7,r7,r3,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r4,r10,ror#2 @ F_xx_xx - and r11,r5,r6 @ F_xx_xx - add r7,r7,r9 @ E+=X[i] - add r7,r7,r10 @ E+=F_40_59(B,C,D) - add r7,r7,r11,ror#2 - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r6,r8,r6,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r4,r5 @ F_xx_xx - mov r9,r9,ror#31 - add r6,r6,r7,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r3,r10,ror#2 @ F_xx_xx - and r11,r4,r5 @ F_xx_xx - add r6,r6,r9 @ E+=X[i] - add r6,r6,r10 @ E+=F_40_59(B,C,D) - add r6,r6,r11,ror#2 - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r5,r8,r5,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r3,r4 @ F_xx_xx - mov r9,r9,ror#31 - add r5,r5,r6,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r7,r10,ror#2 @ F_xx_xx - and r11,r3,r4 @ F_xx_xx - add r5,r5,r9 @ E+=X[i] - add r5,r5,r10 @ E+=F_40_59(B,C,D) - add r5,r5,r11,ror#2 - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r4,r8,r4,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r7,r3 @ F_xx_xx - mov r9,r9,ror#31 - add r4,r4,r5,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r6,r10,ror#2 @ F_xx_xx - and r11,r7,r3 @ F_xx_xx - add r4,r4,r9 @ E+=X[i] - add r4,r4,r10 @ E+=F_40_59(B,C,D) - add r4,r4,r11,ror#2 - ldr r9,[r14,#15*4] - ldr r10,[r14,#13*4] - ldr r11,[r14,#7*4] - add r3,r8,r3,ror#2 @ E+=K_xx_xx - ldr r12,[r14,#2*4] - eor r9,r9,r10 - eor r11,r11,r12 @ 1 cycle stall - eor r10,r6,r7 @ F_xx_xx - mov r9,r9,ror#31 - add r3,r3,r4,ror#27 @ E+=ROR(A,27) - eor r9,r9,r11,ror#31 - str r9,[r14,#-4]! - and r10,r5,r10,ror#2 @ F_xx_xx - and r11,r6,r7 @ F_xx_xx - add r3,r3,r9 @ E+=X[i] - add r3,r3,r10 @ E+=F_40_59(B,C,D) - add r3,r3,r11,ror#2 - teq r14,sp - bne .L_40_59 @ [+((12+5)*5+2)*4] - - ldr r8,.LK_60_79 - sub sp,sp,#20*4 - cmp sp,#0 @ set carry to denote 60_79 - b .L_20_39_or_60_79 @ [+4], spare 300 bytes -.L_done: - add sp,sp,#80*4 @ "deallocate" stack frame - ldmia r0,{r8,r9,r10,r11,r12} - add r3,r8,r3 - add r4,r9,r4 - add r5,r10,r5,ror#2 - add r6,r11,r6,ror#2 - add r7,r12,r7,ror#2 - stmia r0,{r3,r4,r5,r6,r7} - teq r1,r2 - bne .Lloop @ [+18], total 1307 - -#if __ARM_ARCH__>=5 - ldmia sp!,{r4-r12,pc} -#else - ldmia sp!,{r4-r12,lr} - tst lr,#1 - moveq pc,lr @ be binary compatible with V4, yet - .word 0xe12fff1e @ interoperable with Thumb ISA:-) -#endif -.size sha1_block_data_order,.-sha1_block_data_order - -.align 5 -.LK_00_19: .word 0x5a827999 -.LK_20_39: .word 0x6ed9eba1 -.LK_40_59: .word 0x8f1bbcdc -.LK_60_79: .word 0xca62c1d6 -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-sha1_block_data_order -.asciz "SHA1 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro@openssl.org>" -.align 5 -#if __ARM_ARCH__>=7 -.fpu neon - -.type sha1_block_data_order_neon,%function -.align 4 -sha1_block_data_order_neon: -.LNEON: - stmdb sp!,{r4-r12,lr} - add r2,r1,r2,lsl#6 @ r2 to point at the end of r1 - @ dmb @ errata #451034 on early Cortex A8 - @ vstmdb sp!,{d8-d15} @ ABI specification says so - mov r14,sp - sub sp,sp,#64 @ alloca - adr r8,.LK_00_19 - bic sp,sp,#15 @ align for 128-bit stores - - ldmia r0,{r3,r4,r5,r6,r7} @ load context - mov r12,sp - - vld1.8 {q0-q1},[r1]! @ handles unaligned - veor q15,q15,q15 - vld1.8 {q2-q3},[r1]! - vld1.32 {d28[],d29[]},[r8,:32]! @ load K_00_19 - vrev32.8 q0,q0 @ yes, even on - vrev32.8 q1,q1 @ big-endian... - vrev32.8 q2,q2 - vadd.i32 q8,q0,q14 - vrev32.8 q3,q3 - vadd.i32 q9,q1,q14 - vst1.32 {q8},[r12,:128]! - vadd.i32 q10,q2,q14 - vst1.32 {q9},[r12,:128]! - vst1.32 {q10},[r12,:128]! - ldr r9,[sp] @ big RAW stall - -.Loop_neon: - vext.8 q8,q0,q1,#8 - bic r10,r6,r4 - add r7,r7,r9 - and r11,r5,r4 - vadd.i32 q13,q3,q14 - ldr r9,[sp,#4] - add r7,r7,r3,ror#27 - vext.8 q12,q3,q15,#4 - eor r11,r11,r10 - mov r4,r4,ror#2 - add r7,r7,r11 - veor q8,q8,q0 - bic r10,r5,r3 - add r6,r6,r9 - veor q12,q12,q2 - and r11,r4,r3 - ldr r9,[sp,#8] - veor q12,q12,q8 - add r6,r6,r7,ror#27 - eor r11,r11,r10 - vst1.32 {q13},[r12,:128]! - sub r12,r12,#64 - mov r3,r3,ror#2 - add r6,r6,r11 - vext.8 q13,q15,q12,#4 - bic r10,r4,r7 - add r5,r5,r9 - vadd.i32 q8,q12,q12 - and r11,r3,r7 - ldr r9,[sp,#12] - vsri.32 q8,q12,#31 - add r5,r5,r6,ror#27 - eor r11,r11,r10 - mov r7,r7,ror#2 - vshr.u32 q12,q13,#30 - add r5,r5,r11 - bic r10,r3,r6 - vshl.u32 q13,q13,#2 - add r4,r4,r9 - and r11,r7,r6 - veor q8,q8,q12 - ldr r9,[sp,#16] - add r4,r4,r5,ror#27 - veor q8,q8,q13 - eor r11,r11,r10 - mov r6,r6,ror#2 - add r4,r4,r11 - vext.8 q9,q1,q2,#8 - bic r10,r7,r5 - add r3,r3,r9 - and r11,r6,r5 - vadd.i32 q13,q8,q14 - ldr r9,[sp,#20] - vld1.32 {d28[],d29[]},[r8,:32]! - add r3,r3,r4,ror#27 - vext.8 q12,q8,q15,#4 - eor r11,r11,r10 - mov r5,r5,ror#2 - add r3,r3,r11 - veor q9,q9,q1 - bic r10,r6,r4 - add r7,r7,r9 - veor q12,q12,q3 - and r11,r5,r4 - ldr r9,[sp,#24] - veor q12,q12,q9 - add r7,r7,r3,ror#27 - eor r11,r11,r10 - vst1.32 {q13},[r12,:128]! - mov r4,r4,ror#2 - add r7,r7,r11 - vext.8 q13,q15,q12,#4 - bic r10,r5,r3 - add r6,r6,r9 - vadd.i32 q9,q12,q12 - and r11,r4,r3 - ldr r9,[sp,#28] - vsri.32 q9,q12,#31 - add r6,r6,r7,ror#27 - eor r11,r11,r10 - mov r3,r3,ror#2 - vshr.u32 q12,q13,#30 - add r6,r6,r11 - bic r10,r4,r7 - vshl.u32 q13,q13,#2 - add r5,r5,r9 - and r11,r3,r7 - veor q9,q9,q12 - ldr r9,[sp,#32] - add r5,r5,r6,ror#27 - veor q9,q9,q13 - eor r11,r11,r10 - mov r7,r7,ror#2 - add r5,r5,r11 - vext.8 q10,q2,q3,#8 - bic r10,r3,r6 - add r4,r4,r9 - and r11,r7,r6 - vadd.i32 q13,q9,q14 - ldr r9,[sp,#36] - add r4,r4,r5,ror#27 - vext.8 q12,q9,q15,#4 - eor r11,r11,r10 - mov r6,r6,ror#2 - add r4,r4,r11 - veor q10,q10,q2 - bic r10,r7,r5 - add r3,r3,r9 - veor q12,q12,q8 - and r11,r6,r5 - ldr r9,[sp,#40] - veor q12,q12,q10 - add r3,r3,r4,ror#27 - eor r11,r11,r10 - vst1.32 {q13},[r12,:128]! - mov r5,r5,ror#2 - add r3,r3,r11 - vext.8 q13,q15,q12,#4 - bic r10,r6,r4 - add r7,r7,r9 - vadd.i32 q10,q12,q12 - and r11,r5,r4 - ldr r9,[sp,#44] - vsri.32 q10,q12,#31 - add r7,r7,r3,ror#27 - eor r11,r11,r10 - mov r4,r4,ror#2 - vshr.u32 q12,q13,#30 - add r7,r7,r11 - bic r10,r5,r3 - vshl.u32 q13,q13,#2 - add r6,r6,r9 - and r11,r4,r3 - veor q10,q10,q12 - ldr r9,[sp,#48] - add r6,r6,r7,ror#27 - veor q10,q10,q13 - eor r11,r11,r10 - mov r3,r3,ror#2 - add r6,r6,r11 - vext.8 q11,q3,q8,#8 - bic r10,r4,r7 - add r5,r5,r9 - and r11,r3,r7 - vadd.i32 q13,q10,q14 - ldr r9,[sp,#52] - add r5,r5,r6,ror#27 - vext.8 q12,q10,q15,#4 - eor r11,r11,r10 - mov r7,r7,ror#2 - add r5,r5,r11 - veor q11,q11,q3 - bic r10,r3,r6 - add r4,r4,r9 - veor q12,q12,q9 - and r11,r7,r6 - ldr r9,[sp,#56] - veor q12,q12,q11 - add r4,r4,r5,ror#27 - eor r11,r11,r10 - vst1.32 {q13},[r12,:128]! - mov r6,r6,ror#2 - add r4,r4,r11 - vext.8 q13,q15,q12,#4 - bic r10,r7,r5 - add r3,r3,r9 - vadd.i32 q11,q12,q12 - and r11,r6,r5 - ldr r9,[sp,#60] - vsri.32 q11,q12,#31 - add r3,r3,r4,ror#27 - eor r11,r11,r10 - mov r5,r5,ror#2 - vshr.u32 q12,q13,#30 - add r3,r3,r11 - bic r10,r6,r4 - vshl.u32 q13,q13,#2 - add r7,r7,r9 - and r11,r5,r4 - veor q11,q11,q12 - ldr r9,[sp,#0] - add r7,r7,r3,ror#27 - veor q11,q11,q13 - eor r11,r11,r10 - mov r4,r4,ror#2 - add r7,r7,r11 - vext.8 q12,q10,q11,#8 - bic r10,r5,r3 - add r6,r6,r9 - and r11,r4,r3 - veor q0,q0,q8 - ldr r9,[sp,#4] - add r6,r6,r7,ror#27 - veor q0,q0,q1 - eor r11,r11,r10 - mov r3,r3,ror#2 - vadd.i32 q13,q11,q14 - add r6,r6,r11 - bic r10,r4,r7 - veor q12,q12,q0 - add r5,r5,r9 - and r11,r3,r7 - vshr.u32 q0,q12,#30 - ldr r9,[sp,#8] - add r5,r5,r6,ror#27 - vst1.32 {q13},[r12,:128]! - sub r12,r12,#64 - eor r11,r11,r10 - mov r7,r7,ror#2 - vsli.32 q0,q12,#2 - add r5,r5,r11 - bic r10,r3,r6 - add r4,r4,r9 - and r11,r7,r6 - ldr r9,[sp,#12] - add r4,r4,r5,ror#27 - eor r11,r11,r10 - mov r6,r6,ror#2 - add r4,r4,r11 - bic r10,r7,r5 - add r3,r3,r9 - and r11,r6,r5 - ldr r9,[sp,#16] - add r3,r3,r4,ror#27 - eor r11,r11,r10 - mov r5,r5,ror#2 - add r3,r3,r11 - vext.8 q12,q11,q0,#8 - eor r10,r4,r6 - add r7,r7,r9 - ldr r9,[sp,#20] - veor q1,q1,q9 - eor r11,r10,r5 - add r7,r7,r3,ror#27 - veor q1,q1,q2 - mov r4,r4,ror#2 - add r7,r7,r11 - vadd.i32 q13,q0,q14 - eor r10,r3,r5 - add r6,r6,r9 - veor q12,q12,q1 - ldr r9,[sp,#24] - eor r11,r10,r4 - vshr.u32 q1,q12,#30 - add r6,r6,r7,ror#27 - mov r3,r3,ror#2 - vst1.32 {q13},[r12,:128]! - add r6,r6,r11 - eor r10,r7,r4 - vsli.32 q1,q12,#2 - add r5,r5,r9 - ldr r9,[sp,#28] - eor r11,r10,r3 - add r5,r5,r6,ror#27 - mov r7,r7,ror#2 - add r5,r5,r11 - eor r10,r6,r3 - add r4,r4,r9 - ldr r9,[sp,#32] - eor r11,r10,r7 - add r4,r4,r5,ror#27 - mov r6,r6,ror#2 - add r4,r4,r11 - vext.8 q12,q0,q1,#8 - eor r10,r5,r7 - add r3,r3,r9 - ldr r9,[sp,#36] - veor q2,q2,q10 - eor r11,r10,r6 - add r3,r3,r4,ror#27 - veor q2,q2,q3 - mov r5,r5,ror#2 - add r3,r3,r11 - vadd.i32 q13,q1,q14 - eor r10,r4,r6 - vld1.32 {d28[],d29[]},[r8,:32]! - add r7,r7,r9 - veor q12,q12,q2 - ldr r9,[sp,#40] - eor r11,r10,r5 - vshr.u32 q2,q12,#30 - add r7,r7,r3,ror#27 - mov r4,r4,ror#2 - vst1.32 {q13},[r12,:128]! - add r7,r7,r11 - eor r10,r3,r5 - vsli.32 q2,q12,#2 - add r6,r6,r9 - ldr r9,[sp,#44] - eor r11,r10,r4 - add r6,r6,r7,ror#27 - mov r3,r3,ror#2 - add r6,r6,r11 - eor r10,r7,r4 - add r5,r5,r9 - ldr r9,[sp,#48] - eor r11,r10,r3 - add r5,r5,r6,ror#27 - mov r7,r7,ror#2 - add r5,r5,r11 - vext.8 q12,q1,q2,#8 - eor r10,r6,r3 - add r4,r4,r9 - ldr r9,[sp,#52] - veor q3,q3,q11 - eor r11,r10,r7 - add r4,r4,r5,ror#27 - veor q3,q3,q8 - mov r6,r6,ror#2 - add r4,r4,r11 - vadd.i32 q13,q2,q14 - eor r10,r5,r7 - add r3,r3,r9 - veor q12,q12,q3 - ldr r9,[sp,#56] - eor r11,r10,r6 - vshr.u32 q3,q12,#30 - add r3,r3,r4,ror#27 - mov r5,r5,ror#2 - vst1.32 {q13},[r12,:128]! - add r3,r3,r11 - eor r10,r4,r6 - vsli.32 q3,q12,#2 - add r7,r7,r9 - ldr r9,[sp,#60] - eor r11,r10,r5 - add r7,r7,r3,ror#27 - mov r4,r4,ror#2 - add r7,r7,r11 - eor r10,r3,r5 - add r6,r6,r9 - ldr r9,[sp,#0] - eor r11,r10,r4 - add r6,r6,r7,ror#27 - mov r3,r3,ror#2 - add r6,r6,r11 - vext.8 q12,q2,q3,#8 - eor r10,r7,r4 - add r5,r5,r9 - ldr r9,[sp,#4] - veor q8,q8,q0 - eor r11,r10,r3 - add r5,r5,r6,ror#27 - veor q8,q8,q9 - mov r7,r7,ror#2 - add r5,r5,r11 - vadd.i32 q13,q3,q14 - eor r10,r6,r3 - add r4,r4,r9 - veor q12,q12,q8 - ldr r9,[sp,#8] - eor r11,r10,r7 - vshr.u32 q8,q12,#30 - add r4,r4,r5,ror#27 - mov r6,r6,ror#2 - vst1.32 {q13},[r12,:128]! - sub r12,r12,#64 - add r4,r4,r11 - eor r10,r5,r7 - vsli.32 q8,q12,#2 - add r3,r3,r9 - ldr r9,[sp,#12] - eor r11,r10,r6 - add r3,r3,r4,ror#27 - mov r5,r5,ror#2 - add r3,r3,r11 - eor r10,r4,r6 - add r7,r7,r9 - ldr r9,[sp,#16] - eor r11,r10,r5 - add r7,r7,r3,ror#27 - mov r4,r4,ror#2 - add r7,r7,r11 - vext.8 q12,q3,q8,#8 - eor r10,r3,r5 - add r6,r6,r9 - ldr r9,[sp,#20] - veor q9,q9,q1 - eor r11,r10,r4 - add r6,r6,r7,ror#27 - veor q9,q9,q10 - mov r3,r3,ror#2 - add r6,r6,r11 - vadd.i32 q13,q8,q14 - eor r10,r7,r4 - add r5,r5,r9 - veor q12,q12,q9 - ldr r9,[sp,#24] - eor r11,r10,r3 - vshr.u32 q9,q12,#30 - add r5,r5,r6,ror#27 - mov r7,r7,ror#2 - vst1.32 {q13},[r12,:128]! - add r5,r5,r11 - eor r10,r6,r3 - vsli.32 q9,q12,#2 - add r4,r4,r9 - ldr r9,[sp,#28] - eor r11,r10,r7 - add r4,r4,r5,ror#27 - mov r6,r6,ror#2 - add r4,r4,r11 - eor r10,r5,r7 - add r3,r3,r9 - ldr r9,[sp,#32] - eor r11,r10,r6 - add r3,r3,r4,ror#27 - mov r5,r5,ror#2 - add r3,r3,r11 - vext.8 q12,q8,q9,#8 - add r7,r7,r9 - and r10,r5,r6 - ldr r9,[sp,#36] - veor q10,q10,q2 - add r7,r7,r3,ror#27 - eor r11,r5,r6 - veor q10,q10,q11 - add r7,r7,r10 - and r11,r11,r4 - vadd.i32 q13,q9,q14 - mov r4,r4,ror#2 - add r7,r7,r11 - veor q12,q12,q10 - add r6,r6,r9 - and r10,r4,r5 - vshr.u32 q10,q12,#30 - ldr r9,[sp,#40] - add r6,r6,r7,ror#27 - vst1.32 {q13},[r12,:128]! - eor r11,r4,r5 - add r6,r6,r10 - vsli.32 q10,q12,#2 - and r11,r11,r3 - mov r3,r3,ror#2 - add r6,r6,r11 - add r5,r5,r9 - and r10,r3,r4 - ldr r9,[sp,#44] - add r5,r5,r6,ror#27 - eor r11,r3,r4 - add r5,r5,r10 - and r11,r11,r7 - mov r7,r7,ror#2 - add r5,r5,r11 - add r4,r4,r9 - and r10,r7,r3 - ldr r9,[sp,#48] - add r4,r4,r5,ror#27 - eor r11,r7,r3 - add r4,r4,r10 - and r11,r11,r6 - mov r6,r6,ror#2 - add r4,r4,r11 - vext.8 q12,q9,q10,#8 - add r3,r3,r9 - and r10,r6,r7 - ldr r9,[sp,#52] - veor q11,q11,q3 - add r3,r3,r4,ror#27 - eor r11,r6,r7 - veor q11,q11,q0 - add r3,r3,r10 - and r11,r11,r5 - vadd.i32 q13,q10,q14 - mov r5,r5,ror#2 - vld1.32 {d28[],d29[]},[r8,:32]! - add r3,r3,r11 - veor q12,q12,q11 - add r7,r7,r9 - and r10,r5,r6 - vshr.u32 q11,q12,#30 - ldr r9,[sp,#56] - add r7,r7,r3,ror#27 - vst1.32 {q13},[r12,:128]! - eor r11,r5,r6 - add r7,r7,r10 - vsli.32 q11,q12,#2 - and r11,r11,r4 - mov r4,r4,ror#2 - add r7,r7,r11 - add r6,r6,r9 - and r10,r4,r5 - ldr r9,[sp,#60] - add r6,r6,r7,ror#27 - eor r11,r4,r5 - add r6,r6,r10 - and r11,r11,r3 - mov r3,r3,ror#2 - add r6,r6,r11 - add r5,r5,r9 - and r10,r3,r4 - ldr r9,[sp,#0] - add r5,r5,r6,ror#27 - eor r11,r3,r4 - add r5,r5,r10 - and r11,r11,r7 - mov r7,r7,ror#2 - add r5,r5,r11 - vext.8 q12,q10,q11,#8 - add r4,r4,r9 - and r10,r7,r3 - ldr r9,[sp,#4] - veor q0,q0,q8 - add r4,r4,r5,ror#27 - eor r11,r7,r3 - veor q0,q0,q1 - add r4,r4,r10 - and r11,r11,r6 - vadd.i32 q13,q11,q14 - mov r6,r6,ror#2 - add r4,r4,r11 - veor q12,q12,q0 - add r3,r3,r9 - and r10,r6,r7 - vshr.u32 q0,q12,#30 - ldr r9,[sp,#8] - add r3,r3,r4,ror#27 - vst1.32 {q13},[r12,:128]! - sub r12,r12,#64 - eor r11,r6,r7 - add r3,r3,r10 - vsli.32 q0,q12,#2 - and r11,r11,r5 - mov r5,r5,ror#2 - add r3,r3,r11 - add r7,r7,r9 - and r10,r5,r6 - ldr r9,[sp,#12] - add r7,r7,r3,ror#27 - eor r11,r5,r6 - add r7,r7,r10 - and r11,r11,r4 - mov r4,r4,ror#2 - add r7,r7,r11 - add r6,r6,r9 - and r10,r4,r5 - ldr r9,[sp,#16] - add r6,r6,r7,ror#27 - eor r11,r4,r5 - add r6,r6,r10 - and r11,r11,r3 - mov r3,r3,ror#2 - add r6,r6,r11 - vext.8 q12,q11,q0,#8 - add r5,r5,r9 - and r10,r3,r4 - ldr r9,[sp,#20] - veor q1,q1,q9 - add r5,r5,r6,ror#27 - eor r11,r3,r4 - veor q1,q1,q2 - add r5,r5,r10 - and r11,r11,r7 - vadd.i32 q13,q0,q14 - mov r7,r7,ror#2 - add r5,r5,r11 - veor q12,q12,q1 - add r4,r4,r9 - and r10,r7,r3 - vshr.u32 q1,q12,#30 - ldr r9,[sp,#24] - add r4,r4,r5,ror#27 - vst1.32 {q13},[r12,:128]! - eor r11,r7,r3 - add r4,r4,r10 - vsli.32 q1,q12,#2 - and r11,r11,r6 - mov r6,r6,ror#2 - add r4,r4,r11 - add r3,r3,r9 - and r10,r6,r7 - ldr r9,[sp,#28] - add r3,r3,r4,ror#27 - eor r11,r6,r7 - add r3,r3,r10 - and r11,r11,r5 - mov r5,r5,ror#2 - add r3,r3,r11 - add r7,r7,r9 - and r10,r5,r6 - ldr r9,[sp,#32] - add r7,r7,r3,ror#27 - eor r11,r5,r6 - add r7,r7,r10 - and r11,r11,r4 - mov r4,r4,ror#2 - add r7,r7,r11 - vext.8 q12,q0,q1,#8 - add r6,r6,r9 - and r10,r4,r5 - ldr r9,[sp,#36] - veor q2,q2,q10 - add r6,r6,r7,ror#27 - eor r11,r4,r5 - veor q2,q2,q3 - add r6,r6,r10 - and r11,r11,r3 - vadd.i32 q13,q1,q14 - mov r3,r3,ror#2 - add r6,r6,r11 - veor q12,q12,q2 - add r5,r5,r9 - and r10,r3,r4 - vshr.u32 q2,q12,#30 - ldr r9,[sp,#40] - add r5,r5,r6,ror#27 - vst1.32 {q13},[r12,:128]! - eor r11,r3,r4 - add r5,r5,r10 - vsli.32 q2,q12,#2 - and r11,r11,r7 - mov r7,r7,ror#2 - add r5,r5,r11 - add r4,r4,r9 - and r10,r7,r3 - ldr r9,[sp,#44] - add r4,r4,r5,ror#27 - eor r11,r7,r3 - add r4,r4,r10 - and r11,r11,r6 - mov r6,r6,ror#2 - add r4,r4,r11 - add r3,r3,r9 - and r10,r6,r7 - ldr r9,[sp,#48] - add r3,r3,r4,ror#27 - eor r11,r6,r7 - add r3,r3,r10 - and r11,r11,r5 - mov r5,r5,ror#2 - add r3,r3,r11 - vext.8 q12,q1,q2,#8 - eor r10,r4,r6 - add r7,r7,r9 - ldr r9,[sp,#52] - veor q3,q3,q11 - eor r11,r10,r5 - add r7,r7,r3,ror#27 - veor q3,q3,q8 - mov r4,r4,ror#2 - add r7,r7,r11 - vadd.i32 q13,q2,q14 - eor r10,r3,r5 - add r6,r6,r9 - veor q12,q12,q3 - ldr r9,[sp,#56] - eor r11,r10,r4 - vshr.u32 q3,q12,#30 - add r6,r6,r7,ror#27 - mov r3,r3,ror#2 - vst1.32 {q13},[r12,:128]! - add r6,r6,r11 - eor r10,r7,r4 - vsli.32 q3,q12,#2 - add r5,r5,r9 - ldr r9,[sp,#60] - eor r11,r10,r3 - add r5,r5,r6,ror#27 - mov r7,r7,ror#2 - add r5,r5,r11 - eor r10,r6,r3 - add r4,r4,r9 - ldr r9,[sp,#0] - eor r11,r10,r7 - add r4,r4,r5,ror#27 - mov r6,r6,ror#2 - add r4,r4,r11 - vadd.i32 q13,q3,q14 - eor r10,r5,r7 - add r3,r3,r9 - vst1.32 {q13},[r12,:128]! - sub r12,r12,#64 - teq r1,r2 - sub r8,r8,#16 - subeq r1,r1,#64 - vld1.8 {q0-q1},[r1]! - ldr r9,[sp,#4] - eor r11,r10,r6 - vld1.8 {q2-q3},[r1]! - add r3,r3,r4,ror#27 - mov r5,r5,ror#2 - vld1.32 {d28[],d29[]},[r8,:32]! - add r3,r3,r11 - eor r10,r4,r6 - vrev32.8 q0,q0 - add r7,r7,r9 - ldr r9,[sp,#8] - eor r11,r10,r5 - add r7,r7,r3,ror#27 - mov r4,r4,ror#2 - add r7,r7,r11 - eor r10,r3,r5 - add r6,r6,r9 - ldr r9,[sp,#12] - eor r11,r10,r4 - add r6,r6,r7,ror#27 - mov r3,r3,ror#2 - add r6,r6,r11 - eor r10,r7,r4 - add r5,r5,r9 - ldr r9,[sp,#16] - eor r11,r10,r3 - add r5,r5,r6,ror#27 - mov r7,r7,ror#2 - add r5,r5,r11 - vrev32.8 q1,q1 - eor r10,r6,r3 - add r4,r4,r9 - vadd.i32 q8,q0,q14 - ldr r9,[sp,#20] - eor r11,r10,r7 - vst1.32 {q8},[r12,:128]! - add r4,r4,r5,ror#27 - mov r6,r6,ror#2 - add r4,r4,r11 - eor r10,r5,r7 - add r3,r3,r9 - ldr r9,[sp,#24] - eor r11,r10,r6 - add r3,r3,r4,ror#27 - mov r5,r5,ror#2 - add r3,r3,r11 - eor r10,r4,r6 - add r7,r7,r9 - ldr r9,[sp,#28] - eor r11,r10,r5 - add r7,r7,r3,ror#27 - mov r4,r4,ror#2 - add r7,r7,r11 - eor r10,r3,r5 - add r6,r6,r9 - ldr r9,[sp,#32] - eor r11,r10,r4 - add r6,r6,r7,ror#27 - mov r3,r3,ror#2 - add r6,r6,r11 - vrev32.8 q2,q2 - eor r10,r7,r4 - add r5,r5,r9 - vadd.i32 q9,q1,q14 - ldr r9,[sp,#36] - eor r11,r10,r3 - vst1.32 {q9},[r12,:128]! - add r5,r5,r6,ror#27 - mov r7,r7,ror#2 - add r5,r5,r11 - eor r10,r6,r3 - add r4,r4,r9 - ldr r9,[sp,#40] - eor r11,r10,r7 - add r4,r4,r5,ror#27 - mov r6,r6,ror#2 - add r4,r4,r11 - eor r10,r5,r7 - add r3,r3,r9 - ldr r9,[sp,#44] - eor r11,r10,r6 - add r3,r3,r4,ror#27 - mov r5,r5,ror#2 - add r3,r3,r11 - eor r10,r4,r6 - add r7,r7,r9 - ldr r9,[sp,#48] - eor r11,r10,r5 - add r7,r7,r3,ror#27 - mov r4,r4,ror#2 - add r7,r7,r11 - vrev32.8 q3,q3 - eor r10,r3,r5 - add r6,r6,r9 - vadd.i32 q10,q2,q14 - ldr r9,[sp,#52] - eor r11,r10,r4 - vst1.32 {q10},[r12,:128]! - add r6,r6,r7,ror#27 - mov r3,r3,ror#2 - add r6,r6,r11 - eor r10,r7,r4 - add r5,r5,r9 - ldr r9,[sp,#56] - eor r11,r10,r3 - add r5,r5,r6,ror#27 - mov r7,r7,ror#2 - add r5,r5,r11 - eor r10,r6,r3 - add r4,r4,r9 - ldr r9,[sp,#60] - eor r11,r10,r7 - add r4,r4,r5,ror#27 - mov r6,r6,ror#2 - add r4,r4,r11 - eor r10,r5,r7 - add r3,r3,r9 - eor r11,r10,r6 - add r3,r3,r4,ror#27 - mov r5,r5,ror#2 - add r3,r3,r11 - ldmia r0,{r9,r10,r11,r12} @ accumulate context - add r3,r3,r9 - ldr r9,[r0,#16] - add r4,r4,r10 - add r5,r5,r11 - add r6,r6,r12 - moveq sp,r14 - add r7,r7,r9 - ldrne r9,[sp] - stmia r0,{r3,r4,r5,r6,r7} - addne r12,sp,#3*16 - bne .Loop_neon - - @ vldmia sp!,{d8-d15} - ldmia sp!,{r4-r12,pc} -.size sha1_block_data_order_neon,.-sha1_block_data_order_neon -#endif -#if __ARM_ARCH__>=7 -.type sha1_block_data_order_armv8,%function -.align 5 -sha1_block_data_order_armv8: -.LARMv8: - vstmdb sp!,{d8-d15} @ ABI specification says so - - veor q1,q1,q1 - adr r3,.LK_00_19 - vld1.32 {q0},[r0]! - vld1.32 {d2[0]},[r0] - sub r0,r0,#16 - vld1.32 {d16[],d17[]},[r3,:32]! - vld1.32 {d18[],d19[]},[r3,:32]! - vld1.32 {d20[],d21[]},[r3,:32]! - vld1.32 {d22[],d23[]},[r3,:32] - -.Loop_v8: - vld1.8 {q4-q5},[r1]! - vld1.8 {q6-q7},[r1]! - vrev32.8 q4,q4 - vrev32.8 q5,q5 - - vadd.i32 q12,q8,q4 - vrev32.8 q6,q6 - vmov q14,q0 @ offload - subs r2,r2,#1 - - vadd.i32 q13,q8,q5 - vrev32.8 q7,q7 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 0 - .byte 0x68,0x0c,0x02,0xf2 @ sha1c q0,q1,q12 - vadd.i32 q12,q8,q6 - .byte 0x4c,0x8c,0x3a,0xf2 @ sha1su0 q4,q5,q6 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 1 - .byte 0x6a,0x0c,0x06,0xf2 @ sha1c q0,q3,q13 - vadd.i32 q13,q8,q7 - .byte 0x8e,0x83,0xba,0xf3 @ sha1su1 q4,q7 - .byte 0x4e,0xac,0x3c,0xf2 @ sha1su0 q5,q6,q7 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 2 - .byte 0x68,0x0c,0x04,0xf2 @ sha1c q0,q2,q12 - vadd.i32 q12,q8,q4 - .byte 0x88,0xa3,0xba,0xf3 @ sha1su1 q5,q4 - .byte 0x48,0xcc,0x3e,0xf2 @ sha1su0 q6,q7,q4 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 3 - .byte 0x6a,0x0c,0x06,0xf2 @ sha1c q0,q3,q13 - vadd.i32 q13,q9,q5 - .byte 0x8a,0xc3,0xba,0xf3 @ sha1su1 q6,q5 - .byte 0x4a,0xec,0x38,0xf2 @ sha1su0 q7,q4,q5 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 4 - .byte 0x68,0x0c,0x04,0xf2 @ sha1c q0,q2,q12 - vadd.i32 q12,q9,q6 - .byte 0x8c,0xe3,0xba,0xf3 @ sha1su1 q7,q6 - .byte 0x4c,0x8c,0x3a,0xf2 @ sha1su0 q4,q5,q6 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 5 - .byte 0x6a,0x0c,0x16,0xf2 @ sha1p q0,q3,q13 - vadd.i32 q13,q9,q7 - .byte 0x8e,0x83,0xba,0xf3 @ sha1su1 q4,q7 - .byte 0x4e,0xac,0x3c,0xf2 @ sha1su0 q5,q6,q7 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 6 - .byte 0x68,0x0c,0x14,0xf2 @ sha1p q0,q2,q12 - vadd.i32 q12,q9,q4 - .byte 0x88,0xa3,0xba,0xf3 @ sha1su1 q5,q4 - .byte 0x48,0xcc,0x3e,0xf2 @ sha1su0 q6,q7,q4 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 7 - .byte 0x6a,0x0c,0x16,0xf2 @ sha1p q0,q3,q13 - vadd.i32 q13,q9,q5 - .byte 0x8a,0xc3,0xba,0xf3 @ sha1su1 q6,q5 - .byte 0x4a,0xec,0x38,0xf2 @ sha1su0 q7,q4,q5 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 8 - .byte 0x68,0x0c,0x14,0xf2 @ sha1p q0,q2,q12 - vadd.i32 q12,q10,q6 - .byte 0x8c,0xe3,0xba,0xf3 @ sha1su1 q7,q6 - .byte 0x4c,0x8c,0x3a,0xf2 @ sha1su0 q4,q5,q6 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 9 - .byte 0x6a,0x0c,0x16,0xf2 @ sha1p q0,q3,q13 - vadd.i32 q13,q10,q7 - .byte 0x8e,0x83,0xba,0xf3 @ sha1su1 q4,q7 - .byte 0x4e,0xac,0x3c,0xf2 @ sha1su0 q5,q6,q7 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 10 - .byte 0x68,0x0c,0x24,0xf2 @ sha1m q0,q2,q12 - vadd.i32 q12,q10,q4 - .byte 0x88,0xa3,0xba,0xf3 @ sha1su1 q5,q4 - .byte 0x48,0xcc,0x3e,0xf2 @ sha1su0 q6,q7,q4 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 11 - .byte 0x6a,0x0c,0x26,0xf2 @ sha1m q0,q3,q13 - vadd.i32 q13,q10,q5 - .byte 0x8a,0xc3,0xba,0xf3 @ sha1su1 q6,q5 - .byte 0x4a,0xec,0x38,0xf2 @ sha1su0 q7,q4,q5 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 12 - .byte 0x68,0x0c,0x24,0xf2 @ sha1m q0,q2,q12 - vadd.i32 q12,q10,q6 - .byte 0x8c,0xe3,0xba,0xf3 @ sha1su1 q7,q6 - .byte 0x4c,0x8c,0x3a,0xf2 @ sha1su0 q4,q5,q6 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 13 - .byte 0x6a,0x0c,0x26,0xf2 @ sha1m q0,q3,q13 - vadd.i32 q13,q11,q7 - .byte 0x8e,0x83,0xba,0xf3 @ sha1su1 q4,q7 - .byte 0x4e,0xac,0x3c,0xf2 @ sha1su0 q5,q6,q7 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 14 - .byte 0x68,0x0c,0x24,0xf2 @ sha1m q0,q2,q12 - vadd.i32 q12,q11,q4 - .byte 0x88,0xa3,0xba,0xf3 @ sha1su1 q5,q4 - .byte 0x48,0xcc,0x3e,0xf2 @ sha1su0 q6,q7,q4 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 15 - .byte 0x6a,0x0c,0x16,0xf2 @ sha1p q0,q3,q13 - vadd.i32 q13,q11,q5 - .byte 0x8a,0xc3,0xba,0xf3 @ sha1su1 q6,q5 - .byte 0x4a,0xec,0x38,0xf2 @ sha1su0 q7,q4,q5 - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 16 - .byte 0x68,0x0c,0x14,0xf2 @ sha1p q0,q2,q12 - vadd.i32 q12,q11,q6 - .byte 0x8c,0xe3,0xba,0xf3 @ sha1su1 q7,q6 - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 17 - .byte 0x6a,0x0c,0x16,0xf2 @ sha1p q0,q3,q13 - vadd.i32 q13,q11,q7 - - .byte 0xc0,0x62,0xb9,0xf3 @ sha1h q3,q0 @ 18 - .byte 0x68,0x0c,0x14,0xf2 @ sha1p q0,q2,q12 - - .byte 0xc0,0x42,0xb9,0xf3 @ sha1h q2,q0 @ 19 - .byte 0x6a,0x0c,0x16,0xf2 @ sha1p q0,q3,q13 - - vadd.i32 q1,q1,q2 - vadd.i32 q0,q0,q14 - bne .Loop_v8 - - vst1.32 {q0},[r0]! - vst1.32 {d2[0]},[r0] - - vldmia sp!,{d8-d15} - bx lr @ bx lr -.size sha1_block_data_order_armv8,.-sha1_block_data_order_armv8 -#endif -.comm OPENSSL_armcap_P,4,4 diff --git a/app/openssl/crypto/sha/asm/sha1-armv4-large.pl b/app/openssl/crypto/sha/asm/sha1-armv4-large.pl deleted file mode 100644 index 50bd07b3..00000000 --- a/app/openssl/crypto/sha/asm/sha1-armv4-large.pl +++ /dev/null @@ -1,678 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# sha1_block procedure for ARMv4. -# -# January 2007. - -# Size/performance trade-off -# ==================================================================== -# impl size in bytes comp cycles[*] measured performance -# ==================================================================== -# thumb 304 3212 4420 -# armv4-small 392/+29% 1958/+64% 2250/+96% -# armv4-compact 740/+89% 1552/+26% 1840/+22% -# armv4-large 1420/+92% 1307/+19% 1370/+34%[***] -# full unroll ~5100/+260% ~1260/+4% ~1300/+5% -# ==================================================================== -# thumb = same as 'small' but in Thumb instructions[**] and -# with recurring code in two private functions; -# small = detached Xload/update, loops are folded; -# compact = detached Xload/update, 5x unroll; -# large = interleaved Xload/update, 5x unroll; -# full unroll = interleaved Xload/update, full unroll, estimated[!]; -# -# [*] Manually counted instructions in "grand" loop body. Measured -# performance is affected by prologue and epilogue overhead, -# i-cache availability, branch penalties, etc. -# [**] While each Thumb instruction is twice smaller, they are not as -# diverse as ARM ones: e.g., there are only two arithmetic -# instructions with 3 arguments, no [fixed] rotate, addressing -# modes are limited. As result it takes more instructions to do -# the same job in Thumb, therefore the code is never twice as -# small and always slower. -# [***] which is also ~35% better than compiler generated code. Dual- -# issue Cortex A8 core was measured to process input block in -# ~990 cycles. - -# August 2010. -# -# Rescheduling for dual-issue pipeline resulted in 13% improvement on -# Cortex A8 core and in absolute terms ~870 cycles per input block -# [or 13.6 cycles per byte]. - -# February 2011. -# -# Profiler-assisted and platform-specific optimization resulted in 10% -# improvement on Cortex A8 core and 12.2 cycles per byte. - -# September 2013. -# -# Add NEON implementation (see sha1-586.pl for background info). On -# Cortex A8 it was measured to process one byte in 6.7 cycles or >80% -# faster than integer-only code. Because [fully unrolled] NEON code -# is ~2.5x larger and there are some redundant instructions executed -# when processing last block, improvement is not as big for smallest -# blocks, only ~30%. Snapdragon S4 is a tad faster, 6.4 cycles per -# byte, which is also >80% faster than integer-only code. - -# May 2014. -# -# Add ARMv8 code path performing at 2.35 cpb on Apple A7. - -while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} -open STDOUT,">$output"; - -$ctx="r0"; -$inp="r1"; -$len="r2"; -$a="r3"; -$b="r4"; -$c="r5"; -$d="r6"; -$e="r7"; -$K="r8"; -$t0="r9"; -$t1="r10"; -$t2="r11"; -$t3="r12"; -$Xi="r14"; -@V=($a,$b,$c,$d,$e); - -sub Xupdate { -my ($a,$b,$c,$d,$e,$opt1,$opt2)=@_; -$code.=<<___; - ldr $t0,[$Xi,#15*4] - ldr $t1,[$Xi,#13*4] - ldr $t2,[$Xi,#7*4] - add $e,$K,$e,ror#2 @ E+=K_xx_xx - ldr $t3,[$Xi,#2*4] - eor $t0,$t0,$t1 - eor $t2,$t2,$t3 @ 1 cycle stall - eor $t1,$c,$d @ F_xx_xx - mov $t0,$t0,ror#31 - add $e,$e,$a,ror#27 @ E+=ROR(A,27) - eor $t0,$t0,$t2,ror#31 - str $t0,[$Xi,#-4]! - $opt1 @ F_xx_xx - $opt2 @ F_xx_xx - add $e,$e,$t0 @ E+=X[i] -___ -} - -sub BODY_00_15 { -my ($a,$b,$c,$d,$e)=@_; -$code.=<<___; -#if __ARM_ARCH__<7 - ldrb $t1,[$inp,#2] - ldrb $t0,[$inp,#3] - ldrb $t2,[$inp,#1] - add $e,$K,$e,ror#2 @ E+=K_00_19 - ldrb $t3,[$inp],#4 - orr $t0,$t0,$t1,lsl#8 - eor $t1,$c,$d @ F_xx_xx - orr $t0,$t0,$t2,lsl#16 - add $e,$e,$a,ror#27 @ E+=ROR(A,27) - orr $t0,$t0,$t3,lsl#24 -#else - ldr $t0,[$inp],#4 @ handles unaligned - add $e,$K,$e,ror#2 @ E+=K_00_19 - eor $t1,$c,$d @ F_xx_xx - add $e,$e,$a,ror#27 @ E+=ROR(A,27) -#ifdef __ARMEL__ - rev $t0,$t0 @ byte swap -#endif -#endif - and $t1,$b,$t1,ror#2 - add $e,$e,$t0 @ E+=X[i] - eor $t1,$t1,$d,ror#2 @ F_00_19(B,C,D) - str $t0,[$Xi,#-4]! - add $e,$e,$t1 @ E+=F_00_19(B,C,D) -___ -} - -sub BODY_16_19 { -my ($a,$b,$c,$d,$e)=@_; - &Xupdate(@_,"and $t1,$b,$t1,ror#2"); -$code.=<<___; - eor $t1,$t1,$d,ror#2 @ F_00_19(B,C,D) - add $e,$e,$t1 @ E+=F_00_19(B,C,D) -___ -} - -sub BODY_20_39 { -my ($a,$b,$c,$d,$e)=@_; - &Xupdate(@_,"eor $t1,$b,$t1,ror#2"); -$code.=<<___; - add $e,$e,$t1 @ E+=F_20_39(B,C,D) -___ -} - -sub BODY_40_59 { -my ($a,$b,$c,$d,$e)=@_; - &Xupdate(@_,"and $t1,$b,$t1,ror#2","and $t2,$c,$d"); -$code.=<<___; - add $e,$e,$t1 @ E+=F_40_59(B,C,D) - add $e,$e,$t2,ror#2 -___ -} - -$code=<<___; -#include "arm_arch.h" - -.text -.code 32 - -.global sha1_block_data_order -.type sha1_block_data_order,%function - -.align 5 -sha1_block_data_order: -#if __ARM_ARCH__>=7 - sub r3,pc,#8 @ sha1_block_data_order - ldr r12,.LOPENSSL_armcap - ldr r12,[r3,r12] @ OPENSSL_armcap_P - tst r12,#ARMV8_SHA1 - bne .LARMv8 - tst r12,#ARMV7_NEON - bne .LNEON -#endif - stmdb sp!,{r4-r12,lr} - add $len,$inp,$len,lsl#6 @ $len to point at the end of $inp - ldmia $ctx,{$a,$b,$c,$d,$e} -.Lloop: - ldr $K,.LK_00_19 - mov $Xi,sp - sub sp,sp,#15*4 - mov $c,$c,ror#30 - mov $d,$d,ror#30 - mov $e,$e,ror#30 @ [6] -.L_00_15: -___ -for($i=0;$i<5;$i++) { - &BODY_00_15(@V); unshift(@V,pop(@V)); -} -$code.=<<___; - teq $Xi,sp - bne .L_00_15 @ [((11+4)*5+2)*3] - sub sp,sp,#25*4 -___ - &BODY_00_15(@V); unshift(@V,pop(@V)); - &BODY_16_19(@V); unshift(@V,pop(@V)); - &BODY_16_19(@V); unshift(@V,pop(@V)); - &BODY_16_19(@V); unshift(@V,pop(@V)); - &BODY_16_19(@V); unshift(@V,pop(@V)); -$code.=<<___; - - ldr $K,.LK_20_39 @ [+15+16*4] - cmn sp,#0 @ [+3], clear carry to denote 20_39 -.L_20_39_or_60_79: -___ -for($i=0;$i<5;$i++) { - &BODY_20_39(@V); unshift(@V,pop(@V)); -} -$code.=<<___; - teq $Xi,sp @ preserve carry - bne .L_20_39_or_60_79 @ [+((12+3)*5+2)*4] - bcs .L_done @ [+((12+3)*5+2)*4], spare 300 bytes - - ldr $K,.LK_40_59 - sub sp,sp,#20*4 @ [+2] -.L_40_59: -___ -for($i=0;$i<5;$i++) { - &BODY_40_59(@V); unshift(@V,pop(@V)); -} -$code.=<<___; - teq $Xi,sp - bne .L_40_59 @ [+((12+5)*5+2)*4] - - ldr $K,.LK_60_79 - sub sp,sp,#20*4 - cmp sp,#0 @ set carry to denote 60_79 - b .L_20_39_or_60_79 @ [+4], spare 300 bytes -.L_done: - add sp,sp,#80*4 @ "deallocate" stack frame - ldmia $ctx,{$K,$t0,$t1,$t2,$t3} - add $a,$K,$a - add $b,$t0,$b - add $c,$t1,$c,ror#2 - add $d,$t2,$d,ror#2 - add $e,$t3,$e,ror#2 - stmia $ctx,{$a,$b,$c,$d,$e} - teq $inp,$len - bne .Lloop @ [+18], total 1307 - -#if __ARM_ARCH__>=5 - ldmia sp!,{r4-r12,pc} -#else - ldmia sp!,{r4-r12,lr} - tst lr,#1 - moveq pc,lr @ be binary compatible with V4, yet - bx lr @ interoperable with Thumb ISA:-) -#endif -.size sha1_block_data_order,.-sha1_block_data_order - -.align 5 -.LK_00_19: .word 0x5a827999 -.LK_20_39: .word 0x6ed9eba1 -.LK_40_59: .word 0x8f1bbcdc -.LK_60_79: .word 0xca62c1d6 -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-sha1_block_data_order -.asciz "SHA1 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro\@openssl.org>" -.align 5 -___ -##################################################################### -# NEON stuff -# -{{{ -my @V=($a,$b,$c,$d,$e); -my ($K_XX_XX,$Ki,$t0,$t1,$Xfer,$saved_sp)=map("r$_",(8..12,14)); -my $Xi=4; -my @X=map("q$_",(8..11,0..3)); -my @Tx=("q12","q13"); -my ($K,$zero)=("q14","q15"); -my $j=0; - -sub AUTOLOAD() # thunk [simplified] x86-style perlasm -{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./; - my $arg = pop; - $arg = "#$arg" if ($arg*1 eq $arg); - $code .= "\t$opcode\t".join(',',@_,$arg)."\n"; -} - -sub body_00_19 () { - ( - '($a,$b,$c,$d,$e)=@V;'. # '$code.="@ $j\n";'. - '&bic ($t0,$d,$b)', - '&add ($e,$e,$Ki)', # e+=X[i]+K - '&and ($t1,$c,$b)', - '&ldr ($Ki,sprintf "[sp,#%d]",4*(($j+1)&15))', - '&add ($e,$e,$a,"ror#27")', # e+=ROR(A,27) - '&eor ($t1,$t1,$t0)', # F_00_19 - '&mov ($b,$b,"ror#2")', # b=ROR(b,2) - '&add ($e,$e,$t1);'. # e+=F_00_19 - '$j++; unshift(@V,pop(@V));' - ) -} -sub body_20_39 () { - ( - '($a,$b,$c,$d,$e)=@V;'. # '$code.="@ $j\n";'. - '&eor ($t0,$b,$d)', - '&add ($e,$e,$Ki)', # e+=X[i]+K - '&ldr ($Ki,sprintf "[sp,#%d]",4*(($j+1)&15)) if ($j<79)', - '&eor ($t1,$t0,$c)', # F_20_39 - '&add ($e,$e,$a,"ror#27")', # e+=ROR(A,27) - '&mov ($b,$b,"ror#2")', # b=ROR(b,2) - '&add ($e,$e,$t1);'. # e+=F_20_39 - '$j++; unshift(@V,pop(@V));' - ) -} -sub body_40_59 () { - ( - '($a,$b,$c,$d,$e)=@V;'. # '$code.="@ $j\n";'. - '&add ($e,$e,$Ki)', # e+=X[i]+K - '&and ($t0,$c,$d)', - '&ldr ($Ki,sprintf "[sp,#%d]",4*(($j+1)&15))', - '&add ($e,$e,$a,"ror#27")', # e+=ROR(A,27) - '&eor ($t1,$c,$d)', - '&add ($e,$e,$t0)', - '&and ($t1,$t1,$b)', - '&mov ($b,$b,"ror#2")', # b=ROR(b,2) - '&add ($e,$e,$t1);'. # e+=F_40_59 - '$j++; unshift(@V,pop(@V));' - ) -} - -sub Xupdate_16_31 () -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e); - - &vext_8 (@X[0],@X[-4&7],@X[-3&7],8); # compose "X[-14]" in "X[0]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@Tx[1],@X[-1&7],$K); - eval(shift(@insns)); - &vld1_32 ("{$K\[]}","[$K_XX_XX,:32]!") if ($Xi%5==0); - eval(shift(@insns)); - &vext_8 (@Tx[0],@X[-1&7],$zero,4); # "X[-3]", 3 words - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &veor (@X[0],@X[0],@X[-4&7]); # "X[0]"^="X[-16]" - eval(shift(@insns)); - eval(shift(@insns)); - &veor (@Tx[0],@Tx[0],@X[-2&7]); # "X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - &veor (@Tx[0],@Tx[0],@X[0]); # "X[0]"^="X[-3]"^"X[-8] - eval(shift(@insns)); - eval(shift(@insns)); - &vst1_32 ("{@Tx[1]}","[$Xfer,:128]!"); # X[]+K xfer - &sub ($Xfer,$Xfer,64) if ($Xi%4==0); - eval(shift(@insns)); - eval(shift(@insns)); - &vext_8 (@Tx[1],$zero,@Tx[0],4); # "X[0]"<<96, extract one dword - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@X[0],@Tx[0],@Tx[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vsri_32 (@X[0],@Tx[0],31); # "X[0]"<<<=1 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 (@Tx[0],@Tx[1],30); - eval(shift(@insns)); - eval(shift(@insns)); - &vshl_u32 (@Tx[1],@Tx[1],2); - eval(shift(@insns)); - eval(shift(@insns)); - &veor (@X[0],@X[0],@Tx[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor (@X[0],@X[0],@Tx[1]); # "X[0]"^=("X[0]">>96)<<<2 - - foreach (@insns) { eval; } # remaining instructions [if any] - - $Xi++; push(@X,shift(@X)); # "rotate" X[] -} - -sub Xupdate_32_79 () -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e); - - &vext_8 (@Tx[0],@X[-2&7],@X[-1&7],8); # compose "X[-6]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &veor (@X[0],@X[0],@X[-4&7]); # "X[0]"="X[-32]"^"X[-16]" - eval(shift(@insns)); - eval(shift(@insns)); - &veor (@X[0],@X[0],@X[-7&7]); # "X[0]"^="X[-28]" - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@Tx[1],@X[-1&7],$K); - eval(shift(@insns)); - &vld1_32 ("{$K\[]}","[$K_XX_XX,:32]!") if ($Xi%5==0); - eval(shift(@insns)); - &veor (@Tx[0],@Tx[0],@X[0]); # "X[-6]"^="X[0]" - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 (@X[0],@Tx[0],30); - eval(shift(@insns)); - eval(shift(@insns)); - &vst1_32 ("{@Tx[1]}","[$Xfer,:128]!"); # X[]+K xfer - &sub ($Xfer,$Xfer,64) if ($Xi%4==0); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 (@X[0],@Tx[0],2); # "X[0]"="X[-6]"<<<2 - - foreach (@insns) { eval; } # remaining instructions [if any] - - $Xi++; push(@X,shift(@X)); # "rotate" X[] -} - -sub Xuplast_80 () -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e); - - &vadd_i32 (@Tx[1],@X[-1&7],$K); - eval(shift(@insns)); - eval(shift(@insns)); - &vst1_32 ("{@Tx[1]}","[$Xfer,:128]!"); - &sub ($Xfer,$Xfer,64); - - &teq ($inp,$len); - &sub ($K_XX_XX,$K_XX_XX,16); # rewind $K_XX_XX - &subeq ($inp,$inp,64); # reload last block to avoid SEGV - &vld1_8 ("{@X[-4&7]-@X[-3&7]}","[$inp]!"); - eval(shift(@insns)); - eval(shift(@insns)); - &vld1_8 ("{@X[-2&7]-@X[-1&7]}","[$inp]!"); - eval(shift(@insns)); - eval(shift(@insns)); - &vld1_32 ("{$K\[]}","[$K_XX_XX,:32]!"); # load K_00_19 - eval(shift(@insns)); - eval(shift(@insns)); - &vrev32_8 (@X[-4&7],@X[-4&7]); - - foreach (@insns) { eval; } # remaining instructions - - $Xi=0; -} - -sub Xloop() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e); - - &vrev32_8 (@X[($Xi-3)&7],@X[($Xi-3)&7]); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@X[$Xi&7],@X[($Xi-4)&7],$K); - eval(shift(@insns)); - eval(shift(@insns)); - &vst1_32 ("{@X[$Xi&7]}","[$Xfer,:128]!");# X[]+K xfer to IALU - - foreach (@insns) { eval; } - - $Xi++; -} - -$code.=<<___; -#if __ARM_ARCH__>=7 -.fpu neon - -.type sha1_block_data_order_neon,%function -.align 4 -sha1_block_data_order_neon: -.LNEON: - stmdb sp!,{r4-r12,lr} - add $len,$inp,$len,lsl#6 @ $len to point at the end of $inp - @ dmb @ errata #451034 on early Cortex A8 - @ vstmdb sp!,{d8-d15} @ ABI specification says so - mov $saved_sp,sp - sub sp,sp,#64 @ alloca - adr $K_XX_XX,.LK_00_19 - bic sp,sp,#15 @ align for 128-bit stores - - ldmia $ctx,{$a,$b,$c,$d,$e} @ load context - mov $Xfer,sp - - vld1.8 {@X[-4&7]-@X[-3&7]},[$inp]! @ handles unaligned - veor $zero,$zero,$zero - vld1.8 {@X[-2&7]-@X[-1&7]},[$inp]! - vld1.32 {${K}\[]},[$K_XX_XX,:32]! @ load K_00_19 - vrev32.8 @X[-4&7],@X[-4&7] @ yes, even on - vrev32.8 @X[-3&7],@X[-3&7] @ big-endian... - vrev32.8 @X[-2&7],@X[-2&7] - vadd.i32 @X[0],@X[-4&7],$K - vrev32.8 @X[-1&7],@X[-1&7] - vadd.i32 @X[1],@X[-3&7],$K - vst1.32 {@X[0]},[$Xfer,:128]! - vadd.i32 @X[2],@X[-2&7],$K - vst1.32 {@X[1]},[$Xfer,:128]! - vst1.32 {@X[2]},[$Xfer,:128]! - ldr $Ki,[sp] @ big RAW stall - -.Loop_neon: -___ - &Xupdate_16_31(\&body_00_19); - &Xupdate_16_31(\&body_00_19); - &Xupdate_16_31(\&body_00_19); - &Xupdate_16_31(\&body_00_19); - &Xupdate_32_79(\&body_00_19); - &Xupdate_32_79(\&body_20_39); - &Xupdate_32_79(\&body_20_39); - &Xupdate_32_79(\&body_20_39); - &Xupdate_32_79(\&body_20_39); - &Xupdate_32_79(\&body_20_39); - &Xupdate_32_79(\&body_40_59); - &Xupdate_32_79(\&body_40_59); - &Xupdate_32_79(\&body_40_59); - &Xupdate_32_79(\&body_40_59); - &Xupdate_32_79(\&body_40_59); - &Xupdate_32_79(\&body_20_39); - &Xuplast_80(\&body_20_39); - &Xloop(\&body_20_39); - &Xloop(\&body_20_39); - &Xloop(\&body_20_39); -$code.=<<___; - ldmia $ctx,{$Ki,$t0,$t1,$Xfer} @ accumulate context - add $a,$a,$Ki - ldr $Ki,[$ctx,#16] - add $b,$b,$t0 - add $c,$c,$t1 - add $d,$d,$Xfer - moveq sp,$saved_sp - add $e,$e,$Ki - ldrne $Ki,[sp] - stmia $ctx,{$a,$b,$c,$d,$e} - addne $Xfer,sp,#3*16 - bne .Loop_neon - - @ vldmia sp!,{d8-d15} - ldmia sp!,{r4-r12,pc} -.size sha1_block_data_order_neon,.-sha1_block_data_order_neon -#endif -___ -}}} -##################################################################### -# ARMv8 stuff -# -{{{ -my ($ABCD,$E,$E0,$E1)=map("q$_",(0..3)); -my @MSG=map("q$_",(4..7)); -my @Kxx=map("q$_",(8..11)); -my ($W0,$W1,$ABCD_SAVE)=map("q$_",(12..14)); - -$code.=<<___; -#if __ARM_ARCH__>=7 -.type sha1_block_data_order_armv8,%function -.align 5 -sha1_block_data_order_armv8: -.LARMv8: - vstmdb sp!,{d8-d15} @ ABI specification says so - - veor $E,$E,$E - adr r3,.LK_00_19 - vld1.32 {$ABCD},[$ctx]! - vld1.32 {$E\[0]},[$ctx] - sub $ctx,$ctx,#16 - vld1.32 {@Kxx[0]\[]},[r3,:32]! - vld1.32 {@Kxx[1]\[]},[r3,:32]! - vld1.32 {@Kxx[2]\[]},[r3,:32]! - vld1.32 {@Kxx[3]\[]},[r3,:32] - -.Loop_v8: - vld1.8 {@MSG[0]-@MSG[1]},[$inp]! - vld1.8 {@MSG[2]-@MSG[3]},[$inp]! - vrev32.8 @MSG[0],@MSG[0] - vrev32.8 @MSG[1],@MSG[1] - - vadd.i32 $W0,@Kxx[0],@MSG[0] - vrev32.8 @MSG[2],@MSG[2] - vmov $ABCD_SAVE,$ABCD @ offload - subs $len,$len,#1 - - vadd.i32 $W1,@Kxx[0],@MSG[1] - vrev32.8 @MSG[3],@MSG[3] - sha1h $E1,$ABCD @ 0 - sha1c $ABCD,$E,$W0 - vadd.i32 $W0,@Kxx[$j],@MSG[2] - sha1su0 @MSG[0],@MSG[1],@MSG[2] -___ -for ($j=0,$i=1;$i<20-3;$i++) { -my $f=("c","p","m","p")[$i/5]; -$code.=<<___; - sha1h $E0,$ABCD @ $i - sha1$f $ABCD,$E1,$W1 - vadd.i32 $W1,@Kxx[$j],@MSG[3] - sha1su1 @MSG[0],@MSG[3] -___ -$code.=<<___ if ($i<20-4); - sha1su0 @MSG[1],@MSG[2],@MSG[3] -___ - ($E0,$E1)=($E1,$E0); ($W0,$W1)=($W1,$W0); - push(@MSG,shift(@MSG)); $j++ if ((($i+3)%5)==0); -} -$code.=<<___; - sha1h $E0,$ABCD @ $i - sha1p $ABCD,$E1,$W1 - vadd.i32 $W1,@Kxx[$j],@MSG[3] - - sha1h $E1,$ABCD @ 18 - sha1p $ABCD,$E0,$W0 - - sha1h $E0,$ABCD @ 19 - sha1p $ABCD,$E1,$W1 - - vadd.i32 $E,$E,$E0 - vadd.i32 $ABCD,$ABCD,$ABCD_SAVE - bne .Loop_v8 - - vst1.32 {$ABCD},[$ctx]! - vst1.32 {$E\[0]},[$ctx] - - vldmia sp!,{d8-d15} - ret @ bx lr -.size sha1_block_data_order_armv8,.-sha1_block_data_order_armv8 -#endif -___ -}}} -$code.=<<___; -.comm OPENSSL_armcap_P,4,4 -___ - -{ my %opcode = ( - "sha1c" => 0xf2000c40, "sha1p" => 0xf2100c40, - "sha1m" => 0xf2200c40, "sha1su0" => 0xf2300c40, - "sha1h" => 0xf3b902c0, "sha1su1" => 0xf3ba0380 ); - - sub unsha1 { - my ($mnemonic,$arg)=@_; - - if ($arg =~ m/q([0-9]+)(?:,\s*q([0-9]+))?,\s*q([0-9]+)/o) { - my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19) - |(($2&7)<<17)|(($2&8)<<4) - |(($3&7)<<1) |(($3&8)<<2); - # since ARMv7 instructions are always encoded little-endian. - # correct solution is to use .inst directive, but older - # assemblers don't implement it:-( - sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s", - $word&0xff,($word>>8)&0xff, - ($word>>16)&0xff,($word>>24)&0xff, - $mnemonic,$arg; - } - } -} - -foreach (split($/,$code)) { - s/{q([0-9]+)\[\]}/sprintf "{d%d[],d%d[]}",2*$1,2*$1+1/eo or - s/{q([0-9]+)\[0\]}/sprintf "{d%d[0]}",2*$1/eo; - - s/\b(sha1\w+)\s+(q.*)/unsha1($1,$2)/geo; - - s/\bret\b/bx lr/o or - s/\bbx\s+lr\b/.word\t0xe12fff1e/o; # make it possible to compile with -march=armv4 - - print $_,$/; -} - -close STDOUT; # enforce flush diff --git a/app/openssl/crypto/sha/asm/sha1-armv8.S b/app/openssl/crypto/sha/asm/sha1-armv8.S deleted file mode 100644 index f9d12625..00000000 --- a/app/openssl/crypto/sha/asm/sha1-armv8.S +++ /dev/null @@ -1,1211 +0,0 @@ -#include "arm_arch.h" - -.text - -.globl sha1_block_data_order -.type sha1_block_data_order,%function -.align 6 -sha1_block_data_order: - ldr x16,.LOPENSSL_armcap_P - adr x17,.LOPENSSL_armcap_P - add x16,x16,x17 - ldr w16,[x16] - tst w16,#ARMV8_SHA1 - b.ne .Lv8_entry - - stp x29,x30,[sp,#-96]! - add x29,sp,#0 - stp x19,x20,[sp,#16] - stp x21,x22,[sp,#32] - stp x23,x24,[sp,#48] - stp x25,x26,[sp,#64] - stp x27,x28,[sp,#80] - - ldp w20,w21,[x0] - ldp w22,w23,[x0,#8] - ldr w24,[x0,#16] - -.Loop: - ldr x3,[x1],#64 - movz w28,#0x7999 - sub x2,x2,#1 - movk w28,#0x5a82,lsl#16 -#ifdef __ARMEB__ - ror x3,x3,#32 -#else - rev32 x3,x3 -#endif - add w24,w24,w28 // warm it up - add w24,w24,w3 - lsr x4,x3,#32 - ldr x5,[x1,#-56] - bic w25,w23,w21 - and w26,w22,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - orr w25,w25,w26 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - add w23,w23,w4 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) -#ifdef __ARMEB__ - ror x5,x5,#32 -#else - rev32 x5,x5 -#endif - bic w25,w22,w20 - and w26,w21,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - orr w25,w25,w26 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - add w22,w22,w5 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - lsr x6,x5,#32 - ldr x7,[x1,#-48] - bic w25,w21,w24 - and w26,w20,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - orr w25,w25,w26 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - add w21,w21,w6 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) -#ifdef __ARMEB__ - ror x7,x7,#32 -#else - rev32 x7,x7 -#endif - bic w25,w20,w23 - and w26,w24,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - orr w25,w25,w26 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - add w20,w20,w7 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - lsr x8,x7,#32 - ldr x9,[x1,#-40] - bic w25,w24,w22 - and w26,w23,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - orr w25,w25,w26 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - add w24,w24,w8 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) -#ifdef __ARMEB__ - ror x9,x9,#32 -#else - rev32 x9,x9 -#endif - bic w25,w23,w21 - and w26,w22,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - orr w25,w25,w26 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - add w23,w23,w9 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - lsr x10,x9,#32 - ldr x11,[x1,#-32] - bic w25,w22,w20 - and w26,w21,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - orr w25,w25,w26 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - add w22,w22,w10 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) -#ifdef __ARMEB__ - ror x11,x11,#32 -#else - rev32 x11,x11 -#endif - bic w25,w21,w24 - and w26,w20,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - orr w25,w25,w26 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - add w21,w21,w11 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - lsr x12,x11,#32 - ldr x13,[x1,#-24] - bic w25,w20,w23 - and w26,w24,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - orr w25,w25,w26 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - add w20,w20,w12 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) -#ifdef __ARMEB__ - ror x13,x13,#32 -#else - rev32 x13,x13 -#endif - bic w25,w24,w22 - and w26,w23,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - orr w25,w25,w26 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - add w24,w24,w13 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - lsr x14,x13,#32 - ldr x15,[x1,#-16] - bic w25,w23,w21 - and w26,w22,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - orr w25,w25,w26 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - add w23,w23,w14 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) -#ifdef __ARMEB__ - ror x15,x15,#32 -#else - rev32 x15,x15 -#endif - bic w25,w22,w20 - and w26,w21,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - orr w25,w25,w26 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - add w22,w22,w15 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - lsr x16,x15,#32 - ldr x17,[x1,#-8] - bic w25,w21,w24 - and w26,w20,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - orr w25,w25,w26 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - add w21,w21,w16 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) -#ifdef __ARMEB__ - ror x17,x17,#32 -#else - rev32 x17,x17 -#endif - bic w25,w20,w23 - and w26,w24,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - orr w25,w25,w26 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - add w20,w20,w17 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - lsr x19,x17,#32 - eor w3,w3,w5 - bic w25,w24,w22 - and w26,w23,w22 - ror w27,w21,#27 - eor w3,w3,w11 - add w24,w24,w28 // future e+=K - orr w25,w25,w26 - add w20,w20,w27 // e+=rot(a,5) - eor w3,w3,w16 - ror w22,w22,#2 - add w24,w24,w19 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w3,w3,#31 - eor w4,w4,w6 - bic w25,w23,w21 - and w26,w22,w21 - ror w27,w20,#27 - eor w4,w4,w12 - add w23,w23,w28 // future e+=K - orr w25,w25,w26 - add w24,w24,w27 // e+=rot(a,5) - eor w4,w4,w17 - ror w21,w21,#2 - add w23,w23,w3 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w4,w4,#31 - eor w5,w5,w7 - bic w25,w22,w20 - and w26,w21,w20 - ror w27,w24,#27 - eor w5,w5,w13 - add w22,w22,w28 // future e+=K - orr w25,w25,w26 - add w23,w23,w27 // e+=rot(a,5) - eor w5,w5,w19 - ror w20,w20,#2 - add w22,w22,w4 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w5,w5,#31 - eor w6,w6,w8 - bic w25,w21,w24 - and w26,w20,w24 - ror w27,w23,#27 - eor w6,w6,w14 - add w21,w21,w28 // future e+=K - orr w25,w25,w26 - add w22,w22,w27 // e+=rot(a,5) - eor w6,w6,w3 - ror w24,w24,#2 - add w21,w21,w5 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w6,w6,#31 - eor w7,w7,w9 - bic w25,w20,w23 - and w26,w24,w23 - ror w27,w22,#27 - eor w7,w7,w15 - add w20,w20,w28 // future e+=K - orr w25,w25,w26 - add w21,w21,w27 // e+=rot(a,5) - eor w7,w7,w4 - ror w23,w23,#2 - add w20,w20,w6 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w7,w7,#31 - movz w28,#0xeba1 - movk w28,#0x6ed9,lsl#16 - eor w8,w8,w10 - bic w25,w24,w22 - and w26,w23,w22 - ror w27,w21,#27 - eor w8,w8,w16 - add w24,w24,w28 // future e+=K - orr w25,w25,w26 - add w20,w20,w27 // e+=rot(a,5) - eor w8,w8,w5 - ror w22,w22,#2 - add w24,w24,w7 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w8,w8,#31 - eor w9,w9,w11 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w9,w9,w17 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w9,w9,w6 - add w23,w23,w8 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w9,w9,#31 - eor w10,w10,w12 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w10,w10,w19 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w10,w10,w7 - add w22,w22,w9 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w10,w10,#31 - eor w11,w11,w13 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w11,w11,w3 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w11,w11,w8 - add w21,w21,w10 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w11,w11,#31 - eor w12,w12,w14 - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w12,w12,w4 - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - eor w12,w12,w9 - add w20,w20,w11 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w12,w12,#31 - eor w13,w13,w15 - eor w25,w24,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - eor w13,w13,w5 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - eor w13,w13,w10 - add w24,w24,w12 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w13,w13,#31 - eor w14,w14,w16 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w14,w14,w6 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w14,w14,w11 - add w23,w23,w13 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w14,w14,#31 - eor w15,w15,w17 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w15,w15,w7 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w15,w15,w12 - add w22,w22,w14 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w15,w15,#31 - eor w16,w16,w19 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w16,w16,w8 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w16,w16,w13 - add w21,w21,w15 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w16,w16,#31 - eor w17,w17,w3 - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w17,w17,w9 - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - eor w17,w17,w14 - add w20,w20,w16 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w17,w17,#31 - eor w19,w19,w4 - eor w25,w24,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - eor w19,w19,w10 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - eor w19,w19,w15 - add w24,w24,w17 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w19,w19,#31 - eor w3,w3,w5 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w3,w3,w11 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w3,w3,w16 - add w23,w23,w19 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w3,w3,#31 - eor w4,w4,w6 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w4,w4,w12 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w4,w4,w17 - add w22,w22,w3 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w4,w4,#31 - eor w5,w5,w7 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w5,w5,w13 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w5,w5,w19 - add w21,w21,w4 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w5,w5,#31 - eor w6,w6,w8 - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w6,w6,w14 - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - eor w6,w6,w3 - add w20,w20,w5 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w6,w6,#31 - eor w7,w7,w9 - eor w25,w24,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - eor w7,w7,w15 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - eor w7,w7,w4 - add w24,w24,w6 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w7,w7,#31 - eor w8,w8,w10 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w8,w8,w16 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w8,w8,w5 - add w23,w23,w7 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w8,w8,#31 - eor w9,w9,w11 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w9,w9,w17 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w9,w9,w6 - add w22,w22,w8 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w9,w9,#31 - eor w10,w10,w12 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w10,w10,w19 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w10,w10,w7 - add w21,w21,w9 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w10,w10,#31 - eor w11,w11,w13 - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w11,w11,w3 - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - eor w11,w11,w8 - add w20,w20,w10 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w11,w11,#31 - movz w28,#0xbcdc - movk w28,#0x8f1b,lsl#16 - eor w12,w12,w14 - eor w25,w24,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - eor w12,w12,w4 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - eor w12,w12,w9 - add w24,w24,w11 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w12,w12,#31 - orr w25,w21,w22 - and w26,w21,w22 - eor w13,w13,w15 - ror w27,w20,#27 - and w25,w25,w23 - add w23,w23,w28 // future e+=K - eor w13,w13,w5 - add w24,w24,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w21,w21,#2 - eor w13,w13,w10 - add w23,w23,w12 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w13,w13,#31 - orr w25,w20,w21 - and w26,w20,w21 - eor w14,w14,w16 - ror w27,w24,#27 - and w25,w25,w22 - add w22,w22,w28 // future e+=K - eor w14,w14,w6 - add w23,w23,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w20,w20,#2 - eor w14,w14,w11 - add w22,w22,w13 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w14,w14,#31 - orr w25,w24,w20 - and w26,w24,w20 - eor w15,w15,w17 - ror w27,w23,#27 - and w25,w25,w21 - add w21,w21,w28 // future e+=K - eor w15,w15,w7 - add w22,w22,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w24,w24,#2 - eor w15,w15,w12 - add w21,w21,w14 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w15,w15,#31 - orr w25,w23,w24 - and w26,w23,w24 - eor w16,w16,w19 - ror w27,w22,#27 - and w25,w25,w20 - add w20,w20,w28 // future e+=K - eor w16,w16,w8 - add w21,w21,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w23,w23,#2 - eor w16,w16,w13 - add w20,w20,w15 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w16,w16,#31 - orr w25,w22,w23 - and w26,w22,w23 - eor w17,w17,w3 - ror w27,w21,#27 - and w25,w25,w24 - add w24,w24,w28 // future e+=K - eor w17,w17,w9 - add w20,w20,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w22,w22,#2 - eor w17,w17,w14 - add w24,w24,w16 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w17,w17,#31 - orr w25,w21,w22 - and w26,w21,w22 - eor w19,w19,w4 - ror w27,w20,#27 - and w25,w25,w23 - add w23,w23,w28 // future e+=K - eor w19,w19,w10 - add w24,w24,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w21,w21,#2 - eor w19,w19,w15 - add w23,w23,w17 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w19,w19,#31 - orr w25,w20,w21 - and w26,w20,w21 - eor w3,w3,w5 - ror w27,w24,#27 - and w25,w25,w22 - add w22,w22,w28 // future e+=K - eor w3,w3,w11 - add w23,w23,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w20,w20,#2 - eor w3,w3,w16 - add w22,w22,w19 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w3,w3,#31 - orr w25,w24,w20 - and w26,w24,w20 - eor w4,w4,w6 - ror w27,w23,#27 - and w25,w25,w21 - add w21,w21,w28 // future e+=K - eor w4,w4,w12 - add w22,w22,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w24,w24,#2 - eor w4,w4,w17 - add w21,w21,w3 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w4,w4,#31 - orr w25,w23,w24 - and w26,w23,w24 - eor w5,w5,w7 - ror w27,w22,#27 - and w25,w25,w20 - add w20,w20,w28 // future e+=K - eor w5,w5,w13 - add w21,w21,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w23,w23,#2 - eor w5,w5,w19 - add w20,w20,w4 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w5,w5,#31 - orr w25,w22,w23 - and w26,w22,w23 - eor w6,w6,w8 - ror w27,w21,#27 - and w25,w25,w24 - add w24,w24,w28 // future e+=K - eor w6,w6,w14 - add w20,w20,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w22,w22,#2 - eor w6,w6,w3 - add w24,w24,w5 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w6,w6,#31 - orr w25,w21,w22 - and w26,w21,w22 - eor w7,w7,w9 - ror w27,w20,#27 - and w25,w25,w23 - add w23,w23,w28 // future e+=K - eor w7,w7,w15 - add w24,w24,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w21,w21,#2 - eor w7,w7,w4 - add w23,w23,w6 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w7,w7,#31 - orr w25,w20,w21 - and w26,w20,w21 - eor w8,w8,w10 - ror w27,w24,#27 - and w25,w25,w22 - add w22,w22,w28 // future e+=K - eor w8,w8,w16 - add w23,w23,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w20,w20,#2 - eor w8,w8,w5 - add w22,w22,w7 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w8,w8,#31 - orr w25,w24,w20 - and w26,w24,w20 - eor w9,w9,w11 - ror w27,w23,#27 - and w25,w25,w21 - add w21,w21,w28 // future e+=K - eor w9,w9,w17 - add w22,w22,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w24,w24,#2 - eor w9,w9,w6 - add w21,w21,w8 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w9,w9,#31 - orr w25,w23,w24 - and w26,w23,w24 - eor w10,w10,w12 - ror w27,w22,#27 - and w25,w25,w20 - add w20,w20,w28 // future e+=K - eor w10,w10,w19 - add w21,w21,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w23,w23,#2 - eor w10,w10,w7 - add w20,w20,w9 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w10,w10,#31 - orr w25,w22,w23 - and w26,w22,w23 - eor w11,w11,w13 - ror w27,w21,#27 - and w25,w25,w24 - add w24,w24,w28 // future e+=K - eor w11,w11,w3 - add w20,w20,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w22,w22,#2 - eor w11,w11,w8 - add w24,w24,w10 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w11,w11,#31 - orr w25,w21,w22 - and w26,w21,w22 - eor w12,w12,w14 - ror w27,w20,#27 - and w25,w25,w23 - add w23,w23,w28 // future e+=K - eor w12,w12,w4 - add w24,w24,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w21,w21,#2 - eor w12,w12,w9 - add w23,w23,w11 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w12,w12,#31 - orr w25,w20,w21 - and w26,w20,w21 - eor w13,w13,w15 - ror w27,w24,#27 - and w25,w25,w22 - add w22,w22,w28 // future e+=K - eor w13,w13,w5 - add w23,w23,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w20,w20,#2 - eor w13,w13,w10 - add w22,w22,w12 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w13,w13,#31 - orr w25,w24,w20 - and w26,w24,w20 - eor w14,w14,w16 - ror w27,w23,#27 - and w25,w25,w21 - add w21,w21,w28 // future e+=K - eor w14,w14,w6 - add w22,w22,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w24,w24,#2 - eor w14,w14,w11 - add w21,w21,w13 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w14,w14,#31 - orr w25,w23,w24 - and w26,w23,w24 - eor w15,w15,w17 - ror w27,w22,#27 - and w25,w25,w20 - add w20,w20,w28 // future e+=K - eor w15,w15,w7 - add w21,w21,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w23,w23,#2 - eor w15,w15,w12 - add w20,w20,w14 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w15,w15,#31 - movz w28,#0xc1d6 - movk w28,#0xca62,lsl#16 - orr w25,w22,w23 - and w26,w22,w23 - eor w16,w16,w19 - ror w27,w21,#27 - and w25,w25,w24 - add w24,w24,w28 // future e+=K - eor w16,w16,w8 - add w20,w20,w27 // e+=rot(a,5) - orr w25,w25,w26 - ror w22,w22,#2 - eor w16,w16,w13 - add w24,w24,w15 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w16,w16,#31 - eor w17,w17,w3 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w17,w17,w9 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w17,w17,w14 - add w23,w23,w16 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w17,w17,#31 - eor w19,w19,w4 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w19,w19,w10 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w19,w19,w15 - add w22,w22,w17 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w19,w19,#31 - eor w3,w3,w5 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w3,w3,w11 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w3,w3,w16 - add w21,w21,w19 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w3,w3,#31 - eor w4,w4,w6 - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w4,w4,w12 - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - eor w4,w4,w17 - add w20,w20,w3 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w4,w4,#31 - eor w5,w5,w7 - eor w25,w24,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - eor w5,w5,w13 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - eor w5,w5,w19 - add w24,w24,w4 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w5,w5,#31 - eor w6,w6,w8 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w6,w6,w14 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w6,w6,w3 - add w23,w23,w5 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w6,w6,#31 - eor w7,w7,w9 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w7,w7,w15 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w7,w7,w4 - add w22,w22,w6 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w7,w7,#31 - eor w8,w8,w10 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w8,w8,w16 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w8,w8,w5 - add w21,w21,w7 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w8,w8,#31 - eor w9,w9,w11 - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w9,w9,w17 - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - eor w9,w9,w6 - add w20,w20,w8 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w9,w9,#31 - eor w10,w10,w12 - eor w25,w24,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - eor w10,w10,w19 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - eor w10,w10,w7 - add w24,w24,w9 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w10,w10,#31 - eor w11,w11,w13 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w11,w11,w3 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w11,w11,w8 - add w23,w23,w10 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w11,w11,#31 - eor w12,w12,w14 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w12,w12,w4 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w12,w12,w9 - add w22,w22,w11 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w12,w12,#31 - eor w13,w13,w15 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w13,w13,w5 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w13,w13,w10 - add w21,w21,w12 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w13,w13,#31 - eor w14,w14,w16 - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w14,w14,w6 - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - eor w14,w14,w11 - add w20,w20,w13 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ror w14,w14,#31 - eor w15,w15,w17 - eor w25,w24,w22 - ror w27,w21,#27 - add w24,w24,w28 // future e+=K - eor w15,w15,w7 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - eor w15,w15,w12 - add w24,w24,w14 // future e+=X[i] - add w20,w20,w25 // e+=F(b,c,d) - ror w15,w15,#31 - eor w16,w16,w19 - eor w25,w23,w21 - ror w27,w20,#27 - add w23,w23,w28 // future e+=K - eor w16,w16,w8 - eor w25,w25,w22 - add w24,w24,w27 // e+=rot(a,5) - ror w21,w21,#2 - eor w16,w16,w13 - add w23,w23,w15 // future e+=X[i] - add w24,w24,w25 // e+=F(b,c,d) - ror w16,w16,#31 - eor w17,w17,w3 - eor w25,w22,w20 - ror w27,w24,#27 - add w22,w22,w28 // future e+=K - eor w17,w17,w9 - eor w25,w25,w21 - add w23,w23,w27 // e+=rot(a,5) - ror w20,w20,#2 - eor w17,w17,w14 - add w22,w22,w16 // future e+=X[i] - add w23,w23,w25 // e+=F(b,c,d) - ror w17,w17,#31 - eor w19,w19,w4 - eor w25,w21,w24 - ror w27,w23,#27 - add w21,w21,w28 // future e+=K - eor w19,w19,w10 - eor w25,w25,w20 - add w22,w22,w27 // e+=rot(a,5) - ror w24,w24,#2 - eor w19,w19,w15 - add w21,w21,w17 // future e+=X[i] - add w22,w22,w25 // e+=F(b,c,d) - ror w19,w19,#31 - ldp w4,w5,[x0] - eor w25,w20,w23 - ror w27,w22,#27 - add w20,w20,w28 // future e+=K - eor w25,w25,w24 - add w21,w21,w27 // e+=rot(a,5) - ror w23,w23,#2 - add w20,w20,w19 // future e+=X[i] - add w21,w21,w25 // e+=F(b,c,d) - ldp w6,w7,[x0,#8] - eor w25,w24,w22 - ror w27,w21,#27 - eor w25,w25,w23 - add w20,w20,w27 // e+=rot(a,5) - ror w22,w22,#2 - ldr w8,[x0,#16] - add w20,w20,w25 // e+=F(b,c,d) - add w21,w21,w5 - add w22,w22,w6 - add w20,w20,w4 - add w23,w23,w7 - add w24,w24,w8 - stp w20,w21,[x0] - stp w22,w23,[x0,#8] - str w24,[x0,#16] - cbnz x2,.Loop - - ldp x19,x20,[sp,#16] - ldp x21,x22,[sp,#32] - ldp x23,x24,[sp,#48] - ldp x25,x26,[sp,#64] - ldp x27,x28,[sp,#80] - ldr x29,[sp],#96 - ret -.size sha1_block_data_order,.-sha1_block_data_order -.type sha1_block_armv8,%function -.align 6 -sha1_block_armv8: -.Lv8_entry: - stp x29,x30,[sp,#-16]! - add x29,sp,#0 - - adr x4,.Lconst - eor v1.16b,v1.16b,v1.16b - ld1 {v0.4s},[x0],#16 - ld1 {v1.s}[0],[x0] - sub x0,x0,#16 - ld1 {v16.4s-v19.4s},[x4] - -.Loop_hw: - ld1 {v4.16b-v7.16b},[x1],#64 - sub x2,x2,#1 - rev32 v4.16b,v4.16b - rev32 v5.16b,v5.16b - - add v20.4s,v16.4s,v4.4s - rev32 v6.16b,v6.16b - orr v22.16b,v0.16b,v0.16b // offload - - add v21.4s,v16.4s,v5.4s - rev32 v7.16b,v7.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b - .inst 0x5e140020 //sha1c v0.16b,v1.16b,v20.4s // 0 - add v20.4s,v16.4s,v6.4s - .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 1 - .inst 0x5e150060 //sha1c v0.16b,v3.16b,v21.4s - add v21.4s,v16.4s,v7.4s - .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b - .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 2 - .inst 0x5e140040 //sha1c v0.16b,v2.16b,v20.4s - add v20.4s,v16.4s,v4.4s - .inst 0x5e281885 //sha1su1 v5.16b,v4.16b - .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 3 - .inst 0x5e150060 //sha1c v0.16b,v3.16b,v21.4s - add v21.4s,v17.4s,v5.4s - .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b - .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 4 - .inst 0x5e140040 //sha1c v0.16b,v2.16b,v20.4s - add v20.4s,v17.4s,v6.4s - .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b - .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 5 - .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s - add v21.4s,v17.4s,v7.4s - .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b - .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 6 - .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s - add v20.4s,v17.4s,v4.4s - .inst 0x5e281885 //sha1su1 v5.16b,v4.16b - .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 7 - .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s - add v21.4s,v17.4s,v5.4s - .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b - .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 8 - .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s - add v20.4s,v18.4s,v6.4s - .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b - .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 9 - .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s - add v21.4s,v18.4s,v7.4s - .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b - .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 10 - .inst 0x5e142040 //sha1m v0.16b,v2.16b,v20.4s - add v20.4s,v18.4s,v4.4s - .inst 0x5e281885 //sha1su1 v5.16b,v4.16b - .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 11 - .inst 0x5e152060 //sha1m v0.16b,v3.16b,v21.4s - add v21.4s,v18.4s,v5.4s - .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b - .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 12 - .inst 0x5e142040 //sha1m v0.16b,v2.16b,v20.4s - add v20.4s,v18.4s,v6.4s - .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b - .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 13 - .inst 0x5e152060 //sha1m v0.16b,v3.16b,v21.4s - add v21.4s,v19.4s,v7.4s - .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b - .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 14 - .inst 0x5e142040 //sha1m v0.16b,v2.16b,v20.4s - add v20.4s,v19.4s,v4.4s - .inst 0x5e281885 //sha1su1 v5.16b,v4.16b - .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 15 - .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s - add v21.4s,v19.4s,v5.4s - .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b - .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 16 - .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s - add v20.4s,v19.4s,v6.4s - .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 17 - .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s - add v21.4s,v19.4s,v7.4s - - .inst 0x5e280803 //sha1h v3.16b,v0.16b // 18 - .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s - - .inst 0x5e280802 //sha1h v2.16b,v0.16b // 19 - .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s - - add v1.4s,v1.4s,v2.4s - add v0.4s,v0.4s,v22.4s - - cbnz x2,.Loop_hw - - st1 {v0.4s},[x0],#16 - st1 {v1.s}[0],[x0] - - ldr x29,[sp],#16 - ret -.size sha1_block_armv8,.-sha1_block_armv8 -.align 6 -.Lconst: -.long 0x5a827999,0x5a827999,0x5a827999,0x5a827999 //K_00_19 -.long 0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1 //K_20_39 -.long 0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc //K_40_59 -.long 0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6 //K_60_79 -.LOPENSSL_armcap_P: -.quad OPENSSL_armcap_P-. -.asciz "SHA1 block transform for ARMv8, CRYPTOGAMS by <appro@openssl.org>" -.align 2 -.comm OPENSSL_armcap_P,4,4 diff --git a/app/openssl/crypto/sha/asm/sha1-armv8.pl b/app/openssl/crypto/sha/asm/sha1-armv8.pl deleted file mode 100644 index c1f552b6..00000000 --- a/app/openssl/crypto/sha/asm/sha1-armv8.pl +++ /dev/null @@ -1,333 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== -# -# SHA1 for ARMv8. -# -# Performance in cycles per processed byte and improvement coefficient -# over code generated with "default" compiler: -# -# hardware-assisted software(*) -# Apple A7 2.31 4.13 (+14%) -# Cortex-A5x n/a n/a -# -# (*) Software results are presented mostly for reference purposes. - -$flavour = shift; -open STDOUT,">".shift; - -($ctx,$inp,$num)=("x0","x1","x2"); -@Xw=map("w$_",(3..17,19)); -@Xx=map("x$_",(3..17,19)); -@V=($A,$B,$C,$D,$E)=map("w$_",(20..24)); -($t0,$t1,$t2,$K)=map("w$_",(25..28)); - - -sub BODY_00_19 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=($i+2)&15; - -$code.=<<___ if ($i<15 && !($i&1)); - lsr @Xx[$i+1],@Xx[$i],#32 -___ -$code.=<<___ if ($i<14 && !($i&1)); - ldr @Xx[$i+2],[$inp,#`($i+2)*4-64`] -___ -$code.=<<___ if ($i<14 && ($i&1)); -#ifdef __ARMEB__ - ror @Xx[$i+1],@Xx[$i+1],#32 -#else - rev32 @Xx[$i+1],@Xx[$i+1] -#endif -___ -$code.=<<___ if ($i<14); - bic $t0,$d,$b - and $t1,$c,$b - ror $t2,$a,#27 - add $d,$d,$K // future e+=K - orr $t0,$t0,$t1 - add $e,$e,$t2 // e+=rot(a,5) - ror $b,$b,#2 - add $d,$d,@Xw[($i+1)&15] // future e+=X[i] - add $e,$e,$t0 // e+=F(b,c,d) -___ -$code.=<<___ if ($i==19); - movz $K,#0xeba1 - movk $K,#0x6ed9,lsl#16 -___ -$code.=<<___ if ($i>=14); - eor @Xw[$j],@Xw[$j],@Xw[($j+2)&15] - bic $t0,$d,$b - and $t1,$c,$b - ror $t2,$a,#27 - eor @Xw[$j],@Xw[$j],@Xw[($j+8)&15] - add $d,$d,$K // future e+=K - orr $t0,$t0,$t1 - add $e,$e,$t2 // e+=rot(a,5) - eor @Xw[$j],@Xw[$j],@Xw[($j+13)&15] - ror $b,$b,#2 - add $d,$d,@Xw[($i+1)&15] // future e+=X[i] - add $e,$e,$t0 // e+=F(b,c,d) - ror @Xw[$j],@Xw[$j],#31 -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=($i+2)&15; - -$code.=<<___ if ($i==59); - movz $K,#0xc1d6 - movk $K,#0xca62,lsl#16 -___ -$code.=<<___; - orr $t0,$b,$c - and $t1,$b,$c - eor @Xw[$j],@Xw[$j],@Xw[($j+2)&15] - ror $t2,$a,#27 - and $t0,$t0,$d - add $d,$d,$K // future e+=K - eor @Xw[$j],@Xw[$j],@Xw[($j+8)&15] - add $e,$e,$t2 // e+=rot(a,5) - orr $t0,$t0,$t1 - ror $b,$b,#2 - eor @Xw[$j],@Xw[$j],@Xw[($j+13)&15] - add $d,$d,@Xw[($i+1)&15] // future e+=X[i] - add $e,$e,$t0 // e+=F(b,c,d) - ror @Xw[$j],@Xw[$j],#31 -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=($i+2)&15; - -$code.=<<___ if ($i==39); - movz $K,#0xbcdc - movk $K,#0x8f1b,lsl#16 -___ -$code.=<<___ if ($i<78); - eor @Xw[$j],@Xw[$j],@Xw[($j+2)&15] - eor $t0,$d,$b - ror $t2,$a,#27 - add $d,$d,$K // future e+=K - eor @Xw[$j],@Xw[$j],@Xw[($j+8)&15] - eor $t0,$t0,$c - add $e,$e,$t2 // e+=rot(a,5) - ror $b,$b,#2 - eor @Xw[$j],@Xw[$j],@Xw[($j+13)&15] - add $d,$d,@Xw[($i+1)&15] // future e+=X[i] - add $e,$e,$t0 // e+=F(b,c,d) - ror @Xw[$j],@Xw[$j],#31 -___ -$code.=<<___ if ($i==78); - ldp @Xw[1],@Xw[2],[$ctx] - eor $t0,$d,$b - ror $t2,$a,#27 - add $d,$d,$K // future e+=K - eor $t0,$t0,$c - add $e,$e,$t2 // e+=rot(a,5) - ror $b,$b,#2 - add $d,$d,@Xw[($i+1)&15] // future e+=X[i] - add $e,$e,$t0 // e+=F(b,c,d) -___ -$code.=<<___ if ($i==79); - ldp @Xw[3],@Xw[4],[$ctx,#8] - eor $t0,$d,$b - ror $t2,$a,#27 - eor $t0,$t0,$c - add $e,$e,$t2 // e+=rot(a,5) - ror $b,$b,#2 - ldr @Xw[5],[$ctx,#16] - add $e,$e,$t0 // e+=F(b,c,d) -___ -} - -$code.=<<___; -#include "arm_arch.h" - -.text - -.globl sha1_block_data_order -.type sha1_block_data_order,%function -.align 6 -sha1_block_data_order: - ldr x16,.LOPENSSL_armcap_P - adr x17,.LOPENSSL_armcap_P - add x16,x16,x17 - ldr w16,[x16] - tst w16,#ARMV8_SHA1 - b.ne .Lv8_entry - - stp x29,x30,[sp,#-96]! - add x29,sp,#0 - stp x19,x20,[sp,#16] - stp x21,x22,[sp,#32] - stp x23,x24,[sp,#48] - stp x25,x26,[sp,#64] - stp x27,x28,[sp,#80] - - ldp $A,$B,[$ctx] - ldp $C,$D,[$ctx,#8] - ldr $E,[$ctx,#16] - -.Loop: - ldr @Xx[0],[$inp],#64 - movz $K,#0x7999 - sub $num,$num,#1 - movk $K,#0x5a82,lsl#16 -#ifdef __ARMEB__ - ror $Xx[0],@Xx[0],#32 -#else - rev32 @Xx[0],@Xx[0] -#endif - add $E,$E,$K // warm it up - add $E,$E,@Xw[0] -___ -for($i=0;$i<20;$i++) { &BODY_00_19($i,@V); unshift(@V,pop(@V)); } -for(;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -for(;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -for(;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - add $B,$B,@Xw[2] - add $C,$C,@Xw[3] - add $A,$A,@Xw[1] - add $D,$D,@Xw[4] - add $E,$E,@Xw[5] - stp $A,$B,[$ctx] - stp $C,$D,[$ctx,#8] - str $E,[$ctx,#16] - cbnz $num,.Loop - - ldp x19,x20,[sp,#16] - ldp x21,x22,[sp,#32] - ldp x23,x24,[sp,#48] - ldp x25,x26,[sp,#64] - ldp x27,x28,[sp,#80] - ldr x29,[sp],#96 - ret -.size sha1_block_data_order,.-sha1_block_data_order -___ -{{{ -my ($ABCD,$E,$E0,$E1)=map("v$_.16b",(0..3)); -my @MSG=map("v$_.16b",(4..7)); -my @Kxx=map("v$_.4s",(16..19)); -my ($W0,$W1)=("v20.4s","v21.4s"); -my $ABCD_SAVE="v22.16b"; - -$code.=<<___; -.type sha1_block_armv8,%function -.align 6 -sha1_block_armv8: -.Lv8_entry: - stp x29,x30,[sp,#-16]! - add x29,sp,#0 - - adr x4,.Lconst - eor $E,$E,$E - ld1.32 {$ABCD},[$ctx],#16 - ld1.32 {$E}[0],[$ctx] - sub $ctx,$ctx,#16 - ld1.32 {@Kxx[0]-@Kxx[3]},[x4] - -.Loop_hw: - ld1 {@MSG[0]-@MSG[3]},[$inp],#64 - sub $num,$num,#1 - rev32 @MSG[0],@MSG[0] - rev32 @MSG[1],@MSG[1] - - add.i32 $W0,@Kxx[0],@MSG[0] - rev32 @MSG[2],@MSG[2] - orr $ABCD_SAVE,$ABCD,$ABCD // offload - - add.i32 $W1,@Kxx[0],@MSG[1] - rev32 @MSG[3],@MSG[3] - sha1h $E1,$ABCD - sha1c $ABCD,$E,$W0 // 0 - add.i32 $W0,@Kxx[$j],@MSG[2] - sha1su0 @MSG[0],@MSG[1],@MSG[2] -___ -for ($j=0,$i=1;$i<20-3;$i++) { -my $f=("c","p","m","p")[$i/5]; -$code.=<<___; - sha1h $E0,$ABCD // $i - sha1$f $ABCD,$E1,$W1 - add.i32 $W1,@Kxx[$j],@MSG[3] - sha1su1 @MSG[0],@MSG[3] -___ -$code.=<<___ if ($i<20-4); - sha1su0 @MSG[1],@MSG[2],@MSG[3] -___ - ($E0,$E1)=($E1,$E0); ($W0,$W1)=($W1,$W0); - push(@MSG,shift(@MSG)); $j++ if ((($i+3)%5)==0); -} -$code.=<<___; - sha1h $E0,$ABCD // $i - sha1p $ABCD,$E1,$W1 - add.i32 $W1,@Kxx[$j],@MSG[3] - - sha1h $E1,$ABCD // 18 - sha1p $ABCD,$E0,$W0 - - sha1h $E0,$ABCD // 19 - sha1p $ABCD,$E1,$W1 - - add.i32 $E,$E,$E0 - add.i32 $ABCD,$ABCD,$ABCD_SAVE - - cbnz $num,.Loop_hw - - st1.32 {$ABCD},[$ctx],#16 - st1.32 {$E}[0],[$ctx] - - ldr x29,[sp],#16 - ret -.size sha1_block_armv8,.-sha1_block_armv8 -.align 6 -.Lconst: -.long 0x5a827999,0x5a827999,0x5a827999,0x5a827999 //K_00_19 -.long 0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1 //K_20_39 -.long 0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc //K_40_59 -.long 0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6 //K_60_79 -.LOPENSSL_armcap_P: -.quad OPENSSL_armcap_P-. -.asciz "SHA1 block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>" -.align 2 -.comm OPENSSL_armcap_P,4,4 -___ -}}} - -{ my %opcode = ( - "sha1c" => 0x5e000000, "sha1p" => 0x5e001000, - "sha1m" => 0x5e002000, "sha1su0" => 0x5e003000, - "sha1h" => 0x5e280800, "sha1su1" => 0x5e281800 ); - - sub unsha1 { - my ($mnemonic,$arg)=@_; - - $arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)[^,]*(?:,\s*[qv]([0-9]+))?/o - && - sprintf ".inst\t0x%08x\t//%s %s", - $opcode{$mnemonic}|$1|($2<<5)|($3<<16), - $mnemonic,$arg; - } -} - -foreach(split("\n",$code)) { - - s/\`([^\`]*)\`/eval($1)/geo; - - s/\b(sha1\w+)\s+([qv].*)/unsha1($1,$2)/geo; - - s/\.\w?32\b//o and s/\.16b/\.4s/go; - m/(ld|st)1[^\[]+\[0\]/o and s/\.4s/\.s/go; - - print $_,"\n"; -} - -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-ia64.pl b/app/openssl/crypto/sha/asm/sha1-ia64.pl deleted file mode 100644 index 02d35d16..00000000 --- a/app/openssl/crypto/sha/asm/sha1-ia64.pl +++ /dev/null @@ -1,305 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== -# -# Eternal question is what's wrong with compiler generated code? The -# trick is that it's possible to reduce the number of shifts required -# to perform rotations by maintaining copy of 32-bit value in upper -# bits of 64-bit register. Just follow mux2 and shrp instructions... -# Performance under big-endian OS such as HP-UX is 179MBps*1GHz, which -# is >50% better than HP C and >2x better than gcc. - -$code=<<___; -.ident \"sha1-ia64.s, version 1.3\" -.ident \"IA-64 ISA artwork by Andy Polyakov <appro\@fy.chalmers.se>\" -.explicit - -___ - - -if ($^O eq "hpux") { - $ADDP="addp4"; - for (@ARGV) { $ADDP="add" if (/[\+DD|\-mlp]64/); } -} else { $ADDP="add"; } - -#$human=1; -if ($human) { # useful for visual code auditing... - ($A,$B,$C,$D,$E) = ("A","B","C","D","E"); - ($h0,$h1,$h2,$h3,$h4) = ("h0","h1","h2","h3","h4"); - ($K_00_19, $K_20_39, $K_40_59, $K_60_79) = - ( "K_00_19","K_20_39","K_40_59","K_60_79" ); - @X= ( "X0", "X1", "X2", "X3", "X4", "X5", "X6", "X7", - "X8", "X9","X10","X11","X12","X13","X14","X15" ); -} -else { - ($A,$B,$C,$D,$E) = ("loc0","loc1","loc2","loc3","loc4"); - ($h0,$h1,$h2,$h3,$h4) = ("loc5","loc6","loc7","loc8","loc9"); - ($K_00_19, $K_20_39, $K_40_59, $K_60_79) = - ( "r14", "r15", "loc10", "loc11" ); - @X= ( "r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23", - "r24", "r25", "r26", "r27", "r28", "r29", "r30", "r31" ); -} - -sub BODY_00_15 { -local *code=shift; -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -my $Xn=@X[$j%16]; - -$code.=<<___ if ($i==0); -{ .mmi; ld1 $X[$i]=[inp],2 // MSB - ld1 tmp2=[tmp3],2 };; -{ .mmi; ld1 tmp0=[inp],2 - ld1 tmp4=[tmp3],2 // LSB - dep $X[$i]=$X[$i],tmp2,8,8 };; -___ -if ($i<15) { - $code.=<<___; -{ .mmi; ld1 $Xn=[inp],2 // forward Xload - nop.m 0x0 - dep tmp1=tmp0,tmp4,8,8 };; -{ .mmi; ld1 tmp2=[tmp3],2 // forward Xload - and tmp4=$c,$b - dep $X[$i]=$X[$i],tmp1,16,16} //;; -{ .mmi; add $e=$e,$K_00_19 // e+=K_00_19 - andcm tmp1=$d,$b - dep.z tmp5=$a,5,27 };; // a<<5 -{ .mmi; add $e=$e,$X[$i] // e+=Xload - or tmp4=tmp4,tmp1 // F_00_19(b,c,d)=(b&c)|(~b&d) - extr.u tmp1=$a,27,5 };; // a>>27 -{ .mmi; ld1 tmp0=[inp],2 // forward Xload - add $e=$e,tmp4 // e+=F_00_19(b,c,d) - shrp $b=tmp6,tmp6,2 } // b=ROTATE(b,30) -{ .mmi; ld1 tmp4=[tmp3],2 // forward Xload - or tmp5=tmp1,tmp5 // ROTATE(a,5) - mux2 tmp6=$a,0x44 };; // see b in next iteration -{ .mii; add $e=$e,tmp5 // e+=ROTATE(a,5) - dep $Xn=$Xn,tmp2,8,8 // forward Xload - mux2 $X[$i]=$X[$i],0x44 } //;; - -___ - } -else { - $code.=<<___; -{ .mii; and tmp3=$c,$b - dep tmp1=tmp0,tmp4,8,8;; - dep $X[$i]=$X[$i],tmp1,16,16} //;; -{ .mmi; add $e=$e,$K_00_19 // e+=K_00_19 - andcm tmp1=$d,$b - dep.z tmp5=$a,5,27 };; // a<<5 -{ .mmi; add $e=$e,$X[$i] // e+=Xupdate - or tmp4=tmp3,tmp1 // F_00_19(b,c,d)=(b&c)|(~b&d) - extr.u tmp1=$a,27,5 } // a>>27 -{ .mmi; xor $Xn=$Xn,$X[($j+2)%16] // forward Xupdate - xor tmp3=$X[($j+8)%16],$X[($j+13)%16] // forward Xupdate - nop.i 0 };; -{ .mmi; add $e=$e,tmp4 // e+=F_00_19(b,c,d) - xor $Xn=$Xn,tmp3 // forward Xupdate - shrp $b=tmp6,tmp6,2 } // b=ROTATE(b,30) -{ .mmi; or tmp1=tmp1,tmp5 // ROTATE(a,5) - mux2 tmp6=$a,0x44 };; // see b in next iteration -{ .mii; add $e=$e,tmp1 // e+=ROTATE(a,5) - shrp $Xn=$Xn,$Xn,31 // ROTATE(x[0]^x[2]^x[8]^x[13],1) - mux2 $X[$i]=$X[$i],0x44 };; - -___ - } -} - -sub BODY_16_19 { -local *code=shift; -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -my $Xn=@X[$j%16]; - -$code.=<<___; -{ .mib; add $e=$e,$K_00_19 // e+=K_00_19 - dep.z tmp5=$a,5,27 } // a<<5 -{ .mib; andcm tmp1=$d,$b - and tmp0=$c,$b };; -{ .mmi; add $e=$e,$X[$i%16] // e+=Xupdate - or tmp0=tmp0,tmp1 // F_00_19(b,c,d)=(b&c)|(~b&d) - extr.u tmp1=$a,27,5 } // a>>27 -{ .mmi; xor $Xn=$Xn,$X[($j+2)%16] // forward Xupdate - xor tmp3=$X[($j+8)%16],$X[($j+13)%16] // forward Xupdate - nop.i 0 };; -{ .mmi; add $e=$e,tmp0 // f+=F_00_19(b,c,d) - xor $Xn=$Xn,tmp3 // forward Xupdate - shrp $b=tmp6,tmp6,2 } // b=ROTATE(b,30) -{ .mmi; or tmp1=tmp1,tmp5 // ROTATE(a,5) - mux2 tmp6=$a,0x44 };; // see b in next iteration -{ .mii; add $e=$e,tmp1 // e+=ROTATE(a,5) - shrp $Xn=$Xn,$Xn,31 // ROTATE(x[0]^x[2]^x[8]^x[13],1) - nop.i 0 };; - -___ -} - -sub BODY_20_39 { -local *code=shift; -my ($i,$a,$b,$c,$d,$e,$Konst)=@_; - $Konst = $K_20_39 if (!defined($Konst)); -my $j=$i+1; -my $Xn=@X[$j%16]; - -if ($i<79) { -$code.=<<___; -{ .mib; add $e=$e,$Konst // e+=K_XX_XX - dep.z tmp5=$a,5,27 } // a<<5 -{ .mib; xor tmp0=$c,$b - xor $Xn=$Xn,$X[($j+2)%16] };; // forward Xupdate -{ .mib; add $e=$e,$X[$i%16] // e+=Xupdate - extr.u tmp1=$a,27,5 } // a>>27 -{ .mib; xor tmp0=tmp0,$d // F_20_39(b,c,d)=b^c^d - xor $Xn=$Xn,$X[($j+8)%16] };; // forward Xupdate -{ .mmi; add $e=$e,tmp0 // e+=F_20_39(b,c,d) - xor $Xn=$Xn,$X[($j+13)%16] // forward Xupdate - shrp $b=tmp6,tmp6,2 } // b=ROTATE(b,30) -{ .mmi; or tmp1=tmp1,tmp5 // ROTATE(a,5) - mux2 tmp6=$a,0x44 };; // see b in next iteration -{ .mii; add $e=$e,tmp1 // e+=ROTATE(a,5) - shrp $Xn=$Xn,$Xn,31 // ROTATE(x[0]^x[2]^x[8]^x[13],1) - nop.i 0 };; - -___ -} -else { -$code.=<<___; -{ .mib; add $e=$e,$Konst // e+=K_60_79 - dep.z tmp5=$a,5,27 } // a<<5 -{ .mib; xor tmp0=$c,$b - add $h1=$h1,$a };; // wrap up -{ .mib; add $e=$e,$X[$i%16] // e+=Xupdate - extr.u tmp1=$a,27,5 } // a>>27 -{ .mib; xor tmp0=tmp0,$d // F_20_39(b,c,d)=b^c^d - add $h3=$h3,$c };; // wrap up -{ .mmi; add $e=$e,tmp0 // e+=F_20_39(b,c,d) - or tmp1=tmp1,tmp5 // ROTATE(a,5) - shrp $b=tmp6,tmp6,2 };; // b=ROTATE(b,30) ;;? -{ .mmi; add $e=$e,tmp1 // e+=ROTATE(a,5) - add tmp3=1,inp // used in unaligned codepath - add $h4=$h4,$d };; // wrap up - -___ -} -} - -sub BODY_40_59 { -local *code=shift; -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -my $Xn=@X[$j%16]; - -$code.=<<___; -{ .mib; add $e=$e,$K_40_59 // e+=K_40_59 - dep.z tmp5=$a,5,27 } // a<<5 -{ .mib; and tmp1=$c,$d - xor tmp0=$c,$d };; -{ .mmi; add $e=$e,$X[$i%16] // e+=Xupdate - add tmp5=tmp5,tmp1 // a<<5+(c&d) - extr.u tmp1=$a,27,5 } // a>>27 -{ .mmi; and tmp0=tmp0,$b - xor $Xn=$Xn,$X[($j+2)%16] // forward Xupdate - xor tmp3=$X[($j+8)%16],$X[($j+13)%16] };; // forward Xupdate -{ .mmi; add $e=$e,tmp0 // e+=b&(c^d) - add tmp5=tmp5,tmp1 // ROTATE(a,5)+(c&d) - shrp $b=tmp6,tmp6,2 } // b=ROTATE(b,30) -{ .mmi; xor $Xn=$Xn,tmp3 - mux2 tmp6=$a,0x44 };; // see b in next iteration -{ .mii; add $e=$e,tmp5 // e+=ROTATE(a,5)+(c&d) - shrp $Xn=$Xn,$Xn,31 // ROTATE(x[0]^x[2]^x[8]^x[13],1) - nop.i 0x0 };; - -___ -} -sub BODY_60_79 { &BODY_20_39(@_,$K_60_79); } - -$code.=<<___; -.text - -tmp0=r8; -tmp1=r9; -tmp2=r10; -tmp3=r11; -ctx=r32; // in0 -inp=r33; // in1 - -// void sha1_block_data_order(SHA_CTX *c,const void *p,size_t num); -.global sha1_block_data_order# -.proc sha1_block_data_order# -.align 32 -sha1_block_data_order: - .prologue -{ .mmi; alloc tmp1=ar.pfs,3,14,0,0 - $ADDP tmp0=4,ctx - .save ar.lc,r3 - mov r3=ar.lc } -{ .mmi; $ADDP ctx=0,ctx - $ADDP inp=0,inp - mov r2=pr };; -tmp4=in2; -tmp5=loc12; -tmp6=loc13; - .body -{ .mlx; ld4 $h0=[ctx],8 - movl $K_00_19=0x5a827999 } -{ .mlx; ld4 $h1=[tmp0],8 - movl $K_20_39=0x6ed9eba1 };; -{ .mlx; ld4 $h2=[ctx],8 - movl $K_40_59=0x8f1bbcdc } -{ .mlx; ld4 $h3=[tmp0] - movl $K_60_79=0xca62c1d6 };; -{ .mmi; ld4 $h4=[ctx],-16 - add in2=-1,in2 // adjust num for ar.lc - mov ar.ec=1 };; -{ .mmi; nop.m 0 - add tmp3=1,inp - mov ar.lc=in2 };; // brp.loop.imp: too far - -.Ldtop: -{ .mmi; mov $A=$h0 - mov $B=$h1 - mux2 tmp6=$h1,0x44 } -{ .mmi; mov $C=$h2 - mov $D=$h3 - mov $E=$h4 };; - -___ - -{ my $i; - my @V=($A,$B,$C,$D,$E); - - for($i=0;$i<16;$i++) { &BODY_00_15(\$code,$i,@V); unshift(@V,pop(@V)); } - for(;$i<20;$i++) { &BODY_16_19(\$code,$i,@V); unshift(@V,pop(@V)); } - for(;$i<40;$i++) { &BODY_20_39(\$code,$i,@V); unshift(@V,pop(@V)); } - for(;$i<60;$i++) { &BODY_40_59(\$code,$i,@V); unshift(@V,pop(@V)); } - for(;$i<80;$i++) { &BODY_60_79(\$code,$i,@V); unshift(@V,pop(@V)); } - - (($V[0] eq $A) and ($V[4] eq $E)) or die; # double-check -} - -$code.=<<___; -{ .mmb; add $h0=$h0,$A - add $h2=$h2,$C - br.ctop.dptk.many .Ldtop };; -.Ldend: -{ .mmi; add tmp0=4,ctx - mov ar.lc=r3 };; -{ .mmi; st4 [ctx]=$h0,8 - st4 [tmp0]=$h1,8 };; -{ .mmi; st4 [ctx]=$h2,8 - st4 [tmp0]=$h3 };; -{ .mib; st4 [ctx]=$h4,-16 - mov pr=r2,0x1ffff - br.ret.sptk.many b0 };; -.endp sha1_block_data_order# -stringz "SHA1 block transform for IA64, CRYPTOGAMS by <appro\@openssl.org>" -___ - -$output=shift and open STDOUT,">$output"; -print $code; diff --git a/app/openssl/crypto/sha/asm/sha1-mips.S b/app/openssl/crypto/sha/asm/sha1-mips.S deleted file mode 100644 index 865da255..00000000 --- a/app/openssl/crypto/sha/asm/sha1-mips.S +++ /dev/null @@ -1,1664 +0,0 @@ -#ifdef OPENSSL_FIPSCANISTER -# include <openssl/fipssyms.h> -#endif - -.text - -.set noat -.set noreorder -.align 5 -.globl sha1_block_data_order -.ent sha1_block_data_order -sha1_block_data_order: - .frame $29,16*4,$31 - .mask 3237937152,-4 - .set noreorder - sub $29,16*4 - sw $31,(16-1)*4($29) - sw $30,(16-2)*4($29) - sw $23,(16-3)*4($29) - sw $22,(16-4)*4($29) - sw $21,(16-5)*4($29) - sw $20,(16-6)*4($29) - sw $19,(16-7)*4($29) - sw $18,(16-8)*4($29) - sw $17,(16-9)*4($29) - sw $16,(16-10)*4($29) - sll $6,6 - add $6,$5 - sw $6,0($29) - lw $1,0($4) - lw $2,4($4) - lw $3,8($4) - lw $7,12($4) - b .Loop - lw $24,16($4) -.align 4 -.Loop: - .set reorder - lwl $8,3($5) - lui $31,0x5a82 - lwr $8,0($5) - ori $31,0x7999 # K_00_19 - srl $25,$8,24 # byte swap(0) - srl $6,$8,8 - andi $30,$8,0xFF00 - sll $8,$8,24 - andi $6,0xFF00 - sll $30,$30,8 - or $8,$25 - or $6,$30 - or $8,$6 - lwl $9,1*4+3($5) - sll $25,$1,5 # 0 - addu $24,$31 - lwr $9,1*4+0($5) - srl $6,$1,27 - addu $24,$25 - xor $25,$3,$7 - addu $24,$6 - sll $30,$2,30 - and $25,$2 - srl $2,$2,2 - xor $25,$7 - addu $24,$8 - or $2,$30 - addu $24,$25 - srl $25,$9,24 # byte swap(1) - srl $6,$9,8 - andi $30,$9,0xFF00 - sll $9,$9,24 - andi $6,0xFF00 - sll $30,$30,8 - or $9,$25 - or $6,$30 - or $9,$6 - lwl $10,2*4+3($5) - sll $25,$24,5 # 1 - addu $7,$31 - lwr $10,2*4+0($5) - srl $6,$24,27 - addu $7,$25 - xor $25,$2,$3 - addu $7,$6 - sll $30,$1,30 - and $25,$1 - srl $1,$1,2 - xor $25,$3 - addu $7,$9 - or $1,$30 - addu $7,$25 - srl $25,$10,24 # byte swap(2) - srl $6,$10,8 - andi $30,$10,0xFF00 - sll $10,$10,24 - andi $6,0xFF00 - sll $30,$30,8 - or $10,$25 - or $6,$30 - or $10,$6 - lwl $11,3*4+3($5) - sll $25,$7,5 # 2 - addu $3,$31 - lwr $11,3*4+0($5) - srl $6,$7,27 - addu $3,$25 - xor $25,$1,$2 - addu $3,$6 - sll $30,$24,30 - and $25,$24 - srl $24,$24,2 - xor $25,$2 - addu $3,$10 - or $24,$30 - addu $3,$25 - srl $25,$11,24 # byte swap(3) - srl $6,$11,8 - andi $30,$11,0xFF00 - sll $11,$11,24 - andi $6,0xFF00 - sll $30,$30,8 - or $11,$25 - or $6,$30 - or $11,$6 - lwl $12,4*4+3($5) - sll $25,$3,5 # 3 - addu $2,$31 - lwr $12,4*4+0($5) - srl $6,$3,27 - addu $2,$25 - xor $25,$24,$1 - addu $2,$6 - sll $30,$7,30 - and $25,$7 - srl $7,$7,2 - xor $25,$1 - addu $2,$11 - or $7,$30 - addu $2,$25 - srl $25,$12,24 # byte swap(4) - srl $6,$12,8 - andi $30,$12,0xFF00 - sll $12,$12,24 - andi $6,0xFF00 - sll $30,$30,8 - or $12,$25 - or $6,$30 - or $12,$6 - lwl $13,5*4+3($5) - sll $25,$2,5 # 4 - addu $1,$31 - lwr $13,5*4+0($5) - srl $6,$2,27 - addu $1,$25 - xor $25,$7,$24 - addu $1,$6 - sll $30,$3,30 - and $25,$3 - srl $3,$3,2 - xor $25,$24 - addu $1,$12 - or $3,$30 - addu $1,$25 - srl $25,$13,24 # byte swap(5) - srl $6,$13,8 - andi $30,$13,0xFF00 - sll $13,$13,24 - andi $6,0xFF00 - sll $30,$30,8 - or $13,$25 - or $6,$30 - or $13,$6 - lwl $14,6*4+3($5) - sll $25,$1,5 # 5 - addu $24,$31 - lwr $14,6*4+0($5) - srl $6,$1,27 - addu $24,$25 - xor $25,$3,$7 - addu $24,$6 - sll $30,$2,30 - and $25,$2 - srl $2,$2,2 - xor $25,$7 - addu $24,$13 - or $2,$30 - addu $24,$25 - srl $25,$14,24 # byte swap(6) - srl $6,$14,8 - andi $30,$14,0xFF00 - sll $14,$14,24 - andi $6,0xFF00 - sll $30,$30,8 - or $14,$25 - or $6,$30 - or $14,$6 - lwl $15,7*4+3($5) - sll $25,$24,5 # 6 - addu $7,$31 - lwr $15,7*4+0($5) - srl $6,$24,27 - addu $7,$25 - xor $25,$2,$3 - addu $7,$6 - sll $30,$1,30 - and $25,$1 - srl $1,$1,2 - xor $25,$3 - addu $7,$14 - or $1,$30 - addu $7,$25 - srl $25,$15,24 # byte swap(7) - srl $6,$15,8 - andi $30,$15,0xFF00 - sll $15,$15,24 - andi $6,0xFF00 - sll $30,$30,8 - or $15,$25 - or $6,$30 - or $15,$6 - lwl $16,8*4+3($5) - sll $25,$7,5 # 7 - addu $3,$31 - lwr $16,8*4+0($5) - srl $6,$7,27 - addu $3,$25 - xor $25,$1,$2 - addu $3,$6 - sll $30,$24,30 - and $25,$24 - srl $24,$24,2 - xor $25,$2 - addu $3,$15 - or $24,$30 - addu $3,$25 - srl $25,$16,24 # byte swap(8) - srl $6,$16,8 - andi $30,$16,0xFF00 - sll $16,$16,24 - andi $6,0xFF00 - sll $30,$30,8 - or $16,$25 - or $6,$30 - or $16,$6 - lwl $17,9*4+3($5) - sll $25,$3,5 # 8 - addu $2,$31 - lwr $17,9*4+0($5) - srl $6,$3,27 - addu $2,$25 - xor $25,$24,$1 - addu $2,$6 - sll $30,$7,30 - and $25,$7 - srl $7,$7,2 - xor $25,$1 - addu $2,$16 - or $7,$30 - addu $2,$25 - srl $25,$17,24 # byte swap(9) - srl $6,$17,8 - andi $30,$17,0xFF00 - sll $17,$17,24 - andi $6,0xFF00 - sll $30,$30,8 - or $17,$25 - or $6,$30 - or $17,$6 - lwl $18,10*4+3($5) - sll $25,$2,5 # 9 - addu $1,$31 - lwr $18,10*4+0($5) - srl $6,$2,27 - addu $1,$25 - xor $25,$7,$24 - addu $1,$6 - sll $30,$3,30 - and $25,$3 - srl $3,$3,2 - xor $25,$24 - addu $1,$17 - or $3,$30 - addu $1,$25 - srl $25,$18,24 # byte swap(10) - srl $6,$18,8 - andi $30,$18,0xFF00 - sll $18,$18,24 - andi $6,0xFF00 - sll $30,$30,8 - or $18,$25 - or $6,$30 - or $18,$6 - lwl $19,11*4+3($5) - sll $25,$1,5 # 10 - addu $24,$31 - lwr $19,11*4+0($5) - srl $6,$1,27 - addu $24,$25 - xor $25,$3,$7 - addu $24,$6 - sll $30,$2,30 - and $25,$2 - srl $2,$2,2 - xor $25,$7 - addu $24,$18 - or $2,$30 - addu $24,$25 - srl $25,$19,24 # byte swap(11) - srl $6,$19,8 - andi $30,$19,0xFF00 - sll $19,$19,24 - andi $6,0xFF00 - sll $30,$30,8 - or $19,$25 - or $6,$30 - or $19,$6 - lwl $20,12*4+3($5) - sll $25,$24,5 # 11 - addu $7,$31 - lwr $20,12*4+0($5) - srl $6,$24,27 - addu $7,$25 - xor $25,$2,$3 - addu $7,$6 - sll $30,$1,30 - and $25,$1 - srl $1,$1,2 - xor $25,$3 - addu $7,$19 - or $1,$30 - addu $7,$25 - srl $25,$20,24 # byte swap(12) - srl $6,$20,8 - andi $30,$20,0xFF00 - sll $20,$20,24 - andi $6,0xFF00 - sll $30,$30,8 - or $20,$25 - or $6,$30 - or $20,$6 - lwl $21,13*4+3($5) - sll $25,$7,5 # 12 - addu $3,$31 - lwr $21,13*4+0($5) - srl $6,$7,27 - addu $3,$25 - xor $25,$1,$2 - addu $3,$6 - sll $30,$24,30 - and $25,$24 - srl $24,$24,2 - xor $25,$2 - addu $3,$20 - or $24,$30 - addu $3,$25 - srl $25,$21,24 # byte swap(13) - srl $6,$21,8 - andi $30,$21,0xFF00 - sll $21,$21,24 - andi $6,0xFF00 - sll $30,$30,8 - or $21,$25 - or $6,$30 - or $21,$6 - lwl $22,14*4+3($5) - sll $25,$3,5 # 13 - addu $2,$31 - lwr $22,14*4+0($5) - srl $6,$3,27 - addu $2,$25 - xor $25,$24,$1 - addu $2,$6 - sll $30,$7,30 - and $25,$7 - srl $7,$7,2 - xor $25,$1 - addu $2,$21 - or $7,$30 - addu $2,$25 - srl $25,$22,24 # byte swap(14) - srl $6,$22,8 - andi $30,$22,0xFF00 - sll $22,$22,24 - andi $6,0xFF00 - sll $30,$30,8 - or $22,$25 - or $6,$30 - or $22,$6 - lwl $23,15*4+3($5) - sll $25,$2,5 # 14 - addu $1,$31 - lwr $23,15*4+0($5) - srl $6,$2,27 - addu $1,$25 - xor $25,$7,$24 - addu $1,$6 - sll $30,$3,30 - and $25,$3 - srl $3,$3,2 - xor $25,$24 - addu $1,$22 - or $3,$30 - addu $1,$25 - srl $25,$23,24 # byte swap(15) - srl $6,$23,8 - andi $30,$23,0xFF00 - sll $23,$23,24 - andi $6,0xFF00 - sll $30,$30,8 - or $23,$25 - or $23,$6 - or $23,$30 - xor $8,$10 - sll $25,$1,5 # 15 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $8,$16 - xor $25,$3,$7 - addu $24,$6 - xor $8,$21 - sll $30,$2,30 - and $25,$2 - srl $6,$8,31 - addu $8,$8 - srl $2,$2,2 - xor $25,$7 - or $8,$6 - addu $24,$23 - or $2,$30 - addu $24,$25 - xor $9,$11 - sll $25,$24,5 # 16 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $9,$17 - xor $25,$2,$3 - addu $7,$6 - xor $9,$22 - sll $30,$1,30 - and $25,$1 - srl $6,$9,31 - addu $9,$9 - srl $1,$1,2 - xor $25,$3 - or $9,$6 - addu $7,$8 - or $1,$30 - addu $7,$25 - xor $10,$12 - sll $25,$7,5 # 17 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $10,$18 - xor $25,$1,$2 - addu $3,$6 - xor $10,$23 - sll $30,$24,30 - and $25,$24 - srl $6,$10,31 - addu $10,$10 - srl $24,$24,2 - xor $25,$2 - or $10,$6 - addu $3,$9 - or $24,$30 - addu $3,$25 - xor $11,$13 - sll $25,$3,5 # 18 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $11,$19 - xor $25,$24,$1 - addu $2,$6 - xor $11,$8 - sll $30,$7,30 - and $25,$7 - srl $6,$11,31 - addu $11,$11 - srl $7,$7,2 - xor $25,$1 - or $11,$6 - addu $2,$10 - or $7,$30 - addu $2,$25 - xor $12,$14 - sll $25,$2,5 # 19 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $12,$20 - xor $25,$7,$24 - addu $1,$6 - xor $12,$9 - sll $30,$3,30 - and $25,$3 - srl $6,$12,31 - addu $12,$12 - srl $3,$3,2 - xor $25,$24 - or $12,$6 - addu $1,$11 - or $3,$30 - addu $1,$25 - lui $31,0x6ed9 - ori $31,0xeba1 # K_20_39 - xor $13,$15 - sll $25,$1,5 # 20 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $13,$21 - xor $25,$3,$7 - addu $24,$6 - xor $13,$10 - sll $30,$2,30 - xor $25,$2 - srl $6,$13,31 - addu $13,$13 - srl $2,$2,2 - addu $24,$12 - or $13,$6 - or $2,$30 - addu $24,$25 - xor $14,$16 - sll $25,$24,5 # 21 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $14,$22 - xor $25,$2,$3 - addu $7,$6 - xor $14,$11 - sll $30,$1,30 - xor $25,$1 - srl $6,$14,31 - addu $14,$14 - srl $1,$1,2 - addu $7,$13 - or $14,$6 - or $1,$30 - addu $7,$25 - xor $15,$17 - sll $25,$7,5 # 22 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $15,$23 - xor $25,$1,$2 - addu $3,$6 - xor $15,$12 - sll $30,$24,30 - xor $25,$24 - srl $6,$15,31 - addu $15,$15 - srl $24,$24,2 - addu $3,$14 - or $15,$6 - or $24,$30 - addu $3,$25 - xor $16,$18 - sll $25,$3,5 # 23 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $16,$8 - xor $25,$24,$1 - addu $2,$6 - xor $16,$13 - sll $30,$7,30 - xor $25,$7 - srl $6,$16,31 - addu $16,$16 - srl $7,$7,2 - addu $2,$15 - or $16,$6 - or $7,$30 - addu $2,$25 - xor $17,$19 - sll $25,$2,5 # 24 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $17,$9 - xor $25,$7,$24 - addu $1,$6 - xor $17,$14 - sll $30,$3,30 - xor $25,$3 - srl $6,$17,31 - addu $17,$17 - srl $3,$3,2 - addu $1,$16 - or $17,$6 - or $3,$30 - addu $1,$25 - xor $18,$20 - sll $25,$1,5 # 25 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $18,$10 - xor $25,$3,$7 - addu $24,$6 - xor $18,$15 - sll $30,$2,30 - xor $25,$2 - srl $6,$18,31 - addu $18,$18 - srl $2,$2,2 - addu $24,$17 - or $18,$6 - or $2,$30 - addu $24,$25 - xor $19,$21 - sll $25,$24,5 # 26 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $19,$11 - xor $25,$2,$3 - addu $7,$6 - xor $19,$16 - sll $30,$1,30 - xor $25,$1 - srl $6,$19,31 - addu $19,$19 - srl $1,$1,2 - addu $7,$18 - or $19,$6 - or $1,$30 - addu $7,$25 - xor $20,$22 - sll $25,$7,5 # 27 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $20,$12 - xor $25,$1,$2 - addu $3,$6 - xor $20,$17 - sll $30,$24,30 - xor $25,$24 - srl $6,$20,31 - addu $20,$20 - srl $24,$24,2 - addu $3,$19 - or $20,$6 - or $24,$30 - addu $3,$25 - xor $21,$23 - sll $25,$3,5 # 28 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $21,$13 - xor $25,$24,$1 - addu $2,$6 - xor $21,$18 - sll $30,$7,30 - xor $25,$7 - srl $6,$21,31 - addu $21,$21 - srl $7,$7,2 - addu $2,$20 - or $21,$6 - or $7,$30 - addu $2,$25 - xor $22,$8 - sll $25,$2,5 # 29 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $22,$14 - xor $25,$7,$24 - addu $1,$6 - xor $22,$19 - sll $30,$3,30 - xor $25,$3 - srl $6,$22,31 - addu $22,$22 - srl $3,$3,2 - addu $1,$21 - or $22,$6 - or $3,$30 - addu $1,$25 - xor $23,$9 - sll $25,$1,5 # 30 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $23,$15 - xor $25,$3,$7 - addu $24,$6 - xor $23,$20 - sll $30,$2,30 - xor $25,$2 - srl $6,$23,31 - addu $23,$23 - srl $2,$2,2 - addu $24,$22 - or $23,$6 - or $2,$30 - addu $24,$25 - xor $8,$10 - sll $25,$24,5 # 31 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $8,$16 - xor $25,$2,$3 - addu $7,$6 - xor $8,$21 - sll $30,$1,30 - xor $25,$1 - srl $6,$8,31 - addu $8,$8 - srl $1,$1,2 - addu $7,$23 - or $8,$6 - or $1,$30 - addu $7,$25 - xor $9,$11 - sll $25,$7,5 # 32 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $9,$17 - xor $25,$1,$2 - addu $3,$6 - xor $9,$22 - sll $30,$24,30 - xor $25,$24 - srl $6,$9,31 - addu $9,$9 - srl $24,$24,2 - addu $3,$8 - or $9,$6 - or $24,$30 - addu $3,$25 - xor $10,$12 - sll $25,$3,5 # 33 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $10,$18 - xor $25,$24,$1 - addu $2,$6 - xor $10,$23 - sll $30,$7,30 - xor $25,$7 - srl $6,$10,31 - addu $10,$10 - srl $7,$7,2 - addu $2,$9 - or $10,$6 - or $7,$30 - addu $2,$25 - xor $11,$13 - sll $25,$2,5 # 34 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $11,$19 - xor $25,$7,$24 - addu $1,$6 - xor $11,$8 - sll $30,$3,30 - xor $25,$3 - srl $6,$11,31 - addu $11,$11 - srl $3,$3,2 - addu $1,$10 - or $11,$6 - or $3,$30 - addu $1,$25 - xor $12,$14 - sll $25,$1,5 # 35 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $12,$20 - xor $25,$3,$7 - addu $24,$6 - xor $12,$9 - sll $30,$2,30 - xor $25,$2 - srl $6,$12,31 - addu $12,$12 - srl $2,$2,2 - addu $24,$11 - or $12,$6 - or $2,$30 - addu $24,$25 - xor $13,$15 - sll $25,$24,5 # 36 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $13,$21 - xor $25,$2,$3 - addu $7,$6 - xor $13,$10 - sll $30,$1,30 - xor $25,$1 - srl $6,$13,31 - addu $13,$13 - srl $1,$1,2 - addu $7,$12 - or $13,$6 - or $1,$30 - addu $7,$25 - xor $14,$16 - sll $25,$7,5 # 37 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $14,$22 - xor $25,$1,$2 - addu $3,$6 - xor $14,$11 - sll $30,$24,30 - xor $25,$24 - srl $6,$14,31 - addu $14,$14 - srl $24,$24,2 - addu $3,$13 - or $14,$6 - or $24,$30 - addu $3,$25 - xor $15,$17 - sll $25,$3,5 # 38 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $15,$23 - xor $25,$24,$1 - addu $2,$6 - xor $15,$12 - sll $30,$7,30 - xor $25,$7 - srl $6,$15,31 - addu $15,$15 - srl $7,$7,2 - addu $2,$14 - or $15,$6 - or $7,$30 - addu $2,$25 - xor $16,$18 - sll $25,$2,5 # 39 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $16,$8 - xor $25,$7,$24 - addu $1,$6 - xor $16,$13 - sll $30,$3,30 - xor $25,$3 - srl $6,$16,31 - addu $16,$16 - srl $3,$3,2 - addu $1,$15 - or $16,$6 - or $3,$30 - addu $1,$25 - lui $31,0x8f1b - ori $31,0xbcdc # K_40_59 - xor $17,$19 - sll $25,$1,5 # 40 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $17,$9 - and $25,$3,$7 - addu $24,$6 - xor $17,$14 - sll $30,$2,30 - addu $24,$25 - srl $6,$17,31 - xor $25,$3,$7 - addu $17,$17 - and $25,$2 - srl $2,$2,2 - or $17,$6 - addu $24,$16 - or $2,$30 - addu $24,$25 - xor $18,$20 - sll $25,$24,5 # 41 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $18,$10 - and $25,$2,$3 - addu $7,$6 - xor $18,$15 - sll $30,$1,30 - addu $7,$25 - srl $6,$18,31 - xor $25,$2,$3 - addu $18,$18 - and $25,$1 - srl $1,$1,2 - or $18,$6 - addu $7,$17 - or $1,$30 - addu $7,$25 - xor $19,$21 - sll $25,$7,5 # 42 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $19,$11 - and $25,$1,$2 - addu $3,$6 - xor $19,$16 - sll $30,$24,30 - addu $3,$25 - srl $6,$19,31 - xor $25,$1,$2 - addu $19,$19 - and $25,$24 - srl $24,$24,2 - or $19,$6 - addu $3,$18 - or $24,$30 - addu $3,$25 - xor $20,$22 - sll $25,$3,5 # 43 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $20,$12 - and $25,$24,$1 - addu $2,$6 - xor $20,$17 - sll $30,$7,30 - addu $2,$25 - srl $6,$20,31 - xor $25,$24,$1 - addu $20,$20 - and $25,$7 - srl $7,$7,2 - or $20,$6 - addu $2,$19 - or $7,$30 - addu $2,$25 - xor $21,$23 - sll $25,$2,5 # 44 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $21,$13 - and $25,$7,$24 - addu $1,$6 - xor $21,$18 - sll $30,$3,30 - addu $1,$25 - srl $6,$21,31 - xor $25,$7,$24 - addu $21,$21 - and $25,$3 - srl $3,$3,2 - or $21,$6 - addu $1,$20 - or $3,$30 - addu $1,$25 - xor $22,$8 - sll $25,$1,5 # 45 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $22,$14 - and $25,$3,$7 - addu $24,$6 - xor $22,$19 - sll $30,$2,30 - addu $24,$25 - srl $6,$22,31 - xor $25,$3,$7 - addu $22,$22 - and $25,$2 - srl $2,$2,2 - or $22,$6 - addu $24,$21 - or $2,$30 - addu $24,$25 - xor $23,$9 - sll $25,$24,5 # 46 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $23,$15 - and $25,$2,$3 - addu $7,$6 - xor $23,$20 - sll $30,$1,30 - addu $7,$25 - srl $6,$23,31 - xor $25,$2,$3 - addu $23,$23 - and $25,$1 - srl $1,$1,2 - or $23,$6 - addu $7,$22 - or $1,$30 - addu $7,$25 - xor $8,$10 - sll $25,$7,5 # 47 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $8,$16 - and $25,$1,$2 - addu $3,$6 - xor $8,$21 - sll $30,$24,30 - addu $3,$25 - srl $6,$8,31 - xor $25,$1,$2 - addu $8,$8 - and $25,$24 - srl $24,$24,2 - or $8,$6 - addu $3,$23 - or $24,$30 - addu $3,$25 - xor $9,$11 - sll $25,$3,5 # 48 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $9,$17 - and $25,$24,$1 - addu $2,$6 - xor $9,$22 - sll $30,$7,30 - addu $2,$25 - srl $6,$9,31 - xor $25,$24,$1 - addu $9,$9 - and $25,$7 - srl $7,$7,2 - or $9,$6 - addu $2,$8 - or $7,$30 - addu $2,$25 - xor $10,$12 - sll $25,$2,5 # 49 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $10,$18 - and $25,$7,$24 - addu $1,$6 - xor $10,$23 - sll $30,$3,30 - addu $1,$25 - srl $6,$10,31 - xor $25,$7,$24 - addu $10,$10 - and $25,$3 - srl $3,$3,2 - or $10,$6 - addu $1,$9 - or $3,$30 - addu $1,$25 - xor $11,$13 - sll $25,$1,5 # 50 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $11,$19 - and $25,$3,$7 - addu $24,$6 - xor $11,$8 - sll $30,$2,30 - addu $24,$25 - srl $6,$11,31 - xor $25,$3,$7 - addu $11,$11 - and $25,$2 - srl $2,$2,2 - or $11,$6 - addu $24,$10 - or $2,$30 - addu $24,$25 - xor $12,$14 - sll $25,$24,5 # 51 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $12,$20 - and $25,$2,$3 - addu $7,$6 - xor $12,$9 - sll $30,$1,30 - addu $7,$25 - srl $6,$12,31 - xor $25,$2,$3 - addu $12,$12 - and $25,$1 - srl $1,$1,2 - or $12,$6 - addu $7,$11 - or $1,$30 - addu $7,$25 - xor $13,$15 - sll $25,$7,5 # 52 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $13,$21 - and $25,$1,$2 - addu $3,$6 - xor $13,$10 - sll $30,$24,30 - addu $3,$25 - srl $6,$13,31 - xor $25,$1,$2 - addu $13,$13 - and $25,$24 - srl $24,$24,2 - or $13,$6 - addu $3,$12 - or $24,$30 - addu $3,$25 - xor $14,$16 - sll $25,$3,5 # 53 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $14,$22 - and $25,$24,$1 - addu $2,$6 - xor $14,$11 - sll $30,$7,30 - addu $2,$25 - srl $6,$14,31 - xor $25,$24,$1 - addu $14,$14 - and $25,$7 - srl $7,$7,2 - or $14,$6 - addu $2,$13 - or $7,$30 - addu $2,$25 - xor $15,$17 - sll $25,$2,5 # 54 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $15,$23 - and $25,$7,$24 - addu $1,$6 - xor $15,$12 - sll $30,$3,30 - addu $1,$25 - srl $6,$15,31 - xor $25,$7,$24 - addu $15,$15 - and $25,$3 - srl $3,$3,2 - or $15,$6 - addu $1,$14 - or $3,$30 - addu $1,$25 - xor $16,$18 - sll $25,$1,5 # 55 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $16,$8 - and $25,$3,$7 - addu $24,$6 - xor $16,$13 - sll $30,$2,30 - addu $24,$25 - srl $6,$16,31 - xor $25,$3,$7 - addu $16,$16 - and $25,$2 - srl $2,$2,2 - or $16,$6 - addu $24,$15 - or $2,$30 - addu $24,$25 - xor $17,$19 - sll $25,$24,5 # 56 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $17,$9 - and $25,$2,$3 - addu $7,$6 - xor $17,$14 - sll $30,$1,30 - addu $7,$25 - srl $6,$17,31 - xor $25,$2,$3 - addu $17,$17 - and $25,$1 - srl $1,$1,2 - or $17,$6 - addu $7,$16 - or $1,$30 - addu $7,$25 - xor $18,$20 - sll $25,$7,5 # 57 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $18,$10 - and $25,$1,$2 - addu $3,$6 - xor $18,$15 - sll $30,$24,30 - addu $3,$25 - srl $6,$18,31 - xor $25,$1,$2 - addu $18,$18 - and $25,$24 - srl $24,$24,2 - or $18,$6 - addu $3,$17 - or $24,$30 - addu $3,$25 - xor $19,$21 - sll $25,$3,5 # 58 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $19,$11 - and $25,$24,$1 - addu $2,$6 - xor $19,$16 - sll $30,$7,30 - addu $2,$25 - srl $6,$19,31 - xor $25,$24,$1 - addu $19,$19 - and $25,$7 - srl $7,$7,2 - or $19,$6 - addu $2,$18 - or $7,$30 - addu $2,$25 - xor $20,$22 - sll $25,$2,5 # 59 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $20,$12 - and $25,$7,$24 - addu $1,$6 - xor $20,$17 - sll $30,$3,30 - addu $1,$25 - srl $6,$20,31 - xor $25,$7,$24 - addu $20,$20 - and $25,$3 - srl $3,$3,2 - or $20,$6 - addu $1,$19 - or $3,$30 - addu $1,$25 - lui $31,0xca62 - ori $31,0xc1d6 # K_60_79 - xor $21,$23 - sll $25,$1,5 # 60 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $21,$13 - xor $25,$3,$7 - addu $24,$6 - xor $21,$18 - sll $30,$2,30 - xor $25,$2 - srl $6,$21,31 - addu $21,$21 - srl $2,$2,2 - addu $24,$20 - or $21,$6 - or $2,$30 - addu $24,$25 - xor $22,$8 - sll $25,$24,5 # 61 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $22,$14 - xor $25,$2,$3 - addu $7,$6 - xor $22,$19 - sll $30,$1,30 - xor $25,$1 - srl $6,$22,31 - addu $22,$22 - srl $1,$1,2 - addu $7,$21 - or $22,$6 - or $1,$30 - addu $7,$25 - xor $23,$9 - sll $25,$7,5 # 62 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $23,$15 - xor $25,$1,$2 - addu $3,$6 - xor $23,$20 - sll $30,$24,30 - xor $25,$24 - srl $6,$23,31 - addu $23,$23 - srl $24,$24,2 - addu $3,$22 - or $23,$6 - or $24,$30 - addu $3,$25 - xor $8,$10 - sll $25,$3,5 # 63 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $8,$16 - xor $25,$24,$1 - addu $2,$6 - xor $8,$21 - sll $30,$7,30 - xor $25,$7 - srl $6,$8,31 - addu $8,$8 - srl $7,$7,2 - addu $2,$23 - or $8,$6 - or $7,$30 - addu $2,$25 - xor $9,$11 - sll $25,$2,5 # 64 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $9,$17 - xor $25,$7,$24 - addu $1,$6 - xor $9,$22 - sll $30,$3,30 - xor $25,$3 - srl $6,$9,31 - addu $9,$9 - srl $3,$3,2 - addu $1,$8 - or $9,$6 - or $3,$30 - addu $1,$25 - xor $10,$12 - sll $25,$1,5 # 65 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $10,$18 - xor $25,$3,$7 - addu $24,$6 - xor $10,$23 - sll $30,$2,30 - xor $25,$2 - srl $6,$10,31 - addu $10,$10 - srl $2,$2,2 - addu $24,$9 - or $10,$6 - or $2,$30 - addu $24,$25 - xor $11,$13 - sll $25,$24,5 # 66 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $11,$19 - xor $25,$2,$3 - addu $7,$6 - xor $11,$8 - sll $30,$1,30 - xor $25,$1 - srl $6,$11,31 - addu $11,$11 - srl $1,$1,2 - addu $7,$10 - or $11,$6 - or $1,$30 - addu $7,$25 - xor $12,$14 - sll $25,$7,5 # 67 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $12,$20 - xor $25,$1,$2 - addu $3,$6 - xor $12,$9 - sll $30,$24,30 - xor $25,$24 - srl $6,$12,31 - addu $12,$12 - srl $24,$24,2 - addu $3,$11 - or $12,$6 - or $24,$30 - addu $3,$25 - xor $13,$15 - sll $25,$3,5 # 68 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $13,$21 - xor $25,$24,$1 - addu $2,$6 - xor $13,$10 - sll $30,$7,30 - xor $25,$7 - srl $6,$13,31 - addu $13,$13 - srl $7,$7,2 - addu $2,$12 - or $13,$6 - or $7,$30 - addu $2,$25 - xor $14,$16 - sll $25,$2,5 # 69 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $14,$22 - xor $25,$7,$24 - addu $1,$6 - xor $14,$11 - sll $30,$3,30 - xor $25,$3 - srl $6,$14,31 - addu $14,$14 - srl $3,$3,2 - addu $1,$13 - or $14,$6 - or $3,$30 - addu $1,$25 - xor $15,$17 - sll $25,$1,5 # 70 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $15,$23 - xor $25,$3,$7 - addu $24,$6 - xor $15,$12 - sll $30,$2,30 - xor $25,$2 - srl $6,$15,31 - addu $15,$15 - srl $2,$2,2 - addu $24,$14 - or $15,$6 - or $2,$30 - addu $24,$25 - xor $16,$18 - sll $25,$24,5 # 71 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $16,$8 - xor $25,$2,$3 - addu $7,$6 - xor $16,$13 - sll $30,$1,30 - xor $25,$1 - srl $6,$16,31 - addu $16,$16 - srl $1,$1,2 - addu $7,$15 - or $16,$6 - or $1,$30 - addu $7,$25 - xor $17,$19 - sll $25,$7,5 # 72 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $17,$9 - xor $25,$1,$2 - addu $3,$6 - xor $17,$14 - sll $30,$24,30 - xor $25,$24 - srl $6,$17,31 - addu $17,$17 - srl $24,$24,2 - addu $3,$16 - or $17,$6 - or $24,$30 - addu $3,$25 - xor $18,$20 - sll $25,$3,5 # 73 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $18,$10 - xor $25,$24,$1 - addu $2,$6 - xor $18,$15 - sll $30,$7,30 - xor $25,$7 - srl $6,$18,31 - addu $18,$18 - srl $7,$7,2 - addu $2,$17 - or $18,$6 - or $7,$30 - addu $2,$25 - xor $19,$21 - sll $25,$2,5 # 74 - addu $1,$31 - srl $6,$2,27 - addu $1,$25 - xor $19,$11 - xor $25,$7,$24 - addu $1,$6 - xor $19,$16 - sll $30,$3,30 - xor $25,$3 - srl $6,$19,31 - addu $19,$19 - srl $3,$3,2 - addu $1,$18 - or $19,$6 - or $3,$30 - addu $1,$25 - xor $20,$22 - sll $25,$1,5 # 75 - addu $24,$31 - srl $6,$1,27 - addu $24,$25 - xor $20,$12 - xor $25,$3,$7 - addu $24,$6 - xor $20,$17 - sll $30,$2,30 - xor $25,$2 - srl $6,$20,31 - addu $20,$20 - srl $2,$2,2 - addu $24,$19 - or $20,$6 - or $2,$30 - addu $24,$25 - xor $21,$23 - sll $25,$24,5 # 76 - addu $7,$31 - srl $6,$24,27 - addu $7,$25 - xor $21,$13 - xor $25,$2,$3 - addu $7,$6 - xor $21,$18 - sll $30,$1,30 - xor $25,$1 - srl $6,$21,31 - addu $21,$21 - srl $1,$1,2 - addu $7,$20 - or $21,$6 - or $1,$30 - addu $7,$25 - xor $22,$8 - sll $25,$7,5 # 77 - addu $3,$31 - srl $6,$7,27 - addu $3,$25 - xor $22,$14 - xor $25,$1,$2 - addu $3,$6 - xor $22,$19 - sll $30,$24,30 - xor $25,$24 - srl $6,$22,31 - addu $22,$22 - srl $24,$24,2 - addu $3,$21 - or $22,$6 - or $24,$30 - addu $3,$25 - xor $23,$9 - sll $25,$3,5 # 78 - addu $2,$31 - srl $6,$3,27 - addu $2,$25 - xor $23,$15 - xor $25,$24,$1 - addu $2,$6 - xor $23,$20 - sll $30,$7,30 - xor $25,$7 - srl $6,$23,31 - addu $23,$23 - srl $7,$7,2 - addu $2,$22 - or $23,$6 - or $7,$30 - addu $2,$25 - lw $8,0($4) - sll $25,$2,5 # 79 - addu $1,$31 - lw $9,4($4) - srl $6,$2,27 - addu $1,$25 - lw $10,8($4) - xor $25,$7,$24 - addu $1,$6 - lw $11,12($4) - sll $30,$3,30 - xor $25,$3 - lw $12,16($4) - srl $3,$3,2 - addu $1,$23 - or $3,$30 - addu $1,$25 - add $5,64 - lw $6,0($29) - - addu $1,$8 - addu $2,$9 - sw $1,0($4) - addu $3,$10 - addu $7,$11 - sw $2,4($4) - addu $24,$12 - sw $3,8($4) - sw $7,12($4) - sw $24,16($4) - .set noreorder - bne $5,$6,.Loop - nop - - .set noreorder - lw $31,(16-1)*4($29) - lw $30,(16-2)*4($29) - lw $23,(16-3)*4($29) - lw $22,(16-4)*4($29) - lw $21,(16-5)*4($29) - lw $20,(16-6)*4($29) - lw $19,(16-7)*4($29) - lw $18,(16-8)*4($29) - lw $17,(16-9)*4($29) - lw $16,(16-10)*4($29) - jr $31 - add $29,16*4 -.end sha1_block_data_order -.rdata -.asciiz "SHA1 for MIPS, CRYPTOGAMS by <appro@openssl.org>" diff --git a/app/openssl/crypto/sha/asm/sha1-mips.pl b/app/openssl/crypto/sha/asm/sha1-mips.pl deleted file mode 100644 index f1a702f3..00000000 --- a/app/openssl/crypto/sha/asm/sha1-mips.pl +++ /dev/null @@ -1,354 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA1 block procedure for MIPS. - -# Performance improvement is 30% on unaligned input. The "secret" is -# to deploy lwl/lwr pair to load unaligned input. One could have -# vectorized Xupdate on MIPSIII/IV, but the goal was to code MIPS32- -# compatible subroutine. There is room for minor optimization on -# little-endian platforms... - -###################################################################### -# There is a number of MIPS ABI in use, O32 and N32/64 are most -# widely used. Then there is a new contender: NUBI. It appears that if -# one picks the latter, it's possible to arrange code in ABI neutral -# manner. Therefore let's stick to NUBI register layout: -# -($zero,$at,$t0,$t1,$t2)=map("\$$_",(0..2,24,25)); -($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11)); -($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7,$s8,$s9,$s10,$s11)=map("\$$_",(12..23)); -($gp,$tp,$sp,$fp,$ra)=map("\$$_",(3,28..31)); -# -# The return value is placed in $a0. Following coding rules facilitate -# interoperability: -# -# - never ever touch $tp, "thread pointer", former $gp; -# - copy return value to $t0, former $v0 [or to $a0 if you're adapting -# old code]; -# - on O32 populate $a4-$a7 with 'lw $aN,4*N($sp)' if necessary; -# -# For reference here is register layout for N32/64 MIPS ABIs: -# -# ($zero,$at,$v0,$v1)=map("\$$_",(0..3)); -# ($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11)); -# ($t0,$t1,$t2,$t3,$t8,$t9)=map("\$$_",(12..15,24,25)); -# ($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7)=map("\$$_",(16..23)); -# ($gp,$sp,$fp,$ra)=map("\$$_",(28..31)); -# -$flavour = shift; # supported flavours are o32,n32,64,nubi32,nubi64 - -if ($flavour =~ /64|n32/i) { - $PTR_ADD="dadd"; # incidentally works even on n32 - $PTR_SUB="dsub"; # incidentally works even on n32 - $REG_S="sd"; - $REG_L="ld"; - $PTR_SLL="dsll"; # incidentally works even on n32 - $SZREG=8; -} else { - $PTR_ADD="add"; - $PTR_SUB="sub"; - $REG_S="sw"; - $REG_L="lw"; - $PTR_SLL="sll"; - $SZREG=4; -} -# -# <appro@openssl.org> -# -###################################################################### - -$big_endian=(`echo MIPSEL | $ENV{CC} -E -P -`=~/MIPSEL/)?1:0; - -for (@ARGV) { $output=$_ if (/^\w[\w\-]*\.\w+$/); } -open STDOUT,">$output"; - -if (!defined($big_endian)) - { $big_endian=(unpack('L',pack('N',1))==1); } - -# offsets of the Most and Least Significant Bytes -$MSB=$big_endian?0:3; -$LSB=3&~$MSB; - -@X=map("\$$_",(8..23)); # a4-a7,s0-s11 - -$ctx=$a0; -$inp=$a1; -$num=$a2; -$A="\$1"; -$B="\$2"; -$C="\$3"; -$D="\$7"; -$E="\$24"; @V=($A,$B,$C,$D,$E); -$t0="\$25"; -$t1=$num; # $num is offloaded to stack -$t2="\$30"; # fp -$K="\$31"; # ra - -sub BODY_00_14 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if (!$big_endian); - srl $t0,@X[$i],24 # byte swap($i) - srl $t1,@X[$i],8 - andi $t2,@X[$i],0xFF00 - sll @X[$i],@X[$i],24 - andi $t1,0xFF00 - sll $t2,$t2,8 - or @X[$i],$t0 - or $t1,$t2 - or @X[$i],$t1 -___ -$code.=<<___; - lwl @X[$j],$j*4+$MSB($inp) - sll $t0,$a,5 # $i - addu $e,$K - lwr @X[$j],$j*4+$LSB($inp) - srl $t1,$a,27 - addu $e,$t0 - xor $t0,$c,$d - addu $e,$t1 - sll $t2,$b,30 - and $t0,$b - srl $b,$b,2 - xor $t0,$d - addu $e,@X[$i] - or $b,$t2 - addu $e,$t0 -___ -} - -sub BODY_15_19 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; - -$code.=<<___ if (!$big_endian && $i==15); - srl $t0,@X[$i],24 # byte swap($i) - srl $t1,@X[$i],8 - andi $t2,@X[$i],0xFF00 - sll @X[$i],@X[$i],24 - andi $t1,0xFF00 - sll $t2,$t2,8 - or @X[$i],$t0 - or @X[$i],$t1 - or @X[$i],$t2 -___ -$code.=<<___; - xor @X[$j%16],@X[($j+2)%16] - sll $t0,$a,5 # $i - addu $e,$K - srl $t1,$a,27 - addu $e,$t0 - xor @X[$j%16],@X[($j+8)%16] - xor $t0,$c,$d - addu $e,$t1 - xor @X[$j%16],@X[($j+13)%16] - sll $t2,$b,30 - and $t0,$b - srl $t1,@X[$j%16],31 - addu @X[$j%16],@X[$j%16] - srl $b,$b,2 - xor $t0,$d - or @X[$j%16],$t1 - addu $e,@X[$i%16] - or $b,$t2 - addu $e,$t0 -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if ($i<79); - xor @X[$j%16],@X[($j+2)%16] - sll $t0,$a,5 # $i - addu $e,$K - srl $t1,$a,27 - addu $e,$t0 - xor @X[$j%16],@X[($j+8)%16] - xor $t0,$c,$d - addu $e,$t1 - xor @X[$j%16],@X[($j+13)%16] - sll $t2,$b,30 - xor $t0,$b - srl $t1,@X[$j%16],31 - addu @X[$j%16],@X[$j%16] - srl $b,$b,2 - addu $e,@X[$i%16] - or @X[$j%16],$t1 - or $b,$t2 - addu $e,$t0 -___ -$code.=<<___ if ($i==79); - lw @X[0],0($ctx) - sll $t0,$a,5 # $i - addu $e,$K - lw @X[1],4($ctx) - srl $t1,$a,27 - addu $e,$t0 - lw @X[2],8($ctx) - xor $t0,$c,$d - addu $e,$t1 - lw @X[3],12($ctx) - sll $t2,$b,30 - xor $t0,$b - lw @X[4],16($ctx) - srl $b,$b,2 - addu $e,@X[$i%16] - or $b,$t2 - addu $e,$t0 -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if ($i<79); - xor @X[$j%16],@X[($j+2)%16] - sll $t0,$a,5 # $i - addu $e,$K - srl $t1,$a,27 - addu $e,$t0 - xor @X[$j%16],@X[($j+8)%16] - and $t0,$c,$d - addu $e,$t1 - xor @X[$j%16],@X[($j+13)%16] - sll $t2,$b,30 - addu $e,$t0 - srl $t1,@X[$j%16],31 - xor $t0,$c,$d - addu @X[$j%16],@X[$j%16] - and $t0,$b - srl $b,$b,2 - or @X[$j%16],$t1 - addu $e,@X[$i%16] - or $b,$t2 - addu $e,$t0 -___ -} - -$FRAMESIZE=16; # large enough to accomodate NUBI saved registers -$SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? 0xc0fff008 : 0xc0ff0000; - -$code=<<___; -#ifdef OPENSSL_FIPSCANISTER -# include <openssl/fipssyms.h> -#endif - -.text - -.set noat -.set noreorder -.align 5 -.globl sha1_block_data_order -.ent sha1_block_data_order -sha1_block_data_order: - .frame $sp,$FRAMESIZE*$SZREG,$ra - .mask $SAVED_REGS_MASK,-$SZREG - .set noreorder - $PTR_SUB $sp,$FRAMESIZE*$SZREG - $REG_S $ra,($FRAMESIZE-1)*$SZREG($sp) - $REG_S $fp,($FRAMESIZE-2)*$SZREG($sp) - $REG_S $s11,($FRAMESIZE-3)*$SZREG($sp) - $REG_S $s10,($FRAMESIZE-4)*$SZREG($sp) - $REG_S $s9,($FRAMESIZE-5)*$SZREG($sp) - $REG_S $s8,($FRAMESIZE-6)*$SZREG($sp) - $REG_S $s7,($FRAMESIZE-7)*$SZREG($sp) - $REG_S $s6,($FRAMESIZE-8)*$SZREG($sp) - $REG_S $s5,($FRAMESIZE-9)*$SZREG($sp) - $REG_S $s4,($FRAMESIZE-10)*$SZREG($sp) -___ -$code.=<<___ if ($flavour =~ /nubi/i); # optimize non-nubi prologue - $REG_S $s3,($FRAMESIZE-11)*$SZREG($sp) - $REG_S $s2,($FRAMESIZE-12)*$SZREG($sp) - $REG_S $s1,($FRAMESIZE-13)*$SZREG($sp) - $REG_S $s0,($FRAMESIZE-14)*$SZREG($sp) - $REG_S $gp,($FRAMESIZE-15)*$SZREG($sp) -___ -$code.=<<___; - $PTR_SLL $num,6 - $PTR_ADD $num,$inp - $REG_S $num,0($sp) - lw $A,0($ctx) - lw $B,4($ctx) - lw $C,8($ctx) - lw $D,12($ctx) - b .Loop - lw $E,16($ctx) -.align 4 -.Loop: - .set reorder - lwl @X[0],$MSB($inp) - lui $K,0x5a82 - lwr @X[0],$LSB($inp) - ori $K,0x7999 # K_00_19 -___ -for ($i=0;$i<15;$i++) { &BODY_00_14($i,@V); unshift(@V,pop(@V)); } -for (;$i<20;$i++) { &BODY_15_19($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - lui $K,0x6ed9 - ori $K,0xeba1 # K_20_39 -___ -for (;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - lui $K,0x8f1b - ori $K,0xbcdc # K_40_59 -___ -for (;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - lui $K,0xca62 - ori $K,0xc1d6 # K_60_79 -___ -for (;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - $PTR_ADD $inp,64 - $REG_L $num,0($sp) - - addu $A,$X[0] - addu $B,$X[1] - sw $A,0($ctx) - addu $C,$X[2] - addu $D,$X[3] - sw $B,4($ctx) - addu $E,$X[4] - sw $C,8($ctx) - sw $D,12($ctx) - sw $E,16($ctx) - .set noreorder - bne $inp,$num,.Loop - nop - - .set noreorder - $REG_L $ra,($FRAMESIZE-1)*$SZREG($sp) - $REG_L $fp,($FRAMESIZE-2)*$SZREG($sp) - $REG_L $s11,($FRAMESIZE-3)*$SZREG($sp) - $REG_L $s10,($FRAMESIZE-4)*$SZREG($sp) - $REG_L $s9,($FRAMESIZE-5)*$SZREG($sp) - $REG_L $s8,($FRAMESIZE-6)*$SZREG($sp) - $REG_L $s7,($FRAMESIZE-7)*$SZREG($sp) - $REG_L $s6,($FRAMESIZE-8)*$SZREG($sp) - $REG_L $s5,($FRAMESIZE-9)*$SZREG($sp) - $REG_L $s4,($FRAMESIZE-10)*$SZREG($sp) -___ -$code.=<<___ if ($flavour =~ /nubi/i); - $REG_L $s3,($FRAMESIZE-11)*$SZREG($sp) - $REG_L $s2,($FRAMESIZE-12)*$SZREG($sp) - $REG_L $s1,($FRAMESIZE-13)*$SZREG($sp) - $REG_L $s0,($FRAMESIZE-14)*$SZREG($sp) - $REG_L $gp,($FRAMESIZE-15)*$SZREG($sp) -___ -$code.=<<___; - jr $ra - $PTR_ADD $sp,$FRAMESIZE*$SZREG -.end sha1_block_data_order -.rdata -.asciiz "SHA1 for MIPS, CRYPTOGAMS by <appro\@openssl.org>" -___ -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-parisc.pl b/app/openssl/crypto/sha/asm/sha1-parisc.pl deleted file mode 100644 index 6e5a328a..00000000 --- a/app/openssl/crypto/sha/asm/sha1-parisc.pl +++ /dev/null @@ -1,260 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA1 block procedure for PA-RISC. - -# June 2009. -# -# On PA-7100LC performance is >30% better than gcc 3.2 generated code -# for aligned input and >50% better for unaligned. Compared to vendor -# compiler on PA-8600 it's almost 60% faster in 64-bit build and just -# few percent faster in 32-bit one (this for aligned input, data for -# unaligned input is not available). -# -# Special thanks to polarhome.com for providing HP-UX account. - -$flavour = shift; -$output = shift; -open STDOUT,">$output"; - -if ($flavour =~ /64/) { - $LEVEL ="2.0W"; - $SIZE_T =8; - $FRAME_MARKER =80; - $SAVED_RP =16; - $PUSH ="std"; - $PUSHMA ="std,ma"; - $POP ="ldd"; - $POPMB ="ldd,mb"; -} else { - $LEVEL ="1.0"; - $SIZE_T =4; - $FRAME_MARKER =48; - $SAVED_RP =20; - $PUSH ="stw"; - $PUSHMA ="stwm"; - $POP ="ldw"; - $POPMB ="ldwm"; -} - -$FRAME=14*$SIZE_T+$FRAME_MARKER;# 14 saved regs + frame marker - # [+ argument transfer] -$ctx="%r26"; # arg0 -$inp="%r25"; # arg1 -$num="%r24"; # arg2 - -$t0="%r28"; -$t1="%r29"; -$K="%r31"; - -@X=("%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7", "%r8", - "%r9", "%r10","%r11","%r12","%r13","%r14","%r15","%r16",$t0); - -@V=($A,$B,$C,$D,$E)=("%r19","%r20","%r21","%r22","%r23"); - -sub BODY_00_19 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if ($i<15); - addl $K,$e,$e ; $i - shd $a,$a,27,$t1 - addl @X[$i],$e,$e - and $c,$b,$t0 - addl $t1,$e,$e - andcm $d,$b,$t1 - shd $b,$b,2,$b - or $t1,$t0,$t0 - addl $t0,$e,$e -___ -$code.=<<___ if ($i>=15); # with forward Xupdate - addl $K,$e,$e ; $i - shd $a,$a,27,$t1 - xor @X[($j+2)%16],@X[$j%16],@X[$j%16] - addl @X[$i%16],$e,$e - and $c,$b,$t0 - xor @X[($j+8)%16],@X[$j%16],@X[$j%16] - addl $t1,$e,$e - andcm $d,$b,$t1 - shd $b,$b,2,$b - or $t1,$t0,$t0 - xor @X[($j+13)%16],@X[$j%16],@X[$j%16] - add $t0,$e,$e - shd @X[$j%16],@X[$j%16],31,@X[$j%16] -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if ($i<79); - xor @X[($j+2)%16],@X[$j%16],@X[$j%16] ; $i - addl $K,$e,$e - shd $a,$a,27,$t1 - xor @X[($j+8)%16],@X[$j%16],@X[$j%16] - addl @X[$i%16],$e,$e - xor $b,$c,$t0 - xor @X[($j+13)%16],@X[$j%16],@X[$j%16] - addl $t1,$e,$e - shd $b,$b,2,$b - xor $d,$t0,$t0 - shd @X[$j%16],@X[$j%16],31,@X[$j%16] - addl $t0,$e,$e -___ -$code.=<<___ if ($i==79); # with context load - ldw 0($ctx),@X[0] ; $i - addl $K,$e,$e - shd $a,$a,27,$t1 - ldw 4($ctx),@X[1] - addl @X[$i%16],$e,$e - xor $b,$c,$t0 - ldw 8($ctx),@X[2] - addl $t1,$e,$e - shd $b,$b,2,$b - xor $d,$t0,$t0 - ldw 12($ctx),@X[3] - addl $t0,$e,$e - ldw 16($ctx),@X[4] -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___; - shd $a,$a,27,$t1 ; $i - addl $K,$e,$e - xor @X[($j+2)%16],@X[$j%16],@X[$j%16] - xor $d,$c,$t0 - addl @X[$i%16],$e,$e - xor @X[($j+8)%16],@X[$j%16],@X[$j%16] - and $b,$t0,$t0 - addl $t1,$e,$e - shd $b,$b,2,$b - xor @X[($j+13)%16],@X[$j%16],@X[$j%16] - addl $t0,$e,$e - and $d,$c,$t1 - shd @X[$j%16],@X[$j%16],31,@X[$j%16] - addl $t1,$e,$e -___ -} - -$code=<<___; - .LEVEL $LEVEL - .SPACE \$TEXT\$ - .SUBSPA \$CODE\$,QUAD=0,ALIGN=8,ACCESS=0x2C,CODE_ONLY - - .EXPORT sha1_block_data_order,ENTRY,ARGW0=GR,ARGW1=GR,ARGW2=GR -sha1_block_data_order - .PROC - .CALLINFO FRAME=`$FRAME-14*$SIZE_T`,NO_CALLS,SAVE_RP,ENTRY_GR=16 - .ENTRY - $PUSH %r2,-$SAVED_RP(%sp) ; standard prologue - $PUSHMA %r3,$FRAME(%sp) - $PUSH %r4,`-$FRAME+1*$SIZE_T`(%sp) - $PUSH %r5,`-$FRAME+2*$SIZE_T`(%sp) - $PUSH %r6,`-$FRAME+3*$SIZE_T`(%sp) - $PUSH %r7,`-$FRAME+4*$SIZE_T`(%sp) - $PUSH %r8,`-$FRAME+5*$SIZE_T`(%sp) - $PUSH %r9,`-$FRAME+6*$SIZE_T`(%sp) - $PUSH %r10,`-$FRAME+7*$SIZE_T`(%sp) - $PUSH %r11,`-$FRAME+8*$SIZE_T`(%sp) - $PUSH %r12,`-$FRAME+9*$SIZE_T`(%sp) - $PUSH %r13,`-$FRAME+10*$SIZE_T`(%sp) - $PUSH %r14,`-$FRAME+11*$SIZE_T`(%sp) - $PUSH %r15,`-$FRAME+12*$SIZE_T`(%sp) - $PUSH %r16,`-$FRAME+13*$SIZE_T`(%sp) - - ldw 0($ctx),$A - ldw 4($ctx),$B - ldw 8($ctx),$C - ldw 12($ctx),$D - ldw 16($ctx),$E - - extru $inp,31,2,$t0 ; t0=inp&3; - sh3addl $t0,%r0,$t0 ; t0*=8; - subi 32,$t0,$t0 ; t0=32-t0; - mtctl $t0,%cr11 ; %sar=t0; - -L\$oop - ldi 3,$t0 - andcm $inp,$t0,$t0 ; 64-bit neutral -___ - for ($i=0;$i<15;$i++) { # load input block - $code.="\tldw `4*$i`($t0),@X[$i]\n"; } -$code.=<<___; - cmpb,*= $inp,$t0,L\$aligned - ldw 60($t0),@X[15] - ldw 64($t0),@X[16] -___ - for ($i=0;$i<16;$i++) { # align input - $code.="\tvshd @X[$i],@X[$i+1],@X[$i]\n"; } -$code.=<<___; -L\$aligned - ldil L'0x5a827000,$K ; K_00_19 - ldo 0x999($K),$K -___ -for ($i=0;$i<20;$i++) { &BODY_00_19($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - ldil L'0x6ed9e000,$K ; K_20_39 - ldo 0xba1($K),$K -___ - -for (;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - ldil L'0x8f1bb000,$K ; K_40_59 - ldo 0xcdc($K),$K -___ - -for (;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - ldil L'0xca62c000,$K ; K_60_79 - ldo 0x1d6($K),$K -___ -for (;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } - -$code.=<<___; - addl @X[0],$A,$A - addl @X[1],$B,$B - addl @X[2],$C,$C - addl @X[3],$D,$D - addl @X[4],$E,$E - stw $A,0($ctx) - stw $B,4($ctx) - stw $C,8($ctx) - stw $D,12($ctx) - stw $E,16($ctx) - addib,*<> -1,$num,L\$oop - ldo 64($inp),$inp - - $POP `-$FRAME-$SAVED_RP`(%sp),%r2 ; standard epilogue - $POP `-$FRAME+1*$SIZE_T`(%sp),%r4 - $POP `-$FRAME+2*$SIZE_T`(%sp),%r5 - $POP `-$FRAME+3*$SIZE_T`(%sp),%r6 - $POP `-$FRAME+4*$SIZE_T`(%sp),%r7 - $POP `-$FRAME+5*$SIZE_T`(%sp),%r8 - $POP `-$FRAME+6*$SIZE_T`(%sp),%r9 - $POP `-$FRAME+7*$SIZE_T`(%sp),%r10 - $POP `-$FRAME+8*$SIZE_T`(%sp),%r11 - $POP `-$FRAME+9*$SIZE_T`(%sp),%r12 - $POP `-$FRAME+10*$SIZE_T`(%sp),%r13 - $POP `-$FRAME+11*$SIZE_T`(%sp),%r14 - $POP `-$FRAME+12*$SIZE_T`(%sp),%r15 - $POP `-$FRAME+13*$SIZE_T`(%sp),%r16 - bv (%r2) - .EXIT - $POPMB -$FRAME(%sp),%r3 - .PROCEND - .STRINGZ "SHA1 block transform for PA-RISC, CRYPTOGAMS by <appro\@openssl.org>" -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -$code =~ s/,\*/,/gm if ($SIZE_T==4); -$code =~ s/\bbv\b/bve/gm if ($SIZE_T==8); -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-ppc.pl b/app/openssl/crypto/sha/asm/sha1-ppc.pl deleted file mode 100755 index 2140dd2f..00000000 --- a/app/openssl/crypto/sha/asm/sha1-ppc.pl +++ /dev/null @@ -1,326 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# I let hardware handle unaligned input(*), except on page boundaries -# (see below for details). Otherwise straightforward implementation -# with X vector in register bank. The module is big-endian [which is -# not big deal as there're no little-endian targets left around]. -# -# (*) this means that this module is inappropriate for PPC403? Does -# anybody know if pre-POWER3 can sustain unaligned load? - -# -m64 -m32 -# ---------------------------------- -# PPC970,gcc-4.0.0 +76% +59% -# Power6,xlc-7 +68% +33% - -$flavour = shift; - -if ($flavour =~ /64/) { - $SIZE_T =8; - $LRSAVE =2*$SIZE_T; - $UCMP ="cmpld"; - $STU ="stdu"; - $POP ="ld"; - $PUSH ="std"; -} elsif ($flavour =~ /32/) { - $SIZE_T =4; - $LRSAVE =$SIZE_T; - $UCMP ="cmplw"; - $STU ="stwu"; - $POP ="lwz"; - $PUSH ="stw"; -} else { die "nonsense $flavour"; } - -$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; -( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or -( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or -die "can't locate ppc-xlate.pl"; - -open STDOUT,"| $^X $xlate $flavour ".shift || die "can't call $xlate: $!"; - -$FRAME=24*$SIZE_T+64; -$LOCALS=6*$SIZE_T; - -$K ="r0"; -$sp ="r1"; -$toc="r2"; -$ctx="r3"; -$inp="r4"; -$num="r5"; -$t0 ="r15"; -$t1 ="r6"; - -$A ="r7"; -$B ="r8"; -$C ="r9"; -$D ="r10"; -$E ="r11"; -$T ="r12"; - -@V=($A,$B,$C,$D,$E,$T); -@X=("r16","r17","r18","r19","r20","r21","r22","r23", - "r24","r25","r26","r27","r28","r29","r30","r31"); - -sub BODY_00_19 { -my ($i,$a,$b,$c,$d,$e,$f)=@_; -my $j=$i+1; -$code.=<<___ if ($i==0); - lwz @X[$i],`$i*4`($inp) -___ -$code.=<<___ if ($i<15); - lwz @X[$j],`$j*4`($inp) - add $f,$K,$e - rotlwi $e,$a,5 - add $f,$f,@X[$i] - and $t0,$c,$b - add $f,$f,$e - andc $t1,$d,$b - rotlwi $b,$b,30 - or $t0,$t0,$t1 - add $f,$f,$t0 -___ -$code.=<<___ if ($i>=15); - add $f,$K,$e - rotlwi $e,$a,5 - xor @X[$j%16],@X[$j%16],@X[($j+2)%16] - add $f,$f,@X[$i%16] - and $t0,$c,$b - xor @X[$j%16],@X[$j%16],@X[($j+8)%16] - add $f,$f,$e - andc $t1,$d,$b - rotlwi $b,$b,30 - or $t0,$t0,$t1 - xor @X[$j%16],@X[$j%16],@X[($j+13)%16] - add $f,$f,$t0 - rotlwi @X[$j%16],@X[$j%16],1 -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e,$f)=@_; -my $j=$i+1; -$code.=<<___ if ($i<79); - add $f,$K,$e - rotlwi $e,$a,5 - xor @X[$j%16],@X[$j%16],@X[($j+2)%16] - add $f,$f,@X[$i%16] - xor $t0,$b,$c - xor @X[$j%16],@X[$j%16],@X[($j+8)%16] - add $f,$f,$e - rotlwi $b,$b,30 - xor $t0,$t0,$d - xor @X[$j%16],@X[$j%16],@X[($j+13)%16] - add $f,$f,$t0 - rotlwi @X[$j%16],@X[$j%16],1 -___ -$code.=<<___ if ($i==79); - add $f,$K,$e - rotlwi $e,$a,5 - lwz r16,0($ctx) - add $f,$f,@X[$i%16] - xor $t0,$b,$c - lwz r17,4($ctx) - add $f,$f,$e - rotlwi $b,$b,30 - lwz r18,8($ctx) - xor $t0,$t0,$d - lwz r19,12($ctx) - add $f,$f,$t0 - lwz r20,16($ctx) -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e,$f)=@_; -my $j=$i+1; -$code.=<<___; - add $f,$K,$e - rotlwi $e,$a,5 - xor @X[$j%16],@X[$j%16],@X[($j+2)%16] - add $f,$f,@X[$i%16] - and $t0,$b,$c - xor @X[$j%16],@X[$j%16],@X[($j+8)%16] - add $f,$f,$e - or $t1,$b,$c - rotlwi $b,$b,30 - xor @X[$j%16],@X[$j%16],@X[($j+13)%16] - and $t1,$t1,$d - or $t0,$t0,$t1 - rotlwi @X[$j%16],@X[$j%16],1 - add $f,$f,$t0 -___ -} - -$code=<<___; -.machine "any" -.text - -.globl .sha1_block_data_order -.align 4 -.sha1_block_data_order: - $STU $sp,-$FRAME($sp) - mflr r0 - $PUSH r15,`$FRAME-$SIZE_T*17`($sp) - $PUSH r16,`$FRAME-$SIZE_T*16`($sp) - $PUSH r17,`$FRAME-$SIZE_T*15`($sp) - $PUSH r18,`$FRAME-$SIZE_T*14`($sp) - $PUSH r19,`$FRAME-$SIZE_T*13`($sp) - $PUSH r20,`$FRAME-$SIZE_T*12`($sp) - $PUSH r21,`$FRAME-$SIZE_T*11`($sp) - $PUSH r22,`$FRAME-$SIZE_T*10`($sp) - $PUSH r23,`$FRAME-$SIZE_T*9`($sp) - $PUSH r24,`$FRAME-$SIZE_T*8`($sp) - $PUSH r25,`$FRAME-$SIZE_T*7`($sp) - $PUSH r26,`$FRAME-$SIZE_T*6`($sp) - $PUSH r27,`$FRAME-$SIZE_T*5`($sp) - $PUSH r28,`$FRAME-$SIZE_T*4`($sp) - $PUSH r29,`$FRAME-$SIZE_T*3`($sp) - $PUSH r30,`$FRAME-$SIZE_T*2`($sp) - $PUSH r31,`$FRAME-$SIZE_T*1`($sp) - $PUSH r0,`$FRAME+$LRSAVE`($sp) - lwz $A,0($ctx) - lwz $B,4($ctx) - lwz $C,8($ctx) - lwz $D,12($ctx) - lwz $E,16($ctx) - andi. r0,$inp,3 - bne Lunaligned -Laligned: - mtctr $num - bl Lsha1_block_private - b Ldone - -; PowerPC specification allows an implementation to be ill-behaved -; upon unaligned access which crosses page boundary. "Better safe -; than sorry" principle makes me treat it specially. But I don't -; look for particular offending word, but rather for 64-byte input -; block which crosses the boundary. Once found that block is aligned -; and hashed separately... -.align 4 -Lunaligned: - subfic $t1,$inp,4096 - andi. $t1,$t1,4095 ; distance to closest page boundary - srwi. $t1,$t1,6 ; t1/=64 - beq Lcross_page - $UCMP $num,$t1 - ble- Laligned ; didn't cross the page boundary - mtctr $t1 - subfc $num,$t1,$num - bl Lsha1_block_private -Lcross_page: - li $t1,16 - mtctr $t1 - addi r20,$sp,$LOCALS ; spot within the frame -Lmemcpy: - lbz r16,0($inp) - lbz r17,1($inp) - lbz r18,2($inp) - lbz r19,3($inp) - addi $inp,$inp,4 - stb r16,0(r20) - stb r17,1(r20) - stb r18,2(r20) - stb r19,3(r20) - addi r20,r20,4 - bdnz Lmemcpy - - $PUSH $inp,`$FRAME-$SIZE_T*18`($sp) - li $t1,1 - addi $inp,$sp,$LOCALS - mtctr $t1 - bl Lsha1_block_private - $POP $inp,`$FRAME-$SIZE_T*18`($sp) - addic. $num,$num,-1 - bne- Lunaligned - -Ldone: - $POP r0,`$FRAME+$LRSAVE`($sp) - $POP r15,`$FRAME-$SIZE_T*17`($sp) - $POP r16,`$FRAME-$SIZE_T*16`($sp) - $POP r17,`$FRAME-$SIZE_T*15`($sp) - $POP r18,`$FRAME-$SIZE_T*14`($sp) - $POP r19,`$FRAME-$SIZE_T*13`($sp) - $POP r20,`$FRAME-$SIZE_T*12`($sp) - $POP r21,`$FRAME-$SIZE_T*11`($sp) - $POP r22,`$FRAME-$SIZE_T*10`($sp) - $POP r23,`$FRAME-$SIZE_T*9`($sp) - $POP r24,`$FRAME-$SIZE_T*8`($sp) - $POP r25,`$FRAME-$SIZE_T*7`($sp) - $POP r26,`$FRAME-$SIZE_T*6`($sp) - $POP r27,`$FRAME-$SIZE_T*5`($sp) - $POP r28,`$FRAME-$SIZE_T*4`($sp) - $POP r29,`$FRAME-$SIZE_T*3`($sp) - $POP r30,`$FRAME-$SIZE_T*2`($sp) - $POP r31,`$FRAME-$SIZE_T*1`($sp) - mtlr r0 - addi $sp,$sp,$FRAME - blr - .long 0 - .byte 0,12,4,1,0x80,18,3,0 - .long 0 -___ - -# This is private block function, which uses tailored calling -# interface, namely upon entry SHA_CTX is pre-loaded to given -# registers and counter register contains amount of chunks to -# digest... -$code.=<<___; -.align 4 -Lsha1_block_private: -___ -$code.=<<___; # load K_00_19 - lis $K,0x5a82 - ori $K,$K,0x7999 -___ -for($i=0;$i<20;$i++) { &BODY_00_19($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; # load K_20_39 - lis $K,0x6ed9 - ori $K,$K,0xeba1 -___ -for(;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; # load K_40_59 - lis $K,0x8f1b - ori $K,$K,0xbcdc -___ -for(;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; # load K_60_79 - lis $K,0xca62 - ori $K,$K,0xc1d6 -___ -for(;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - add r16,r16,$E - add r17,r17,$T - add r18,r18,$A - add r19,r19,$B - add r20,r20,$C - stw r16,0($ctx) - mr $A,r16 - stw r17,4($ctx) - mr $B,r17 - stw r18,8($ctx) - mr $C,r18 - stw r19,12($ctx) - mr $D,r19 - stw r20,16($ctx) - mr $E,r20 - addi $inp,$inp,`16*4` - bdnz- Lsha1_block_private - blr - .long 0 - .byte 0,12,0x14,0,0,0,0,0 -___ -$code.=<<___; -.asciz "SHA1 block transform for PPC, CRYPTOGAMS by <appro\@fy.chalmers.se>" -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-s390x.pl b/app/openssl/crypto/sha/asm/sha1-s390x.pl deleted file mode 100644 index 9193dda4..00000000 --- a/app/openssl/crypto/sha/asm/sha1-s390x.pl +++ /dev/null @@ -1,246 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA1 block procedure for s390x. - -# April 2007. -# -# Performance is >30% better than gcc 3.3 generated code. But the real -# twist is that SHA1 hardware support is detected and utilized. In -# which case performance can reach further >4.5x for larger chunks. - -# January 2009. -# -# Optimize Xupdate for amount of memory references and reschedule -# instructions to favour dual-issue z10 pipeline. On z10 hardware is -# "only" ~2.3x faster than software. - -# November 2010. -# -# Adapt for -m31 build. If kernel supports what's called "highgprs" -# feature on Linux [see /proc/cpuinfo], it's possible to use 64-bit -# instructions and achieve "64-bit" performance even in 31-bit legacy -# application context. The feature is not specific to any particular -# processor, as long as it's "z-CPU". Latter implies that the code -# remains z/Architecture specific. - -$kimdfunc=1; # magic function code for kimd instruction - -$flavour = shift; - -if ($flavour =~ /3[12]/) { - $SIZE_T=4; - $g=""; -} else { - $SIZE_T=8; - $g="g"; -} - -while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} -open STDOUT,">$output"; - -$K_00_39="%r0"; $K=$K_00_39; -$K_40_79="%r1"; -$ctx="%r2"; $prefetch="%r2"; -$inp="%r3"; -$len="%r4"; - -$A="%r5"; -$B="%r6"; -$C="%r7"; -$D="%r8"; -$E="%r9"; @V=($A,$B,$C,$D,$E); -$t0="%r10"; -$t1="%r11"; -@X=("%r12","%r13","%r14"); -$sp="%r15"; - -$stdframe=16*$SIZE_T+4*8; -$frame=$stdframe+16*4; - -sub Xupdate { -my $i=shift; - -$code.=<<___ if ($i==15); - lg $prefetch,$stdframe($sp) ### Xupdate(16) warm-up - lr $X[0],$X[2] -___ -return if ($i&1); # Xupdate is vectorized and executed every 2nd cycle -$code.=<<___ if ($i<16); - lg $X[0],`$i*4`($inp) ### Xload($i) - rllg $X[1],$X[0],32 -___ -$code.=<<___ if ($i>=16); - xgr $X[0],$prefetch ### Xupdate($i) - lg $prefetch,`$stdframe+4*(($i+2)%16)`($sp) - xg $X[0],`$stdframe+4*(($i+8)%16)`($sp) - xgr $X[0],$prefetch - rll $X[0],$X[0],1 - rllg $X[1],$X[0],32 - rll $X[1],$X[1],1 - rllg $X[0],$X[1],32 - lr $X[2],$X[1] # feedback -___ -$code.=<<___ if ($i<=70); - stg $X[0],`$stdframe+4*($i%16)`($sp) -___ -unshift(@X,pop(@X)); -} - -sub BODY_00_19 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $xi=$X[1]; - - &Xupdate($i); -$code.=<<___; - alr $e,$K ### $i - rll $t1,$a,5 - lr $t0,$d - xr $t0,$c - alr $e,$t1 - nr $t0,$b - alr $e,$xi - xr $t0,$d - rll $b,$b,30 - alr $e,$t0 -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $xi=$X[1]; - - &Xupdate($i); -$code.=<<___; - alr $e,$K ### $i - rll $t1,$a,5 - lr $t0,$b - alr $e,$t1 - xr $t0,$c - alr $e,$xi - xr $t0,$d - rll $b,$b,30 - alr $e,$t0 -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $xi=$X[1]; - - &Xupdate($i); -$code.=<<___; - alr $e,$K ### $i - rll $t1,$a,5 - lr $t0,$b - alr $e,$t1 - or $t0,$c - lr $t1,$b - nr $t0,$d - nr $t1,$c - alr $e,$xi - or $t0,$t1 - rll $b,$b,30 - alr $e,$t0 -___ -} - -$code.=<<___; -.text -.align 64 -.type Ktable,\@object -Ktable: .long 0x5a827999,0x6ed9eba1,0x8f1bbcdc,0xca62c1d6 - .skip 48 #.long 0,0,0,0,0,0,0,0,0,0,0,0 -.size Ktable,.-Ktable -.globl sha1_block_data_order -.type sha1_block_data_order,\@function -sha1_block_data_order: -___ -$code.=<<___ if ($kimdfunc); - larl %r1,OPENSSL_s390xcap_P - lg %r0,0(%r1) - tmhl %r0,0x4000 # check for message-security assist - jz .Lsoftware - lghi %r0,0 - la %r1,`2*$SIZE_T`($sp) - .long 0xb93e0002 # kimd %r0,%r2 - lg %r0,`2*$SIZE_T`($sp) - tmhh %r0,`0x8000>>$kimdfunc` - jz .Lsoftware - lghi %r0,$kimdfunc - lgr %r1,$ctx - lgr %r2,$inp - sllg %r3,$len,6 - .long 0xb93e0002 # kimd %r0,%r2 - brc 1,.-4 # pay attention to "partial completion" - br %r14 -.align 16 -.Lsoftware: -___ -$code.=<<___; - lghi %r1,-$frame - st${g} $ctx,`2*$SIZE_T`($sp) - stm${g} %r6,%r15,`6*$SIZE_T`($sp) - lgr %r0,$sp - la $sp,0(%r1,$sp) - st${g} %r0,0($sp) - - larl $t0,Ktable - llgf $A,0($ctx) - llgf $B,4($ctx) - llgf $C,8($ctx) - llgf $D,12($ctx) - llgf $E,16($ctx) - - lg $K_00_39,0($t0) - lg $K_40_79,8($t0) - -.Lloop: - rllg $K_00_39,$K_00_39,32 -___ -for ($i=0;$i<20;$i++) { &BODY_00_19($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - rllg $K_00_39,$K_00_39,32 -___ -for (;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; $K=$K_40_79; - rllg $K_40_79,$K_40_79,32 -___ -for (;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - rllg $K_40_79,$K_40_79,32 -___ -for (;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - - l${g} $ctx,`$frame+2*$SIZE_T`($sp) - la $inp,64($inp) - al $A,0($ctx) - al $B,4($ctx) - al $C,8($ctx) - al $D,12($ctx) - al $E,16($ctx) - st $A,0($ctx) - st $B,4($ctx) - st $C,8($ctx) - st $D,12($ctx) - st $E,16($ctx) - brct${g} $len,.Lloop - - lm${g} %r6,%r15,`$frame+6*$SIZE_T`($sp) - br %r14 -.size sha1_block_data_order,.-sha1_block_data_order -.string "SHA1 block transform for s390x, CRYPTOGAMS by <appro\@openssl.org>" -.comm OPENSSL_s390xcap_P,16,8 -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; - -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-sparcv9.pl b/app/openssl/crypto/sha/asm/sha1-sparcv9.pl deleted file mode 100644 index 5c161cec..00000000 --- a/app/openssl/crypto/sha/asm/sha1-sparcv9.pl +++ /dev/null @@ -1,284 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# Performance improvement is not really impressive on pre-T1 CPU: +8% -# over Sun C and +25% over gcc [3.3]. While on T1, a.k.a. Niagara, it -# turned to be 40% faster than 64-bit code generated by Sun C 5.8 and -# >2x than 64-bit code generated by gcc 3.4. And there is a gimmick. -# X[16] vector is packed to 8 64-bit registers and as result nothing -# is spilled on stack. In addition input data is loaded in compact -# instruction sequence, thus minimizing the window when the code is -# subject to [inter-thread] cache-thrashing hazard. The goal is to -# ensure scalability on UltraSPARC T1, or rather to avoid decay when -# amount of active threads exceeds the number of physical cores. - -$bits=32; -for (@ARGV) { $bits=64 if (/\-m64/ || /\-xarch\=v9/); } -if ($bits==64) { $bias=2047; $frame=192; } -else { $bias=0; $frame=112; } - -$output=shift; -open STDOUT,">$output"; - -@X=("%o0","%o1","%o2","%o3","%o4","%o5","%g1","%o7"); -$rot1m="%g2"; -$tmp64="%g3"; -$Xi="%g4"; -$A="%l0"; -$B="%l1"; -$C="%l2"; -$D="%l3"; -$E="%l4"; -@V=($A,$B,$C,$D,$E); -$K_00_19="%l5"; -$K_20_39="%l6"; -$K_40_59="%l7"; -$K_60_79="%g5"; -@K=($K_00_19,$K_20_39,$K_40_59,$K_60_79); - -$ctx="%i0"; -$inp="%i1"; -$len="%i2"; -$tmp0="%i3"; -$tmp1="%i4"; -$tmp2="%i5"; - -sub BODY_00_15 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $xi=($i&1)?@X[($i/2)%8]:$Xi; - -$code.=<<___; - sll $a,5,$tmp0 !! $i - add @K[$i/20],$e,$e - srl $a,27,$tmp1 - add $tmp0,$e,$e - and $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - andn $d,$b,$tmp1 - srl $b,2,$b - or $tmp1,$tmp0,$tmp1 - or $tmp2,$b,$b - add $xi,$e,$e -___ -if ($i&1 && $i<15) { - $code.= - " srlx @X[(($i+1)/2)%8],32,$Xi\n"; -} -$code.=<<___; - add $tmp1,$e,$e -___ -} - -sub Xupdate { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i/2; - -if ($i&1) { -$code.=<<___; - sll $a,5,$tmp0 !! $i - add @K[$i/20],$e,$e - srl $a,27,$tmp1 -___ -} else { -$code.=<<___; - sllx @X[($j+6)%8],32,$Xi ! Xupdate($i) - xor @X[($j+1)%8],@X[$j%8],@X[$j%8] - srlx @X[($j+7)%8],32,$tmp1 - xor @X[($j+4)%8],@X[$j%8],@X[$j%8] - sll $a,5,$tmp0 !! $i - or $tmp1,$Xi,$Xi - add @K[$i/20],$e,$e !! - xor $Xi,@X[$j%8],@X[$j%8] - srlx @X[$j%8],31,$Xi - add @X[$j%8],@X[$j%8],@X[$j%8] - and $Xi,$rot1m,$Xi - andn @X[$j%8],$rot1m,@X[$j%8] - srl $a,27,$tmp1 !! - or $Xi,@X[$j%8],@X[$j%8] -___ -} -} - -sub BODY_16_19 { -my ($i,$a,$b,$c,$d,$e)=@_; - - &Xupdate(@_); - if ($i&1) { - $xi=@X[($i/2)%8]; - } else { - $xi=$Xi; - $code.="\tsrlx @X[($i/2)%8],32,$xi\n"; - } -$code.=<<___; - add $tmp0,$e,$e !! - and $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - add $xi,$e,$e - andn $d,$b,$tmp1 - srl $b,2,$b - or $tmp1,$tmp0,$tmp1 - or $tmp2,$b,$b - add $tmp1,$e,$e -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $xi; - &Xupdate(@_); - if ($i&1) { - $xi=@X[($i/2)%8]; - } else { - $xi=$Xi; - $code.="\tsrlx @X[($i/2)%8],32,$xi\n"; - } -$code.=<<___; - add $tmp0,$e,$e !! - xor $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - srl $b,2,$b - add $tmp1,$e,$e - or $tmp2,$b,$b - add $xi,$e,$e -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $xi; - &Xupdate(@_); - if ($i&1) { - $xi=@X[($i/2)%8]; - } else { - $xi=$Xi; - $code.="\tsrlx @X[($i/2)%8],32,$xi\n"; - } -$code.=<<___; - add $tmp0,$e,$e !! - and $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - or $c,$b,$tmp1 - srl $b,2,$b - and $d,$tmp1,$tmp1 - add $xi,$e,$e - or $tmp1,$tmp0,$tmp1 - or $tmp2,$b,$b - add $tmp1,$e,$e -___ -} - -$code.=<<___ if ($bits==64); -.register %g2,#scratch -.register %g3,#scratch -___ -$code.=<<___; -.section ".text",#alloc,#execinstr - -.align 32 -.globl sha1_block_data_order -sha1_block_data_order: - save %sp,-$frame,%sp - sllx $len,6,$len - add $inp,$len,$len - - or %g0,1,$rot1m - sllx $rot1m,32,$rot1m - or $rot1m,1,$rot1m - - ld [$ctx+0],$A - ld [$ctx+4],$B - ld [$ctx+8],$C - ld [$ctx+12],$D - ld [$ctx+16],$E - andn $inp,7,$tmp0 - - sethi %hi(0x5a827999),$K_00_19 - or $K_00_19,%lo(0x5a827999),$K_00_19 - sethi %hi(0x6ed9eba1),$K_20_39 - or $K_20_39,%lo(0x6ed9eba1),$K_20_39 - sethi %hi(0x8f1bbcdc),$K_40_59 - or $K_40_59,%lo(0x8f1bbcdc),$K_40_59 - sethi %hi(0xca62c1d6),$K_60_79 - or $K_60_79,%lo(0xca62c1d6),$K_60_79 - -.Lloop: - ldx [$tmp0+0],@X[0] - ldx [$tmp0+16],@X[2] - ldx [$tmp0+32],@X[4] - ldx [$tmp0+48],@X[6] - and $inp,7,$tmp1 - ldx [$tmp0+8],@X[1] - sll $tmp1,3,$tmp1 - ldx [$tmp0+24],@X[3] - subcc %g0,$tmp1,$tmp2 ! should be 64-$tmp1, but -$tmp1 works too - ldx [$tmp0+40],@X[5] - bz,pt %icc,.Laligned - ldx [$tmp0+56],@X[7] - - sllx @X[0],$tmp1,@X[0] - ldx [$tmp0+64],$tmp64 -___ -for($i=0;$i<7;$i++) -{ $code.=<<___; - srlx @X[$i+1],$tmp2,$Xi - sllx @X[$i+1],$tmp1,@X[$i+1] - or $Xi,@X[$i],@X[$i] -___ -} -$code.=<<___; - srlx $tmp64,$tmp2,$tmp64 - or $tmp64,@X[7],@X[7] -.Laligned: - srlx @X[0],32,$Xi -___ -for ($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); } -for (;$i<20;$i++) { &BODY_16_19($i,@V); unshift(@V,pop(@V)); } -for (;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -for (;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -for (;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - - ld [$ctx+0],@X[0] - ld [$ctx+4],@X[1] - ld [$ctx+8],@X[2] - ld [$ctx+12],@X[3] - add $inp,64,$inp - ld [$ctx+16],@X[4] - cmp $inp,$len - - add $A,@X[0],$A - st $A,[$ctx+0] - add $B,@X[1],$B - st $B,[$ctx+4] - add $C,@X[2],$C - st $C,[$ctx+8] - add $D,@X[3],$D - st $D,[$ctx+12] - add $E,@X[4],$E - st $E,[$ctx+16] - - bne `$bits==64?"%xcc":"%icc"`,.Lloop - andn $inp,7,$tmp0 - - ret - restore -.type sha1_block_data_order,#function -.size sha1_block_data_order,(.-sha1_block_data_order) -.asciz "SHA1 block transform for SPARCv9, CRYPTOGAMS by <appro\@openssl.org>" -.align 4 -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-sparcv9a.pl b/app/openssl/crypto/sha/asm/sha1-sparcv9a.pl deleted file mode 100644 index e65291bb..00000000 --- a/app/openssl/crypto/sha/asm/sha1-sparcv9a.pl +++ /dev/null @@ -1,601 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# January 2009 -# -# Provided that UltraSPARC VIS instructions are pipe-lined(*) and -# pairable(*) with IALU ones, offloading of Xupdate to the UltraSPARC -# Graphic Unit would make it possible to achieve higher instruction- -# level parallelism, ILP, and thus higher performance. It should be -# explicitly noted that ILP is the keyword, and it means that this -# code would be unsuitable for cores like UltraSPARC-Tx. The idea is -# not really novel, Sun had VIS-powered implementation for a while. -# Unlike Sun's implementation this one can process multiple unaligned -# input blocks, and as such works as drop-in replacement for OpenSSL -# sha1_block_data_order. Performance improvement was measured to be -# 40% over pure IALU sha1-sparcv9.pl on UltraSPARC-IIi, but 12% on -# UltraSPARC-III. See below for discussion... -# -# The module does not present direct interest for OpenSSL, because -# it doesn't provide better performance on contemporary SPARCv9 CPUs, -# UltraSPARC-Tx and SPARC64-V[II] to be specific. Those who feel they -# absolutely must score on UltraSPARC-I-IV can simply replace -# crypto/sha/asm/sha1-sparcv9.pl with this module. -# -# (*) "Pipe-lined" means that even if it takes several cycles to -# complete, next instruction using same functional unit [but not -# depending on the result of the current instruction] can start -# execution without having to wait for the unit. "Pairable" -# means that two [or more] independent instructions can be -# issued at the very same time. - -$bits=32; -for (@ARGV) { $bits=64 if (/\-m64/ || /\-xarch\=v9/); } -if ($bits==64) { $bias=2047; $frame=192; } -else { $bias=0; $frame=112; } - -$output=shift; -open STDOUT,">$output"; - -$ctx="%i0"; -$inp="%i1"; -$len="%i2"; -$tmp0="%i3"; -$tmp1="%i4"; -$tmp2="%i5"; -$tmp3="%g5"; - -$base="%g1"; -$align="%g4"; -$Xfer="%o5"; -$nXfer=$tmp3; -$Xi="%o7"; - -$A="%l0"; -$B="%l1"; -$C="%l2"; -$D="%l3"; -$E="%l4"; -@V=($A,$B,$C,$D,$E); - -$Actx="%o0"; -$Bctx="%o1"; -$Cctx="%o2"; -$Dctx="%o3"; -$Ectx="%o4"; - -$fmul="%f32"; -$VK_00_19="%f34"; -$VK_20_39="%f36"; -$VK_40_59="%f38"; -$VK_60_79="%f40"; -@VK=($VK_00_19,$VK_20_39,$VK_40_59,$VK_60_79); -@X=("%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7", - "%f8", "%f9","%f10","%f11","%f12","%f13","%f14","%f15","%f16"); - -# This is reference 2x-parallelized VIS-powered Xupdate procedure. It -# covers even K_NN_MM addition... -sub Xupdate { -my ($i)=@_; -my $K=@VK[($i+16)/20]; -my $j=($i+16)%16; - -# [ provided that GSR.alignaddr_offset is 5, $mul contains -# 0x100ULL<<32|0x100 value and K_NN_MM are pre-loaded to -# chosen registers... ] -$code.=<<___; - fxors @X[($j+13)%16],@X[$j],@X[$j] !-1/-1/-1:X[0]^=X[13] - fxors @X[($j+14)%16],@X[$j+1],@X[$j+1]! 0/ 0/ 0:X[1]^=X[14] - fxor @X[($j+2)%16],@X[($j+8)%16],%f18! 1/ 1/ 1:Tmp=X[2,3]^X[8,9] - fxor %f18,@X[$j],@X[$j] ! 2/ 4/ 3:X[0,1]^=X[2,3]^X[8,9] - faligndata @X[$j],@X[$j],%f18 ! 3/ 7/ 5:Tmp=X[0,1]>>>24 - fpadd32 @X[$j],@X[$j],@X[$j] ! 4/ 8/ 6:X[0,1]<<=1 - fmul8ulx16 %f18,$fmul,%f18 ! 5/10/ 7:Tmp>>=7, Tmp&=1 - ![fxors %f15,%f2,%f2] - for %f18,@X[$j],@X[$j] ! 8/14/10:X[0,1]|=Tmp - ![fxors %f0,%f3,%f3] !10/17/12:X[0] dependency - fpadd32 $K,@X[$j],%f20 - std %f20,[$Xfer+`4*$j`] -___ -# The numbers delimited with slash are the earliest possible dispatch -# cycles for given instruction assuming 1 cycle latency for simple VIS -# instructions, such as on UltraSPARC-I&II, 3 cycles latency, such as -# on UltraSPARC-III&IV, and 2 cycles latency(*), respectively. Being -# 2x-parallelized the procedure is "worth" 5, 8.5 or 6 ticks per SHA1 -# round. As [long as] FPU/VIS instructions are perfectly pairable with -# IALU ones, the round timing is defined by the maximum between VIS -# and IALU timings. The latter varies from round to round and averages -# out at 6.25 ticks. This means that USI&II should operate at IALU -# rate, while USIII&IV - at VIS rate. This explains why performance -# improvement varies among processors. Well, given that pure IALU -# sha1-sparcv9.pl module exhibits virtually uniform performance of -# ~9.3 cycles per SHA1 round. Timings mentioned above are theoretical -# lower limits. Real-life performance was measured to be 6.6 cycles -# per SHA1 round on USIIi and 8.3 on USIII. The latter is lower than -# half-round VIS timing, because there are 16 Xupdate-free rounds, -# which "push down" average theoretical timing to 8 cycles... - -# (*) SPARC64-V[II] was originally believed to have 2 cycles VIS -# latency. Well, it might have, but it doesn't have dedicated -# VIS-unit. Instead, VIS instructions are executed by other -# functional units, ones used here - by IALU. This doesn't -# improve effective ILP... -} - -# The reference Xupdate procedure is then "strained" over *pairs* of -# BODY_NN_MM and kind of modulo-scheduled in respect to X[n]^=X[n+13] -# and K_NN_MM addition. It's "running" 15 rounds ahead, which leaves -# plenty of room to amortize for read-after-write hazard, as well as -# to fetch and align input for the next spin. The VIS instructions are -# scheduled for latency of 2 cycles, because there are not enough IALU -# instructions to schedule for latency of 3, while scheduling for 1 -# would give no gain on USI&II anyway. - -sub BODY_00_19 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i&~1; -my $k=($j+16+2)%16; # ahead reference -my $l=($j+16-2)%16; # behind reference -my $K=@VK[($j+16-2)/20]; - -$j=($j+16)%16; - -$code.=<<___ if (!($i&1)); - sll $a,5,$tmp0 !! $i - and $c,$b,$tmp3 - ld [$Xfer+`4*($i%16)`],$Xi - fxors @X[($j+14)%16],@X[$j+1],@X[$j+1]! 0/ 0/ 0:X[1]^=X[14] - srl $a,27,$tmp1 - add $tmp0,$e,$e - fxor @X[($j+2)%16],@X[($j+8)%16],%f18! 1/ 1/ 1:Tmp=X[2,3]^X[8,9] - sll $b,30,$tmp2 - add $tmp1,$e,$e - andn $d,$b,$tmp1 - add $Xi,$e,$e - fxor %f18,@X[$j],@X[$j] ! 2/ 4/ 3:X[0,1]^=X[2,3]^X[8,9] - srl $b,2,$b - or $tmp1,$tmp3,$tmp1 - or $tmp2,$b,$b - add $tmp1,$e,$e - faligndata @X[$j],@X[$j],%f18 ! 3/ 7/ 5:Tmp=X[0,1]>>>24 -___ -$code.=<<___ if ($i&1); - sll $a,5,$tmp0 !! $i - and $c,$b,$tmp3 - ld [$Xfer+`4*($i%16)`],$Xi - fpadd32 @X[$j],@X[$j],@X[$j] ! 4/ 8/ 6:X[0,1]<<=1 - srl $a,27,$tmp1 - add $tmp0,$e,$e - fmul8ulx16 %f18,$fmul,%f18 ! 5/10/ 7:Tmp>>=7, Tmp&=1 - sll $b,30,$tmp2 - add $tmp1,$e,$e - fpadd32 $K,@X[$l],%f20 ! - andn $d,$b,$tmp1 - add $Xi,$e,$e - fxors @X[($k+13)%16],@X[$k],@X[$k] !-1/-1/-1:X[0]^=X[13] - srl $b,2,$b - or $tmp1,$tmp3,$tmp1 - fxor %f18,@X[$j],@X[$j] ! 8/14/10:X[0,1]|=Tmp - or $tmp2,$b,$b - add $tmp1,$e,$e -___ -$code.=<<___ if ($i&1 && $i>=2); - std %f20,[$Xfer+`4*$l`] ! -___ -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i&~1; -my $k=($j+16+2)%16; # ahead reference -my $l=($j+16-2)%16; # behind reference -my $K=@VK[($j+16-2)/20]; - -$j=($j+16)%16; - -$code.=<<___ if (!($i&1) && $i<64); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - fxors @X[($j+14)%16],@X[$j+1],@X[$j+1]! 0/ 0/ 0:X[1]^=X[14] - srl $a,27,$tmp1 - add $tmp0,$e,$e - fxor @X[($j+2)%16],@X[($j+8)%16],%f18! 1/ 1/ 1:Tmp=X[2,3]^X[8,9] - xor $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - fxor %f18,@X[$j],@X[$j] ! 2/ 4/ 3:X[0,1]^=X[2,3]^X[8,9] - srl $b,2,$b - add $tmp1,$e,$e - or $tmp2,$b,$b - add $Xi,$e,$e - faligndata @X[$j],@X[$j],%f18 ! 3/ 7/ 5:Tmp=X[0,1]>>>24 -___ -$code.=<<___ if ($i&1 && $i<64); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - fpadd32 @X[$j],@X[$j],@X[$j] ! 4/ 8/ 6:X[0,1]<<=1 - srl $a,27,$tmp1 - add $tmp0,$e,$e - fmul8ulx16 %f18,$fmul,%f18 ! 5/10/ 7:Tmp>>=7, Tmp&=1 - xor $c,$b,$tmp0 - add $tmp1,$e,$e - fpadd32 $K,@X[$l],%f20 ! - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - fxors @X[($k+13)%16],@X[$k],@X[$k] !-1/-1/-1:X[0]^=X[13] - srl $b,2,$b - add $tmp1,$e,$e - fxor %f18,@X[$j],@X[$j] ! 8/14/10:X[0,1]|=Tmp - or $tmp2,$b,$b - add $Xi,$e,$e - std %f20,[$Xfer+`4*$l`] ! -___ -$code.=<<___ if ($i==64); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - fpadd32 $K,@X[$l],%f20 - srl $a,27,$tmp1 - add $tmp0,$e,$e - xor $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - std %f20,[$Xfer+`4*$l`] - srl $b,2,$b - add $tmp1,$e,$e - or $tmp2,$b,$b - add $Xi,$e,$e -___ -$code.=<<___ if ($i>64); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - srl $a,27,$tmp1 - add $tmp0,$e,$e - xor $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - srl $b,2,$b - add $tmp1,$e,$e - or $tmp2,$b,$b - add $Xi,$e,$e -___ -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i&~1; -my $k=($j+16+2)%16; # ahead reference -my $l=($j+16-2)%16; # behind reference -my $K=@VK[($j+16-2)/20]; - -$j=($j+16)%16; - -$code.=<<___ if (!($i&1)); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - fxors @X[($j+14)%16],@X[$j+1],@X[$j+1]! 0/ 0/ 0:X[1]^=X[14] - srl $a,27,$tmp1 - add $tmp0,$e,$e - fxor @X[($j+2)%16],@X[($j+8)%16],%f18! 1/ 1/ 1:Tmp=X[2,3]^X[8,9] - and $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - or $c,$b,$tmp1 - fxor %f18,@X[$j],@X[$j] ! 2/ 4/ 3:X[0,1]^=X[2,3]^X[8,9] - srl $b,2,$b - and $d,$tmp1,$tmp1 - add $Xi,$e,$e - or $tmp1,$tmp0,$tmp1 - faligndata @X[$j],@X[$j],%f18 ! 3/ 7/ 5:Tmp=X[0,1]>>>24 - or $tmp2,$b,$b - add $tmp1,$e,$e - fpadd32 @X[$j],@X[$j],@X[$j] ! 4/ 8/ 6:X[0,1]<<=1 -___ -$code.=<<___ if ($i&1); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - srl $a,27,$tmp1 - add $tmp0,$e,$e - fmul8ulx16 %f18,$fmul,%f18 ! 5/10/ 7:Tmp>>=7, Tmp&=1 - and $c,$b,$tmp0 - add $tmp1,$e,$e - fpadd32 $K,@X[$l],%f20 ! - sll $b,30,$tmp2 - or $c,$b,$tmp1 - fxors @X[($k+13)%16],@X[$k],@X[$k] !-1/-1/-1:X[0]^=X[13] - srl $b,2,$b - and $d,$tmp1,$tmp1 - fxor %f18,@X[$j],@X[$j] ! 8/14/10:X[0,1]|=Tmp - add $Xi,$e,$e - or $tmp1,$tmp0,$tmp1 - or $tmp2,$b,$b - add $tmp1,$e,$e - std %f20,[$Xfer+`4*$l`] ! -___ -} - -# If there is more data to process, then we pre-fetch the data for -# next iteration in last ten rounds... -sub BODY_70_79 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i&~1; -my $m=($i%8)*2; - -$j=($j+16)%16; - -$code.=<<___ if ($i==70); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - srl $a,27,$tmp1 - add $tmp0,$e,$e - ldd [$inp+64],@X[0] - xor $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - srl $b,2,$b - add $tmp1,$e,$e - or $tmp2,$b,$b - add $Xi,$e,$e - - and $inp,-64,$nXfer - inc 64,$inp - and $nXfer,255,$nXfer - alignaddr %g0,$align,%g0 - add $base,$nXfer,$nXfer -___ -$code.=<<___ if ($i==71); - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - srl $a,27,$tmp1 - add $tmp0,$e,$e - xor $c,$b,$tmp0 - add $tmp1,$e,$e - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - srl $b,2,$b - add $tmp1,$e,$e - or $tmp2,$b,$b - add $Xi,$e,$e -___ -$code.=<<___ if ($i>=72); - faligndata @X[$m],@X[$m+2],@X[$m] - sll $a,5,$tmp0 !! $i - ld [$Xfer+`4*($i%16)`],$Xi - srl $a,27,$tmp1 - add $tmp0,$e,$e - xor $c,$b,$tmp0 - add $tmp1,$e,$e - fpadd32 $VK_00_19,@X[$m],%f20 - sll $b,30,$tmp2 - xor $d,$tmp0,$tmp1 - srl $b,2,$b - add $tmp1,$e,$e - or $tmp2,$b,$b - add $Xi,$e,$e -___ -$code.=<<___ if ($i<77); - ldd [$inp+`8*($i+1-70)`],@X[2*($i+1-70)] -___ -$code.=<<___ if ($i==77); # redundant if $inp was aligned - add $align,63,$tmp0 - and $tmp0,-8,$tmp0 - ldd [$inp+$tmp0],@X[16] -___ -$code.=<<___ if ($i>=72); - std %f20,[$nXfer+`4*$m`] -___ -} - -$code.=<<___; -.section ".text",#alloc,#execinstr - -.align 64 -vis_const: -.long 0x5a827999,0x5a827999 ! K_00_19 -.long 0x6ed9eba1,0x6ed9eba1 ! K_20_39 -.long 0x8f1bbcdc,0x8f1bbcdc ! K_40_59 -.long 0xca62c1d6,0xca62c1d6 ! K_60_79 -.long 0x00000100,0x00000100 -.align 64 -.type vis_const,#object -.size vis_const,(.-vis_const) - -.globl sha1_block_data_order -sha1_block_data_order: - save %sp,-$frame,%sp - add %fp,$bias-256,$base - -1: call .+8 - add %o7,vis_const-1b,$tmp0 - - ldd [$tmp0+0],$VK_00_19 - ldd [$tmp0+8],$VK_20_39 - ldd [$tmp0+16],$VK_40_59 - ldd [$tmp0+24],$VK_60_79 - ldd [$tmp0+32],$fmul - - ld [$ctx+0],$Actx - and $base,-256,$base - ld [$ctx+4],$Bctx - sub $base,$bias+$frame,%sp - ld [$ctx+8],$Cctx - and $inp,7,$align - ld [$ctx+12],$Dctx - and $inp,-8,$inp - ld [$ctx+16],$Ectx - - ! X[16] is maintained in FP register bank - alignaddr %g0,$align,%g0 - ldd [$inp+0],@X[0] - sub $inp,-64,$Xfer - ldd [$inp+8],@X[2] - and $Xfer,-64,$Xfer - ldd [$inp+16],@X[4] - and $Xfer,255,$Xfer - ldd [$inp+24],@X[6] - add $base,$Xfer,$Xfer - ldd [$inp+32],@X[8] - ldd [$inp+40],@X[10] - ldd [$inp+48],@X[12] - brz,pt $align,.Laligned - ldd [$inp+56],@X[14] - - ldd [$inp+64],@X[16] - faligndata @X[0],@X[2],@X[0] - faligndata @X[2],@X[4],@X[2] - faligndata @X[4],@X[6],@X[4] - faligndata @X[6],@X[8],@X[6] - faligndata @X[8],@X[10],@X[8] - faligndata @X[10],@X[12],@X[10] - faligndata @X[12],@X[14],@X[12] - faligndata @X[14],@X[16],@X[14] - -.Laligned: - mov 5,$tmp0 - dec 1,$len - alignaddr %g0,$tmp0,%g0 - fpadd32 $VK_00_19,@X[0],%f16 - fpadd32 $VK_00_19,@X[2],%f18 - fpadd32 $VK_00_19,@X[4],%f20 - fpadd32 $VK_00_19,@X[6],%f22 - fpadd32 $VK_00_19,@X[8],%f24 - fpadd32 $VK_00_19,@X[10],%f26 - fpadd32 $VK_00_19,@X[12],%f28 - fpadd32 $VK_00_19,@X[14],%f30 - std %f16,[$Xfer+0] - mov $Actx,$A - std %f18,[$Xfer+8] - mov $Bctx,$B - std %f20,[$Xfer+16] - mov $Cctx,$C - std %f22,[$Xfer+24] - mov $Dctx,$D - std %f24,[$Xfer+32] - mov $Ectx,$E - std %f26,[$Xfer+40] - fxors @X[13],@X[0],@X[0] - std %f28,[$Xfer+48] - ba .Loop - std %f30,[$Xfer+56] -.align 32 -.Loop: -___ -for ($i=0;$i<20;$i++) { &BODY_00_19($i,@V); unshift(@V,pop(@V)); } -for (;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -for (;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -for (;$i<70;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - tst $len - bz,pn `$bits==32?"%icc":"%xcc"`,.Ltail - nop -___ -for (;$i<80;$i++) { &BODY_70_79($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - add $A,$Actx,$Actx - add $B,$Bctx,$Bctx - add $C,$Cctx,$Cctx - add $D,$Dctx,$Dctx - add $E,$Ectx,$Ectx - mov 5,$tmp0 - fxors @X[13],@X[0],@X[0] - mov $Actx,$A - mov $Bctx,$B - mov $Cctx,$C - mov $Dctx,$D - mov $Ectx,$E - alignaddr %g0,$tmp0,%g0 - dec 1,$len - ba .Loop - mov $nXfer,$Xfer - -.align 32 -.Ltail: -___ -for($i=70;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - add $A,$Actx,$Actx - add $B,$Bctx,$Bctx - add $C,$Cctx,$Cctx - add $D,$Dctx,$Dctx - add $E,$Ectx,$Ectx - - st $Actx,[$ctx+0] - st $Bctx,[$ctx+4] - st $Cctx,[$ctx+8] - st $Dctx,[$ctx+12] - st $Ectx,[$ctx+16] - - ret - restore -.type sha1_block_data_order,#function -.size sha1_block_data_order,(.-sha1_block_data_order) -.asciz "SHA1 block transform for SPARCv9a, CRYPTOGAMS by <appro\@openssl.org>" -.align 4 -___ - -# Purpose of these subroutines is to explicitly encode VIS instructions, -# so that one can compile the module without having to specify VIS -# extentions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a. -# Idea is to reserve for option to produce "universal" binary and let -# programmer detect if current CPU is VIS capable at run-time. -sub unvis { -my ($mnemonic,$rs1,$rs2,$rd)=@_; -my ($ref,$opf); -my %visopf = ( "fmul8ulx16" => 0x037, - "faligndata" => 0x048, - "fpadd32" => 0x052, - "fxor" => 0x06c, - "fxors" => 0x06d ); - - $ref = "$mnemonic\t$rs1,$rs2,$rd"; - - if ($opf=$visopf{$mnemonic}) { - foreach ($rs1,$rs2,$rd) { - return $ref if (!/%f([0-9]{1,2})/); - $_=$1; - if ($1>=32) { - return $ref if ($1&1); - # re-encode for upper double register addressing - $_=($1|$1>>5)&31; - } - } - - return sprintf ".word\t0x%08x !%s", - 0x81b00000|$rd<<25|$rs1<<14|$opf<<5|$rs2, - $ref; - } else { - return $ref; - } -} -sub unalignaddr { -my ($mnemonic,$rs1,$rs2,$rd)=@_; -my %bias = ( "g" => 0, "o" => 8, "l" => 16, "i" => 24 ); -my $ref="$mnemonic\t$rs1,$rs2,$rd"; - - foreach ($rs1,$rs2,$rd) { - if (/%([goli])([0-7])/) { $_=$bias{$1}+$2; } - else { return $ref; } - } - return sprintf ".word\t0x%08x !%s", - 0x81b00300|$rd<<25|$rs1<<14|$rs2, - $ref; -} - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -$code =~ s/\b(f[^\s]*)\s+(%f[0-9]{1,2}),(%f[0-9]{1,2}),(%f[0-9]{1,2})/ - &unvis($1,$2,$3,$4) - /gem; -$code =~ s/\b(alignaddr)\s+(%[goli][0-7]),(%[goli][0-7]),(%[goli][0-7])/ - &unalignaddr($1,$2,$3,$4) - /gem; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha1-thumb.pl b/app/openssl/crypto/sha/asm/sha1-thumb.pl deleted file mode 100644 index 7c9ea9b0..00000000 --- a/app/openssl/crypto/sha/asm/sha1-thumb.pl +++ /dev/null @@ -1,259 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# sha1_block for Thumb. -# -# January 2007. -# -# The code does not present direct interest to OpenSSL, because of low -# performance. Its purpose is to establish _size_ benchmark. Pretty -# useless one I must say, because 30% or 88 bytes larger ARMv4 code -# [avialable on demand] is almost _twice_ as fast. It should also be -# noted that in-lining of .Lcommon and .Lrotate improves performance -# by over 40%, while code increases by only 10% or 32 bytes. But once -# again, the goal was to establish _size_ benchmark, not performance. - -$output=shift; -open STDOUT,">$output"; - -$inline=0; -#$cheat_on_binutils=1; - -$t0="r0"; -$t1="r1"; -$t2="r2"; -$a="r3"; -$b="r4"; -$c="r5"; -$d="r6"; -$e="r7"; -$K="r8"; # "upper" registers can be used in add/sub and mov insns -$ctx="r9"; -$inp="r10"; -$len="r11"; -$Xi="r12"; - -sub common { -<<___; - sub $t0,#4 - ldr $t1,[$t0] - add $e,$K @ E+=K_xx_xx - lsl $t2,$a,#5 - add $t2,$e - lsr $e,$a,#27 - add $t2,$e @ E+=ROR(A,27) - add $t2,$t1 @ E+=X[i] -___ -} -sub rotate { -<<___; - mov $e,$d @ E=D - mov $d,$c @ D=C - lsl $c,$b,#30 - lsr $b,$b,#2 - orr $c,$b @ C=ROR(B,2) - mov $b,$a @ B=A - add $a,$t2,$t1 @ A=E+F_xx_xx(B,C,D) -___ -} - -sub BODY_00_19 { -$code.=$inline?&common():"\tbl .Lcommon\n"; -$code.=<<___; - mov $t1,$c - eor $t1,$d - and $t1,$b - eor $t1,$d @ F_00_19(B,C,D) -___ -$code.=$inline?&rotate():"\tbl .Lrotate\n"; -} - -sub BODY_20_39 { -$code.=$inline?&common():"\tbl .Lcommon\n"; -$code.=<<___; - mov $t1,$b - eor $t1,$c - eor $t1,$d @ F_20_39(B,C,D) -___ -$code.=$inline?&rotate():"\tbl .Lrotate\n"; -} - -sub BODY_40_59 { -$code.=$inline?&common():"\tbl .Lcommon\n"; -$code.=<<___; - mov $t1,$b - and $t1,$c - mov $e,$b - orr $e,$c - and $e,$d - orr $t1,$e @ F_40_59(B,C,D) -___ -$code.=$inline?&rotate():"\tbl .Lrotate\n"; -} - -$code=<<___; -.text -.code 16 - -.global sha1_block_data_order -.type sha1_block_data_order,%function - -.align 2 -sha1_block_data_order: -___ -if ($cheat_on_binutils) { -$code.=<<___; -.code 32 - add r3,pc,#1 - bx r3 @ switch to Thumb ISA -.code 16 -___ -} -$code.=<<___; - push {r4-r7} - mov r3,r8 - mov r4,r9 - mov r5,r10 - mov r6,r11 - mov r7,r12 - push {r3-r7,lr} - lsl r2,#6 - mov $ctx,r0 @ save context - mov $inp,r1 @ save inp - mov $len,r2 @ save len - add $len,$inp @ $len to point at inp end - -.Lloop: - mov $Xi,sp - mov $t2,sp - sub $t2,#16*4 @ [3] -.LXload: - ldrb $a,[$t1,#0] @ $t1 is r1 and holds inp - ldrb $b,[$t1,#1] - ldrb $c,[$t1,#2] - ldrb $d,[$t1,#3] - lsl $a,#24 - lsl $b,#16 - lsl $c,#8 - orr $a,$b - orr $a,$c - orr $a,$d - add $t1,#4 - push {$a} - cmp sp,$t2 - bne .LXload @ [+14*16] - - mov $inp,$t1 @ update $inp - sub $t2,#32*4 - sub $t2,#32*4 - mov $e,#31 @ [+4] -.LXupdate: - ldr $a,[sp,#15*4] - ldr $b,[sp,#13*4] - ldr $c,[sp,#7*4] - ldr $d,[sp,#2*4] - eor $a,$b - eor $a,$c - eor $a,$d - ror $a,$e - push {$a} - cmp sp,$t2 - bne .LXupdate @ [+(11+1)*64] - - ldmia $t0!,{$a,$b,$c,$d,$e} @ $t0 is r0 and holds ctx - mov $t0,$Xi - - ldr $t2,.LK_00_19 - mov $t1,$t0 - sub $t1,#20*4 - mov $Xi,$t1 - mov $K,$t2 @ [+7+4] -.L_00_19: -___ - &BODY_00_19(); -$code.=<<___; - cmp $Xi,$t0 - bne .L_00_19 @ [+(2+9+4+2+8+2)*20] - - ldr $t2,.LK_20_39 - mov $t1,$t0 - sub $t1,#20*4 - mov $Xi,$t1 - mov $K,$t2 @ [+5] -.L_20_39_or_60_79: -___ - &BODY_20_39(); -$code.=<<___; - cmp $Xi,$t0 - bne .L_20_39_or_60_79 @ [+(2+9+3+2+8+2)*20*2] - cmp sp,$t0 - beq .Ldone @ [+2] - - ldr $t2,.LK_40_59 - mov $t1,$t0 - sub $t1,#20*4 - mov $Xi,$t1 - mov $K,$t2 @ [+5] -.L_40_59: -___ - &BODY_40_59(); -$code.=<<___; - cmp $Xi,$t0 - bne .L_40_59 @ [+(2+9+6+2+8+2)*20] - - ldr $t2,.LK_60_79 - mov $Xi,sp - mov $K,$t2 - b .L_20_39_or_60_79 @ [+4] -.Ldone: - mov $t0,$ctx - ldr $t1,[$t0,#0] - ldr $t2,[$t0,#4] - add $a,$t1 - ldr $t1,[$t0,#8] - add $b,$t2 - ldr $t2,[$t0,#12] - add $c,$t1 - ldr $t1,[$t0,#16] - add $d,$t2 - add $e,$t1 - stmia $t0!,{$a,$b,$c,$d,$e} @ [+20] - - add sp,#80*4 @ deallocate stack frame - mov $t0,$ctx @ restore ctx - mov $t1,$inp @ restore inp - cmp $t1,$len - beq .Lexit - b .Lloop @ [+6] total 3212 cycles -.Lexit: - pop {r2-r7} - mov r8,r2 - mov r9,r3 - mov r10,r4 - mov r11,r5 - mov r12,r6 - mov lr,r7 - pop {r4-r7} - bx lr -.align 2 -___ -$code.=".Lcommon:\n".&common()."\tmov pc,lr\n" if (!$inline); -$code.=".Lrotate:\n".&rotate()."\tmov pc,lr\n" if (!$inline); -$code.=<<___; -.align 2 -.LK_00_19: .word 0x5a827999 -.LK_20_39: .word 0x6ed9eba1 -.LK_40_59: .word 0x8f1bbcdc -.LK_60_79: .word 0xca62c1d6 -.size sha1_block_data_order,.-sha1_block_data_order -.asciz "SHA1 block transform for Thumb, CRYPTOGAMS by <appro\@openssl.org>" -___ - -print $code; -close STDOUT; # enforce flush diff --git a/app/openssl/crypto/sha/asm/sha1-x86_64.S b/app/openssl/crypto/sha/asm/sha1-x86_64.S deleted file mode 100644 index 3922e203..00000000 --- a/app/openssl/crypto/sha/asm/sha1-x86_64.S +++ /dev/null @@ -1,2486 +0,0 @@ -.text - - -.globl sha1_block_data_order -.type sha1_block_data_order,@function -.align 16 -sha1_block_data_order: - movl OPENSSL_ia32cap_P+0(%rip),%r9d - movl OPENSSL_ia32cap_P+4(%rip),%r8d - testl $512,%r8d - jz .Lialu - jmp _ssse3_shortcut - -.align 16 -.Lialu: - pushq %rbx - pushq %rbp - pushq %r12 - pushq %r13 - movq %rsp,%r11 - movq %rdi,%r8 - subq $72,%rsp - movq %rsi,%r9 - andq $-64,%rsp - movq %rdx,%r10 - movq %r11,64(%rsp) -.Lprologue: - - movl 0(%r8),%esi - movl 4(%r8),%edi - movl 8(%r8),%r11d - movl 12(%r8),%r12d - movl 16(%r8),%r13d - jmp .Lloop - -.align 16 -.Lloop: - movl 0(%r9),%edx - bswapl %edx - movl %edx,0(%rsp) - movl %r11d,%eax - movl 4(%r9),%ebp - movl %esi,%ecx - xorl %r12d,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%r13,1),%r13d - andl %edi,%eax - movl %ebp,4(%rsp) - addl %ecx,%r13d - xorl %r12d,%eax - roll $30,%edi - addl %eax,%r13d - movl %edi,%eax - movl 8(%r9),%edx - movl %r13d,%ecx - xorl %r11d,%eax - bswapl %edx - roll $5,%ecx - leal 1518500249(%rbp,%r12,1),%r12d - andl %esi,%eax - movl %edx,8(%rsp) - addl %ecx,%r12d - xorl %r11d,%eax - roll $30,%esi - addl %eax,%r12d - movl %esi,%eax - movl 12(%r9),%ebp - movl %r12d,%ecx - xorl %edi,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%r11,1),%r11d - andl %r13d,%eax - movl %ebp,12(%rsp) - addl %ecx,%r11d - xorl %edi,%eax - roll $30,%r13d - addl %eax,%r11d - movl %r13d,%eax - movl 16(%r9),%edx - movl %r11d,%ecx - xorl %esi,%eax - bswapl %edx - roll $5,%ecx - leal 1518500249(%rbp,%rdi,1),%edi - andl %r12d,%eax - movl %edx,16(%rsp) - addl %ecx,%edi - xorl %esi,%eax - roll $30,%r12d - addl %eax,%edi - movl %r12d,%eax - movl 20(%r9),%ebp - movl %edi,%ecx - xorl %r13d,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%rsi,1),%esi - andl %r11d,%eax - movl %ebp,20(%rsp) - addl %ecx,%esi - xorl %r13d,%eax - roll $30,%r11d - addl %eax,%esi - movl %r11d,%eax - movl 24(%r9),%edx - movl %esi,%ecx - xorl %r12d,%eax - bswapl %edx - roll $5,%ecx - leal 1518500249(%rbp,%r13,1),%r13d - andl %edi,%eax - movl %edx,24(%rsp) - addl %ecx,%r13d - xorl %r12d,%eax - roll $30,%edi - addl %eax,%r13d - movl %edi,%eax - movl 28(%r9),%ebp - movl %r13d,%ecx - xorl %r11d,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%r12,1),%r12d - andl %esi,%eax - movl %ebp,28(%rsp) - addl %ecx,%r12d - xorl %r11d,%eax - roll $30,%esi - addl %eax,%r12d - movl %esi,%eax - movl 32(%r9),%edx - movl %r12d,%ecx - xorl %edi,%eax - bswapl %edx - roll $5,%ecx - leal 1518500249(%rbp,%r11,1),%r11d - andl %r13d,%eax - movl %edx,32(%rsp) - addl %ecx,%r11d - xorl %edi,%eax - roll $30,%r13d - addl %eax,%r11d - movl %r13d,%eax - movl 36(%r9),%ebp - movl %r11d,%ecx - xorl %esi,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%rdi,1),%edi - andl %r12d,%eax - movl %ebp,36(%rsp) - addl %ecx,%edi - xorl %esi,%eax - roll $30,%r12d - addl %eax,%edi - movl %r12d,%eax - movl 40(%r9),%edx - movl %edi,%ecx - xorl %r13d,%eax - bswapl %edx - roll $5,%ecx - leal 1518500249(%rbp,%rsi,1),%esi - andl %r11d,%eax - movl %edx,40(%rsp) - addl %ecx,%esi - xorl %r13d,%eax - roll $30,%r11d - addl %eax,%esi - movl %r11d,%eax - movl 44(%r9),%ebp - movl %esi,%ecx - xorl %r12d,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%r13,1),%r13d - andl %edi,%eax - movl %ebp,44(%rsp) - addl %ecx,%r13d - xorl %r12d,%eax - roll $30,%edi - addl %eax,%r13d - movl %edi,%eax - movl 48(%r9),%edx - movl %r13d,%ecx - xorl %r11d,%eax - bswapl %edx - roll $5,%ecx - leal 1518500249(%rbp,%r12,1),%r12d - andl %esi,%eax - movl %edx,48(%rsp) - addl %ecx,%r12d - xorl %r11d,%eax - roll $30,%esi - addl %eax,%r12d - movl %esi,%eax - movl 52(%r9),%ebp - movl %r12d,%ecx - xorl %edi,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%r11,1),%r11d - andl %r13d,%eax - movl %ebp,52(%rsp) - addl %ecx,%r11d - xorl %edi,%eax - roll $30,%r13d - addl %eax,%r11d - movl %r13d,%eax - movl 56(%r9),%edx - movl %r11d,%ecx - xorl %esi,%eax - bswapl %edx - roll $5,%ecx - leal 1518500249(%rbp,%rdi,1),%edi - andl %r12d,%eax - movl %edx,56(%rsp) - addl %ecx,%edi - xorl %esi,%eax - roll $30,%r12d - addl %eax,%edi - movl %r12d,%eax - movl 60(%r9),%ebp - movl %edi,%ecx - xorl %r13d,%eax - bswapl %ebp - roll $5,%ecx - leal 1518500249(%rdx,%rsi,1),%esi - andl %r11d,%eax - movl %ebp,60(%rsp) - addl %ecx,%esi - xorl %r13d,%eax - roll $30,%r11d - addl %eax,%esi - movl 0(%rsp),%edx - movl %r11d,%eax - movl %esi,%ecx - xorl 8(%rsp),%edx - xorl %r12d,%eax - roll $5,%ecx - xorl 32(%rsp),%edx - andl %edi,%eax - leal 1518500249(%rbp,%r13,1),%r13d - xorl 52(%rsp),%edx - xorl %r12d,%eax - roll $1,%edx - addl %ecx,%r13d - roll $30,%edi - movl %edx,0(%rsp) - addl %eax,%r13d - movl 4(%rsp),%ebp - movl %edi,%eax - movl %r13d,%ecx - xorl 12(%rsp),%ebp - xorl %r11d,%eax - roll $5,%ecx - xorl 36(%rsp),%ebp - andl %esi,%eax - leal 1518500249(%rdx,%r12,1),%r12d - xorl 56(%rsp),%ebp - xorl %r11d,%eax - roll $1,%ebp - addl %ecx,%r12d - roll $30,%esi - movl %ebp,4(%rsp) - addl %eax,%r12d - movl 8(%rsp),%edx - movl %esi,%eax - movl %r12d,%ecx - xorl 16(%rsp),%edx - xorl %edi,%eax - roll $5,%ecx - xorl 40(%rsp),%edx - andl %r13d,%eax - leal 1518500249(%rbp,%r11,1),%r11d - xorl 60(%rsp),%edx - xorl %edi,%eax - roll $1,%edx - addl %ecx,%r11d - roll $30,%r13d - movl %edx,8(%rsp) - addl %eax,%r11d - movl 12(%rsp),%ebp - movl %r13d,%eax - movl %r11d,%ecx - xorl 20(%rsp),%ebp - xorl %esi,%eax - roll $5,%ecx - xorl 44(%rsp),%ebp - andl %r12d,%eax - leal 1518500249(%rdx,%rdi,1),%edi - xorl 0(%rsp),%ebp - xorl %esi,%eax - roll $1,%ebp - addl %ecx,%edi - roll $30,%r12d - movl %ebp,12(%rsp) - addl %eax,%edi - movl 16(%rsp),%edx - movl %r12d,%eax - movl %edi,%ecx - xorl 24(%rsp),%edx - xorl %r13d,%eax - roll $5,%ecx - xorl 48(%rsp),%edx - andl %r11d,%eax - leal 1518500249(%rbp,%rsi,1),%esi - xorl 4(%rsp),%edx - xorl %r13d,%eax - roll $1,%edx - addl %ecx,%esi - roll $30,%r11d - movl %edx,16(%rsp) - addl %eax,%esi - movl 20(%rsp),%ebp - movl %r11d,%eax - movl %esi,%ecx - xorl 28(%rsp),%ebp - xorl %edi,%eax - roll $5,%ecx - leal 1859775393(%rdx,%r13,1),%r13d - xorl 52(%rsp),%ebp - xorl %r12d,%eax - addl %ecx,%r13d - xorl 8(%rsp),%ebp - roll $30,%edi - addl %eax,%r13d - roll $1,%ebp - movl %ebp,20(%rsp) - movl 24(%rsp),%edx - movl %edi,%eax - movl %r13d,%ecx - xorl 32(%rsp),%edx - xorl %esi,%eax - roll $5,%ecx - leal 1859775393(%rbp,%r12,1),%r12d - xorl 56(%rsp),%edx - xorl %r11d,%eax - addl %ecx,%r12d - xorl 12(%rsp),%edx - roll $30,%esi - addl %eax,%r12d - roll $1,%edx - movl %edx,24(%rsp) - movl 28(%rsp),%ebp - movl %esi,%eax - movl %r12d,%ecx - xorl 36(%rsp),%ebp - xorl %r13d,%eax - roll $5,%ecx - leal 1859775393(%rdx,%r11,1),%r11d - xorl 60(%rsp),%ebp - xorl %edi,%eax - addl %ecx,%r11d - xorl 16(%rsp),%ebp - roll $30,%r13d - addl %eax,%r11d - roll $1,%ebp - movl %ebp,28(%rsp) - movl 32(%rsp),%edx - movl %r13d,%eax - movl %r11d,%ecx - xorl 40(%rsp),%edx - xorl %r12d,%eax - roll $5,%ecx - leal 1859775393(%rbp,%rdi,1),%edi - xorl 0(%rsp),%edx - xorl %esi,%eax - addl %ecx,%edi - xorl 20(%rsp),%edx - roll $30,%r12d - addl %eax,%edi - roll $1,%edx - movl %edx,32(%rsp) - movl 36(%rsp),%ebp - movl %r12d,%eax - movl %edi,%ecx - xorl 44(%rsp),%ebp - xorl %r11d,%eax - roll $5,%ecx - leal 1859775393(%rdx,%rsi,1),%esi - xorl 4(%rsp),%ebp - xorl %r13d,%eax - addl %ecx,%esi - xorl 24(%rsp),%ebp - roll $30,%r11d - addl %eax,%esi - roll $1,%ebp - movl %ebp,36(%rsp) - movl 40(%rsp),%edx - movl %r11d,%eax - movl %esi,%ecx - xorl 48(%rsp),%edx - xorl %edi,%eax - roll $5,%ecx - leal 1859775393(%rbp,%r13,1),%r13d - xorl 8(%rsp),%edx - xorl %r12d,%eax - addl %ecx,%r13d - xorl 28(%rsp),%edx - roll $30,%edi - addl %eax,%r13d - roll $1,%edx - movl %edx,40(%rsp) - movl 44(%rsp),%ebp - movl %edi,%eax - movl %r13d,%ecx - xorl 52(%rsp),%ebp - xorl %esi,%eax - roll $5,%ecx - leal 1859775393(%rdx,%r12,1),%r12d - xorl 12(%rsp),%ebp - xorl %r11d,%eax - addl %ecx,%r12d - xorl 32(%rsp),%ebp - roll $30,%esi - addl %eax,%r12d - roll $1,%ebp - movl %ebp,44(%rsp) - movl 48(%rsp),%edx - movl %esi,%eax - movl %r12d,%ecx - xorl 56(%rsp),%edx - xorl %r13d,%eax - roll $5,%ecx - leal 1859775393(%rbp,%r11,1),%r11d - xorl 16(%rsp),%edx - xorl %edi,%eax - addl %ecx,%r11d - xorl 36(%rsp),%edx - roll $30,%r13d - addl %eax,%r11d - roll $1,%edx - movl %edx,48(%rsp) - movl 52(%rsp),%ebp - movl %r13d,%eax - movl %r11d,%ecx - xorl 60(%rsp),%ebp - xorl %r12d,%eax - roll $5,%ecx - leal 1859775393(%rdx,%rdi,1),%edi - xorl 20(%rsp),%ebp - xorl %esi,%eax - addl %ecx,%edi - xorl 40(%rsp),%ebp - roll $30,%r12d - addl %eax,%edi - roll $1,%ebp - movl %ebp,52(%rsp) - movl 56(%rsp),%edx - movl %r12d,%eax - movl %edi,%ecx - xorl 0(%rsp),%edx - xorl %r11d,%eax - roll $5,%ecx - leal 1859775393(%rbp,%rsi,1),%esi - xorl 24(%rsp),%edx - xorl %r13d,%eax - addl %ecx,%esi - xorl 44(%rsp),%edx - roll $30,%r11d - addl %eax,%esi - roll $1,%edx - movl %edx,56(%rsp) - movl 60(%rsp),%ebp - movl %r11d,%eax - movl %esi,%ecx - xorl 4(%rsp),%ebp - xorl %edi,%eax - roll $5,%ecx - leal 1859775393(%rdx,%r13,1),%r13d - xorl 28(%rsp),%ebp - xorl %r12d,%eax - addl %ecx,%r13d - xorl 48(%rsp),%ebp - roll $30,%edi - addl %eax,%r13d - roll $1,%ebp - movl %ebp,60(%rsp) - movl 0(%rsp),%edx - movl %edi,%eax - movl %r13d,%ecx - xorl 8(%rsp),%edx - xorl %esi,%eax - roll $5,%ecx - leal 1859775393(%rbp,%r12,1),%r12d - xorl 32(%rsp),%edx - xorl %r11d,%eax - addl %ecx,%r12d - xorl 52(%rsp),%edx - roll $30,%esi - addl %eax,%r12d - roll $1,%edx - movl %edx,0(%rsp) - movl 4(%rsp),%ebp - movl %esi,%eax - movl %r12d,%ecx - xorl 12(%rsp),%ebp - xorl %r13d,%eax - roll $5,%ecx - leal 1859775393(%rdx,%r11,1),%r11d - xorl 36(%rsp),%ebp - xorl %edi,%eax - addl %ecx,%r11d - xorl 56(%rsp),%ebp - roll $30,%r13d - addl %eax,%r11d - roll $1,%ebp - movl %ebp,4(%rsp) - movl 8(%rsp),%edx - movl %r13d,%eax - movl %r11d,%ecx - xorl 16(%rsp),%edx - xorl %r12d,%eax - roll $5,%ecx - leal 1859775393(%rbp,%rdi,1),%edi - xorl 40(%rsp),%edx - xorl %esi,%eax - addl %ecx,%edi - xorl 60(%rsp),%edx - roll $30,%r12d - addl %eax,%edi - roll $1,%edx - movl %edx,8(%rsp) - movl 12(%rsp),%ebp - movl %r12d,%eax - movl %edi,%ecx - xorl 20(%rsp),%ebp - xorl %r11d,%eax - roll $5,%ecx - leal 1859775393(%rdx,%rsi,1),%esi - xorl 44(%rsp),%ebp - xorl %r13d,%eax - addl %ecx,%esi - xorl 0(%rsp),%ebp - roll $30,%r11d - addl %eax,%esi - roll $1,%ebp - movl %ebp,12(%rsp) - movl 16(%rsp),%edx - movl %r11d,%eax - movl %esi,%ecx - xorl 24(%rsp),%edx - xorl %edi,%eax - roll $5,%ecx - leal 1859775393(%rbp,%r13,1),%r13d - xorl 48(%rsp),%edx - xorl %r12d,%eax - addl %ecx,%r13d - xorl 4(%rsp),%edx - roll $30,%edi - addl %eax,%r13d - roll $1,%edx - movl %edx,16(%rsp) - movl 20(%rsp),%ebp - movl %edi,%eax - movl %r13d,%ecx - xorl 28(%rsp),%ebp - xorl %esi,%eax - roll $5,%ecx - leal 1859775393(%rdx,%r12,1),%r12d - xorl 52(%rsp),%ebp - xorl %r11d,%eax - addl %ecx,%r12d - xorl 8(%rsp),%ebp - roll $30,%esi - addl %eax,%r12d - roll $1,%ebp - movl %ebp,20(%rsp) - movl 24(%rsp),%edx - movl %esi,%eax - movl %r12d,%ecx - xorl 32(%rsp),%edx - xorl %r13d,%eax - roll $5,%ecx - leal 1859775393(%rbp,%r11,1),%r11d - xorl 56(%rsp),%edx - xorl %edi,%eax - addl %ecx,%r11d - xorl 12(%rsp),%edx - roll $30,%r13d - addl %eax,%r11d - roll $1,%edx - movl %edx,24(%rsp) - movl 28(%rsp),%ebp - movl %r13d,%eax - movl %r11d,%ecx - xorl 36(%rsp),%ebp - xorl %r12d,%eax - roll $5,%ecx - leal 1859775393(%rdx,%rdi,1),%edi - xorl 60(%rsp),%ebp - xorl %esi,%eax - addl %ecx,%edi - xorl 16(%rsp),%ebp - roll $30,%r12d - addl %eax,%edi - roll $1,%ebp - movl %ebp,28(%rsp) - movl 32(%rsp),%edx - movl %r12d,%eax - movl %edi,%ecx - xorl 40(%rsp),%edx - xorl %r11d,%eax - roll $5,%ecx - leal 1859775393(%rbp,%rsi,1),%esi - xorl 0(%rsp),%edx - xorl %r13d,%eax - addl %ecx,%esi - xorl 20(%rsp),%edx - roll $30,%r11d - addl %eax,%esi - roll $1,%edx - movl %edx,32(%rsp) - movl 36(%rsp),%ebp - movl %r11d,%eax - movl %r11d,%ebx - xorl 44(%rsp),%ebp - andl %r12d,%eax - movl %esi,%ecx - xorl 4(%rsp),%ebp - xorl %r12d,%ebx - leal -1894007588(%rdx,%r13,1),%r13d - roll $5,%ecx - xorl 24(%rsp),%ebp - addl %eax,%r13d - andl %edi,%ebx - roll $1,%ebp - addl %ebx,%r13d - roll $30,%edi - movl %ebp,36(%rsp) - addl %ecx,%r13d - movl 40(%rsp),%edx - movl %edi,%eax - movl %edi,%ebx - xorl 48(%rsp),%edx - andl %r11d,%eax - movl %r13d,%ecx - xorl 8(%rsp),%edx - xorl %r11d,%ebx - leal -1894007588(%rbp,%r12,1),%r12d - roll $5,%ecx - xorl 28(%rsp),%edx - addl %eax,%r12d - andl %esi,%ebx - roll $1,%edx - addl %ebx,%r12d - roll $30,%esi - movl %edx,40(%rsp) - addl %ecx,%r12d - movl 44(%rsp),%ebp - movl %esi,%eax - movl %esi,%ebx - xorl 52(%rsp),%ebp - andl %edi,%eax - movl %r12d,%ecx - xorl 12(%rsp),%ebp - xorl %edi,%ebx - leal -1894007588(%rdx,%r11,1),%r11d - roll $5,%ecx - xorl 32(%rsp),%ebp - addl %eax,%r11d - andl %r13d,%ebx - roll $1,%ebp - addl %ebx,%r11d - roll $30,%r13d - movl %ebp,44(%rsp) - addl %ecx,%r11d - movl 48(%rsp),%edx - movl %r13d,%eax - movl %r13d,%ebx - xorl 56(%rsp),%edx - andl %esi,%eax - movl %r11d,%ecx - xorl 16(%rsp),%edx - xorl %esi,%ebx - leal -1894007588(%rbp,%rdi,1),%edi - roll $5,%ecx - xorl 36(%rsp),%edx - addl %eax,%edi - andl %r12d,%ebx - roll $1,%edx - addl %ebx,%edi - roll $30,%r12d - movl %edx,48(%rsp) - addl %ecx,%edi - movl 52(%rsp),%ebp - movl %r12d,%eax - movl %r12d,%ebx - xorl 60(%rsp),%ebp - andl %r13d,%eax - movl %edi,%ecx - xorl 20(%rsp),%ebp - xorl %r13d,%ebx - leal -1894007588(%rdx,%rsi,1),%esi - roll $5,%ecx - xorl 40(%rsp),%ebp - addl %eax,%esi - andl %r11d,%ebx - roll $1,%ebp - addl %ebx,%esi - roll $30,%r11d - movl %ebp,52(%rsp) - addl %ecx,%esi - movl 56(%rsp),%edx - movl %r11d,%eax - movl %r11d,%ebx - xorl 0(%rsp),%edx - andl %r12d,%eax - movl %esi,%ecx - xorl 24(%rsp),%edx - xorl %r12d,%ebx - leal -1894007588(%rbp,%r13,1),%r13d - roll $5,%ecx - xorl 44(%rsp),%edx - addl %eax,%r13d - andl %edi,%ebx - roll $1,%edx - addl %ebx,%r13d - roll $30,%edi - movl %edx,56(%rsp) - addl %ecx,%r13d - movl 60(%rsp),%ebp - movl %edi,%eax - movl %edi,%ebx - xorl 4(%rsp),%ebp - andl %r11d,%eax - movl %r13d,%ecx - xorl 28(%rsp),%ebp - xorl %r11d,%ebx - leal -1894007588(%rdx,%r12,1),%r12d - roll $5,%ecx - xorl 48(%rsp),%ebp - addl %eax,%r12d - andl %esi,%ebx - roll $1,%ebp - addl %ebx,%r12d - roll $30,%esi - movl %ebp,60(%rsp) - addl %ecx,%r12d - movl 0(%rsp),%edx - movl %esi,%eax - movl %esi,%ebx - xorl 8(%rsp),%edx - andl %edi,%eax - movl %r12d,%ecx - xorl 32(%rsp),%edx - xorl %edi,%ebx - leal -1894007588(%rbp,%r11,1),%r11d - roll $5,%ecx - xorl 52(%rsp),%edx - addl %eax,%r11d - andl %r13d,%ebx - roll $1,%edx - addl %ebx,%r11d - roll $30,%r13d - movl %edx,0(%rsp) - addl %ecx,%r11d - movl 4(%rsp),%ebp - movl %r13d,%eax - movl %r13d,%ebx - xorl 12(%rsp),%ebp - andl %esi,%eax - movl %r11d,%ecx - xorl 36(%rsp),%ebp - xorl %esi,%ebx - leal -1894007588(%rdx,%rdi,1),%edi - roll $5,%ecx - xorl 56(%rsp),%ebp - addl %eax,%edi - andl %r12d,%ebx - roll $1,%ebp - addl %ebx,%edi - roll $30,%r12d - movl %ebp,4(%rsp) - addl %ecx,%edi - movl 8(%rsp),%edx - movl %r12d,%eax - movl %r12d,%ebx - xorl 16(%rsp),%edx - andl %r13d,%eax - movl %edi,%ecx - xorl 40(%rsp),%edx - xorl %r13d,%ebx - leal -1894007588(%rbp,%rsi,1),%esi - roll $5,%ecx - xorl 60(%rsp),%edx - addl %eax,%esi - andl %r11d,%ebx - roll $1,%edx - addl %ebx,%esi - roll $30,%r11d - movl %edx,8(%rsp) - addl %ecx,%esi - movl 12(%rsp),%ebp - movl %r11d,%eax - movl %r11d,%ebx - xorl 20(%rsp),%ebp - andl %r12d,%eax - movl %esi,%ecx - xorl 44(%rsp),%ebp - xorl %r12d,%ebx - leal -1894007588(%rdx,%r13,1),%r13d - roll $5,%ecx - xorl 0(%rsp),%ebp - addl %eax,%r13d - andl %edi,%ebx - roll $1,%ebp - addl %ebx,%r13d - roll $30,%edi - movl %ebp,12(%rsp) - addl %ecx,%r13d - movl 16(%rsp),%edx - movl %edi,%eax - movl %edi,%ebx - xorl 24(%rsp),%edx - andl %r11d,%eax - movl %r13d,%ecx - xorl 48(%rsp),%edx - xorl %r11d,%ebx - leal -1894007588(%rbp,%r12,1),%r12d - roll $5,%ecx - xorl 4(%rsp),%edx - addl %eax,%r12d - andl %esi,%ebx - roll $1,%edx - addl %ebx,%r12d - roll $30,%esi - movl %edx,16(%rsp) - addl %ecx,%r12d - movl 20(%rsp),%ebp - movl %esi,%eax - movl %esi,%ebx - xorl 28(%rsp),%ebp - andl %edi,%eax - movl %r12d,%ecx - xorl 52(%rsp),%ebp - xorl %edi,%ebx - leal -1894007588(%rdx,%r11,1),%r11d - roll $5,%ecx - xorl 8(%rsp),%ebp - addl %eax,%r11d - andl %r13d,%ebx - roll $1,%ebp - addl %ebx,%r11d - roll $30,%r13d - movl %ebp,20(%rsp) - addl %ecx,%r11d - movl 24(%rsp),%edx - movl %r13d,%eax - movl %r13d,%ebx - xorl 32(%rsp),%edx - andl %esi,%eax - movl %r11d,%ecx - xorl 56(%rsp),%edx - xorl %esi,%ebx - leal -1894007588(%rbp,%rdi,1),%edi - roll $5,%ecx - xorl 12(%rsp),%edx - addl %eax,%edi - andl %r12d,%ebx - roll $1,%edx - addl %ebx,%edi - roll $30,%r12d - movl %edx,24(%rsp) - addl %ecx,%edi - movl 28(%rsp),%ebp - movl %r12d,%eax - movl %r12d,%ebx - xorl 36(%rsp),%ebp - andl %r13d,%eax - movl %edi,%ecx - xorl 60(%rsp),%ebp - xorl %r13d,%ebx - leal -1894007588(%rdx,%rsi,1),%esi - roll $5,%ecx - xorl 16(%rsp),%ebp - addl %eax,%esi - andl %r11d,%ebx - roll $1,%ebp - addl %ebx,%esi - roll $30,%r11d - movl %ebp,28(%rsp) - addl %ecx,%esi - movl 32(%rsp),%edx - movl %r11d,%eax - movl %r11d,%ebx - xorl 40(%rsp),%edx - andl %r12d,%eax - movl %esi,%ecx - xorl 0(%rsp),%edx - xorl %r12d,%ebx - leal -1894007588(%rbp,%r13,1),%r13d - roll $5,%ecx - xorl 20(%rsp),%edx - addl %eax,%r13d - andl %edi,%ebx - roll $1,%edx - addl %ebx,%r13d - roll $30,%edi - movl %edx,32(%rsp) - addl %ecx,%r13d - movl 36(%rsp),%ebp - movl %edi,%eax - movl %edi,%ebx - xorl 44(%rsp),%ebp - andl %r11d,%eax - movl %r13d,%ecx - xorl 4(%rsp),%ebp - xorl %r11d,%ebx - leal -1894007588(%rdx,%r12,1),%r12d - roll $5,%ecx - xorl 24(%rsp),%ebp - addl %eax,%r12d - andl %esi,%ebx - roll $1,%ebp - addl %ebx,%r12d - roll $30,%esi - movl %ebp,36(%rsp) - addl %ecx,%r12d - movl 40(%rsp),%edx - movl %esi,%eax - movl %esi,%ebx - xorl 48(%rsp),%edx - andl %edi,%eax - movl %r12d,%ecx - xorl 8(%rsp),%edx - xorl %edi,%ebx - leal -1894007588(%rbp,%r11,1),%r11d - roll $5,%ecx - xorl 28(%rsp),%edx - addl %eax,%r11d - andl %r13d,%ebx - roll $1,%edx - addl %ebx,%r11d - roll $30,%r13d - movl %edx,40(%rsp) - addl %ecx,%r11d - movl 44(%rsp),%ebp - movl %r13d,%eax - movl %r13d,%ebx - xorl 52(%rsp),%ebp - andl %esi,%eax - movl %r11d,%ecx - xorl 12(%rsp),%ebp - xorl %esi,%ebx - leal -1894007588(%rdx,%rdi,1),%edi - roll $5,%ecx - xorl 32(%rsp),%ebp - addl %eax,%edi - andl %r12d,%ebx - roll $1,%ebp - addl %ebx,%edi - roll $30,%r12d - movl %ebp,44(%rsp) - addl %ecx,%edi - movl 48(%rsp),%edx - movl %r12d,%eax - movl %r12d,%ebx - xorl 56(%rsp),%edx - andl %r13d,%eax - movl %edi,%ecx - xorl 16(%rsp),%edx - xorl %r13d,%ebx - leal -1894007588(%rbp,%rsi,1),%esi - roll $5,%ecx - xorl 36(%rsp),%edx - addl %eax,%esi - andl %r11d,%ebx - roll $1,%edx - addl %ebx,%esi - roll $30,%r11d - movl %edx,48(%rsp) - addl %ecx,%esi - movl 52(%rsp),%ebp - movl %r11d,%eax - movl %esi,%ecx - xorl 60(%rsp),%ebp - xorl %edi,%eax - roll $5,%ecx - leal -899497514(%rdx,%r13,1),%r13d - xorl 20(%rsp),%ebp - xorl %r12d,%eax - addl %ecx,%r13d - xorl 40(%rsp),%ebp - roll $30,%edi - addl %eax,%r13d - roll $1,%ebp - movl %ebp,52(%rsp) - movl 56(%rsp),%edx - movl %edi,%eax - movl %r13d,%ecx - xorl 0(%rsp),%edx - xorl %esi,%eax - roll $5,%ecx - leal -899497514(%rbp,%r12,1),%r12d - xorl 24(%rsp),%edx - xorl %r11d,%eax - addl %ecx,%r12d - xorl 44(%rsp),%edx - roll $30,%esi - addl %eax,%r12d - roll $1,%edx - movl %edx,56(%rsp) - movl 60(%rsp),%ebp - movl %esi,%eax - movl %r12d,%ecx - xorl 4(%rsp),%ebp - xorl %r13d,%eax - roll $5,%ecx - leal -899497514(%rdx,%r11,1),%r11d - xorl 28(%rsp),%ebp - xorl %edi,%eax - addl %ecx,%r11d - xorl 48(%rsp),%ebp - roll $30,%r13d - addl %eax,%r11d - roll $1,%ebp - movl %ebp,60(%rsp) - movl 0(%rsp),%edx - movl %r13d,%eax - movl %r11d,%ecx - xorl 8(%rsp),%edx - xorl %r12d,%eax - roll $5,%ecx - leal -899497514(%rbp,%rdi,1),%edi - xorl 32(%rsp),%edx - xorl %esi,%eax - addl %ecx,%edi - xorl 52(%rsp),%edx - roll $30,%r12d - addl %eax,%edi - roll $1,%edx - movl %edx,0(%rsp) - movl 4(%rsp),%ebp - movl %r12d,%eax - movl %edi,%ecx - xorl 12(%rsp),%ebp - xorl %r11d,%eax - roll $5,%ecx - leal -899497514(%rdx,%rsi,1),%esi - xorl 36(%rsp),%ebp - xorl %r13d,%eax - addl %ecx,%esi - xorl 56(%rsp),%ebp - roll $30,%r11d - addl %eax,%esi - roll $1,%ebp - movl %ebp,4(%rsp) - movl 8(%rsp),%edx - movl %r11d,%eax - movl %esi,%ecx - xorl 16(%rsp),%edx - xorl %edi,%eax - roll $5,%ecx - leal -899497514(%rbp,%r13,1),%r13d - xorl 40(%rsp),%edx - xorl %r12d,%eax - addl %ecx,%r13d - xorl 60(%rsp),%edx - roll $30,%edi - addl %eax,%r13d - roll $1,%edx - movl %edx,8(%rsp) - movl 12(%rsp),%ebp - movl %edi,%eax - movl %r13d,%ecx - xorl 20(%rsp),%ebp - xorl %esi,%eax - roll $5,%ecx - leal -899497514(%rdx,%r12,1),%r12d - xorl 44(%rsp),%ebp - xorl %r11d,%eax - addl %ecx,%r12d - xorl 0(%rsp),%ebp - roll $30,%esi - addl %eax,%r12d - roll $1,%ebp - movl %ebp,12(%rsp) - movl 16(%rsp),%edx - movl %esi,%eax - movl %r12d,%ecx - xorl 24(%rsp),%edx - xorl %r13d,%eax - roll $5,%ecx - leal -899497514(%rbp,%r11,1),%r11d - xorl 48(%rsp),%edx - xorl %edi,%eax - addl %ecx,%r11d - xorl 4(%rsp),%edx - roll $30,%r13d - addl %eax,%r11d - roll $1,%edx - movl %edx,16(%rsp) - movl 20(%rsp),%ebp - movl %r13d,%eax - movl %r11d,%ecx - xorl 28(%rsp),%ebp - xorl %r12d,%eax - roll $5,%ecx - leal -899497514(%rdx,%rdi,1),%edi - xorl 52(%rsp),%ebp - xorl %esi,%eax - addl %ecx,%edi - xorl 8(%rsp),%ebp - roll $30,%r12d - addl %eax,%edi - roll $1,%ebp - movl %ebp,20(%rsp) - movl 24(%rsp),%edx - movl %r12d,%eax - movl %edi,%ecx - xorl 32(%rsp),%edx - xorl %r11d,%eax - roll $5,%ecx - leal -899497514(%rbp,%rsi,1),%esi - xorl 56(%rsp),%edx - xorl %r13d,%eax - addl %ecx,%esi - xorl 12(%rsp),%edx - roll $30,%r11d - addl %eax,%esi - roll $1,%edx - movl %edx,24(%rsp) - movl 28(%rsp),%ebp - movl %r11d,%eax - movl %esi,%ecx - xorl 36(%rsp),%ebp - xorl %edi,%eax - roll $5,%ecx - leal -899497514(%rdx,%r13,1),%r13d - xorl 60(%rsp),%ebp - xorl %r12d,%eax - addl %ecx,%r13d - xorl 16(%rsp),%ebp - roll $30,%edi - addl %eax,%r13d - roll $1,%ebp - movl %ebp,28(%rsp) - movl 32(%rsp),%edx - movl %edi,%eax - movl %r13d,%ecx - xorl 40(%rsp),%edx - xorl %esi,%eax - roll $5,%ecx - leal -899497514(%rbp,%r12,1),%r12d - xorl 0(%rsp),%edx - xorl %r11d,%eax - addl %ecx,%r12d - xorl 20(%rsp),%edx - roll $30,%esi - addl %eax,%r12d - roll $1,%edx - movl %edx,32(%rsp) - movl 36(%rsp),%ebp - movl %esi,%eax - movl %r12d,%ecx - xorl 44(%rsp),%ebp - xorl %r13d,%eax - roll $5,%ecx - leal -899497514(%rdx,%r11,1),%r11d - xorl 4(%rsp),%ebp - xorl %edi,%eax - addl %ecx,%r11d - xorl 24(%rsp),%ebp - roll $30,%r13d - addl %eax,%r11d - roll $1,%ebp - movl %ebp,36(%rsp) - movl 40(%rsp),%edx - movl %r13d,%eax - movl %r11d,%ecx - xorl 48(%rsp),%edx - xorl %r12d,%eax - roll $5,%ecx - leal -899497514(%rbp,%rdi,1),%edi - xorl 8(%rsp),%edx - xorl %esi,%eax - addl %ecx,%edi - xorl 28(%rsp),%edx - roll $30,%r12d - addl %eax,%edi - roll $1,%edx - movl %edx,40(%rsp) - movl 44(%rsp),%ebp - movl %r12d,%eax - movl %edi,%ecx - xorl 52(%rsp),%ebp - xorl %r11d,%eax - roll $5,%ecx - leal -899497514(%rdx,%rsi,1),%esi - xorl 12(%rsp),%ebp - xorl %r13d,%eax - addl %ecx,%esi - xorl 32(%rsp),%ebp - roll $30,%r11d - addl %eax,%esi - roll $1,%ebp - movl %ebp,44(%rsp) - movl 48(%rsp),%edx - movl %r11d,%eax - movl %esi,%ecx - xorl 56(%rsp),%edx - xorl %edi,%eax - roll $5,%ecx - leal -899497514(%rbp,%r13,1),%r13d - xorl 16(%rsp),%edx - xorl %r12d,%eax - addl %ecx,%r13d - xorl 36(%rsp),%edx - roll $30,%edi - addl %eax,%r13d - roll $1,%edx - movl %edx,48(%rsp) - movl 52(%rsp),%ebp - movl %edi,%eax - movl %r13d,%ecx - xorl 60(%rsp),%ebp - xorl %esi,%eax - roll $5,%ecx - leal -899497514(%rdx,%r12,1),%r12d - xorl 20(%rsp),%ebp - xorl %r11d,%eax - addl %ecx,%r12d - xorl 40(%rsp),%ebp - roll $30,%esi - addl %eax,%r12d - roll $1,%ebp - movl 56(%rsp),%edx - movl %esi,%eax - movl %r12d,%ecx - xorl 0(%rsp),%edx - xorl %r13d,%eax - roll $5,%ecx - leal -899497514(%rbp,%r11,1),%r11d - xorl 24(%rsp),%edx - xorl %edi,%eax - addl %ecx,%r11d - xorl 44(%rsp),%edx - roll $30,%r13d - addl %eax,%r11d - roll $1,%edx - movl 60(%rsp),%ebp - movl %r13d,%eax - movl %r11d,%ecx - xorl 4(%rsp),%ebp - xorl %r12d,%eax - roll $5,%ecx - leal -899497514(%rdx,%rdi,1),%edi - xorl 28(%rsp),%ebp - xorl %esi,%eax - addl %ecx,%edi - xorl 48(%rsp),%ebp - roll $30,%r12d - addl %eax,%edi - roll $1,%ebp - movl %r12d,%eax - movl %edi,%ecx - xorl %r11d,%eax - leal -899497514(%rbp,%rsi,1),%esi - roll $5,%ecx - xorl %r13d,%eax - addl %ecx,%esi - roll $30,%r11d - addl %eax,%esi - addl 0(%r8),%esi - addl 4(%r8),%edi - addl 8(%r8),%r11d - addl 12(%r8),%r12d - addl 16(%r8),%r13d - movl %esi,0(%r8) - movl %edi,4(%r8) - movl %r11d,8(%r8) - movl %r12d,12(%r8) - movl %r13d,16(%r8) - - subq $1,%r10 - leaq 64(%r9),%r9 - jnz .Lloop - - movq 64(%rsp),%rsi - movq (%rsi),%r13 - movq 8(%rsi),%r12 - movq 16(%rsi),%rbp - movq 24(%rsi),%rbx - leaq 32(%rsi),%rsp -.Lepilogue: - .byte 0xf3,0xc3 -.size sha1_block_data_order,.-sha1_block_data_order -.type sha1_block_data_order_ssse3,@function -.align 16 -sha1_block_data_order_ssse3: -_ssse3_shortcut: - pushq %rbx - pushq %rbp - pushq %r12 - leaq -64(%rsp),%rsp - movq %rdi,%r8 - movq %rsi,%r9 - movq %rdx,%r10 - - shlq $6,%r10 - addq %r9,%r10 - leaq K_XX_XX(%rip),%r11 - - movl 0(%r8),%eax - movl 4(%r8),%ebx - movl 8(%r8),%ecx - movl 12(%r8),%edx - movl %ebx,%esi - movl 16(%r8),%ebp - - movdqa 64(%r11),%xmm6 - movdqa 0(%r11),%xmm9 - movdqu 0(%r9),%xmm0 - movdqu 16(%r9),%xmm1 - movdqu 32(%r9),%xmm2 - movdqu 48(%r9),%xmm3 -.byte 102,15,56,0,198 - addq $64,%r9 -.byte 102,15,56,0,206 -.byte 102,15,56,0,214 -.byte 102,15,56,0,222 - paddd %xmm9,%xmm0 - paddd %xmm9,%xmm1 - paddd %xmm9,%xmm2 - movdqa %xmm0,0(%rsp) - psubd %xmm9,%xmm0 - movdqa %xmm1,16(%rsp) - psubd %xmm9,%xmm1 - movdqa %xmm2,32(%rsp) - psubd %xmm9,%xmm2 - jmp .Loop_ssse3 -.align 16 -.Loop_ssse3: - movdqa %xmm1,%xmm4 - addl 0(%rsp),%ebp - xorl %edx,%ecx - movdqa %xmm3,%xmm8 -.byte 102,15,58,15,224,8 - movl %eax,%edi - roll $5,%eax - paddd %xmm3,%xmm9 - andl %ecx,%esi - xorl %edx,%ecx - psrldq $4,%xmm8 - xorl %edx,%esi - addl %eax,%ebp - pxor %xmm0,%xmm4 - rorl $2,%ebx - addl %esi,%ebp - pxor %xmm2,%xmm8 - addl 4(%rsp),%edx - xorl %ecx,%ebx - movl %ebp,%esi - roll $5,%ebp - pxor %xmm8,%xmm4 - andl %ebx,%edi - xorl %ecx,%ebx - movdqa %xmm9,48(%rsp) - xorl %ecx,%edi - addl %ebp,%edx - movdqa %xmm4,%xmm10 - movdqa %xmm4,%xmm8 - rorl $7,%eax - addl %edi,%edx - addl 8(%rsp),%ecx - xorl %ebx,%eax - pslldq $12,%xmm10 - paddd %xmm4,%xmm4 - movl %edx,%edi - roll $5,%edx - andl %eax,%esi - xorl %ebx,%eax - psrld $31,%xmm8 - xorl %ebx,%esi - addl %edx,%ecx - movdqa %xmm10,%xmm9 - rorl $7,%ebp - addl %esi,%ecx - psrld $30,%xmm10 - por %xmm8,%xmm4 - addl 12(%rsp),%ebx - xorl %eax,%ebp - movl %ecx,%esi - roll $5,%ecx - pslld $2,%xmm9 - pxor %xmm10,%xmm4 - andl %ebp,%edi - xorl %eax,%ebp - movdqa 0(%r11),%xmm10 - xorl %eax,%edi - addl %ecx,%ebx - pxor %xmm9,%xmm4 - rorl $7,%edx - addl %edi,%ebx - movdqa %xmm2,%xmm5 - addl 16(%rsp),%eax - xorl %ebp,%edx - movdqa %xmm4,%xmm9 -.byte 102,15,58,15,233,8 - movl %ebx,%edi - roll $5,%ebx - paddd %xmm4,%xmm10 - andl %edx,%esi - xorl %ebp,%edx - psrldq $4,%xmm9 - xorl %ebp,%esi - addl %ebx,%eax - pxor %xmm1,%xmm5 - rorl $7,%ecx - addl %esi,%eax - pxor %xmm3,%xmm9 - addl 20(%rsp),%ebp - xorl %edx,%ecx - movl %eax,%esi - roll $5,%eax - pxor %xmm9,%xmm5 - andl %ecx,%edi - xorl %edx,%ecx - movdqa %xmm10,0(%rsp) - xorl %edx,%edi - addl %eax,%ebp - movdqa %xmm5,%xmm8 - movdqa %xmm5,%xmm9 - rorl $7,%ebx - addl %edi,%ebp - addl 24(%rsp),%edx - xorl %ecx,%ebx - pslldq $12,%xmm8 - paddd %xmm5,%xmm5 - movl %ebp,%edi - roll $5,%ebp - andl %ebx,%esi - xorl %ecx,%ebx - psrld $31,%xmm9 - xorl %ecx,%esi - addl %ebp,%edx - movdqa %xmm8,%xmm10 - rorl $7,%eax - addl %esi,%edx - psrld $30,%xmm8 - por %xmm9,%xmm5 - addl 28(%rsp),%ecx - xorl %ebx,%eax - movl %edx,%esi - roll $5,%edx - pslld $2,%xmm10 - pxor %xmm8,%xmm5 - andl %eax,%edi - xorl %ebx,%eax - movdqa 16(%r11),%xmm8 - xorl %ebx,%edi - addl %edx,%ecx - pxor %xmm10,%xmm5 - rorl $7,%ebp - addl %edi,%ecx - movdqa %xmm3,%xmm6 - addl 32(%rsp),%ebx - xorl %eax,%ebp - movdqa %xmm5,%xmm10 -.byte 102,15,58,15,242,8 - movl %ecx,%edi - roll $5,%ecx - paddd %xmm5,%xmm8 - andl %ebp,%esi - xorl %eax,%ebp - psrldq $4,%xmm10 - xorl %eax,%esi - addl %ecx,%ebx - pxor %xmm2,%xmm6 - rorl $7,%edx - addl %esi,%ebx - pxor %xmm4,%xmm10 - addl 36(%rsp),%eax - xorl %ebp,%edx - movl %ebx,%esi - roll $5,%ebx - pxor %xmm10,%xmm6 - andl %edx,%edi - xorl %ebp,%edx - movdqa %xmm8,16(%rsp) - xorl %ebp,%edi - addl %ebx,%eax - movdqa %xmm6,%xmm9 - movdqa %xmm6,%xmm10 - rorl $7,%ecx - addl %edi,%eax - addl 40(%rsp),%ebp - xorl %edx,%ecx - pslldq $12,%xmm9 - paddd %xmm6,%xmm6 - movl %eax,%edi - roll $5,%eax - andl %ecx,%esi - xorl %edx,%ecx - psrld $31,%xmm10 - xorl %edx,%esi - addl %eax,%ebp - movdqa %xmm9,%xmm8 - rorl $7,%ebx - addl %esi,%ebp - psrld $30,%xmm9 - por %xmm10,%xmm6 - addl 44(%rsp),%edx - xorl %ecx,%ebx - movl %ebp,%esi - roll $5,%ebp - pslld $2,%xmm8 - pxor %xmm9,%xmm6 - andl %ebx,%edi - xorl %ecx,%ebx - movdqa 16(%r11),%xmm9 - xorl %ecx,%edi - addl %ebp,%edx - pxor %xmm8,%xmm6 - rorl $7,%eax - addl %edi,%edx - movdqa %xmm4,%xmm7 - addl 48(%rsp),%ecx - xorl %ebx,%eax - movdqa %xmm6,%xmm8 -.byte 102,15,58,15,251,8 - movl %edx,%edi - roll $5,%edx - paddd %xmm6,%xmm9 - andl %eax,%esi - xorl %ebx,%eax - psrldq $4,%xmm8 - xorl %ebx,%esi - addl %edx,%ecx - pxor %xmm3,%xmm7 - rorl $7,%ebp - addl %esi,%ecx - pxor %xmm5,%xmm8 - addl 52(%rsp),%ebx - xorl %eax,%ebp - movl %ecx,%esi - roll $5,%ecx - pxor %xmm8,%xmm7 - andl %ebp,%edi - xorl %eax,%ebp - movdqa %xmm9,32(%rsp) - xorl %eax,%edi - addl %ecx,%ebx - movdqa %xmm7,%xmm10 - movdqa %xmm7,%xmm8 - rorl $7,%edx - addl %edi,%ebx - addl 56(%rsp),%eax - xorl %ebp,%edx - pslldq $12,%xmm10 - paddd %xmm7,%xmm7 - movl %ebx,%edi - roll $5,%ebx - andl %edx,%esi - xorl %ebp,%edx - psrld $31,%xmm8 - xorl %ebp,%esi - addl %ebx,%eax - movdqa %xmm10,%xmm9 - rorl $7,%ecx - addl %esi,%eax - psrld $30,%xmm10 - por %xmm8,%xmm7 - addl 60(%rsp),%ebp - xorl %edx,%ecx - movl %eax,%esi - roll $5,%eax - pslld $2,%xmm9 - pxor %xmm10,%xmm7 - andl %ecx,%edi - xorl %edx,%ecx - movdqa 16(%r11),%xmm10 - xorl %edx,%edi - addl %eax,%ebp - pxor %xmm9,%xmm7 - rorl $7,%ebx - addl %edi,%ebp - movdqa %xmm7,%xmm9 - addl 0(%rsp),%edx - pxor %xmm4,%xmm0 -.byte 102,68,15,58,15,206,8 - xorl %ecx,%ebx - movl %ebp,%edi - roll $5,%ebp - pxor %xmm1,%xmm0 - andl %ebx,%esi - xorl %ecx,%ebx - movdqa %xmm10,%xmm8 - paddd %xmm7,%xmm10 - xorl %ecx,%esi - addl %ebp,%edx - pxor %xmm9,%xmm0 - rorl $7,%eax - addl %esi,%edx - addl 4(%rsp),%ecx - xorl %ebx,%eax - movdqa %xmm0,%xmm9 - movdqa %xmm10,48(%rsp) - movl %edx,%esi - roll $5,%edx - andl %eax,%edi - xorl %ebx,%eax - pslld $2,%xmm0 - xorl %ebx,%edi - addl %edx,%ecx - psrld $30,%xmm9 - rorl $7,%ebp - addl %edi,%ecx - addl 8(%rsp),%ebx - xorl %eax,%ebp - movl %ecx,%edi - roll $5,%ecx - por %xmm9,%xmm0 - andl %ebp,%esi - xorl %eax,%ebp - movdqa %xmm0,%xmm10 - xorl %eax,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 12(%rsp),%eax - xorl %ebp,%edx - movl %ebx,%esi - roll $5,%ebx - andl %edx,%edi - xorl %ebp,%edx - xorl %ebp,%edi - addl %ebx,%eax - rorl $7,%ecx - addl %edi,%eax - addl 16(%rsp),%ebp - pxor %xmm5,%xmm1 -.byte 102,68,15,58,15,215,8 - xorl %edx,%esi - movl %eax,%edi - roll $5,%eax - pxor %xmm2,%xmm1 - xorl %ecx,%esi - addl %eax,%ebp - movdqa %xmm8,%xmm9 - paddd %xmm0,%xmm8 - rorl $7,%ebx - addl %esi,%ebp - pxor %xmm10,%xmm1 - addl 20(%rsp),%edx - xorl %ecx,%edi - movl %ebp,%esi - roll $5,%ebp - movdqa %xmm1,%xmm10 - movdqa %xmm8,0(%rsp) - xorl %ebx,%edi - addl %ebp,%edx - rorl $7,%eax - addl %edi,%edx - pslld $2,%xmm1 - addl 24(%rsp),%ecx - xorl %ebx,%esi - psrld $30,%xmm10 - movl %edx,%edi - roll $5,%edx - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%ebp - addl %esi,%ecx - por %xmm10,%xmm1 - addl 28(%rsp),%ebx - xorl %eax,%edi - movdqa %xmm1,%xmm8 - movl %ecx,%esi - roll $5,%ecx - xorl %ebp,%edi - addl %ecx,%ebx - rorl $7,%edx - addl %edi,%ebx - addl 32(%rsp),%eax - pxor %xmm6,%xmm2 -.byte 102,68,15,58,15,192,8 - xorl %ebp,%esi - movl %ebx,%edi - roll $5,%ebx - pxor %xmm3,%xmm2 - xorl %edx,%esi - addl %ebx,%eax - movdqa 32(%r11),%xmm10 - paddd %xmm1,%xmm9 - rorl $7,%ecx - addl %esi,%eax - pxor %xmm8,%xmm2 - addl 36(%rsp),%ebp - xorl %edx,%edi - movl %eax,%esi - roll $5,%eax - movdqa %xmm2,%xmm8 - movdqa %xmm9,16(%rsp) - xorl %ecx,%edi - addl %eax,%ebp - rorl $7,%ebx - addl %edi,%ebp - pslld $2,%xmm2 - addl 40(%rsp),%edx - xorl %ecx,%esi - psrld $30,%xmm8 - movl %ebp,%edi - roll $5,%ebp - xorl %ebx,%esi - addl %ebp,%edx - rorl $7,%eax - addl %esi,%edx - por %xmm8,%xmm2 - addl 44(%rsp),%ecx - xorl %ebx,%edi - movdqa %xmm2,%xmm9 - movl %edx,%esi - roll $5,%edx - xorl %eax,%edi - addl %edx,%ecx - rorl $7,%ebp - addl %edi,%ecx - addl 48(%rsp),%ebx - pxor %xmm7,%xmm3 -.byte 102,68,15,58,15,201,8 - xorl %eax,%esi - movl %ecx,%edi - roll $5,%ecx - pxor %xmm4,%xmm3 - xorl %ebp,%esi - addl %ecx,%ebx - movdqa %xmm10,%xmm8 - paddd %xmm2,%xmm10 - rorl $7,%edx - addl %esi,%ebx - pxor %xmm9,%xmm3 - addl 52(%rsp),%eax - xorl %ebp,%edi - movl %ebx,%esi - roll $5,%ebx - movdqa %xmm3,%xmm9 - movdqa %xmm10,32(%rsp) - xorl %edx,%edi - addl %ebx,%eax - rorl $7,%ecx - addl %edi,%eax - pslld $2,%xmm3 - addl 56(%rsp),%ebp - xorl %edx,%esi - psrld $30,%xmm9 - movl %eax,%edi - roll $5,%eax - xorl %ecx,%esi - addl %eax,%ebp - rorl $7,%ebx - addl %esi,%ebp - por %xmm9,%xmm3 - addl 60(%rsp),%edx - xorl %ecx,%edi - movdqa %xmm3,%xmm10 - movl %ebp,%esi - roll $5,%ebp - xorl %ebx,%edi - addl %ebp,%edx - rorl $7,%eax - addl %edi,%edx - addl 0(%rsp),%ecx - pxor %xmm0,%xmm4 -.byte 102,68,15,58,15,210,8 - xorl %ebx,%esi - movl %edx,%edi - roll $5,%edx - pxor %xmm5,%xmm4 - xorl %eax,%esi - addl %edx,%ecx - movdqa %xmm8,%xmm9 - paddd %xmm3,%xmm8 - rorl $7,%ebp - addl %esi,%ecx - pxor %xmm10,%xmm4 - addl 4(%rsp),%ebx - xorl %eax,%edi - movl %ecx,%esi - roll $5,%ecx - movdqa %xmm4,%xmm10 - movdqa %xmm8,48(%rsp) - xorl %ebp,%edi - addl %ecx,%ebx - rorl $7,%edx - addl %edi,%ebx - pslld $2,%xmm4 - addl 8(%rsp),%eax - xorl %ebp,%esi - psrld $30,%xmm10 - movl %ebx,%edi - roll $5,%ebx - xorl %edx,%esi - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - por %xmm10,%xmm4 - addl 12(%rsp),%ebp - xorl %edx,%edi - movdqa %xmm4,%xmm8 - movl %eax,%esi - roll $5,%eax - xorl %ecx,%edi - addl %eax,%ebp - rorl $7,%ebx - addl %edi,%ebp - addl 16(%rsp),%edx - pxor %xmm1,%xmm5 -.byte 102,68,15,58,15,195,8 - xorl %ecx,%esi - movl %ebp,%edi - roll $5,%ebp - pxor %xmm6,%xmm5 - xorl %ebx,%esi - addl %ebp,%edx - movdqa %xmm9,%xmm10 - paddd %xmm4,%xmm9 - rorl $7,%eax - addl %esi,%edx - pxor %xmm8,%xmm5 - addl 20(%rsp),%ecx - xorl %ebx,%edi - movl %edx,%esi - roll $5,%edx - movdqa %xmm5,%xmm8 - movdqa %xmm9,0(%rsp) - xorl %eax,%edi - addl %edx,%ecx - rorl $7,%ebp - addl %edi,%ecx - pslld $2,%xmm5 - addl 24(%rsp),%ebx - xorl %eax,%esi - psrld $30,%xmm8 - movl %ecx,%edi - roll $5,%ecx - xorl %ebp,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - por %xmm8,%xmm5 - addl 28(%rsp),%eax - xorl %ebp,%edi - movdqa %xmm5,%xmm9 - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%edi - addl %ebx,%eax - rorl $7,%ecx - addl %edi,%eax - movl %ecx,%edi - pxor %xmm2,%xmm6 -.byte 102,68,15,58,15,204,8 - xorl %edx,%ecx - addl 32(%rsp),%ebp - andl %edx,%edi - pxor %xmm7,%xmm6 - andl %ecx,%esi - rorl $7,%ebx - movdqa %xmm10,%xmm8 - paddd %xmm5,%xmm10 - addl %edi,%ebp - movl %eax,%edi - pxor %xmm9,%xmm6 - roll $5,%eax - addl %esi,%ebp - xorl %edx,%ecx - addl %eax,%ebp - movdqa %xmm6,%xmm9 - movdqa %xmm10,16(%rsp) - movl %ebx,%esi - xorl %ecx,%ebx - addl 36(%rsp),%edx - andl %ecx,%esi - pslld $2,%xmm6 - andl %ebx,%edi - rorl $7,%eax - psrld $30,%xmm9 - addl %esi,%edx - movl %ebp,%esi - roll $5,%ebp - addl %edi,%edx - xorl %ecx,%ebx - addl %ebp,%edx - por %xmm9,%xmm6 - movl %eax,%edi - xorl %ebx,%eax - movdqa %xmm6,%xmm10 - addl 40(%rsp),%ecx - andl %ebx,%edi - andl %eax,%esi - rorl $7,%ebp - addl %edi,%ecx - movl %edx,%edi - roll $5,%edx - addl %esi,%ecx - xorl %ebx,%eax - addl %edx,%ecx - movl %ebp,%esi - xorl %eax,%ebp - addl 44(%rsp),%ebx - andl %eax,%esi - andl %ebp,%edi - rorl $7,%edx - addl %esi,%ebx - movl %ecx,%esi - roll $5,%ecx - addl %edi,%ebx - xorl %eax,%ebp - addl %ecx,%ebx - movl %edx,%edi - pxor %xmm3,%xmm7 -.byte 102,68,15,58,15,213,8 - xorl %ebp,%edx - addl 48(%rsp),%eax - andl %ebp,%edi - pxor %xmm0,%xmm7 - andl %edx,%esi - rorl $7,%ecx - movdqa 48(%r11),%xmm9 - paddd %xmm6,%xmm8 - addl %edi,%eax - movl %ebx,%edi - pxor %xmm10,%xmm7 - roll $5,%ebx - addl %esi,%eax - xorl %ebp,%edx - addl %ebx,%eax - movdqa %xmm7,%xmm10 - movdqa %xmm8,32(%rsp) - movl %ecx,%esi - xorl %edx,%ecx - addl 52(%rsp),%ebp - andl %edx,%esi - pslld $2,%xmm7 - andl %ecx,%edi - rorl $7,%ebx - psrld $30,%xmm10 - addl %esi,%ebp - movl %eax,%esi - roll $5,%eax - addl %edi,%ebp - xorl %edx,%ecx - addl %eax,%ebp - por %xmm10,%xmm7 - movl %ebx,%edi - xorl %ecx,%ebx - movdqa %xmm7,%xmm8 - addl 56(%rsp),%edx - andl %ecx,%edi - andl %ebx,%esi - rorl $7,%eax - addl %edi,%edx - movl %ebp,%edi - roll $5,%ebp - addl %esi,%edx - xorl %ecx,%ebx - addl %ebp,%edx - movl %eax,%esi - xorl %ebx,%eax - addl 60(%rsp),%ecx - andl %ebx,%esi - andl %eax,%edi - rorl $7,%ebp - addl %esi,%ecx - movl %edx,%esi - roll $5,%edx - addl %edi,%ecx - xorl %ebx,%eax - addl %edx,%ecx - movl %ebp,%edi - pxor %xmm4,%xmm0 -.byte 102,68,15,58,15,198,8 - xorl %eax,%ebp - addl 0(%rsp),%ebx - andl %eax,%edi - pxor %xmm1,%xmm0 - andl %ebp,%esi - rorl $7,%edx - movdqa %xmm9,%xmm10 - paddd %xmm7,%xmm9 - addl %edi,%ebx - movl %ecx,%edi - pxor %xmm8,%xmm0 - roll $5,%ecx - addl %esi,%ebx - xorl %eax,%ebp - addl %ecx,%ebx - movdqa %xmm0,%xmm8 - movdqa %xmm9,48(%rsp) - movl %edx,%esi - xorl %ebp,%edx - addl 4(%rsp),%eax - andl %ebp,%esi - pslld $2,%xmm0 - andl %edx,%edi - rorl $7,%ecx - psrld $30,%xmm8 - addl %esi,%eax - movl %ebx,%esi - roll $5,%ebx - addl %edi,%eax - xorl %ebp,%edx - addl %ebx,%eax - por %xmm8,%xmm0 - movl %ecx,%edi - xorl %edx,%ecx - movdqa %xmm0,%xmm9 - addl 8(%rsp),%ebp - andl %edx,%edi - andl %ecx,%esi - rorl $7,%ebx - addl %edi,%ebp - movl %eax,%edi - roll $5,%eax - addl %esi,%ebp - xorl %edx,%ecx - addl %eax,%ebp - movl %ebx,%esi - xorl %ecx,%ebx - addl 12(%rsp),%edx - andl %ecx,%esi - andl %ebx,%edi - rorl $7,%eax - addl %esi,%edx - movl %ebp,%esi - roll $5,%ebp - addl %edi,%edx - xorl %ecx,%ebx - addl %ebp,%edx - movl %eax,%edi - pxor %xmm5,%xmm1 -.byte 102,68,15,58,15,207,8 - xorl %ebx,%eax - addl 16(%rsp),%ecx - andl %ebx,%edi - pxor %xmm2,%xmm1 - andl %eax,%esi - rorl $7,%ebp - movdqa %xmm10,%xmm8 - paddd %xmm0,%xmm10 - addl %edi,%ecx - movl %edx,%edi - pxor %xmm9,%xmm1 - roll $5,%edx - addl %esi,%ecx - xorl %ebx,%eax - addl %edx,%ecx - movdqa %xmm1,%xmm9 - movdqa %xmm10,0(%rsp) - movl %ebp,%esi - xorl %eax,%ebp - addl 20(%rsp),%ebx - andl %eax,%esi - pslld $2,%xmm1 - andl %ebp,%edi - rorl $7,%edx - psrld $30,%xmm9 - addl %esi,%ebx - movl %ecx,%esi - roll $5,%ecx - addl %edi,%ebx - xorl %eax,%ebp - addl %ecx,%ebx - por %xmm9,%xmm1 - movl %edx,%edi - xorl %ebp,%edx - movdqa %xmm1,%xmm10 - addl 24(%rsp),%eax - andl %ebp,%edi - andl %edx,%esi - rorl $7,%ecx - addl %edi,%eax - movl %ebx,%edi - roll $5,%ebx - addl %esi,%eax - xorl %ebp,%edx - addl %ebx,%eax - movl %ecx,%esi - xorl %edx,%ecx - addl 28(%rsp),%ebp - andl %edx,%esi - andl %ecx,%edi - rorl $7,%ebx - addl %esi,%ebp - movl %eax,%esi - roll $5,%eax - addl %edi,%ebp - xorl %edx,%ecx - addl %eax,%ebp - movl %ebx,%edi - pxor %xmm6,%xmm2 -.byte 102,68,15,58,15,208,8 - xorl %ecx,%ebx - addl 32(%rsp),%edx - andl %ecx,%edi - pxor %xmm3,%xmm2 - andl %ebx,%esi - rorl $7,%eax - movdqa %xmm8,%xmm9 - paddd %xmm1,%xmm8 - addl %edi,%edx - movl %ebp,%edi - pxor %xmm10,%xmm2 - roll $5,%ebp - addl %esi,%edx - xorl %ecx,%ebx - addl %ebp,%edx - movdqa %xmm2,%xmm10 - movdqa %xmm8,16(%rsp) - movl %eax,%esi - xorl %ebx,%eax - addl 36(%rsp),%ecx - andl %ebx,%esi - pslld $2,%xmm2 - andl %eax,%edi - rorl $7,%ebp - psrld $30,%xmm10 - addl %esi,%ecx - movl %edx,%esi - roll $5,%edx - addl %edi,%ecx - xorl %ebx,%eax - addl %edx,%ecx - por %xmm10,%xmm2 - movl %ebp,%edi - xorl %eax,%ebp - movdqa %xmm2,%xmm8 - addl 40(%rsp),%ebx - andl %eax,%edi - andl %ebp,%esi - rorl $7,%edx - addl %edi,%ebx - movl %ecx,%edi - roll $5,%ecx - addl %esi,%ebx - xorl %eax,%ebp - addl %ecx,%ebx - movl %edx,%esi - xorl %ebp,%edx - addl 44(%rsp),%eax - andl %ebp,%esi - andl %edx,%edi - rorl $7,%ecx - addl %esi,%eax - movl %ebx,%esi - roll $5,%ebx - addl %edi,%eax - xorl %ebp,%edx - addl %ebx,%eax - addl 48(%rsp),%ebp - pxor %xmm7,%xmm3 -.byte 102,68,15,58,15,193,8 - xorl %edx,%esi - movl %eax,%edi - roll $5,%eax - pxor %xmm4,%xmm3 - xorl %ecx,%esi - addl %eax,%ebp - movdqa %xmm9,%xmm10 - paddd %xmm2,%xmm9 - rorl $7,%ebx - addl %esi,%ebp - pxor %xmm8,%xmm3 - addl 52(%rsp),%edx - xorl %ecx,%edi - movl %ebp,%esi - roll $5,%ebp - movdqa %xmm3,%xmm8 - movdqa %xmm9,32(%rsp) - xorl %ebx,%edi - addl %ebp,%edx - rorl $7,%eax - addl %edi,%edx - pslld $2,%xmm3 - addl 56(%rsp),%ecx - xorl %ebx,%esi - psrld $30,%xmm8 - movl %edx,%edi - roll $5,%edx - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%ebp - addl %esi,%ecx - por %xmm8,%xmm3 - addl 60(%rsp),%ebx - xorl %eax,%edi - movl %ecx,%esi - roll $5,%ecx - xorl %ebp,%edi - addl %ecx,%ebx - rorl $7,%edx - addl %edi,%ebx - addl 0(%rsp),%eax - paddd %xmm3,%xmm10 - xorl %ebp,%esi - movl %ebx,%edi - roll $5,%ebx - xorl %edx,%esi - movdqa %xmm10,48(%rsp) - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - addl 4(%rsp),%ebp - xorl %edx,%edi - movl %eax,%esi - roll $5,%eax - xorl %ecx,%edi - addl %eax,%ebp - rorl $7,%ebx - addl %edi,%ebp - addl 8(%rsp),%edx - xorl %ecx,%esi - movl %ebp,%edi - roll $5,%ebp - xorl %ebx,%esi - addl %ebp,%edx - rorl $7,%eax - addl %esi,%edx - addl 12(%rsp),%ecx - xorl %ebx,%edi - movl %edx,%esi - roll $5,%edx - xorl %eax,%edi - addl %edx,%ecx - rorl $7,%ebp - addl %edi,%ecx - cmpq %r10,%r9 - je .Ldone_ssse3 - movdqa 64(%r11),%xmm6 - movdqa 0(%r11),%xmm9 - movdqu 0(%r9),%xmm0 - movdqu 16(%r9),%xmm1 - movdqu 32(%r9),%xmm2 - movdqu 48(%r9),%xmm3 -.byte 102,15,56,0,198 - addq $64,%r9 - addl 16(%rsp),%ebx - xorl %eax,%esi -.byte 102,15,56,0,206 - movl %ecx,%edi - roll $5,%ecx - paddd %xmm9,%xmm0 - xorl %ebp,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - movdqa %xmm0,0(%rsp) - addl 20(%rsp),%eax - xorl %ebp,%edi - psubd %xmm9,%xmm0 - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%edi - addl %ebx,%eax - rorl $7,%ecx - addl %edi,%eax - addl 24(%rsp),%ebp - xorl %edx,%esi - movl %eax,%edi - roll $5,%eax - xorl %ecx,%esi - addl %eax,%ebp - rorl $7,%ebx - addl %esi,%ebp - addl 28(%rsp),%edx - xorl %ecx,%edi - movl %ebp,%esi - roll $5,%ebp - xorl %ebx,%edi - addl %ebp,%edx - rorl $7,%eax - addl %edi,%edx - addl 32(%rsp),%ecx - xorl %ebx,%esi -.byte 102,15,56,0,214 - movl %edx,%edi - roll $5,%edx - paddd %xmm9,%xmm1 - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%ebp - addl %esi,%ecx - movdqa %xmm1,16(%rsp) - addl 36(%rsp),%ebx - xorl %eax,%edi - psubd %xmm9,%xmm1 - movl %ecx,%esi - roll $5,%ecx - xorl %ebp,%edi - addl %ecx,%ebx - rorl $7,%edx - addl %edi,%ebx - addl 40(%rsp),%eax - xorl %ebp,%esi - movl %ebx,%edi - roll $5,%ebx - xorl %edx,%esi - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - addl 44(%rsp),%ebp - xorl %edx,%edi - movl %eax,%esi - roll $5,%eax - xorl %ecx,%edi - addl %eax,%ebp - rorl $7,%ebx - addl %edi,%ebp - addl 48(%rsp),%edx - xorl %ecx,%esi -.byte 102,15,56,0,222 - movl %ebp,%edi - roll $5,%ebp - paddd %xmm9,%xmm2 - xorl %ebx,%esi - addl %ebp,%edx - rorl $7,%eax - addl %esi,%edx - movdqa %xmm2,32(%rsp) - addl 52(%rsp),%ecx - xorl %ebx,%edi - psubd %xmm9,%xmm2 - movl %edx,%esi - roll $5,%edx - xorl %eax,%edi - addl %edx,%ecx - rorl $7,%ebp - addl %edi,%ecx - addl 56(%rsp),%ebx - xorl %eax,%esi - movl %ecx,%edi - roll $5,%ecx - xorl %ebp,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 60(%rsp),%eax - xorl %ebp,%edi - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%edi - addl %ebx,%eax - rorl $7,%ecx - addl %edi,%eax - addl 0(%r8),%eax - addl 4(%r8),%esi - addl 8(%r8),%ecx - addl 12(%r8),%edx - movl %eax,0(%r8) - addl 16(%r8),%ebp - movl %esi,4(%r8) - movl %esi,%ebx - movl %ecx,8(%r8) - movl %edx,12(%r8) - movl %ebp,16(%r8) - jmp .Loop_ssse3 - -.align 16 -.Ldone_ssse3: - addl 16(%rsp),%ebx - xorl %eax,%esi - movl %ecx,%edi - roll $5,%ecx - xorl %ebp,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 20(%rsp),%eax - xorl %ebp,%edi - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%edi - addl %ebx,%eax - rorl $7,%ecx - addl %edi,%eax - addl 24(%rsp),%ebp - xorl %edx,%esi - movl %eax,%edi - roll $5,%eax - xorl %ecx,%esi - addl %eax,%ebp - rorl $7,%ebx - addl %esi,%ebp - addl 28(%rsp),%edx - xorl %ecx,%edi - movl %ebp,%esi - roll $5,%ebp - xorl %ebx,%edi - addl %ebp,%edx - rorl $7,%eax - addl %edi,%edx - addl 32(%rsp),%ecx - xorl %ebx,%esi - movl %edx,%edi - roll $5,%edx - xorl %eax,%esi - addl %edx,%ecx - rorl $7,%ebp - addl %esi,%ecx - addl 36(%rsp),%ebx - xorl %eax,%edi - movl %ecx,%esi - roll $5,%ecx - xorl %ebp,%edi - addl %ecx,%ebx - rorl $7,%edx - addl %edi,%ebx - addl 40(%rsp),%eax - xorl %ebp,%esi - movl %ebx,%edi - roll $5,%ebx - xorl %edx,%esi - addl %ebx,%eax - rorl $7,%ecx - addl %esi,%eax - addl 44(%rsp),%ebp - xorl %edx,%edi - movl %eax,%esi - roll $5,%eax - xorl %ecx,%edi - addl %eax,%ebp - rorl $7,%ebx - addl %edi,%ebp - addl 48(%rsp),%edx - xorl %ecx,%esi - movl %ebp,%edi - roll $5,%ebp - xorl %ebx,%esi - addl %ebp,%edx - rorl $7,%eax - addl %esi,%edx - addl 52(%rsp),%ecx - xorl %ebx,%edi - movl %edx,%esi - roll $5,%edx - xorl %eax,%edi - addl %edx,%ecx - rorl $7,%ebp - addl %edi,%ecx - addl 56(%rsp),%ebx - xorl %eax,%esi - movl %ecx,%edi - roll $5,%ecx - xorl %ebp,%esi - addl %ecx,%ebx - rorl $7,%edx - addl %esi,%ebx - addl 60(%rsp),%eax - xorl %ebp,%edi - movl %ebx,%esi - roll $5,%ebx - xorl %edx,%edi - addl %ebx,%eax - rorl $7,%ecx - addl %edi,%eax - addl 0(%r8),%eax - addl 4(%r8),%esi - addl 8(%r8),%ecx - movl %eax,0(%r8) - addl 12(%r8),%edx - movl %esi,4(%r8) - addl 16(%r8),%ebp - movl %ecx,8(%r8) - movl %edx,12(%r8) - movl %ebp,16(%r8) - leaq 64(%rsp),%rsi - movq 0(%rsi),%r12 - movq 8(%rsi),%rbp - movq 16(%rsi),%rbx - leaq 24(%rsi),%rsp -.Lepilogue_ssse3: - .byte 0xf3,0xc3 -.size sha1_block_data_order_ssse3,.-sha1_block_data_order_ssse3 -.align 64 -K_XX_XX: -.long 0x5a827999,0x5a827999,0x5a827999,0x5a827999 -.long 0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1 -.long 0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc -.long 0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6 -.long 0x00010203,0x04050607,0x08090a0b,0x0c0d0e0f -.byte 83,72,65,49,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0 -.align 64 diff --git a/app/openssl/crypto/sha/asm/sha1-x86_64.pl b/app/openssl/crypto/sha/asm/sha1-x86_64.pl deleted file mode 100755 index f15c7ec3..00000000 --- a/app/openssl/crypto/sha/asm/sha1-x86_64.pl +++ /dev/null @@ -1,1261 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== -# -# sha1_block procedure for x86_64. -# -# It was brought to my attention that on EM64T compiler-generated code -# was far behind 32-bit assembler implementation. This is unlike on -# Opteron where compiler-generated code was only 15% behind 32-bit -# assembler, which originally made it hard to motivate the effort. -# There was suggestion to mechanically translate 32-bit code, but I -# dismissed it, reasoning that x86_64 offers enough register bank -# capacity to fully utilize SHA-1 parallelism. Therefore this fresh -# implementation:-) However! While 64-bit code does perform better -# on Opteron, I failed to beat 32-bit assembler on EM64T core. Well, -# x86_64 does offer larger *addressable* bank, but out-of-order core -# reaches for even more registers through dynamic aliasing, and EM64T -# core must have managed to run-time optimize even 32-bit code just as -# good as 64-bit one. Performance improvement is summarized in the -# following table: -# -# gcc 3.4 32-bit asm cycles/byte -# Opteron +45% +20% 6.8 -# Xeon P4 +65% +0% 9.9 -# Core2 +60% +10% 7.0 - -# August 2009. -# -# The code was revised to minimize code size and to maximize -# "distance" between instructions producing input to 'lea' -# instruction and the 'lea' instruction itself, which is essential -# for Intel Atom core. - -# October 2010. -# -# Add SSSE3, Supplemental[!] SSE3, implementation. The idea behind it -# is to offload message schedule denoted by Wt in NIST specification, -# or Xupdate in OpenSSL source, to SIMD unit. See sha1-586.pl module -# for background and implementation details. The only difference from -# 32-bit code is that 64-bit code doesn't have to spill @X[] elements -# to free temporary registers. - -# April 2011. -# -# Add AVX code path. See sha1-586.pl for further information. - -###################################################################### -# Current performance is summarized in following table. Numbers are -# CPU clock cycles spent to process single byte (less is better). -# -# x86_64 SSSE3 AVX -# P4 9.8 - -# Opteron 6.6 - -# Core2 6.7 6.1/+10% - -# Atom 11.0 9.7/+13% - -# Westmere 7.1 5.6/+27% - -# Sandy Bridge 7.9 6.3/+25% 5.2/+51% - -$flavour = shift; -$output = shift; -if ($flavour =~ /\./) { $output = $flavour; undef $flavour; } - -$win64=0; $win64=1 if ($flavour =~ /[nm]asm|mingw64/ || $output =~ /\.asm$/); - -$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; -( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or -( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or -die "can't locate x86_64-xlate.pl"; - -$avx=1 if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1` - =~ /GNU assembler version ([2-9]\.[0-9]+)/ && - $1>=2.19); -$avx=1 if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) && - `nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)/ && - $1>=2.09); -$avx=1 if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) && - `ml64 2>&1` =~ /Version ([0-9]+)\./ && - $1>=10); - -open OUT,"| \"$^X\" $xlate $flavour $output"; -*STDOUT=*OUT; - -$ctx="%rdi"; # 1st arg -$inp="%rsi"; # 2nd arg -$num="%rdx"; # 3rd arg - -# reassign arguments in order to produce more compact code -$ctx="%r8"; -$inp="%r9"; -$num="%r10"; - -$t0="%eax"; -$t1="%ebx"; -$t2="%ecx"; -@xi=("%edx","%ebp"); -$A="%esi"; -$B="%edi"; -$C="%r11d"; -$D="%r12d"; -$E="%r13d"; - -@V=($A,$B,$C,$D,$E); - -sub BODY_00_19 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___ if ($i==0); - mov `4*$i`($inp),$xi[0] - bswap $xi[0] - mov $xi[0],`4*$i`(%rsp) -___ -$code.=<<___ if ($i<15); - mov $c,$t0 - mov `4*$j`($inp),$xi[1] - mov $a,$t2 - xor $d,$t0 - bswap $xi[1] - rol \$5,$t2 - lea 0x5a827999($xi[0],$e),$e - and $b,$t0 - mov $xi[1],`4*$j`(%rsp) - add $t2,$e - xor $d,$t0 - rol \$30,$b - add $t0,$e -___ -$code.=<<___ if ($i>=15); - mov `4*($j%16)`(%rsp),$xi[1] - mov $c,$t0 - mov $a,$t2 - xor `4*(($j+2)%16)`(%rsp),$xi[1] - xor $d,$t0 - rol \$5,$t2 - xor `4*(($j+8)%16)`(%rsp),$xi[1] - and $b,$t0 - lea 0x5a827999($xi[0],$e),$e - xor `4*(($j+13)%16)`(%rsp),$xi[1] - xor $d,$t0 - rol \$1,$xi[1] - add $t2,$e - rol \$30,$b - mov $xi[1],`4*($j%16)`(%rsp) - add $t0,$e -___ -unshift(@xi,pop(@xi)); -} - -sub BODY_20_39 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -my $K=($i<40)?0x6ed9eba1:0xca62c1d6; -$code.=<<___ if ($i<79); - mov `4*($j%16)`(%rsp),$xi[1] - mov $c,$t0 - mov $a,$t2 - xor `4*(($j+2)%16)`(%rsp),$xi[1] - xor $b,$t0 - rol \$5,$t2 - lea $K($xi[0],$e),$e - xor `4*(($j+8)%16)`(%rsp),$xi[1] - xor $d,$t0 - add $t2,$e - xor `4*(($j+13)%16)`(%rsp),$xi[1] - rol \$30,$b - add $t0,$e - rol \$1,$xi[1] -___ -$code.=<<___ if ($i<76); - mov $xi[1],`4*($j%16)`(%rsp) -___ -$code.=<<___ if ($i==79); - mov $c,$t0 - mov $a,$t2 - xor $b,$t0 - lea $K($xi[0],$e),$e - rol \$5,$t2 - xor $d,$t0 - add $t2,$e - rol \$30,$b - add $t0,$e -___ -unshift(@xi,pop(@xi)); -} - -sub BODY_40_59 { -my ($i,$a,$b,$c,$d,$e)=@_; -my $j=$i+1; -$code.=<<___; - mov `4*($j%16)`(%rsp),$xi[1] - mov $c,$t0 - mov $c,$t1 - xor `4*(($j+2)%16)`(%rsp),$xi[1] - and $d,$t0 - mov $a,$t2 - xor `4*(($j+8)%16)`(%rsp),$xi[1] - xor $d,$t1 - lea 0x8f1bbcdc($xi[0],$e),$e - rol \$5,$t2 - xor `4*(($j+13)%16)`(%rsp),$xi[1] - add $t0,$e - and $b,$t1 - rol \$1,$xi[1] - add $t1,$e - rol \$30,$b - mov $xi[1],`4*($j%16)`(%rsp) - add $t2,$e -___ -unshift(@xi,pop(@xi)); -} - -$code.=<<___; -.text -.extern OPENSSL_ia32cap_P - -.globl sha1_block_data_order -.type sha1_block_data_order,\@function,3 -.align 16 -sha1_block_data_order: - mov OPENSSL_ia32cap_P+0(%rip),%r9d - mov OPENSSL_ia32cap_P+4(%rip),%r8d - test \$`1<<9`,%r8d # check SSSE3 bit - jz .Lialu -___ -$code.=<<___ if ($avx); - and \$`1<<28`,%r8d # mask AVX bit - and \$`1<<30`,%r9d # mask "Intel CPU" bit - or %r9d,%r8d - cmp \$`1<<28|1<<30`,%r8d - je _avx_shortcut -___ -$code.=<<___; - jmp _ssse3_shortcut - -.align 16 -.Lialu: - push %rbx - push %rbp - push %r12 - push %r13 - mov %rsp,%r11 - mov %rdi,$ctx # reassigned argument - sub \$`8+16*4`,%rsp - mov %rsi,$inp # reassigned argument - and \$-64,%rsp - mov %rdx,$num # reassigned argument - mov %r11,`16*4`(%rsp) -.Lprologue: - - mov 0($ctx),$A - mov 4($ctx),$B - mov 8($ctx),$C - mov 12($ctx),$D - mov 16($ctx),$E - jmp .Lloop - -.align 16 -.Lloop: -___ -for($i=0;$i<20;$i++) { &BODY_00_19($i,@V); unshift(@V,pop(@V)); } -for(;$i<40;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -for(;$i<60;$i++) { &BODY_40_59($i,@V); unshift(@V,pop(@V)); } -for(;$i<80;$i++) { &BODY_20_39($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - add 0($ctx),$A - add 4($ctx),$B - add 8($ctx),$C - add 12($ctx),$D - add 16($ctx),$E - mov $A,0($ctx) - mov $B,4($ctx) - mov $C,8($ctx) - mov $D,12($ctx) - mov $E,16($ctx) - - sub \$1,$num - lea `16*4`($inp),$inp - jnz .Lloop - - mov `16*4`(%rsp),%rsi - mov (%rsi),%r13 - mov 8(%rsi),%r12 - mov 16(%rsi),%rbp - mov 24(%rsi),%rbx - lea 32(%rsi),%rsp -.Lepilogue: - ret -.size sha1_block_data_order,.-sha1_block_data_order -___ -{{{ -my $Xi=4; -my @X=map("%xmm$_",(4..7,0..3)); -my @Tx=map("%xmm$_",(8..10)); -my @V=($A,$B,$C,$D,$E)=("%eax","%ebx","%ecx","%edx","%ebp"); # size optimization -my @T=("%esi","%edi"); -my $j=0; -my $K_XX_XX="%r11"; - -my $_rol=sub { &rol(@_) }; -my $_ror=sub { &ror(@_) }; - -$code.=<<___; -.type sha1_block_data_order_ssse3,\@function,3 -.align 16 -sha1_block_data_order_ssse3: -_ssse3_shortcut: - push %rbx - push %rbp - push %r12 - lea `-64-($win64?5*16:0)`(%rsp),%rsp -___ -$code.=<<___ if ($win64); - movaps %xmm6,64+0(%rsp) - movaps %xmm7,64+16(%rsp) - movaps %xmm8,64+32(%rsp) - movaps %xmm9,64+48(%rsp) - movaps %xmm10,64+64(%rsp) -.Lprologue_ssse3: -___ -$code.=<<___; - mov %rdi,$ctx # reassigned argument - mov %rsi,$inp # reassigned argument - mov %rdx,$num # reassigned argument - - shl \$6,$num - add $inp,$num - lea K_XX_XX(%rip),$K_XX_XX - - mov 0($ctx),$A # load context - mov 4($ctx),$B - mov 8($ctx),$C - mov 12($ctx),$D - mov $B,@T[0] # magic seed - mov 16($ctx),$E - - movdqa 64($K_XX_XX),@X[2] # pbswap mask - movdqa 0($K_XX_XX),@Tx[1] # K_00_19 - movdqu 0($inp),@X[-4&7] # load input to %xmm[0-3] - movdqu 16($inp),@X[-3&7] - movdqu 32($inp),@X[-2&7] - movdqu 48($inp),@X[-1&7] - pshufb @X[2],@X[-4&7] # byte swap - add \$64,$inp - pshufb @X[2],@X[-3&7] - pshufb @X[2],@X[-2&7] - pshufb @X[2],@X[-1&7] - paddd @Tx[1],@X[-4&7] # add K_00_19 - paddd @Tx[1],@X[-3&7] - paddd @Tx[1],@X[-2&7] - movdqa @X[-4&7],0(%rsp) # X[]+K xfer to IALU - psubd @Tx[1],@X[-4&7] # restore X[] - movdqa @X[-3&7],16(%rsp) - psubd @Tx[1],@X[-3&7] - movdqa @X[-2&7],32(%rsp) - psubd @Tx[1],@X[-2&7] - jmp .Loop_ssse3 -___ - -sub AUTOLOAD() # thunk [simplified] 32-bit style perlasm -{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; - my $arg = pop; - $arg = "\$$arg" if ($arg*1 eq $arg); - $code .= "\t$opcode\t".join(',',$arg,reverse @_)."\n"; -} - -sub Xupdate_ssse3_16_31() # recall that $Xi starts wtih 4 -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 40 instructions - my ($a,$b,$c,$d,$e); - - &movdqa (@X[0],@X[-3&7]); - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (@Tx[0],@X[-1&7]); - &palignr(@X[0],@X[-4&7],8); # compose "X[-14]" in "X[0]" - eval(shift(@insns)); - eval(shift(@insns)); - - &paddd (@Tx[1],@X[-1&7]); - eval(shift(@insns)); - eval(shift(@insns)); - &psrldq (@Tx[0],4); # "X[-3]", 3 dwords - eval(shift(@insns)); - eval(shift(@insns)); - &pxor (@X[0],@X[-4&7]); # "X[0]"^="X[-16]" - eval(shift(@insns)); - eval(shift(@insns)); - - &pxor (@Tx[0],@X[-2&7]); # "X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &pxor (@X[0],@Tx[0]); # "X[0]"^="X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (eval(16*(($Xi-1)&3))."(%rsp)",@Tx[1]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - - &movdqa (@Tx[2],@X[0]); - &movdqa (@Tx[0],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &pslldq (@Tx[2],12); # "X[0]"<<96, extract one dword - &paddd (@X[0],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &psrld (@Tx[0],31); - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (@Tx[1],@Tx[2]); - eval(shift(@insns)); - eval(shift(@insns)); - - &psrld (@Tx[2],30); - &por (@X[0],@Tx[0]); # "X[0]"<<<=1 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &pslld (@Tx[1],2); - &pxor (@X[0],@Tx[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (@Tx[2],eval(16*(($Xi)/5))."($K_XX_XX)"); # K_XX_XX - eval(shift(@insns)); - eval(shift(@insns)); - - &pxor (@X[0],@Tx[1]); # "X[0]"^=("X[0]">>96)<<<2 - - foreach (@insns) { eval; } # remaining instructions [if any] - - $Xi++; push(@X,shift(@X)); # "rotate" X[] - push(@Tx,shift(@Tx)); -} - -sub Xupdate_ssse3_32_79() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 to 48 instructions - my ($a,$b,$c,$d,$e); - - &movdqa (@Tx[0],@X[-1&7]) if ($Xi==8); - eval(shift(@insns)); # body_20_39 - &pxor (@X[0],@X[-4&7]); # "X[0]"="X[-32]"^"X[-16]" - &palignr(@Tx[0],@X[-2&7],8); # compose "X[-6]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &pxor (@X[0],@X[-7&7]); # "X[0]"^="X[-28]" - eval(shift(@insns)); - eval(shift(@insns)) if (@insns[0] !~ /&ro[rl]/); - if ($Xi%5) { - &movdqa (@Tx[2],@Tx[1]);# "perpetuate" K_XX_XX... - } else { # ... or load next one - &movdqa (@Tx[2],eval(16*($Xi/5))."($K_XX_XX)"); - } - &paddd (@Tx[1],@X[-1&7]); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &pxor (@X[0],@Tx[0]); # "X[0]"^="X[-6]" - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &movdqa (@Tx[0],@X[0]); - &movdqa (eval(16*(($Xi-1)&3))."(%rsp)",@Tx[1]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &pslld (@X[0],2); - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - &psrld (@Tx[0],30); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &por (@X[0],@Tx[0]); # "X[0]"<<<=2 - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - &movdqa (@Tx[1],@X[0]) if ($Xi<19); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - - foreach (@insns) { eval; } # remaining instructions - - $Xi++; push(@X,shift(@X)); # "rotate" X[] - push(@Tx,shift(@Tx)); -} - -sub Xuplast_ssse3_80() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - &paddd (@Tx[1],@X[-1&7]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &movdqa (eval(16*(($Xi-1)&3))."(%rsp)",@Tx[1]); # X[]+K xfer IALU - - foreach (@insns) { eval; } # remaining instructions - - &cmp ($inp,$num); - &je (".Ldone_ssse3"); - - unshift(@Tx,pop(@Tx)); - - &movdqa (@X[2],"64($K_XX_XX)"); # pbswap mask - &movdqa (@Tx[1],"0($K_XX_XX)"); # K_00_19 - &movdqu (@X[-4&7],"0($inp)"); # load input - &movdqu (@X[-3&7],"16($inp)"); - &movdqu (@X[-2&7],"32($inp)"); - &movdqu (@X[-1&7],"48($inp)"); - &pshufb (@X[-4&7],@X[2]); # byte swap - &add ($inp,64); - - $Xi=0; -} - -sub Xloop_ssse3() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - eval(shift(@insns)); - &pshufb (@X[($Xi-3)&7],@X[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &paddd (@X[($Xi-4)&7],@Tx[1]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &movdqa (eval(16*$Xi)."(%rsp)",@X[($Xi-4)&7]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - &psubd (@X[($Xi-4)&7],@Tx[1]); - - foreach (@insns) { eval; } - $Xi++; -} - -sub Xtail_ssse3() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - foreach (@insns) { eval; } -} - -sub body_00_19 () { - ( - '($a,$b,$c,$d,$e)=@V;'. - '&add ($e,eval(4*($j&15))."(%rsp)");', # X[]+K xfer - '&xor ($c,$d);', - '&mov (@T[1],$a);', # $b in next round - '&$_rol ($a,5);', - '&and (@T[0],$c);', # ($b&($c^$d)) - '&xor ($c,$d);', # restore $c - '&xor (@T[0],$d);', - '&add ($e,$a);', - '&$_ror ($b,$j?7:2);', # $b>>>2 - '&add ($e,@T[0]);' .'$j++; unshift(@V,pop(@V)); unshift(@T,pop(@T));' - ); -} - -sub body_20_39 () { - ( - '($a,$b,$c,$d,$e)=@V;'. - '&add ($e,eval(4*($j++&15))."(%rsp)");', # X[]+K xfer - '&xor (@T[0],$d);', # ($b^$d) - '&mov (@T[1],$a);', # $b in next round - '&$_rol ($a,5);', - '&xor (@T[0],$c);', # ($b^$d^$c) - '&add ($e,$a);', - '&$_ror ($b,7);', # $b>>>2 - '&add ($e,@T[0]);' .'unshift(@V,pop(@V)); unshift(@T,pop(@T));' - ); -} - -sub body_40_59 () { - ( - '($a,$b,$c,$d,$e)=@V;'. - '&mov (@T[1],$c);', - '&xor ($c,$d);', - '&add ($e,eval(4*($j++&15))."(%rsp)");', # X[]+K xfer - '&and (@T[1],$d);', - '&and (@T[0],$c);', # ($b&($c^$d)) - '&$_ror ($b,7);', # $b>>>2 - '&add ($e,@T[1]);', - '&mov (@T[1],$a);', # $b in next round - '&$_rol ($a,5);', - '&add ($e,@T[0]);', - '&xor ($c,$d);', # restore $c - '&add ($e,$a);' .'unshift(@V,pop(@V)); unshift(@T,pop(@T));' - ); -} -$code.=<<___; -.align 16 -.Loop_ssse3: -___ - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_16_31(\&body_00_19); - &Xupdate_ssse3_32_79(\&body_00_19); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_40_59); - &Xupdate_ssse3_32_79(\&body_20_39); - &Xuplast_ssse3_80(\&body_20_39); # can jump to "done" - - $saved_j=$j; @saved_V=@V; - - &Xloop_ssse3(\&body_20_39); - &Xloop_ssse3(\&body_20_39); - &Xloop_ssse3(\&body_20_39); - -$code.=<<___; - add 0($ctx),$A # update context - add 4($ctx),@T[0] - add 8($ctx),$C - add 12($ctx),$D - mov $A,0($ctx) - add 16($ctx),$E - mov @T[0],4($ctx) - mov @T[0],$B # magic seed - mov $C,8($ctx) - mov $D,12($ctx) - mov $E,16($ctx) - jmp .Loop_ssse3 - -.align 16 -.Ldone_ssse3: -___ - $j=$saved_j; @V=@saved_V; - - &Xtail_ssse3(\&body_20_39); - &Xtail_ssse3(\&body_20_39); - &Xtail_ssse3(\&body_20_39); - -$code.=<<___; - add 0($ctx),$A # update context - add 4($ctx),@T[0] - add 8($ctx),$C - mov $A,0($ctx) - add 12($ctx),$D - mov @T[0],4($ctx) - add 16($ctx),$E - mov $C,8($ctx) - mov $D,12($ctx) - mov $E,16($ctx) -___ -$code.=<<___ if ($win64); - movaps 64+0(%rsp),%xmm6 - movaps 64+16(%rsp),%xmm7 - movaps 64+32(%rsp),%xmm8 - movaps 64+48(%rsp),%xmm9 - movaps 64+64(%rsp),%xmm10 -___ -$code.=<<___; - lea `64+($win64?5*16:0)`(%rsp),%rsi - mov 0(%rsi),%r12 - mov 8(%rsi),%rbp - mov 16(%rsi),%rbx - lea 24(%rsi),%rsp -.Lepilogue_ssse3: - ret -.size sha1_block_data_order_ssse3,.-sha1_block_data_order_ssse3 -___ - -if ($avx) { -my $Xi=4; -my @X=map("%xmm$_",(4..7,0..3)); -my @Tx=map("%xmm$_",(8..10)); -my @V=($A,$B,$C,$D,$E)=("%eax","%ebx","%ecx","%edx","%ebp"); # size optimization -my @T=("%esi","%edi"); -my $j=0; -my $K_XX_XX="%r11"; - -my $_rol=sub { &shld(@_[0],@_) }; -my $_ror=sub { &shrd(@_[0],@_) }; - -$code.=<<___; -.type sha1_block_data_order_avx,\@function,3 -.align 16 -sha1_block_data_order_avx: -_avx_shortcut: - push %rbx - push %rbp - push %r12 - lea `-64-($win64?5*16:0)`(%rsp),%rsp -___ -$code.=<<___ if ($win64); - movaps %xmm6,64+0(%rsp) - movaps %xmm7,64+16(%rsp) - movaps %xmm8,64+32(%rsp) - movaps %xmm9,64+48(%rsp) - movaps %xmm10,64+64(%rsp) -.Lprologue_avx: -___ -$code.=<<___; - mov %rdi,$ctx # reassigned argument - mov %rsi,$inp # reassigned argument - mov %rdx,$num # reassigned argument - vzeroupper - - shl \$6,$num - add $inp,$num - lea K_XX_XX(%rip),$K_XX_XX - - mov 0($ctx),$A # load context - mov 4($ctx),$B - mov 8($ctx),$C - mov 12($ctx),$D - mov $B,@T[0] # magic seed - mov 16($ctx),$E - - vmovdqa 64($K_XX_XX),@X[2] # pbswap mask - vmovdqa 0($K_XX_XX),@Tx[1] # K_00_19 - vmovdqu 0($inp),@X[-4&7] # load input to %xmm[0-3] - vmovdqu 16($inp),@X[-3&7] - vmovdqu 32($inp),@X[-2&7] - vmovdqu 48($inp),@X[-1&7] - vpshufb @X[2],@X[-4&7],@X[-4&7] # byte swap - add \$64,$inp - vpshufb @X[2],@X[-3&7],@X[-3&7] - vpshufb @X[2],@X[-2&7],@X[-2&7] - vpshufb @X[2],@X[-1&7],@X[-1&7] - vpaddd @Tx[1],@X[-4&7],@X[0] # add K_00_19 - vpaddd @Tx[1],@X[-3&7],@X[1] - vpaddd @Tx[1],@X[-2&7],@X[2] - vmovdqa @X[0],0(%rsp) # X[]+K xfer to IALU - vmovdqa @X[1],16(%rsp) - vmovdqa @X[2],32(%rsp) - jmp .Loop_avx -___ - -sub Xupdate_avx_16_31() # recall that $Xi starts wtih 4 -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 40 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - eval(shift(@insns)); - &vpalignr(@X[0],@X[-3&7],@X[-4&7],8); # compose "X[-14]" in "X[0]" - eval(shift(@insns)); - eval(shift(@insns)); - - &vpaddd (@Tx[1],@Tx[1],@X[-1&7]); - eval(shift(@insns)); - eval(shift(@insns)); - &vpsrldq(@Tx[0],@X[-1&7],4); # "X[-3]", 3 dwords - eval(shift(@insns)); - eval(shift(@insns)); - &vpxor (@X[0],@X[0],@X[-4&7]); # "X[0]"^="X[-16]" - eval(shift(@insns)); - eval(shift(@insns)); - - &vpxor (@Tx[0],@Tx[0],@X[-2&7]); # "X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpxor (@X[0],@X[0],@Tx[0]); # "X[0]"^="X[-3]"^"X[-8]" - eval(shift(@insns)); - eval(shift(@insns)); - &vmovdqa (eval(16*(($Xi-1)&3))."(%rsp)",@Tx[1]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - - &vpsrld (@Tx[0],@X[0],31); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpslldq(@Tx[2],@X[0],12); # "X[0]"<<96, extract one dword - &vpaddd (@X[0],@X[0],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpsrld (@Tx[1],@Tx[2],30); - &vpor (@X[0],@X[0],@Tx[0]); # "X[0]"<<<=1 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpslld (@Tx[2],@Tx[2],2); - &vpxor (@X[0],@X[0],@Tx[1]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &vpxor (@X[0],@X[0],@Tx[2]); # "X[0]"^=("X[0]">>96)<<<2 - eval(shift(@insns)); - eval(shift(@insns)); - &vmovdqa (@Tx[2],eval(16*(($Xi)/5))."($K_XX_XX)"); # K_XX_XX - eval(shift(@insns)); - eval(shift(@insns)); - - - foreach (@insns) { eval; } # remaining instructions [if any] - - $Xi++; push(@X,shift(@X)); # "rotate" X[] - push(@Tx,shift(@Tx)); -} - -sub Xupdate_avx_32_79() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 to 48 instructions - my ($a,$b,$c,$d,$e); - - &vpalignr(@Tx[0],@X[-1&7],@X[-2&7],8); # compose "X[-6]" - &vpxor (@X[0],@X[0],@X[-4&7]); # "X[0]"="X[-32]"^"X[-16]" - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &vpxor (@X[0],@X[0],@X[-7&7]); # "X[0]"^="X[-28]" - eval(shift(@insns)); - eval(shift(@insns)) if (@insns[0] !~ /&ro[rl]/); - if ($Xi%5) { - &vmovdqa (@Tx[2],@Tx[1]);# "perpetuate" K_XX_XX... - } else { # ... or load next one - &vmovdqa (@Tx[2],eval(16*($Xi/5))."($K_XX_XX)"); - } - &vpaddd (@Tx[1],@Tx[1],@X[-1&7]); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &vpxor (@X[0],@X[0],@Tx[0]); # "X[0]"^="X[-6]" - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - - &vpsrld (@Tx[0],@X[0],30); - &vmovdqa (eval(16*(($Xi-1)&3))."(%rsp)",@Tx[1]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &vpslld (@X[0],@X[0],2); - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # ror - eval(shift(@insns)); - - &vpor (@X[0],@X[0],@Tx[0]); # "X[0]"<<<=2 - eval(shift(@insns)); # body_20_39 - eval(shift(@insns)); - &vmovdqa (@Tx[1],@X[0]) if ($Xi<19); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); # rol - eval(shift(@insns)); - - foreach (@insns) { eval; } # remaining instructions - - $Xi++; push(@X,shift(@X)); # "rotate" X[] - push(@Tx,shift(@Tx)); -} - -sub Xuplast_avx_80() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - &vpaddd (@Tx[1],@Tx[1],@X[-1&7]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - - &movdqa (eval(16*(($Xi-1)&3))."(%rsp)",@Tx[1]); # X[]+K xfer IALU - - foreach (@insns) { eval; } # remaining instructions - - &cmp ($inp,$num); - &je (".Ldone_avx"); - - unshift(@Tx,pop(@Tx)); - - &vmovdqa(@X[2],"64($K_XX_XX)"); # pbswap mask - &vmovdqa(@Tx[1],"0($K_XX_XX)"); # K_00_19 - &vmovdqu(@X[-4&7],"0($inp)"); # load input - &vmovdqu(@X[-3&7],"16($inp)"); - &vmovdqu(@X[-2&7],"32($inp)"); - &vmovdqu(@X[-1&7],"48($inp)"); - &vpshufb(@X[-4&7],@X[-4&7],@X[2]); # byte swap - &add ($inp,64); - - $Xi=0; -} - -sub Xloop_avx() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - eval(shift(@insns)); - eval(shift(@insns)); - &vpshufb(@X[($Xi-3)&7],@X[($Xi-3)&7],@X[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &vpaddd (@X[$Xi&7],@X[($Xi-4)&7],@Tx[1]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vmovdqa(eval(16*$Xi)."(%rsp)",@X[$Xi&7]); # X[]+K xfer to IALU - eval(shift(@insns)); - eval(shift(@insns)); - - foreach (@insns) { eval; } - $Xi++; -} - -sub Xtail_avx() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); # 32 instructions - my ($a,$b,$c,$d,$e); - - foreach (@insns) { eval; } -} - -$code.=<<___; -.align 16 -.Loop_avx: -___ - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_16_31(\&body_00_19); - &Xupdate_avx_32_79(\&body_00_19); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_20_39); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_40_59); - &Xupdate_avx_32_79(\&body_20_39); - &Xuplast_avx_80(\&body_20_39); # can jump to "done" - - $saved_j=$j; @saved_V=@V; - - &Xloop_avx(\&body_20_39); - &Xloop_avx(\&body_20_39); - &Xloop_avx(\&body_20_39); - -$code.=<<___; - add 0($ctx),$A # update context - add 4($ctx),@T[0] - add 8($ctx),$C - add 12($ctx),$D - mov $A,0($ctx) - add 16($ctx),$E - mov @T[0],4($ctx) - mov @T[0],$B # magic seed - mov $C,8($ctx) - mov $D,12($ctx) - mov $E,16($ctx) - jmp .Loop_avx - -.align 16 -.Ldone_avx: -___ - $j=$saved_j; @V=@saved_V; - - &Xtail_avx(\&body_20_39); - &Xtail_avx(\&body_20_39); - &Xtail_avx(\&body_20_39); - -$code.=<<___; - vzeroupper - - add 0($ctx),$A # update context - add 4($ctx),@T[0] - add 8($ctx),$C - mov $A,0($ctx) - add 12($ctx),$D - mov @T[0],4($ctx) - add 16($ctx),$E - mov $C,8($ctx) - mov $D,12($ctx) - mov $E,16($ctx) -___ -$code.=<<___ if ($win64); - movaps 64+0(%rsp),%xmm6 - movaps 64+16(%rsp),%xmm7 - movaps 64+32(%rsp),%xmm8 - movaps 64+48(%rsp),%xmm9 - movaps 64+64(%rsp),%xmm10 -___ -$code.=<<___; - lea `64+($win64?5*16:0)`(%rsp),%rsi - mov 0(%rsi),%r12 - mov 8(%rsi),%rbp - mov 16(%rsi),%rbx - lea 24(%rsi),%rsp -.Lepilogue_avx: - ret -.size sha1_block_data_order_avx,.-sha1_block_data_order_avx -___ -} -$code.=<<___; -.align 64 -K_XX_XX: -.long 0x5a827999,0x5a827999,0x5a827999,0x5a827999 # K_00_19 -.long 0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1 # K_20_39 -.long 0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc # K_40_59 -.long 0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6 # K_60_79 -.long 0x00010203,0x04050607,0x08090a0b,0x0c0d0e0f # pbswap mask -___ -}}} -$code.=<<___; -.asciz "SHA1 block transform for x86_64, CRYPTOGAMS by <appro\@openssl.org>" -.align 64 -___ - -# EXCEPTION_DISPOSITION handler (EXCEPTION_RECORD *rec,ULONG64 frame, -# CONTEXT *context,DISPATCHER_CONTEXT *disp) -if ($win64) { -$rec="%rcx"; -$frame="%rdx"; -$context="%r8"; -$disp="%r9"; - -$code.=<<___; -.extern __imp_RtlVirtualUnwind -.type se_handler,\@abi-omnipotent -.align 16 -se_handler: - push %rsi - push %rdi - push %rbx - push %rbp - push %r12 - push %r13 - push %r14 - push %r15 - pushfq - sub \$64,%rsp - - mov 120($context),%rax # pull context->Rax - mov 248($context),%rbx # pull context->Rip - - lea .Lprologue(%rip),%r10 - cmp %r10,%rbx # context->Rip<.Lprologue - jb .Lcommon_seh_tail - - mov 152($context),%rax # pull context->Rsp - - lea .Lepilogue(%rip),%r10 - cmp %r10,%rbx # context->Rip>=.Lepilogue - jae .Lcommon_seh_tail - - mov `16*4`(%rax),%rax # pull saved stack pointer - lea 32(%rax),%rax - - mov -8(%rax),%rbx - mov -16(%rax),%rbp - mov -24(%rax),%r12 - mov -32(%rax),%r13 - mov %rbx,144($context) # restore context->Rbx - mov %rbp,160($context) # restore context->Rbp - mov %r12,216($context) # restore context->R12 - mov %r13,224($context) # restore context->R13 - - jmp .Lcommon_seh_tail -.size se_handler,.-se_handler - -.type ssse3_handler,\@abi-omnipotent -.align 16 -ssse3_handler: - push %rsi - push %rdi - push %rbx - push %rbp - push %r12 - push %r13 - push %r14 - push %r15 - pushfq - sub \$64,%rsp - - mov 120($context),%rax # pull context->Rax - mov 248($context),%rbx # pull context->Rip - - mov 8($disp),%rsi # disp->ImageBase - mov 56($disp),%r11 # disp->HandlerData - - mov 0(%r11),%r10d # HandlerData[0] - lea (%rsi,%r10),%r10 # prologue label - cmp %r10,%rbx # context->Rip<prologue label - jb .Lcommon_seh_tail - - mov 152($context),%rax # pull context->Rsp - - mov 4(%r11),%r10d # HandlerData[1] - lea (%rsi,%r10),%r10 # epilogue label - cmp %r10,%rbx # context->Rip>=epilogue label - jae .Lcommon_seh_tail - - lea 64(%rax),%rsi - lea 512($context),%rdi # &context.Xmm6 - mov \$10,%ecx - .long 0xa548f3fc # cld; rep movsq - lea `24+64+5*16`(%rax),%rax # adjust stack pointer - - mov -8(%rax),%rbx - mov -16(%rax),%rbp - mov -24(%rax),%r12 - mov %rbx,144($context) # restore context->Rbx - mov %rbp,160($context) # restore context->Rbp - mov %r12,216($context) # restore cotnext->R12 - -.Lcommon_seh_tail: - mov 8(%rax),%rdi - mov 16(%rax),%rsi - mov %rax,152($context) # restore context->Rsp - mov %rsi,168($context) # restore context->Rsi - mov %rdi,176($context) # restore context->Rdi - - mov 40($disp),%rdi # disp->ContextRecord - mov $context,%rsi # context - mov \$154,%ecx # sizeof(CONTEXT) - .long 0xa548f3fc # cld; rep movsq - - mov $disp,%rsi - xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER - mov 8(%rsi),%rdx # arg2, disp->ImageBase - mov 0(%rsi),%r8 # arg3, disp->ControlPc - mov 16(%rsi),%r9 # arg4, disp->FunctionEntry - mov 40(%rsi),%r10 # disp->ContextRecord - lea 56(%rsi),%r11 # &disp->HandlerData - lea 24(%rsi),%r12 # &disp->EstablisherFrame - mov %r10,32(%rsp) # arg5 - mov %r11,40(%rsp) # arg6 - mov %r12,48(%rsp) # arg7 - mov %rcx,56(%rsp) # arg8, (NULL) - call *__imp_RtlVirtualUnwind(%rip) - - mov \$1,%eax # ExceptionContinueSearch - add \$64,%rsp - popfq - pop %r15 - pop %r14 - pop %r13 - pop %r12 - pop %rbp - pop %rbx - pop %rdi - pop %rsi - ret -.size ssse3_handler,.-ssse3_handler - -.section .pdata -.align 4 - .rva .LSEH_begin_sha1_block_data_order - .rva .LSEH_end_sha1_block_data_order - .rva .LSEH_info_sha1_block_data_order - .rva .LSEH_begin_sha1_block_data_order_ssse3 - .rva .LSEH_end_sha1_block_data_order_ssse3 - .rva .LSEH_info_sha1_block_data_order_ssse3 -___ -$code.=<<___ if ($avx); - .rva .LSEH_begin_sha1_block_data_order_avx - .rva .LSEH_end_sha1_block_data_order_avx - .rva .LSEH_info_sha1_block_data_order_avx -___ -$code.=<<___; -.section .xdata -.align 8 -.LSEH_info_sha1_block_data_order: - .byte 9,0,0,0 - .rva se_handler -.LSEH_info_sha1_block_data_order_ssse3: - .byte 9,0,0,0 - .rva ssse3_handler - .rva .Lprologue_ssse3,.Lepilogue_ssse3 # HandlerData[] -___ -$code.=<<___ if ($avx); -.LSEH_info_sha1_block_data_order_avx: - .byte 9,0,0,0 - .rva ssse3_handler - .rva .Lprologue_avx,.Lepilogue_avx # HandlerData[] -___ -} - -#################################################################### - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha256-586.S b/app/openssl/crypto/sha/asm/sha256-586.S deleted file mode 100644 index 77a89514..00000000 --- a/app/openssl/crypto/sha/asm/sha256-586.S +++ /dev/null @@ -1,258 +0,0 @@ -.file "sha512-586.s" -.text -.globl sha256_block_data_order -.type sha256_block_data_order,@function -.align 16 -sha256_block_data_order: -.L_sha256_block_data_order_begin: - pushl %ebp - pushl %ebx - pushl %esi - pushl %edi - movl 20(%esp),%esi - movl 24(%esp),%edi - movl 28(%esp),%eax - movl %esp,%ebx - call .L000pic_point -.L000pic_point: - popl %ebp - leal .L001K256-.L000pic_point(%ebp),%ebp - subl $16,%esp - andl $-64,%esp - shll $6,%eax - addl %edi,%eax - movl %esi,(%esp) - movl %edi,4(%esp) - movl %eax,8(%esp) - movl %ebx,12(%esp) -.align 16 -.L002loop: - movl (%edi),%eax - movl 4(%edi),%ebx - movl 8(%edi),%ecx - movl 12(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 16(%edi),%eax - movl 20(%edi),%ebx - movl 24(%edi),%ecx - movl 28(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 32(%edi),%eax - movl 36(%edi),%ebx - movl 40(%edi),%ecx - movl 44(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 48(%edi),%eax - movl 52(%edi),%ebx - movl 56(%edi),%ecx - movl 60(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - addl $64,%edi - subl $32,%esp - movl %edi,100(%esp) - movl (%esi),%eax - movl 4(%esi),%ebx - movl 8(%esi),%ecx - movl 12(%esi),%edi - movl %ebx,4(%esp) - movl %ecx,8(%esp) - movl %edi,12(%esp) - movl 16(%esi),%edx - movl 20(%esi),%ebx - movl 24(%esi),%ecx - movl 28(%esi),%edi - movl %ebx,20(%esp) - movl %ecx,24(%esp) - movl %edi,28(%esp) -.align 16 -.L00300_15: - movl 92(%esp),%ebx - movl %edx,%ecx - rorl $14,%ecx - movl 20(%esp),%esi - xorl %edx,%ecx - rorl $5,%ecx - xorl %edx,%ecx - rorl $6,%ecx - movl 24(%esp),%edi - addl %ecx,%ebx - xorl %edi,%esi - movl %edx,16(%esp) - movl %eax,%ecx - andl %edx,%esi - movl 12(%esp),%edx - xorl %edi,%esi - movl %eax,%edi - addl %esi,%ebx - rorl $9,%ecx - addl 28(%esp),%ebx - xorl %eax,%ecx - rorl $11,%ecx - movl 4(%esp),%esi - xorl %eax,%ecx - rorl $2,%ecx - addl %ebx,%edx - movl 8(%esp),%edi - addl %ecx,%ebx - movl %eax,(%esp) - movl %eax,%ecx - subl $4,%esp - orl %esi,%eax - andl %esi,%ecx - andl %edi,%eax - movl (%ebp),%esi - orl %ecx,%eax - addl $4,%ebp - addl %ebx,%eax - addl %esi,%edx - addl %esi,%eax - cmpl $3248222580,%esi - jne .L00300_15 - movl 152(%esp),%ebx -.align 16 -.L00416_63: - movl %ebx,%esi - movl 100(%esp),%ecx - rorl $11,%esi - movl %ecx,%edi - xorl %ebx,%esi - rorl $7,%esi - shrl $3,%ebx - rorl $2,%edi - xorl %esi,%ebx - xorl %ecx,%edi - rorl $17,%edi - shrl $10,%ecx - addl 156(%esp),%ebx - xorl %ecx,%edi - addl 120(%esp),%ebx - movl %edx,%ecx - addl %edi,%ebx - rorl $14,%ecx - movl 20(%esp),%esi - xorl %edx,%ecx - rorl $5,%ecx - movl %ebx,92(%esp) - xorl %edx,%ecx - rorl $6,%ecx - movl 24(%esp),%edi - addl %ecx,%ebx - xorl %edi,%esi - movl %edx,16(%esp) - movl %eax,%ecx - andl %edx,%esi - movl 12(%esp),%edx - xorl %edi,%esi - movl %eax,%edi - addl %esi,%ebx - rorl $9,%ecx - addl 28(%esp),%ebx - xorl %eax,%ecx - rorl $11,%ecx - movl 4(%esp),%esi - xorl %eax,%ecx - rorl $2,%ecx - addl %ebx,%edx - movl 8(%esp),%edi - addl %ecx,%ebx - movl %eax,(%esp) - movl %eax,%ecx - subl $4,%esp - orl %esi,%eax - andl %esi,%ecx - andl %edi,%eax - movl (%ebp),%esi - orl %ecx,%eax - addl $4,%ebp - addl %ebx,%eax - movl 152(%esp),%ebx - addl %esi,%edx - addl %esi,%eax - cmpl $3329325298,%esi - jne .L00416_63 - movl 352(%esp),%esi - movl 4(%esp),%ebx - movl 8(%esp),%ecx - movl 12(%esp),%edi - addl (%esi),%eax - addl 4(%esi),%ebx - addl 8(%esi),%ecx - addl 12(%esi),%edi - movl %eax,(%esi) - movl %ebx,4(%esi) - movl %ecx,8(%esi) - movl %edi,12(%esi) - movl 20(%esp),%eax - movl 24(%esp),%ebx - movl 28(%esp),%ecx - movl 356(%esp),%edi - addl 16(%esi),%edx - addl 20(%esi),%eax - addl 24(%esi),%ebx - addl 28(%esi),%ecx - movl %edx,16(%esi) - movl %eax,20(%esi) - movl %ebx,24(%esi) - movl %ecx,28(%esi) - addl $352,%esp - subl $256,%ebp - cmpl 8(%esp),%edi - jb .L002loop - movl 12(%esp),%esp - popl %edi - popl %esi - popl %ebx - popl %ebp - ret -.align 64 -.L001K256: -.long 1116352408,1899447441,3049323471,3921009573 -.long 961987163,1508970993,2453635748,2870763221 -.long 3624381080,310598401,607225278,1426881987 -.long 1925078388,2162078206,2614888103,3248222580 -.long 3835390401,4022224774,264347078,604807628 -.long 770255983,1249150122,1555081692,1996064986 -.long 2554220882,2821834349,2952996808,3210313671 -.long 3336571891,3584528711,113926993,338241895 -.long 666307205,773529912,1294757372,1396182291 -.long 1695183700,1986661051,2177026350,2456956037 -.long 2730485921,2820302411,3259730800,3345764771 -.long 3516065817,3600352804,4094571909,275423344 -.long 430227734,506948616,659060556,883997877 -.long 958139571,1322822218,1537002063,1747873779 -.long 1955562222,2024104815,2227730452,2361852424 -.long 2428436474,2756734187,3204031479,3329325298 -.size sha256_block_data_order,.-.L_sha256_block_data_order_begin -.byte 83,72,65,50,53,54,32,98,108,111,99,107,32,116,114,97 -.byte 110,115,102,111,114,109,32,102,111,114,32,120,56,54,44,32 -.byte 67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97 -.byte 112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103 -.byte 62,0 diff --git a/app/openssl/crypto/sha/asm/sha256-586.pl b/app/openssl/crypto/sha/asm/sha256-586.pl deleted file mode 100644 index 52a7c7f8..00000000 --- a/app/openssl/crypto/sha/asm/sha256-586.pl +++ /dev/null @@ -1,249 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== -# -# SHA256 block transform for x86. September 2007. -# -# Performance in clock cycles per processed byte (less is better): -# -# Pentium PIII P4 AMD K8 Core2 -# gcc 46 36 41 27 26 -# icc 57 33 38 25 23 -# x86 asm 40 30 33 20 18 -# x86_64 asm(*) - - 21 16 16 -# -# (*) x86_64 assembler performance is presented for reference -# purposes. -# -# Performance improvement over compiler generated code varies from -# 10% to 40% [see above]. Not very impressive on some µ-archs, but -# it's 5 times smaller and optimizies amount of writes. - -$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; -push(@INC,"${dir}","${dir}../../perlasm"); -require "x86asm.pl"; - -&asm_init($ARGV[0],"sha512-586.pl",$ARGV[$#ARGV] eq "386"); - -$A="eax"; -$E="edx"; -$T="ebx"; -$Aoff=&DWP(0,"esp"); -$Boff=&DWP(4,"esp"); -$Coff=&DWP(8,"esp"); -$Doff=&DWP(12,"esp"); -$Eoff=&DWP(16,"esp"); -$Foff=&DWP(20,"esp"); -$Goff=&DWP(24,"esp"); -$Hoff=&DWP(28,"esp"); -$Xoff=&DWP(32,"esp"); -$K256="ebp"; - -sub BODY_00_15() { - my $in_16_63=shift; - - &mov ("ecx",$E); - &add ($T,"edi") if ($in_16_63); # T += sigma1(X[-2]) - &ror ("ecx",25-11); - &mov ("esi",$Foff); - &xor ("ecx",$E); - &ror ("ecx",11-6); - &mov (&DWP(4*(8+15),"esp"),$T) if ($in_16_63); # save X[0] - &xor ("ecx",$E); - &ror ("ecx",6); # Sigma1(e) - &mov ("edi",$Goff); - &add ($T,"ecx"); # T += Sigma1(e) - - &xor ("esi","edi"); - &mov ($Eoff,$E); # modulo-scheduled - &mov ("ecx",$A); - &and ("esi",$E); - &mov ($E,$Doff); # e becomes d, which is e in next iteration - &xor ("esi","edi"); # Ch(e,f,g) - &mov ("edi",$A); - &add ($T,"esi"); # T += Ch(e,f,g) - - &ror ("ecx",22-13); - &add ($T,$Hoff); # T += h - &xor ("ecx",$A); - &ror ("ecx",13-2); - &mov ("esi",$Boff); - &xor ("ecx",$A); - &ror ("ecx",2); # Sigma0(a) - &add ($E,$T); # d += T - &mov ("edi",$Coff); - - &add ($T,"ecx"); # T += Sigma0(a) - &mov ($Aoff,$A); # modulo-scheduled - - &mov ("ecx",$A); - &sub ("esp",4); - &or ($A,"esi"); # a becomes h, which is a in next iteration - &and ("ecx","esi"); - &and ($A,"edi"); - &mov ("esi",&DWP(0,$K256)); - &or ($A,"ecx"); # h=Maj(a,b,c) - - &add ($K256,4); - &add ($A,$T); # h += T - &mov ($T,&DWP(4*(8+15+16-1),"esp")) if ($in_16_63); # preload T - &add ($E,"esi"); # d += K256[i] - &add ($A,"esi"); # h += K256[i] -} - -&function_begin("sha256_block_data_order"); - &mov ("esi",wparam(0)); # ctx - &mov ("edi",wparam(1)); # inp - &mov ("eax",wparam(2)); # num - &mov ("ebx","esp"); # saved sp - - &call (&label("pic_point")); # make it PIC! -&set_label("pic_point"); - &blindpop($K256); - &lea ($K256,&DWP(&label("K256")."-".&label("pic_point"),$K256)); - - &sub ("esp",16); - &and ("esp",-64); - - &shl ("eax",6); - &add ("eax","edi"); - &mov (&DWP(0,"esp"),"esi"); # ctx - &mov (&DWP(4,"esp"),"edi"); # inp - &mov (&DWP(8,"esp"),"eax"); # inp+num*128 - &mov (&DWP(12,"esp"),"ebx"); # saved sp - -&set_label("loop",16); - # copy input block to stack reversing byte and dword order - for($i=0;$i<4;$i++) { - &mov ("eax",&DWP($i*16+0,"edi")); - &mov ("ebx",&DWP($i*16+4,"edi")); - &mov ("ecx",&DWP($i*16+8,"edi")); - &mov ("edx",&DWP($i*16+12,"edi")); - &bswap ("eax"); - &bswap ("ebx"); - &bswap ("ecx"); - &bswap ("edx"); - &push ("eax"); - &push ("ebx"); - &push ("ecx"); - &push ("edx"); - } - &add ("edi",64); - &sub ("esp",4*8); # place for A,B,C,D,E,F,G,H - &mov (&DWP(4*(8+16)+4,"esp"),"edi"); - - # copy ctx->h[0-7] to A,B,C,D,E,F,G,H on stack - &mov ($A,&DWP(0,"esi")); - &mov ("ebx",&DWP(4,"esi")); - &mov ("ecx",&DWP(8,"esi")); - &mov ("edi",&DWP(12,"esi")); - # &mov ($Aoff,$A); - &mov ($Boff,"ebx"); - &mov ($Coff,"ecx"); - &mov ($Doff,"edi"); - &mov ($E,&DWP(16,"esi")); - &mov ("ebx",&DWP(20,"esi")); - &mov ("ecx",&DWP(24,"esi")); - &mov ("edi",&DWP(28,"esi")); - # &mov ($Eoff,$E); - &mov ($Foff,"ebx"); - &mov ($Goff,"ecx"); - &mov ($Hoff,"edi"); - -&set_label("00_15",16); - &mov ($T,&DWP(4*(8+15),"esp")); - - &BODY_00_15(); - - &cmp ("esi",0xc19bf174); - &jne (&label("00_15")); - - &mov ($T,&DWP(4*(8+15+16-1),"esp")); # preloaded in BODY_00_15(1) -&set_label("16_63",16); - &mov ("esi",$T); - &mov ("ecx",&DWP(4*(8+15+16-14),"esp")); - &ror ("esi",18-7); - &mov ("edi","ecx"); - &xor ("esi",$T); - &ror ("esi",7); - &shr ($T,3); - - &ror ("edi",19-17); - &xor ($T,"esi"); # T = sigma0(X[-15]) - &xor ("edi","ecx"); - &ror ("edi",17); - &shr ("ecx",10); - &add ($T,&DWP(4*(8+15+16),"esp")); # T += X[-16] - &xor ("edi","ecx"); # sigma1(X[-2]) - - &add ($T,&DWP(4*(8+15+16-9),"esp")); # T += X[-7] - # &add ($T,"edi"); # T += sigma1(X[-2]) - # &mov (&DWP(4*(8+15),"esp"),$T); # save X[0] - - &BODY_00_15(1); - - &cmp ("esi",0xc67178f2); - &jne (&label("16_63")); - - &mov ("esi",&DWP(4*(8+16+64)+0,"esp"));#ctx - # &mov ($A,$Aoff); - &mov ("ebx",$Boff); - &mov ("ecx",$Coff); - &mov ("edi",$Doff); - &add ($A,&DWP(0,"esi")); - &add ("ebx",&DWP(4,"esi")); - &add ("ecx",&DWP(8,"esi")); - &add ("edi",&DWP(12,"esi")); - &mov (&DWP(0,"esi"),$A); - &mov (&DWP(4,"esi"),"ebx"); - &mov (&DWP(8,"esi"),"ecx"); - &mov (&DWP(12,"esi"),"edi"); - # &mov ($E,$Eoff); - &mov ("eax",$Foff); - &mov ("ebx",$Goff); - &mov ("ecx",$Hoff); - &mov ("edi",&DWP(4*(8+16+64)+4,"esp"));#inp - &add ($E,&DWP(16,"esi")); - &add ("eax",&DWP(20,"esi")); - &add ("ebx",&DWP(24,"esi")); - &add ("ecx",&DWP(28,"esi")); - &mov (&DWP(16,"esi"),$E); - &mov (&DWP(20,"esi"),"eax"); - &mov (&DWP(24,"esi"),"ebx"); - &mov (&DWP(28,"esi"),"ecx"); - - &add ("esp",4*(8+16+64)); # destroy frame - &sub ($K256,4*64); # rewind K - - &cmp ("edi",&DWP(8,"esp")); # are we done yet? - &jb (&label("loop")); - - &mov ("esp",&DWP(12,"esp")); # restore sp -&function_end_A(); - -&set_label("K256",64); # Yes! I keep it in the code segment! - &data_word(0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5); - &data_word(0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5); - &data_word(0xd807aa98,0x12835b01,0x243185be,0x550c7dc3); - &data_word(0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174); - &data_word(0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc); - &data_word(0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da); - &data_word(0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7); - &data_word(0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967); - &data_word(0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13); - &data_word(0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85); - &data_word(0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3); - &data_word(0xd192e819,0xd6990624,0xf40e3585,0x106aa070); - &data_word(0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5); - &data_word(0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3); - &data_word(0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208); - &data_word(0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2); -&function_end_B("sha256_block_data_order"); -&asciz("SHA256 block transform for x86, CRYPTOGAMS by <appro\@openssl.org>"); - -&asm_finish(); diff --git a/app/openssl/crypto/sha/asm/sha256-armv4.S b/app/openssl/crypto/sha/asm/sha256-armv4.S deleted file mode 100644 index 853d7da5..00000000 --- a/app/openssl/crypto/sha/asm/sha256-armv4.S +++ /dev/null @@ -1,2690 +0,0 @@ -#include "arm_arch.h" - -.text -.code 32 - -.type K256,%object -.align 5 -K256: -.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 -.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 -.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 -.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 -.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc -.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da -.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 -.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 -.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 -.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 -.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 -.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 -.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 -.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 -.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 -.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -.size K256,.-K256 -.word 0 @ terminator -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-sha256_block_data_order -.align 5 - -.global sha256_block_data_order -.type sha256_block_data_order,%function -sha256_block_data_order: - sub r3,pc,#8 @ sha256_block_data_order - add r2,r1,r2,lsl#6 @ len to point at the end of inp -#if __ARM_ARCH__>=7 - ldr r12,.LOPENSSL_armcap - ldr r12,[r3,r12] @ OPENSSL_armcap_P - tst r12,#ARMV8_SHA256 - bne .LARMv8 - tst r12,#ARMV7_NEON - bne .LNEON -#endif - stmdb sp!,{r0,r1,r2,r4-r11,lr} - ldmia r0,{r4,r5,r6,r7,r8,r9,r10,r11} - sub r14,r3,#256+32 @ K256 - sub sp,sp,#16*4 @ alloca(X[16]) -.Loop: -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 -# else - ldrb r2,[r1,#3] -# endif - eor r3,r5,r6 @ magic - eor r12,r12,r12 -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 0 -# if 0==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r8,r8,ror#5 - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r8,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 0 - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 0==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r8,r8,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r8,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r11,r11,r2 @ h+=X[i] - str r2,[sp,#0*4] - eor r2,r9,r10 - add r11,r11,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r8 - add r11,r11,r12 @ h+=K256[i] - eor r2,r2,r10 @ Ch(e,f,g) - eor r0,r4,r4,ror#11 - add r11,r11,r2 @ h+=Ch(e,f,g) -#if 0==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 0<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r4,r5 @ a^b, b^c in next round -#else - ldr r2,[sp,#2*4] @ from future BODY_16_xx - eor r12,r4,r5 @ a^b, b^c in next round - ldr r1,[sp,#15*4] @ from future BODY_16_xx -#endif - eor r0,r0,r4,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r7,r7,r11 @ d+=h - eor r3,r3,r5 @ Maj(a,b,c) - add r11,r11,r0,ror#2 @ h+=Sigma0(a) - @ add r11,r11,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 1 -# if 1==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r7,r7,ror#5 - add r11,r11,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r7,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 1 - add r11,r11,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 1==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r7,r7,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r7,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r10,r10,r2 @ h+=X[i] - str r2,[sp,#1*4] - eor r2,r8,r9 - add r10,r10,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r7 - add r10,r10,r3 @ h+=K256[i] - eor r2,r2,r9 @ Ch(e,f,g) - eor r0,r11,r11,ror#11 - add r10,r10,r2 @ h+=Ch(e,f,g) -#if 1==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 1<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r11,r4 @ a^b, b^c in next round -#else - ldr r2,[sp,#3*4] @ from future BODY_16_xx - eor r3,r11,r4 @ a^b, b^c in next round - ldr r1,[sp,#0*4] @ from future BODY_16_xx -#endif - eor r0,r0,r11,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r6,r6,r10 @ d+=h - eor r12,r12,r4 @ Maj(a,b,c) - add r10,r10,r0,ror#2 @ h+=Sigma0(a) - @ add r10,r10,r12 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 2 -# if 2==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r6,r6,ror#5 - add r10,r10,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r6,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 2 - add r10,r10,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 2==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r6,r6,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r6,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r9,r9,r2 @ h+=X[i] - str r2,[sp,#2*4] - eor r2,r7,r8 - add r9,r9,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r6 - add r9,r9,r12 @ h+=K256[i] - eor r2,r2,r8 @ Ch(e,f,g) - eor r0,r10,r10,ror#11 - add r9,r9,r2 @ h+=Ch(e,f,g) -#if 2==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 2<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r10,r11 @ a^b, b^c in next round -#else - ldr r2,[sp,#4*4] @ from future BODY_16_xx - eor r12,r10,r11 @ a^b, b^c in next round - ldr r1,[sp,#1*4] @ from future BODY_16_xx -#endif - eor r0,r0,r10,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r5,r5,r9 @ d+=h - eor r3,r3,r11 @ Maj(a,b,c) - add r9,r9,r0,ror#2 @ h+=Sigma0(a) - @ add r9,r9,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 3 -# if 3==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r5,r5,ror#5 - add r9,r9,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r5,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 3 - add r9,r9,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 3==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r5,r5,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r5,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r8,r8,r2 @ h+=X[i] - str r2,[sp,#3*4] - eor r2,r6,r7 - add r8,r8,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r5 - add r8,r8,r3 @ h+=K256[i] - eor r2,r2,r7 @ Ch(e,f,g) - eor r0,r9,r9,ror#11 - add r8,r8,r2 @ h+=Ch(e,f,g) -#if 3==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 3<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r9,r10 @ a^b, b^c in next round -#else - ldr r2,[sp,#5*4] @ from future BODY_16_xx - eor r3,r9,r10 @ a^b, b^c in next round - ldr r1,[sp,#2*4] @ from future BODY_16_xx -#endif - eor r0,r0,r9,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r4,r4,r8 @ d+=h - eor r12,r12,r10 @ Maj(a,b,c) - add r8,r8,r0,ror#2 @ h+=Sigma0(a) - @ add r8,r8,r12 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 4 -# if 4==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r4,r4,ror#5 - add r8,r8,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r4,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 4 - add r8,r8,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 4==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r4,r4,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r4,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r7,r7,r2 @ h+=X[i] - str r2,[sp,#4*4] - eor r2,r5,r6 - add r7,r7,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r4 - add r7,r7,r12 @ h+=K256[i] - eor r2,r2,r6 @ Ch(e,f,g) - eor r0,r8,r8,ror#11 - add r7,r7,r2 @ h+=Ch(e,f,g) -#if 4==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 4<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r8,r9 @ a^b, b^c in next round -#else - ldr r2,[sp,#6*4] @ from future BODY_16_xx - eor r12,r8,r9 @ a^b, b^c in next round - ldr r1,[sp,#3*4] @ from future BODY_16_xx -#endif - eor r0,r0,r8,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r11,r11,r7 @ d+=h - eor r3,r3,r9 @ Maj(a,b,c) - add r7,r7,r0,ror#2 @ h+=Sigma0(a) - @ add r7,r7,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 5 -# if 5==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r11,r11,ror#5 - add r7,r7,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r11,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 5 - add r7,r7,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 5==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r11,r11,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r11,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r6,r6,r2 @ h+=X[i] - str r2,[sp,#5*4] - eor r2,r4,r5 - add r6,r6,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r11 - add r6,r6,r3 @ h+=K256[i] - eor r2,r2,r5 @ Ch(e,f,g) - eor r0,r7,r7,ror#11 - add r6,r6,r2 @ h+=Ch(e,f,g) -#if 5==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 5<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r7,r8 @ a^b, b^c in next round -#else - ldr r2,[sp,#7*4] @ from future BODY_16_xx - eor r3,r7,r8 @ a^b, b^c in next round - ldr r1,[sp,#4*4] @ from future BODY_16_xx -#endif - eor r0,r0,r7,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r10,r10,r6 @ d+=h - eor r12,r12,r8 @ Maj(a,b,c) - add r6,r6,r0,ror#2 @ h+=Sigma0(a) - @ add r6,r6,r12 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 6 -# if 6==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r10,r10,ror#5 - add r6,r6,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r10,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 6 - add r6,r6,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 6==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r10,r10,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r10,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r5,r5,r2 @ h+=X[i] - str r2,[sp,#6*4] - eor r2,r11,r4 - add r5,r5,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r10 - add r5,r5,r12 @ h+=K256[i] - eor r2,r2,r4 @ Ch(e,f,g) - eor r0,r6,r6,ror#11 - add r5,r5,r2 @ h+=Ch(e,f,g) -#if 6==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 6<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r6,r7 @ a^b, b^c in next round -#else - ldr r2,[sp,#8*4] @ from future BODY_16_xx - eor r12,r6,r7 @ a^b, b^c in next round - ldr r1,[sp,#5*4] @ from future BODY_16_xx -#endif - eor r0,r0,r6,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r9,r9,r5 @ d+=h - eor r3,r3,r7 @ Maj(a,b,c) - add r5,r5,r0,ror#2 @ h+=Sigma0(a) - @ add r5,r5,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 7 -# if 7==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r9,r9,ror#5 - add r5,r5,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r9,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 7 - add r5,r5,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 7==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r9,r9,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r9,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r4,r4,r2 @ h+=X[i] - str r2,[sp,#7*4] - eor r2,r10,r11 - add r4,r4,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r9 - add r4,r4,r3 @ h+=K256[i] - eor r2,r2,r11 @ Ch(e,f,g) - eor r0,r5,r5,ror#11 - add r4,r4,r2 @ h+=Ch(e,f,g) -#if 7==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 7<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r5,r6 @ a^b, b^c in next round -#else - ldr r2,[sp,#9*4] @ from future BODY_16_xx - eor r3,r5,r6 @ a^b, b^c in next round - ldr r1,[sp,#6*4] @ from future BODY_16_xx -#endif - eor r0,r0,r5,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r8,r8,r4 @ d+=h - eor r12,r12,r6 @ Maj(a,b,c) - add r4,r4,r0,ror#2 @ h+=Sigma0(a) - @ add r4,r4,r12 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 8 -# if 8==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r8,r8,ror#5 - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r8,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 8 - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 8==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r8,r8,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r8,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r11,r11,r2 @ h+=X[i] - str r2,[sp,#8*4] - eor r2,r9,r10 - add r11,r11,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r8 - add r11,r11,r12 @ h+=K256[i] - eor r2,r2,r10 @ Ch(e,f,g) - eor r0,r4,r4,ror#11 - add r11,r11,r2 @ h+=Ch(e,f,g) -#if 8==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 8<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r4,r5 @ a^b, b^c in next round -#else - ldr r2,[sp,#10*4] @ from future BODY_16_xx - eor r12,r4,r5 @ a^b, b^c in next round - ldr r1,[sp,#7*4] @ from future BODY_16_xx -#endif - eor r0,r0,r4,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r7,r7,r11 @ d+=h - eor r3,r3,r5 @ Maj(a,b,c) - add r11,r11,r0,ror#2 @ h+=Sigma0(a) - @ add r11,r11,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 9 -# if 9==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r7,r7,ror#5 - add r11,r11,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r7,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 9 - add r11,r11,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 9==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r7,r7,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r7,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r10,r10,r2 @ h+=X[i] - str r2,[sp,#9*4] - eor r2,r8,r9 - add r10,r10,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r7 - add r10,r10,r3 @ h+=K256[i] - eor r2,r2,r9 @ Ch(e,f,g) - eor r0,r11,r11,ror#11 - add r10,r10,r2 @ h+=Ch(e,f,g) -#if 9==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 9<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r11,r4 @ a^b, b^c in next round -#else - ldr r2,[sp,#11*4] @ from future BODY_16_xx - eor r3,r11,r4 @ a^b, b^c in next round - ldr r1,[sp,#8*4] @ from future BODY_16_xx -#endif - eor r0,r0,r11,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r6,r6,r10 @ d+=h - eor r12,r12,r4 @ Maj(a,b,c) - add r10,r10,r0,ror#2 @ h+=Sigma0(a) - @ add r10,r10,r12 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 10 -# if 10==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r6,r6,ror#5 - add r10,r10,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r6,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 10 - add r10,r10,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 10==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r6,r6,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r6,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r9,r9,r2 @ h+=X[i] - str r2,[sp,#10*4] - eor r2,r7,r8 - add r9,r9,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r6 - add r9,r9,r12 @ h+=K256[i] - eor r2,r2,r8 @ Ch(e,f,g) - eor r0,r10,r10,ror#11 - add r9,r9,r2 @ h+=Ch(e,f,g) -#if 10==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 10<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r10,r11 @ a^b, b^c in next round -#else - ldr r2,[sp,#12*4] @ from future BODY_16_xx - eor r12,r10,r11 @ a^b, b^c in next round - ldr r1,[sp,#9*4] @ from future BODY_16_xx -#endif - eor r0,r0,r10,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r5,r5,r9 @ d+=h - eor r3,r3,r11 @ Maj(a,b,c) - add r9,r9,r0,ror#2 @ h+=Sigma0(a) - @ add r9,r9,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 11 -# if 11==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r5,r5,ror#5 - add r9,r9,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r5,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 11 - add r9,r9,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 11==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r5,r5,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r5,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r8,r8,r2 @ h+=X[i] - str r2,[sp,#11*4] - eor r2,r6,r7 - add r8,r8,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r5 - add r8,r8,r3 @ h+=K256[i] - eor r2,r2,r7 @ Ch(e,f,g) - eor r0,r9,r9,ror#11 - add r8,r8,r2 @ h+=Ch(e,f,g) -#if 11==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 11<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r9,r10 @ a^b, b^c in next round -#else - ldr r2,[sp,#13*4] @ from future BODY_16_xx - eor r3,r9,r10 @ a^b, b^c in next round - ldr r1,[sp,#10*4] @ from future BODY_16_xx -#endif - eor r0,r0,r9,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r4,r4,r8 @ d+=h - eor r12,r12,r10 @ Maj(a,b,c) - add r8,r8,r0,ror#2 @ h+=Sigma0(a) - @ add r8,r8,r12 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 12 -# if 12==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r4,r4,ror#5 - add r8,r8,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r4,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 12 - add r8,r8,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 12==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r4,r4,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r4,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r7,r7,r2 @ h+=X[i] - str r2,[sp,#12*4] - eor r2,r5,r6 - add r7,r7,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r4 - add r7,r7,r12 @ h+=K256[i] - eor r2,r2,r6 @ Ch(e,f,g) - eor r0,r8,r8,ror#11 - add r7,r7,r2 @ h+=Ch(e,f,g) -#if 12==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 12<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r8,r9 @ a^b, b^c in next round -#else - ldr r2,[sp,#14*4] @ from future BODY_16_xx - eor r12,r8,r9 @ a^b, b^c in next round - ldr r1,[sp,#11*4] @ from future BODY_16_xx -#endif - eor r0,r0,r8,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r11,r11,r7 @ d+=h - eor r3,r3,r9 @ Maj(a,b,c) - add r7,r7,r0,ror#2 @ h+=Sigma0(a) - @ add r7,r7,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 13 -# if 13==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r11,r11,ror#5 - add r7,r7,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r11,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 13 - add r7,r7,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 13==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r11,r11,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r11,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r6,r6,r2 @ h+=X[i] - str r2,[sp,#13*4] - eor r2,r4,r5 - add r6,r6,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r11 - add r6,r6,r3 @ h+=K256[i] - eor r2,r2,r5 @ Ch(e,f,g) - eor r0,r7,r7,ror#11 - add r6,r6,r2 @ h+=Ch(e,f,g) -#if 13==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 13<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r7,r8 @ a^b, b^c in next round -#else - ldr r2,[sp,#15*4] @ from future BODY_16_xx - eor r3,r7,r8 @ a^b, b^c in next round - ldr r1,[sp,#12*4] @ from future BODY_16_xx -#endif - eor r0,r0,r7,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r10,r10,r6 @ d+=h - eor r12,r12,r8 @ Maj(a,b,c) - add r6,r6,r0,ror#2 @ h+=Sigma0(a) - @ add r6,r6,r12 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 14 -# if 14==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r10,r10,ror#5 - add r6,r6,r12 @ h+=Maj(a,b,c) from the past - eor r0,r0,r10,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 14 - add r6,r6,r12 @ h+=Maj(a,b,c) from the past - ldrb r12,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r12,lsl#8 - ldrb r12,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 14==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r10,r10,ror#5 - orr r2,r2,r12,lsl#24 - eor r0,r0,r10,ror#19 @ Sigma1(e) -#endif - ldr r12,[r14],#4 @ *K256++ - add r5,r5,r2 @ h+=X[i] - str r2,[sp,#14*4] - eor r2,r11,r4 - add r5,r5,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r10 - add r5,r5,r12 @ h+=K256[i] - eor r2,r2,r4 @ Ch(e,f,g) - eor r0,r6,r6,ror#11 - add r5,r5,r2 @ h+=Ch(e,f,g) -#if 14==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 14<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r6,r7 @ a^b, b^c in next round -#else - ldr r2,[sp,#0*4] @ from future BODY_16_xx - eor r12,r6,r7 @ a^b, b^c in next round - ldr r1,[sp,#13*4] @ from future BODY_16_xx -#endif - eor r0,r0,r6,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r9,r9,r5 @ d+=h - eor r3,r3,r7 @ Maj(a,b,c) - add r5,r5,r0,ror#2 @ h+=Sigma0(a) - @ add r5,r5,r3 @ h+=Maj(a,b,c) -#if __ARM_ARCH__>=7 - @ ldr r2,[r1],#4 @ 15 -# if 15==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r9,r9,ror#5 - add r5,r5,r3 @ h+=Maj(a,b,c) from the past - eor r0,r0,r9,ror#19 @ Sigma1(e) - rev r2,r2 -#else - @ ldrb r2,[r1,#3] @ 15 - add r5,r5,r3 @ h+=Maj(a,b,c) from the past - ldrb r3,[r1,#2] - ldrb r0,[r1,#1] - orr r2,r2,r3,lsl#8 - ldrb r3,[r1],#4 - orr r2,r2,r0,lsl#16 -# if 15==15 - str r1,[sp,#17*4] @ make room for r1 -# endif - eor r0,r9,r9,ror#5 - orr r2,r2,r3,lsl#24 - eor r0,r0,r9,ror#19 @ Sigma1(e) -#endif - ldr r3,[r14],#4 @ *K256++ - add r4,r4,r2 @ h+=X[i] - str r2,[sp,#15*4] - eor r2,r10,r11 - add r4,r4,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r9 - add r4,r4,r3 @ h+=K256[i] - eor r2,r2,r11 @ Ch(e,f,g) - eor r0,r5,r5,ror#11 - add r4,r4,r2 @ h+=Ch(e,f,g) -#if 15==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 15<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r5,r6 @ a^b, b^c in next round -#else - ldr r2,[sp,#1*4] @ from future BODY_16_xx - eor r3,r5,r6 @ a^b, b^c in next round - ldr r1,[sp,#14*4] @ from future BODY_16_xx -#endif - eor r0,r0,r5,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r8,r8,r4 @ d+=h - eor r12,r12,r6 @ Maj(a,b,c) - add r4,r4,r0,ror#2 @ h+=Sigma0(a) - @ add r4,r4,r12 @ h+=Maj(a,b,c) -.Lrounds_16_xx: - @ ldr r2,[sp,#1*4] @ 16 - @ ldr r1,[sp,#14*4] - mov r0,r2,ror#7 - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#0*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#9*4] - - add r12,r12,r0 - eor r0,r8,r8,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r8,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r11,r11,r2 @ h+=X[i] - str r2,[sp,#0*4] - eor r2,r9,r10 - add r11,r11,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r8 - add r11,r11,r12 @ h+=K256[i] - eor r2,r2,r10 @ Ch(e,f,g) - eor r0,r4,r4,ror#11 - add r11,r11,r2 @ h+=Ch(e,f,g) -#if 16==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 16<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r4,r5 @ a^b, b^c in next round -#else - ldr r2,[sp,#2*4] @ from future BODY_16_xx - eor r12,r4,r5 @ a^b, b^c in next round - ldr r1,[sp,#15*4] @ from future BODY_16_xx -#endif - eor r0,r0,r4,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r7,r7,r11 @ d+=h - eor r3,r3,r5 @ Maj(a,b,c) - add r11,r11,r0,ror#2 @ h+=Sigma0(a) - @ add r11,r11,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#2*4] @ 17 - @ ldr r1,[sp,#15*4] - mov r0,r2,ror#7 - add r11,r11,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#1*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#10*4] - - add r3,r3,r0 - eor r0,r7,r7,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r7,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r10,r10,r2 @ h+=X[i] - str r2,[sp,#1*4] - eor r2,r8,r9 - add r10,r10,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r7 - add r10,r10,r3 @ h+=K256[i] - eor r2,r2,r9 @ Ch(e,f,g) - eor r0,r11,r11,ror#11 - add r10,r10,r2 @ h+=Ch(e,f,g) -#if 17==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 17<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r11,r4 @ a^b, b^c in next round -#else - ldr r2,[sp,#3*4] @ from future BODY_16_xx - eor r3,r11,r4 @ a^b, b^c in next round - ldr r1,[sp,#0*4] @ from future BODY_16_xx -#endif - eor r0,r0,r11,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r6,r6,r10 @ d+=h - eor r12,r12,r4 @ Maj(a,b,c) - add r10,r10,r0,ror#2 @ h+=Sigma0(a) - @ add r10,r10,r12 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#3*4] @ 18 - @ ldr r1,[sp,#0*4] - mov r0,r2,ror#7 - add r10,r10,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#2*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#11*4] - - add r12,r12,r0 - eor r0,r6,r6,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r6,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r9,r9,r2 @ h+=X[i] - str r2,[sp,#2*4] - eor r2,r7,r8 - add r9,r9,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r6 - add r9,r9,r12 @ h+=K256[i] - eor r2,r2,r8 @ Ch(e,f,g) - eor r0,r10,r10,ror#11 - add r9,r9,r2 @ h+=Ch(e,f,g) -#if 18==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 18<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r10,r11 @ a^b, b^c in next round -#else - ldr r2,[sp,#4*4] @ from future BODY_16_xx - eor r12,r10,r11 @ a^b, b^c in next round - ldr r1,[sp,#1*4] @ from future BODY_16_xx -#endif - eor r0,r0,r10,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r5,r5,r9 @ d+=h - eor r3,r3,r11 @ Maj(a,b,c) - add r9,r9,r0,ror#2 @ h+=Sigma0(a) - @ add r9,r9,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#4*4] @ 19 - @ ldr r1,[sp,#1*4] - mov r0,r2,ror#7 - add r9,r9,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#3*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#12*4] - - add r3,r3,r0 - eor r0,r5,r5,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r5,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r8,r8,r2 @ h+=X[i] - str r2,[sp,#3*4] - eor r2,r6,r7 - add r8,r8,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r5 - add r8,r8,r3 @ h+=K256[i] - eor r2,r2,r7 @ Ch(e,f,g) - eor r0,r9,r9,ror#11 - add r8,r8,r2 @ h+=Ch(e,f,g) -#if 19==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 19<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r9,r10 @ a^b, b^c in next round -#else - ldr r2,[sp,#5*4] @ from future BODY_16_xx - eor r3,r9,r10 @ a^b, b^c in next round - ldr r1,[sp,#2*4] @ from future BODY_16_xx -#endif - eor r0,r0,r9,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r4,r4,r8 @ d+=h - eor r12,r12,r10 @ Maj(a,b,c) - add r8,r8,r0,ror#2 @ h+=Sigma0(a) - @ add r8,r8,r12 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#5*4] @ 20 - @ ldr r1,[sp,#2*4] - mov r0,r2,ror#7 - add r8,r8,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#4*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#13*4] - - add r12,r12,r0 - eor r0,r4,r4,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r4,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r7,r7,r2 @ h+=X[i] - str r2,[sp,#4*4] - eor r2,r5,r6 - add r7,r7,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r4 - add r7,r7,r12 @ h+=K256[i] - eor r2,r2,r6 @ Ch(e,f,g) - eor r0,r8,r8,ror#11 - add r7,r7,r2 @ h+=Ch(e,f,g) -#if 20==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 20<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r8,r9 @ a^b, b^c in next round -#else - ldr r2,[sp,#6*4] @ from future BODY_16_xx - eor r12,r8,r9 @ a^b, b^c in next round - ldr r1,[sp,#3*4] @ from future BODY_16_xx -#endif - eor r0,r0,r8,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r11,r11,r7 @ d+=h - eor r3,r3,r9 @ Maj(a,b,c) - add r7,r7,r0,ror#2 @ h+=Sigma0(a) - @ add r7,r7,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#6*4] @ 21 - @ ldr r1,[sp,#3*4] - mov r0,r2,ror#7 - add r7,r7,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#5*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#14*4] - - add r3,r3,r0 - eor r0,r11,r11,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r11,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r6,r6,r2 @ h+=X[i] - str r2,[sp,#5*4] - eor r2,r4,r5 - add r6,r6,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r11 - add r6,r6,r3 @ h+=K256[i] - eor r2,r2,r5 @ Ch(e,f,g) - eor r0,r7,r7,ror#11 - add r6,r6,r2 @ h+=Ch(e,f,g) -#if 21==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 21<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r7,r8 @ a^b, b^c in next round -#else - ldr r2,[sp,#7*4] @ from future BODY_16_xx - eor r3,r7,r8 @ a^b, b^c in next round - ldr r1,[sp,#4*4] @ from future BODY_16_xx -#endif - eor r0,r0,r7,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r10,r10,r6 @ d+=h - eor r12,r12,r8 @ Maj(a,b,c) - add r6,r6,r0,ror#2 @ h+=Sigma0(a) - @ add r6,r6,r12 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#7*4] @ 22 - @ ldr r1,[sp,#4*4] - mov r0,r2,ror#7 - add r6,r6,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#6*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#15*4] - - add r12,r12,r0 - eor r0,r10,r10,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r10,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r5,r5,r2 @ h+=X[i] - str r2,[sp,#6*4] - eor r2,r11,r4 - add r5,r5,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r10 - add r5,r5,r12 @ h+=K256[i] - eor r2,r2,r4 @ Ch(e,f,g) - eor r0,r6,r6,ror#11 - add r5,r5,r2 @ h+=Ch(e,f,g) -#if 22==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 22<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r6,r7 @ a^b, b^c in next round -#else - ldr r2,[sp,#8*4] @ from future BODY_16_xx - eor r12,r6,r7 @ a^b, b^c in next round - ldr r1,[sp,#5*4] @ from future BODY_16_xx -#endif - eor r0,r0,r6,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r9,r9,r5 @ d+=h - eor r3,r3,r7 @ Maj(a,b,c) - add r5,r5,r0,ror#2 @ h+=Sigma0(a) - @ add r5,r5,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#8*4] @ 23 - @ ldr r1,[sp,#5*4] - mov r0,r2,ror#7 - add r5,r5,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#7*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#0*4] - - add r3,r3,r0 - eor r0,r9,r9,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r9,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r4,r4,r2 @ h+=X[i] - str r2,[sp,#7*4] - eor r2,r10,r11 - add r4,r4,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r9 - add r4,r4,r3 @ h+=K256[i] - eor r2,r2,r11 @ Ch(e,f,g) - eor r0,r5,r5,ror#11 - add r4,r4,r2 @ h+=Ch(e,f,g) -#if 23==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 23<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r5,r6 @ a^b, b^c in next round -#else - ldr r2,[sp,#9*4] @ from future BODY_16_xx - eor r3,r5,r6 @ a^b, b^c in next round - ldr r1,[sp,#6*4] @ from future BODY_16_xx -#endif - eor r0,r0,r5,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r8,r8,r4 @ d+=h - eor r12,r12,r6 @ Maj(a,b,c) - add r4,r4,r0,ror#2 @ h+=Sigma0(a) - @ add r4,r4,r12 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#9*4] @ 24 - @ ldr r1,[sp,#6*4] - mov r0,r2,ror#7 - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#8*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#1*4] - - add r12,r12,r0 - eor r0,r8,r8,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r8,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r11,r11,r2 @ h+=X[i] - str r2,[sp,#8*4] - eor r2,r9,r10 - add r11,r11,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r8 - add r11,r11,r12 @ h+=K256[i] - eor r2,r2,r10 @ Ch(e,f,g) - eor r0,r4,r4,ror#11 - add r11,r11,r2 @ h+=Ch(e,f,g) -#if 24==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 24<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r4,r5 @ a^b, b^c in next round -#else - ldr r2,[sp,#10*4] @ from future BODY_16_xx - eor r12,r4,r5 @ a^b, b^c in next round - ldr r1,[sp,#7*4] @ from future BODY_16_xx -#endif - eor r0,r0,r4,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r7,r7,r11 @ d+=h - eor r3,r3,r5 @ Maj(a,b,c) - add r11,r11,r0,ror#2 @ h+=Sigma0(a) - @ add r11,r11,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#10*4] @ 25 - @ ldr r1,[sp,#7*4] - mov r0,r2,ror#7 - add r11,r11,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#9*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#2*4] - - add r3,r3,r0 - eor r0,r7,r7,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r7,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r10,r10,r2 @ h+=X[i] - str r2,[sp,#9*4] - eor r2,r8,r9 - add r10,r10,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r7 - add r10,r10,r3 @ h+=K256[i] - eor r2,r2,r9 @ Ch(e,f,g) - eor r0,r11,r11,ror#11 - add r10,r10,r2 @ h+=Ch(e,f,g) -#if 25==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 25<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r11,r4 @ a^b, b^c in next round -#else - ldr r2,[sp,#11*4] @ from future BODY_16_xx - eor r3,r11,r4 @ a^b, b^c in next round - ldr r1,[sp,#8*4] @ from future BODY_16_xx -#endif - eor r0,r0,r11,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r6,r6,r10 @ d+=h - eor r12,r12,r4 @ Maj(a,b,c) - add r10,r10,r0,ror#2 @ h+=Sigma0(a) - @ add r10,r10,r12 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#11*4] @ 26 - @ ldr r1,[sp,#8*4] - mov r0,r2,ror#7 - add r10,r10,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#10*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#3*4] - - add r12,r12,r0 - eor r0,r6,r6,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r6,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r9,r9,r2 @ h+=X[i] - str r2,[sp,#10*4] - eor r2,r7,r8 - add r9,r9,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r6 - add r9,r9,r12 @ h+=K256[i] - eor r2,r2,r8 @ Ch(e,f,g) - eor r0,r10,r10,ror#11 - add r9,r9,r2 @ h+=Ch(e,f,g) -#if 26==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 26<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r10,r11 @ a^b, b^c in next round -#else - ldr r2,[sp,#12*4] @ from future BODY_16_xx - eor r12,r10,r11 @ a^b, b^c in next round - ldr r1,[sp,#9*4] @ from future BODY_16_xx -#endif - eor r0,r0,r10,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r5,r5,r9 @ d+=h - eor r3,r3,r11 @ Maj(a,b,c) - add r9,r9,r0,ror#2 @ h+=Sigma0(a) - @ add r9,r9,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#12*4] @ 27 - @ ldr r1,[sp,#9*4] - mov r0,r2,ror#7 - add r9,r9,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#11*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#4*4] - - add r3,r3,r0 - eor r0,r5,r5,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r5,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r8,r8,r2 @ h+=X[i] - str r2,[sp,#11*4] - eor r2,r6,r7 - add r8,r8,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r5 - add r8,r8,r3 @ h+=K256[i] - eor r2,r2,r7 @ Ch(e,f,g) - eor r0,r9,r9,ror#11 - add r8,r8,r2 @ h+=Ch(e,f,g) -#if 27==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 27<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r9,r10 @ a^b, b^c in next round -#else - ldr r2,[sp,#13*4] @ from future BODY_16_xx - eor r3,r9,r10 @ a^b, b^c in next round - ldr r1,[sp,#10*4] @ from future BODY_16_xx -#endif - eor r0,r0,r9,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r4,r4,r8 @ d+=h - eor r12,r12,r10 @ Maj(a,b,c) - add r8,r8,r0,ror#2 @ h+=Sigma0(a) - @ add r8,r8,r12 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#13*4] @ 28 - @ ldr r1,[sp,#10*4] - mov r0,r2,ror#7 - add r8,r8,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#12*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#5*4] - - add r12,r12,r0 - eor r0,r4,r4,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r4,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r7,r7,r2 @ h+=X[i] - str r2,[sp,#12*4] - eor r2,r5,r6 - add r7,r7,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r4 - add r7,r7,r12 @ h+=K256[i] - eor r2,r2,r6 @ Ch(e,f,g) - eor r0,r8,r8,ror#11 - add r7,r7,r2 @ h+=Ch(e,f,g) -#if 28==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 28<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r8,r9 @ a^b, b^c in next round -#else - ldr r2,[sp,#14*4] @ from future BODY_16_xx - eor r12,r8,r9 @ a^b, b^c in next round - ldr r1,[sp,#11*4] @ from future BODY_16_xx -#endif - eor r0,r0,r8,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r11,r11,r7 @ d+=h - eor r3,r3,r9 @ Maj(a,b,c) - add r7,r7,r0,ror#2 @ h+=Sigma0(a) - @ add r7,r7,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#14*4] @ 29 - @ ldr r1,[sp,#11*4] - mov r0,r2,ror#7 - add r7,r7,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#13*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#6*4] - - add r3,r3,r0 - eor r0,r11,r11,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r11,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r6,r6,r2 @ h+=X[i] - str r2,[sp,#13*4] - eor r2,r4,r5 - add r6,r6,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r11 - add r6,r6,r3 @ h+=K256[i] - eor r2,r2,r5 @ Ch(e,f,g) - eor r0,r7,r7,ror#11 - add r6,r6,r2 @ h+=Ch(e,f,g) -#if 29==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 29<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r7,r8 @ a^b, b^c in next round -#else - ldr r2,[sp,#15*4] @ from future BODY_16_xx - eor r3,r7,r8 @ a^b, b^c in next round - ldr r1,[sp,#12*4] @ from future BODY_16_xx -#endif - eor r0,r0,r7,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r10,r10,r6 @ d+=h - eor r12,r12,r8 @ Maj(a,b,c) - add r6,r6,r0,ror#2 @ h+=Sigma0(a) - @ add r6,r6,r12 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#15*4] @ 30 - @ ldr r1,[sp,#12*4] - mov r0,r2,ror#7 - add r6,r6,r12 @ h+=Maj(a,b,c) from the past - mov r12,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r12,r12,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#14*4] - eor r12,r12,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#7*4] - - add r12,r12,r0 - eor r0,r10,r10,ror#5 @ from BODY_00_15 - add r2,r2,r12 - eor r0,r0,r10,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r12,[r14],#4 @ *K256++ - add r5,r5,r2 @ h+=X[i] - str r2,[sp,#14*4] - eor r2,r11,r4 - add r5,r5,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r10 - add r5,r5,r12 @ h+=K256[i] - eor r2,r2,r4 @ Ch(e,f,g) - eor r0,r6,r6,ror#11 - add r5,r5,r2 @ h+=Ch(e,f,g) -#if 30==31 - and r12,r12,#0xff - cmp r12,#0xf2 @ done? -#endif -#if 30<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r12,r6,r7 @ a^b, b^c in next round -#else - ldr r2,[sp,#0*4] @ from future BODY_16_xx - eor r12,r6,r7 @ a^b, b^c in next round - ldr r1,[sp,#13*4] @ from future BODY_16_xx -#endif - eor r0,r0,r6,ror#20 @ Sigma0(a) - and r3,r3,r12 @ (b^c)&=(a^b) - add r9,r9,r5 @ d+=h - eor r3,r3,r7 @ Maj(a,b,c) - add r5,r5,r0,ror#2 @ h+=Sigma0(a) - @ add r5,r5,r3 @ h+=Maj(a,b,c) - @ ldr r2,[sp,#0*4] @ 31 - @ ldr r1,[sp,#13*4] - mov r0,r2,ror#7 - add r5,r5,r3 @ h+=Maj(a,b,c) from the past - mov r3,r1,ror#17 - eor r0,r0,r2,ror#18 - eor r3,r3,r1,ror#19 - eor r0,r0,r2,lsr#3 @ sigma0(X[i+1]) - ldr r2,[sp,#15*4] - eor r3,r3,r1,lsr#10 @ sigma1(X[i+14]) - ldr r1,[sp,#8*4] - - add r3,r3,r0 - eor r0,r9,r9,ror#5 @ from BODY_00_15 - add r2,r2,r3 - eor r0,r0,r9,ror#19 @ Sigma1(e) - add r2,r2,r1 @ X[i] - ldr r3,[r14],#4 @ *K256++ - add r4,r4,r2 @ h+=X[i] - str r2,[sp,#15*4] - eor r2,r10,r11 - add r4,r4,r0,ror#6 @ h+=Sigma1(e) - and r2,r2,r9 - add r4,r4,r3 @ h+=K256[i] - eor r2,r2,r11 @ Ch(e,f,g) - eor r0,r5,r5,ror#11 - add r4,r4,r2 @ h+=Ch(e,f,g) -#if 31==31 - and r3,r3,#0xff - cmp r3,#0xf2 @ done? -#endif -#if 31<15 -# if __ARM_ARCH__>=7 - ldr r2,[r1],#4 @ prefetch -# else - ldrb r2,[r1,#3] -# endif - eor r3,r5,r6 @ a^b, b^c in next round -#else - ldr r2,[sp,#1*4] @ from future BODY_16_xx - eor r3,r5,r6 @ a^b, b^c in next round - ldr r1,[sp,#14*4] @ from future BODY_16_xx -#endif - eor r0,r0,r5,ror#20 @ Sigma0(a) - and r12,r12,r3 @ (b^c)&=(a^b) - add r8,r8,r4 @ d+=h - eor r12,r12,r6 @ Maj(a,b,c) - add r4,r4,r0,ror#2 @ h+=Sigma0(a) - @ add r4,r4,r12 @ h+=Maj(a,b,c) - ldreq r3,[sp,#16*4] @ pull ctx - bne .Lrounds_16_xx - - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - ldr r0,[r3,#0] - ldr r2,[r3,#4] - ldr r12,[r3,#8] - add r4,r4,r0 - ldr r0,[r3,#12] - add r5,r5,r2 - ldr r2,[r3,#16] - add r6,r6,r12 - ldr r12,[r3,#20] - add r7,r7,r0 - ldr r0,[r3,#24] - add r8,r8,r2 - ldr r2,[r3,#28] - add r9,r9,r12 - ldr r1,[sp,#17*4] @ pull inp - ldr r12,[sp,#18*4] @ pull inp+len - add r10,r10,r0 - add r11,r11,r2 - stmia r3,{r4,r5,r6,r7,r8,r9,r10,r11} - cmp r1,r12 - sub r14,r14,#256 @ rewind Ktbl - bne .Loop - - add sp,sp,#19*4 @ destroy frame -#if __ARM_ARCH__>=5 - ldmia sp!,{r4-r11,pc} -#else - ldmia sp!,{r4-r11,lr} - tst lr,#1 - moveq pc,lr @ be binary compatible with V4, yet - .word 0xe12fff1e @ interoperable with Thumb ISA:-) -#endif -.size sha256_block_data_order,.-sha256_block_data_order -#if __ARM_ARCH__>=7 -.fpu neon - -.type sha256_block_data_order_neon,%function -.align 4 -sha256_block_data_order_neon: -.LNEON: - stmdb sp!,{r4-r12,lr} - - mov r12,sp - sub sp,sp,#16*4+16 @ alloca - sub r14,r3,#256+32 @ K256 - bic sp,sp,#15 @ align for 128-bit stores - - vld1.8 {q0},[r1]! - vld1.8 {q1},[r1]! - vld1.8 {q2},[r1]! - vld1.8 {q3},[r1]! - vld1.32 {q8},[r14,:128]! - vld1.32 {q9},[r14,:128]! - vld1.32 {q10},[r14,:128]! - vld1.32 {q11},[r14,:128]! - vrev32.8 q0,q0 @ yes, even on - str r0,[sp,#64] - vrev32.8 q1,q1 @ big-endian - str r1,[sp,#68] - mov r1,sp - vrev32.8 q2,q2 - str r2,[sp,#72] - vrev32.8 q3,q3 - str r12,[sp,#76] @ save original sp - vadd.i32 q8,q8,q0 - vadd.i32 q9,q9,q1 - vst1.32 {q8},[r1,:128]! - vadd.i32 q10,q10,q2 - vst1.32 {q9},[r1,:128]! - vadd.i32 q11,q11,q3 - vst1.32 {q10},[r1,:128]! - vst1.32 {q11},[r1,:128]! - - ldmia r0,{r4-r11} - sub r1,r1,#64 - ldr r2,[sp,#0] - eor r12,r12,r12 - eor r3,r5,r6 - b .L_00_48 - -.align 4 -.L_00_48: - vext.8 q8,q0,q1,#4 - add r11,r11,r2 - eor r2,r9,r10 - eor r0,r8,r8,ror#5 - vext.8 q9,q2,q3,#4 - add r4,r4,r12 - and r2,r2,r8 - eor r12,r0,r8,ror#19 - vshr.u32 q10,q8,#7 - eor r0,r4,r4,ror#11 - eor r2,r2,r10 - vadd.i32 q0,q0,q9 - add r11,r11,r12,ror#6 - eor r12,r4,r5 - vshr.u32 q9,q8,#3 - eor r0,r0,r4,ror#20 - add r11,r11,r2 - vsli.32 q10,q8,#25 - ldr r2,[sp,#4] - and r3,r3,r12 - vshr.u32 q11,q8,#18 - add r7,r7,r11 - add r11,r11,r0,ror#2 - eor r3,r3,r5 - veor q9,q9,q10 - add r10,r10,r2 - vsli.32 q11,q8,#14 - eor r2,r8,r9 - eor r0,r7,r7,ror#5 - vshr.u32 d24,d7,#17 - add r11,r11,r3 - and r2,r2,r7 - veor q9,q9,q11 - eor r3,r0,r7,ror#19 - eor r0,r11,r11,ror#11 - vsli.32 d24,d7,#15 - eor r2,r2,r9 - add r10,r10,r3,ror#6 - vshr.u32 d25,d7,#10 - eor r3,r11,r4 - eor r0,r0,r11,ror#20 - vadd.i32 q0,q0,q9 - add r10,r10,r2 - ldr r2,[sp,#8] - veor d25,d25,d24 - and r12,r12,r3 - add r6,r6,r10 - vshr.u32 d24,d7,#19 - add r10,r10,r0,ror#2 - eor r12,r12,r4 - vsli.32 d24,d7,#13 - add r9,r9,r2 - eor r2,r7,r8 - veor d25,d25,d24 - eor r0,r6,r6,ror#5 - add r10,r10,r12 - vadd.i32 d0,d0,d25 - and r2,r2,r6 - eor r12,r0,r6,ror#19 - vshr.u32 d24,d0,#17 - eor r0,r10,r10,ror#11 - eor r2,r2,r8 - vsli.32 d24,d0,#15 - add r9,r9,r12,ror#6 - eor r12,r10,r11 - vshr.u32 d25,d0,#10 - eor r0,r0,r10,ror#20 - add r9,r9,r2 - veor d25,d25,d24 - ldr r2,[sp,#12] - and r3,r3,r12 - vshr.u32 d24,d0,#19 - add r5,r5,r9 - add r9,r9,r0,ror#2 - eor r3,r3,r11 - vld1.32 {q8},[r14,:128]! - add r8,r8,r2 - vsli.32 d24,d0,#13 - eor r2,r6,r7 - eor r0,r5,r5,ror#5 - veor d25,d25,d24 - add r9,r9,r3 - and r2,r2,r5 - vadd.i32 d1,d1,d25 - eor r3,r0,r5,ror#19 - eor r0,r9,r9,ror#11 - vadd.i32 q8,q8,q0 - eor r2,r2,r7 - add r8,r8,r3,ror#6 - eor r3,r9,r10 - eor r0,r0,r9,ror#20 - add r8,r8,r2 - ldr r2,[sp,#16] - and r12,r12,r3 - add r4,r4,r8 - vst1.32 {q8},[r1,:128]! - add r8,r8,r0,ror#2 - eor r12,r12,r10 - vext.8 q8,q1,q2,#4 - add r7,r7,r2 - eor r2,r5,r6 - eor r0,r4,r4,ror#5 - vext.8 q9,q3,q0,#4 - add r8,r8,r12 - and r2,r2,r4 - eor r12,r0,r4,ror#19 - vshr.u32 q10,q8,#7 - eor r0,r8,r8,ror#11 - eor r2,r2,r6 - vadd.i32 q1,q1,q9 - add r7,r7,r12,ror#6 - eor r12,r8,r9 - vshr.u32 q9,q8,#3 - eor r0,r0,r8,ror#20 - add r7,r7,r2 - vsli.32 q10,q8,#25 - ldr r2,[sp,#20] - and r3,r3,r12 - vshr.u32 q11,q8,#18 - add r11,r11,r7 - add r7,r7,r0,ror#2 - eor r3,r3,r9 - veor q9,q9,q10 - add r6,r6,r2 - vsli.32 q11,q8,#14 - eor r2,r4,r5 - eor r0,r11,r11,ror#5 - vshr.u32 d24,d1,#17 - add r7,r7,r3 - and r2,r2,r11 - veor q9,q9,q11 - eor r3,r0,r11,ror#19 - eor r0,r7,r7,ror#11 - vsli.32 d24,d1,#15 - eor r2,r2,r5 - add r6,r6,r3,ror#6 - vshr.u32 d25,d1,#10 - eor r3,r7,r8 - eor r0,r0,r7,ror#20 - vadd.i32 q1,q1,q9 - add r6,r6,r2 - ldr r2,[sp,#24] - veor d25,d25,d24 - and r12,r12,r3 - add r10,r10,r6 - vshr.u32 d24,d1,#19 - add r6,r6,r0,ror#2 - eor r12,r12,r8 - vsli.32 d24,d1,#13 - add r5,r5,r2 - eor r2,r11,r4 - veor d25,d25,d24 - eor r0,r10,r10,ror#5 - add r6,r6,r12 - vadd.i32 d2,d2,d25 - and r2,r2,r10 - eor r12,r0,r10,ror#19 - vshr.u32 d24,d2,#17 - eor r0,r6,r6,ror#11 - eor r2,r2,r4 - vsli.32 d24,d2,#15 - add r5,r5,r12,ror#6 - eor r12,r6,r7 - vshr.u32 d25,d2,#10 - eor r0,r0,r6,ror#20 - add r5,r5,r2 - veor d25,d25,d24 - ldr r2,[sp,#28] - and r3,r3,r12 - vshr.u32 d24,d2,#19 - add r9,r9,r5 - add r5,r5,r0,ror#2 - eor r3,r3,r7 - vld1.32 {q8},[r14,:128]! - add r4,r4,r2 - vsli.32 d24,d2,#13 - eor r2,r10,r11 - eor r0,r9,r9,ror#5 - veor d25,d25,d24 - add r5,r5,r3 - and r2,r2,r9 - vadd.i32 d3,d3,d25 - eor r3,r0,r9,ror#19 - eor r0,r5,r5,ror#11 - vadd.i32 q8,q8,q1 - eor r2,r2,r11 - add r4,r4,r3,ror#6 - eor r3,r5,r6 - eor r0,r0,r5,ror#20 - add r4,r4,r2 - ldr r2,[sp,#32] - and r12,r12,r3 - add r8,r8,r4 - vst1.32 {q8},[r1,:128]! - add r4,r4,r0,ror#2 - eor r12,r12,r6 - vext.8 q8,q2,q3,#4 - add r11,r11,r2 - eor r2,r9,r10 - eor r0,r8,r8,ror#5 - vext.8 q9,q0,q1,#4 - add r4,r4,r12 - and r2,r2,r8 - eor r12,r0,r8,ror#19 - vshr.u32 q10,q8,#7 - eor r0,r4,r4,ror#11 - eor r2,r2,r10 - vadd.i32 q2,q2,q9 - add r11,r11,r12,ror#6 - eor r12,r4,r5 - vshr.u32 q9,q8,#3 - eor r0,r0,r4,ror#20 - add r11,r11,r2 - vsli.32 q10,q8,#25 - ldr r2,[sp,#36] - and r3,r3,r12 - vshr.u32 q11,q8,#18 - add r7,r7,r11 - add r11,r11,r0,ror#2 - eor r3,r3,r5 - veor q9,q9,q10 - add r10,r10,r2 - vsli.32 q11,q8,#14 - eor r2,r8,r9 - eor r0,r7,r7,ror#5 - vshr.u32 d24,d3,#17 - add r11,r11,r3 - and r2,r2,r7 - veor q9,q9,q11 - eor r3,r0,r7,ror#19 - eor r0,r11,r11,ror#11 - vsli.32 d24,d3,#15 - eor r2,r2,r9 - add r10,r10,r3,ror#6 - vshr.u32 d25,d3,#10 - eor r3,r11,r4 - eor r0,r0,r11,ror#20 - vadd.i32 q2,q2,q9 - add r10,r10,r2 - ldr r2,[sp,#40] - veor d25,d25,d24 - and r12,r12,r3 - add r6,r6,r10 - vshr.u32 d24,d3,#19 - add r10,r10,r0,ror#2 - eor r12,r12,r4 - vsli.32 d24,d3,#13 - add r9,r9,r2 - eor r2,r7,r8 - veor d25,d25,d24 - eor r0,r6,r6,ror#5 - add r10,r10,r12 - vadd.i32 d4,d4,d25 - and r2,r2,r6 - eor r12,r0,r6,ror#19 - vshr.u32 d24,d4,#17 - eor r0,r10,r10,ror#11 - eor r2,r2,r8 - vsli.32 d24,d4,#15 - add r9,r9,r12,ror#6 - eor r12,r10,r11 - vshr.u32 d25,d4,#10 - eor r0,r0,r10,ror#20 - add r9,r9,r2 - veor d25,d25,d24 - ldr r2,[sp,#44] - and r3,r3,r12 - vshr.u32 d24,d4,#19 - add r5,r5,r9 - add r9,r9,r0,ror#2 - eor r3,r3,r11 - vld1.32 {q8},[r14,:128]! - add r8,r8,r2 - vsli.32 d24,d4,#13 - eor r2,r6,r7 - eor r0,r5,r5,ror#5 - veor d25,d25,d24 - add r9,r9,r3 - and r2,r2,r5 - vadd.i32 d5,d5,d25 - eor r3,r0,r5,ror#19 - eor r0,r9,r9,ror#11 - vadd.i32 q8,q8,q2 - eor r2,r2,r7 - add r8,r8,r3,ror#6 - eor r3,r9,r10 - eor r0,r0,r9,ror#20 - add r8,r8,r2 - ldr r2,[sp,#48] - and r12,r12,r3 - add r4,r4,r8 - vst1.32 {q8},[r1,:128]! - add r8,r8,r0,ror#2 - eor r12,r12,r10 - vext.8 q8,q3,q0,#4 - add r7,r7,r2 - eor r2,r5,r6 - eor r0,r4,r4,ror#5 - vext.8 q9,q1,q2,#4 - add r8,r8,r12 - and r2,r2,r4 - eor r12,r0,r4,ror#19 - vshr.u32 q10,q8,#7 - eor r0,r8,r8,ror#11 - eor r2,r2,r6 - vadd.i32 q3,q3,q9 - add r7,r7,r12,ror#6 - eor r12,r8,r9 - vshr.u32 q9,q8,#3 - eor r0,r0,r8,ror#20 - add r7,r7,r2 - vsli.32 q10,q8,#25 - ldr r2,[sp,#52] - and r3,r3,r12 - vshr.u32 q11,q8,#18 - add r11,r11,r7 - add r7,r7,r0,ror#2 - eor r3,r3,r9 - veor q9,q9,q10 - add r6,r6,r2 - vsli.32 q11,q8,#14 - eor r2,r4,r5 - eor r0,r11,r11,ror#5 - vshr.u32 d24,d5,#17 - add r7,r7,r3 - and r2,r2,r11 - veor q9,q9,q11 - eor r3,r0,r11,ror#19 - eor r0,r7,r7,ror#11 - vsli.32 d24,d5,#15 - eor r2,r2,r5 - add r6,r6,r3,ror#6 - vshr.u32 d25,d5,#10 - eor r3,r7,r8 - eor r0,r0,r7,ror#20 - vadd.i32 q3,q3,q9 - add r6,r6,r2 - ldr r2,[sp,#56] - veor d25,d25,d24 - and r12,r12,r3 - add r10,r10,r6 - vshr.u32 d24,d5,#19 - add r6,r6,r0,ror#2 - eor r12,r12,r8 - vsli.32 d24,d5,#13 - add r5,r5,r2 - eor r2,r11,r4 - veor d25,d25,d24 - eor r0,r10,r10,ror#5 - add r6,r6,r12 - vadd.i32 d6,d6,d25 - and r2,r2,r10 - eor r12,r0,r10,ror#19 - vshr.u32 d24,d6,#17 - eor r0,r6,r6,ror#11 - eor r2,r2,r4 - vsli.32 d24,d6,#15 - add r5,r5,r12,ror#6 - eor r12,r6,r7 - vshr.u32 d25,d6,#10 - eor r0,r0,r6,ror#20 - add r5,r5,r2 - veor d25,d25,d24 - ldr r2,[sp,#60] - and r3,r3,r12 - vshr.u32 d24,d6,#19 - add r9,r9,r5 - add r5,r5,r0,ror#2 - eor r3,r3,r7 - vld1.32 {q8},[r14,:128]! - add r4,r4,r2 - vsli.32 d24,d6,#13 - eor r2,r10,r11 - eor r0,r9,r9,ror#5 - veor d25,d25,d24 - add r5,r5,r3 - and r2,r2,r9 - vadd.i32 d7,d7,d25 - eor r3,r0,r9,ror#19 - eor r0,r5,r5,ror#11 - vadd.i32 q8,q8,q3 - eor r2,r2,r11 - add r4,r4,r3,ror#6 - eor r3,r5,r6 - eor r0,r0,r5,ror#20 - add r4,r4,r2 - ldr r2,[r14] - and r12,r12,r3 - add r8,r8,r4 - vst1.32 {q8},[r1,:128]! - add r4,r4,r0,ror#2 - eor r12,r12,r6 - teq r2,#0 @ check for K256 terminator - ldr r2,[sp,#0] - sub r1,r1,#64 - bne .L_00_48 - - ldr r1,[sp,#68] - ldr r0,[sp,#72] - sub r14,r14,#256 @ rewind r14 - teq r1,r0 - subeq r1,r1,#64 @ avoid SEGV - vld1.8 {q0},[r1]! @ load next input block - vld1.8 {q1},[r1]! - vld1.8 {q2},[r1]! - vld1.8 {q3},[r1]! - strne r1,[sp,#68] - mov r1,sp - add r11,r11,r2 - eor r2,r9,r10 - eor r0,r8,r8,ror#5 - add r4,r4,r12 - vld1.32 {q8},[r14,:128]! - and r2,r2,r8 - eor r12,r0,r8,ror#19 - eor r0,r4,r4,ror#11 - eor r2,r2,r10 - vrev32.8 q0,q0 - add r11,r11,r12,ror#6 - eor r12,r4,r5 - eor r0,r0,r4,ror#20 - add r11,r11,r2 - vadd.i32 q8,q8,q0 - ldr r2,[sp,#4] - and r3,r3,r12 - add r7,r7,r11 - add r11,r11,r0,ror#2 - eor r3,r3,r5 - add r10,r10,r2 - eor r2,r8,r9 - eor r0,r7,r7,ror#5 - add r11,r11,r3 - and r2,r2,r7 - eor r3,r0,r7,ror#19 - eor r0,r11,r11,ror#11 - eor r2,r2,r9 - add r10,r10,r3,ror#6 - eor r3,r11,r4 - eor r0,r0,r11,ror#20 - add r10,r10,r2 - ldr r2,[sp,#8] - and r12,r12,r3 - add r6,r6,r10 - add r10,r10,r0,ror#2 - eor r12,r12,r4 - add r9,r9,r2 - eor r2,r7,r8 - eor r0,r6,r6,ror#5 - add r10,r10,r12 - and r2,r2,r6 - eor r12,r0,r6,ror#19 - eor r0,r10,r10,ror#11 - eor r2,r2,r8 - add r9,r9,r12,ror#6 - eor r12,r10,r11 - eor r0,r0,r10,ror#20 - add r9,r9,r2 - ldr r2,[sp,#12] - and r3,r3,r12 - add r5,r5,r9 - add r9,r9,r0,ror#2 - eor r3,r3,r11 - add r8,r8,r2 - eor r2,r6,r7 - eor r0,r5,r5,ror#5 - add r9,r9,r3 - and r2,r2,r5 - eor r3,r0,r5,ror#19 - eor r0,r9,r9,ror#11 - eor r2,r2,r7 - add r8,r8,r3,ror#6 - eor r3,r9,r10 - eor r0,r0,r9,ror#20 - add r8,r8,r2 - ldr r2,[sp,#16] - and r12,r12,r3 - add r4,r4,r8 - add r8,r8,r0,ror#2 - eor r12,r12,r10 - vst1.32 {q8},[r1,:128]! - add r7,r7,r2 - eor r2,r5,r6 - eor r0,r4,r4,ror#5 - add r8,r8,r12 - vld1.32 {q8},[r14,:128]! - and r2,r2,r4 - eor r12,r0,r4,ror#19 - eor r0,r8,r8,ror#11 - eor r2,r2,r6 - vrev32.8 q1,q1 - add r7,r7,r12,ror#6 - eor r12,r8,r9 - eor r0,r0,r8,ror#20 - add r7,r7,r2 - vadd.i32 q8,q8,q1 - ldr r2,[sp,#20] - and r3,r3,r12 - add r11,r11,r7 - add r7,r7,r0,ror#2 - eor r3,r3,r9 - add r6,r6,r2 - eor r2,r4,r5 - eor r0,r11,r11,ror#5 - add r7,r7,r3 - and r2,r2,r11 - eor r3,r0,r11,ror#19 - eor r0,r7,r7,ror#11 - eor r2,r2,r5 - add r6,r6,r3,ror#6 - eor r3,r7,r8 - eor r0,r0,r7,ror#20 - add r6,r6,r2 - ldr r2,[sp,#24] - and r12,r12,r3 - add r10,r10,r6 - add r6,r6,r0,ror#2 - eor r12,r12,r8 - add r5,r5,r2 - eor r2,r11,r4 - eor r0,r10,r10,ror#5 - add r6,r6,r12 - and r2,r2,r10 - eor r12,r0,r10,ror#19 - eor r0,r6,r6,ror#11 - eor r2,r2,r4 - add r5,r5,r12,ror#6 - eor r12,r6,r7 - eor r0,r0,r6,ror#20 - add r5,r5,r2 - ldr r2,[sp,#28] - and r3,r3,r12 - add r9,r9,r5 - add r5,r5,r0,ror#2 - eor r3,r3,r7 - add r4,r4,r2 - eor r2,r10,r11 - eor r0,r9,r9,ror#5 - add r5,r5,r3 - and r2,r2,r9 - eor r3,r0,r9,ror#19 - eor r0,r5,r5,ror#11 - eor r2,r2,r11 - add r4,r4,r3,ror#6 - eor r3,r5,r6 - eor r0,r0,r5,ror#20 - add r4,r4,r2 - ldr r2,[sp,#32] - and r12,r12,r3 - add r8,r8,r4 - add r4,r4,r0,ror#2 - eor r12,r12,r6 - vst1.32 {q8},[r1,:128]! - add r11,r11,r2 - eor r2,r9,r10 - eor r0,r8,r8,ror#5 - add r4,r4,r12 - vld1.32 {q8},[r14,:128]! - and r2,r2,r8 - eor r12,r0,r8,ror#19 - eor r0,r4,r4,ror#11 - eor r2,r2,r10 - vrev32.8 q2,q2 - add r11,r11,r12,ror#6 - eor r12,r4,r5 - eor r0,r0,r4,ror#20 - add r11,r11,r2 - vadd.i32 q8,q8,q2 - ldr r2,[sp,#36] - and r3,r3,r12 - add r7,r7,r11 - add r11,r11,r0,ror#2 - eor r3,r3,r5 - add r10,r10,r2 - eor r2,r8,r9 - eor r0,r7,r7,ror#5 - add r11,r11,r3 - and r2,r2,r7 - eor r3,r0,r7,ror#19 - eor r0,r11,r11,ror#11 - eor r2,r2,r9 - add r10,r10,r3,ror#6 - eor r3,r11,r4 - eor r0,r0,r11,ror#20 - add r10,r10,r2 - ldr r2,[sp,#40] - and r12,r12,r3 - add r6,r6,r10 - add r10,r10,r0,ror#2 - eor r12,r12,r4 - add r9,r9,r2 - eor r2,r7,r8 - eor r0,r6,r6,ror#5 - add r10,r10,r12 - and r2,r2,r6 - eor r12,r0,r6,ror#19 - eor r0,r10,r10,ror#11 - eor r2,r2,r8 - add r9,r9,r12,ror#6 - eor r12,r10,r11 - eor r0,r0,r10,ror#20 - add r9,r9,r2 - ldr r2,[sp,#44] - and r3,r3,r12 - add r5,r5,r9 - add r9,r9,r0,ror#2 - eor r3,r3,r11 - add r8,r8,r2 - eor r2,r6,r7 - eor r0,r5,r5,ror#5 - add r9,r9,r3 - and r2,r2,r5 - eor r3,r0,r5,ror#19 - eor r0,r9,r9,ror#11 - eor r2,r2,r7 - add r8,r8,r3,ror#6 - eor r3,r9,r10 - eor r0,r0,r9,ror#20 - add r8,r8,r2 - ldr r2,[sp,#48] - and r12,r12,r3 - add r4,r4,r8 - add r8,r8,r0,ror#2 - eor r12,r12,r10 - vst1.32 {q8},[r1,:128]! - add r7,r7,r2 - eor r2,r5,r6 - eor r0,r4,r4,ror#5 - add r8,r8,r12 - vld1.32 {q8},[r14,:128]! - and r2,r2,r4 - eor r12,r0,r4,ror#19 - eor r0,r8,r8,ror#11 - eor r2,r2,r6 - vrev32.8 q3,q3 - add r7,r7,r12,ror#6 - eor r12,r8,r9 - eor r0,r0,r8,ror#20 - add r7,r7,r2 - vadd.i32 q8,q8,q3 - ldr r2,[sp,#52] - and r3,r3,r12 - add r11,r11,r7 - add r7,r7,r0,ror#2 - eor r3,r3,r9 - add r6,r6,r2 - eor r2,r4,r5 - eor r0,r11,r11,ror#5 - add r7,r7,r3 - and r2,r2,r11 - eor r3,r0,r11,ror#19 - eor r0,r7,r7,ror#11 - eor r2,r2,r5 - add r6,r6,r3,ror#6 - eor r3,r7,r8 - eor r0,r0,r7,ror#20 - add r6,r6,r2 - ldr r2,[sp,#56] - and r12,r12,r3 - add r10,r10,r6 - add r6,r6,r0,ror#2 - eor r12,r12,r8 - add r5,r5,r2 - eor r2,r11,r4 - eor r0,r10,r10,ror#5 - add r6,r6,r12 - and r2,r2,r10 - eor r12,r0,r10,ror#19 - eor r0,r6,r6,ror#11 - eor r2,r2,r4 - add r5,r5,r12,ror#6 - eor r12,r6,r7 - eor r0,r0,r6,ror#20 - add r5,r5,r2 - ldr r2,[sp,#60] - and r3,r3,r12 - add r9,r9,r5 - add r5,r5,r0,ror#2 - eor r3,r3,r7 - add r4,r4,r2 - eor r2,r10,r11 - eor r0,r9,r9,ror#5 - add r5,r5,r3 - and r2,r2,r9 - eor r3,r0,r9,ror#19 - eor r0,r5,r5,ror#11 - eor r2,r2,r11 - add r4,r4,r3,ror#6 - eor r3,r5,r6 - eor r0,r0,r5,ror#20 - add r4,r4,r2 - ldr r2,[sp,#64] - and r12,r12,r3 - add r8,r8,r4 - add r4,r4,r0,ror#2 - eor r12,r12,r6 - vst1.32 {q8},[r1,:128]! - ldr r0,[r2,#0] - add r4,r4,r12 @ h+=Maj(a,b,c) from the past - ldr r12,[r2,#4] - ldr r3,[r2,#8] - ldr r1,[r2,#12] - add r4,r4,r0 @ accumulate - ldr r0,[r2,#16] - add r5,r5,r12 - ldr r12,[r2,#20] - add r6,r6,r3 - ldr r3,[r2,#24] - add r7,r7,r1 - ldr r1,[r2,#28] - add r8,r8,r0 - str r4,[r2],#4 - add r9,r9,r12 - str r5,[r2],#4 - add r10,r10,r3 - str r6,[r2],#4 - add r11,r11,r1 - str r7,[r2],#4 - stmia r2,{r8-r11} - - movne r1,sp - ldrne r2,[sp,#0] - eorne r12,r12,r12 - ldreq sp,[sp,#76] @ restore original sp - eorne r3,r5,r6 - bne .L_00_48 - - ldmia sp!,{r4-r12,pc} -.size sha256_block_data_order_neon,.-sha256_block_data_order_neon -#endif -#if __ARM_ARCH__>=7 -.type sha256_block_data_order_armv8,%function -.align 5 -sha256_block_data_order_armv8: -.LARMv8: - vld1.32 {q0,q1},[r0] - sub r3,r3,#sha256_block_data_order-K256 - -.Loop_v8: - vld1.8 {q8-q9},[r1]! - vld1.8 {q10-q11},[r1]! - vld1.32 {q12},[r3]! - vrev32.8 q8,q8 - vrev32.8 q9,q9 - vrev32.8 q10,q10 - vrev32.8 q11,q11 - vmov q14,q0 @ offload - vmov q15,q1 - teq r1,r2 - vld1.32 {q13},[r3]! - vadd.i32 q12,q12,q8 - .byte 0xe2,0x03,0xfa,0xf3 @ sha256su0 q8,q9 - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - .byte 0xe6,0x0c,0x64,0xf3 @ sha256su1 q8,q10,q11 - vld1.32 {q12},[r3]! - vadd.i32 q13,q13,q9 - .byte 0xe4,0x23,0xfa,0xf3 @ sha256su0 q9,q10 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - .byte 0xe0,0x2c,0x66,0xf3 @ sha256su1 q9,q11,q8 - vld1.32 {q13},[r3]! - vadd.i32 q12,q12,q10 - .byte 0xe6,0x43,0xfa,0xf3 @ sha256su0 q10,q11 - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - .byte 0xe2,0x4c,0x60,0xf3 @ sha256su1 q10,q8,q9 - vld1.32 {q12},[r3]! - vadd.i32 q13,q13,q11 - .byte 0xe0,0x63,0xfa,0xf3 @ sha256su0 q11,q8 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - .byte 0xe4,0x6c,0x62,0xf3 @ sha256su1 q11,q9,q10 - vld1.32 {q13},[r3]! - vadd.i32 q12,q12,q8 - .byte 0xe2,0x03,0xfa,0xf3 @ sha256su0 q8,q9 - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - .byte 0xe6,0x0c,0x64,0xf3 @ sha256su1 q8,q10,q11 - vld1.32 {q12},[r3]! - vadd.i32 q13,q13,q9 - .byte 0xe4,0x23,0xfa,0xf3 @ sha256su0 q9,q10 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - .byte 0xe0,0x2c,0x66,0xf3 @ sha256su1 q9,q11,q8 - vld1.32 {q13},[r3]! - vadd.i32 q12,q12,q10 - .byte 0xe6,0x43,0xfa,0xf3 @ sha256su0 q10,q11 - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - .byte 0xe2,0x4c,0x60,0xf3 @ sha256su1 q10,q8,q9 - vld1.32 {q12},[r3]! - vadd.i32 q13,q13,q11 - .byte 0xe0,0x63,0xfa,0xf3 @ sha256su0 q11,q8 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - .byte 0xe4,0x6c,0x62,0xf3 @ sha256su1 q11,q9,q10 - vld1.32 {q13},[r3]! - vadd.i32 q12,q12,q8 - .byte 0xe2,0x03,0xfa,0xf3 @ sha256su0 q8,q9 - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - .byte 0xe6,0x0c,0x64,0xf3 @ sha256su1 q8,q10,q11 - vld1.32 {q12},[r3]! - vadd.i32 q13,q13,q9 - .byte 0xe4,0x23,0xfa,0xf3 @ sha256su0 q9,q10 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - .byte 0xe0,0x2c,0x66,0xf3 @ sha256su1 q9,q11,q8 - vld1.32 {q13},[r3]! - vadd.i32 q12,q12,q10 - .byte 0xe6,0x43,0xfa,0xf3 @ sha256su0 q10,q11 - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - .byte 0xe2,0x4c,0x60,0xf3 @ sha256su1 q10,q8,q9 - vld1.32 {q12},[r3]! - vadd.i32 q13,q13,q11 - .byte 0xe0,0x63,0xfa,0xf3 @ sha256su0 q11,q8 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - .byte 0xe4,0x6c,0x62,0xf3 @ sha256su1 q11,q9,q10 - vld1.32 {q13},[r3]! - vadd.i32 q12,q12,q8 - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - - vld1.32 {q12},[r3]! - vadd.i32 q13,q13,q9 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - - vld1.32 {q13},[r3] - vadd.i32 q12,q12,q10 - sub r3,r3,#256-16 @ rewind - vmov q2,q0 - .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12 - .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12 - - vadd.i32 q13,q13,q11 - vmov q2,q0 - .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13 - .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13 - - vadd.i32 q0,q0,q14 - vadd.i32 q1,q1,q15 - bne .Loop_v8 - - vst1.32 {q0,q1},[r0] - - bx lr @ bx lr -.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8 -#endif -.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro@openssl.org>" -.align 2 -.comm OPENSSL_armcap_P,4,4 diff --git a/app/openssl/crypto/sha/asm/sha256-armv4.pl b/app/openssl/crypto/sha/asm/sha256-armv4.pl deleted file mode 100644 index 505ca8f3..00000000 --- a/app/openssl/crypto/sha/asm/sha256-armv4.pl +++ /dev/null @@ -1,656 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA256 block procedure for ARMv4. May 2007. - -# Performance is ~2x better than gcc 3.4 generated code and in "abso- -# lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per -# byte [on single-issue Xscale PXA250 core]. - -# July 2010. -# -# Rescheduling for dual-issue pipeline resulted in 22% improvement on -# Cortex A8 core and ~20 cycles per processed byte. - -# February 2011. -# -# Profiler-assisted and platform-specific optimization resulted in 16% -# improvement on Cortex A8 core and ~15.4 cycles per processed byte. - -# September 2013. -# -# Add NEON implementation. On Cortex A8 it was measured to process one -# byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon -# S4 does it in 12.5 cycles too, but it's 50% faster than integer-only -# code (meaning that latter performs sub-optimally, nothing was done -# about it). - -# May 2014. -# -# Add ARMv8 code path performing at 2.0 cpb on Apple A7. - -while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} -open STDOUT,">$output"; - -$ctx="r0"; $t0="r0"; -$inp="r1"; $t4="r1"; -$len="r2"; $t1="r2"; -$T1="r3"; $t3="r3"; -$A="r4"; -$B="r5"; -$C="r6"; -$D="r7"; -$E="r8"; -$F="r9"; -$G="r10"; -$H="r11"; -@V=($A,$B,$C,$D,$E,$F,$G,$H); -$t2="r12"; -$Ktbl="r14"; - -@Sigma0=( 2,13,22); -@Sigma1=( 6,11,25); -@sigma0=( 7,18, 3); -@sigma1=(17,19,10); - -sub BODY_00_15 { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___ if ($i<16); -#if __ARM_ARCH__>=7 - @ ldr $t1,[$inp],#4 @ $i -# if $i==15 - str $inp,[sp,#17*4] @ make room for $t4 -# endif - eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` - add $a,$a,$t2 @ h+=Maj(a,b,c) from the past - eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) - rev $t1,$t1 -#else - @ ldrb $t1,[$inp,#3] @ $i - add $a,$a,$t2 @ h+=Maj(a,b,c) from the past - ldrb $t2,[$inp,#2] - ldrb $t0,[$inp,#1] - orr $t1,$t1,$t2,lsl#8 - ldrb $t2,[$inp],#4 - orr $t1,$t1,$t0,lsl#16 -# if $i==15 - str $inp,[sp,#17*4] @ make room for $t4 -# endif - eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` - orr $t1,$t1,$t2,lsl#24 - eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) -#endif -___ -$code.=<<___; - ldr $t2,[$Ktbl],#4 @ *K256++ - add $h,$h,$t1 @ h+=X[i] - str $t1,[sp,#`$i%16`*4] - eor $t1,$f,$g - add $h,$h,$t0,ror#$Sigma1[0] @ h+=Sigma1(e) - and $t1,$t1,$e - add $h,$h,$t2 @ h+=K256[i] - eor $t1,$t1,$g @ Ch(e,f,g) - eor $t0,$a,$a,ror#`$Sigma0[1]-$Sigma0[0]` - add $h,$h,$t1 @ h+=Ch(e,f,g) -#if $i==31 - and $t2,$t2,#0xff - cmp $t2,#0xf2 @ done? -#endif -#if $i<15 -# if __ARM_ARCH__>=7 - ldr $t1,[$inp],#4 @ prefetch -# else - ldrb $t1,[$inp,#3] -# endif - eor $t2,$a,$b @ a^b, b^c in next round -#else - ldr $t1,[sp,#`($i+2)%16`*4] @ from future BODY_16_xx - eor $t2,$a,$b @ a^b, b^c in next round - ldr $t4,[sp,#`($i+15)%16`*4] @ from future BODY_16_xx -#endif - eor $t0,$t0,$a,ror#`$Sigma0[2]-$Sigma0[0]` @ Sigma0(a) - and $t3,$t3,$t2 @ (b^c)&=(a^b) - add $d,$d,$h @ d+=h - eor $t3,$t3,$b @ Maj(a,b,c) - add $h,$h,$t0,ror#$Sigma0[0] @ h+=Sigma0(a) - @ add $h,$h,$t3 @ h+=Maj(a,b,c) -___ - ($t2,$t3)=($t3,$t2); -} - -sub BODY_16_XX { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___; - @ ldr $t1,[sp,#`($i+1)%16`*4] @ $i - @ ldr $t4,[sp,#`($i+14)%16`*4] - mov $t0,$t1,ror#$sigma0[0] - add $a,$a,$t2 @ h+=Maj(a,b,c) from the past - mov $t2,$t4,ror#$sigma1[0] - eor $t0,$t0,$t1,ror#$sigma0[1] - eor $t2,$t2,$t4,ror#$sigma1[1] - eor $t0,$t0,$t1,lsr#$sigma0[2] @ sigma0(X[i+1]) - ldr $t1,[sp,#`($i+0)%16`*4] - eor $t2,$t2,$t4,lsr#$sigma1[2] @ sigma1(X[i+14]) - ldr $t4,[sp,#`($i+9)%16`*4] - - add $t2,$t2,$t0 - eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` @ from BODY_00_15 - add $t1,$t1,$t2 - eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) - add $t1,$t1,$t4 @ X[i] -___ - &BODY_00_15(@_); -} - -$code=<<___; -#include "arm_arch.h" - -.text -.code 32 - -.type K256,%object -.align 5 -K256: -.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 -.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 -.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 -.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 -.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc -.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da -.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 -.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 -.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 -.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 -.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 -.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 -.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 -.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 -.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 -.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -.size K256,.-K256 -.word 0 @ terminator -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-sha256_block_data_order -.align 5 - -.global sha256_block_data_order -.type sha256_block_data_order,%function -sha256_block_data_order: - sub r3,pc,#8 @ sha256_block_data_order - add $len,$inp,$len,lsl#6 @ len to point at the end of inp -#if __ARM_ARCH__>=7 - ldr r12,.LOPENSSL_armcap - ldr r12,[r3,r12] @ OPENSSL_armcap_P - tst r12,#ARMV8_SHA256 - bne .LARMv8 - tst r12,#ARMV7_NEON - bne .LNEON -#endif - stmdb sp!,{$ctx,$inp,$len,r4-r11,lr} - ldmia $ctx,{$A,$B,$C,$D,$E,$F,$G,$H} - sub $Ktbl,r3,#256+32 @ K256 - sub sp,sp,#16*4 @ alloca(X[16]) -.Loop: -# if __ARM_ARCH__>=7 - ldr $t1,[$inp],#4 -# else - ldrb $t1,[$inp,#3] -# endif - eor $t3,$B,$C @ magic - eor $t2,$t2,$t2 -___ -for($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); } -$code.=".Lrounds_16_xx:\n"; -for (;$i<32;$i++) { &BODY_16_XX($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - ldreq $t3,[sp,#16*4] @ pull ctx - bne .Lrounds_16_xx - - add $A,$A,$t2 @ h+=Maj(a,b,c) from the past - ldr $t0,[$t3,#0] - ldr $t1,[$t3,#4] - ldr $t2,[$t3,#8] - add $A,$A,$t0 - ldr $t0,[$t3,#12] - add $B,$B,$t1 - ldr $t1,[$t3,#16] - add $C,$C,$t2 - ldr $t2,[$t3,#20] - add $D,$D,$t0 - ldr $t0,[$t3,#24] - add $E,$E,$t1 - ldr $t1,[$t3,#28] - add $F,$F,$t2 - ldr $inp,[sp,#17*4] @ pull inp - ldr $t2,[sp,#18*4] @ pull inp+len - add $G,$G,$t0 - add $H,$H,$t1 - stmia $t3,{$A,$B,$C,$D,$E,$F,$G,$H} - cmp $inp,$t2 - sub $Ktbl,$Ktbl,#256 @ rewind Ktbl - bne .Loop - - add sp,sp,#`16+3`*4 @ destroy frame -#if __ARM_ARCH__>=5 - ldmia sp!,{r4-r11,pc} -#else - ldmia sp!,{r4-r11,lr} - tst lr,#1 - moveq pc,lr @ be binary compatible with V4, yet - bx lr @ interoperable with Thumb ISA:-) -#endif -.size sha256_block_data_order,.-sha256_block_data_order -___ -###################################################################### -# NEON stuff -# -{{{ -my @X=map("q$_",(0..3)); -my ($T0,$T1,$T2,$T3,$T4,$T5)=("q8","q9","q10","q11","d24","d25"); -my $Xfer=$t4; -my $j=0; - -sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; } -sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; } - -sub AUTOLOAD() # thunk [simplified] x86-style perlasm -{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./; - my $arg = pop; - $arg = "#$arg" if ($arg*1 eq $arg); - $code .= "\t$opcode\t".join(',',@_,$arg)."\n"; -} - -sub Xupdate() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e,$f,$g,$h); - - &vext_8 ($T0,@X[0],@X[1],4); # X[1..4] - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vext_8 ($T1,@X[2],@X[3],4); # X[9..12] - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T2,$T0,$sigma0[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += X[9..12] - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T1,$T0,$sigma0[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T2,$T0,32-$sigma0[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T3,$T0,$sigma0[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T1,$T1,$T2); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T3,$T0,32-$sigma0[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T1,$T1,$T3); # sigma0(X[1..4]) - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T5,&Dhi(@X[3]),$sigma1[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += sigma0(X[1..4]) - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); # sigma1(X[14..15]) - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (&Dlo(@X[0]),&Dlo(@X[0]),$T5);# X[0..1] += sigma1(X[14..15]) - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T5,&Dlo(@X[0]),$sigma1[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &vld1_32 ("{$T0}","[$Ktbl,:128]!"); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); # sigma1(X[16..17]) - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (&Dhi(@X[0]),&Dhi(@X[0]),$T5);# X[2..3] += sigma1(X[16..17]) - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 ($T0,$T0,@X[0]); - while($#insns>=2) { eval(shift(@insns)); } - &vst1_32 ("{$T0}","[$Xfer,:128]!"); - eval(shift(@insns)); - eval(shift(@insns)); - - push(@X,shift(@X)); # "rotate" X[] -} - -sub Xpreload() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e,$f,$g,$h); - - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vld1_32 ("{$T0}","[$Ktbl,:128]!"); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vrev32_8 (@X[0],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 ($T0,$T0,@X[0]); - foreach (@insns) { eval; } # remaining instructions - &vst1_32 ("{$T0}","[$Xfer,:128]!"); - - push(@X,shift(@X)); # "rotate" X[] -} - -sub body_00_15 () { - ( - '($a,$b,$c,$d,$e,$f,$g,$h)=@V;'. - '&add ($h,$h,$t1)', # h+=X[i]+K[i] - '&eor ($t1,$f,$g)', - '&eor ($t0,$e,$e,"ror#".($Sigma1[1]-$Sigma1[0]))', - '&add ($a,$a,$t2)', # h+=Maj(a,b,c) from the past - '&and ($t1,$t1,$e)', - '&eor ($t2,$t0,$e,"ror#".($Sigma1[2]-$Sigma1[0]))', # Sigma1(e) - '&eor ($t0,$a,$a,"ror#".($Sigma0[1]-$Sigma0[0]))', - '&eor ($t1,$t1,$g)', # Ch(e,f,g) - '&add ($h,$h,$t2,"ror#$Sigma1[0]")', # h+=Sigma1(e) - '&eor ($t2,$a,$b)', # a^b, b^c in next round - '&eor ($t0,$t0,$a,"ror#".($Sigma0[2]-$Sigma0[0]))', # Sigma0(a) - '&add ($h,$h,$t1)', # h+=Ch(e,f,g) - '&ldr ($t1,sprintf "[sp,#%d]",4*(($j+1)&15)) if (($j&15)!=15);'. - '&ldr ($t1,"[$Ktbl]") if ($j==15);'. - '&ldr ($t1,"[sp,#64]") if ($j==31)', - '&and ($t3,$t3,$t2)', # (b^c)&=(a^b) - '&add ($d,$d,$h)', # d+=h - '&add ($h,$h,$t0,"ror#$Sigma0[0]");'. # h+=Sigma0(a) - '&eor ($t3,$t3,$b)', # Maj(a,b,c) - '$j++; unshift(@V,pop(@V)); ($t2,$t3)=($t3,$t2);' - ) -} - -$code.=<<___; -#if __ARM_ARCH__>=7 -.fpu neon - -.type sha256_block_data_order_neon,%function -.align 4 -sha256_block_data_order_neon: -.LNEON: - stmdb sp!,{r4-r12,lr} - - mov $t2,sp - sub sp,sp,#16*4+16 @ alloca - sub $Ktbl,r3,#256+32 @ K256 - bic sp,sp,#15 @ align for 128-bit stores - - vld1.8 {@X[0]},[$inp]! - vld1.8 {@X[1]},[$inp]! - vld1.8 {@X[2]},[$inp]! - vld1.8 {@X[3]},[$inp]! - vld1.32 {$T0},[$Ktbl,:128]! - vld1.32 {$T1},[$Ktbl,:128]! - vld1.32 {$T2},[$Ktbl,:128]! - vld1.32 {$T3},[$Ktbl,:128]! - vrev32.8 @X[0],@X[0] @ yes, even on - str $ctx,[sp,#64] - vrev32.8 @X[1],@X[1] @ big-endian - str $inp,[sp,#68] - mov $Xfer,sp - vrev32.8 @X[2],@X[2] - str $len,[sp,#72] - vrev32.8 @X[3],@X[3] - str $t2,[sp,#76] @ save original sp - vadd.i32 $T0,$T0,@X[0] - vadd.i32 $T1,$T1,@X[1] - vst1.32 {$T0},[$Xfer,:128]! - vadd.i32 $T2,$T2,@X[2] - vst1.32 {$T1},[$Xfer,:128]! - vadd.i32 $T3,$T3,@X[3] - vst1.32 {$T2},[$Xfer,:128]! - vst1.32 {$T3},[$Xfer,:128]! - - ldmia $ctx,{$A-$H} - sub $Xfer,$Xfer,#64 - ldr $t1,[sp,#0] - eor $t2,$t2,$t2 - eor $t3,$B,$C - b .L_00_48 - -.align 4 -.L_00_48: -___ - &Xupdate(\&body_00_15); - &Xupdate(\&body_00_15); - &Xupdate(\&body_00_15); - &Xupdate(\&body_00_15); -$code.=<<___; - teq $t1,#0 @ check for K256 terminator - ldr $t1,[sp,#0] - sub $Xfer,$Xfer,#64 - bne .L_00_48 - - ldr $inp,[sp,#68] - ldr $t0,[sp,#72] - sub $Ktbl,$Ktbl,#256 @ rewind $Ktbl - teq $inp,$t0 - subeq $inp,$inp,#64 @ avoid SEGV - vld1.8 {@X[0]},[$inp]! @ load next input block - vld1.8 {@X[1]},[$inp]! - vld1.8 {@X[2]},[$inp]! - vld1.8 {@X[3]},[$inp]! - strne $inp,[sp,#68] - mov $Xfer,sp -___ - &Xpreload(\&body_00_15); - &Xpreload(\&body_00_15); - &Xpreload(\&body_00_15); - &Xpreload(\&body_00_15); -$code.=<<___; - ldr $t0,[$t1,#0] - add $A,$A,$t2 @ h+=Maj(a,b,c) from the past - ldr $t2,[$t1,#4] - ldr $t3,[$t1,#8] - ldr $t4,[$t1,#12] - add $A,$A,$t0 @ accumulate - ldr $t0,[$t1,#16] - add $B,$B,$t2 - ldr $t2,[$t1,#20] - add $C,$C,$t3 - ldr $t3,[$t1,#24] - add $D,$D,$t4 - ldr $t4,[$t1,#28] - add $E,$E,$t0 - str $A,[$t1],#4 - add $F,$F,$t2 - str $B,[$t1],#4 - add $G,$G,$t3 - str $C,[$t1],#4 - add $H,$H,$t4 - str $D,[$t1],#4 - stmia $t1,{$E-$H} - - movne $Xfer,sp - ldrne $t1,[sp,#0] - eorne $t2,$t2,$t2 - ldreq sp,[sp,#76] @ restore original sp - eorne $t3,$B,$C - bne .L_00_48 - - ldmia sp!,{r4-r12,pc} -.size sha256_block_data_order_neon,.-sha256_block_data_order_neon -#endif -___ -}}} -###################################################################### -# ARMv8 stuff -# -{{{ -my ($ABCD,$EFGH,$abcd)=map("q$_",(0..2)); -my @MSG=map("q$_",(8..11)); -my ($W0,$W1,$ABCD_SAVE,$EFGH_SAVE)=map("q$_",(12..15)); -my $Ktbl="r3"; - -$code.=<<___; -#if __ARM_ARCH__>=7 -.type sha256_block_data_order_armv8,%function -.align 5 -sha256_block_data_order_armv8: -.LARMv8: - vld1.32 {$ABCD,$EFGH},[$ctx] - sub $Ktbl,r3,#sha256_block_data_order-K256 - -.Loop_v8: - vld1.8 {@MSG[0]-@MSG[1]},[$inp]! - vld1.8 {@MSG[2]-@MSG[3]},[$inp]! - vld1.32 {$W0},[$Ktbl]! - vrev32.8 @MSG[0],@MSG[0] - vrev32.8 @MSG[1],@MSG[1] - vrev32.8 @MSG[2],@MSG[2] - vrev32.8 @MSG[3],@MSG[3] - vmov $ABCD_SAVE,$ABCD @ offload - vmov $EFGH_SAVE,$EFGH - teq $inp,$len -___ -for($i=0;$i<12;$i++) { -$code.=<<___; - vld1.32 {$W1},[$Ktbl]! - vadd.i32 $W0,$W0,@MSG[0] - sha256su0 @MSG[0],@MSG[1] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - sha256su1 @MSG[0],@MSG[2],@MSG[3] -___ - ($W0,$W1)=($W1,$W0); push(@MSG,shift(@MSG)); -} -$code.=<<___; - vld1.32 {$W1},[$Ktbl]! - vadd.i32 $W0,$W0,@MSG[0] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - - vld1.32 {$W0},[$Ktbl]! - vadd.i32 $W1,$W1,@MSG[1] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W1 - sha256h2 $EFGH,$abcd,$W1 - - vld1.32 {$W1},[$Ktbl] - vadd.i32 $W0,$W0,@MSG[2] - sub $Ktbl,$Ktbl,#256-16 @ rewind - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - - vadd.i32 $W1,$W1,@MSG[3] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W1 - sha256h2 $EFGH,$abcd,$W1 - - vadd.i32 $ABCD,$ABCD,$ABCD_SAVE - vadd.i32 $EFGH,$EFGH,$EFGH_SAVE - bne .Loop_v8 - - vst1.32 {$ABCD,$EFGH},[$ctx] - - ret @ bx lr -.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8 -#endif -___ -}}} -$code.=<<___; -.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro\@openssl.org>" -.align 2 -.comm OPENSSL_armcap_P,4,4 -___ - -{ my %opcode = ( - "sha256h" => 0xf3000c40, "sha256h2" => 0xf3100c40, - "sha256su0" => 0xf3ba03c0, "sha256su1" => 0xf3200c40 ); - - sub unsha256 { - my ($mnemonic,$arg)=@_; - - if ($arg =~ m/q([0-9]+)(?:,\s*q([0-9]+))?,\s*q([0-9]+)/o) { - my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19) - |(($2&7)<<17)|(($2&8)<<4) - |(($3&7)<<1) |(($3&8)<<2); - # since ARMv7 instructions are always encoded little-endian. - # correct solution is to use .inst directive, but older - # assemblers don't implement it:-( - sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s", - $word&0xff,($word>>8)&0xff, - ($word>>16)&0xff,($word>>24)&0xff, - $mnemonic,$arg; - } - } -} - -foreach (split($/,$code)) { - - s/\`([^\`]*)\`/eval $1/geo; - - s/\b(sha256\w+)\s+(q.*)/unsha256($1,$2)/geo; - - s/\bret\b/bx lr/go or - s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4 - - print $_,"\n"; -} - -close STDOUT; # enforce flush diff --git a/app/openssl/crypto/sha/asm/sha256-armv8.S b/app/openssl/crypto/sha/asm/sha256-armv8.S deleted file mode 100644 index bd43b1fe..00000000 --- a/app/openssl/crypto/sha/asm/sha256-armv8.S +++ /dev/null @@ -1,1141 +0,0 @@ -#include "arm_arch.h" - -.text - -.globl sha256_block_data_order -.type sha256_block_data_order,%function -.align 6 -sha256_block_data_order: - ldr x16,.LOPENSSL_armcap_P - adr x17,.LOPENSSL_armcap_P - add x16,x16,x17 - ldr w16,[x16] - tst w16,#ARMV8_SHA256 - b.ne .Lv8_entry - stp x29,x30,[sp,#-128]! - add x29,sp,#0 - - stp x19,x20,[sp,#16] - stp x21,x22,[sp,#32] - stp x23,x24,[sp,#48] - stp x25,x26,[sp,#64] - stp x27,x28,[sp,#80] - sub sp,sp,#4*4 - - ldp w20,w21,[x0] // load context - ldp w22,w23,[x0,#2*4] - ldp w24,w25,[x0,#4*4] - add x2,x1,x2,lsl#6 // end of input - ldp w26,w27,[x0,#6*4] - adr x30,K256 - stp x0,x2,[x29,#96] - -.Loop: - ldp w3,w4,[x1],#2*4 - ldr w19,[x30],#4 // *K++ - eor w28,w21,w22 // magic seed - str x1,[x29,#112] -#ifndef __ARMEB__ - rev w3,w3 // 0 -#endif - ror w16,w24,#6 - add w27,w27,w19 // h+=K[i] - eor w6,w24,w24,ror#14 - and w17,w25,w24 - bic w19,w26,w24 - add w27,w27,w3 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w20,w21 // a^b, b^c in next round - eor w16,w16,w6,ror#11 // Sigma1(e) - ror w6,w20,#2 - add w27,w27,w17 // h+=Ch(e,f,g) - eor w17,w20,w20,ror#9 - add w27,w27,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w23,w23,w27 // d+=h - eor w28,w28,w21 // Maj(a,b,c) - eor w17,w6,w17,ror#13 // Sigma0(a) - add w27,w27,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w27,w27,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w4,w4 // 1 -#endif - ldp w5,w6,[x1],#2*4 - add w27,w27,w17 // h+=Sigma0(a) - ror w16,w23,#6 - add w26,w26,w28 // h+=K[i] - eor w7,w23,w23,ror#14 - and w17,w24,w23 - bic w28,w25,w23 - add w26,w26,w4 // h+=X[i] - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w27,w20 // a^b, b^c in next round - eor w16,w16,w7,ror#11 // Sigma1(e) - ror w7,w27,#2 - add w26,w26,w17 // h+=Ch(e,f,g) - eor w17,w27,w27,ror#9 - add w26,w26,w16 // h+=Sigma1(e) - and w19,w19,w28 // (b^c)&=(a^b) - add w22,w22,w26 // d+=h - eor w19,w19,w20 // Maj(a,b,c) - eor w17,w7,w17,ror#13 // Sigma0(a) - add w26,w26,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - //add w26,w26,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w5,w5 // 2 -#endif - add w26,w26,w17 // h+=Sigma0(a) - ror w16,w22,#6 - add w25,w25,w19 // h+=K[i] - eor w8,w22,w22,ror#14 - and w17,w23,w22 - bic w19,w24,w22 - add w25,w25,w5 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w26,w27 // a^b, b^c in next round - eor w16,w16,w8,ror#11 // Sigma1(e) - ror w8,w26,#2 - add w25,w25,w17 // h+=Ch(e,f,g) - eor w17,w26,w26,ror#9 - add w25,w25,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w21,w21,w25 // d+=h - eor w28,w28,w27 // Maj(a,b,c) - eor w17,w8,w17,ror#13 // Sigma0(a) - add w25,w25,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w25,w25,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w6,w6 // 3 -#endif - ldp w7,w8,[x1],#2*4 - add w25,w25,w17 // h+=Sigma0(a) - ror w16,w21,#6 - add w24,w24,w28 // h+=K[i] - eor w9,w21,w21,ror#14 - and w17,w22,w21 - bic w28,w23,w21 - add w24,w24,w6 // h+=X[i] - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w25,w26 // a^b, b^c in next round - eor w16,w16,w9,ror#11 // Sigma1(e) - ror w9,w25,#2 - add w24,w24,w17 // h+=Ch(e,f,g) - eor w17,w25,w25,ror#9 - add w24,w24,w16 // h+=Sigma1(e) - and w19,w19,w28 // (b^c)&=(a^b) - add w20,w20,w24 // d+=h - eor w19,w19,w26 // Maj(a,b,c) - eor w17,w9,w17,ror#13 // Sigma0(a) - add w24,w24,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - //add w24,w24,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w7,w7 // 4 -#endif - add w24,w24,w17 // h+=Sigma0(a) - ror w16,w20,#6 - add w23,w23,w19 // h+=K[i] - eor w10,w20,w20,ror#14 - and w17,w21,w20 - bic w19,w22,w20 - add w23,w23,w7 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w24,w25 // a^b, b^c in next round - eor w16,w16,w10,ror#11 // Sigma1(e) - ror w10,w24,#2 - add w23,w23,w17 // h+=Ch(e,f,g) - eor w17,w24,w24,ror#9 - add w23,w23,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w27,w27,w23 // d+=h - eor w28,w28,w25 // Maj(a,b,c) - eor w17,w10,w17,ror#13 // Sigma0(a) - add w23,w23,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w23,w23,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w8,w8 // 5 -#endif - ldp w9,w10,[x1],#2*4 - add w23,w23,w17 // h+=Sigma0(a) - ror w16,w27,#6 - add w22,w22,w28 // h+=K[i] - eor w11,w27,w27,ror#14 - and w17,w20,w27 - bic w28,w21,w27 - add w22,w22,w8 // h+=X[i] - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w23,w24 // a^b, b^c in next round - eor w16,w16,w11,ror#11 // Sigma1(e) - ror w11,w23,#2 - add w22,w22,w17 // h+=Ch(e,f,g) - eor w17,w23,w23,ror#9 - add w22,w22,w16 // h+=Sigma1(e) - and w19,w19,w28 // (b^c)&=(a^b) - add w26,w26,w22 // d+=h - eor w19,w19,w24 // Maj(a,b,c) - eor w17,w11,w17,ror#13 // Sigma0(a) - add w22,w22,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - //add w22,w22,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w9,w9 // 6 -#endif - add w22,w22,w17 // h+=Sigma0(a) - ror w16,w26,#6 - add w21,w21,w19 // h+=K[i] - eor w12,w26,w26,ror#14 - and w17,w27,w26 - bic w19,w20,w26 - add w21,w21,w9 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w22,w23 // a^b, b^c in next round - eor w16,w16,w12,ror#11 // Sigma1(e) - ror w12,w22,#2 - add w21,w21,w17 // h+=Ch(e,f,g) - eor w17,w22,w22,ror#9 - add w21,w21,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w25,w25,w21 // d+=h - eor w28,w28,w23 // Maj(a,b,c) - eor w17,w12,w17,ror#13 // Sigma0(a) - add w21,w21,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w21,w21,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w10,w10 // 7 -#endif - ldp w11,w12,[x1],#2*4 - add w21,w21,w17 // h+=Sigma0(a) - ror w16,w25,#6 - add w20,w20,w28 // h+=K[i] - eor w13,w25,w25,ror#14 - and w17,w26,w25 - bic w28,w27,w25 - add w20,w20,w10 // h+=X[i] - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w21,w22 // a^b, b^c in next round - eor w16,w16,w13,ror#11 // Sigma1(e) - ror w13,w21,#2 - add w20,w20,w17 // h+=Ch(e,f,g) - eor w17,w21,w21,ror#9 - add w20,w20,w16 // h+=Sigma1(e) - and w19,w19,w28 // (b^c)&=(a^b) - add w24,w24,w20 // d+=h - eor w19,w19,w22 // Maj(a,b,c) - eor w17,w13,w17,ror#13 // Sigma0(a) - add w20,w20,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - //add w20,w20,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w11,w11 // 8 -#endif - add w20,w20,w17 // h+=Sigma0(a) - ror w16,w24,#6 - add w27,w27,w19 // h+=K[i] - eor w14,w24,w24,ror#14 - and w17,w25,w24 - bic w19,w26,w24 - add w27,w27,w11 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w20,w21 // a^b, b^c in next round - eor w16,w16,w14,ror#11 // Sigma1(e) - ror w14,w20,#2 - add w27,w27,w17 // h+=Ch(e,f,g) - eor w17,w20,w20,ror#9 - add w27,w27,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w23,w23,w27 // d+=h - eor w28,w28,w21 // Maj(a,b,c) - eor w17,w14,w17,ror#13 // Sigma0(a) - add w27,w27,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w27,w27,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w12,w12 // 9 -#endif - ldp w13,w14,[x1],#2*4 - add w27,w27,w17 // h+=Sigma0(a) - ror w16,w23,#6 - add w26,w26,w28 // h+=K[i] - eor w15,w23,w23,ror#14 - and w17,w24,w23 - bic w28,w25,w23 - add w26,w26,w12 // h+=X[i] - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w27,w20 // a^b, b^c in next round - eor w16,w16,w15,ror#11 // Sigma1(e) - ror w15,w27,#2 - add w26,w26,w17 // h+=Ch(e,f,g) - eor w17,w27,w27,ror#9 - add w26,w26,w16 // h+=Sigma1(e) - and w19,w19,w28 // (b^c)&=(a^b) - add w22,w22,w26 // d+=h - eor w19,w19,w20 // Maj(a,b,c) - eor w17,w15,w17,ror#13 // Sigma0(a) - add w26,w26,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - //add w26,w26,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w13,w13 // 10 -#endif - add w26,w26,w17 // h+=Sigma0(a) - ror w16,w22,#6 - add w25,w25,w19 // h+=K[i] - eor w0,w22,w22,ror#14 - and w17,w23,w22 - bic w19,w24,w22 - add w25,w25,w13 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w26,w27 // a^b, b^c in next round - eor w16,w16,w0,ror#11 // Sigma1(e) - ror w0,w26,#2 - add w25,w25,w17 // h+=Ch(e,f,g) - eor w17,w26,w26,ror#9 - add w25,w25,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w21,w21,w25 // d+=h - eor w28,w28,w27 // Maj(a,b,c) - eor w17,w0,w17,ror#13 // Sigma0(a) - add w25,w25,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w25,w25,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w14,w14 // 11 -#endif - ldp w15,w0,[x1],#2*4 - add w25,w25,w17 // h+=Sigma0(a) - str w6,[sp,#12] - ror w16,w21,#6 - add w24,w24,w28 // h+=K[i] - eor w6,w21,w21,ror#14 - and w17,w22,w21 - bic w28,w23,w21 - add w24,w24,w14 // h+=X[i] - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w25,w26 // a^b, b^c in next round - eor w16,w16,w6,ror#11 // Sigma1(e) - ror w6,w25,#2 - add w24,w24,w17 // h+=Ch(e,f,g) - eor w17,w25,w25,ror#9 - add w24,w24,w16 // h+=Sigma1(e) - and w19,w19,w28 // (b^c)&=(a^b) - add w20,w20,w24 // d+=h - eor w19,w19,w26 // Maj(a,b,c) - eor w17,w6,w17,ror#13 // Sigma0(a) - add w24,w24,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - //add w24,w24,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w15,w15 // 12 -#endif - add w24,w24,w17 // h+=Sigma0(a) - str w7,[sp,#0] - ror w16,w20,#6 - add w23,w23,w19 // h+=K[i] - eor w7,w20,w20,ror#14 - and w17,w21,w20 - bic w19,w22,w20 - add w23,w23,w15 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w24,w25 // a^b, b^c in next round - eor w16,w16,w7,ror#11 // Sigma1(e) - ror w7,w24,#2 - add w23,w23,w17 // h+=Ch(e,f,g) - eor w17,w24,w24,ror#9 - add w23,w23,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w27,w27,w23 // d+=h - eor w28,w28,w25 // Maj(a,b,c) - eor w17,w7,w17,ror#13 // Sigma0(a) - add w23,w23,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w23,w23,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w0,w0 // 13 -#endif - ldp w1,w2,[x1] - add w23,w23,w17 // h+=Sigma0(a) - str w8,[sp,#4] - ror w16,w27,#6 - add w22,w22,w28 // h+=K[i] - eor w8,w27,w27,ror#14 - and w17,w20,w27 - bic w28,w21,w27 - add w22,w22,w0 // h+=X[i] - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w23,w24 // a^b, b^c in next round - eor w16,w16,w8,ror#11 // Sigma1(e) - ror w8,w23,#2 - add w22,w22,w17 // h+=Ch(e,f,g) - eor w17,w23,w23,ror#9 - add w22,w22,w16 // h+=Sigma1(e) - and w19,w19,w28 // (b^c)&=(a^b) - add w26,w26,w22 // d+=h - eor w19,w19,w24 // Maj(a,b,c) - eor w17,w8,w17,ror#13 // Sigma0(a) - add w22,w22,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - //add w22,w22,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w1,w1 // 14 -#endif - ldr w6,[sp,#12] - add w22,w22,w17 // h+=Sigma0(a) - str w9,[sp,#8] - ror w16,w26,#6 - add w21,w21,w19 // h+=K[i] - eor w9,w26,w26,ror#14 - and w17,w27,w26 - bic w19,w20,w26 - add w21,w21,w1 // h+=X[i] - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w22,w23 // a^b, b^c in next round - eor w16,w16,w9,ror#11 // Sigma1(e) - ror w9,w22,#2 - add w21,w21,w17 // h+=Ch(e,f,g) - eor w17,w22,w22,ror#9 - add w21,w21,w16 // h+=Sigma1(e) - and w28,w28,w19 // (b^c)&=(a^b) - add w25,w25,w21 // d+=h - eor w28,w28,w23 // Maj(a,b,c) - eor w17,w9,w17,ror#13 // Sigma0(a) - add w21,w21,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - //add w21,w21,w17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev w2,w2 // 15 -#endif - ldr w7,[sp,#0] - add w21,w21,w17 // h+=Sigma0(a) - str w10,[sp,#12] - ror w16,w25,#6 - add w20,w20,w28 // h+=K[i] - ror w9,w4,#7 - and w17,w26,w25 - ror w8,w1,#17 - bic w28,w27,w25 - ror w10,w21,#2 - add w20,w20,w2 // h+=X[i] - eor w16,w16,w25,ror#11 - eor w9,w9,w4,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w21,w22 // a^b, b^c in next round - eor w16,w16,w25,ror#25 // Sigma1(e) - eor w10,w10,w21,ror#13 - add w20,w20,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w8,w8,w1,ror#19 - eor w9,w9,w4,lsr#3 // sigma0(X[i+1]) - add w20,w20,w16 // h+=Sigma1(e) - eor w19,w19,w22 // Maj(a,b,c) - eor w17,w10,w21,ror#22 // Sigma0(a) - eor w8,w8,w1,lsr#10 // sigma1(X[i+14]) - add w3,w3,w12 - add w24,w24,w20 // d+=h - add w20,w20,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w3,w3,w9 - add w20,w20,w17 // h+=Sigma0(a) - add w3,w3,w8 -.Loop_16_xx: - ldr w8,[sp,#4] - str w11,[sp,#0] - ror w16,w24,#6 - add w27,w27,w19 // h+=K[i] - ror w10,w5,#7 - and w17,w25,w24 - ror w9,w2,#17 - bic w19,w26,w24 - ror w11,w20,#2 - add w27,w27,w3 // h+=X[i] - eor w16,w16,w24,ror#11 - eor w10,w10,w5,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w20,w21 // a^b, b^c in next round - eor w16,w16,w24,ror#25 // Sigma1(e) - eor w11,w11,w20,ror#13 - add w27,w27,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w9,w9,w2,ror#19 - eor w10,w10,w5,lsr#3 // sigma0(X[i+1]) - add w27,w27,w16 // h+=Sigma1(e) - eor w28,w28,w21 // Maj(a,b,c) - eor w17,w11,w20,ror#22 // Sigma0(a) - eor w9,w9,w2,lsr#10 // sigma1(X[i+14]) - add w4,w4,w13 - add w23,w23,w27 // d+=h - add w27,w27,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w4,w4,w10 - add w27,w27,w17 // h+=Sigma0(a) - add w4,w4,w9 - ldr w9,[sp,#8] - str w12,[sp,#4] - ror w16,w23,#6 - add w26,w26,w28 // h+=K[i] - ror w11,w6,#7 - and w17,w24,w23 - ror w10,w3,#17 - bic w28,w25,w23 - ror w12,w27,#2 - add w26,w26,w4 // h+=X[i] - eor w16,w16,w23,ror#11 - eor w11,w11,w6,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w27,w20 // a^b, b^c in next round - eor w16,w16,w23,ror#25 // Sigma1(e) - eor w12,w12,w27,ror#13 - add w26,w26,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w10,w10,w3,ror#19 - eor w11,w11,w6,lsr#3 // sigma0(X[i+1]) - add w26,w26,w16 // h+=Sigma1(e) - eor w19,w19,w20 // Maj(a,b,c) - eor w17,w12,w27,ror#22 // Sigma0(a) - eor w10,w10,w3,lsr#10 // sigma1(X[i+14]) - add w5,w5,w14 - add w22,w22,w26 // d+=h - add w26,w26,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w5,w5,w11 - add w26,w26,w17 // h+=Sigma0(a) - add w5,w5,w10 - ldr w10,[sp,#12] - str w13,[sp,#8] - ror w16,w22,#6 - add w25,w25,w19 // h+=K[i] - ror w12,w7,#7 - and w17,w23,w22 - ror w11,w4,#17 - bic w19,w24,w22 - ror w13,w26,#2 - add w25,w25,w5 // h+=X[i] - eor w16,w16,w22,ror#11 - eor w12,w12,w7,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w26,w27 // a^b, b^c in next round - eor w16,w16,w22,ror#25 // Sigma1(e) - eor w13,w13,w26,ror#13 - add w25,w25,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w11,w11,w4,ror#19 - eor w12,w12,w7,lsr#3 // sigma0(X[i+1]) - add w25,w25,w16 // h+=Sigma1(e) - eor w28,w28,w27 // Maj(a,b,c) - eor w17,w13,w26,ror#22 // Sigma0(a) - eor w11,w11,w4,lsr#10 // sigma1(X[i+14]) - add w6,w6,w15 - add w21,w21,w25 // d+=h - add w25,w25,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w6,w6,w12 - add w25,w25,w17 // h+=Sigma0(a) - add w6,w6,w11 - ldr w11,[sp,#0] - str w14,[sp,#12] - ror w16,w21,#6 - add w24,w24,w28 // h+=K[i] - ror w13,w8,#7 - and w17,w22,w21 - ror w12,w5,#17 - bic w28,w23,w21 - ror w14,w25,#2 - add w24,w24,w6 // h+=X[i] - eor w16,w16,w21,ror#11 - eor w13,w13,w8,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w25,w26 // a^b, b^c in next round - eor w16,w16,w21,ror#25 // Sigma1(e) - eor w14,w14,w25,ror#13 - add w24,w24,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w12,w12,w5,ror#19 - eor w13,w13,w8,lsr#3 // sigma0(X[i+1]) - add w24,w24,w16 // h+=Sigma1(e) - eor w19,w19,w26 // Maj(a,b,c) - eor w17,w14,w25,ror#22 // Sigma0(a) - eor w12,w12,w5,lsr#10 // sigma1(X[i+14]) - add w7,w7,w0 - add w20,w20,w24 // d+=h - add w24,w24,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w7,w7,w13 - add w24,w24,w17 // h+=Sigma0(a) - add w7,w7,w12 - ldr w12,[sp,#4] - str w15,[sp,#0] - ror w16,w20,#6 - add w23,w23,w19 // h+=K[i] - ror w14,w9,#7 - and w17,w21,w20 - ror w13,w6,#17 - bic w19,w22,w20 - ror w15,w24,#2 - add w23,w23,w7 // h+=X[i] - eor w16,w16,w20,ror#11 - eor w14,w14,w9,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w24,w25 // a^b, b^c in next round - eor w16,w16,w20,ror#25 // Sigma1(e) - eor w15,w15,w24,ror#13 - add w23,w23,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w13,w13,w6,ror#19 - eor w14,w14,w9,lsr#3 // sigma0(X[i+1]) - add w23,w23,w16 // h+=Sigma1(e) - eor w28,w28,w25 // Maj(a,b,c) - eor w17,w15,w24,ror#22 // Sigma0(a) - eor w13,w13,w6,lsr#10 // sigma1(X[i+14]) - add w8,w8,w1 - add w27,w27,w23 // d+=h - add w23,w23,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w8,w8,w14 - add w23,w23,w17 // h+=Sigma0(a) - add w8,w8,w13 - ldr w13,[sp,#8] - str w0,[sp,#4] - ror w16,w27,#6 - add w22,w22,w28 // h+=K[i] - ror w15,w10,#7 - and w17,w20,w27 - ror w14,w7,#17 - bic w28,w21,w27 - ror w0,w23,#2 - add w22,w22,w8 // h+=X[i] - eor w16,w16,w27,ror#11 - eor w15,w15,w10,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w23,w24 // a^b, b^c in next round - eor w16,w16,w27,ror#25 // Sigma1(e) - eor w0,w0,w23,ror#13 - add w22,w22,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w14,w14,w7,ror#19 - eor w15,w15,w10,lsr#3 // sigma0(X[i+1]) - add w22,w22,w16 // h+=Sigma1(e) - eor w19,w19,w24 // Maj(a,b,c) - eor w17,w0,w23,ror#22 // Sigma0(a) - eor w14,w14,w7,lsr#10 // sigma1(X[i+14]) - add w9,w9,w2 - add w26,w26,w22 // d+=h - add w22,w22,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w9,w9,w15 - add w22,w22,w17 // h+=Sigma0(a) - add w9,w9,w14 - ldr w14,[sp,#12] - str w1,[sp,#8] - ror w16,w26,#6 - add w21,w21,w19 // h+=K[i] - ror w0,w11,#7 - and w17,w27,w26 - ror w15,w8,#17 - bic w19,w20,w26 - ror w1,w22,#2 - add w21,w21,w9 // h+=X[i] - eor w16,w16,w26,ror#11 - eor w0,w0,w11,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w22,w23 // a^b, b^c in next round - eor w16,w16,w26,ror#25 // Sigma1(e) - eor w1,w1,w22,ror#13 - add w21,w21,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w15,w15,w8,ror#19 - eor w0,w0,w11,lsr#3 // sigma0(X[i+1]) - add w21,w21,w16 // h+=Sigma1(e) - eor w28,w28,w23 // Maj(a,b,c) - eor w17,w1,w22,ror#22 // Sigma0(a) - eor w15,w15,w8,lsr#10 // sigma1(X[i+14]) - add w10,w10,w3 - add w25,w25,w21 // d+=h - add w21,w21,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w10,w10,w0 - add w21,w21,w17 // h+=Sigma0(a) - add w10,w10,w15 - ldr w15,[sp,#0] - str w2,[sp,#12] - ror w16,w25,#6 - add w20,w20,w28 // h+=K[i] - ror w1,w12,#7 - and w17,w26,w25 - ror w0,w9,#17 - bic w28,w27,w25 - ror w2,w21,#2 - add w20,w20,w10 // h+=X[i] - eor w16,w16,w25,ror#11 - eor w1,w1,w12,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w21,w22 // a^b, b^c in next round - eor w16,w16,w25,ror#25 // Sigma1(e) - eor w2,w2,w21,ror#13 - add w20,w20,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w0,w0,w9,ror#19 - eor w1,w1,w12,lsr#3 // sigma0(X[i+1]) - add w20,w20,w16 // h+=Sigma1(e) - eor w19,w19,w22 // Maj(a,b,c) - eor w17,w2,w21,ror#22 // Sigma0(a) - eor w0,w0,w9,lsr#10 // sigma1(X[i+14]) - add w11,w11,w4 - add w24,w24,w20 // d+=h - add w20,w20,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w11,w11,w1 - add w20,w20,w17 // h+=Sigma0(a) - add w11,w11,w0 - ldr w0,[sp,#4] - str w3,[sp,#0] - ror w16,w24,#6 - add w27,w27,w19 // h+=K[i] - ror w2,w13,#7 - and w17,w25,w24 - ror w1,w10,#17 - bic w19,w26,w24 - ror w3,w20,#2 - add w27,w27,w11 // h+=X[i] - eor w16,w16,w24,ror#11 - eor w2,w2,w13,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w20,w21 // a^b, b^c in next round - eor w16,w16,w24,ror#25 // Sigma1(e) - eor w3,w3,w20,ror#13 - add w27,w27,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w1,w1,w10,ror#19 - eor w2,w2,w13,lsr#3 // sigma0(X[i+1]) - add w27,w27,w16 // h+=Sigma1(e) - eor w28,w28,w21 // Maj(a,b,c) - eor w17,w3,w20,ror#22 // Sigma0(a) - eor w1,w1,w10,lsr#10 // sigma1(X[i+14]) - add w12,w12,w5 - add w23,w23,w27 // d+=h - add w27,w27,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w12,w12,w2 - add w27,w27,w17 // h+=Sigma0(a) - add w12,w12,w1 - ldr w1,[sp,#8] - str w4,[sp,#4] - ror w16,w23,#6 - add w26,w26,w28 // h+=K[i] - ror w3,w14,#7 - and w17,w24,w23 - ror w2,w11,#17 - bic w28,w25,w23 - ror w4,w27,#2 - add w26,w26,w12 // h+=X[i] - eor w16,w16,w23,ror#11 - eor w3,w3,w14,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w27,w20 // a^b, b^c in next round - eor w16,w16,w23,ror#25 // Sigma1(e) - eor w4,w4,w27,ror#13 - add w26,w26,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w2,w2,w11,ror#19 - eor w3,w3,w14,lsr#3 // sigma0(X[i+1]) - add w26,w26,w16 // h+=Sigma1(e) - eor w19,w19,w20 // Maj(a,b,c) - eor w17,w4,w27,ror#22 // Sigma0(a) - eor w2,w2,w11,lsr#10 // sigma1(X[i+14]) - add w13,w13,w6 - add w22,w22,w26 // d+=h - add w26,w26,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w13,w13,w3 - add w26,w26,w17 // h+=Sigma0(a) - add w13,w13,w2 - ldr w2,[sp,#12] - str w5,[sp,#8] - ror w16,w22,#6 - add w25,w25,w19 // h+=K[i] - ror w4,w15,#7 - and w17,w23,w22 - ror w3,w12,#17 - bic w19,w24,w22 - ror w5,w26,#2 - add w25,w25,w13 // h+=X[i] - eor w16,w16,w22,ror#11 - eor w4,w4,w15,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w26,w27 // a^b, b^c in next round - eor w16,w16,w22,ror#25 // Sigma1(e) - eor w5,w5,w26,ror#13 - add w25,w25,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w3,w3,w12,ror#19 - eor w4,w4,w15,lsr#3 // sigma0(X[i+1]) - add w25,w25,w16 // h+=Sigma1(e) - eor w28,w28,w27 // Maj(a,b,c) - eor w17,w5,w26,ror#22 // Sigma0(a) - eor w3,w3,w12,lsr#10 // sigma1(X[i+14]) - add w14,w14,w7 - add w21,w21,w25 // d+=h - add w25,w25,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w14,w14,w4 - add w25,w25,w17 // h+=Sigma0(a) - add w14,w14,w3 - ldr w3,[sp,#0] - str w6,[sp,#12] - ror w16,w21,#6 - add w24,w24,w28 // h+=K[i] - ror w5,w0,#7 - and w17,w22,w21 - ror w4,w13,#17 - bic w28,w23,w21 - ror w6,w25,#2 - add w24,w24,w14 // h+=X[i] - eor w16,w16,w21,ror#11 - eor w5,w5,w0,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w25,w26 // a^b, b^c in next round - eor w16,w16,w21,ror#25 // Sigma1(e) - eor w6,w6,w25,ror#13 - add w24,w24,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w4,w4,w13,ror#19 - eor w5,w5,w0,lsr#3 // sigma0(X[i+1]) - add w24,w24,w16 // h+=Sigma1(e) - eor w19,w19,w26 // Maj(a,b,c) - eor w17,w6,w25,ror#22 // Sigma0(a) - eor w4,w4,w13,lsr#10 // sigma1(X[i+14]) - add w15,w15,w8 - add w20,w20,w24 // d+=h - add w24,w24,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w15,w15,w5 - add w24,w24,w17 // h+=Sigma0(a) - add w15,w15,w4 - ldr w4,[sp,#4] - str w7,[sp,#0] - ror w16,w20,#6 - add w23,w23,w19 // h+=K[i] - ror w6,w1,#7 - and w17,w21,w20 - ror w5,w14,#17 - bic w19,w22,w20 - ror w7,w24,#2 - add w23,w23,w15 // h+=X[i] - eor w16,w16,w20,ror#11 - eor w6,w6,w1,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w24,w25 // a^b, b^c in next round - eor w16,w16,w20,ror#25 // Sigma1(e) - eor w7,w7,w24,ror#13 - add w23,w23,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w5,w5,w14,ror#19 - eor w6,w6,w1,lsr#3 // sigma0(X[i+1]) - add w23,w23,w16 // h+=Sigma1(e) - eor w28,w28,w25 // Maj(a,b,c) - eor w17,w7,w24,ror#22 // Sigma0(a) - eor w5,w5,w14,lsr#10 // sigma1(X[i+14]) - add w0,w0,w9 - add w27,w27,w23 // d+=h - add w23,w23,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w0,w0,w6 - add w23,w23,w17 // h+=Sigma0(a) - add w0,w0,w5 - ldr w5,[sp,#8] - str w8,[sp,#4] - ror w16,w27,#6 - add w22,w22,w28 // h+=K[i] - ror w7,w2,#7 - and w17,w20,w27 - ror w6,w15,#17 - bic w28,w21,w27 - ror w8,w23,#2 - add w22,w22,w0 // h+=X[i] - eor w16,w16,w27,ror#11 - eor w7,w7,w2,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w23,w24 // a^b, b^c in next round - eor w16,w16,w27,ror#25 // Sigma1(e) - eor w8,w8,w23,ror#13 - add w22,w22,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w6,w6,w15,ror#19 - eor w7,w7,w2,lsr#3 // sigma0(X[i+1]) - add w22,w22,w16 // h+=Sigma1(e) - eor w19,w19,w24 // Maj(a,b,c) - eor w17,w8,w23,ror#22 // Sigma0(a) - eor w6,w6,w15,lsr#10 // sigma1(X[i+14]) - add w1,w1,w10 - add w26,w26,w22 // d+=h - add w22,w22,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w1,w1,w7 - add w22,w22,w17 // h+=Sigma0(a) - add w1,w1,w6 - ldr w6,[sp,#12] - str w9,[sp,#8] - ror w16,w26,#6 - add w21,w21,w19 // h+=K[i] - ror w8,w3,#7 - and w17,w27,w26 - ror w7,w0,#17 - bic w19,w20,w26 - ror w9,w22,#2 - add w21,w21,w1 // h+=X[i] - eor w16,w16,w26,ror#11 - eor w8,w8,w3,ror#18 - orr w17,w17,w19 // Ch(e,f,g) - eor w19,w22,w23 // a^b, b^c in next round - eor w16,w16,w26,ror#25 // Sigma1(e) - eor w9,w9,w22,ror#13 - add w21,w21,w17 // h+=Ch(e,f,g) - and w28,w28,w19 // (b^c)&=(a^b) - eor w7,w7,w0,ror#19 - eor w8,w8,w3,lsr#3 // sigma0(X[i+1]) - add w21,w21,w16 // h+=Sigma1(e) - eor w28,w28,w23 // Maj(a,b,c) - eor w17,w9,w22,ror#22 // Sigma0(a) - eor w7,w7,w0,lsr#10 // sigma1(X[i+14]) - add w2,w2,w11 - add w25,w25,w21 // d+=h - add w21,w21,w28 // h+=Maj(a,b,c) - ldr w28,[x30],#4 // *K++, w19 in next round - add w2,w2,w8 - add w21,w21,w17 // h+=Sigma0(a) - add w2,w2,w7 - ldr w7,[sp,#0] - str w10,[sp,#12] - ror w16,w25,#6 - add w20,w20,w28 // h+=K[i] - ror w9,w4,#7 - and w17,w26,w25 - ror w8,w1,#17 - bic w28,w27,w25 - ror w10,w21,#2 - add w20,w20,w2 // h+=X[i] - eor w16,w16,w25,ror#11 - eor w9,w9,w4,ror#18 - orr w17,w17,w28 // Ch(e,f,g) - eor w28,w21,w22 // a^b, b^c in next round - eor w16,w16,w25,ror#25 // Sigma1(e) - eor w10,w10,w21,ror#13 - add w20,w20,w17 // h+=Ch(e,f,g) - and w19,w19,w28 // (b^c)&=(a^b) - eor w8,w8,w1,ror#19 - eor w9,w9,w4,lsr#3 // sigma0(X[i+1]) - add w20,w20,w16 // h+=Sigma1(e) - eor w19,w19,w22 // Maj(a,b,c) - eor w17,w10,w21,ror#22 // Sigma0(a) - eor w8,w8,w1,lsr#10 // sigma1(X[i+14]) - add w3,w3,w12 - add w24,w24,w20 // d+=h - add w20,w20,w19 // h+=Maj(a,b,c) - ldr w19,[x30],#4 // *K++, w28 in next round - add w3,w3,w9 - add w20,w20,w17 // h+=Sigma0(a) - add w3,w3,w8 - cbnz w19,.Loop_16_xx - - ldp x0,x2,[x29,#96] - ldr x1,[x29,#112] - sub x30,x30,#260 // rewind - - ldp w3,w4,[x0] - ldp w5,w6,[x0,#2*4] - add x1,x1,#14*4 // advance input pointer - ldp w7,w8,[x0,#4*4] - add w20,w20,w3 - ldp w9,w10,[x0,#6*4] - add w21,w21,w4 - add w22,w22,w5 - add w23,w23,w6 - stp w20,w21,[x0] - add w24,w24,w7 - add w25,w25,w8 - stp w22,w23,[x0,#2*4] - add w26,w26,w9 - add w27,w27,w10 - cmp x1,x2 - stp w24,w25,[x0,#4*4] - stp w26,w27,[x0,#6*4] - b.ne .Loop - - ldp x19,x20,[x29,#16] - add sp,sp,#4*4 - ldp x21,x22,[x29,#32] - ldp x23,x24,[x29,#48] - ldp x25,x26,[x29,#64] - ldp x27,x28,[x29,#80] - ldp x29,x30,[sp],#128 - ret -.size sha256_block_data_order,.-sha256_block_data_order - -.align 6 -.type K256,%object -K256: - .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 - .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 - .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 - .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 - .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc - .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da - .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 - .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 - .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 - .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 - .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 - .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 - .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 - .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 - .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 - .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 - .long 0 //terminator -.size K256,.-K256 -.align 3 -.LOPENSSL_armcap_P: - .quad OPENSSL_armcap_P-. -.asciz "SHA256 block transform for ARMv8, CRYPTOGAMS by <appro@openssl.org>" -.align 2 -.type sha256_block_armv8,%function -.align 6 -sha256_block_armv8: -.Lv8_entry: - stp x29,x30,[sp,#-16]! - add x29,sp,#0 - - ld1 {v0.4s,v1.4s},[x0] - adr x3,K256 - -.Loop_hw: - ld1 {v4.16b-v7.16b},[x1],#64 - sub x2,x2,#1 - ld1 {v16.4s},[x3],#16 - rev32 v4.16b,v4.16b - rev32 v5.16b,v5.16b - rev32 v6.16b,v6.16b - rev32 v7.16b,v7.16b - orr v18.16b,v0.16b,v0.16b // offload - orr v19.16b,v1.16b,v1.16b - ld1 {v17.4s},[x3],#16 - add v16.4s,v16.4s,v4.4s - .inst 0x5e2828a4 //sha256su0 v4.16b,v5.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - .inst 0x5e0760c4 //sha256su1 v4.16b,v6.16b,v7.16b - ld1 {v16.4s},[x3],#16 - add v17.4s,v17.4s,v5.4s - .inst 0x5e2828c5 //sha256su0 v5.16b,v6.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - .inst 0x5e0460e5 //sha256su1 v5.16b,v7.16b,v4.16b - ld1 {v17.4s},[x3],#16 - add v16.4s,v16.4s,v6.4s - .inst 0x5e2828e6 //sha256su0 v6.16b,v7.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - .inst 0x5e056086 //sha256su1 v6.16b,v4.16b,v5.16b - ld1 {v16.4s},[x3],#16 - add v17.4s,v17.4s,v7.4s - .inst 0x5e282887 //sha256su0 v7.16b,v4.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - .inst 0x5e0660a7 //sha256su1 v7.16b,v5.16b,v6.16b - ld1 {v17.4s},[x3],#16 - add v16.4s,v16.4s,v4.4s - .inst 0x5e2828a4 //sha256su0 v4.16b,v5.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - .inst 0x5e0760c4 //sha256su1 v4.16b,v6.16b,v7.16b - ld1 {v16.4s},[x3],#16 - add v17.4s,v17.4s,v5.4s - .inst 0x5e2828c5 //sha256su0 v5.16b,v6.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - .inst 0x5e0460e5 //sha256su1 v5.16b,v7.16b,v4.16b - ld1 {v17.4s},[x3],#16 - add v16.4s,v16.4s,v6.4s - .inst 0x5e2828e6 //sha256su0 v6.16b,v7.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - .inst 0x5e056086 //sha256su1 v6.16b,v4.16b,v5.16b - ld1 {v16.4s},[x3],#16 - add v17.4s,v17.4s,v7.4s - .inst 0x5e282887 //sha256su0 v7.16b,v4.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - .inst 0x5e0660a7 //sha256su1 v7.16b,v5.16b,v6.16b - ld1 {v17.4s},[x3],#16 - add v16.4s,v16.4s,v4.4s - .inst 0x5e2828a4 //sha256su0 v4.16b,v5.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - .inst 0x5e0760c4 //sha256su1 v4.16b,v6.16b,v7.16b - ld1 {v16.4s},[x3],#16 - add v17.4s,v17.4s,v5.4s - .inst 0x5e2828c5 //sha256su0 v5.16b,v6.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - .inst 0x5e0460e5 //sha256su1 v5.16b,v7.16b,v4.16b - ld1 {v17.4s},[x3],#16 - add v16.4s,v16.4s,v6.4s - .inst 0x5e2828e6 //sha256su0 v6.16b,v7.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - .inst 0x5e056086 //sha256su1 v6.16b,v4.16b,v5.16b - ld1 {v16.4s},[x3],#16 - add v17.4s,v17.4s,v7.4s - .inst 0x5e282887 //sha256su0 v7.16b,v4.16b - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - .inst 0x5e0660a7 //sha256su1 v7.16b,v5.16b,v6.16b - ld1 {v17.4s},[x3],#16 - add v16.4s,v16.4s,v4.4s - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - - ld1 {v16.4s},[x3],#16 - add v17.4s,v17.4s,v5.4s - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - - ld1 {v17.4s},[x3] - add v16.4s,v16.4s,v6.4s - sub x3,x3,#64*4-16 // rewind - orr v2.16b,v0.16b,v0.16b - .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s - .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s - - add v17.4s,v17.4s,v7.4s - orr v2.16b,v0.16b,v0.16b - .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s - .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s - - add v0.4s,v0.4s,v18.4s - add v1.4s,v1.4s,v19.4s - - cbnz x2,.Loop_hw - - st1 {v0.4s,v1.4s},[x0] - - ldr x29,[sp],#16 - ret -.size sha256_block_armv8,.-sha256_block_armv8 -.comm OPENSSL_armcap_P,4,4 diff --git a/app/openssl/crypto/sha/asm/sha256-mips.S b/app/openssl/crypto/sha/asm/sha256-mips.S deleted file mode 100644 index 2bd728e9..00000000 --- a/app/openssl/crypto/sha/asm/sha256-mips.S +++ /dev/null @@ -1,1998 +0,0 @@ -#ifdef OPENSSL_FIPSCANISTER -# include <openssl/fipssyms.h> -#endif - -.text -.set noat -#if !defined(__vxworks) || defined(__pic__) -.option pic2 -#endif - -.align 5 -.globl sha256_block_data_order -.ent sha256_block_data_order -sha256_block_data_order: - .frame $29,128,$31 - .mask 3237937152,-4 - .set noreorder - .cpload $25 - sub $29,128 - sw $31,128-1*4($29) - sw $30,128-2*4($29) - sw $23,128-3*4($29) - sw $22,128-4*4($29) - sw $21,128-5*4($29) - sw $20,128-6*4($29) - sw $19,128-7*4($29) - sw $18,128-8*4($29) - sw $17,128-9*4($29) - sw $16,128-10*4($29) - sll $23,$6,6 - .set reorder - la $6,K256 # PIC-ified 'load address' - - lw $1,0*4($4) # load context - lw $2,1*4($4) - lw $3,2*4($4) - lw $7,3*4($4) - lw $24,4*4($4) - lw $25,5*4($4) - lw $30,6*4($4) - lw $31,7*4($4) - - add $23,$5 # pointer to the end of input - sw $23,16*4($29) - b .Loop - -.align 5 -.Loop: - lwl $8,3($5) - lwr $8,0($5) - lwl $9,7($5) - lwr $9,4($5) - srl $13,$8,24 # byte swap(0) - srl $14,$8,8 - andi $15,$8,0xFF00 - sll $8,$8,24 - andi $14,0xFF00 - sll $15,$15,8 - or $8,$13 - or $14,$15 - or $8,$14 - addu $12,$8,$31 # 0 - srl $31,$24,6 - xor $15,$25,$30 - sll $14,$24,7 - and $15,$24 - srl $13,$24,11 - xor $31,$14 - sll $14,$24,21 - xor $31,$13 - srl $13,$24,25 - xor $31,$14 - sll $14,$24,26 - xor $31,$13 - xor $15,$30 # Ch(e,f,g) - xor $13,$14,$31 # Sigma1(e) - - srl $31,$1,2 - addu $12,$15 - lw $15,0($6) # K[0] - sll $14,$1,10 - addu $12,$13 - srl $13,$1,13 - xor $31,$14 - sll $14,$1,19 - xor $31,$13 - srl $13,$1,22 - xor $31,$14 - sll $14,$1,30 - xor $31,$13 - sw $8,0($29) # offload to ring buffer - xor $31,$14 # Sigma0(a) - - or $13,$1,$2 - and $14,$1,$2 - and $13,$3 - or $14,$13 # Maj(a,b,c) - addu $12,$15 # +=K[0] - addu $31,$14 - - addu $7,$12 - addu $31,$12 - lwl $10,11($5) - lwr $10,8($5) - srl $14,$9,24 # byte swap(1) - srl $15,$9,8 - andi $16,$9,0xFF00 - sll $9,$9,24 - andi $15,0xFF00 - sll $16,$16,8 - or $9,$14 - or $15,$16 - or $9,$15 - addu $13,$9,$30 # 1 - srl $30,$7,6 - xor $16,$24,$25 - sll $15,$7,7 - and $16,$7 - srl $14,$7,11 - xor $30,$15 - sll $15,$7,21 - xor $30,$14 - srl $14,$7,25 - xor $30,$15 - sll $15,$7,26 - xor $30,$14 - xor $16,$25 # Ch(e,f,g) - xor $14,$15,$30 # Sigma1(e) - - srl $30,$31,2 - addu $13,$16 - lw $16,4($6) # K[1] - sll $15,$31,10 - addu $13,$14 - srl $14,$31,13 - xor $30,$15 - sll $15,$31,19 - xor $30,$14 - srl $14,$31,22 - xor $30,$15 - sll $15,$31,30 - xor $30,$14 - sw $9,4($29) # offload to ring buffer - xor $30,$15 # Sigma0(a) - - or $14,$31,$1 - and $15,$31,$1 - and $14,$2 - or $15,$14 # Maj(a,b,c) - addu $13,$16 # +=K[1] - addu $30,$15 - - addu $3,$13 - addu $30,$13 - lwl $11,15($5) - lwr $11,12($5) - srl $15,$10,24 # byte swap(2) - srl $16,$10,8 - andi $17,$10,0xFF00 - sll $10,$10,24 - andi $16,0xFF00 - sll $17,$17,8 - or $10,$15 - or $16,$17 - or $10,$16 - addu $14,$10,$25 # 2 - srl $25,$3,6 - xor $17,$7,$24 - sll $16,$3,7 - and $17,$3 - srl $15,$3,11 - xor $25,$16 - sll $16,$3,21 - xor $25,$15 - srl $15,$3,25 - xor $25,$16 - sll $16,$3,26 - xor $25,$15 - xor $17,$24 # Ch(e,f,g) - xor $15,$16,$25 # Sigma1(e) - - srl $25,$30,2 - addu $14,$17 - lw $17,8($6) # K[2] - sll $16,$30,10 - addu $14,$15 - srl $15,$30,13 - xor $25,$16 - sll $16,$30,19 - xor $25,$15 - srl $15,$30,22 - xor $25,$16 - sll $16,$30,30 - xor $25,$15 - sw $10,8($29) # offload to ring buffer - xor $25,$16 # Sigma0(a) - - or $15,$30,$31 - and $16,$30,$31 - and $15,$1 - or $16,$15 # Maj(a,b,c) - addu $14,$17 # +=K[2] - addu $25,$16 - - addu $2,$14 - addu $25,$14 - lwl $12,19($5) - lwr $12,16($5) - srl $16,$11,24 # byte swap(3) - srl $17,$11,8 - andi $18,$11,0xFF00 - sll $11,$11,24 - andi $17,0xFF00 - sll $18,$18,8 - or $11,$16 - or $17,$18 - or $11,$17 - addu $15,$11,$24 # 3 - srl $24,$2,6 - xor $18,$3,$7 - sll $17,$2,7 - and $18,$2 - srl $16,$2,11 - xor $24,$17 - sll $17,$2,21 - xor $24,$16 - srl $16,$2,25 - xor $24,$17 - sll $17,$2,26 - xor $24,$16 - xor $18,$7 # Ch(e,f,g) - xor $16,$17,$24 # Sigma1(e) - - srl $24,$25,2 - addu $15,$18 - lw $18,12($6) # K[3] - sll $17,$25,10 - addu $15,$16 - srl $16,$25,13 - xor $24,$17 - sll $17,$25,19 - xor $24,$16 - srl $16,$25,22 - xor $24,$17 - sll $17,$25,30 - xor $24,$16 - sw $11,12($29) # offload to ring buffer - xor $24,$17 # Sigma0(a) - - or $16,$25,$30 - and $17,$25,$30 - and $16,$31 - or $17,$16 # Maj(a,b,c) - addu $15,$18 # +=K[3] - addu $24,$17 - - addu $1,$15 - addu $24,$15 - lwl $13,23($5) - lwr $13,20($5) - srl $17,$12,24 # byte swap(4) - srl $18,$12,8 - andi $19,$12,0xFF00 - sll $12,$12,24 - andi $18,0xFF00 - sll $19,$19,8 - or $12,$17 - or $18,$19 - or $12,$18 - addu $16,$12,$7 # 4 - srl $7,$1,6 - xor $19,$2,$3 - sll $18,$1,7 - and $19,$1 - srl $17,$1,11 - xor $7,$18 - sll $18,$1,21 - xor $7,$17 - srl $17,$1,25 - xor $7,$18 - sll $18,$1,26 - xor $7,$17 - xor $19,$3 # Ch(e,f,g) - xor $17,$18,$7 # Sigma1(e) - - srl $7,$24,2 - addu $16,$19 - lw $19,16($6) # K[4] - sll $18,$24,10 - addu $16,$17 - srl $17,$24,13 - xor $7,$18 - sll $18,$24,19 - xor $7,$17 - srl $17,$24,22 - xor $7,$18 - sll $18,$24,30 - xor $7,$17 - sw $12,16($29) # offload to ring buffer - xor $7,$18 # Sigma0(a) - - or $17,$24,$25 - and $18,$24,$25 - and $17,$30 - or $18,$17 # Maj(a,b,c) - addu $16,$19 # +=K[4] - addu $7,$18 - - addu $31,$16 - addu $7,$16 - lwl $14,27($5) - lwr $14,24($5) - srl $18,$13,24 # byte swap(5) - srl $19,$13,8 - andi $20,$13,0xFF00 - sll $13,$13,24 - andi $19,0xFF00 - sll $20,$20,8 - or $13,$18 - or $19,$20 - or $13,$19 - addu $17,$13,$3 # 5 - srl $3,$31,6 - xor $20,$1,$2 - sll $19,$31,7 - and $20,$31 - srl $18,$31,11 - xor $3,$19 - sll $19,$31,21 - xor $3,$18 - srl $18,$31,25 - xor $3,$19 - sll $19,$31,26 - xor $3,$18 - xor $20,$2 # Ch(e,f,g) - xor $18,$19,$3 # Sigma1(e) - - srl $3,$7,2 - addu $17,$20 - lw $20,20($6) # K[5] - sll $19,$7,10 - addu $17,$18 - srl $18,$7,13 - xor $3,$19 - sll $19,$7,19 - xor $3,$18 - srl $18,$7,22 - xor $3,$19 - sll $19,$7,30 - xor $3,$18 - sw $13,20($29) # offload to ring buffer - xor $3,$19 # Sigma0(a) - - or $18,$7,$24 - and $19,$7,$24 - and $18,$25 - or $19,$18 # Maj(a,b,c) - addu $17,$20 # +=K[5] - addu $3,$19 - - addu $30,$17 - addu $3,$17 - lwl $15,31($5) - lwr $15,28($5) - srl $19,$14,24 # byte swap(6) - srl $20,$14,8 - andi $21,$14,0xFF00 - sll $14,$14,24 - andi $20,0xFF00 - sll $21,$21,8 - or $14,$19 - or $20,$21 - or $14,$20 - addu $18,$14,$2 # 6 - srl $2,$30,6 - xor $21,$31,$1 - sll $20,$30,7 - and $21,$30 - srl $19,$30,11 - xor $2,$20 - sll $20,$30,21 - xor $2,$19 - srl $19,$30,25 - xor $2,$20 - sll $20,$30,26 - xor $2,$19 - xor $21,$1 # Ch(e,f,g) - xor $19,$20,$2 # Sigma1(e) - - srl $2,$3,2 - addu $18,$21 - lw $21,24($6) # K[6] - sll $20,$3,10 - addu $18,$19 - srl $19,$3,13 - xor $2,$20 - sll $20,$3,19 - xor $2,$19 - srl $19,$3,22 - xor $2,$20 - sll $20,$3,30 - xor $2,$19 - sw $14,24($29) # offload to ring buffer - xor $2,$20 # Sigma0(a) - - or $19,$3,$7 - and $20,$3,$7 - and $19,$24 - or $20,$19 # Maj(a,b,c) - addu $18,$21 # +=K[6] - addu $2,$20 - - addu $25,$18 - addu $2,$18 - lwl $16,35($5) - lwr $16,32($5) - srl $20,$15,24 # byte swap(7) - srl $21,$15,8 - andi $22,$15,0xFF00 - sll $15,$15,24 - andi $21,0xFF00 - sll $22,$22,8 - or $15,$20 - or $21,$22 - or $15,$21 - addu $19,$15,$1 # 7 - srl $1,$25,6 - xor $22,$30,$31 - sll $21,$25,7 - and $22,$25 - srl $20,$25,11 - xor $1,$21 - sll $21,$25,21 - xor $1,$20 - srl $20,$25,25 - xor $1,$21 - sll $21,$25,26 - xor $1,$20 - xor $22,$31 # Ch(e,f,g) - xor $20,$21,$1 # Sigma1(e) - - srl $1,$2,2 - addu $19,$22 - lw $22,28($6) # K[7] - sll $21,$2,10 - addu $19,$20 - srl $20,$2,13 - xor $1,$21 - sll $21,$2,19 - xor $1,$20 - srl $20,$2,22 - xor $1,$21 - sll $21,$2,30 - xor $1,$20 - sw $15,28($29) # offload to ring buffer - xor $1,$21 # Sigma0(a) - - or $20,$2,$3 - and $21,$2,$3 - and $20,$7 - or $21,$20 # Maj(a,b,c) - addu $19,$22 # +=K[7] - addu $1,$21 - - addu $24,$19 - addu $1,$19 - lwl $17,39($5) - lwr $17,36($5) - srl $21,$16,24 # byte swap(8) - srl $22,$16,8 - andi $23,$16,0xFF00 - sll $16,$16,24 - andi $22,0xFF00 - sll $23,$23,8 - or $16,$21 - or $22,$23 - or $16,$22 - addu $20,$16,$31 # 8 - srl $31,$24,6 - xor $23,$25,$30 - sll $22,$24,7 - and $23,$24 - srl $21,$24,11 - xor $31,$22 - sll $22,$24,21 - xor $31,$21 - srl $21,$24,25 - xor $31,$22 - sll $22,$24,26 - xor $31,$21 - xor $23,$30 # Ch(e,f,g) - xor $21,$22,$31 # Sigma1(e) - - srl $31,$1,2 - addu $20,$23 - lw $23,32($6) # K[8] - sll $22,$1,10 - addu $20,$21 - srl $21,$1,13 - xor $31,$22 - sll $22,$1,19 - xor $31,$21 - srl $21,$1,22 - xor $31,$22 - sll $22,$1,30 - xor $31,$21 - sw $16,32($29) # offload to ring buffer - xor $31,$22 # Sigma0(a) - - or $21,$1,$2 - and $22,$1,$2 - and $21,$3 - or $22,$21 # Maj(a,b,c) - addu $20,$23 # +=K[8] - addu $31,$22 - - addu $7,$20 - addu $31,$20 - lwl $18,43($5) - lwr $18,40($5) - srl $22,$17,24 # byte swap(9) - srl $23,$17,8 - andi $8,$17,0xFF00 - sll $17,$17,24 - andi $23,0xFF00 - sll $8,$8,8 - or $17,$22 - or $23,$8 - or $17,$23 - addu $21,$17,$30 # 9 - srl $30,$7,6 - xor $8,$24,$25 - sll $23,$7,7 - and $8,$7 - srl $22,$7,11 - xor $30,$23 - sll $23,$7,21 - xor $30,$22 - srl $22,$7,25 - xor $30,$23 - sll $23,$7,26 - xor $30,$22 - xor $8,$25 # Ch(e,f,g) - xor $22,$23,$30 # Sigma1(e) - - srl $30,$31,2 - addu $21,$8 - lw $8,36($6) # K[9] - sll $23,$31,10 - addu $21,$22 - srl $22,$31,13 - xor $30,$23 - sll $23,$31,19 - xor $30,$22 - srl $22,$31,22 - xor $30,$23 - sll $23,$31,30 - xor $30,$22 - sw $17,36($29) # offload to ring buffer - xor $30,$23 # Sigma0(a) - - or $22,$31,$1 - and $23,$31,$1 - and $22,$2 - or $23,$22 # Maj(a,b,c) - addu $21,$8 # +=K[9] - addu $30,$23 - - addu $3,$21 - addu $30,$21 - lwl $19,47($5) - lwr $19,44($5) - srl $23,$18,24 # byte swap(10) - srl $8,$18,8 - andi $9,$18,0xFF00 - sll $18,$18,24 - andi $8,0xFF00 - sll $9,$9,8 - or $18,$23 - or $8,$9 - or $18,$8 - addu $22,$18,$25 # 10 - srl $25,$3,6 - xor $9,$7,$24 - sll $8,$3,7 - and $9,$3 - srl $23,$3,11 - xor $25,$8 - sll $8,$3,21 - xor $25,$23 - srl $23,$3,25 - xor $25,$8 - sll $8,$3,26 - xor $25,$23 - xor $9,$24 # Ch(e,f,g) - xor $23,$8,$25 # Sigma1(e) - - srl $25,$30,2 - addu $22,$9 - lw $9,40($6) # K[10] - sll $8,$30,10 - addu $22,$23 - srl $23,$30,13 - xor $25,$8 - sll $8,$30,19 - xor $25,$23 - srl $23,$30,22 - xor $25,$8 - sll $8,$30,30 - xor $25,$23 - sw $18,40($29) # offload to ring buffer - xor $25,$8 # Sigma0(a) - - or $23,$30,$31 - and $8,$30,$31 - and $23,$1 - or $8,$23 # Maj(a,b,c) - addu $22,$9 # +=K[10] - addu $25,$8 - - addu $2,$22 - addu $25,$22 - lwl $20,51($5) - lwr $20,48($5) - srl $8,$19,24 # byte swap(11) - srl $9,$19,8 - andi $10,$19,0xFF00 - sll $19,$19,24 - andi $9,0xFF00 - sll $10,$10,8 - or $19,$8 - or $9,$10 - or $19,$9 - addu $23,$19,$24 # 11 - srl $24,$2,6 - xor $10,$3,$7 - sll $9,$2,7 - and $10,$2 - srl $8,$2,11 - xor $24,$9 - sll $9,$2,21 - xor $24,$8 - srl $8,$2,25 - xor $24,$9 - sll $9,$2,26 - xor $24,$8 - xor $10,$7 # Ch(e,f,g) - xor $8,$9,$24 # Sigma1(e) - - srl $24,$25,2 - addu $23,$10 - lw $10,44($6) # K[11] - sll $9,$25,10 - addu $23,$8 - srl $8,$25,13 - xor $24,$9 - sll $9,$25,19 - xor $24,$8 - srl $8,$25,22 - xor $24,$9 - sll $9,$25,30 - xor $24,$8 - sw $19,44($29) # offload to ring buffer - xor $24,$9 # Sigma0(a) - - or $8,$25,$30 - and $9,$25,$30 - and $8,$31 - or $9,$8 # Maj(a,b,c) - addu $23,$10 # +=K[11] - addu $24,$9 - - addu $1,$23 - addu $24,$23 - lwl $21,55($5) - lwr $21,52($5) - srl $9,$20,24 # byte swap(12) - srl $10,$20,8 - andi $11,$20,0xFF00 - sll $20,$20,24 - andi $10,0xFF00 - sll $11,$11,8 - or $20,$9 - or $10,$11 - or $20,$10 - addu $8,$20,$7 # 12 - srl $7,$1,6 - xor $11,$2,$3 - sll $10,$1,7 - and $11,$1 - srl $9,$1,11 - xor $7,$10 - sll $10,$1,21 - xor $7,$9 - srl $9,$1,25 - xor $7,$10 - sll $10,$1,26 - xor $7,$9 - xor $11,$3 # Ch(e,f,g) - xor $9,$10,$7 # Sigma1(e) - - srl $7,$24,2 - addu $8,$11 - lw $11,48($6) # K[12] - sll $10,$24,10 - addu $8,$9 - srl $9,$24,13 - xor $7,$10 - sll $10,$24,19 - xor $7,$9 - srl $9,$24,22 - xor $7,$10 - sll $10,$24,30 - xor $7,$9 - sw $20,48($29) # offload to ring buffer - xor $7,$10 # Sigma0(a) - - or $9,$24,$25 - and $10,$24,$25 - and $9,$30 - or $10,$9 # Maj(a,b,c) - addu $8,$11 # +=K[12] - addu $7,$10 - - addu $31,$8 - addu $7,$8 - lwl $22,59($5) - lwr $22,56($5) - srl $10,$21,24 # byte swap(13) - srl $11,$21,8 - andi $12,$21,0xFF00 - sll $21,$21,24 - andi $11,0xFF00 - sll $12,$12,8 - or $21,$10 - or $11,$12 - or $21,$11 - addu $9,$21,$3 # 13 - srl $3,$31,6 - xor $12,$1,$2 - sll $11,$31,7 - and $12,$31 - srl $10,$31,11 - xor $3,$11 - sll $11,$31,21 - xor $3,$10 - srl $10,$31,25 - xor $3,$11 - sll $11,$31,26 - xor $3,$10 - xor $12,$2 # Ch(e,f,g) - xor $10,$11,$3 # Sigma1(e) - - srl $3,$7,2 - addu $9,$12 - lw $12,52($6) # K[13] - sll $11,$7,10 - addu $9,$10 - srl $10,$7,13 - xor $3,$11 - sll $11,$7,19 - xor $3,$10 - srl $10,$7,22 - xor $3,$11 - sll $11,$7,30 - xor $3,$10 - sw $21,52($29) # offload to ring buffer - xor $3,$11 # Sigma0(a) - - or $10,$7,$24 - and $11,$7,$24 - and $10,$25 - or $11,$10 # Maj(a,b,c) - addu $9,$12 # +=K[13] - addu $3,$11 - - addu $30,$9 - addu $3,$9 - lw $8,0($29) # prefetch from ring buffer - lwl $23,63($5) - lwr $23,60($5) - srl $11,$22,24 # byte swap(14) - srl $12,$22,8 - andi $13,$22,0xFF00 - sll $22,$22,24 - andi $12,0xFF00 - sll $13,$13,8 - or $22,$11 - or $12,$13 - or $22,$12 - addu $10,$22,$2 # 14 - srl $2,$30,6 - xor $13,$31,$1 - sll $12,$30,7 - and $13,$30 - srl $11,$30,11 - xor $2,$12 - sll $12,$30,21 - xor $2,$11 - srl $11,$30,25 - xor $2,$12 - sll $12,$30,26 - xor $2,$11 - xor $13,$1 # Ch(e,f,g) - xor $11,$12,$2 # Sigma1(e) - - srl $2,$3,2 - addu $10,$13 - lw $13,56($6) # K[14] - sll $12,$3,10 - addu $10,$11 - srl $11,$3,13 - xor $2,$12 - sll $12,$3,19 - xor $2,$11 - srl $11,$3,22 - xor $2,$12 - sll $12,$3,30 - xor $2,$11 - sw $22,56($29) # offload to ring buffer - xor $2,$12 # Sigma0(a) - - or $11,$3,$7 - and $12,$3,$7 - and $11,$24 - or $12,$11 # Maj(a,b,c) - addu $10,$13 # +=K[14] - addu $2,$12 - - addu $25,$10 - addu $2,$10 - lw $9,4($29) # prefetch from ring buffer - srl $12,$23,24 # byte swap(15) - srl $13,$23,8 - andi $14,$23,0xFF00 - sll $23,$23,24 - andi $13,0xFF00 - sll $14,$14,8 - or $23,$12 - or $13,$14 - or $23,$13 - addu $11,$23,$1 # 15 - srl $1,$25,6 - xor $14,$30,$31 - sll $13,$25,7 - and $14,$25 - srl $12,$25,11 - xor $1,$13 - sll $13,$25,21 - xor $1,$12 - srl $12,$25,25 - xor $1,$13 - sll $13,$25,26 - xor $1,$12 - xor $14,$31 # Ch(e,f,g) - xor $12,$13,$1 # Sigma1(e) - - srl $1,$2,2 - addu $11,$14 - lw $14,60($6) # K[15] - sll $13,$2,10 - addu $11,$12 - srl $12,$2,13 - xor $1,$13 - sll $13,$2,19 - xor $1,$12 - srl $12,$2,22 - xor $1,$13 - sll $13,$2,30 - xor $1,$12 - sw $23,60($29) # offload to ring buffer - xor $1,$13 # Sigma0(a) - - or $12,$2,$3 - and $13,$2,$3 - and $12,$7 - or $13,$12 # Maj(a,b,c) - addu $11,$14 # +=K[15] - addu $1,$13 - - addu $24,$11 - addu $1,$11 - lw $10,8($29) # prefetch from ring buffer - b .L16_xx -.align 4 -.L16_xx: - srl $14,$9,3 # Xupdate(16) - addu $8,$17 # +=X[i+9] - sll $13,$9,14 - srl $12,$9,7 - xor $14,$13 - sll $13,11 - xor $14,$12 - srl $12,$9,18 - xor $14,$13 - - srl $15,$22,10 - xor $14,$12 # sigma0(X[i+1]) - sll $13,$22,13 - addu $8,$14 - srl $12,$22,17 - xor $15,$13 - sll $13,2 - xor $15,$12 - srl $12,$22,19 - xor $15,$13 - - xor $15,$12 # sigma1(X[i+14]) - addu $8,$15 - addu $12,$8,$31 # 16 - srl $31,$24,6 - xor $15,$25,$30 - sll $14,$24,7 - and $15,$24 - srl $13,$24,11 - xor $31,$14 - sll $14,$24,21 - xor $31,$13 - srl $13,$24,25 - xor $31,$14 - sll $14,$24,26 - xor $31,$13 - xor $15,$30 # Ch(e,f,g) - xor $13,$14,$31 # Sigma1(e) - - srl $31,$1,2 - addu $12,$15 - lw $15,64($6) # K[16] - sll $14,$1,10 - addu $12,$13 - srl $13,$1,13 - xor $31,$14 - sll $14,$1,19 - xor $31,$13 - srl $13,$1,22 - xor $31,$14 - sll $14,$1,30 - xor $31,$13 - sw $8,0($29) # offload to ring buffer - xor $31,$14 # Sigma0(a) - - or $13,$1,$2 - and $14,$1,$2 - and $13,$3 - or $14,$13 # Maj(a,b,c) - addu $12,$15 # +=K[16] - addu $31,$14 - - addu $7,$12 - addu $31,$12 - lw $11,12($29) # prefetch from ring buffer - srl $15,$10,3 # Xupdate(17) - addu $9,$18 # +=X[i+9] - sll $14,$10,14 - srl $13,$10,7 - xor $15,$14 - sll $14,11 - xor $15,$13 - srl $13,$10,18 - xor $15,$14 - - srl $16,$23,10 - xor $15,$13 # sigma0(X[i+1]) - sll $14,$23,13 - addu $9,$15 - srl $13,$23,17 - xor $16,$14 - sll $14,2 - xor $16,$13 - srl $13,$23,19 - xor $16,$14 - - xor $16,$13 # sigma1(X[i+14]) - addu $9,$16 - addu $13,$9,$30 # 17 - srl $30,$7,6 - xor $16,$24,$25 - sll $15,$7,7 - and $16,$7 - srl $14,$7,11 - xor $30,$15 - sll $15,$7,21 - xor $30,$14 - srl $14,$7,25 - xor $30,$15 - sll $15,$7,26 - xor $30,$14 - xor $16,$25 # Ch(e,f,g) - xor $14,$15,$30 # Sigma1(e) - - srl $30,$31,2 - addu $13,$16 - lw $16,68($6) # K[17] - sll $15,$31,10 - addu $13,$14 - srl $14,$31,13 - xor $30,$15 - sll $15,$31,19 - xor $30,$14 - srl $14,$31,22 - xor $30,$15 - sll $15,$31,30 - xor $30,$14 - sw $9,4($29) # offload to ring buffer - xor $30,$15 # Sigma0(a) - - or $14,$31,$1 - and $15,$31,$1 - and $14,$2 - or $15,$14 # Maj(a,b,c) - addu $13,$16 # +=K[17] - addu $30,$15 - - addu $3,$13 - addu $30,$13 - lw $12,16($29) # prefetch from ring buffer - srl $16,$11,3 # Xupdate(18) - addu $10,$19 # +=X[i+9] - sll $15,$11,14 - srl $14,$11,7 - xor $16,$15 - sll $15,11 - xor $16,$14 - srl $14,$11,18 - xor $16,$15 - - srl $17,$8,10 - xor $16,$14 # sigma0(X[i+1]) - sll $15,$8,13 - addu $10,$16 - srl $14,$8,17 - xor $17,$15 - sll $15,2 - xor $17,$14 - srl $14,$8,19 - xor $17,$15 - - xor $17,$14 # sigma1(X[i+14]) - addu $10,$17 - addu $14,$10,$25 # 18 - srl $25,$3,6 - xor $17,$7,$24 - sll $16,$3,7 - and $17,$3 - srl $15,$3,11 - xor $25,$16 - sll $16,$3,21 - xor $25,$15 - srl $15,$3,25 - xor $25,$16 - sll $16,$3,26 - xor $25,$15 - xor $17,$24 # Ch(e,f,g) - xor $15,$16,$25 # Sigma1(e) - - srl $25,$30,2 - addu $14,$17 - lw $17,72($6) # K[18] - sll $16,$30,10 - addu $14,$15 - srl $15,$30,13 - xor $25,$16 - sll $16,$30,19 - xor $25,$15 - srl $15,$30,22 - xor $25,$16 - sll $16,$30,30 - xor $25,$15 - sw $10,8($29) # offload to ring buffer - xor $25,$16 # Sigma0(a) - - or $15,$30,$31 - and $16,$30,$31 - and $15,$1 - or $16,$15 # Maj(a,b,c) - addu $14,$17 # +=K[18] - addu $25,$16 - - addu $2,$14 - addu $25,$14 - lw $13,20($29) # prefetch from ring buffer - srl $17,$12,3 # Xupdate(19) - addu $11,$20 # +=X[i+9] - sll $16,$12,14 - srl $15,$12,7 - xor $17,$16 - sll $16,11 - xor $17,$15 - srl $15,$12,18 - xor $17,$16 - - srl $18,$9,10 - xor $17,$15 # sigma0(X[i+1]) - sll $16,$9,13 - addu $11,$17 - srl $15,$9,17 - xor $18,$16 - sll $16,2 - xor $18,$15 - srl $15,$9,19 - xor $18,$16 - - xor $18,$15 # sigma1(X[i+14]) - addu $11,$18 - addu $15,$11,$24 # 19 - srl $24,$2,6 - xor $18,$3,$7 - sll $17,$2,7 - and $18,$2 - srl $16,$2,11 - xor $24,$17 - sll $17,$2,21 - xor $24,$16 - srl $16,$2,25 - xor $24,$17 - sll $17,$2,26 - xor $24,$16 - xor $18,$7 # Ch(e,f,g) - xor $16,$17,$24 # Sigma1(e) - - srl $24,$25,2 - addu $15,$18 - lw $18,76($6) # K[19] - sll $17,$25,10 - addu $15,$16 - srl $16,$25,13 - xor $24,$17 - sll $17,$25,19 - xor $24,$16 - srl $16,$25,22 - xor $24,$17 - sll $17,$25,30 - xor $24,$16 - sw $11,12($29) # offload to ring buffer - xor $24,$17 # Sigma0(a) - - or $16,$25,$30 - and $17,$25,$30 - and $16,$31 - or $17,$16 # Maj(a,b,c) - addu $15,$18 # +=K[19] - addu $24,$17 - - addu $1,$15 - addu $24,$15 - lw $14,24($29) # prefetch from ring buffer - srl $18,$13,3 # Xupdate(20) - addu $12,$21 # +=X[i+9] - sll $17,$13,14 - srl $16,$13,7 - xor $18,$17 - sll $17,11 - xor $18,$16 - srl $16,$13,18 - xor $18,$17 - - srl $19,$10,10 - xor $18,$16 # sigma0(X[i+1]) - sll $17,$10,13 - addu $12,$18 - srl $16,$10,17 - xor $19,$17 - sll $17,2 - xor $19,$16 - srl $16,$10,19 - xor $19,$17 - - xor $19,$16 # sigma1(X[i+14]) - addu $12,$19 - addu $16,$12,$7 # 20 - srl $7,$1,6 - xor $19,$2,$3 - sll $18,$1,7 - and $19,$1 - srl $17,$1,11 - xor $7,$18 - sll $18,$1,21 - xor $7,$17 - srl $17,$1,25 - xor $7,$18 - sll $18,$1,26 - xor $7,$17 - xor $19,$3 # Ch(e,f,g) - xor $17,$18,$7 # Sigma1(e) - - srl $7,$24,2 - addu $16,$19 - lw $19,80($6) # K[20] - sll $18,$24,10 - addu $16,$17 - srl $17,$24,13 - xor $7,$18 - sll $18,$24,19 - xor $7,$17 - srl $17,$24,22 - xor $7,$18 - sll $18,$24,30 - xor $7,$17 - sw $12,16($29) # offload to ring buffer - xor $7,$18 # Sigma0(a) - - or $17,$24,$25 - and $18,$24,$25 - and $17,$30 - or $18,$17 # Maj(a,b,c) - addu $16,$19 # +=K[20] - addu $7,$18 - - addu $31,$16 - addu $7,$16 - lw $15,28($29) # prefetch from ring buffer - srl $19,$14,3 # Xupdate(21) - addu $13,$22 # +=X[i+9] - sll $18,$14,14 - srl $17,$14,7 - xor $19,$18 - sll $18,11 - xor $19,$17 - srl $17,$14,18 - xor $19,$18 - - srl $20,$11,10 - xor $19,$17 # sigma0(X[i+1]) - sll $18,$11,13 - addu $13,$19 - srl $17,$11,17 - xor $20,$18 - sll $18,2 - xor $20,$17 - srl $17,$11,19 - xor $20,$18 - - xor $20,$17 # sigma1(X[i+14]) - addu $13,$20 - addu $17,$13,$3 # 21 - srl $3,$31,6 - xor $20,$1,$2 - sll $19,$31,7 - and $20,$31 - srl $18,$31,11 - xor $3,$19 - sll $19,$31,21 - xor $3,$18 - srl $18,$31,25 - xor $3,$19 - sll $19,$31,26 - xor $3,$18 - xor $20,$2 # Ch(e,f,g) - xor $18,$19,$3 # Sigma1(e) - - srl $3,$7,2 - addu $17,$20 - lw $20,84($6) # K[21] - sll $19,$7,10 - addu $17,$18 - srl $18,$7,13 - xor $3,$19 - sll $19,$7,19 - xor $3,$18 - srl $18,$7,22 - xor $3,$19 - sll $19,$7,30 - xor $3,$18 - sw $13,20($29) # offload to ring buffer - xor $3,$19 # Sigma0(a) - - or $18,$7,$24 - and $19,$7,$24 - and $18,$25 - or $19,$18 # Maj(a,b,c) - addu $17,$20 # +=K[21] - addu $3,$19 - - addu $30,$17 - addu $3,$17 - lw $16,32($29) # prefetch from ring buffer - srl $20,$15,3 # Xupdate(22) - addu $14,$23 # +=X[i+9] - sll $19,$15,14 - srl $18,$15,7 - xor $20,$19 - sll $19,11 - xor $20,$18 - srl $18,$15,18 - xor $20,$19 - - srl $21,$12,10 - xor $20,$18 # sigma0(X[i+1]) - sll $19,$12,13 - addu $14,$20 - srl $18,$12,17 - xor $21,$19 - sll $19,2 - xor $21,$18 - srl $18,$12,19 - xor $21,$19 - - xor $21,$18 # sigma1(X[i+14]) - addu $14,$21 - addu $18,$14,$2 # 22 - srl $2,$30,6 - xor $21,$31,$1 - sll $20,$30,7 - and $21,$30 - srl $19,$30,11 - xor $2,$20 - sll $20,$30,21 - xor $2,$19 - srl $19,$30,25 - xor $2,$20 - sll $20,$30,26 - xor $2,$19 - xor $21,$1 # Ch(e,f,g) - xor $19,$20,$2 # Sigma1(e) - - srl $2,$3,2 - addu $18,$21 - lw $21,88($6) # K[22] - sll $20,$3,10 - addu $18,$19 - srl $19,$3,13 - xor $2,$20 - sll $20,$3,19 - xor $2,$19 - srl $19,$3,22 - xor $2,$20 - sll $20,$3,30 - xor $2,$19 - sw $14,24($29) # offload to ring buffer - xor $2,$20 # Sigma0(a) - - or $19,$3,$7 - and $20,$3,$7 - and $19,$24 - or $20,$19 # Maj(a,b,c) - addu $18,$21 # +=K[22] - addu $2,$20 - - addu $25,$18 - addu $2,$18 - lw $17,36($29) # prefetch from ring buffer - srl $21,$16,3 # Xupdate(23) - addu $15,$8 # +=X[i+9] - sll $20,$16,14 - srl $19,$16,7 - xor $21,$20 - sll $20,11 - xor $21,$19 - srl $19,$16,18 - xor $21,$20 - - srl $22,$13,10 - xor $21,$19 # sigma0(X[i+1]) - sll $20,$13,13 - addu $15,$21 - srl $19,$13,17 - xor $22,$20 - sll $20,2 - xor $22,$19 - srl $19,$13,19 - xor $22,$20 - - xor $22,$19 # sigma1(X[i+14]) - addu $15,$22 - addu $19,$15,$1 # 23 - srl $1,$25,6 - xor $22,$30,$31 - sll $21,$25,7 - and $22,$25 - srl $20,$25,11 - xor $1,$21 - sll $21,$25,21 - xor $1,$20 - srl $20,$25,25 - xor $1,$21 - sll $21,$25,26 - xor $1,$20 - xor $22,$31 # Ch(e,f,g) - xor $20,$21,$1 # Sigma1(e) - - srl $1,$2,2 - addu $19,$22 - lw $22,92($6) # K[23] - sll $21,$2,10 - addu $19,$20 - srl $20,$2,13 - xor $1,$21 - sll $21,$2,19 - xor $1,$20 - srl $20,$2,22 - xor $1,$21 - sll $21,$2,30 - xor $1,$20 - sw $15,28($29) # offload to ring buffer - xor $1,$21 # Sigma0(a) - - or $20,$2,$3 - and $21,$2,$3 - and $20,$7 - or $21,$20 # Maj(a,b,c) - addu $19,$22 # +=K[23] - addu $1,$21 - - addu $24,$19 - addu $1,$19 - lw $18,40($29) # prefetch from ring buffer - srl $22,$17,3 # Xupdate(24) - addu $16,$9 # +=X[i+9] - sll $21,$17,14 - srl $20,$17,7 - xor $22,$21 - sll $21,11 - xor $22,$20 - srl $20,$17,18 - xor $22,$21 - - srl $23,$14,10 - xor $22,$20 # sigma0(X[i+1]) - sll $21,$14,13 - addu $16,$22 - srl $20,$14,17 - xor $23,$21 - sll $21,2 - xor $23,$20 - srl $20,$14,19 - xor $23,$21 - - xor $23,$20 # sigma1(X[i+14]) - addu $16,$23 - addu $20,$16,$31 # 24 - srl $31,$24,6 - xor $23,$25,$30 - sll $22,$24,7 - and $23,$24 - srl $21,$24,11 - xor $31,$22 - sll $22,$24,21 - xor $31,$21 - srl $21,$24,25 - xor $31,$22 - sll $22,$24,26 - xor $31,$21 - xor $23,$30 # Ch(e,f,g) - xor $21,$22,$31 # Sigma1(e) - - srl $31,$1,2 - addu $20,$23 - lw $23,96($6) # K[24] - sll $22,$1,10 - addu $20,$21 - srl $21,$1,13 - xor $31,$22 - sll $22,$1,19 - xor $31,$21 - srl $21,$1,22 - xor $31,$22 - sll $22,$1,30 - xor $31,$21 - sw $16,32($29) # offload to ring buffer - xor $31,$22 # Sigma0(a) - - or $21,$1,$2 - and $22,$1,$2 - and $21,$3 - or $22,$21 # Maj(a,b,c) - addu $20,$23 # +=K[24] - addu $31,$22 - - addu $7,$20 - addu $31,$20 - lw $19,44($29) # prefetch from ring buffer - srl $23,$18,3 # Xupdate(25) - addu $17,$10 # +=X[i+9] - sll $22,$18,14 - srl $21,$18,7 - xor $23,$22 - sll $22,11 - xor $23,$21 - srl $21,$18,18 - xor $23,$22 - - srl $8,$15,10 - xor $23,$21 # sigma0(X[i+1]) - sll $22,$15,13 - addu $17,$23 - srl $21,$15,17 - xor $8,$22 - sll $22,2 - xor $8,$21 - srl $21,$15,19 - xor $8,$22 - - xor $8,$21 # sigma1(X[i+14]) - addu $17,$8 - addu $21,$17,$30 # 25 - srl $30,$7,6 - xor $8,$24,$25 - sll $23,$7,7 - and $8,$7 - srl $22,$7,11 - xor $30,$23 - sll $23,$7,21 - xor $30,$22 - srl $22,$7,25 - xor $30,$23 - sll $23,$7,26 - xor $30,$22 - xor $8,$25 # Ch(e,f,g) - xor $22,$23,$30 # Sigma1(e) - - srl $30,$31,2 - addu $21,$8 - lw $8,100($6) # K[25] - sll $23,$31,10 - addu $21,$22 - srl $22,$31,13 - xor $30,$23 - sll $23,$31,19 - xor $30,$22 - srl $22,$31,22 - xor $30,$23 - sll $23,$31,30 - xor $30,$22 - sw $17,36($29) # offload to ring buffer - xor $30,$23 # Sigma0(a) - - or $22,$31,$1 - and $23,$31,$1 - and $22,$2 - or $23,$22 # Maj(a,b,c) - addu $21,$8 # +=K[25] - addu $30,$23 - - addu $3,$21 - addu $30,$21 - lw $20,48($29) # prefetch from ring buffer - srl $8,$19,3 # Xupdate(26) - addu $18,$11 # +=X[i+9] - sll $23,$19,14 - srl $22,$19,7 - xor $8,$23 - sll $23,11 - xor $8,$22 - srl $22,$19,18 - xor $8,$23 - - srl $9,$16,10 - xor $8,$22 # sigma0(X[i+1]) - sll $23,$16,13 - addu $18,$8 - srl $22,$16,17 - xor $9,$23 - sll $23,2 - xor $9,$22 - srl $22,$16,19 - xor $9,$23 - - xor $9,$22 # sigma1(X[i+14]) - addu $18,$9 - addu $22,$18,$25 # 26 - srl $25,$3,6 - xor $9,$7,$24 - sll $8,$3,7 - and $9,$3 - srl $23,$3,11 - xor $25,$8 - sll $8,$3,21 - xor $25,$23 - srl $23,$3,25 - xor $25,$8 - sll $8,$3,26 - xor $25,$23 - xor $9,$24 # Ch(e,f,g) - xor $23,$8,$25 # Sigma1(e) - - srl $25,$30,2 - addu $22,$9 - lw $9,104($6) # K[26] - sll $8,$30,10 - addu $22,$23 - srl $23,$30,13 - xor $25,$8 - sll $8,$30,19 - xor $25,$23 - srl $23,$30,22 - xor $25,$8 - sll $8,$30,30 - xor $25,$23 - sw $18,40($29) # offload to ring buffer - xor $25,$8 # Sigma0(a) - - or $23,$30,$31 - and $8,$30,$31 - and $23,$1 - or $8,$23 # Maj(a,b,c) - addu $22,$9 # +=K[26] - addu $25,$8 - - addu $2,$22 - addu $25,$22 - lw $21,52($29) # prefetch from ring buffer - srl $9,$20,3 # Xupdate(27) - addu $19,$12 # +=X[i+9] - sll $8,$20,14 - srl $23,$20,7 - xor $9,$8 - sll $8,11 - xor $9,$23 - srl $23,$20,18 - xor $9,$8 - - srl $10,$17,10 - xor $9,$23 # sigma0(X[i+1]) - sll $8,$17,13 - addu $19,$9 - srl $23,$17,17 - xor $10,$8 - sll $8,2 - xor $10,$23 - srl $23,$17,19 - xor $10,$8 - - xor $10,$23 # sigma1(X[i+14]) - addu $19,$10 - addu $23,$19,$24 # 27 - srl $24,$2,6 - xor $10,$3,$7 - sll $9,$2,7 - and $10,$2 - srl $8,$2,11 - xor $24,$9 - sll $9,$2,21 - xor $24,$8 - srl $8,$2,25 - xor $24,$9 - sll $9,$2,26 - xor $24,$8 - xor $10,$7 # Ch(e,f,g) - xor $8,$9,$24 # Sigma1(e) - - srl $24,$25,2 - addu $23,$10 - lw $10,108($6) # K[27] - sll $9,$25,10 - addu $23,$8 - srl $8,$25,13 - xor $24,$9 - sll $9,$25,19 - xor $24,$8 - srl $8,$25,22 - xor $24,$9 - sll $9,$25,30 - xor $24,$8 - sw $19,44($29) # offload to ring buffer - xor $24,$9 # Sigma0(a) - - or $8,$25,$30 - and $9,$25,$30 - and $8,$31 - or $9,$8 # Maj(a,b,c) - addu $23,$10 # +=K[27] - addu $24,$9 - - addu $1,$23 - addu $24,$23 - lw $22,56($29) # prefetch from ring buffer - srl $10,$21,3 # Xupdate(28) - addu $20,$13 # +=X[i+9] - sll $9,$21,14 - srl $8,$21,7 - xor $10,$9 - sll $9,11 - xor $10,$8 - srl $8,$21,18 - xor $10,$9 - - srl $11,$18,10 - xor $10,$8 # sigma0(X[i+1]) - sll $9,$18,13 - addu $20,$10 - srl $8,$18,17 - xor $11,$9 - sll $9,2 - xor $11,$8 - srl $8,$18,19 - xor $11,$9 - - xor $11,$8 # sigma1(X[i+14]) - addu $20,$11 - addu $8,$20,$7 # 28 - srl $7,$1,6 - xor $11,$2,$3 - sll $10,$1,7 - and $11,$1 - srl $9,$1,11 - xor $7,$10 - sll $10,$1,21 - xor $7,$9 - srl $9,$1,25 - xor $7,$10 - sll $10,$1,26 - xor $7,$9 - xor $11,$3 # Ch(e,f,g) - xor $9,$10,$7 # Sigma1(e) - - srl $7,$24,2 - addu $8,$11 - lw $11,112($6) # K[28] - sll $10,$24,10 - addu $8,$9 - srl $9,$24,13 - xor $7,$10 - sll $10,$24,19 - xor $7,$9 - srl $9,$24,22 - xor $7,$10 - sll $10,$24,30 - xor $7,$9 - sw $20,48($29) # offload to ring buffer - xor $7,$10 # Sigma0(a) - - or $9,$24,$25 - and $10,$24,$25 - and $9,$30 - or $10,$9 # Maj(a,b,c) - addu $8,$11 # +=K[28] - addu $7,$10 - - addu $31,$8 - addu $7,$8 - lw $23,60($29) # prefetch from ring buffer - srl $11,$22,3 # Xupdate(29) - addu $21,$14 # +=X[i+9] - sll $10,$22,14 - srl $9,$22,7 - xor $11,$10 - sll $10,11 - xor $11,$9 - srl $9,$22,18 - xor $11,$10 - - srl $12,$19,10 - xor $11,$9 # sigma0(X[i+1]) - sll $10,$19,13 - addu $21,$11 - srl $9,$19,17 - xor $12,$10 - sll $10,2 - xor $12,$9 - srl $9,$19,19 - xor $12,$10 - - xor $12,$9 # sigma1(X[i+14]) - addu $21,$12 - addu $9,$21,$3 # 29 - srl $3,$31,6 - xor $12,$1,$2 - sll $11,$31,7 - and $12,$31 - srl $10,$31,11 - xor $3,$11 - sll $11,$31,21 - xor $3,$10 - srl $10,$31,25 - xor $3,$11 - sll $11,$31,26 - xor $3,$10 - xor $12,$2 # Ch(e,f,g) - xor $10,$11,$3 # Sigma1(e) - - srl $3,$7,2 - addu $9,$12 - lw $12,116($6) # K[29] - sll $11,$7,10 - addu $9,$10 - srl $10,$7,13 - xor $3,$11 - sll $11,$7,19 - xor $3,$10 - srl $10,$7,22 - xor $3,$11 - sll $11,$7,30 - xor $3,$10 - sw $21,52($29) # offload to ring buffer - xor $3,$11 # Sigma0(a) - - or $10,$7,$24 - and $11,$7,$24 - and $10,$25 - or $11,$10 # Maj(a,b,c) - addu $9,$12 # +=K[29] - addu $3,$11 - - addu $30,$9 - addu $3,$9 - lw $8,0($29) # prefetch from ring buffer - srl $12,$23,3 # Xupdate(30) - addu $22,$15 # +=X[i+9] - sll $11,$23,14 - srl $10,$23,7 - xor $12,$11 - sll $11,11 - xor $12,$10 - srl $10,$23,18 - xor $12,$11 - - srl $13,$20,10 - xor $12,$10 # sigma0(X[i+1]) - sll $11,$20,13 - addu $22,$12 - srl $10,$20,17 - xor $13,$11 - sll $11,2 - xor $13,$10 - srl $10,$20,19 - xor $13,$11 - - xor $13,$10 # sigma1(X[i+14]) - addu $22,$13 - addu $10,$22,$2 # 30 - srl $2,$30,6 - xor $13,$31,$1 - sll $12,$30,7 - and $13,$30 - srl $11,$30,11 - xor $2,$12 - sll $12,$30,21 - xor $2,$11 - srl $11,$30,25 - xor $2,$12 - sll $12,$30,26 - xor $2,$11 - xor $13,$1 # Ch(e,f,g) - xor $11,$12,$2 # Sigma1(e) - - srl $2,$3,2 - addu $10,$13 - lw $13,120($6) # K[30] - sll $12,$3,10 - addu $10,$11 - srl $11,$3,13 - xor $2,$12 - sll $12,$3,19 - xor $2,$11 - srl $11,$3,22 - xor $2,$12 - sll $12,$3,30 - xor $2,$11 - sw $22,56($29) # offload to ring buffer - xor $2,$12 # Sigma0(a) - - or $11,$3,$7 - and $12,$3,$7 - and $11,$24 - or $12,$11 # Maj(a,b,c) - addu $10,$13 # +=K[30] - addu $2,$12 - - addu $25,$10 - addu $2,$10 - lw $9,4($29) # prefetch from ring buffer - srl $13,$8,3 # Xupdate(31) - addu $23,$16 # +=X[i+9] - sll $12,$8,14 - srl $11,$8,7 - xor $13,$12 - sll $12,11 - xor $13,$11 - srl $11,$8,18 - xor $13,$12 - - srl $14,$21,10 - xor $13,$11 # sigma0(X[i+1]) - sll $12,$21,13 - addu $23,$13 - srl $11,$21,17 - xor $14,$12 - sll $12,2 - xor $14,$11 - srl $11,$21,19 - xor $14,$12 - - xor $14,$11 # sigma1(X[i+14]) - addu $23,$14 - addu $11,$23,$1 # 31 - srl $1,$25,6 - xor $14,$30,$31 - sll $13,$25,7 - and $14,$25 - srl $12,$25,11 - xor $1,$13 - sll $13,$25,21 - xor $1,$12 - srl $12,$25,25 - xor $1,$13 - sll $13,$25,26 - xor $1,$12 - xor $14,$31 # Ch(e,f,g) - xor $12,$13,$1 # Sigma1(e) - - srl $1,$2,2 - addu $11,$14 - lw $14,124($6) # K[31] - sll $13,$2,10 - addu $11,$12 - srl $12,$2,13 - xor $1,$13 - sll $13,$2,19 - xor $1,$12 - srl $12,$2,22 - xor $1,$13 - sll $13,$2,30 - xor $1,$12 - sw $23,60($29) # offload to ring buffer - xor $1,$13 # Sigma0(a) - - or $12,$2,$3 - and $13,$2,$3 - and $12,$7 - or $13,$12 # Maj(a,b,c) - addu $11,$14 # +=K[31] - addu $1,$13 - - addu $24,$11 - addu $1,$11 - lw $10,8($29) # prefetch from ring buffer - and $14,0xfff - li $15,2290 - .set noreorder - bne $14,$15,.L16_xx - add $6,16*4 # Ktbl+=16 - - lw $23,16*4($29) # restore pointer to the end of input - lw $8,0*4($4) - lw $9,1*4($4) - lw $10,2*4($4) - add $5,16*4 - lw $11,3*4($4) - addu $1,$8 - lw $12,4*4($4) - addu $2,$9 - lw $13,5*4($4) - addu $3,$10 - lw $14,6*4($4) - addu $7,$11 - lw $15,7*4($4) - addu $24,$12 - sw $1,0*4($4) - addu $25,$13 - sw $2,1*4($4) - addu $30,$14 - sw $3,2*4($4) - addu $31,$15 - sw $7,3*4($4) - sw $24,4*4($4) - sw $25,5*4($4) - sw $30,6*4($4) - sw $31,7*4($4) - - bne $5,$23,.Loop - sub $6,192 # rewind $6 - - lw $31,128-1*4($29) - lw $30,128-2*4($29) - lw $23,128-3*4($29) - lw $22,128-4*4($29) - lw $21,128-5*4($29) - lw $20,128-6*4($29) - lw $19,128-7*4($29) - lw $18,128-8*4($29) - lw $17,128-9*4($29) - lw $16,128-10*4($29) - jr $31 - add $29,128 -.end sha256_block_data_order - -.rdata -.align 5 -K256: - .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5 - .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5 - .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3 - .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174 - .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc - .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da - .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7 - .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967 - .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13 - .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85 - .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3 - .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070 - .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5 - .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3 - .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208 - .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 -.asciiz "SHA256 for MIPS, CRYPTOGAMS by <appro@openssl.org>" -.align 5 - diff --git a/app/openssl/crypto/sha/asm/sha256-x86_64.S b/app/openssl/crypto/sha/asm/sha256-x86_64.S deleted file mode 100644 index db5b898f..00000000 --- a/app/openssl/crypto/sha/asm/sha256-x86_64.S +++ /dev/null @@ -1,1778 +0,0 @@ -.text - -.globl sha256_block_data_order -.type sha256_block_data_order,@function -.align 16 -sha256_block_data_order: - pushq %rbx - pushq %rbp - pushq %r12 - pushq %r13 - pushq %r14 - pushq %r15 - movq %rsp,%r11 - shlq $4,%rdx - subq $64+32,%rsp - leaq (%rsi,%rdx,4),%rdx - andq $-64,%rsp - movq %rdi,64+0(%rsp) - movq %rsi,64+8(%rsp) - movq %rdx,64+16(%rsp) - movq %r11,64+24(%rsp) -.Lprologue: - - leaq K256(%rip),%rbp - - movl 0(%rdi),%eax - movl 4(%rdi),%ebx - movl 8(%rdi),%ecx - movl 12(%rdi),%edx - movl 16(%rdi),%r8d - movl 20(%rdi),%r9d - movl 24(%rdi),%r10d - movl 28(%rdi),%r11d - jmp .Lloop - -.align 16 -.Lloop: - xorq %rdi,%rdi - movl 0(%rsi),%r12d - movl %r8d,%r13d - movl %eax,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r9d,%r15d - movl %r12d,0(%rsp) - - rorl $9,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - rorl $5,%r13d - addl %r11d,%r12d - xorl %eax,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r8d,%r15d - movl %ebx,%r11d - - rorl $11,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - xorl %ecx,%r11d - xorl %eax,%r14d - addl %r15d,%r12d - movl %ebx,%r15d - - rorl $6,%r13d - andl %eax,%r11d - andl %ecx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r11d - - addl %r12d,%edx - addl %r12d,%r11d - leaq 1(%rdi),%rdi - addl %r14d,%r11d - - movl 4(%rsi),%r12d - movl %edx,%r13d - movl %r11d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r8d,%r15d - movl %r12d,4(%rsp) - - rorl $9,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - rorl $5,%r13d - addl %r10d,%r12d - xorl %r11d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %edx,%r15d - movl %eax,%r10d - - rorl $11,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - xorl %ebx,%r10d - xorl %r11d,%r14d - addl %r15d,%r12d - movl %eax,%r15d - - rorl $6,%r13d - andl %r11d,%r10d - andl %ebx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r10d - - addl %r12d,%ecx - addl %r12d,%r10d - leaq 1(%rdi),%rdi - addl %r14d,%r10d - - movl 8(%rsi),%r12d - movl %ecx,%r13d - movl %r10d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %edx,%r15d - movl %r12d,8(%rsp) - - rorl $9,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - rorl $5,%r13d - addl %r9d,%r12d - xorl %r10d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ecx,%r15d - movl %r11d,%r9d - - rorl $11,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - xorl %eax,%r9d - xorl %r10d,%r14d - addl %r15d,%r12d - movl %r11d,%r15d - - rorl $6,%r13d - andl %r10d,%r9d - andl %eax,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r9d - - addl %r12d,%ebx - addl %r12d,%r9d - leaq 1(%rdi),%rdi - addl %r14d,%r9d - - movl 12(%rsi),%r12d - movl %ebx,%r13d - movl %r9d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %ecx,%r15d - movl %r12d,12(%rsp) - - rorl $9,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - rorl $5,%r13d - addl %r8d,%r12d - xorl %r9d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ebx,%r15d - movl %r10d,%r8d - - rorl $11,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - xorl %r11d,%r8d - xorl %r9d,%r14d - addl %r15d,%r12d - movl %r10d,%r15d - - rorl $6,%r13d - andl %r9d,%r8d - andl %r11d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r8d - - addl %r12d,%eax - addl %r12d,%r8d - leaq 1(%rdi),%rdi - addl %r14d,%r8d - - movl 16(%rsi),%r12d - movl %eax,%r13d - movl %r8d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %ebx,%r15d - movl %r12d,16(%rsp) - - rorl $9,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - rorl $5,%r13d - addl %edx,%r12d - xorl %r8d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %eax,%r15d - movl %r9d,%edx - - rorl $11,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - xorl %r10d,%edx - xorl %r8d,%r14d - addl %r15d,%r12d - movl %r9d,%r15d - - rorl $6,%r13d - andl %r8d,%edx - andl %r10d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%edx - - addl %r12d,%r11d - addl %r12d,%edx - leaq 1(%rdi),%rdi - addl %r14d,%edx - - movl 20(%rsi),%r12d - movl %r11d,%r13d - movl %edx,%r14d - bswapl %r12d - rorl $14,%r13d - movl %eax,%r15d - movl %r12d,20(%rsp) - - rorl $9,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - rorl $5,%r13d - addl %ecx,%r12d - xorl %edx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r11d,%r15d - movl %r8d,%ecx - - rorl $11,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - xorl %r9d,%ecx - xorl %edx,%r14d - addl %r15d,%r12d - movl %r8d,%r15d - - rorl $6,%r13d - andl %edx,%ecx - andl %r9d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ecx - - addl %r12d,%r10d - addl %r12d,%ecx - leaq 1(%rdi),%rdi - addl %r14d,%ecx - - movl 24(%rsi),%r12d - movl %r10d,%r13d - movl %ecx,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r11d,%r15d - movl %r12d,24(%rsp) - - rorl $9,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - rorl $5,%r13d - addl %ebx,%r12d - xorl %ecx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r10d,%r15d - movl %edx,%ebx - - rorl $11,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - xorl %r8d,%ebx - xorl %ecx,%r14d - addl %r15d,%r12d - movl %edx,%r15d - - rorl $6,%r13d - andl %ecx,%ebx - andl %r8d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ebx - - addl %r12d,%r9d - addl %r12d,%ebx - leaq 1(%rdi),%rdi - addl %r14d,%ebx - - movl 28(%rsi),%r12d - movl %r9d,%r13d - movl %ebx,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r10d,%r15d - movl %r12d,28(%rsp) - - rorl $9,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - rorl $5,%r13d - addl %eax,%r12d - xorl %ebx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r9d,%r15d - movl %ecx,%eax - - rorl $11,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - xorl %edx,%eax - xorl %ebx,%r14d - addl %r15d,%r12d - movl %ecx,%r15d - - rorl $6,%r13d - andl %ebx,%eax - andl %edx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%eax - - addl %r12d,%r8d - addl %r12d,%eax - leaq 1(%rdi),%rdi - addl %r14d,%eax - - movl 32(%rsi),%r12d - movl %r8d,%r13d - movl %eax,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r9d,%r15d - movl %r12d,32(%rsp) - - rorl $9,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - rorl $5,%r13d - addl %r11d,%r12d - xorl %eax,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r8d,%r15d - movl %ebx,%r11d - - rorl $11,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - xorl %ecx,%r11d - xorl %eax,%r14d - addl %r15d,%r12d - movl %ebx,%r15d - - rorl $6,%r13d - andl %eax,%r11d - andl %ecx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r11d - - addl %r12d,%edx - addl %r12d,%r11d - leaq 1(%rdi),%rdi - addl %r14d,%r11d - - movl 36(%rsi),%r12d - movl %edx,%r13d - movl %r11d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r8d,%r15d - movl %r12d,36(%rsp) - - rorl $9,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - rorl $5,%r13d - addl %r10d,%r12d - xorl %r11d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %edx,%r15d - movl %eax,%r10d - - rorl $11,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - xorl %ebx,%r10d - xorl %r11d,%r14d - addl %r15d,%r12d - movl %eax,%r15d - - rorl $6,%r13d - andl %r11d,%r10d - andl %ebx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r10d - - addl %r12d,%ecx - addl %r12d,%r10d - leaq 1(%rdi),%rdi - addl %r14d,%r10d - - movl 40(%rsi),%r12d - movl %ecx,%r13d - movl %r10d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %edx,%r15d - movl %r12d,40(%rsp) - - rorl $9,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - rorl $5,%r13d - addl %r9d,%r12d - xorl %r10d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ecx,%r15d - movl %r11d,%r9d - - rorl $11,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - xorl %eax,%r9d - xorl %r10d,%r14d - addl %r15d,%r12d - movl %r11d,%r15d - - rorl $6,%r13d - andl %r10d,%r9d - andl %eax,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r9d - - addl %r12d,%ebx - addl %r12d,%r9d - leaq 1(%rdi),%rdi - addl %r14d,%r9d - - movl 44(%rsi),%r12d - movl %ebx,%r13d - movl %r9d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %ecx,%r15d - movl %r12d,44(%rsp) - - rorl $9,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - rorl $5,%r13d - addl %r8d,%r12d - xorl %r9d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ebx,%r15d - movl %r10d,%r8d - - rorl $11,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - xorl %r11d,%r8d - xorl %r9d,%r14d - addl %r15d,%r12d - movl %r10d,%r15d - - rorl $6,%r13d - andl %r9d,%r8d - andl %r11d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r8d - - addl %r12d,%eax - addl %r12d,%r8d - leaq 1(%rdi),%rdi - addl %r14d,%r8d - - movl 48(%rsi),%r12d - movl %eax,%r13d - movl %r8d,%r14d - bswapl %r12d - rorl $14,%r13d - movl %ebx,%r15d - movl %r12d,48(%rsp) - - rorl $9,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - rorl $5,%r13d - addl %edx,%r12d - xorl %r8d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %eax,%r15d - movl %r9d,%edx - - rorl $11,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - xorl %r10d,%edx - xorl %r8d,%r14d - addl %r15d,%r12d - movl %r9d,%r15d - - rorl $6,%r13d - andl %r8d,%edx - andl %r10d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%edx - - addl %r12d,%r11d - addl %r12d,%edx - leaq 1(%rdi),%rdi - addl %r14d,%edx - - movl 52(%rsi),%r12d - movl %r11d,%r13d - movl %edx,%r14d - bswapl %r12d - rorl $14,%r13d - movl %eax,%r15d - movl %r12d,52(%rsp) - - rorl $9,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - rorl $5,%r13d - addl %ecx,%r12d - xorl %edx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r11d,%r15d - movl %r8d,%ecx - - rorl $11,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - xorl %r9d,%ecx - xorl %edx,%r14d - addl %r15d,%r12d - movl %r8d,%r15d - - rorl $6,%r13d - andl %edx,%ecx - andl %r9d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ecx - - addl %r12d,%r10d - addl %r12d,%ecx - leaq 1(%rdi),%rdi - addl %r14d,%ecx - - movl 56(%rsi),%r12d - movl %r10d,%r13d - movl %ecx,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r11d,%r15d - movl %r12d,56(%rsp) - - rorl $9,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - rorl $5,%r13d - addl %ebx,%r12d - xorl %ecx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r10d,%r15d - movl %edx,%ebx - - rorl $11,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - xorl %r8d,%ebx - xorl %ecx,%r14d - addl %r15d,%r12d - movl %edx,%r15d - - rorl $6,%r13d - andl %ecx,%ebx - andl %r8d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ebx - - addl %r12d,%r9d - addl %r12d,%ebx - leaq 1(%rdi),%rdi - addl %r14d,%ebx - - movl 60(%rsi),%r12d - movl %r9d,%r13d - movl %ebx,%r14d - bswapl %r12d - rorl $14,%r13d - movl %r10d,%r15d - movl %r12d,60(%rsp) - - rorl $9,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - rorl $5,%r13d - addl %eax,%r12d - xorl %ebx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r9d,%r15d - movl %ecx,%eax - - rorl $11,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - xorl %edx,%eax - xorl %ebx,%r14d - addl %r15d,%r12d - movl %ecx,%r15d - - rorl $6,%r13d - andl %ebx,%eax - andl %edx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%eax - - addl %r12d,%r8d - addl %r12d,%eax - leaq 1(%rdi),%rdi - addl %r14d,%eax - - jmp .Lrounds_16_xx -.align 16 -.Lrounds_16_xx: - movl 4(%rsp),%r13d - movl 56(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 36(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 0(%rsp),%r12d - movl %r8d,%r13d - addl %r14d,%r12d - movl %eax,%r14d - rorl $14,%r13d - movl %r9d,%r15d - movl %r12d,0(%rsp) - - rorl $9,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - rorl $5,%r13d - addl %r11d,%r12d - xorl %eax,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r8d,%r15d - movl %ebx,%r11d - - rorl $11,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - xorl %ecx,%r11d - xorl %eax,%r14d - addl %r15d,%r12d - movl %ebx,%r15d - - rorl $6,%r13d - andl %eax,%r11d - andl %ecx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r11d - - addl %r12d,%edx - addl %r12d,%r11d - leaq 1(%rdi),%rdi - addl %r14d,%r11d - - movl 8(%rsp),%r13d - movl 60(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 40(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 4(%rsp),%r12d - movl %edx,%r13d - addl %r14d,%r12d - movl %r11d,%r14d - rorl $14,%r13d - movl %r8d,%r15d - movl %r12d,4(%rsp) - - rorl $9,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - rorl $5,%r13d - addl %r10d,%r12d - xorl %r11d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %edx,%r15d - movl %eax,%r10d - - rorl $11,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - xorl %ebx,%r10d - xorl %r11d,%r14d - addl %r15d,%r12d - movl %eax,%r15d - - rorl $6,%r13d - andl %r11d,%r10d - andl %ebx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r10d - - addl %r12d,%ecx - addl %r12d,%r10d - leaq 1(%rdi),%rdi - addl %r14d,%r10d - - movl 12(%rsp),%r13d - movl 0(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 44(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 8(%rsp),%r12d - movl %ecx,%r13d - addl %r14d,%r12d - movl %r10d,%r14d - rorl $14,%r13d - movl %edx,%r15d - movl %r12d,8(%rsp) - - rorl $9,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - rorl $5,%r13d - addl %r9d,%r12d - xorl %r10d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ecx,%r15d - movl %r11d,%r9d - - rorl $11,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - xorl %eax,%r9d - xorl %r10d,%r14d - addl %r15d,%r12d - movl %r11d,%r15d - - rorl $6,%r13d - andl %r10d,%r9d - andl %eax,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r9d - - addl %r12d,%ebx - addl %r12d,%r9d - leaq 1(%rdi),%rdi - addl %r14d,%r9d - - movl 16(%rsp),%r13d - movl 4(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 48(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 12(%rsp),%r12d - movl %ebx,%r13d - addl %r14d,%r12d - movl %r9d,%r14d - rorl $14,%r13d - movl %ecx,%r15d - movl %r12d,12(%rsp) - - rorl $9,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - rorl $5,%r13d - addl %r8d,%r12d - xorl %r9d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ebx,%r15d - movl %r10d,%r8d - - rorl $11,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - xorl %r11d,%r8d - xorl %r9d,%r14d - addl %r15d,%r12d - movl %r10d,%r15d - - rorl $6,%r13d - andl %r9d,%r8d - andl %r11d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r8d - - addl %r12d,%eax - addl %r12d,%r8d - leaq 1(%rdi),%rdi - addl %r14d,%r8d - - movl 20(%rsp),%r13d - movl 8(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 52(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 16(%rsp),%r12d - movl %eax,%r13d - addl %r14d,%r12d - movl %r8d,%r14d - rorl $14,%r13d - movl %ebx,%r15d - movl %r12d,16(%rsp) - - rorl $9,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - rorl $5,%r13d - addl %edx,%r12d - xorl %r8d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %eax,%r15d - movl %r9d,%edx - - rorl $11,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - xorl %r10d,%edx - xorl %r8d,%r14d - addl %r15d,%r12d - movl %r9d,%r15d - - rorl $6,%r13d - andl %r8d,%edx - andl %r10d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%edx - - addl %r12d,%r11d - addl %r12d,%edx - leaq 1(%rdi),%rdi - addl %r14d,%edx - - movl 24(%rsp),%r13d - movl 12(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 56(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 20(%rsp),%r12d - movl %r11d,%r13d - addl %r14d,%r12d - movl %edx,%r14d - rorl $14,%r13d - movl %eax,%r15d - movl %r12d,20(%rsp) - - rorl $9,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - rorl $5,%r13d - addl %ecx,%r12d - xorl %edx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r11d,%r15d - movl %r8d,%ecx - - rorl $11,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - xorl %r9d,%ecx - xorl %edx,%r14d - addl %r15d,%r12d - movl %r8d,%r15d - - rorl $6,%r13d - andl %edx,%ecx - andl %r9d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ecx - - addl %r12d,%r10d - addl %r12d,%ecx - leaq 1(%rdi),%rdi - addl %r14d,%ecx - - movl 28(%rsp),%r13d - movl 16(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 60(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 24(%rsp),%r12d - movl %r10d,%r13d - addl %r14d,%r12d - movl %ecx,%r14d - rorl $14,%r13d - movl %r11d,%r15d - movl %r12d,24(%rsp) - - rorl $9,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - rorl $5,%r13d - addl %ebx,%r12d - xorl %ecx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r10d,%r15d - movl %edx,%ebx - - rorl $11,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - xorl %r8d,%ebx - xorl %ecx,%r14d - addl %r15d,%r12d - movl %edx,%r15d - - rorl $6,%r13d - andl %ecx,%ebx - andl %r8d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ebx - - addl %r12d,%r9d - addl %r12d,%ebx - leaq 1(%rdi),%rdi - addl %r14d,%ebx - - movl 32(%rsp),%r13d - movl 20(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 0(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 28(%rsp),%r12d - movl %r9d,%r13d - addl %r14d,%r12d - movl %ebx,%r14d - rorl $14,%r13d - movl %r10d,%r15d - movl %r12d,28(%rsp) - - rorl $9,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - rorl $5,%r13d - addl %eax,%r12d - xorl %ebx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r9d,%r15d - movl %ecx,%eax - - rorl $11,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - xorl %edx,%eax - xorl %ebx,%r14d - addl %r15d,%r12d - movl %ecx,%r15d - - rorl $6,%r13d - andl %ebx,%eax - andl %edx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%eax - - addl %r12d,%r8d - addl %r12d,%eax - leaq 1(%rdi),%rdi - addl %r14d,%eax - - movl 36(%rsp),%r13d - movl 24(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 4(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 32(%rsp),%r12d - movl %r8d,%r13d - addl %r14d,%r12d - movl %eax,%r14d - rorl $14,%r13d - movl %r9d,%r15d - movl %r12d,32(%rsp) - - rorl $9,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - rorl $5,%r13d - addl %r11d,%r12d - xorl %eax,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r8d,%r15d - movl %ebx,%r11d - - rorl $11,%r14d - xorl %r8d,%r13d - xorl %r10d,%r15d - - xorl %ecx,%r11d - xorl %eax,%r14d - addl %r15d,%r12d - movl %ebx,%r15d - - rorl $6,%r13d - andl %eax,%r11d - andl %ecx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r11d - - addl %r12d,%edx - addl %r12d,%r11d - leaq 1(%rdi),%rdi - addl %r14d,%r11d - - movl 40(%rsp),%r13d - movl 28(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 8(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 36(%rsp),%r12d - movl %edx,%r13d - addl %r14d,%r12d - movl %r11d,%r14d - rorl $14,%r13d - movl %r8d,%r15d - movl %r12d,36(%rsp) - - rorl $9,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - rorl $5,%r13d - addl %r10d,%r12d - xorl %r11d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %edx,%r15d - movl %eax,%r10d - - rorl $11,%r14d - xorl %edx,%r13d - xorl %r9d,%r15d - - xorl %ebx,%r10d - xorl %r11d,%r14d - addl %r15d,%r12d - movl %eax,%r15d - - rorl $6,%r13d - andl %r11d,%r10d - andl %ebx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r10d - - addl %r12d,%ecx - addl %r12d,%r10d - leaq 1(%rdi),%rdi - addl %r14d,%r10d - - movl 44(%rsp),%r13d - movl 32(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 12(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 40(%rsp),%r12d - movl %ecx,%r13d - addl %r14d,%r12d - movl %r10d,%r14d - rorl $14,%r13d - movl %edx,%r15d - movl %r12d,40(%rsp) - - rorl $9,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - rorl $5,%r13d - addl %r9d,%r12d - xorl %r10d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ecx,%r15d - movl %r11d,%r9d - - rorl $11,%r14d - xorl %ecx,%r13d - xorl %r8d,%r15d - - xorl %eax,%r9d - xorl %r10d,%r14d - addl %r15d,%r12d - movl %r11d,%r15d - - rorl $6,%r13d - andl %r10d,%r9d - andl %eax,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r9d - - addl %r12d,%ebx - addl %r12d,%r9d - leaq 1(%rdi),%rdi - addl %r14d,%r9d - - movl 48(%rsp),%r13d - movl 36(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 16(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 44(%rsp),%r12d - movl %ebx,%r13d - addl %r14d,%r12d - movl %r9d,%r14d - rorl $14,%r13d - movl %ecx,%r15d - movl %r12d,44(%rsp) - - rorl $9,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - rorl $5,%r13d - addl %r8d,%r12d - xorl %r9d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %ebx,%r15d - movl %r10d,%r8d - - rorl $11,%r14d - xorl %ebx,%r13d - xorl %edx,%r15d - - xorl %r11d,%r8d - xorl %r9d,%r14d - addl %r15d,%r12d - movl %r10d,%r15d - - rorl $6,%r13d - andl %r9d,%r8d - andl %r11d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%r8d - - addl %r12d,%eax - addl %r12d,%r8d - leaq 1(%rdi),%rdi - addl %r14d,%r8d - - movl 52(%rsp),%r13d - movl 40(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 20(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 48(%rsp),%r12d - movl %eax,%r13d - addl %r14d,%r12d - movl %r8d,%r14d - rorl $14,%r13d - movl %ebx,%r15d - movl %r12d,48(%rsp) - - rorl $9,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - rorl $5,%r13d - addl %edx,%r12d - xorl %r8d,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %eax,%r15d - movl %r9d,%edx - - rorl $11,%r14d - xorl %eax,%r13d - xorl %ecx,%r15d - - xorl %r10d,%edx - xorl %r8d,%r14d - addl %r15d,%r12d - movl %r9d,%r15d - - rorl $6,%r13d - andl %r8d,%edx - andl %r10d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%edx - - addl %r12d,%r11d - addl %r12d,%edx - leaq 1(%rdi),%rdi - addl %r14d,%edx - - movl 56(%rsp),%r13d - movl 44(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 24(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 52(%rsp),%r12d - movl %r11d,%r13d - addl %r14d,%r12d - movl %edx,%r14d - rorl $14,%r13d - movl %eax,%r15d - movl %r12d,52(%rsp) - - rorl $9,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - rorl $5,%r13d - addl %ecx,%r12d - xorl %edx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r11d,%r15d - movl %r8d,%ecx - - rorl $11,%r14d - xorl %r11d,%r13d - xorl %ebx,%r15d - - xorl %r9d,%ecx - xorl %edx,%r14d - addl %r15d,%r12d - movl %r8d,%r15d - - rorl $6,%r13d - andl %edx,%ecx - andl %r9d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ecx - - addl %r12d,%r10d - addl %r12d,%ecx - leaq 1(%rdi),%rdi - addl %r14d,%ecx - - movl 60(%rsp),%r13d - movl 48(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 28(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 56(%rsp),%r12d - movl %r10d,%r13d - addl %r14d,%r12d - movl %ecx,%r14d - rorl $14,%r13d - movl %r11d,%r15d - movl %r12d,56(%rsp) - - rorl $9,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - rorl $5,%r13d - addl %ebx,%r12d - xorl %ecx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r10d,%r15d - movl %edx,%ebx - - rorl $11,%r14d - xorl %r10d,%r13d - xorl %eax,%r15d - - xorl %r8d,%ebx - xorl %ecx,%r14d - addl %r15d,%r12d - movl %edx,%r15d - - rorl $6,%r13d - andl %ecx,%ebx - andl %r8d,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%ebx - - addl %r12d,%r9d - addl %r12d,%ebx - leaq 1(%rdi),%rdi - addl %r14d,%ebx - - movl 0(%rsp),%r13d - movl 52(%rsp),%r14d - movl %r13d,%r12d - movl %r14d,%r15d - - rorl $11,%r12d - xorl %r13d,%r12d - shrl $3,%r13d - - rorl $7,%r12d - xorl %r12d,%r13d - movl 32(%rsp),%r12d - - rorl $2,%r15d - xorl %r14d,%r15d - shrl $10,%r14d - - rorl $17,%r15d - addl %r13d,%r12d - xorl %r15d,%r14d - - addl 60(%rsp),%r12d - movl %r9d,%r13d - addl %r14d,%r12d - movl %ebx,%r14d - rorl $14,%r13d - movl %r10d,%r15d - movl %r12d,60(%rsp) - - rorl $9,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - rorl $5,%r13d - addl %eax,%r12d - xorl %ebx,%r14d - - addl (%rbp,%rdi,4),%r12d - andl %r9d,%r15d - movl %ecx,%eax - - rorl $11,%r14d - xorl %r9d,%r13d - xorl %r11d,%r15d - - xorl %edx,%eax - xorl %ebx,%r14d - addl %r15d,%r12d - movl %ecx,%r15d - - rorl $6,%r13d - andl %ebx,%eax - andl %edx,%r15d - - rorl $2,%r14d - addl %r13d,%r12d - addl %r15d,%eax - - addl %r12d,%r8d - addl %r12d,%eax - leaq 1(%rdi),%rdi - addl %r14d,%eax - - cmpq $64,%rdi - jb .Lrounds_16_xx - - movq 64+0(%rsp),%rdi - leaq 64(%rsi),%rsi - - addl 0(%rdi),%eax - addl 4(%rdi),%ebx - addl 8(%rdi),%ecx - addl 12(%rdi),%edx - addl 16(%rdi),%r8d - addl 20(%rdi),%r9d - addl 24(%rdi),%r10d - addl 28(%rdi),%r11d - - cmpq 64+16(%rsp),%rsi - - movl %eax,0(%rdi) - movl %ebx,4(%rdi) - movl %ecx,8(%rdi) - movl %edx,12(%rdi) - movl %r8d,16(%rdi) - movl %r9d,20(%rdi) - movl %r10d,24(%rdi) - movl %r11d,28(%rdi) - jb .Lloop - - movq 64+24(%rsp),%rsi - movq (%rsi),%r15 - movq 8(%rsi),%r14 - movq 16(%rsi),%r13 - movq 24(%rsi),%r12 - movq 32(%rsi),%rbp - movq 40(%rsi),%rbx - leaq 48(%rsi),%rsp -.Lepilogue: - .byte 0xf3,0xc3 -.size sha256_block_data_order,.-sha256_block_data_order -.align 64 -.type K256,@object -K256: -.long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 -.long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 -.long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 -.long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 -.long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc -.long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da -.long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 -.long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 -.long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 -.long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 -.long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 -.long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 -.long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 -.long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 -.long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 -.long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 diff --git a/app/openssl/crypto/sha/asm/sha512-586.S b/app/openssl/crypto/sha/asm/sha512-586.S deleted file mode 100644 index 82c76c41..00000000 --- a/app/openssl/crypto/sha/asm/sha512-586.S +++ /dev/null @@ -1,836 +0,0 @@ -.file "sha512-586.s" -.text -.globl sha512_block_data_order -.type sha512_block_data_order,@function -.align 16 -sha512_block_data_order: -.L_sha512_block_data_order_begin: - pushl %ebp - pushl %ebx - pushl %esi - pushl %edi - movl 20(%esp),%esi - movl 24(%esp),%edi - movl 28(%esp),%eax - movl %esp,%ebx - call .L000pic_point -.L000pic_point: - popl %ebp - leal .L001K512-.L000pic_point(%ebp),%ebp - subl $16,%esp - andl $-64,%esp - shll $7,%eax - addl %edi,%eax - movl %esi,(%esp) - movl %edi,4(%esp) - movl %eax,8(%esp) - movl %ebx,12(%esp) - leal _GLOBAL_OFFSET_TABLE_+[.-.L001K512](%ebp),%edx - movl OPENSSL_ia32cap_P@GOT(%edx),%edx - btl $26,(%edx) - jnc .L002loop_x86 - movq (%esi),%mm0 - movq 8(%esi),%mm1 - movq 16(%esi),%mm2 - movq 24(%esi),%mm3 - movq 32(%esi),%mm4 - movq 40(%esi),%mm5 - movq 48(%esi),%mm6 - movq 56(%esi),%mm7 - subl $80,%esp -.align 16 -.L003loop_sse2: - movq %mm1,8(%esp) - movq %mm2,16(%esp) - movq %mm3,24(%esp) - movq %mm5,40(%esp) - movq %mm6,48(%esp) - movq %mm7,56(%esp) - movl (%edi),%ecx - movl 4(%edi),%edx - addl $8,%edi - bswap %ecx - bswap %edx - movl %ecx,76(%esp) - movl %edx,72(%esp) -.align 16 -.L00400_14_sse2: - movl (%edi),%eax - movl 4(%edi),%ebx - addl $8,%edi - bswap %eax - bswap %ebx - movl %eax,68(%esp) - movl %ebx,64(%esp) - movq 40(%esp),%mm5 - movq 48(%esp),%mm6 - movq 56(%esp),%mm7 - movq %mm4,%mm1 - movq %mm4,%mm2 - psrlq $14,%mm1 - movq %mm4,32(%esp) - psllq $23,%mm2 - movq %mm1,%mm3 - psrlq $4,%mm1 - pxor %mm2,%mm3 - psllq $23,%mm2 - pxor %mm1,%mm3 - psrlq $23,%mm1 - pxor %mm2,%mm3 - psllq $4,%mm2 - pxor %mm1,%mm3 - paddq (%ebp),%mm7 - pxor %mm2,%mm3 - pxor %mm6,%mm5 - movq 8(%esp),%mm1 - pand %mm4,%mm5 - movq 16(%esp),%mm2 - pxor %mm6,%mm5 - movq 24(%esp),%mm4 - paddq %mm5,%mm3 - movq %mm0,(%esp) - paddq %mm7,%mm3 - movq %mm0,%mm5 - movq %mm0,%mm6 - paddq 72(%esp),%mm3 - psrlq $28,%mm5 - paddq %mm3,%mm4 - psllq $25,%mm6 - movq %mm5,%mm7 - psrlq $6,%mm5 - pxor %mm6,%mm7 - psllq $5,%mm6 - pxor %mm5,%mm7 - psrlq $5,%mm5 - pxor %mm6,%mm7 - psllq $6,%mm6 - pxor %mm5,%mm7 - subl $8,%esp - pxor %mm6,%mm7 - movq %mm0,%mm5 - por %mm2,%mm0 - pand %mm2,%mm5 - pand %mm1,%mm0 - por %mm0,%mm5 - paddq %mm5,%mm7 - movq %mm3,%mm0 - movb (%ebp),%dl - paddq %mm7,%mm0 - addl $8,%ebp - cmpb $53,%dl - jne .L00400_14_sse2 - movq 40(%esp),%mm5 - movq 48(%esp),%mm6 - movq 56(%esp),%mm7 - movq %mm4,%mm1 - movq %mm4,%mm2 - psrlq $14,%mm1 - movq %mm4,32(%esp) - psllq $23,%mm2 - movq %mm1,%mm3 - psrlq $4,%mm1 - pxor %mm2,%mm3 - psllq $23,%mm2 - pxor %mm1,%mm3 - psrlq $23,%mm1 - pxor %mm2,%mm3 - psllq $4,%mm2 - pxor %mm1,%mm3 - paddq (%ebp),%mm7 - pxor %mm2,%mm3 - pxor %mm6,%mm5 - movq 8(%esp),%mm1 - pand %mm4,%mm5 - movq 16(%esp),%mm2 - pxor %mm6,%mm5 - movq 24(%esp),%mm4 - paddq %mm5,%mm3 - movq %mm0,(%esp) - paddq %mm7,%mm3 - movq %mm0,%mm5 - movq %mm0,%mm6 - paddq 72(%esp),%mm3 - psrlq $28,%mm5 - paddq %mm3,%mm4 - psllq $25,%mm6 - movq %mm5,%mm7 - psrlq $6,%mm5 - pxor %mm6,%mm7 - psllq $5,%mm6 - pxor %mm5,%mm7 - psrlq $5,%mm5 - pxor %mm6,%mm7 - psllq $6,%mm6 - pxor %mm5,%mm7 - subl $8,%esp - pxor %mm6,%mm7 - movq %mm0,%mm5 - por %mm2,%mm0 - movq 88(%esp),%mm6 - pand %mm2,%mm5 - pand %mm1,%mm0 - movq 192(%esp),%mm2 - por %mm0,%mm5 - paddq %mm5,%mm7 - movq %mm3,%mm0 - movb (%ebp),%dl - paddq %mm7,%mm0 - addl $8,%ebp -.align 16 -.L00516_79_sse2: - movq %mm2,%mm1 - psrlq $1,%mm2 - movq %mm6,%mm7 - psrlq $6,%mm6 - movq %mm2,%mm3 - psrlq $6,%mm2 - movq %mm6,%mm5 - psrlq $13,%mm6 - pxor %mm2,%mm3 - psrlq $1,%mm2 - pxor %mm6,%mm5 - psrlq $42,%mm6 - pxor %mm2,%mm3 - movq 200(%esp),%mm2 - psllq $56,%mm1 - pxor %mm6,%mm5 - psllq $3,%mm7 - pxor %mm1,%mm3 - paddq 128(%esp),%mm2 - psllq $7,%mm1 - pxor %mm7,%mm5 - psllq $42,%mm7 - pxor %mm1,%mm3 - pxor %mm7,%mm5 - paddq %mm5,%mm3 - paddq %mm2,%mm3 - movq %mm3,72(%esp) - movq 40(%esp),%mm5 - movq 48(%esp),%mm6 - movq 56(%esp),%mm7 - movq %mm4,%mm1 - movq %mm4,%mm2 - psrlq $14,%mm1 - movq %mm4,32(%esp) - psllq $23,%mm2 - movq %mm1,%mm3 - psrlq $4,%mm1 - pxor %mm2,%mm3 - psllq $23,%mm2 - pxor %mm1,%mm3 - psrlq $23,%mm1 - pxor %mm2,%mm3 - psllq $4,%mm2 - pxor %mm1,%mm3 - paddq (%ebp),%mm7 - pxor %mm2,%mm3 - pxor %mm6,%mm5 - movq 8(%esp),%mm1 - pand %mm4,%mm5 - movq 16(%esp),%mm2 - pxor %mm6,%mm5 - movq 24(%esp),%mm4 - paddq %mm5,%mm3 - movq %mm0,(%esp) - paddq %mm7,%mm3 - movq %mm0,%mm5 - movq %mm0,%mm6 - paddq 72(%esp),%mm3 - psrlq $28,%mm5 - paddq %mm3,%mm4 - psllq $25,%mm6 - movq %mm5,%mm7 - psrlq $6,%mm5 - pxor %mm6,%mm7 - psllq $5,%mm6 - pxor %mm5,%mm7 - psrlq $5,%mm5 - pxor %mm6,%mm7 - psllq $6,%mm6 - pxor %mm5,%mm7 - subl $8,%esp - pxor %mm6,%mm7 - movq %mm0,%mm5 - por %mm2,%mm0 - movq 88(%esp),%mm6 - pand %mm2,%mm5 - pand %mm1,%mm0 - movq 192(%esp),%mm2 - por %mm0,%mm5 - paddq %mm5,%mm7 - movq %mm3,%mm0 - movb (%ebp),%dl - paddq %mm7,%mm0 - addl $8,%ebp - cmpb $23,%dl - jne .L00516_79_sse2 - movq 8(%esp),%mm1 - movq 16(%esp),%mm2 - movq 24(%esp),%mm3 - movq 40(%esp),%mm5 - movq 48(%esp),%mm6 - movq 56(%esp),%mm7 - paddq (%esi),%mm0 - paddq 8(%esi),%mm1 - paddq 16(%esi),%mm2 - paddq 24(%esi),%mm3 - paddq 32(%esi),%mm4 - paddq 40(%esi),%mm5 - paddq 48(%esi),%mm6 - paddq 56(%esi),%mm7 - movq %mm0,(%esi) - movq %mm1,8(%esi) - movq %mm2,16(%esi) - movq %mm3,24(%esi) - movq %mm4,32(%esi) - movq %mm5,40(%esi) - movq %mm6,48(%esi) - movq %mm7,56(%esi) - addl $640,%esp - subl $640,%ebp - cmpl 88(%esp),%edi - jb .L003loop_sse2 - emms - movl 92(%esp),%esp - popl %edi - popl %esi - popl %ebx - popl %ebp - ret -.align 16 -.L002loop_x86: - movl (%edi),%eax - movl 4(%edi),%ebx - movl 8(%edi),%ecx - movl 12(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 16(%edi),%eax - movl 20(%edi),%ebx - movl 24(%edi),%ecx - movl 28(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 32(%edi),%eax - movl 36(%edi),%ebx - movl 40(%edi),%ecx - movl 44(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 48(%edi),%eax - movl 52(%edi),%ebx - movl 56(%edi),%ecx - movl 60(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 64(%edi),%eax - movl 68(%edi),%ebx - movl 72(%edi),%ecx - movl 76(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 80(%edi),%eax - movl 84(%edi),%ebx - movl 88(%edi),%ecx - movl 92(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 96(%edi),%eax - movl 100(%edi),%ebx - movl 104(%edi),%ecx - movl 108(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - movl 112(%edi),%eax - movl 116(%edi),%ebx - movl 120(%edi),%ecx - movl 124(%edi),%edx - bswap %eax - bswap %ebx - bswap %ecx - bswap %edx - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - addl $128,%edi - subl $72,%esp - movl %edi,204(%esp) - leal 8(%esp),%edi - movl $16,%ecx -.long 2784229001 -.align 16 -.L00600_15_x86: - movl 40(%esp),%ecx - movl 44(%esp),%edx - movl %ecx,%esi - shrl $9,%ecx - movl %edx,%edi - shrl $9,%edx - movl %ecx,%ebx - shll $14,%esi - movl %edx,%eax - shll $14,%edi - xorl %esi,%ebx - shrl $5,%ecx - xorl %edi,%eax - shrl $5,%edx - xorl %ecx,%eax - shll $4,%esi - xorl %edx,%ebx - shll $4,%edi - xorl %esi,%ebx - shrl $4,%ecx - xorl %edi,%eax - shrl $4,%edx - xorl %ecx,%eax - shll $5,%esi - xorl %edx,%ebx - shll $5,%edi - xorl %esi,%eax - xorl %edi,%ebx - movl 48(%esp),%ecx - movl 52(%esp),%edx - movl 56(%esp),%esi - movl 60(%esp),%edi - addl 64(%esp),%eax - adcl 68(%esp),%ebx - xorl %esi,%ecx - xorl %edi,%edx - andl 40(%esp),%ecx - andl 44(%esp),%edx - addl 192(%esp),%eax - adcl 196(%esp),%ebx - xorl %esi,%ecx - xorl %edi,%edx - movl (%ebp),%esi - movl 4(%ebp),%edi - addl %ecx,%eax - adcl %edx,%ebx - movl 32(%esp),%ecx - movl 36(%esp),%edx - addl %esi,%eax - adcl %edi,%ebx - movl %eax,(%esp) - movl %ebx,4(%esp) - addl %ecx,%eax - adcl %edx,%ebx - movl 8(%esp),%ecx - movl 12(%esp),%edx - movl %eax,32(%esp) - movl %ebx,36(%esp) - movl %ecx,%esi - shrl $2,%ecx - movl %edx,%edi - shrl $2,%edx - movl %ecx,%ebx - shll $4,%esi - movl %edx,%eax - shll $4,%edi - xorl %esi,%ebx - shrl $5,%ecx - xorl %edi,%eax - shrl $5,%edx - xorl %ecx,%ebx - shll $21,%esi - xorl %edx,%eax - shll $21,%edi - xorl %esi,%eax - shrl $21,%ecx - xorl %edi,%ebx - shrl $21,%edx - xorl %ecx,%eax - shll $5,%esi - xorl %edx,%ebx - shll $5,%edi - xorl %esi,%eax - xorl %edi,%ebx - movl 8(%esp),%ecx - movl 12(%esp),%edx - movl 16(%esp),%esi - movl 20(%esp),%edi - addl (%esp),%eax - adcl 4(%esp),%ebx - orl %esi,%ecx - orl %edi,%edx - andl 24(%esp),%ecx - andl 28(%esp),%edx - andl 8(%esp),%esi - andl 12(%esp),%edi - orl %esi,%ecx - orl %edi,%edx - addl %ecx,%eax - adcl %edx,%ebx - movl %eax,(%esp) - movl %ebx,4(%esp) - movb (%ebp),%dl - subl $8,%esp - leal 8(%ebp),%ebp - cmpb $148,%dl - jne .L00600_15_x86 -.align 16 -.L00716_79_x86: - movl 312(%esp),%ecx - movl 316(%esp),%edx - movl %ecx,%esi - shrl $1,%ecx - movl %edx,%edi - shrl $1,%edx - movl %ecx,%eax - shll $24,%esi - movl %edx,%ebx - shll $24,%edi - xorl %esi,%ebx - shrl $6,%ecx - xorl %edi,%eax - shrl $6,%edx - xorl %ecx,%eax - shll $7,%esi - xorl %edx,%ebx - shll $1,%edi - xorl %esi,%ebx - shrl $1,%ecx - xorl %edi,%eax - shrl $1,%edx - xorl %ecx,%eax - shll $6,%edi - xorl %edx,%ebx - xorl %edi,%eax - movl %eax,(%esp) - movl %ebx,4(%esp) - movl 208(%esp),%ecx - movl 212(%esp),%edx - movl %ecx,%esi - shrl $6,%ecx - movl %edx,%edi - shrl $6,%edx - movl %ecx,%eax - shll $3,%esi - movl %edx,%ebx - shll $3,%edi - xorl %esi,%eax - shrl $13,%ecx - xorl %edi,%ebx - shrl $13,%edx - xorl %ecx,%eax - shll $10,%esi - xorl %edx,%ebx - shll $10,%edi - xorl %esi,%ebx - shrl $10,%ecx - xorl %edi,%eax - shrl $10,%edx - xorl %ecx,%ebx - shll $13,%edi - xorl %edx,%eax - xorl %edi,%eax - movl 320(%esp),%ecx - movl 324(%esp),%edx - addl (%esp),%eax - adcl 4(%esp),%ebx - movl 248(%esp),%esi - movl 252(%esp),%edi - addl %ecx,%eax - adcl %edx,%ebx - addl %esi,%eax - adcl %edi,%ebx - movl %eax,192(%esp) - movl %ebx,196(%esp) - movl 40(%esp),%ecx - movl 44(%esp),%edx - movl %ecx,%esi - shrl $9,%ecx - movl %edx,%edi - shrl $9,%edx - movl %ecx,%ebx - shll $14,%esi - movl %edx,%eax - shll $14,%edi - xorl %esi,%ebx - shrl $5,%ecx - xorl %edi,%eax - shrl $5,%edx - xorl %ecx,%eax - shll $4,%esi - xorl %edx,%ebx - shll $4,%edi - xorl %esi,%ebx - shrl $4,%ecx - xorl %edi,%eax - shrl $4,%edx - xorl %ecx,%eax - shll $5,%esi - xorl %edx,%ebx - shll $5,%edi - xorl %esi,%eax - xorl %edi,%ebx - movl 48(%esp),%ecx - movl 52(%esp),%edx - movl 56(%esp),%esi - movl 60(%esp),%edi - addl 64(%esp),%eax - adcl 68(%esp),%ebx - xorl %esi,%ecx - xorl %edi,%edx - andl 40(%esp),%ecx - andl 44(%esp),%edx - addl 192(%esp),%eax - adcl 196(%esp),%ebx - xorl %esi,%ecx - xorl %edi,%edx - movl (%ebp),%esi - movl 4(%ebp),%edi - addl %ecx,%eax - adcl %edx,%ebx - movl 32(%esp),%ecx - movl 36(%esp),%edx - addl %esi,%eax - adcl %edi,%ebx - movl %eax,(%esp) - movl %ebx,4(%esp) - addl %ecx,%eax - adcl %edx,%ebx - movl 8(%esp),%ecx - movl 12(%esp),%edx - movl %eax,32(%esp) - movl %ebx,36(%esp) - movl %ecx,%esi - shrl $2,%ecx - movl %edx,%edi - shrl $2,%edx - movl %ecx,%ebx - shll $4,%esi - movl %edx,%eax - shll $4,%edi - xorl %esi,%ebx - shrl $5,%ecx - xorl %edi,%eax - shrl $5,%edx - xorl %ecx,%ebx - shll $21,%esi - xorl %edx,%eax - shll $21,%edi - xorl %esi,%eax - shrl $21,%ecx - xorl %edi,%ebx - shrl $21,%edx - xorl %ecx,%eax - shll $5,%esi - xorl %edx,%ebx - shll $5,%edi - xorl %esi,%eax - xorl %edi,%ebx - movl 8(%esp),%ecx - movl 12(%esp),%edx - movl 16(%esp),%esi - movl 20(%esp),%edi - addl (%esp),%eax - adcl 4(%esp),%ebx - orl %esi,%ecx - orl %edi,%edx - andl 24(%esp),%ecx - andl 28(%esp),%edx - andl 8(%esp),%esi - andl 12(%esp),%edi - orl %esi,%ecx - orl %edi,%edx - addl %ecx,%eax - adcl %edx,%ebx - movl %eax,(%esp) - movl %ebx,4(%esp) - movb (%ebp),%dl - subl $8,%esp - leal 8(%ebp),%ebp - cmpb $23,%dl - jne .L00716_79_x86 - movl 840(%esp),%esi - movl 844(%esp),%edi - movl (%esi),%eax - movl 4(%esi),%ebx - movl 8(%esi),%ecx - movl 12(%esi),%edx - addl 8(%esp),%eax - adcl 12(%esp),%ebx - movl %eax,(%esi) - movl %ebx,4(%esi) - addl 16(%esp),%ecx - adcl 20(%esp),%edx - movl %ecx,8(%esi) - movl %edx,12(%esi) - movl 16(%esi),%eax - movl 20(%esi),%ebx - movl 24(%esi),%ecx - movl 28(%esi),%edx - addl 24(%esp),%eax - adcl 28(%esp),%ebx - movl %eax,16(%esi) - movl %ebx,20(%esi) - addl 32(%esp),%ecx - adcl 36(%esp),%edx - movl %ecx,24(%esi) - movl %edx,28(%esi) - movl 32(%esi),%eax - movl 36(%esi),%ebx - movl 40(%esi),%ecx - movl 44(%esi),%edx - addl 40(%esp),%eax - adcl 44(%esp),%ebx - movl %eax,32(%esi) - movl %ebx,36(%esi) - addl 48(%esp),%ecx - adcl 52(%esp),%edx - movl %ecx,40(%esi) - movl %edx,44(%esi) - movl 48(%esi),%eax - movl 52(%esi),%ebx - movl 56(%esi),%ecx - movl 60(%esi),%edx - addl 56(%esp),%eax - adcl 60(%esp),%ebx - movl %eax,48(%esi) - movl %ebx,52(%esi) - addl 64(%esp),%ecx - adcl 68(%esp),%edx - movl %ecx,56(%esi) - movl %edx,60(%esi) - addl $840,%esp - subl $640,%ebp - cmpl 8(%esp),%edi - jb .L002loop_x86 - movl 12(%esp),%esp - popl %edi - popl %esi - popl %ebx - popl %ebp - ret -.align 64 -.L001K512: -.long 3609767458,1116352408 -.long 602891725,1899447441 -.long 3964484399,3049323471 -.long 2173295548,3921009573 -.long 4081628472,961987163 -.long 3053834265,1508970993 -.long 2937671579,2453635748 -.long 3664609560,2870763221 -.long 2734883394,3624381080 -.long 1164996542,310598401 -.long 1323610764,607225278 -.long 3590304994,1426881987 -.long 4068182383,1925078388 -.long 991336113,2162078206 -.long 633803317,2614888103 -.long 3479774868,3248222580 -.long 2666613458,3835390401 -.long 944711139,4022224774 -.long 2341262773,264347078 -.long 2007800933,604807628 -.long 1495990901,770255983 -.long 1856431235,1249150122 -.long 3175218132,1555081692 -.long 2198950837,1996064986 -.long 3999719339,2554220882 -.long 766784016,2821834349 -.long 2566594879,2952996808 -.long 3203337956,3210313671 -.long 1034457026,3336571891 -.long 2466948901,3584528711 -.long 3758326383,113926993 -.long 168717936,338241895 -.long 1188179964,666307205 -.long 1546045734,773529912 -.long 1522805485,1294757372 -.long 2643833823,1396182291 -.long 2343527390,1695183700 -.long 1014477480,1986661051 -.long 1206759142,2177026350 -.long 344077627,2456956037 -.long 1290863460,2730485921 -.long 3158454273,2820302411 -.long 3505952657,3259730800 -.long 106217008,3345764771 -.long 3606008344,3516065817 -.long 1432725776,3600352804 -.long 1467031594,4094571909 -.long 851169720,275423344 -.long 3100823752,430227734 -.long 1363258195,506948616 -.long 3750685593,659060556 -.long 3785050280,883997877 -.long 3318307427,958139571 -.long 3812723403,1322822218 -.long 2003034995,1537002063 -.long 3602036899,1747873779 -.long 1575990012,1955562222 -.long 1125592928,2024104815 -.long 2716904306,2227730452 -.long 442776044,2361852424 -.long 593698344,2428436474 -.long 3733110249,2756734187 -.long 2999351573,3204031479 -.long 3815920427,3329325298 -.long 3928383900,3391569614 -.long 566280711,3515267271 -.long 3454069534,3940187606 -.long 4000239992,4118630271 -.long 1914138554,116418474 -.long 2731055270,174292421 -.long 3203993006,289380356 -.long 320620315,460393269 -.long 587496836,685471733 -.long 1086792851,852142971 -.long 365543100,1017036298 -.long 2618297676,1126000580 -.long 3409855158,1288033470 -.long 4234509866,1501505948 -.long 987167468,1607167915 -.long 1246189591,1816402316 -.size sha512_block_data_order,.-.L_sha512_block_data_order_begin -.byte 83,72,65,53,49,50,32,98,108,111,99,107,32,116,114,97 -.byte 110,115,102,111,114,109,32,102,111,114,32,120,56,54,44,32 -.byte 67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97 -.byte 112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103 -.byte 62,0 -.comm OPENSSL_ia32cap_P,8,4 diff --git a/app/openssl/crypto/sha/asm/sha512-586.pl b/app/openssl/crypto/sha/asm/sha512-586.pl deleted file mode 100644 index 9f8c51eb..00000000 --- a/app/openssl/crypto/sha/asm/sha512-586.pl +++ /dev/null @@ -1,644 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== -# -# SHA512 block transform for x86. September 2007. -# -# Performance in clock cycles per processed byte (less is better): -# -# Pentium PIII P4 AMD K8 Core2 -# gcc 100 75 116 54 66 -# icc 97 77 95 55 57 -# x86 asm 61 56 82 36 40 -# SSE2 asm - - 38 24 20 -# x86_64 asm(*) - - 30 10.0 10.5 -# -# (*) x86_64 assembler performance is presented for reference -# purposes. -# -# IALU code-path is optimized for elder Pentiums. On vanilla Pentium -# performance improvement over compiler generated code reaches ~60%, -# while on PIII - ~35%. On newer µ-archs improvement varies from 15% -# to 50%, but it's less important as they are expected to execute SSE2 -# code-path, which is commonly ~2-3x faster [than compiler generated -# code]. SSE2 code-path is as fast as original sha512-sse2.pl, even -# though it does not use 128-bit operations. The latter means that -# SSE2-aware kernel is no longer required to execute the code. Another -# difference is that new code optimizes amount of writes, but at the -# cost of increased data cache "footprint" by 1/2KB. - -$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; -push(@INC,"${dir}","${dir}../../perlasm"); -require "x86asm.pl"; - -&asm_init($ARGV[0],"sha512-586.pl",$ARGV[$#ARGV] eq "386"); - -$sse2=0; -for (@ARGV) { $sse2=1 if (/-DOPENSSL_IA32_SSE2/); } - -&external_label("OPENSSL_ia32cap_P") if ($sse2); - -$Tlo=&DWP(0,"esp"); $Thi=&DWP(4,"esp"); -$Alo=&DWP(8,"esp"); $Ahi=&DWP(8+4,"esp"); -$Blo=&DWP(16,"esp"); $Bhi=&DWP(16+4,"esp"); -$Clo=&DWP(24,"esp"); $Chi=&DWP(24+4,"esp"); -$Dlo=&DWP(32,"esp"); $Dhi=&DWP(32+4,"esp"); -$Elo=&DWP(40,"esp"); $Ehi=&DWP(40+4,"esp"); -$Flo=&DWP(48,"esp"); $Fhi=&DWP(48+4,"esp"); -$Glo=&DWP(56,"esp"); $Ghi=&DWP(56+4,"esp"); -$Hlo=&DWP(64,"esp"); $Hhi=&DWP(64+4,"esp"); -$K512="ebp"; - -$Asse2=&QWP(0,"esp"); -$Bsse2=&QWP(8,"esp"); -$Csse2=&QWP(16,"esp"); -$Dsse2=&QWP(24,"esp"); -$Esse2=&QWP(32,"esp"); -$Fsse2=&QWP(40,"esp"); -$Gsse2=&QWP(48,"esp"); -$Hsse2=&QWP(56,"esp"); - -$A="mm0"; # B-D and -$E="mm4"; # F-H are commonly loaded to respectively mm1-mm3 and - # mm5-mm7, but it's done on on-demand basis... - -sub BODY_00_15_sse2 { - my $prefetch=shift; - - &movq ("mm5",$Fsse2); # load f - &movq ("mm6",$Gsse2); # load g - &movq ("mm7",$Hsse2); # load h - - &movq ("mm1",$E); # %mm1 is sliding right - &movq ("mm2",$E); # %mm2 is sliding left - &psrlq ("mm1",14); - &movq ($Esse2,$E); # modulo-scheduled save e - &psllq ("mm2",23); - &movq ("mm3","mm1"); # %mm3 is T1 - &psrlq ("mm1",4); - &pxor ("mm3","mm2"); - &psllq ("mm2",23); - &pxor ("mm3","mm1"); - &psrlq ("mm1",23); - &pxor ("mm3","mm2"); - &psllq ("mm2",4); - &pxor ("mm3","mm1"); - &paddq ("mm7",QWP(0,$K512)); # h+=K512[i] - &pxor ("mm3","mm2"); # T1=Sigma1_512(e) - - &pxor ("mm5","mm6"); # f^=g - &movq ("mm1",$Bsse2); # load b - &pand ("mm5",$E); # f&=e - &movq ("mm2",$Csse2); # load c - &pxor ("mm5","mm6"); # f^=g - &movq ($E,$Dsse2); # e = load d - &paddq ("mm3","mm5"); # T1+=Ch(e,f,g) - &movq (&QWP(0,"esp"),$A); # modulo-scheduled save a - &paddq ("mm3","mm7"); # T1+=h - - &movq ("mm5",$A); # %mm5 is sliding right - &movq ("mm6",$A); # %mm6 is sliding left - &paddq ("mm3",&QWP(8*9,"esp")); # T1+=X[0] - &psrlq ("mm5",28); - &paddq ($E,"mm3"); # e += T1 - &psllq ("mm6",25); - &movq ("mm7","mm5"); # %mm7 is T2 - &psrlq ("mm5",6); - &pxor ("mm7","mm6"); - &psllq ("mm6",5); - &pxor ("mm7","mm5"); - &psrlq ("mm5",5); - &pxor ("mm7","mm6"); - &psllq ("mm6",6); - &pxor ("mm7","mm5"); - &sub ("esp",8); - &pxor ("mm7","mm6"); # T2=Sigma0_512(a) - - &movq ("mm5",$A); # %mm5=a - &por ($A,"mm2"); # a=a|c - &movq ("mm6",&QWP(8*(9+16-14),"esp")) if ($prefetch); - &pand ("mm5","mm2"); # %mm5=a&c - &pand ($A,"mm1"); # a=(a|c)&b - &movq ("mm2",&QWP(8*(9+16-1),"esp")) if ($prefetch); - &por ("mm5",$A); # %mm5=(a&c)|((a|c)&b) - &paddq ("mm7","mm5"); # T2+=Maj(a,b,c) - &movq ($A,"mm3"); # a=T1 - - &mov (&LB("edx"),&BP(0,$K512)); - &paddq ($A,"mm7"); # a+=T2 - &add ($K512,8); -} - -sub BODY_00_15_x86 { - #define Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41)) - # LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23 - # HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23 - &mov ("ecx",$Elo); - &mov ("edx",$Ehi); - &mov ("esi","ecx"); - - &shr ("ecx",9); # lo>>9 - &mov ("edi","edx"); - &shr ("edx",9); # hi>>9 - &mov ("ebx","ecx"); - &shl ("esi",14); # lo<<14 - &mov ("eax","edx"); - &shl ("edi",14); # hi<<14 - &xor ("ebx","esi"); - - &shr ("ecx",14-9); # lo>>14 - &xor ("eax","edi"); - &shr ("edx",14-9); # hi>>14 - &xor ("eax","ecx"); - &shl ("esi",18-14); # lo<<18 - &xor ("ebx","edx"); - &shl ("edi",18-14); # hi<<18 - &xor ("ebx","esi"); - - &shr ("ecx",18-14); # lo>>18 - &xor ("eax","edi"); - &shr ("edx",18-14); # hi>>18 - &xor ("eax","ecx"); - &shl ("esi",23-18); # lo<<23 - &xor ("ebx","edx"); - &shl ("edi",23-18); # hi<<23 - &xor ("eax","esi"); - &xor ("ebx","edi"); # T1 = Sigma1(e) - - &mov ("ecx",$Flo); - &mov ("edx",$Fhi); - &mov ("esi",$Glo); - &mov ("edi",$Ghi); - &add ("eax",$Hlo); - &adc ("ebx",$Hhi); # T1 += h - &xor ("ecx","esi"); - &xor ("edx","edi"); - &and ("ecx",$Elo); - &and ("edx",$Ehi); - &add ("eax",&DWP(8*(9+15)+0,"esp")); - &adc ("ebx",&DWP(8*(9+15)+4,"esp")); # T1 += X[0] - &xor ("ecx","esi"); - &xor ("edx","edi"); # Ch(e,f,g) = (f^g)&e)^g - - &mov ("esi",&DWP(0,$K512)); - &mov ("edi",&DWP(4,$K512)); # K[i] - &add ("eax","ecx"); - &adc ("ebx","edx"); # T1 += Ch(e,f,g) - &mov ("ecx",$Dlo); - &mov ("edx",$Dhi); - &add ("eax","esi"); - &adc ("ebx","edi"); # T1 += K[i] - &mov ($Tlo,"eax"); - &mov ($Thi,"ebx"); # put T1 away - &add ("eax","ecx"); - &adc ("ebx","edx"); # d += T1 - - #define Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39)) - # LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25 - # HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25 - &mov ("ecx",$Alo); - &mov ("edx",$Ahi); - &mov ($Dlo,"eax"); - &mov ($Dhi,"ebx"); - &mov ("esi","ecx"); - - &shr ("ecx",2); # lo>>2 - &mov ("edi","edx"); - &shr ("edx",2); # hi>>2 - &mov ("ebx","ecx"); - &shl ("esi",4); # lo<<4 - &mov ("eax","edx"); - &shl ("edi",4); # hi<<4 - &xor ("ebx","esi"); - - &shr ("ecx",7-2); # lo>>7 - &xor ("eax","edi"); - &shr ("edx",7-2); # hi>>7 - &xor ("ebx","ecx"); - &shl ("esi",25-4); # lo<<25 - &xor ("eax","edx"); - &shl ("edi",25-4); # hi<<25 - &xor ("eax","esi"); - - &shr ("ecx",28-7); # lo>>28 - &xor ("ebx","edi"); - &shr ("edx",28-7); # hi>>28 - &xor ("eax","ecx"); - &shl ("esi",30-25); # lo<<30 - &xor ("ebx","edx"); - &shl ("edi",30-25); # hi<<30 - &xor ("eax","esi"); - &xor ("ebx","edi"); # Sigma0(a) - - &mov ("ecx",$Alo); - &mov ("edx",$Ahi); - &mov ("esi",$Blo); - &mov ("edi",$Bhi); - &add ("eax",$Tlo); - &adc ("ebx",$Thi); # T1 = Sigma0(a)+T1 - &or ("ecx","esi"); - &or ("edx","edi"); - &and ("ecx",$Clo); - &and ("edx",$Chi); - &and ("esi",$Alo); - &and ("edi",$Ahi); - &or ("ecx","esi"); - &or ("edx","edi"); # Maj(a,b,c) = ((a|b)&c)|(a&b) - - &add ("eax","ecx"); - &adc ("ebx","edx"); # T1 += Maj(a,b,c) - &mov ($Tlo,"eax"); - &mov ($Thi,"ebx"); - - &mov (&LB("edx"),&BP(0,$K512)); # pre-fetch LSB of *K - &sub ("esp",8); - &lea ($K512,&DWP(8,$K512)); # K++ -} - - -&function_begin("sha512_block_data_order"); - &mov ("esi",wparam(0)); # ctx - &mov ("edi",wparam(1)); # inp - &mov ("eax",wparam(2)); # num - &mov ("ebx","esp"); # saved sp - - &call (&label("pic_point")); # make it PIC! -&set_label("pic_point"); - &blindpop($K512); - &lea ($K512,&DWP(&label("K512")."-".&label("pic_point"),$K512)); - - &sub ("esp",16); - &and ("esp",-64); - - &shl ("eax",7); - &add ("eax","edi"); - &mov (&DWP(0,"esp"),"esi"); # ctx - &mov (&DWP(4,"esp"),"edi"); # inp - &mov (&DWP(8,"esp"),"eax"); # inp+num*128 - &mov (&DWP(12,"esp"),"ebx"); # saved sp - -if ($sse2) { - &picmeup("edx","OPENSSL_ia32cap_P",$K512,&label("K512")); - &bt (&DWP(0,"edx"),26); - &jnc (&label("loop_x86")); - - # load ctx->h[0-7] - &movq ($A,&QWP(0,"esi")); - &movq ("mm1",&QWP(8,"esi")); - &movq ("mm2",&QWP(16,"esi")); - &movq ("mm3",&QWP(24,"esi")); - &movq ($E,&QWP(32,"esi")); - &movq ("mm5",&QWP(40,"esi")); - &movq ("mm6",&QWP(48,"esi")); - &movq ("mm7",&QWP(56,"esi")); - &sub ("esp",8*10); - -&set_label("loop_sse2",16); - # &movq ($Asse2,$A); - &movq ($Bsse2,"mm1"); - &movq ($Csse2,"mm2"); - &movq ($Dsse2,"mm3"); - # &movq ($Esse2,$E); - &movq ($Fsse2,"mm5"); - &movq ($Gsse2,"mm6"); - &movq ($Hsse2,"mm7"); - - &mov ("ecx",&DWP(0,"edi")); - &mov ("edx",&DWP(4,"edi")); - &add ("edi",8); - &bswap ("ecx"); - &bswap ("edx"); - &mov (&DWP(8*9+4,"esp"),"ecx"); - &mov (&DWP(8*9+0,"esp"),"edx"); - -&set_label("00_14_sse2",16); - &mov ("eax",&DWP(0,"edi")); - &mov ("ebx",&DWP(4,"edi")); - &add ("edi",8); - &bswap ("eax"); - &bswap ("ebx"); - &mov (&DWP(8*8+4,"esp"),"eax"); - &mov (&DWP(8*8+0,"esp"),"ebx"); - - &BODY_00_15_sse2(); - - &cmp (&LB("edx"),0x35); - &jne (&label("00_14_sse2")); - - &BODY_00_15_sse2(1); - -&set_label("16_79_sse2",16); - #&movq ("mm2",&QWP(8*(9+16-1),"esp")); #prefetched in BODY_00_15 - #&movq ("mm6",&QWP(8*(9+16-14),"esp")); - &movq ("mm1","mm2"); - - &psrlq ("mm2",1); - &movq ("mm7","mm6"); - &psrlq ("mm6",6); - &movq ("mm3","mm2"); - - &psrlq ("mm2",7-1); - &movq ("mm5","mm6"); - &psrlq ("mm6",19-6); - &pxor ("mm3","mm2"); - - &psrlq ("mm2",8-7); - &pxor ("mm5","mm6"); - &psrlq ("mm6",61-19); - &pxor ("mm3","mm2"); - - &movq ("mm2",&QWP(8*(9+16),"esp")); - - &psllq ("mm1",56); - &pxor ("mm5","mm6"); - &psllq ("mm7",3); - &pxor ("mm3","mm1"); - - &paddq ("mm2",&QWP(8*(9+16-9),"esp")); - - &psllq ("mm1",63-56); - &pxor ("mm5","mm7"); - &psllq ("mm7",45-3); - &pxor ("mm3","mm1"); - &pxor ("mm5","mm7"); - - &paddq ("mm3","mm5"); - &paddq ("mm3","mm2"); - &movq (&QWP(8*9,"esp"),"mm3"); - - &BODY_00_15_sse2(1); - - &cmp (&LB("edx"),0x17); - &jne (&label("16_79_sse2")); - - # &movq ($A,$Asse2); - &movq ("mm1",$Bsse2); - &movq ("mm2",$Csse2); - &movq ("mm3",$Dsse2); - # &movq ($E,$Esse2); - &movq ("mm5",$Fsse2); - &movq ("mm6",$Gsse2); - &movq ("mm7",$Hsse2); - - &paddq ($A,&QWP(0,"esi")); - &paddq ("mm1",&QWP(8,"esi")); - &paddq ("mm2",&QWP(16,"esi")); - &paddq ("mm3",&QWP(24,"esi")); - &paddq ($E,&QWP(32,"esi")); - &paddq ("mm5",&QWP(40,"esi")); - &paddq ("mm6",&QWP(48,"esi")); - &paddq ("mm7",&QWP(56,"esi")); - - &movq (&QWP(0,"esi"),$A); - &movq (&QWP(8,"esi"),"mm1"); - &movq (&QWP(16,"esi"),"mm2"); - &movq (&QWP(24,"esi"),"mm3"); - &movq (&QWP(32,"esi"),$E); - &movq (&QWP(40,"esi"),"mm5"); - &movq (&QWP(48,"esi"),"mm6"); - &movq (&QWP(56,"esi"),"mm7"); - - &add ("esp",8*80); # destroy frame - &sub ($K512,8*80); # rewind K - - &cmp ("edi",&DWP(8*10+8,"esp")); # are we done yet? - &jb (&label("loop_sse2")); - - &emms (); - &mov ("esp",&DWP(8*10+12,"esp")); # restore sp -&function_end_A(); -} -&set_label("loop_x86",16); - # copy input block to stack reversing byte and qword order - for ($i=0;$i<8;$i++) { - &mov ("eax",&DWP($i*16+0,"edi")); - &mov ("ebx",&DWP($i*16+4,"edi")); - &mov ("ecx",&DWP($i*16+8,"edi")); - &mov ("edx",&DWP($i*16+12,"edi")); - &bswap ("eax"); - &bswap ("ebx"); - &bswap ("ecx"); - &bswap ("edx"); - &push ("eax"); - &push ("ebx"); - &push ("ecx"); - &push ("edx"); - } - &add ("edi",128); - &sub ("esp",9*8); # place for T,A,B,C,D,E,F,G,H - &mov (&DWP(8*(9+16)+4,"esp"),"edi"); - - # copy ctx->h[0-7] to A,B,C,D,E,F,G,H on stack - &lea ("edi",&DWP(8,"esp")); - &mov ("ecx",16); - &data_word(0xA5F3F689); # rep movsd - -&set_label("00_15_x86",16); - &BODY_00_15_x86(); - - &cmp (&LB("edx"),0x94); - &jne (&label("00_15_x86")); - -&set_label("16_79_x86",16); - #define sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7)) - # LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25 - # HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7 - &mov ("ecx",&DWP(8*(9+15+16-1)+0,"esp")); - &mov ("edx",&DWP(8*(9+15+16-1)+4,"esp")); - &mov ("esi","ecx"); - - &shr ("ecx",1); # lo>>1 - &mov ("edi","edx"); - &shr ("edx",1); # hi>>1 - &mov ("eax","ecx"); - &shl ("esi",24); # lo<<24 - &mov ("ebx","edx"); - &shl ("edi",24); # hi<<24 - &xor ("ebx","esi"); - - &shr ("ecx",7-1); # lo>>7 - &xor ("eax","edi"); - &shr ("edx",7-1); # hi>>7 - &xor ("eax","ecx"); - &shl ("esi",31-24); # lo<<31 - &xor ("ebx","edx"); - &shl ("edi",25-24); # hi<<25 - &xor ("ebx","esi"); - - &shr ("ecx",8-7); # lo>>8 - &xor ("eax","edi"); - &shr ("edx",8-7); # hi>>8 - &xor ("eax","ecx"); - &shl ("edi",31-25); # hi<<31 - &xor ("ebx","edx"); - &xor ("eax","edi"); # T1 = sigma0(X[-15]) - - &mov (&DWP(0,"esp"),"eax"); - &mov (&DWP(4,"esp"),"ebx"); # put T1 away - - #define sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6)) - # LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26 - # HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6 - &mov ("ecx",&DWP(8*(9+15+16-14)+0,"esp")); - &mov ("edx",&DWP(8*(9+15+16-14)+4,"esp")); - &mov ("esi","ecx"); - - &shr ("ecx",6); # lo>>6 - &mov ("edi","edx"); - &shr ("edx",6); # hi>>6 - &mov ("eax","ecx"); - &shl ("esi",3); # lo<<3 - &mov ("ebx","edx"); - &shl ("edi",3); # hi<<3 - &xor ("eax","esi"); - - &shr ("ecx",19-6); # lo>>19 - &xor ("ebx","edi"); - &shr ("edx",19-6); # hi>>19 - &xor ("eax","ecx"); - &shl ("esi",13-3); # lo<<13 - &xor ("ebx","edx"); - &shl ("edi",13-3); # hi<<13 - &xor ("ebx","esi"); - - &shr ("ecx",29-19); # lo>>29 - &xor ("eax","edi"); - &shr ("edx",29-19); # hi>>29 - &xor ("ebx","ecx"); - &shl ("edi",26-13); # hi<<26 - &xor ("eax","edx"); - &xor ("eax","edi"); # sigma1(X[-2]) - - &mov ("ecx",&DWP(8*(9+15+16)+0,"esp")); - &mov ("edx",&DWP(8*(9+15+16)+4,"esp")); - &add ("eax",&DWP(0,"esp")); - &adc ("ebx",&DWP(4,"esp")); # T1 = sigma1(X[-2])+T1 - &mov ("esi",&DWP(8*(9+15+16-9)+0,"esp")); - &mov ("edi",&DWP(8*(9+15+16-9)+4,"esp")); - &add ("eax","ecx"); - &adc ("ebx","edx"); # T1 += X[-16] - &add ("eax","esi"); - &adc ("ebx","edi"); # T1 += X[-7] - &mov (&DWP(8*(9+15)+0,"esp"),"eax"); - &mov (&DWP(8*(9+15)+4,"esp"),"ebx"); # save X[0] - - &BODY_00_15_x86(); - - &cmp (&LB("edx"),0x17); - &jne (&label("16_79_x86")); - - &mov ("esi",&DWP(8*(9+16+80)+0,"esp"));# ctx - &mov ("edi",&DWP(8*(9+16+80)+4,"esp"));# inp - for($i=0;$i<4;$i++) { - &mov ("eax",&DWP($i*16+0,"esi")); - &mov ("ebx",&DWP($i*16+4,"esi")); - &mov ("ecx",&DWP($i*16+8,"esi")); - &mov ("edx",&DWP($i*16+12,"esi")); - &add ("eax",&DWP(8+($i*16)+0,"esp")); - &adc ("ebx",&DWP(8+($i*16)+4,"esp")); - &mov (&DWP($i*16+0,"esi"),"eax"); - &mov (&DWP($i*16+4,"esi"),"ebx"); - &add ("ecx",&DWP(8+($i*16)+8,"esp")); - &adc ("edx",&DWP(8+($i*16)+12,"esp")); - &mov (&DWP($i*16+8,"esi"),"ecx"); - &mov (&DWP($i*16+12,"esi"),"edx"); - } - &add ("esp",8*(9+16+80)); # destroy frame - &sub ($K512,8*80); # rewind K - - &cmp ("edi",&DWP(8,"esp")); # are we done yet? - &jb (&label("loop_x86")); - - &mov ("esp",&DWP(12,"esp")); # restore sp -&function_end_A(); - -&set_label("K512",64); # Yes! I keep it in the code segment! - &data_word(0xd728ae22,0x428a2f98); # u64 - &data_word(0x23ef65cd,0x71374491); # u64 - &data_word(0xec4d3b2f,0xb5c0fbcf); # u64 - &data_word(0x8189dbbc,0xe9b5dba5); # u64 - &data_word(0xf348b538,0x3956c25b); # u64 - &data_word(0xb605d019,0x59f111f1); # u64 - &data_word(0xaf194f9b,0x923f82a4); # u64 - &data_word(0xda6d8118,0xab1c5ed5); # u64 - &data_word(0xa3030242,0xd807aa98); # u64 - &data_word(0x45706fbe,0x12835b01); # u64 - &data_word(0x4ee4b28c,0x243185be); # u64 - &data_word(0xd5ffb4e2,0x550c7dc3); # u64 - &data_word(0xf27b896f,0x72be5d74); # u64 - &data_word(0x3b1696b1,0x80deb1fe); # u64 - &data_word(0x25c71235,0x9bdc06a7); # u64 - &data_word(0xcf692694,0xc19bf174); # u64 - &data_word(0x9ef14ad2,0xe49b69c1); # u64 - &data_word(0x384f25e3,0xefbe4786); # u64 - &data_word(0x8b8cd5b5,0x0fc19dc6); # u64 - &data_word(0x77ac9c65,0x240ca1cc); # u64 - &data_word(0x592b0275,0x2de92c6f); # u64 - &data_word(0x6ea6e483,0x4a7484aa); # u64 - &data_word(0xbd41fbd4,0x5cb0a9dc); # u64 - &data_word(0x831153b5,0x76f988da); # u64 - &data_word(0xee66dfab,0x983e5152); # u64 - &data_word(0x2db43210,0xa831c66d); # u64 - &data_word(0x98fb213f,0xb00327c8); # u64 - &data_word(0xbeef0ee4,0xbf597fc7); # u64 - &data_word(0x3da88fc2,0xc6e00bf3); # u64 - &data_word(0x930aa725,0xd5a79147); # u64 - &data_word(0xe003826f,0x06ca6351); # u64 - &data_word(0x0a0e6e70,0x14292967); # u64 - &data_word(0x46d22ffc,0x27b70a85); # u64 - &data_word(0x5c26c926,0x2e1b2138); # u64 - &data_word(0x5ac42aed,0x4d2c6dfc); # u64 - &data_word(0x9d95b3df,0x53380d13); # u64 - &data_word(0x8baf63de,0x650a7354); # u64 - &data_word(0x3c77b2a8,0x766a0abb); # u64 - &data_word(0x47edaee6,0x81c2c92e); # u64 - &data_word(0x1482353b,0x92722c85); # u64 - &data_word(0x4cf10364,0xa2bfe8a1); # u64 - &data_word(0xbc423001,0xa81a664b); # u64 - &data_word(0xd0f89791,0xc24b8b70); # u64 - &data_word(0x0654be30,0xc76c51a3); # u64 - &data_word(0xd6ef5218,0xd192e819); # u64 - &data_word(0x5565a910,0xd6990624); # u64 - &data_word(0x5771202a,0xf40e3585); # u64 - &data_word(0x32bbd1b8,0x106aa070); # u64 - &data_word(0xb8d2d0c8,0x19a4c116); # u64 - &data_word(0x5141ab53,0x1e376c08); # u64 - &data_word(0xdf8eeb99,0x2748774c); # u64 - &data_word(0xe19b48a8,0x34b0bcb5); # u64 - &data_word(0xc5c95a63,0x391c0cb3); # u64 - &data_word(0xe3418acb,0x4ed8aa4a); # u64 - &data_word(0x7763e373,0x5b9cca4f); # u64 - &data_word(0xd6b2b8a3,0x682e6ff3); # u64 - &data_word(0x5defb2fc,0x748f82ee); # u64 - &data_word(0x43172f60,0x78a5636f); # u64 - &data_word(0xa1f0ab72,0x84c87814); # u64 - &data_word(0x1a6439ec,0x8cc70208); # u64 - &data_word(0x23631e28,0x90befffa); # u64 - &data_word(0xde82bde9,0xa4506ceb); # u64 - &data_word(0xb2c67915,0xbef9a3f7); # u64 - &data_word(0xe372532b,0xc67178f2); # u64 - &data_word(0xea26619c,0xca273ece); # u64 - &data_word(0x21c0c207,0xd186b8c7); # u64 - &data_word(0xcde0eb1e,0xeada7dd6); # u64 - &data_word(0xee6ed178,0xf57d4f7f); # u64 - &data_word(0x72176fba,0x06f067aa); # u64 - &data_word(0xa2c898a6,0x0a637dc5); # u64 - &data_word(0xbef90dae,0x113f9804); # u64 - &data_word(0x131c471b,0x1b710b35); # u64 - &data_word(0x23047d84,0x28db77f5); # u64 - &data_word(0x40c72493,0x32caab7b); # u64 - &data_word(0x15c9bebc,0x3c9ebe0a); # u64 - &data_word(0x9c100d4c,0x431d67c4); # u64 - &data_word(0xcb3e42b6,0x4cc5d4be); # u64 - &data_word(0xfc657e2a,0x597f299c); # u64 - &data_word(0x3ad6faec,0x5fcb6fab); # u64 - &data_word(0x4a475817,0x6c44198c); # u64 -&function_end_B("sha512_block_data_order"); -&asciz("SHA512 block transform for x86, CRYPTOGAMS by <appro\@openssl.org>"); - -&asm_finish(); diff --git a/app/openssl/crypto/sha/asm/sha512-armv4.S b/app/openssl/crypto/sha/asm/sha512-armv4.S deleted file mode 100644 index fd462771..00000000 --- a/app/openssl/crypto/sha/asm/sha512-armv4.S +++ /dev/null @@ -1,1783 +0,0 @@ -#include "arm_arch.h" -#ifdef __ARMEL__ -# define LO 0 -# define HI 4 -# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1 -#else -# define HI 0 -# define LO 4 -# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1 -#endif - -.text -.code 32 -.type K512,%object -.align 5 -K512: -WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd) -WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc) -WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019) -WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118) -WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe) -WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2) -WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1) -WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694) -WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3) -WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65) -WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483) -WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5) -WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210) -WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4) -WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725) -WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70) -WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926) -WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df) -WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8) -WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b) -WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001) -WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30) -WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910) -WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8) -WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53) -WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8) -WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb) -WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3) -WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60) -WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec) -WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9) -WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b) -WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207) -WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178) -WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6) -WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b) -WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493) -WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c) -WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a) -WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) -.size K512,.-K512 -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-sha512_block_data_order -.skip 32-4 - -.global sha512_block_data_order -.type sha512_block_data_order,%function -sha512_block_data_order: - sub r3,pc,#8 @ sha512_block_data_order - add r2,r1,r2,lsl#7 @ len to point at the end of inp -#if __ARM_ARCH__>=7 - ldr r12,.LOPENSSL_armcap - ldr r12,[r3,r12] @ OPENSSL_armcap_P - tst r12,#1 - bne .LNEON -#endif - stmdb sp!,{r4-r12,lr} - sub r14,r3,#672 @ K512 - sub sp,sp,#9*8 - - ldr r7,[r0,#32+LO] - ldr r8,[r0,#32+HI] - ldr r9, [r0,#48+LO] - ldr r10, [r0,#48+HI] - ldr r11, [r0,#56+LO] - ldr r12, [r0,#56+HI] -.Loop: - str r9, [sp,#48+0] - str r10, [sp,#48+4] - str r11, [sp,#56+0] - str r12, [sp,#56+4] - ldr r5,[r0,#0+LO] - ldr r6,[r0,#0+HI] - ldr r3,[r0,#8+LO] - ldr r4,[r0,#8+HI] - ldr r9, [r0,#16+LO] - ldr r10, [r0,#16+HI] - ldr r11, [r0,#24+LO] - ldr r12, [r0,#24+HI] - str r3,[sp,#8+0] - str r4,[sp,#8+4] - str r9, [sp,#16+0] - str r10, [sp,#16+4] - str r11, [sp,#24+0] - str r12, [sp,#24+4] - ldr r3,[r0,#40+LO] - ldr r4,[r0,#40+HI] - str r3,[sp,#40+0] - str r4,[sp,#40+4] - -.L00_15: -#if __ARM_ARCH__<7 - ldrb r3,[r1,#7] - ldrb r9, [r1,#6] - ldrb r10, [r1,#5] - ldrb r11, [r1,#4] - ldrb r4,[r1,#3] - ldrb r12, [r1,#2] - orr r3,r3,r9,lsl#8 - ldrb r9, [r1,#1] - orr r3,r3,r10,lsl#16 - ldrb r10, [r1],#8 - orr r3,r3,r11,lsl#24 - orr r4,r4,r12,lsl#8 - orr r4,r4,r9,lsl#16 - orr r4,r4,r10,lsl#24 -#else - ldr r3,[r1,#4] - ldr r4,[r1],#8 -#ifdef __ARMEL__ - rev r3,r3 - rev r4,r4 -#endif -#endif - @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41)) - @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23 - @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23 - mov r9,r7,lsr#14 - str r3,[sp,#64+0] - mov r10,r8,lsr#14 - str r4,[sp,#64+4] - eor r9,r9,r8,lsl#18 - ldr r11,[sp,#56+0] @ h.lo - eor r10,r10,r7,lsl#18 - ldr r12,[sp,#56+4] @ h.hi - eor r9,r9,r7,lsr#18 - eor r10,r10,r8,lsr#18 - eor r9,r9,r8,lsl#14 - eor r10,r10,r7,lsl#14 - eor r9,r9,r8,lsr#9 - eor r10,r10,r7,lsr#9 - eor r9,r9,r7,lsl#23 - eor r10,r10,r8,lsl#23 @ Sigma1(e) - adds r3,r3,r9 - ldr r9,[sp,#40+0] @ f.lo - adc r4,r4,r10 @ T += Sigma1(e) - ldr r10,[sp,#40+4] @ f.hi - adds r3,r3,r11 - ldr r11,[sp,#48+0] @ g.lo - adc r4,r4,r12 @ T += h - ldr r12,[sp,#48+4] @ g.hi - - eor r9,r9,r11 - str r7,[sp,#32+0] - eor r10,r10,r12 - str r8,[sp,#32+4] - and r9,r9,r7 - str r5,[sp,#0+0] - and r10,r10,r8 - str r6,[sp,#0+4] - eor r9,r9,r11 - ldr r11,[r14,#LO] @ K[i].lo - eor r10,r10,r12 @ Ch(e,f,g) - ldr r12,[r14,#HI] @ K[i].hi - - adds r3,r3,r9 - ldr r7,[sp,#24+0] @ d.lo - adc r4,r4,r10 @ T += Ch(e,f,g) - ldr r8,[sp,#24+4] @ d.hi - adds r3,r3,r11 - and r9,r11,#0xff - adc r4,r4,r12 @ T += K[i] - adds r7,r7,r3 - ldr r11,[sp,#8+0] @ b.lo - adc r8,r8,r4 @ d += T - teq r9,#148 - - ldr r12,[sp,#16+0] @ c.lo - orreq r14,r14,#1 - @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39)) - @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25 - @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25 - mov r9,r5,lsr#28 - mov r10,r6,lsr#28 - eor r9,r9,r6,lsl#4 - eor r10,r10,r5,lsl#4 - eor r9,r9,r6,lsr#2 - eor r10,r10,r5,lsr#2 - eor r9,r9,r5,lsl#30 - eor r10,r10,r6,lsl#30 - eor r9,r9,r6,lsr#7 - eor r10,r10,r5,lsr#7 - eor r9,r9,r5,lsl#25 - eor r10,r10,r6,lsl#25 @ Sigma0(a) - adds r3,r3,r9 - and r9,r5,r11 - adc r4,r4,r10 @ T += Sigma0(a) - - ldr r10,[sp,#8+4] @ b.hi - orr r5,r5,r11 - ldr r11,[sp,#16+4] @ c.hi - and r5,r5,r12 - and r12,r6,r10 - orr r6,r6,r10 - orr r5,r5,r9 @ Maj(a,b,c).lo - and r6,r6,r11 - adds r5,r5,r3 - orr r6,r6,r12 @ Maj(a,b,c).hi - sub sp,sp,#8 - adc r6,r6,r4 @ h += T - tst r14,#1 - add r14,r14,#8 - tst r14,#1 - beq .L00_15 - ldr r9,[sp,#184+0] - ldr r10,[sp,#184+4] - bic r14,r14,#1 -.L16_79: - @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7)) - @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25 - @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7 - mov r3,r9,lsr#1 - ldr r11,[sp,#80+0] - mov r4,r10,lsr#1 - ldr r12,[sp,#80+4] - eor r3,r3,r10,lsl#31 - eor r4,r4,r9,lsl#31 - eor r3,r3,r9,lsr#8 - eor r4,r4,r10,lsr#8 - eor r3,r3,r10,lsl#24 - eor r4,r4,r9,lsl#24 - eor r3,r3,r9,lsr#7 - eor r4,r4,r10,lsr#7 - eor r3,r3,r10,lsl#25 - - @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6)) - @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26 - @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6 - mov r9,r11,lsr#19 - mov r10,r12,lsr#19 - eor r9,r9,r12,lsl#13 - eor r10,r10,r11,lsl#13 - eor r9,r9,r12,lsr#29 - eor r10,r10,r11,lsr#29 - eor r9,r9,r11,lsl#3 - eor r10,r10,r12,lsl#3 - eor r9,r9,r11,lsr#6 - eor r10,r10,r12,lsr#6 - ldr r11,[sp,#120+0] - eor r9,r9,r12,lsl#26 - - ldr r12,[sp,#120+4] - adds r3,r3,r9 - ldr r9,[sp,#192+0] - adc r4,r4,r10 - - ldr r10,[sp,#192+4] - adds r3,r3,r11 - adc r4,r4,r12 - adds r3,r3,r9 - adc r4,r4,r10 - @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41)) - @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23 - @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23 - mov r9,r7,lsr#14 - str r3,[sp,#64+0] - mov r10,r8,lsr#14 - str r4,[sp,#64+4] - eor r9,r9,r8,lsl#18 - ldr r11,[sp,#56+0] @ h.lo - eor r10,r10,r7,lsl#18 - ldr r12,[sp,#56+4] @ h.hi - eor r9,r9,r7,lsr#18 - eor r10,r10,r8,lsr#18 - eor r9,r9,r8,lsl#14 - eor r10,r10,r7,lsl#14 - eor r9,r9,r8,lsr#9 - eor r10,r10,r7,lsr#9 - eor r9,r9,r7,lsl#23 - eor r10,r10,r8,lsl#23 @ Sigma1(e) - adds r3,r3,r9 - ldr r9,[sp,#40+0] @ f.lo - adc r4,r4,r10 @ T += Sigma1(e) - ldr r10,[sp,#40+4] @ f.hi - adds r3,r3,r11 - ldr r11,[sp,#48+0] @ g.lo - adc r4,r4,r12 @ T += h - ldr r12,[sp,#48+4] @ g.hi - - eor r9,r9,r11 - str r7,[sp,#32+0] - eor r10,r10,r12 - str r8,[sp,#32+4] - and r9,r9,r7 - str r5,[sp,#0+0] - and r10,r10,r8 - str r6,[sp,#0+4] - eor r9,r9,r11 - ldr r11,[r14,#LO] @ K[i].lo - eor r10,r10,r12 @ Ch(e,f,g) - ldr r12,[r14,#HI] @ K[i].hi - - adds r3,r3,r9 - ldr r7,[sp,#24+0] @ d.lo - adc r4,r4,r10 @ T += Ch(e,f,g) - ldr r8,[sp,#24+4] @ d.hi - adds r3,r3,r11 - and r9,r11,#0xff - adc r4,r4,r12 @ T += K[i] - adds r7,r7,r3 - ldr r11,[sp,#8+0] @ b.lo - adc r8,r8,r4 @ d += T - teq r9,#23 - - ldr r12,[sp,#16+0] @ c.lo - orreq r14,r14,#1 - @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39)) - @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25 - @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25 - mov r9,r5,lsr#28 - mov r10,r6,lsr#28 - eor r9,r9,r6,lsl#4 - eor r10,r10,r5,lsl#4 - eor r9,r9,r6,lsr#2 - eor r10,r10,r5,lsr#2 - eor r9,r9,r5,lsl#30 - eor r10,r10,r6,lsl#30 - eor r9,r9,r6,lsr#7 - eor r10,r10,r5,lsr#7 - eor r9,r9,r5,lsl#25 - eor r10,r10,r6,lsl#25 @ Sigma0(a) - adds r3,r3,r9 - and r9,r5,r11 - adc r4,r4,r10 @ T += Sigma0(a) - - ldr r10,[sp,#8+4] @ b.hi - orr r5,r5,r11 - ldr r11,[sp,#16+4] @ c.hi - and r5,r5,r12 - and r12,r6,r10 - orr r6,r6,r10 - orr r5,r5,r9 @ Maj(a,b,c).lo - and r6,r6,r11 - adds r5,r5,r3 - orr r6,r6,r12 @ Maj(a,b,c).hi - sub sp,sp,#8 - adc r6,r6,r4 @ h += T - tst r14,#1 - add r14,r14,#8 - ldreq r9,[sp,#184+0] - ldreq r10,[sp,#184+4] - beq .L16_79 - bic r14,r14,#1 - - ldr r3,[sp,#8+0] - ldr r4,[sp,#8+4] - ldr r9, [r0,#0+LO] - ldr r10, [r0,#0+HI] - ldr r11, [r0,#8+LO] - ldr r12, [r0,#8+HI] - adds r9,r5,r9 - str r9, [r0,#0+LO] - adc r10,r6,r10 - str r10, [r0,#0+HI] - adds r11,r3,r11 - str r11, [r0,#8+LO] - adc r12,r4,r12 - str r12, [r0,#8+HI] - - ldr r5,[sp,#16+0] - ldr r6,[sp,#16+4] - ldr r3,[sp,#24+0] - ldr r4,[sp,#24+4] - ldr r9, [r0,#16+LO] - ldr r10, [r0,#16+HI] - ldr r11, [r0,#24+LO] - ldr r12, [r0,#24+HI] - adds r9,r5,r9 - str r9, [r0,#16+LO] - adc r10,r6,r10 - str r10, [r0,#16+HI] - adds r11,r3,r11 - str r11, [r0,#24+LO] - adc r12,r4,r12 - str r12, [r0,#24+HI] - - ldr r3,[sp,#40+0] - ldr r4,[sp,#40+4] - ldr r9, [r0,#32+LO] - ldr r10, [r0,#32+HI] - ldr r11, [r0,#40+LO] - ldr r12, [r0,#40+HI] - adds r7,r7,r9 - str r7,[r0,#32+LO] - adc r8,r8,r10 - str r8,[r0,#32+HI] - adds r11,r3,r11 - str r11, [r0,#40+LO] - adc r12,r4,r12 - str r12, [r0,#40+HI] - - ldr r5,[sp,#48+0] - ldr r6,[sp,#48+4] - ldr r3,[sp,#56+0] - ldr r4,[sp,#56+4] - ldr r9, [r0,#48+LO] - ldr r10, [r0,#48+HI] - ldr r11, [r0,#56+LO] - ldr r12, [r0,#56+HI] - adds r9,r5,r9 - str r9, [r0,#48+LO] - adc r10,r6,r10 - str r10, [r0,#48+HI] - adds r11,r3,r11 - str r11, [r0,#56+LO] - adc r12,r4,r12 - str r12, [r0,#56+HI] - - add sp,sp,#640 - sub r14,r14,#640 - - teq r1,r2 - bne .Loop - - add sp,sp,#8*9 @ destroy frame -#if __ARM_ARCH__>=5 - ldmia sp!,{r4-r12,pc} -#else - ldmia sp!,{r4-r12,lr} - tst lr,#1 - moveq pc,lr @ be binary compatible with V4, yet - .word 0xe12fff1e @ interoperable with Thumb ISA:-) -#endif -#if __ARM_ARCH__>=7 -.fpu neon - -.align 4 -.LNEON: - dmb @ errata #451034 on early Cortex A8 - vstmdb sp!,{d8-d15} @ ABI specification says so - sub r3,r3,#672 @ K512 - vldmia r0,{d16-d23} @ load context -.Loop_neon: - vshr.u64 d24,d20,#14 @ 0 -#if 0<16 - vld1.64 {d0},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d20,#18 - vshr.u64 d26,d20,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d20,#50 - vsli.64 d25,d20,#46 - vsli.64 d26,d20,#23 -#if 0<16 && defined(__ARMEL__) - vrev64.8 d0,d0 -#endif - vadd.i64 d27,d28,d23 - veor d29,d21,d22 - veor d24,d25 - vand d29,d20 - veor d24,d26 @ Sigma1(e) - veor d29,d22 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d16,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d16,#34 - vshr.u64 d26,d16,#39 - vsli.64 d24,d16,#36 - vsli.64 d25,d16,#30 - vsli.64 d26,d16,#25 - vadd.i64 d27,d0 - vorr d30,d16,d18 - vand d29,d16,d18 - veor d23,d24,d25 - vand d30,d17 - veor d23,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d23,d27 - vadd.i64 d19,d27 - vadd.i64 d23,d30 - vshr.u64 d24,d19,#14 @ 1 -#if 1<16 - vld1.64 {d1},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d19,#18 - vshr.u64 d26,d19,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d19,#50 - vsli.64 d25,d19,#46 - vsli.64 d26,d19,#23 -#if 1<16 && defined(__ARMEL__) - vrev64.8 d1,d1 -#endif - vadd.i64 d27,d28,d22 - veor d29,d20,d21 - veor d24,d25 - vand d29,d19 - veor d24,d26 @ Sigma1(e) - veor d29,d21 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d23,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d23,#34 - vshr.u64 d26,d23,#39 - vsli.64 d24,d23,#36 - vsli.64 d25,d23,#30 - vsli.64 d26,d23,#25 - vadd.i64 d27,d1 - vorr d30,d23,d17 - vand d29,d23,d17 - veor d22,d24,d25 - vand d30,d16 - veor d22,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d22,d27 - vadd.i64 d18,d27 - vadd.i64 d22,d30 - vshr.u64 d24,d18,#14 @ 2 -#if 2<16 - vld1.64 {d2},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d18,#18 - vshr.u64 d26,d18,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d18,#50 - vsli.64 d25,d18,#46 - vsli.64 d26,d18,#23 -#if 2<16 && defined(__ARMEL__) - vrev64.8 d2,d2 -#endif - vadd.i64 d27,d28,d21 - veor d29,d19,d20 - veor d24,d25 - vand d29,d18 - veor d24,d26 @ Sigma1(e) - veor d29,d20 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d22,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d22,#34 - vshr.u64 d26,d22,#39 - vsli.64 d24,d22,#36 - vsli.64 d25,d22,#30 - vsli.64 d26,d22,#25 - vadd.i64 d27,d2 - vorr d30,d22,d16 - vand d29,d22,d16 - veor d21,d24,d25 - vand d30,d23 - veor d21,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d21,d27 - vadd.i64 d17,d27 - vadd.i64 d21,d30 - vshr.u64 d24,d17,#14 @ 3 -#if 3<16 - vld1.64 {d3},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d17,#18 - vshr.u64 d26,d17,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d17,#50 - vsli.64 d25,d17,#46 - vsli.64 d26,d17,#23 -#if 3<16 && defined(__ARMEL__) - vrev64.8 d3,d3 -#endif - vadd.i64 d27,d28,d20 - veor d29,d18,d19 - veor d24,d25 - vand d29,d17 - veor d24,d26 @ Sigma1(e) - veor d29,d19 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d21,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d21,#34 - vshr.u64 d26,d21,#39 - vsli.64 d24,d21,#36 - vsli.64 d25,d21,#30 - vsli.64 d26,d21,#25 - vadd.i64 d27,d3 - vorr d30,d21,d23 - vand d29,d21,d23 - veor d20,d24,d25 - vand d30,d22 - veor d20,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d20,d27 - vadd.i64 d16,d27 - vadd.i64 d20,d30 - vshr.u64 d24,d16,#14 @ 4 -#if 4<16 - vld1.64 {d4},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d16,#18 - vshr.u64 d26,d16,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d16,#50 - vsli.64 d25,d16,#46 - vsli.64 d26,d16,#23 -#if 4<16 && defined(__ARMEL__) - vrev64.8 d4,d4 -#endif - vadd.i64 d27,d28,d19 - veor d29,d17,d18 - veor d24,d25 - vand d29,d16 - veor d24,d26 @ Sigma1(e) - veor d29,d18 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d20,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d20,#34 - vshr.u64 d26,d20,#39 - vsli.64 d24,d20,#36 - vsli.64 d25,d20,#30 - vsli.64 d26,d20,#25 - vadd.i64 d27,d4 - vorr d30,d20,d22 - vand d29,d20,d22 - veor d19,d24,d25 - vand d30,d21 - veor d19,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d19,d27 - vadd.i64 d23,d27 - vadd.i64 d19,d30 - vshr.u64 d24,d23,#14 @ 5 -#if 5<16 - vld1.64 {d5},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d23,#18 - vshr.u64 d26,d23,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d23,#50 - vsli.64 d25,d23,#46 - vsli.64 d26,d23,#23 -#if 5<16 && defined(__ARMEL__) - vrev64.8 d5,d5 -#endif - vadd.i64 d27,d28,d18 - veor d29,d16,d17 - veor d24,d25 - vand d29,d23 - veor d24,d26 @ Sigma1(e) - veor d29,d17 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d19,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d19,#34 - vshr.u64 d26,d19,#39 - vsli.64 d24,d19,#36 - vsli.64 d25,d19,#30 - vsli.64 d26,d19,#25 - vadd.i64 d27,d5 - vorr d30,d19,d21 - vand d29,d19,d21 - veor d18,d24,d25 - vand d30,d20 - veor d18,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d18,d27 - vadd.i64 d22,d27 - vadd.i64 d18,d30 - vshr.u64 d24,d22,#14 @ 6 -#if 6<16 - vld1.64 {d6},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d22,#18 - vshr.u64 d26,d22,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d22,#50 - vsli.64 d25,d22,#46 - vsli.64 d26,d22,#23 -#if 6<16 && defined(__ARMEL__) - vrev64.8 d6,d6 -#endif - vadd.i64 d27,d28,d17 - veor d29,d23,d16 - veor d24,d25 - vand d29,d22 - veor d24,d26 @ Sigma1(e) - veor d29,d16 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d18,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d18,#34 - vshr.u64 d26,d18,#39 - vsli.64 d24,d18,#36 - vsli.64 d25,d18,#30 - vsli.64 d26,d18,#25 - vadd.i64 d27,d6 - vorr d30,d18,d20 - vand d29,d18,d20 - veor d17,d24,d25 - vand d30,d19 - veor d17,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d17,d27 - vadd.i64 d21,d27 - vadd.i64 d17,d30 - vshr.u64 d24,d21,#14 @ 7 -#if 7<16 - vld1.64 {d7},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d21,#18 - vshr.u64 d26,d21,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d21,#50 - vsli.64 d25,d21,#46 - vsli.64 d26,d21,#23 -#if 7<16 && defined(__ARMEL__) - vrev64.8 d7,d7 -#endif - vadd.i64 d27,d28,d16 - veor d29,d22,d23 - veor d24,d25 - vand d29,d21 - veor d24,d26 @ Sigma1(e) - veor d29,d23 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d17,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d17,#34 - vshr.u64 d26,d17,#39 - vsli.64 d24,d17,#36 - vsli.64 d25,d17,#30 - vsli.64 d26,d17,#25 - vadd.i64 d27,d7 - vorr d30,d17,d19 - vand d29,d17,d19 - veor d16,d24,d25 - vand d30,d18 - veor d16,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d16,d27 - vadd.i64 d20,d27 - vadd.i64 d16,d30 - vshr.u64 d24,d20,#14 @ 8 -#if 8<16 - vld1.64 {d8},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d20,#18 - vshr.u64 d26,d20,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d20,#50 - vsli.64 d25,d20,#46 - vsli.64 d26,d20,#23 -#if 8<16 && defined(__ARMEL__) - vrev64.8 d8,d8 -#endif - vadd.i64 d27,d28,d23 - veor d29,d21,d22 - veor d24,d25 - vand d29,d20 - veor d24,d26 @ Sigma1(e) - veor d29,d22 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d16,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d16,#34 - vshr.u64 d26,d16,#39 - vsli.64 d24,d16,#36 - vsli.64 d25,d16,#30 - vsli.64 d26,d16,#25 - vadd.i64 d27,d8 - vorr d30,d16,d18 - vand d29,d16,d18 - veor d23,d24,d25 - vand d30,d17 - veor d23,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d23,d27 - vadd.i64 d19,d27 - vadd.i64 d23,d30 - vshr.u64 d24,d19,#14 @ 9 -#if 9<16 - vld1.64 {d9},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d19,#18 - vshr.u64 d26,d19,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d19,#50 - vsli.64 d25,d19,#46 - vsli.64 d26,d19,#23 -#if 9<16 && defined(__ARMEL__) - vrev64.8 d9,d9 -#endif - vadd.i64 d27,d28,d22 - veor d29,d20,d21 - veor d24,d25 - vand d29,d19 - veor d24,d26 @ Sigma1(e) - veor d29,d21 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d23,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d23,#34 - vshr.u64 d26,d23,#39 - vsli.64 d24,d23,#36 - vsli.64 d25,d23,#30 - vsli.64 d26,d23,#25 - vadd.i64 d27,d9 - vorr d30,d23,d17 - vand d29,d23,d17 - veor d22,d24,d25 - vand d30,d16 - veor d22,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d22,d27 - vadd.i64 d18,d27 - vadd.i64 d22,d30 - vshr.u64 d24,d18,#14 @ 10 -#if 10<16 - vld1.64 {d10},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d18,#18 - vshr.u64 d26,d18,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d18,#50 - vsli.64 d25,d18,#46 - vsli.64 d26,d18,#23 -#if 10<16 && defined(__ARMEL__) - vrev64.8 d10,d10 -#endif - vadd.i64 d27,d28,d21 - veor d29,d19,d20 - veor d24,d25 - vand d29,d18 - veor d24,d26 @ Sigma1(e) - veor d29,d20 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d22,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d22,#34 - vshr.u64 d26,d22,#39 - vsli.64 d24,d22,#36 - vsli.64 d25,d22,#30 - vsli.64 d26,d22,#25 - vadd.i64 d27,d10 - vorr d30,d22,d16 - vand d29,d22,d16 - veor d21,d24,d25 - vand d30,d23 - veor d21,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d21,d27 - vadd.i64 d17,d27 - vadd.i64 d21,d30 - vshr.u64 d24,d17,#14 @ 11 -#if 11<16 - vld1.64 {d11},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d17,#18 - vshr.u64 d26,d17,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d17,#50 - vsli.64 d25,d17,#46 - vsli.64 d26,d17,#23 -#if 11<16 && defined(__ARMEL__) - vrev64.8 d11,d11 -#endif - vadd.i64 d27,d28,d20 - veor d29,d18,d19 - veor d24,d25 - vand d29,d17 - veor d24,d26 @ Sigma1(e) - veor d29,d19 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d21,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d21,#34 - vshr.u64 d26,d21,#39 - vsli.64 d24,d21,#36 - vsli.64 d25,d21,#30 - vsli.64 d26,d21,#25 - vadd.i64 d27,d11 - vorr d30,d21,d23 - vand d29,d21,d23 - veor d20,d24,d25 - vand d30,d22 - veor d20,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d20,d27 - vadd.i64 d16,d27 - vadd.i64 d20,d30 - vshr.u64 d24,d16,#14 @ 12 -#if 12<16 - vld1.64 {d12},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d16,#18 - vshr.u64 d26,d16,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d16,#50 - vsli.64 d25,d16,#46 - vsli.64 d26,d16,#23 -#if 12<16 && defined(__ARMEL__) - vrev64.8 d12,d12 -#endif - vadd.i64 d27,d28,d19 - veor d29,d17,d18 - veor d24,d25 - vand d29,d16 - veor d24,d26 @ Sigma1(e) - veor d29,d18 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d20,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d20,#34 - vshr.u64 d26,d20,#39 - vsli.64 d24,d20,#36 - vsli.64 d25,d20,#30 - vsli.64 d26,d20,#25 - vadd.i64 d27,d12 - vorr d30,d20,d22 - vand d29,d20,d22 - veor d19,d24,d25 - vand d30,d21 - veor d19,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d19,d27 - vadd.i64 d23,d27 - vadd.i64 d19,d30 - vshr.u64 d24,d23,#14 @ 13 -#if 13<16 - vld1.64 {d13},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d23,#18 - vshr.u64 d26,d23,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d23,#50 - vsli.64 d25,d23,#46 - vsli.64 d26,d23,#23 -#if 13<16 && defined(__ARMEL__) - vrev64.8 d13,d13 -#endif - vadd.i64 d27,d28,d18 - veor d29,d16,d17 - veor d24,d25 - vand d29,d23 - veor d24,d26 @ Sigma1(e) - veor d29,d17 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d19,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d19,#34 - vshr.u64 d26,d19,#39 - vsli.64 d24,d19,#36 - vsli.64 d25,d19,#30 - vsli.64 d26,d19,#25 - vadd.i64 d27,d13 - vorr d30,d19,d21 - vand d29,d19,d21 - veor d18,d24,d25 - vand d30,d20 - veor d18,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d18,d27 - vadd.i64 d22,d27 - vadd.i64 d18,d30 - vshr.u64 d24,d22,#14 @ 14 -#if 14<16 - vld1.64 {d14},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d22,#18 - vshr.u64 d26,d22,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d22,#50 - vsli.64 d25,d22,#46 - vsli.64 d26,d22,#23 -#if 14<16 && defined(__ARMEL__) - vrev64.8 d14,d14 -#endif - vadd.i64 d27,d28,d17 - veor d29,d23,d16 - veor d24,d25 - vand d29,d22 - veor d24,d26 @ Sigma1(e) - veor d29,d16 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d18,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d18,#34 - vshr.u64 d26,d18,#39 - vsli.64 d24,d18,#36 - vsli.64 d25,d18,#30 - vsli.64 d26,d18,#25 - vadd.i64 d27,d14 - vorr d30,d18,d20 - vand d29,d18,d20 - veor d17,d24,d25 - vand d30,d19 - veor d17,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d17,d27 - vadd.i64 d21,d27 - vadd.i64 d17,d30 - vshr.u64 d24,d21,#14 @ 15 -#if 15<16 - vld1.64 {d15},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d21,#18 - vshr.u64 d26,d21,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d21,#50 - vsli.64 d25,d21,#46 - vsli.64 d26,d21,#23 -#if 15<16 && defined(__ARMEL__) - vrev64.8 d15,d15 -#endif - vadd.i64 d27,d28,d16 - veor d29,d22,d23 - veor d24,d25 - vand d29,d21 - veor d24,d26 @ Sigma1(e) - veor d29,d23 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d17,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d17,#34 - vshr.u64 d26,d17,#39 - vsli.64 d24,d17,#36 - vsli.64 d25,d17,#30 - vsli.64 d26,d17,#25 - vadd.i64 d27,d15 - vorr d30,d17,d19 - vand d29,d17,d19 - veor d16,d24,d25 - vand d30,d18 - veor d16,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d16,d27 - vadd.i64 d20,d27 - vadd.i64 d16,d30 - mov r12,#4 -.L16_79_neon: - subs r12,#1 - vshr.u64 q12,q7,#19 - vshr.u64 q13,q7,#61 - vshr.u64 q15,q7,#6 - vsli.64 q12,q7,#45 - vext.8 q14,q0,q1,#8 @ X[i+1] - vsli.64 q13,q7,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q0,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q4,q5,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d20,#14 @ from NEON_00_15 - vadd.i64 q0,q14 - vshr.u64 d25,d20,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d20,#41 @ from NEON_00_15 - vadd.i64 q0,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d20,#50 - vsli.64 d25,d20,#46 - vsli.64 d26,d20,#23 -#if 16<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d23 - veor d29,d21,d22 - veor d24,d25 - vand d29,d20 - veor d24,d26 @ Sigma1(e) - veor d29,d22 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d16,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d16,#34 - vshr.u64 d26,d16,#39 - vsli.64 d24,d16,#36 - vsli.64 d25,d16,#30 - vsli.64 d26,d16,#25 - vadd.i64 d27,d0 - vorr d30,d16,d18 - vand d29,d16,d18 - veor d23,d24,d25 - vand d30,d17 - veor d23,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d23,d27 - vadd.i64 d19,d27 - vadd.i64 d23,d30 - vshr.u64 d24,d19,#14 @ 17 -#if 17<16 - vld1.64 {d1},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d19,#18 - vshr.u64 d26,d19,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d19,#50 - vsli.64 d25,d19,#46 - vsli.64 d26,d19,#23 -#if 17<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d22 - veor d29,d20,d21 - veor d24,d25 - vand d29,d19 - veor d24,d26 @ Sigma1(e) - veor d29,d21 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d23,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d23,#34 - vshr.u64 d26,d23,#39 - vsli.64 d24,d23,#36 - vsli.64 d25,d23,#30 - vsli.64 d26,d23,#25 - vadd.i64 d27,d1 - vorr d30,d23,d17 - vand d29,d23,d17 - veor d22,d24,d25 - vand d30,d16 - veor d22,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d22,d27 - vadd.i64 d18,d27 - vadd.i64 d22,d30 - vshr.u64 q12,q0,#19 - vshr.u64 q13,q0,#61 - vshr.u64 q15,q0,#6 - vsli.64 q12,q0,#45 - vext.8 q14,q1,q2,#8 @ X[i+1] - vsli.64 q13,q0,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q1,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q5,q6,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d18,#14 @ from NEON_00_15 - vadd.i64 q1,q14 - vshr.u64 d25,d18,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d18,#41 @ from NEON_00_15 - vadd.i64 q1,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d18,#50 - vsli.64 d25,d18,#46 - vsli.64 d26,d18,#23 -#if 18<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d21 - veor d29,d19,d20 - veor d24,d25 - vand d29,d18 - veor d24,d26 @ Sigma1(e) - veor d29,d20 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d22,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d22,#34 - vshr.u64 d26,d22,#39 - vsli.64 d24,d22,#36 - vsli.64 d25,d22,#30 - vsli.64 d26,d22,#25 - vadd.i64 d27,d2 - vorr d30,d22,d16 - vand d29,d22,d16 - veor d21,d24,d25 - vand d30,d23 - veor d21,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d21,d27 - vadd.i64 d17,d27 - vadd.i64 d21,d30 - vshr.u64 d24,d17,#14 @ 19 -#if 19<16 - vld1.64 {d3},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d17,#18 - vshr.u64 d26,d17,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d17,#50 - vsli.64 d25,d17,#46 - vsli.64 d26,d17,#23 -#if 19<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d20 - veor d29,d18,d19 - veor d24,d25 - vand d29,d17 - veor d24,d26 @ Sigma1(e) - veor d29,d19 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d21,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d21,#34 - vshr.u64 d26,d21,#39 - vsli.64 d24,d21,#36 - vsli.64 d25,d21,#30 - vsli.64 d26,d21,#25 - vadd.i64 d27,d3 - vorr d30,d21,d23 - vand d29,d21,d23 - veor d20,d24,d25 - vand d30,d22 - veor d20,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d20,d27 - vadd.i64 d16,d27 - vadd.i64 d20,d30 - vshr.u64 q12,q1,#19 - vshr.u64 q13,q1,#61 - vshr.u64 q15,q1,#6 - vsli.64 q12,q1,#45 - vext.8 q14,q2,q3,#8 @ X[i+1] - vsli.64 q13,q1,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q2,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q6,q7,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d16,#14 @ from NEON_00_15 - vadd.i64 q2,q14 - vshr.u64 d25,d16,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d16,#41 @ from NEON_00_15 - vadd.i64 q2,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d16,#50 - vsli.64 d25,d16,#46 - vsli.64 d26,d16,#23 -#if 20<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d19 - veor d29,d17,d18 - veor d24,d25 - vand d29,d16 - veor d24,d26 @ Sigma1(e) - veor d29,d18 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d20,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d20,#34 - vshr.u64 d26,d20,#39 - vsli.64 d24,d20,#36 - vsli.64 d25,d20,#30 - vsli.64 d26,d20,#25 - vadd.i64 d27,d4 - vorr d30,d20,d22 - vand d29,d20,d22 - veor d19,d24,d25 - vand d30,d21 - veor d19,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d19,d27 - vadd.i64 d23,d27 - vadd.i64 d19,d30 - vshr.u64 d24,d23,#14 @ 21 -#if 21<16 - vld1.64 {d5},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d23,#18 - vshr.u64 d26,d23,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d23,#50 - vsli.64 d25,d23,#46 - vsli.64 d26,d23,#23 -#if 21<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d18 - veor d29,d16,d17 - veor d24,d25 - vand d29,d23 - veor d24,d26 @ Sigma1(e) - veor d29,d17 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d19,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d19,#34 - vshr.u64 d26,d19,#39 - vsli.64 d24,d19,#36 - vsli.64 d25,d19,#30 - vsli.64 d26,d19,#25 - vadd.i64 d27,d5 - vorr d30,d19,d21 - vand d29,d19,d21 - veor d18,d24,d25 - vand d30,d20 - veor d18,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d18,d27 - vadd.i64 d22,d27 - vadd.i64 d18,d30 - vshr.u64 q12,q2,#19 - vshr.u64 q13,q2,#61 - vshr.u64 q15,q2,#6 - vsli.64 q12,q2,#45 - vext.8 q14,q3,q4,#8 @ X[i+1] - vsli.64 q13,q2,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q3,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q7,q0,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d22,#14 @ from NEON_00_15 - vadd.i64 q3,q14 - vshr.u64 d25,d22,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d22,#41 @ from NEON_00_15 - vadd.i64 q3,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d22,#50 - vsli.64 d25,d22,#46 - vsli.64 d26,d22,#23 -#if 22<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d17 - veor d29,d23,d16 - veor d24,d25 - vand d29,d22 - veor d24,d26 @ Sigma1(e) - veor d29,d16 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d18,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d18,#34 - vshr.u64 d26,d18,#39 - vsli.64 d24,d18,#36 - vsli.64 d25,d18,#30 - vsli.64 d26,d18,#25 - vadd.i64 d27,d6 - vorr d30,d18,d20 - vand d29,d18,d20 - veor d17,d24,d25 - vand d30,d19 - veor d17,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d17,d27 - vadd.i64 d21,d27 - vadd.i64 d17,d30 - vshr.u64 d24,d21,#14 @ 23 -#if 23<16 - vld1.64 {d7},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d21,#18 - vshr.u64 d26,d21,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d21,#50 - vsli.64 d25,d21,#46 - vsli.64 d26,d21,#23 -#if 23<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d16 - veor d29,d22,d23 - veor d24,d25 - vand d29,d21 - veor d24,d26 @ Sigma1(e) - veor d29,d23 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d17,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d17,#34 - vshr.u64 d26,d17,#39 - vsli.64 d24,d17,#36 - vsli.64 d25,d17,#30 - vsli.64 d26,d17,#25 - vadd.i64 d27,d7 - vorr d30,d17,d19 - vand d29,d17,d19 - veor d16,d24,d25 - vand d30,d18 - veor d16,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d16,d27 - vadd.i64 d20,d27 - vadd.i64 d16,d30 - vshr.u64 q12,q3,#19 - vshr.u64 q13,q3,#61 - vshr.u64 q15,q3,#6 - vsli.64 q12,q3,#45 - vext.8 q14,q4,q5,#8 @ X[i+1] - vsli.64 q13,q3,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q4,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q0,q1,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d20,#14 @ from NEON_00_15 - vadd.i64 q4,q14 - vshr.u64 d25,d20,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d20,#41 @ from NEON_00_15 - vadd.i64 q4,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d20,#50 - vsli.64 d25,d20,#46 - vsli.64 d26,d20,#23 -#if 24<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d23 - veor d29,d21,d22 - veor d24,d25 - vand d29,d20 - veor d24,d26 @ Sigma1(e) - veor d29,d22 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d16,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d16,#34 - vshr.u64 d26,d16,#39 - vsli.64 d24,d16,#36 - vsli.64 d25,d16,#30 - vsli.64 d26,d16,#25 - vadd.i64 d27,d8 - vorr d30,d16,d18 - vand d29,d16,d18 - veor d23,d24,d25 - vand d30,d17 - veor d23,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d23,d27 - vadd.i64 d19,d27 - vadd.i64 d23,d30 - vshr.u64 d24,d19,#14 @ 25 -#if 25<16 - vld1.64 {d9},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d19,#18 - vshr.u64 d26,d19,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d19,#50 - vsli.64 d25,d19,#46 - vsli.64 d26,d19,#23 -#if 25<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d22 - veor d29,d20,d21 - veor d24,d25 - vand d29,d19 - veor d24,d26 @ Sigma1(e) - veor d29,d21 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d23,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d23,#34 - vshr.u64 d26,d23,#39 - vsli.64 d24,d23,#36 - vsli.64 d25,d23,#30 - vsli.64 d26,d23,#25 - vadd.i64 d27,d9 - vorr d30,d23,d17 - vand d29,d23,d17 - veor d22,d24,d25 - vand d30,d16 - veor d22,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d22,d27 - vadd.i64 d18,d27 - vadd.i64 d22,d30 - vshr.u64 q12,q4,#19 - vshr.u64 q13,q4,#61 - vshr.u64 q15,q4,#6 - vsli.64 q12,q4,#45 - vext.8 q14,q5,q6,#8 @ X[i+1] - vsli.64 q13,q4,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q5,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q1,q2,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d18,#14 @ from NEON_00_15 - vadd.i64 q5,q14 - vshr.u64 d25,d18,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d18,#41 @ from NEON_00_15 - vadd.i64 q5,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d18,#50 - vsli.64 d25,d18,#46 - vsli.64 d26,d18,#23 -#if 26<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d21 - veor d29,d19,d20 - veor d24,d25 - vand d29,d18 - veor d24,d26 @ Sigma1(e) - veor d29,d20 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d22,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d22,#34 - vshr.u64 d26,d22,#39 - vsli.64 d24,d22,#36 - vsli.64 d25,d22,#30 - vsli.64 d26,d22,#25 - vadd.i64 d27,d10 - vorr d30,d22,d16 - vand d29,d22,d16 - veor d21,d24,d25 - vand d30,d23 - veor d21,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d21,d27 - vadd.i64 d17,d27 - vadd.i64 d21,d30 - vshr.u64 d24,d17,#14 @ 27 -#if 27<16 - vld1.64 {d11},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d17,#18 - vshr.u64 d26,d17,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d17,#50 - vsli.64 d25,d17,#46 - vsli.64 d26,d17,#23 -#if 27<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d20 - veor d29,d18,d19 - veor d24,d25 - vand d29,d17 - veor d24,d26 @ Sigma1(e) - veor d29,d19 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d21,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d21,#34 - vshr.u64 d26,d21,#39 - vsli.64 d24,d21,#36 - vsli.64 d25,d21,#30 - vsli.64 d26,d21,#25 - vadd.i64 d27,d11 - vorr d30,d21,d23 - vand d29,d21,d23 - veor d20,d24,d25 - vand d30,d22 - veor d20,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d20,d27 - vadd.i64 d16,d27 - vadd.i64 d20,d30 - vshr.u64 q12,q5,#19 - vshr.u64 q13,q5,#61 - vshr.u64 q15,q5,#6 - vsli.64 q12,q5,#45 - vext.8 q14,q6,q7,#8 @ X[i+1] - vsli.64 q13,q5,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q6,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q2,q3,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d16,#14 @ from NEON_00_15 - vadd.i64 q6,q14 - vshr.u64 d25,d16,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d16,#41 @ from NEON_00_15 - vadd.i64 q6,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d16,#50 - vsli.64 d25,d16,#46 - vsli.64 d26,d16,#23 -#if 28<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d19 - veor d29,d17,d18 - veor d24,d25 - vand d29,d16 - veor d24,d26 @ Sigma1(e) - veor d29,d18 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d20,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d20,#34 - vshr.u64 d26,d20,#39 - vsli.64 d24,d20,#36 - vsli.64 d25,d20,#30 - vsli.64 d26,d20,#25 - vadd.i64 d27,d12 - vorr d30,d20,d22 - vand d29,d20,d22 - veor d19,d24,d25 - vand d30,d21 - veor d19,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d19,d27 - vadd.i64 d23,d27 - vadd.i64 d19,d30 - vshr.u64 d24,d23,#14 @ 29 -#if 29<16 - vld1.64 {d13},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d23,#18 - vshr.u64 d26,d23,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d23,#50 - vsli.64 d25,d23,#46 - vsli.64 d26,d23,#23 -#if 29<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d18 - veor d29,d16,d17 - veor d24,d25 - vand d29,d23 - veor d24,d26 @ Sigma1(e) - veor d29,d17 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d19,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d19,#34 - vshr.u64 d26,d19,#39 - vsli.64 d24,d19,#36 - vsli.64 d25,d19,#30 - vsli.64 d26,d19,#25 - vadd.i64 d27,d13 - vorr d30,d19,d21 - vand d29,d19,d21 - veor d18,d24,d25 - vand d30,d20 - veor d18,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d18,d27 - vadd.i64 d22,d27 - vadd.i64 d18,d30 - vshr.u64 q12,q6,#19 - vshr.u64 q13,q6,#61 - vshr.u64 q15,q6,#6 - vsli.64 q12,q6,#45 - vext.8 q14,q7,q0,#8 @ X[i+1] - vsli.64 q13,q6,#3 - veor q15,q12 - vshr.u64 q12,q14,#1 - veor q15,q13 @ sigma1(X[i+14]) - vshr.u64 q13,q14,#8 - vadd.i64 q7,q15 - vshr.u64 q15,q14,#7 - vsli.64 q12,q14,#63 - vsli.64 q13,q14,#56 - vext.8 q14,q3,q4,#8 @ X[i+9] - veor q15,q12 - vshr.u64 d24,d22,#14 @ from NEON_00_15 - vadd.i64 q7,q14 - vshr.u64 d25,d22,#18 @ from NEON_00_15 - veor q15,q13 @ sigma0(X[i+1]) - vshr.u64 d26,d22,#41 @ from NEON_00_15 - vadd.i64 q7,q15 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d22,#50 - vsli.64 d25,d22,#46 - vsli.64 d26,d22,#23 -#if 30<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d17 - veor d29,d23,d16 - veor d24,d25 - vand d29,d22 - veor d24,d26 @ Sigma1(e) - veor d29,d16 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d18,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d18,#34 - vshr.u64 d26,d18,#39 - vsli.64 d24,d18,#36 - vsli.64 d25,d18,#30 - vsli.64 d26,d18,#25 - vadd.i64 d27,d14 - vorr d30,d18,d20 - vand d29,d18,d20 - veor d17,d24,d25 - vand d30,d19 - veor d17,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d17,d27 - vadd.i64 d21,d27 - vadd.i64 d17,d30 - vshr.u64 d24,d21,#14 @ 31 -#if 31<16 - vld1.64 {d15},[r1]! @ handles unaligned -#endif - vshr.u64 d25,d21,#18 - vshr.u64 d26,d21,#41 - vld1.64 {d28},[r3,:64]! @ K[i++] - vsli.64 d24,d21,#50 - vsli.64 d25,d21,#46 - vsli.64 d26,d21,#23 -#if 31<16 && defined(__ARMEL__) - vrev64.8 , -#endif - vadd.i64 d27,d28,d16 - veor d29,d22,d23 - veor d24,d25 - vand d29,d21 - veor d24,d26 @ Sigma1(e) - veor d29,d23 @ Ch(e,f,g) - vadd.i64 d27,d24 - vshr.u64 d24,d17,#28 - vadd.i64 d27,d29 - vshr.u64 d25,d17,#34 - vshr.u64 d26,d17,#39 - vsli.64 d24,d17,#36 - vsli.64 d25,d17,#30 - vsli.64 d26,d17,#25 - vadd.i64 d27,d15 - vorr d30,d17,d19 - vand d29,d17,d19 - veor d16,d24,d25 - vand d30,d18 - veor d16,d26 @ Sigma0(a) - vorr d30,d29 @ Maj(a,b,c) - vadd.i64 d16,d27 - vadd.i64 d20,d27 - vadd.i64 d16,d30 - bne .L16_79_neon - - vldmia r0,{d24-d31} @ load context to temp - vadd.i64 q8,q12 @ vectorized accumulate - vadd.i64 q9,q13 - vadd.i64 q10,q14 - vadd.i64 q11,q15 - vstmia r0,{d16-d23} @ save context - teq r1,r2 - sub r3,#640 @ rewind K512 - bne .Loop_neon - - vldmia sp!,{d8-d15} @ epilogue - bx lr @ .word 0xe12fff1e -#endif -.size sha512_block_data_order,.-sha512_block_data_order -.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>" -.align 2 -.comm OPENSSL_armcap_P,4,4 diff --git a/app/openssl/crypto/sha/asm/sha512-armv4.pl b/app/openssl/crypto/sha/asm/sha512-armv4.pl deleted file mode 100644 index 71aa9356..00000000 --- a/app/openssl/crypto/sha/asm/sha512-armv4.pl +++ /dev/null @@ -1,583 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA512 block procedure for ARMv4. September 2007. - -# This code is ~4.5 (four and a half) times faster than code generated -# by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue -# Xscale PXA250 core]. -# -# July 2010. -# -# Rescheduling for dual-issue pipeline resulted in 6% improvement on -# Cortex A8 core and ~40 cycles per processed byte. - -# February 2011. -# -# Profiler-assisted and platform-specific optimization resulted in 7% -# improvement on Coxtex A8 core and ~38 cycles per byte. - -# March 2011. -# -# Add NEON implementation. On Cortex A8 it was measured to process -# one byte in 25.5 cycles or 47% faster than integer-only code. - -# Byte order [in]dependence. ========================================= -# -# Originally caller was expected to maintain specific *dword* order in -# h[0-7], namely with most significant dword at *lower* address, which -# was reflected in below two parameters as 0 and 4. Now caller is -# expected to maintain native byte order for whole 64-bit values. -$hi="HI"; -$lo="LO"; -# ==================================================================== - -while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} -open STDOUT,">$output"; - -$ctx="r0"; # parameter block -$inp="r1"; -$len="r2"; - -$Tlo="r3"; -$Thi="r4"; -$Alo="r5"; -$Ahi="r6"; -$Elo="r7"; -$Ehi="r8"; -$t0="r9"; -$t1="r10"; -$t2="r11"; -$t3="r12"; -############ r13 is stack pointer -$Ktbl="r14"; -############ r15 is program counter - -$Aoff=8*0; -$Boff=8*1; -$Coff=8*2; -$Doff=8*3; -$Eoff=8*4; -$Foff=8*5; -$Goff=8*6; -$Hoff=8*7; -$Xoff=8*8; - -sub BODY_00_15() { -my $magic = shift; -$code.=<<___; - @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41)) - @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23 - @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23 - mov $t0,$Elo,lsr#14 - str $Tlo,[sp,#$Xoff+0] - mov $t1,$Ehi,lsr#14 - str $Thi,[sp,#$Xoff+4] - eor $t0,$t0,$Ehi,lsl#18 - ldr $t2,[sp,#$Hoff+0] @ h.lo - eor $t1,$t1,$Elo,lsl#18 - ldr $t3,[sp,#$Hoff+4] @ h.hi - eor $t0,$t0,$Elo,lsr#18 - eor $t1,$t1,$Ehi,lsr#18 - eor $t0,$t0,$Ehi,lsl#14 - eor $t1,$t1,$Elo,lsl#14 - eor $t0,$t0,$Ehi,lsr#9 - eor $t1,$t1,$Elo,lsr#9 - eor $t0,$t0,$Elo,lsl#23 - eor $t1,$t1,$Ehi,lsl#23 @ Sigma1(e) - adds $Tlo,$Tlo,$t0 - ldr $t0,[sp,#$Foff+0] @ f.lo - adc $Thi,$Thi,$t1 @ T += Sigma1(e) - ldr $t1,[sp,#$Foff+4] @ f.hi - adds $Tlo,$Tlo,$t2 - ldr $t2,[sp,#$Goff+0] @ g.lo - adc $Thi,$Thi,$t3 @ T += h - ldr $t3,[sp,#$Goff+4] @ g.hi - - eor $t0,$t0,$t2 - str $Elo,[sp,#$Eoff+0] - eor $t1,$t1,$t3 - str $Ehi,[sp,#$Eoff+4] - and $t0,$t0,$Elo - str $Alo,[sp,#$Aoff+0] - and $t1,$t1,$Ehi - str $Ahi,[sp,#$Aoff+4] - eor $t0,$t0,$t2 - ldr $t2,[$Ktbl,#$lo] @ K[i].lo - eor $t1,$t1,$t3 @ Ch(e,f,g) - ldr $t3,[$Ktbl,#$hi] @ K[i].hi - - adds $Tlo,$Tlo,$t0 - ldr $Elo,[sp,#$Doff+0] @ d.lo - adc $Thi,$Thi,$t1 @ T += Ch(e,f,g) - ldr $Ehi,[sp,#$Doff+4] @ d.hi - adds $Tlo,$Tlo,$t2 - and $t0,$t2,#0xff - adc $Thi,$Thi,$t3 @ T += K[i] - adds $Elo,$Elo,$Tlo - ldr $t2,[sp,#$Boff+0] @ b.lo - adc $Ehi,$Ehi,$Thi @ d += T - teq $t0,#$magic - - ldr $t3,[sp,#$Coff+0] @ c.lo - orreq $Ktbl,$Ktbl,#1 - @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39)) - @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25 - @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25 - mov $t0,$Alo,lsr#28 - mov $t1,$Ahi,lsr#28 - eor $t0,$t0,$Ahi,lsl#4 - eor $t1,$t1,$Alo,lsl#4 - eor $t0,$t0,$Ahi,lsr#2 - eor $t1,$t1,$Alo,lsr#2 - eor $t0,$t0,$Alo,lsl#30 - eor $t1,$t1,$Ahi,lsl#30 - eor $t0,$t0,$Ahi,lsr#7 - eor $t1,$t1,$Alo,lsr#7 - eor $t0,$t0,$Alo,lsl#25 - eor $t1,$t1,$Ahi,lsl#25 @ Sigma0(a) - adds $Tlo,$Tlo,$t0 - and $t0,$Alo,$t2 - adc $Thi,$Thi,$t1 @ T += Sigma0(a) - - ldr $t1,[sp,#$Boff+4] @ b.hi - orr $Alo,$Alo,$t2 - ldr $t2,[sp,#$Coff+4] @ c.hi - and $Alo,$Alo,$t3 - and $t3,$Ahi,$t1 - orr $Ahi,$Ahi,$t1 - orr $Alo,$Alo,$t0 @ Maj(a,b,c).lo - and $Ahi,$Ahi,$t2 - adds $Alo,$Alo,$Tlo - orr $Ahi,$Ahi,$t3 @ Maj(a,b,c).hi - sub sp,sp,#8 - adc $Ahi,$Ahi,$Thi @ h += T - tst $Ktbl,#1 - add $Ktbl,$Ktbl,#8 -___ -} -$code=<<___; -#include "arm_arch.h" -#ifdef __ARMEL__ -# define LO 0 -# define HI 4 -# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1 -#else -# define HI 0 -# define LO 4 -# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1 -#endif - -.text -.code 32 -.type K512,%object -.align 5 -K512: -WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd) -WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc) -WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019) -WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118) -WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe) -WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2) -WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1) -WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694) -WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3) -WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65) -WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483) -WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5) -WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210) -WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4) -WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725) -WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70) -WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926) -WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df) -WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8) -WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b) -WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001) -WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30) -WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910) -WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8) -WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53) -WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8) -WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb) -WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3) -WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60) -WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec) -WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9) -WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b) -WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207) -WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178) -WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6) -WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b) -WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493) -WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c) -WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a) -WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) -.size K512,.-K512 -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-sha512_block_data_order -.skip 32-4 - -.global sha512_block_data_order -.type sha512_block_data_order,%function -sha512_block_data_order: - sub r3,pc,#8 @ sha512_block_data_order - add $len,$inp,$len,lsl#7 @ len to point at the end of inp -#if __ARM_ARCH__>=7 - ldr r12,.LOPENSSL_armcap - ldr r12,[r3,r12] @ OPENSSL_armcap_P - tst r12,#1 - bne .LNEON -#endif - stmdb sp!,{r4-r12,lr} - sub $Ktbl,r3,#672 @ K512 - sub sp,sp,#9*8 - - ldr $Elo,[$ctx,#$Eoff+$lo] - ldr $Ehi,[$ctx,#$Eoff+$hi] - ldr $t0, [$ctx,#$Goff+$lo] - ldr $t1, [$ctx,#$Goff+$hi] - ldr $t2, [$ctx,#$Hoff+$lo] - ldr $t3, [$ctx,#$Hoff+$hi] -.Loop: - str $t0, [sp,#$Goff+0] - str $t1, [sp,#$Goff+4] - str $t2, [sp,#$Hoff+0] - str $t3, [sp,#$Hoff+4] - ldr $Alo,[$ctx,#$Aoff+$lo] - ldr $Ahi,[$ctx,#$Aoff+$hi] - ldr $Tlo,[$ctx,#$Boff+$lo] - ldr $Thi,[$ctx,#$Boff+$hi] - ldr $t0, [$ctx,#$Coff+$lo] - ldr $t1, [$ctx,#$Coff+$hi] - ldr $t2, [$ctx,#$Doff+$lo] - ldr $t3, [$ctx,#$Doff+$hi] - str $Tlo,[sp,#$Boff+0] - str $Thi,[sp,#$Boff+4] - str $t0, [sp,#$Coff+0] - str $t1, [sp,#$Coff+4] - str $t2, [sp,#$Doff+0] - str $t3, [sp,#$Doff+4] - ldr $Tlo,[$ctx,#$Foff+$lo] - ldr $Thi,[$ctx,#$Foff+$hi] - str $Tlo,[sp,#$Foff+0] - str $Thi,[sp,#$Foff+4] - -.L00_15: -#if __ARM_ARCH__<7 - ldrb $Tlo,[$inp,#7] - ldrb $t0, [$inp,#6] - ldrb $t1, [$inp,#5] - ldrb $t2, [$inp,#4] - ldrb $Thi,[$inp,#3] - ldrb $t3, [$inp,#2] - orr $Tlo,$Tlo,$t0,lsl#8 - ldrb $t0, [$inp,#1] - orr $Tlo,$Tlo,$t1,lsl#16 - ldrb $t1, [$inp],#8 - orr $Tlo,$Tlo,$t2,lsl#24 - orr $Thi,$Thi,$t3,lsl#8 - orr $Thi,$Thi,$t0,lsl#16 - orr $Thi,$Thi,$t1,lsl#24 -#else - ldr $Tlo,[$inp,#4] - ldr $Thi,[$inp],#8 -#ifdef __ARMEL__ - rev $Tlo,$Tlo - rev $Thi,$Thi -#endif -#endif -___ - &BODY_00_15(0x94); -$code.=<<___; - tst $Ktbl,#1 - beq .L00_15 - ldr $t0,[sp,#`$Xoff+8*(16-1)`+0] - ldr $t1,[sp,#`$Xoff+8*(16-1)`+4] - bic $Ktbl,$Ktbl,#1 -.L16_79: - @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7)) - @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25 - @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7 - mov $Tlo,$t0,lsr#1 - ldr $t2,[sp,#`$Xoff+8*(16-14)`+0] - mov $Thi,$t1,lsr#1 - ldr $t3,[sp,#`$Xoff+8*(16-14)`+4] - eor $Tlo,$Tlo,$t1,lsl#31 - eor $Thi,$Thi,$t0,lsl#31 - eor $Tlo,$Tlo,$t0,lsr#8 - eor $Thi,$Thi,$t1,lsr#8 - eor $Tlo,$Tlo,$t1,lsl#24 - eor $Thi,$Thi,$t0,lsl#24 - eor $Tlo,$Tlo,$t0,lsr#7 - eor $Thi,$Thi,$t1,lsr#7 - eor $Tlo,$Tlo,$t1,lsl#25 - - @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6)) - @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26 - @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6 - mov $t0,$t2,lsr#19 - mov $t1,$t3,lsr#19 - eor $t0,$t0,$t3,lsl#13 - eor $t1,$t1,$t2,lsl#13 - eor $t0,$t0,$t3,lsr#29 - eor $t1,$t1,$t2,lsr#29 - eor $t0,$t0,$t2,lsl#3 - eor $t1,$t1,$t3,lsl#3 - eor $t0,$t0,$t2,lsr#6 - eor $t1,$t1,$t3,lsr#6 - ldr $t2,[sp,#`$Xoff+8*(16-9)`+0] - eor $t0,$t0,$t3,lsl#26 - - ldr $t3,[sp,#`$Xoff+8*(16-9)`+4] - adds $Tlo,$Tlo,$t0 - ldr $t0,[sp,#`$Xoff+8*16`+0] - adc $Thi,$Thi,$t1 - - ldr $t1,[sp,#`$Xoff+8*16`+4] - adds $Tlo,$Tlo,$t2 - adc $Thi,$Thi,$t3 - adds $Tlo,$Tlo,$t0 - adc $Thi,$Thi,$t1 -___ - &BODY_00_15(0x17); -$code.=<<___; - ldreq $t0,[sp,#`$Xoff+8*(16-1)`+0] - ldreq $t1,[sp,#`$Xoff+8*(16-1)`+4] - beq .L16_79 - bic $Ktbl,$Ktbl,#1 - - ldr $Tlo,[sp,#$Boff+0] - ldr $Thi,[sp,#$Boff+4] - ldr $t0, [$ctx,#$Aoff+$lo] - ldr $t1, [$ctx,#$Aoff+$hi] - ldr $t2, [$ctx,#$Boff+$lo] - ldr $t3, [$ctx,#$Boff+$hi] - adds $t0,$Alo,$t0 - str $t0, [$ctx,#$Aoff+$lo] - adc $t1,$Ahi,$t1 - str $t1, [$ctx,#$Aoff+$hi] - adds $t2,$Tlo,$t2 - str $t2, [$ctx,#$Boff+$lo] - adc $t3,$Thi,$t3 - str $t3, [$ctx,#$Boff+$hi] - - ldr $Alo,[sp,#$Coff+0] - ldr $Ahi,[sp,#$Coff+4] - ldr $Tlo,[sp,#$Doff+0] - ldr $Thi,[sp,#$Doff+4] - ldr $t0, [$ctx,#$Coff+$lo] - ldr $t1, [$ctx,#$Coff+$hi] - ldr $t2, [$ctx,#$Doff+$lo] - ldr $t3, [$ctx,#$Doff+$hi] - adds $t0,$Alo,$t0 - str $t0, [$ctx,#$Coff+$lo] - adc $t1,$Ahi,$t1 - str $t1, [$ctx,#$Coff+$hi] - adds $t2,$Tlo,$t2 - str $t2, [$ctx,#$Doff+$lo] - adc $t3,$Thi,$t3 - str $t3, [$ctx,#$Doff+$hi] - - ldr $Tlo,[sp,#$Foff+0] - ldr $Thi,[sp,#$Foff+4] - ldr $t0, [$ctx,#$Eoff+$lo] - ldr $t1, [$ctx,#$Eoff+$hi] - ldr $t2, [$ctx,#$Foff+$lo] - ldr $t3, [$ctx,#$Foff+$hi] - adds $Elo,$Elo,$t0 - str $Elo,[$ctx,#$Eoff+$lo] - adc $Ehi,$Ehi,$t1 - str $Ehi,[$ctx,#$Eoff+$hi] - adds $t2,$Tlo,$t2 - str $t2, [$ctx,#$Foff+$lo] - adc $t3,$Thi,$t3 - str $t3, [$ctx,#$Foff+$hi] - - ldr $Alo,[sp,#$Goff+0] - ldr $Ahi,[sp,#$Goff+4] - ldr $Tlo,[sp,#$Hoff+0] - ldr $Thi,[sp,#$Hoff+4] - ldr $t0, [$ctx,#$Goff+$lo] - ldr $t1, [$ctx,#$Goff+$hi] - ldr $t2, [$ctx,#$Hoff+$lo] - ldr $t3, [$ctx,#$Hoff+$hi] - adds $t0,$Alo,$t0 - str $t0, [$ctx,#$Goff+$lo] - adc $t1,$Ahi,$t1 - str $t1, [$ctx,#$Goff+$hi] - adds $t2,$Tlo,$t2 - str $t2, [$ctx,#$Hoff+$lo] - adc $t3,$Thi,$t3 - str $t3, [$ctx,#$Hoff+$hi] - - add sp,sp,#640 - sub $Ktbl,$Ktbl,#640 - - teq $inp,$len - bne .Loop - - add sp,sp,#8*9 @ destroy frame -#if __ARM_ARCH__>=5 - ldmia sp!,{r4-r12,pc} -#else - ldmia sp!,{r4-r12,lr} - tst lr,#1 - moveq pc,lr @ be binary compatible with V4, yet - bx lr @ interoperable with Thumb ISA:-) -#endif -___ - -{ -my @Sigma0=(28,34,39); -my @Sigma1=(14,18,41); -my @sigma0=(1, 8, 7); -my @sigma1=(19,61,6); - -my $Ktbl="r3"; -my $cnt="r12"; # volatile register known as ip, intra-procedure-call scratch - -my @X=map("d$_",(0..15)); -my @V=($A,$B,$C,$D,$E,$F,$G,$H)=map("d$_",(16..23)); - -sub NEON_00_15() { -my $i=shift; -my ($a,$b,$c,$d,$e,$f,$g,$h)=@_; -my ($t0,$t1,$t2,$T1,$K,$Ch,$Maj)=map("d$_",(24..31)); # temps - -$code.=<<___ if ($i<16 || $i&1); - vshr.u64 $t0,$e,#@Sigma1[0] @ $i -#if $i<16 - vld1.64 {@X[$i%16]},[$inp]! @ handles unaligned -#endif - vshr.u64 $t1,$e,#@Sigma1[1] - vshr.u64 $t2,$e,#@Sigma1[2] -___ -$code.=<<___; - vld1.64 {$K},[$Ktbl,:64]! @ K[i++] - vsli.64 $t0,$e,#`64-@Sigma1[0]` - vsli.64 $t1,$e,#`64-@Sigma1[1]` - vsli.64 $t2,$e,#`64-@Sigma1[2]` -#if $i<16 && defined(__ARMEL__) - vrev64.8 @X[$i],@X[$i] -#endif - vadd.i64 $T1,$K,$h - veor $Ch,$f,$g - veor $t0,$t1 - vand $Ch,$e - veor $t0,$t2 @ Sigma1(e) - veor $Ch,$g @ Ch(e,f,g) - vadd.i64 $T1,$t0 - vshr.u64 $t0,$a,#@Sigma0[0] - vadd.i64 $T1,$Ch - vshr.u64 $t1,$a,#@Sigma0[1] - vshr.u64 $t2,$a,#@Sigma0[2] - vsli.64 $t0,$a,#`64-@Sigma0[0]` - vsli.64 $t1,$a,#`64-@Sigma0[1]` - vsli.64 $t2,$a,#`64-@Sigma0[2]` - vadd.i64 $T1,@X[$i%16] - vorr $Maj,$a,$c - vand $Ch,$a,$c - veor $h,$t0,$t1 - vand $Maj,$b - veor $h,$t2 @ Sigma0(a) - vorr $Maj,$Ch @ Maj(a,b,c) - vadd.i64 $h,$T1 - vadd.i64 $d,$T1 - vadd.i64 $h,$Maj -___ -} - -sub NEON_16_79() { -my $i=shift; - -if ($i&1) { &NEON_00_15($i,@_); return; } - -# 2x-vectorized, therefore runs every 2nd round -my @X=map("q$_",(0..7)); # view @X as 128-bit vector -my ($t0,$t1,$s0,$s1) = map("q$_",(12..15)); # temps -my ($d0,$d1,$d2) = map("d$_",(24..26)); # temps from NEON_00_15 -my $e=@_[4]; # $e from NEON_00_15 -$i /= 2; -$code.=<<___; - vshr.u64 $t0,@X[($i+7)%8],#@sigma1[0] - vshr.u64 $t1,@X[($i+7)%8],#@sigma1[1] - vshr.u64 $s1,@X[($i+7)%8],#@sigma1[2] - vsli.64 $t0,@X[($i+7)%8],#`64-@sigma1[0]` - vext.8 $s0,@X[$i%8],@X[($i+1)%8],#8 @ X[i+1] - vsli.64 $t1,@X[($i+7)%8],#`64-@sigma1[1]` - veor $s1,$t0 - vshr.u64 $t0,$s0,#@sigma0[0] - veor $s1,$t1 @ sigma1(X[i+14]) - vshr.u64 $t1,$s0,#@sigma0[1] - vadd.i64 @X[$i%8],$s1 - vshr.u64 $s1,$s0,#@sigma0[2] - vsli.64 $t0,$s0,#`64-@sigma0[0]` - vsli.64 $t1,$s0,#`64-@sigma0[1]` - vext.8 $s0,@X[($i+4)%8],@X[($i+5)%8],#8 @ X[i+9] - veor $s1,$t0 - vshr.u64 $d0,$e,#@Sigma1[0] @ from NEON_00_15 - vadd.i64 @X[$i%8],$s0 - vshr.u64 $d1,$e,#@Sigma1[1] @ from NEON_00_15 - veor $s1,$t1 @ sigma0(X[i+1]) - vshr.u64 $d2,$e,#@Sigma1[2] @ from NEON_00_15 - vadd.i64 @X[$i%8],$s1 -___ - &NEON_00_15(2*$i,@_); -} - -$code.=<<___; -#if __ARM_ARCH__>=7 -.fpu neon - -.align 4 -.LNEON: - dmb @ errata #451034 on early Cortex A8 - vstmdb sp!,{d8-d15} @ ABI specification says so - sub $Ktbl,r3,#672 @ K512 - vldmia $ctx,{$A-$H} @ load context -.Loop_neon: -___ -for($i=0;$i<16;$i++) { &NEON_00_15($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - mov $cnt,#4 -.L16_79_neon: - subs $cnt,#1 -___ -for(;$i<32;$i++) { &NEON_16_79($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - bne .L16_79_neon - - vldmia $ctx,{d24-d31} @ load context to temp - vadd.i64 q8,q12 @ vectorized accumulate - vadd.i64 q9,q13 - vadd.i64 q10,q14 - vadd.i64 q11,q15 - vstmia $ctx,{$A-$H} @ save context - teq $inp,$len - sub $Ktbl,#640 @ rewind K512 - bne .Loop_neon - - vldmia sp!,{d8-d15} @ epilogue - ret @ bx lr -#endif -___ -} -$code.=<<___; -.size sha512_block_data_order,.-sha512_block_data_order -.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>" -.align 2 -.comm OPENSSL_armcap_P,4,4 -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm; # make it possible to compile with -march=armv4 -$code =~ s/\bret\b/bx lr/gm; -print $code; -close STDOUT; # enforce flush diff --git a/app/openssl/crypto/sha/asm/sha512-armv8.S b/app/openssl/crypto/sha/asm/sha512-armv8.S deleted file mode 100644 index 6b0d1940..00000000 --- a/app/openssl/crypto/sha/asm/sha512-armv8.S +++ /dev/null @@ -1,1021 +0,0 @@ -#include "arm_arch.h" - -.text - -.globl sha512_block_data_order -.type sha512_block_data_order,%function -.align 6 -sha512_block_data_order: - stp x29,x30,[sp,#-128]! - add x29,sp,#0 - - stp x19,x20,[sp,#16] - stp x21,x22,[sp,#32] - stp x23,x24,[sp,#48] - stp x25,x26,[sp,#64] - stp x27,x28,[sp,#80] - sub sp,sp,#4*8 - - ldp x20,x21,[x0] // load context - ldp x22,x23,[x0,#2*8] - ldp x24,x25,[x0,#4*8] - add x2,x1,x2,lsl#7 // end of input - ldp x26,x27,[x0,#6*8] - adr x30,K512 - stp x0,x2,[x29,#96] - -.Loop: - ldp x3,x4,[x1],#2*8 - ldr x19,[x30],#8 // *K++ - eor x28,x21,x22 // magic seed - str x1,[x29,#112] -#ifndef __ARMEB__ - rev x3,x3 // 0 -#endif - ror x16,x24,#14 - add x27,x27,x19 // h+=K[i] - eor x6,x24,x24,ror#23 - and x17,x25,x24 - bic x19,x26,x24 - add x27,x27,x3 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x20,x21 // a^b, b^c in next round - eor x16,x16,x6,ror#18 // Sigma1(e) - ror x6,x20,#28 - add x27,x27,x17 // h+=Ch(e,f,g) - eor x17,x20,x20,ror#5 - add x27,x27,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x23,x23,x27 // d+=h - eor x28,x28,x21 // Maj(a,b,c) - eor x17,x6,x17,ror#34 // Sigma0(a) - add x27,x27,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x27,x27,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x4,x4 // 1 -#endif - ldp x5,x6,[x1],#2*8 - add x27,x27,x17 // h+=Sigma0(a) - ror x16,x23,#14 - add x26,x26,x28 // h+=K[i] - eor x7,x23,x23,ror#23 - and x17,x24,x23 - bic x28,x25,x23 - add x26,x26,x4 // h+=X[i] - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x27,x20 // a^b, b^c in next round - eor x16,x16,x7,ror#18 // Sigma1(e) - ror x7,x27,#28 - add x26,x26,x17 // h+=Ch(e,f,g) - eor x17,x27,x27,ror#5 - add x26,x26,x16 // h+=Sigma1(e) - and x19,x19,x28 // (b^c)&=(a^b) - add x22,x22,x26 // d+=h - eor x19,x19,x20 // Maj(a,b,c) - eor x17,x7,x17,ror#34 // Sigma0(a) - add x26,x26,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - //add x26,x26,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x5,x5 // 2 -#endif - add x26,x26,x17 // h+=Sigma0(a) - ror x16,x22,#14 - add x25,x25,x19 // h+=K[i] - eor x8,x22,x22,ror#23 - and x17,x23,x22 - bic x19,x24,x22 - add x25,x25,x5 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x26,x27 // a^b, b^c in next round - eor x16,x16,x8,ror#18 // Sigma1(e) - ror x8,x26,#28 - add x25,x25,x17 // h+=Ch(e,f,g) - eor x17,x26,x26,ror#5 - add x25,x25,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x21,x21,x25 // d+=h - eor x28,x28,x27 // Maj(a,b,c) - eor x17,x8,x17,ror#34 // Sigma0(a) - add x25,x25,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x25,x25,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x6,x6 // 3 -#endif - ldp x7,x8,[x1],#2*8 - add x25,x25,x17 // h+=Sigma0(a) - ror x16,x21,#14 - add x24,x24,x28 // h+=K[i] - eor x9,x21,x21,ror#23 - and x17,x22,x21 - bic x28,x23,x21 - add x24,x24,x6 // h+=X[i] - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x25,x26 // a^b, b^c in next round - eor x16,x16,x9,ror#18 // Sigma1(e) - ror x9,x25,#28 - add x24,x24,x17 // h+=Ch(e,f,g) - eor x17,x25,x25,ror#5 - add x24,x24,x16 // h+=Sigma1(e) - and x19,x19,x28 // (b^c)&=(a^b) - add x20,x20,x24 // d+=h - eor x19,x19,x26 // Maj(a,b,c) - eor x17,x9,x17,ror#34 // Sigma0(a) - add x24,x24,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - //add x24,x24,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x7,x7 // 4 -#endif - add x24,x24,x17 // h+=Sigma0(a) - ror x16,x20,#14 - add x23,x23,x19 // h+=K[i] - eor x10,x20,x20,ror#23 - and x17,x21,x20 - bic x19,x22,x20 - add x23,x23,x7 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x24,x25 // a^b, b^c in next round - eor x16,x16,x10,ror#18 // Sigma1(e) - ror x10,x24,#28 - add x23,x23,x17 // h+=Ch(e,f,g) - eor x17,x24,x24,ror#5 - add x23,x23,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x27,x27,x23 // d+=h - eor x28,x28,x25 // Maj(a,b,c) - eor x17,x10,x17,ror#34 // Sigma0(a) - add x23,x23,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x23,x23,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x8,x8 // 5 -#endif - ldp x9,x10,[x1],#2*8 - add x23,x23,x17 // h+=Sigma0(a) - ror x16,x27,#14 - add x22,x22,x28 // h+=K[i] - eor x11,x27,x27,ror#23 - and x17,x20,x27 - bic x28,x21,x27 - add x22,x22,x8 // h+=X[i] - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x23,x24 // a^b, b^c in next round - eor x16,x16,x11,ror#18 // Sigma1(e) - ror x11,x23,#28 - add x22,x22,x17 // h+=Ch(e,f,g) - eor x17,x23,x23,ror#5 - add x22,x22,x16 // h+=Sigma1(e) - and x19,x19,x28 // (b^c)&=(a^b) - add x26,x26,x22 // d+=h - eor x19,x19,x24 // Maj(a,b,c) - eor x17,x11,x17,ror#34 // Sigma0(a) - add x22,x22,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - //add x22,x22,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x9,x9 // 6 -#endif - add x22,x22,x17 // h+=Sigma0(a) - ror x16,x26,#14 - add x21,x21,x19 // h+=K[i] - eor x12,x26,x26,ror#23 - and x17,x27,x26 - bic x19,x20,x26 - add x21,x21,x9 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x22,x23 // a^b, b^c in next round - eor x16,x16,x12,ror#18 // Sigma1(e) - ror x12,x22,#28 - add x21,x21,x17 // h+=Ch(e,f,g) - eor x17,x22,x22,ror#5 - add x21,x21,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x25,x25,x21 // d+=h - eor x28,x28,x23 // Maj(a,b,c) - eor x17,x12,x17,ror#34 // Sigma0(a) - add x21,x21,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x21,x21,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x10,x10 // 7 -#endif - ldp x11,x12,[x1],#2*8 - add x21,x21,x17 // h+=Sigma0(a) - ror x16,x25,#14 - add x20,x20,x28 // h+=K[i] - eor x13,x25,x25,ror#23 - and x17,x26,x25 - bic x28,x27,x25 - add x20,x20,x10 // h+=X[i] - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x21,x22 // a^b, b^c in next round - eor x16,x16,x13,ror#18 // Sigma1(e) - ror x13,x21,#28 - add x20,x20,x17 // h+=Ch(e,f,g) - eor x17,x21,x21,ror#5 - add x20,x20,x16 // h+=Sigma1(e) - and x19,x19,x28 // (b^c)&=(a^b) - add x24,x24,x20 // d+=h - eor x19,x19,x22 // Maj(a,b,c) - eor x17,x13,x17,ror#34 // Sigma0(a) - add x20,x20,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - //add x20,x20,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x11,x11 // 8 -#endif - add x20,x20,x17 // h+=Sigma0(a) - ror x16,x24,#14 - add x27,x27,x19 // h+=K[i] - eor x14,x24,x24,ror#23 - and x17,x25,x24 - bic x19,x26,x24 - add x27,x27,x11 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x20,x21 // a^b, b^c in next round - eor x16,x16,x14,ror#18 // Sigma1(e) - ror x14,x20,#28 - add x27,x27,x17 // h+=Ch(e,f,g) - eor x17,x20,x20,ror#5 - add x27,x27,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x23,x23,x27 // d+=h - eor x28,x28,x21 // Maj(a,b,c) - eor x17,x14,x17,ror#34 // Sigma0(a) - add x27,x27,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x27,x27,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x12,x12 // 9 -#endif - ldp x13,x14,[x1],#2*8 - add x27,x27,x17 // h+=Sigma0(a) - ror x16,x23,#14 - add x26,x26,x28 // h+=K[i] - eor x15,x23,x23,ror#23 - and x17,x24,x23 - bic x28,x25,x23 - add x26,x26,x12 // h+=X[i] - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x27,x20 // a^b, b^c in next round - eor x16,x16,x15,ror#18 // Sigma1(e) - ror x15,x27,#28 - add x26,x26,x17 // h+=Ch(e,f,g) - eor x17,x27,x27,ror#5 - add x26,x26,x16 // h+=Sigma1(e) - and x19,x19,x28 // (b^c)&=(a^b) - add x22,x22,x26 // d+=h - eor x19,x19,x20 // Maj(a,b,c) - eor x17,x15,x17,ror#34 // Sigma0(a) - add x26,x26,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - //add x26,x26,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x13,x13 // 10 -#endif - add x26,x26,x17 // h+=Sigma0(a) - ror x16,x22,#14 - add x25,x25,x19 // h+=K[i] - eor x0,x22,x22,ror#23 - and x17,x23,x22 - bic x19,x24,x22 - add x25,x25,x13 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x26,x27 // a^b, b^c in next round - eor x16,x16,x0,ror#18 // Sigma1(e) - ror x0,x26,#28 - add x25,x25,x17 // h+=Ch(e,f,g) - eor x17,x26,x26,ror#5 - add x25,x25,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x21,x21,x25 // d+=h - eor x28,x28,x27 // Maj(a,b,c) - eor x17,x0,x17,ror#34 // Sigma0(a) - add x25,x25,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x25,x25,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x14,x14 // 11 -#endif - ldp x15,x0,[x1],#2*8 - add x25,x25,x17 // h+=Sigma0(a) - str x6,[sp,#24] - ror x16,x21,#14 - add x24,x24,x28 // h+=K[i] - eor x6,x21,x21,ror#23 - and x17,x22,x21 - bic x28,x23,x21 - add x24,x24,x14 // h+=X[i] - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x25,x26 // a^b, b^c in next round - eor x16,x16,x6,ror#18 // Sigma1(e) - ror x6,x25,#28 - add x24,x24,x17 // h+=Ch(e,f,g) - eor x17,x25,x25,ror#5 - add x24,x24,x16 // h+=Sigma1(e) - and x19,x19,x28 // (b^c)&=(a^b) - add x20,x20,x24 // d+=h - eor x19,x19,x26 // Maj(a,b,c) - eor x17,x6,x17,ror#34 // Sigma0(a) - add x24,x24,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - //add x24,x24,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x15,x15 // 12 -#endif - add x24,x24,x17 // h+=Sigma0(a) - str x7,[sp,#0] - ror x16,x20,#14 - add x23,x23,x19 // h+=K[i] - eor x7,x20,x20,ror#23 - and x17,x21,x20 - bic x19,x22,x20 - add x23,x23,x15 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x24,x25 // a^b, b^c in next round - eor x16,x16,x7,ror#18 // Sigma1(e) - ror x7,x24,#28 - add x23,x23,x17 // h+=Ch(e,f,g) - eor x17,x24,x24,ror#5 - add x23,x23,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x27,x27,x23 // d+=h - eor x28,x28,x25 // Maj(a,b,c) - eor x17,x7,x17,ror#34 // Sigma0(a) - add x23,x23,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x23,x23,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x0,x0 // 13 -#endif - ldp x1,x2,[x1] - add x23,x23,x17 // h+=Sigma0(a) - str x8,[sp,#8] - ror x16,x27,#14 - add x22,x22,x28 // h+=K[i] - eor x8,x27,x27,ror#23 - and x17,x20,x27 - bic x28,x21,x27 - add x22,x22,x0 // h+=X[i] - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x23,x24 // a^b, b^c in next round - eor x16,x16,x8,ror#18 // Sigma1(e) - ror x8,x23,#28 - add x22,x22,x17 // h+=Ch(e,f,g) - eor x17,x23,x23,ror#5 - add x22,x22,x16 // h+=Sigma1(e) - and x19,x19,x28 // (b^c)&=(a^b) - add x26,x26,x22 // d+=h - eor x19,x19,x24 // Maj(a,b,c) - eor x17,x8,x17,ror#34 // Sigma0(a) - add x22,x22,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - //add x22,x22,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x1,x1 // 14 -#endif - ldr x6,[sp,#24] - add x22,x22,x17 // h+=Sigma0(a) - str x9,[sp,#16] - ror x16,x26,#14 - add x21,x21,x19 // h+=K[i] - eor x9,x26,x26,ror#23 - and x17,x27,x26 - bic x19,x20,x26 - add x21,x21,x1 // h+=X[i] - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x22,x23 // a^b, b^c in next round - eor x16,x16,x9,ror#18 // Sigma1(e) - ror x9,x22,#28 - add x21,x21,x17 // h+=Ch(e,f,g) - eor x17,x22,x22,ror#5 - add x21,x21,x16 // h+=Sigma1(e) - and x28,x28,x19 // (b^c)&=(a^b) - add x25,x25,x21 // d+=h - eor x28,x28,x23 // Maj(a,b,c) - eor x17,x9,x17,ror#34 // Sigma0(a) - add x21,x21,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - //add x21,x21,x17 // h+=Sigma0(a) -#ifndef __ARMEB__ - rev x2,x2 // 15 -#endif - ldr x7,[sp,#0] - add x21,x21,x17 // h+=Sigma0(a) - str x10,[sp,#24] - ror x16,x25,#14 - add x20,x20,x28 // h+=K[i] - ror x9,x4,#1 - and x17,x26,x25 - ror x8,x1,#19 - bic x28,x27,x25 - ror x10,x21,#28 - add x20,x20,x2 // h+=X[i] - eor x16,x16,x25,ror#18 - eor x9,x9,x4,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x21,x22 // a^b, b^c in next round - eor x16,x16,x25,ror#41 // Sigma1(e) - eor x10,x10,x21,ror#34 - add x20,x20,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x8,x8,x1,ror#61 - eor x9,x9,x4,lsr#7 // sigma0(X[i+1]) - add x20,x20,x16 // h+=Sigma1(e) - eor x19,x19,x22 // Maj(a,b,c) - eor x17,x10,x21,ror#39 // Sigma0(a) - eor x8,x8,x1,lsr#6 // sigma1(X[i+14]) - add x3,x3,x12 - add x24,x24,x20 // d+=h - add x20,x20,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x3,x3,x9 - add x20,x20,x17 // h+=Sigma0(a) - add x3,x3,x8 -.Loop_16_xx: - ldr x8,[sp,#8] - str x11,[sp,#0] - ror x16,x24,#14 - add x27,x27,x19 // h+=K[i] - ror x10,x5,#1 - and x17,x25,x24 - ror x9,x2,#19 - bic x19,x26,x24 - ror x11,x20,#28 - add x27,x27,x3 // h+=X[i] - eor x16,x16,x24,ror#18 - eor x10,x10,x5,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x20,x21 // a^b, b^c in next round - eor x16,x16,x24,ror#41 // Sigma1(e) - eor x11,x11,x20,ror#34 - add x27,x27,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x9,x9,x2,ror#61 - eor x10,x10,x5,lsr#7 // sigma0(X[i+1]) - add x27,x27,x16 // h+=Sigma1(e) - eor x28,x28,x21 // Maj(a,b,c) - eor x17,x11,x20,ror#39 // Sigma0(a) - eor x9,x9,x2,lsr#6 // sigma1(X[i+14]) - add x4,x4,x13 - add x23,x23,x27 // d+=h - add x27,x27,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x4,x4,x10 - add x27,x27,x17 // h+=Sigma0(a) - add x4,x4,x9 - ldr x9,[sp,#16] - str x12,[sp,#8] - ror x16,x23,#14 - add x26,x26,x28 // h+=K[i] - ror x11,x6,#1 - and x17,x24,x23 - ror x10,x3,#19 - bic x28,x25,x23 - ror x12,x27,#28 - add x26,x26,x4 // h+=X[i] - eor x16,x16,x23,ror#18 - eor x11,x11,x6,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x27,x20 // a^b, b^c in next round - eor x16,x16,x23,ror#41 // Sigma1(e) - eor x12,x12,x27,ror#34 - add x26,x26,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x10,x10,x3,ror#61 - eor x11,x11,x6,lsr#7 // sigma0(X[i+1]) - add x26,x26,x16 // h+=Sigma1(e) - eor x19,x19,x20 // Maj(a,b,c) - eor x17,x12,x27,ror#39 // Sigma0(a) - eor x10,x10,x3,lsr#6 // sigma1(X[i+14]) - add x5,x5,x14 - add x22,x22,x26 // d+=h - add x26,x26,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x5,x5,x11 - add x26,x26,x17 // h+=Sigma0(a) - add x5,x5,x10 - ldr x10,[sp,#24] - str x13,[sp,#16] - ror x16,x22,#14 - add x25,x25,x19 // h+=K[i] - ror x12,x7,#1 - and x17,x23,x22 - ror x11,x4,#19 - bic x19,x24,x22 - ror x13,x26,#28 - add x25,x25,x5 // h+=X[i] - eor x16,x16,x22,ror#18 - eor x12,x12,x7,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x26,x27 // a^b, b^c in next round - eor x16,x16,x22,ror#41 // Sigma1(e) - eor x13,x13,x26,ror#34 - add x25,x25,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x11,x11,x4,ror#61 - eor x12,x12,x7,lsr#7 // sigma0(X[i+1]) - add x25,x25,x16 // h+=Sigma1(e) - eor x28,x28,x27 // Maj(a,b,c) - eor x17,x13,x26,ror#39 // Sigma0(a) - eor x11,x11,x4,lsr#6 // sigma1(X[i+14]) - add x6,x6,x15 - add x21,x21,x25 // d+=h - add x25,x25,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x6,x6,x12 - add x25,x25,x17 // h+=Sigma0(a) - add x6,x6,x11 - ldr x11,[sp,#0] - str x14,[sp,#24] - ror x16,x21,#14 - add x24,x24,x28 // h+=K[i] - ror x13,x8,#1 - and x17,x22,x21 - ror x12,x5,#19 - bic x28,x23,x21 - ror x14,x25,#28 - add x24,x24,x6 // h+=X[i] - eor x16,x16,x21,ror#18 - eor x13,x13,x8,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x25,x26 // a^b, b^c in next round - eor x16,x16,x21,ror#41 // Sigma1(e) - eor x14,x14,x25,ror#34 - add x24,x24,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x12,x12,x5,ror#61 - eor x13,x13,x8,lsr#7 // sigma0(X[i+1]) - add x24,x24,x16 // h+=Sigma1(e) - eor x19,x19,x26 // Maj(a,b,c) - eor x17,x14,x25,ror#39 // Sigma0(a) - eor x12,x12,x5,lsr#6 // sigma1(X[i+14]) - add x7,x7,x0 - add x20,x20,x24 // d+=h - add x24,x24,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x7,x7,x13 - add x24,x24,x17 // h+=Sigma0(a) - add x7,x7,x12 - ldr x12,[sp,#8] - str x15,[sp,#0] - ror x16,x20,#14 - add x23,x23,x19 // h+=K[i] - ror x14,x9,#1 - and x17,x21,x20 - ror x13,x6,#19 - bic x19,x22,x20 - ror x15,x24,#28 - add x23,x23,x7 // h+=X[i] - eor x16,x16,x20,ror#18 - eor x14,x14,x9,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x24,x25 // a^b, b^c in next round - eor x16,x16,x20,ror#41 // Sigma1(e) - eor x15,x15,x24,ror#34 - add x23,x23,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x13,x13,x6,ror#61 - eor x14,x14,x9,lsr#7 // sigma0(X[i+1]) - add x23,x23,x16 // h+=Sigma1(e) - eor x28,x28,x25 // Maj(a,b,c) - eor x17,x15,x24,ror#39 // Sigma0(a) - eor x13,x13,x6,lsr#6 // sigma1(X[i+14]) - add x8,x8,x1 - add x27,x27,x23 // d+=h - add x23,x23,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x8,x8,x14 - add x23,x23,x17 // h+=Sigma0(a) - add x8,x8,x13 - ldr x13,[sp,#16] - str x0,[sp,#8] - ror x16,x27,#14 - add x22,x22,x28 // h+=K[i] - ror x15,x10,#1 - and x17,x20,x27 - ror x14,x7,#19 - bic x28,x21,x27 - ror x0,x23,#28 - add x22,x22,x8 // h+=X[i] - eor x16,x16,x27,ror#18 - eor x15,x15,x10,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x23,x24 // a^b, b^c in next round - eor x16,x16,x27,ror#41 // Sigma1(e) - eor x0,x0,x23,ror#34 - add x22,x22,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x14,x14,x7,ror#61 - eor x15,x15,x10,lsr#7 // sigma0(X[i+1]) - add x22,x22,x16 // h+=Sigma1(e) - eor x19,x19,x24 // Maj(a,b,c) - eor x17,x0,x23,ror#39 // Sigma0(a) - eor x14,x14,x7,lsr#6 // sigma1(X[i+14]) - add x9,x9,x2 - add x26,x26,x22 // d+=h - add x22,x22,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x9,x9,x15 - add x22,x22,x17 // h+=Sigma0(a) - add x9,x9,x14 - ldr x14,[sp,#24] - str x1,[sp,#16] - ror x16,x26,#14 - add x21,x21,x19 // h+=K[i] - ror x0,x11,#1 - and x17,x27,x26 - ror x15,x8,#19 - bic x19,x20,x26 - ror x1,x22,#28 - add x21,x21,x9 // h+=X[i] - eor x16,x16,x26,ror#18 - eor x0,x0,x11,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x22,x23 // a^b, b^c in next round - eor x16,x16,x26,ror#41 // Sigma1(e) - eor x1,x1,x22,ror#34 - add x21,x21,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x15,x15,x8,ror#61 - eor x0,x0,x11,lsr#7 // sigma0(X[i+1]) - add x21,x21,x16 // h+=Sigma1(e) - eor x28,x28,x23 // Maj(a,b,c) - eor x17,x1,x22,ror#39 // Sigma0(a) - eor x15,x15,x8,lsr#6 // sigma1(X[i+14]) - add x10,x10,x3 - add x25,x25,x21 // d+=h - add x21,x21,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x10,x10,x0 - add x21,x21,x17 // h+=Sigma0(a) - add x10,x10,x15 - ldr x15,[sp,#0] - str x2,[sp,#24] - ror x16,x25,#14 - add x20,x20,x28 // h+=K[i] - ror x1,x12,#1 - and x17,x26,x25 - ror x0,x9,#19 - bic x28,x27,x25 - ror x2,x21,#28 - add x20,x20,x10 // h+=X[i] - eor x16,x16,x25,ror#18 - eor x1,x1,x12,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x21,x22 // a^b, b^c in next round - eor x16,x16,x25,ror#41 // Sigma1(e) - eor x2,x2,x21,ror#34 - add x20,x20,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x0,x0,x9,ror#61 - eor x1,x1,x12,lsr#7 // sigma0(X[i+1]) - add x20,x20,x16 // h+=Sigma1(e) - eor x19,x19,x22 // Maj(a,b,c) - eor x17,x2,x21,ror#39 // Sigma0(a) - eor x0,x0,x9,lsr#6 // sigma1(X[i+14]) - add x11,x11,x4 - add x24,x24,x20 // d+=h - add x20,x20,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x11,x11,x1 - add x20,x20,x17 // h+=Sigma0(a) - add x11,x11,x0 - ldr x0,[sp,#8] - str x3,[sp,#0] - ror x16,x24,#14 - add x27,x27,x19 // h+=K[i] - ror x2,x13,#1 - and x17,x25,x24 - ror x1,x10,#19 - bic x19,x26,x24 - ror x3,x20,#28 - add x27,x27,x11 // h+=X[i] - eor x16,x16,x24,ror#18 - eor x2,x2,x13,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x20,x21 // a^b, b^c in next round - eor x16,x16,x24,ror#41 // Sigma1(e) - eor x3,x3,x20,ror#34 - add x27,x27,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x1,x1,x10,ror#61 - eor x2,x2,x13,lsr#7 // sigma0(X[i+1]) - add x27,x27,x16 // h+=Sigma1(e) - eor x28,x28,x21 // Maj(a,b,c) - eor x17,x3,x20,ror#39 // Sigma0(a) - eor x1,x1,x10,lsr#6 // sigma1(X[i+14]) - add x12,x12,x5 - add x23,x23,x27 // d+=h - add x27,x27,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x12,x12,x2 - add x27,x27,x17 // h+=Sigma0(a) - add x12,x12,x1 - ldr x1,[sp,#16] - str x4,[sp,#8] - ror x16,x23,#14 - add x26,x26,x28 // h+=K[i] - ror x3,x14,#1 - and x17,x24,x23 - ror x2,x11,#19 - bic x28,x25,x23 - ror x4,x27,#28 - add x26,x26,x12 // h+=X[i] - eor x16,x16,x23,ror#18 - eor x3,x3,x14,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x27,x20 // a^b, b^c in next round - eor x16,x16,x23,ror#41 // Sigma1(e) - eor x4,x4,x27,ror#34 - add x26,x26,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x2,x2,x11,ror#61 - eor x3,x3,x14,lsr#7 // sigma0(X[i+1]) - add x26,x26,x16 // h+=Sigma1(e) - eor x19,x19,x20 // Maj(a,b,c) - eor x17,x4,x27,ror#39 // Sigma0(a) - eor x2,x2,x11,lsr#6 // sigma1(X[i+14]) - add x13,x13,x6 - add x22,x22,x26 // d+=h - add x26,x26,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x13,x13,x3 - add x26,x26,x17 // h+=Sigma0(a) - add x13,x13,x2 - ldr x2,[sp,#24] - str x5,[sp,#16] - ror x16,x22,#14 - add x25,x25,x19 // h+=K[i] - ror x4,x15,#1 - and x17,x23,x22 - ror x3,x12,#19 - bic x19,x24,x22 - ror x5,x26,#28 - add x25,x25,x13 // h+=X[i] - eor x16,x16,x22,ror#18 - eor x4,x4,x15,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x26,x27 // a^b, b^c in next round - eor x16,x16,x22,ror#41 // Sigma1(e) - eor x5,x5,x26,ror#34 - add x25,x25,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x3,x3,x12,ror#61 - eor x4,x4,x15,lsr#7 // sigma0(X[i+1]) - add x25,x25,x16 // h+=Sigma1(e) - eor x28,x28,x27 // Maj(a,b,c) - eor x17,x5,x26,ror#39 // Sigma0(a) - eor x3,x3,x12,lsr#6 // sigma1(X[i+14]) - add x14,x14,x7 - add x21,x21,x25 // d+=h - add x25,x25,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x14,x14,x4 - add x25,x25,x17 // h+=Sigma0(a) - add x14,x14,x3 - ldr x3,[sp,#0] - str x6,[sp,#24] - ror x16,x21,#14 - add x24,x24,x28 // h+=K[i] - ror x5,x0,#1 - and x17,x22,x21 - ror x4,x13,#19 - bic x28,x23,x21 - ror x6,x25,#28 - add x24,x24,x14 // h+=X[i] - eor x16,x16,x21,ror#18 - eor x5,x5,x0,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x25,x26 // a^b, b^c in next round - eor x16,x16,x21,ror#41 // Sigma1(e) - eor x6,x6,x25,ror#34 - add x24,x24,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x4,x4,x13,ror#61 - eor x5,x5,x0,lsr#7 // sigma0(X[i+1]) - add x24,x24,x16 // h+=Sigma1(e) - eor x19,x19,x26 // Maj(a,b,c) - eor x17,x6,x25,ror#39 // Sigma0(a) - eor x4,x4,x13,lsr#6 // sigma1(X[i+14]) - add x15,x15,x8 - add x20,x20,x24 // d+=h - add x24,x24,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x15,x15,x5 - add x24,x24,x17 // h+=Sigma0(a) - add x15,x15,x4 - ldr x4,[sp,#8] - str x7,[sp,#0] - ror x16,x20,#14 - add x23,x23,x19 // h+=K[i] - ror x6,x1,#1 - and x17,x21,x20 - ror x5,x14,#19 - bic x19,x22,x20 - ror x7,x24,#28 - add x23,x23,x15 // h+=X[i] - eor x16,x16,x20,ror#18 - eor x6,x6,x1,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x24,x25 // a^b, b^c in next round - eor x16,x16,x20,ror#41 // Sigma1(e) - eor x7,x7,x24,ror#34 - add x23,x23,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x5,x5,x14,ror#61 - eor x6,x6,x1,lsr#7 // sigma0(X[i+1]) - add x23,x23,x16 // h+=Sigma1(e) - eor x28,x28,x25 // Maj(a,b,c) - eor x17,x7,x24,ror#39 // Sigma0(a) - eor x5,x5,x14,lsr#6 // sigma1(X[i+14]) - add x0,x0,x9 - add x27,x27,x23 // d+=h - add x23,x23,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x0,x0,x6 - add x23,x23,x17 // h+=Sigma0(a) - add x0,x0,x5 - ldr x5,[sp,#16] - str x8,[sp,#8] - ror x16,x27,#14 - add x22,x22,x28 // h+=K[i] - ror x7,x2,#1 - and x17,x20,x27 - ror x6,x15,#19 - bic x28,x21,x27 - ror x8,x23,#28 - add x22,x22,x0 // h+=X[i] - eor x16,x16,x27,ror#18 - eor x7,x7,x2,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x23,x24 // a^b, b^c in next round - eor x16,x16,x27,ror#41 // Sigma1(e) - eor x8,x8,x23,ror#34 - add x22,x22,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x6,x6,x15,ror#61 - eor x7,x7,x2,lsr#7 // sigma0(X[i+1]) - add x22,x22,x16 // h+=Sigma1(e) - eor x19,x19,x24 // Maj(a,b,c) - eor x17,x8,x23,ror#39 // Sigma0(a) - eor x6,x6,x15,lsr#6 // sigma1(X[i+14]) - add x1,x1,x10 - add x26,x26,x22 // d+=h - add x22,x22,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x1,x1,x7 - add x22,x22,x17 // h+=Sigma0(a) - add x1,x1,x6 - ldr x6,[sp,#24] - str x9,[sp,#16] - ror x16,x26,#14 - add x21,x21,x19 // h+=K[i] - ror x8,x3,#1 - and x17,x27,x26 - ror x7,x0,#19 - bic x19,x20,x26 - ror x9,x22,#28 - add x21,x21,x1 // h+=X[i] - eor x16,x16,x26,ror#18 - eor x8,x8,x3,ror#8 - orr x17,x17,x19 // Ch(e,f,g) - eor x19,x22,x23 // a^b, b^c in next round - eor x16,x16,x26,ror#41 // Sigma1(e) - eor x9,x9,x22,ror#34 - add x21,x21,x17 // h+=Ch(e,f,g) - and x28,x28,x19 // (b^c)&=(a^b) - eor x7,x7,x0,ror#61 - eor x8,x8,x3,lsr#7 // sigma0(X[i+1]) - add x21,x21,x16 // h+=Sigma1(e) - eor x28,x28,x23 // Maj(a,b,c) - eor x17,x9,x22,ror#39 // Sigma0(a) - eor x7,x7,x0,lsr#6 // sigma1(X[i+14]) - add x2,x2,x11 - add x25,x25,x21 // d+=h - add x21,x21,x28 // h+=Maj(a,b,c) - ldr x28,[x30],#8 // *K++, x19 in next round - add x2,x2,x8 - add x21,x21,x17 // h+=Sigma0(a) - add x2,x2,x7 - ldr x7,[sp,#0] - str x10,[sp,#24] - ror x16,x25,#14 - add x20,x20,x28 // h+=K[i] - ror x9,x4,#1 - and x17,x26,x25 - ror x8,x1,#19 - bic x28,x27,x25 - ror x10,x21,#28 - add x20,x20,x2 // h+=X[i] - eor x16,x16,x25,ror#18 - eor x9,x9,x4,ror#8 - orr x17,x17,x28 // Ch(e,f,g) - eor x28,x21,x22 // a^b, b^c in next round - eor x16,x16,x25,ror#41 // Sigma1(e) - eor x10,x10,x21,ror#34 - add x20,x20,x17 // h+=Ch(e,f,g) - and x19,x19,x28 // (b^c)&=(a^b) - eor x8,x8,x1,ror#61 - eor x9,x9,x4,lsr#7 // sigma0(X[i+1]) - add x20,x20,x16 // h+=Sigma1(e) - eor x19,x19,x22 // Maj(a,b,c) - eor x17,x10,x21,ror#39 // Sigma0(a) - eor x8,x8,x1,lsr#6 // sigma1(X[i+14]) - add x3,x3,x12 - add x24,x24,x20 // d+=h - add x20,x20,x19 // h+=Maj(a,b,c) - ldr x19,[x30],#8 // *K++, x28 in next round - add x3,x3,x9 - add x20,x20,x17 // h+=Sigma0(a) - add x3,x3,x8 - cbnz x19,.Loop_16_xx - - ldp x0,x2,[x29,#96] - ldr x1,[x29,#112] - sub x30,x30,#648 // rewind - - ldp x3,x4,[x0] - ldp x5,x6,[x0,#2*8] - add x1,x1,#14*8 // advance input pointer - ldp x7,x8,[x0,#4*8] - add x20,x20,x3 - ldp x9,x10,[x0,#6*8] - add x21,x21,x4 - add x22,x22,x5 - add x23,x23,x6 - stp x20,x21,[x0] - add x24,x24,x7 - add x25,x25,x8 - stp x22,x23,[x0,#2*8] - add x26,x26,x9 - add x27,x27,x10 - cmp x1,x2 - stp x24,x25,[x0,#4*8] - stp x26,x27,[x0,#6*8] - b.ne .Loop - - ldp x19,x20,[x29,#16] - add sp,sp,#4*8 - ldp x21,x22,[x29,#32] - ldp x23,x24,[x29,#48] - ldp x25,x26,[x29,#64] - ldp x27,x28,[x29,#80] - ldp x29,x30,[sp],#128 - ret -.size sha512_block_data_order,.-sha512_block_data_order - -.align 6 -.type K512,%object -K512: - .quad 0x428a2f98d728ae22,0x7137449123ef65cd - .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc - .quad 0x3956c25bf348b538,0x59f111f1b605d019 - .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118 - .quad 0xd807aa98a3030242,0x12835b0145706fbe - .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2 - .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1 - .quad 0x9bdc06a725c71235,0xc19bf174cf692694 - .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3 - .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65 - .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483 - .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5 - .quad 0x983e5152ee66dfab,0xa831c66d2db43210 - .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4 - .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725 - .quad 0x06ca6351e003826f,0x142929670a0e6e70 - .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926 - .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df - .quad 0x650a73548baf63de,0x766a0abb3c77b2a8 - .quad 0x81c2c92e47edaee6,0x92722c851482353b - .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001 - .quad 0xc24b8b70d0f89791,0xc76c51a30654be30 - .quad 0xd192e819d6ef5218,0xd69906245565a910 - .quad 0xf40e35855771202a,0x106aa07032bbd1b8 - .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53 - .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8 - .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb - .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3 - .quad 0x748f82ee5defb2fc,0x78a5636f43172f60 - .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec - .quad 0x90befffa23631e28,0xa4506cebde82bde9 - .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b - .quad 0xca273eceea26619c,0xd186b8c721c0c207 - .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178 - .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6 - .quad 0x113f9804bef90dae,0x1b710b35131c471b - .quad 0x28db77f523047d84,0x32caab7b40c72493 - .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c - .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a - .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 - .quad 0 // terminator -.size K512,.-K512 -.align 3 -.LOPENSSL_armcap_P: - .quad OPENSSL_armcap_P-. -.asciz "SHA512 block transform for ARMv8, CRYPTOGAMS by <appro@openssl.org>" -.align 2 -.comm OPENSSL_armcap_P,4,4 diff --git a/app/openssl/crypto/sha/asm/sha512-armv8.pl b/app/openssl/crypto/sha/asm/sha512-armv8.pl deleted file mode 100644 index 6935ed65..00000000 --- a/app/openssl/crypto/sha/asm/sha512-armv8.pl +++ /dev/null @@ -1,414 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== -# -# SHA256/512 for ARMv8. -# -# Performance in cycles per processed byte and improvement coefficient -# over code generated with "default" compiler: -# -# SHA256-hw SHA256(*) SHA512 -# Apple A7 1.97 10.5 (+33%) 6.73 (-1%(**)) -# Cortex-A5x n/a n/a n/a -# -# (*) Software SHA256 results are of lesser relevance, presented -# mostly for informational purposes. -# (**) The result is a trade-off: it's possible to improve it by -# 10%, but at the cost of 20% loss on Cortex-A5x. - -$flavour=shift; -$output=shift; -open STDOUT,">$output"; - -if ($output =~ /512/) { - $BITS=512; - $SZ=8; - @Sigma0=(28,34,39); - @Sigma1=(14,18,41); - @sigma0=(1, 8, 7); - @sigma1=(19,61, 6); - $rounds=80; - $reg_t="x"; -} else { - $BITS=256; - $SZ=4; - @Sigma0=( 2,13,22); - @Sigma1=( 6,11,25); - @sigma0=( 7,18, 3); - @sigma1=(17,19,10); - $rounds=64; - $reg_t="w"; -} - -$func="sha${BITS}_block_data_order"; - -($ctx,$inp,$num,$Ktbl)=map("x$_",(0..2,30)); - -@X=map("$reg_t$_",(3..15,0..2)); -@V=($A,$B,$C,$D,$E,$F,$G,$H)=map("$reg_t$_",(20..27)); -($t0,$t1,$t2,$t3)=map("$reg_t$_",(16,17,19,28)); - -sub BODY_00_xx { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; -my $j=($i+1)&15; -my ($T0,$T1,$T2)=(@X[($i-8)&15],@X[($i-9)&15],@X[($i-10)&15]); - $T0=@X[$i+3] if ($i<11); - -$code.=<<___ if ($i<16); -#ifndef __ARMEB__ - rev @X[$i],@X[$i] // $i -#endif -___ -$code.=<<___ if ($i<13 && ($i&1)); - ldp @X[$i+1],@X[$i+2],[$inp],#2*$SZ -___ -$code.=<<___ if ($i==13); - ldp @X[14],@X[15],[$inp] -___ -$code.=<<___ if ($i>=14); - ldr @X[($i-11)&15],[sp,#`$SZ*(($i-11)%4)`] -___ -$code.=<<___ if ($i>0 && $i<16); - add $a,$a,$t1 // h+=Sigma0(a) -___ -$code.=<<___ if ($i>=11); - str @X[($i-8)&15],[sp,#`$SZ*(($i-8)%4)`] -___ -# While ARMv8 specifies merged rotate-n-logical operation such as -# 'eor x,y,z,ror#n', it was found to negatively affect performance -# on Apple A7. The reason seems to be that it requires even 'y' to -# be available earlier. This means that such merged instruction is -# not necessarily best choice on critical path... On the other hand -# Cortex-A5x handles merged instructions much better than disjoint -# rotate and logical... See (**) footnote above. -$code.=<<___ if ($i<15); - ror $t0,$e,#$Sigma1[0] - add $h,$h,$t2 // h+=K[i] - eor $T0,$e,$e,ror#`$Sigma1[2]-$Sigma1[1]` - and $t1,$f,$e - bic $t2,$g,$e - add $h,$h,@X[$i&15] // h+=X[i] - orr $t1,$t1,$t2 // Ch(e,f,g) - eor $t2,$a,$b // a^b, b^c in next round - eor $t0,$t0,$T0,ror#$Sigma1[1] // Sigma1(e) - ror $T0,$a,#$Sigma0[0] - add $h,$h,$t1 // h+=Ch(e,f,g) - eor $t1,$a,$a,ror#`$Sigma0[2]-$Sigma0[1]` - add $h,$h,$t0 // h+=Sigma1(e) - and $t3,$t3,$t2 // (b^c)&=(a^b) - add $d,$d,$h // d+=h - eor $t3,$t3,$b // Maj(a,b,c) - eor $t1,$T0,$t1,ror#$Sigma0[1] // Sigma0(a) - add $h,$h,$t3 // h+=Maj(a,b,c) - ldr $t3,[$Ktbl],#$SZ // *K++, $t2 in next round - //add $h,$h,$t1 // h+=Sigma0(a) -___ -$code.=<<___ if ($i>=15); - ror $t0,$e,#$Sigma1[0] - add $h,$h,$t2 // h+=K[i] - ror $T1,@X[($j+1)&15],#$sigma0[0] - and $t1,$f,$e - ror $T2,@X[($j+14)&15],#$sigma1[0] - bic $t2,$g,$e - ror $T0,$a,#$Sigma0[0] - add $h,$h,@X[$i&15] // h+=X[i] - eor $t0,$t0,$e,ror#$Sigma1[1] - eor $T1,$T1,@X[($j+1)&15],ror#$sigma0[1] - orr $t1,$t1,$t2 // Ch(e,f,g) - eor $t2,$a,$b // a^b, b^c in next round - eor $t0,$t0,$e,ror#$Sigma1[2] // Sigma1(e) - eor $T0,$T0,$a,ror#$Sigma0[1] - add $h,$h,$t1 // h+=Ch(e,f,g) - and $t3,$t3,$t2 // (b^c)&=(a^b) - eor $T2,$T2,@X[($j+14)&15],ror#$sigma1[1] - eor $T1,$T1,@X[($j+1)&15],lsr#$sigma0[2] // sigma0(X[i+1]) - add $h,$h,$t0 // h+=Sigma1(e) - eor $t3,$t3,$b // Maj(a,b,c) - eor $t1,$T0,$a,ror#$Sigma0[2] // Sigma0(a) - eor $T2,$T2,@X[($j+14)&15],lsr#$sigma1[2] // sigma1(X[i+14]) - add @X[$j],@X[$j],@X[($j+9)&15] - add $d,$d,$h // d+=h - add $h,$h,$t3 // h+=Maj(a,b,c) - ldr $t3,[$Ktbl],#$SZ // *K++, $t2 in next round - add @X[$j],@X[$j],$T1 - add $h,$h,$t1 // h+=Sigma0(a) - add @X[$j],@X[$j],$T2 -___ - ($t2,$t3)=($t3,$t2); -} - -$code.=<<___; -#include "arm_arch.h" - -.text - -.globl $func -.type $func,%function -.align 6 -$func: -___ -$code.=<<___ if ($SZ==4); - ldr x16,.LOPENSSL_armcap_P - adr x17,.LOPENSSL_armcap_P - add x16,x16,x17 - ldr w16,[x16] - tst w16,#ARMV8_SHA256 - b.ne .Lv8_entry -___ -$code.=<<___; - stp x29,x30,[sp,#-128]! - add x29,sp,#0 - - stp x19,x20,[sp,#16] - stp x21,x22,[sp,#32] - stp x23,x24,[sp,#48] - stp x25,x26,[sp,#64] - stp x27,x28,[sp,#80] - sub sp,sp,#4*$SZ - - ldp $A,$B,[$ctx] // load context - ldp $C,$D,[$ctx,#2*$SZ] - ldp $E,$F,[$ctx,#4*$SZ] - add $num,$inp,$num,lsl#`log(16*$SZ)/log(2)` // end of input - ldp $G,$H,[$ctx,#6*$SZ] - adr $Ktbl,K$BITS - stp $ctx,$num,[x29,#96] - -.Loop: - ldp @X[0],@X[1],[$inp],#2*$SZ - ldr $t2,[$Ktbl],#$SZ // *K++ - eor $t3,$B,$C // magic seed - str $inp,[x29,#112] -___ -for ($i=0;$i<16;$i++) { &BODY_00_xx($i,@V); unshift(@V,pop(@V)); } -$code.=".Loop_16_xx:\n"; -for (;$i<32;$i++) { &BODY_00_xx($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - cbnz $t2,.Loop_16_xx - - ldp $ctx,$num,[x29,#96] - ldr $inp,[x29,#112] - sub $Ktbl,$Ktbl,#`$SZ*($rounds+1)` // rewind - - ldp @X[0],@X[1],[$ctx] - ldp @X[2],@X[3],[$ctx,#2*$SZ] - add $inp,$inp,#14*$SZ // advance input pointer - ldp @X[4],@X[5],[$ctx,#4*$SZ] - add $A,$A,@X[0] - ldp @X[6],@X[7],[$ctx,#6*$SZ] - add $B,$B,@X[1] - add $C,$C,@X[2] - add $D,$D,@X[3] - stp $A,$B,[$ctx] - add $E,$E,@X[4] - add $F,$F,@X[5] - stp $C,$D,[$ctx,#2*$SZ] - add $G,$G,@X[6] - add $H,$H,@X[7] - cmp $inp,$num - stp $E,$F,[$ctx,#4*$SZ] - stp $G,$H,[$ctx,#6*$SZ] - b.ne .Loop - - ldp x19,x20,[x29,#16] - add sp,sp,#4*$SZ - ldp x21,x22,[x29,#32] - ldp x23,x24,[x29,#48] - ldp x25,x26,[x29,#64] - ldp x27,x28,[x29,#80] - ldp x29,x30,[sp],#128 - ret -.size $func,.-$func - -.align 6 -.type K$BITS,%object -K$BITS: -___ -$code.=<<___ if ($SZ==8); - .quad 0x428a2f98d728ae22,0x7137449123ef65cd - .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc - .quad 0x3956c25bf348b538,0x59f111f1b605d019 - .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118 - .quad 0xd807aa98a3030242,0x12835b0145706fbe - .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2 - .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1 - .quad 0x9bdc06a725c71235,0xc19bf174cf692694 - .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3 - .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65 - .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483 - .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5 - .quad 0x983e5152ee66dfab,0xa831c66d2db43210 - .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4 - .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725 - .quad 0x06ca6351e003826f,0x142929670a0e6e70 - .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926 - .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df - .quad 0x650a73548baf63de,0x766a0abb3c77b2a8 - .quad 0x81c2c92e47edaee6,0x92722c851482353b - .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001 - .quad 0xc24b8b70d0f89791,0xc76c51a30654be30 - .quad 0xd192e819d6ef5218,0xd69906245565a910 - .quad 0xf40e35855771202a,0x106aa07032bbd1b8 - .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53 - .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8 - .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb - .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3 - .quad 0x748f82ee5defb2fc,0x78a5636f43172f60 - .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec - .quad 0x90befffa23631e28,0xa4506cebde82bde9 - .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b - .quad 0xca273eceea26619c,0xd186b8c721c0c207 - .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178 - .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6 - .quad 0x113f9804bef90dae,0x1b710b35131c471b - .quad 0x28db77f523047d84,0x32caab7b40c72493 - .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c - .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a - .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 - .quad 0 // terminator -___ -$code.=<<___ if ($SZ==4); - .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 - .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 - .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 - .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 - .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc - .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da - .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 - .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 - .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 - .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 - .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 - .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 - .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 - .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 - .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 - .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 - .long 0 //terminator -___ -$code.=<<___; -.size K$BITS,.-K$BITS -.align 3 -.LOPENSSL_armcap_P: - .quad OPENSSL_armcap_P-. -.asciz "SHA$BITS block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>" -.align 2 -___ - -if ($SZ==4) { -my $Ktbl="x3"; - -my ($ABCD,$EFGH,$abcd)=map("v$_.16b",(0..2)); -my @MSG=map("v$_.16b",(4..7)); -my ($W0,$W1)=("v16.4s","v17.4s"); -my ($ABCD_SAVE,$EFGH_SAVE)=("v18.16b","v19.16b"); - -$code.=<<___; -.type sha256_block_armv8,%function -.align 6 -sha256_block_armv8: -.Lv8_entry: - stp x29,x30,[sp,#-16]! - add x29,sp,#0 - - ld1.32 {$ABCD,$EFGH},[$ctx] - adr $Ktbl,K256 - -.Loop_hw: - ld1 {@MSG[0]-@MSG[3]},[$inp],#64 - sub $num,$num,#1 - ld1.32 {$W0},[$Ktbl],#16 - rev32 @MSG[0],@MSG[0] - rev32 @MSG[1],@MSG[1] - rev32 @MSG[2],@MSG[2] - rev32 @MSG[3],@MSG[3] - orr $ABCD_SAVE,$ABCD,$ABCD // offload - orr $EFGH_SAVE,$EFGH,$EFGH -___ -for($i=0;$i<12;$i++) { -$code.=<<___; - ld1.32 {$W1},[$Ktbl],#16 - add.i32 $W0,$W0,@MSG[0] - sha256su0 @MSG[0],@MSG[1] - orr $abcd,$ABCD,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - sha256su1 @MSG[0],@MSG[2],@MSG[3] -___ - ($W0,$W1)=($W1,$W0); push(@MSG,shift(@MSG)); -} -$code.=<<___; - ld1.32 {$W1},[$Ktbl],#16 - add.i32 $W0,$W0,@MSG[0] - orr $abcd,$ABCD,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - - ld1.32 {$W0},[$Ktbl],#16 - add.i32 $W1,$W1,@MSG[1] - orr $abcd,$ABCD,$ABCD - sha256h $ABCD,$EFGH,$W1 - sha256h2 $EFGH,$abcd,$W1 - - ld1.32 {$W1},[$Ktbl] - add.i32 $W0,$W0,@MSG[2] - sub $Ktbl,$Ktbl,#$rounds*$SZ-16 // rewind - orr $abcd,$ABCD,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - - add.i32 $W1,$W1,@MSG[3] - orr $abcd,$ABCD,$ABCD - sha256h $ABCD,$EFGH,$W1 - sha256h2 $EFGH,$abcd,$W1 - - add.i32 $ABCD,$ABCD,$ABCD_SAVE - add.i32 $EFGH,$EFGH,$EFGH_SAVE - - cbnz $num,.Loop_hw - - st1.32 {$ABCD,$EFGH},[$ctx] - - ldr x29,[sp],#16 - ret -.size sha256_block_armv8,.-sha256_block_armv8 -___ -} - -$code.=<<___; -.comm OPENSSL_armcap_P,4,4 -___ - -{ my %opcode = ( - "sha256h" => 0x5e004000, "sha256h2" => 0x5e005000, - "sha256su0" => 0x5e282800, "sha256su1" => 0x5e006000 ); - - sub unsha256 { - my ($mnemonic,$arg)=@_; - - $arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)[^,]*(?:,\s*[qv]([0-9]+))?/o - && - sprintf ".inst\t0x%08x\t//%s %s", - $opcode{$mnemonic}|$1|($2<<5)|($3<<16), - $mnemonic,$arg; - } -} - -foreach(split("\n",$code)) { - - s/\`([^\`]*)\`/eval($1)/geo; - - s/\b(sha256\w+)\s+([qv].*)/unsha256($1,$2)/geo; - - s/\.\w?32\b//o and s/\.16b/\.4s/go; - m/(ld|st)1[^\[]+\[0\]/o and s/\.4s/\.s/go; - - print $_,"\n"; -} - -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha512-ia64.pl b/app/openssl/crypto/sha/asm/sha512-ia64.pl deleted file mode 100755 index 1c6ce565..00000000 --- a/app/openssl/crypto/sha/asm/sha512-ia64.pl +++ /dev/null @@ -1,672 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== -# -# SHA256/512_Transform for Itanium. -# -# sha512_block runs in 1003 cycles on Itanium 2, which is almost 50% -# faster than gcc and >60%(!) faster than code generated by HP-UX -# compiler (yes, HP-UX is generating slower code, because unlike gcc, -# it failed to deploy "shift right pair," 'shrp' instruction, which -# substitutes for 64-bit rotate). -# -# 924 cycles long sha256_block outperforms gcc by over factor of 2(!) -# and HP-UX compiler - by >40% (yes, gcc won sha512_block, but lost -# this one big time). Note that "formally" 924 is about 100 cycles -# too much. I mean it's 64 32-bit rounds vs. 80 virtually identical -# 64-bit ones and 1003*64/80 gives 802. Extra cycles, 2 per round, -# are spent on extra work to provide for 32-bit rotations. 32-bit -# rotations are still handled by 'shrp' instruction and for this -# reason lower 32 bits are deposited to upper half of 64-bit register -# prior 'shrp' issue. And in order to minimize the amount of such -# operations, X[16] values are *maintained* with copies of lower -# halves in upper halves, which is why you'll spot such instructions -# as custom 'mux2', "parallel 32-bit add," 'padd4' and "parallel -# 32-bit unsigned right shift," 'pshr4.u' instructions here. -# -# Rules of engagement. -# -# There is only one integer shifter meaning that if I have two rotate, -# deposit or extract instructions in adjacent bundles, they shall -# split [at run-time if they have to]. But note that variable and -# parallel shifts are performed by multi-media ALU and *are* pairable -# with rotates [and alike]. On the backside MMALU is rather slow: it -# takes 2 extra cycles before the result of integer operation is -# available *to* MMALU and 2(*) extra cycles before the result of MM -# operation is available "back" *to* integer ALU, not to mention that -# MMALU itself has 2 cycles latency. However! I explicitly scheduled -# these MM instructions to avoid MM stalls, so that all these extra -# latencies get "hidden" in instruction-level parallelism. -# -# (*) 2 cycles on Itanium 1 and 1 cycle on Itanium 2. But I schedule -# for 2 in order to provide for best *overall* performance, -# because on Itanium 1 stall on MM result is accompanied by -# pipeline flush, which takes 6 cycles:-( -# -# Resulting performance numbers for 900MHz Itanium 2 system: -# -# The 'numbers' are in 1000s of bytes per second processed. -# type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes -# sha1(*) 6210.14k 20376.30k 52447.83k 85870.05k 105478.12k -# sha256 7476.45k 20572.05k 41538.34k 56062.29k 62093.18k -# sha512 4996.56k 20026.28k 47597.20k 85278.79k 111501.31k -# -# (*) SHA1 numbers are for HP-UX compiler and are presented purely -# for reference purposes. I bet it can improved too... -# -# To generate code, pass the file name with either 256 or 512 in its -# name and compiler flags. - -$output=shift; - -if ($output =~ /512.*\.[s|asm]/) { - $SZ=8; - $BITS=8*$SZ; - $LDW="ld8"; - $STW="st8"; - $ADD="add"; - $SHRU="shr.u"; - $TABLE="K512"; - $func="sha512_block_data_order"; - @Sigma0=(28,34,39); - @Sigma1=(14,18,41); - @sigma0=(1, 8, 7); - @sigma1=(19,61, 6); - $rounds=80; -} elsif ($output =~ /256.*\.[s|asm]/) { - $SZ=4; - $BITS=8*$SZ; - $LDW="ld4"; - $STW="st4"; - $ADD="padd4"; - $SHRU="pshr4.u"; - $TABLE="K256"; - $func="sha256_block_data_order"; - @Sigma0=( 2,13,22); - @Sigma1=( 6,11,25); - @sigma0=( 7,18, 3); - @sigma1=(17,19,10); - $rounds=64; -} else { die "nonsense $output"; } - -open STDOUT,">$output" || die "can't open $output: $!"; - -if ($^O eq "hpux") { - $ADDP="addp4"; - for (@ARGV) { $ADDP="add" if (/[\+DD|\-mlp]64/); } -} else { $ADDP="add"; } -for (@ARGV) { $big_endian=1 if (/\-DB_ENDIAN/); - $big_endian=0 if (/\-DL_ENDIAN/); } -if (!defined($big_endian)) - { $big_endian=(unpack('L',pack('N',1))==1); } - -$code=<<___; -.ident \"$output, version 1.1\" -.ident \"IA-64 ISA artwork by Andy Polyakov <appro\@fy.chalmers.se>\" -.explicit -.text - -pfssave=r2; -lcsave=r3; -prsave=r14; -K=r15; -A=r16; B=r17; C=r18; D=r19; -E=r20; F=r21; G=r22; H=r23; -T1=r24; T2=r25; -s0=r26; s1=r27; t0=r28; t1=r29; -Ktbl=r30; -ctx=r31; // 1st arg -input=r48; // 2nd arg -num=r49; // 3rd arg -sgm0=r50; sgm1=r51; // small constants -A_=r54; B_=r55; C_=r56; D_=r57; -E_=r58; F_=r59; G_=r60; H_=r61; - -// void $func (SHA_CTX *ctx, const void *in,size_t num[,int host]) -.global $func# -.proc $func# -.align 32 -$func: - .prologue - .save ar.pfs,pfssave -{ .mmi; alloc pfssave=ar.pfs,3,27,0,16 - $ADDP ctx=0,r32 // 1st arg - .save ar.lc,lcsave - mov lcsave=ar.lc } -{ .mmi; $ADDP input=0,r33 // 2nd arg - mov num=r34 // 3rd arg - .save pr,prsave - mov prsave=pr };; - - .body -{ .mib; add r8=0*$SZ,ctx - add r9=1*$SZ,ctx - brp.loop.imp .L_first16,.L_first16_end-16 } -{ .mib; add r10=2*$SZ,ctx - add r11=3*$SZ,ctx - brp.loop.imp .L_rest,.L_rest_end-16 };; - -// load A-H -.Lpic_point: -{ .mmi; $LDW A_=[r8],4*$SZ - $LDW B_=[r9],4*$SZ - mov Ktbl=ip } -{ .mmi; $LDW C_=[r10],4*$SZ - $LDW D_=[r11],4*$SZ - mov sgm0=$sigma0[2] };; -{ .mmi; $LDW E_=[r8] - $LDW F_=[r9] - add Ktbl=($TABLE#-.Lpic_point),Ktbl } -{ .mmi; $LDW G_=[r10] - $LDW H_=[r11] - cmp.ne p0,p16=0,r0 };; // used in sha256_block -___ -$code.=<<___ if ($BITS==64); -{ .mii; and r8=7,input - and input=~7,input;; - cmp.eq p9,p0=1,r8 } -{ .mmi; cmp.eq p10,p0=2,r8 - cmp.eq p11,p0=3,r8 - cmp.eq p12,p0=4,r8 } -{ .mmi; cmp.eq p13,p0=5,r8 - cmp.eq p14,p0=6,r8 - cmp.eq p15,p0=7,r8 };; -___ -$code.=<<___; -.L_outer: -.rotr X[16] -{ .mmi; mov A=A_ - mov B=B_ - mov ar.lc=14 } -{ .mmi; mov C=C_ - mov D=D_ - mov E=E_ } -{ .mmi; mov F=F_ - mov G=G_ - mov ar.ec=2 } -{ .mmi; ld1 X[15]=[input],$SZ // eliminated in 64-bit - mov H=H_ - mov sgm1=$sigma1[2] };; - -___ -$t0="t0", $t1="t1", $code.=<<___ if ($BITS==32); -.align 32 -.L_first16: -{ .mmi; add r9=1-$SZ,input - add r10=2-$SZ,input - add r11=3-$SZ,input };; -{ .mmi; ld1 r9=[r9] - ld1 r10=[r10] - dep.z $t1=E,32,32 } -{ .mmi; $LDW K=[Ktbl],$SZ - ld1 r11=[r11] - zxt4 E=E };; -{ .mii; or $t1=$t1,E - dep X[15]=X[15],r9,8,8 - dep r11=r10,r11,8,8 };; -{ .mmi; and T1=F,E - and T2=A,B - dep X[15]=X[15],r11,16,16 } -{ .mmi; andcm r8=G,E - and r9=A,C - mux2 $t0=A,0x44 };; // copy lower half to upper -{ .mmi; (p16) ld1 X[15-1]=[input],$SZ // prefetch - xor T1=T1,r8 // T1=((e & f) ^ (~e & g)) - _rotr r11=$t1,$Sigma1[0] } // ROTR(e,14) -{ .mib; and r10=B,C - xor T2=T2,r9 };; -___ -$t0="A", $t1="E", $code.=<<___ if ($BITS==64); -// in 64-bit mode I load whole X[16] at once and take care of alignment... -{ .mmi; add r8=1*$SZ,input - add r9=2*$SZ,input - add r10=3*$SZ,input };; -{ .mmb; $LDW X[15]=[input],4*$SZ - $LDW X[14]=[r8],4*$SZ -(p9) br.cond.dpnt.many .L1byte };; -{ .mmb; $LDW X[13]=[r9],4*$SZ - $LDW X[12]=[r10],4*$SZ -(p10) br.cond.dpnt.many .L2byte };; -{ .mmb; $LDW X[11]=[input],4*$SZ - $LDW X[10]=[r8],4*$SZ -(p11) br.cond.dpnt.many .L3byte };; -{ .mmb; $LDW X[ 9]=[r9],4*$SZ - $LDW X[ 8]=[r10],4*$SZ -(p12) br.cond.dpnt.many .L4byte };; -{ .mmb; $LDW X[ 7]=[input],4*$SZ - $LDW X[ 6]=[r8],4*$SZ -(p13) br.cond.dpnt.many .L5byte };; -{ .mmb; $LDW X[ 5]=[r9],4*$SZ - $LDW X[ 4]=[r10],4*$SZ -(p14) br.cond.dpnt.many .L6byte };; -{ .mmb; $LDW X[ 3]=[input],4*$SZ - $LDW X[ 2]=[r8],4*$SZ -(p15) br.cond.dpnt.many .L7byte };; -{ .mmb; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - br.many .L_first16 };; -.L1byte: -{ .mmi; $LDW X[13]=[r9],4*$SZ - $LDW X[12]=[r10],4*$SZ - shrp X[15]=X[15],X[14],56 };; -{ .mmi; $LDW X[11]=[input],4*$SZ - $LDW X[10]=[r8],4*$SZ - shrp X[14]=X[14],X[13],56 } -{ .mmi; $LDW X[ 9]=[r9],4*$SZ - $LDW X[ 8]=[r10],4*$SZ - shrp X[13]=X[13],X[12],56 };; -{ .mmi; $LDW X[ 7]=[input],4*$SZ - $LDW X[ 6]=[r8],4*$SZ - shrp X[12]=X[12],X[11],56 } -{ .mmi; $LDW X[ 5]=[r9],4*$SZ - $LDW X[ 4]=[r10],4*$SZ - shrp X[11]=X[11],X[10],56 };; -{ .mmi; $LDW X[ 3]=[input],4*$SZ - $LDW X[ 2]=[r8],4*$SZ - shrp X[10]=X[10],X[ 9],56 } -{ .mmi; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - shrp X[ 9]=X[ 9],X[ 8],56 };; -{ .mii; $LDW T1=[input] - shrp X[ 8]=X[ 8],X[ 7],56 - shrp X[ 7]=X[ 7],X[ 6],56 } -{ .mii; shrp X[ 6]=X[ 6],X[ 5],56 - shrp X[ 5]=X[ 5],X[ 4],56 };; -{ .mii; shrp X[ 4]=X[ 4],X[ 3],56 - shrp X[ 3]=X[ 3],X[ 2],56 } -{ .mii; shrp X[ 2]=X[ 2],X[ 1],56 - shrp X[ 1]=X[ 1],X[ 0],56 } -{ .mib; shrp X[ 0]=X[ 0],T1,56 - br.many .L_first16 };; -.L2byte: -{ .mmi; $LDW X[11]=[input],4*$SZ - $LDW X[10]=[r8],4*$SZ - shrp X[15]=X[15],X[14],48 } -{ .mmi; $LDW X[ 9]=[r9],4*$SZ - $LDW X[ 8]=[r10],4*$SZ - shrp X[14]=X[14],X[13],48 };; -{ .mmi; $LDW X[ 7]=[input],4*$SZ - $LDW X[ 6]=[r8],4*$SZ - shrp X[13]=X[13],X[12],48 } -{ .mmi; $LDW X[ 5]=[r9],4*$SZ - $LDW X[ 4]=[r10],4*$SZ - shrp X[12]=X[12],X[11],48 };; -{ .mmi; $LDW X[ 3]=[input],4*$SZ - $LDW X[ 2]=[r8],4*$SZ - shrp X[11]=X[11],X[10],48 } -{ .mmi; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - shrp X[10]=X[10],X[ 9],48 };; -{ .mii; $LDW T1=[input] - shrp X[ 9]=X[ 9],X[ 8],48 - shrp X[ 8]=X[ 8],X[ 7],48 } -{ .mii; shrp X[ 7]=X[ 7],X[ 6],48 - shrp X[ 6]=X[ 6],X[ 5],48 };; -{ .mii; shrp X[ 5]=X[ 5],X[ 4],48 - shrp X[ 4]=X[ 4],X[ 3],48 } -{ .mii; shrp X[ 3]=X[ 3],X[ 2],48 - shrp X[ 2]=X[ 2],X[ 1],48 } -{ .mii; shrp X[ 1]=X[ 1],X[ 0],48 - shrp X[ 0]=X[ 0],T1,48 } -{ .mfb; br.many .L_first16 };; -.L3byte: -{ .mmi; $LDW X[ 9]=[r9],4*$SZ - $LDW X[ 8]=[r10],4*$SZ - shrp X[15]=X[15],X[14],40 };; -{ .mmi; $LDW X[ 7]=[input],4*$SZ - $LDW X[ 6]=[r8],4*$SZ - shrp X[14]=X[14],X[13],40 } -{ .mmi; $LDW X[ 5]=[r9],4*$SZ - $LDW X[ 4]=[r10],4*$SZ - shrp X[13]=X[13],X[12],40 };; -{ .mmi; $LDW X[ 3]=[input],4*$SZ - $LDW X[ 2]=[r8],4*$SZ - shrp X[12]=X[12],X[11],40 } -{ .mmi; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - shrp X[11]=X[11],X[10],40 };; -{ .mii; $LDW T1=[input] - shrp X[10]=X[10],X[ 9],40 - shrp X[ 9]=X[ 9],X[ 8],40 } -{ .mii; shrp X[ 8]=X[ 8],X[ 7],40 - shrp X[ 7]=X[ 7],X[ 6],40 };; -{ .mii; shrp X[ 6]=X[ 6],X[ 5],40 - shrp X[ 5]=X[ 5],X[ 4],40 } -{ .mii; shrp X[ 4]=X[ 4],X[ 3],40 - shrp X[ 3]=X[ 3],X[ 2],40 } -{ .mii; shrp X[ 2]=X[ 2],X[ 1],40 - shrp X[ 1]=X[ 1],X[ 0],40 } -{ .mib; shrp X[ 0]=X[ 0],T1,40 - br.many .L_first16 };; -.L4byte: -{ .mmi; $LDW X[ 7]=[input],4*$SZ - $LDW X[ 6]=[r8],4*$SZ - shrp X[15]=X[15],X[14],32 } -{ .mmi; $LDW X[ 5]=[r9],4*$SZ - $LDW X[ 4]=[r10],4*$SZ - shrp X[14]=X[14],X[13],32 };; -{ .mmi; $LDW X[ 3]=[input],4*$SZ - $LDW X[ 2]=[r8],4*$SZ - shrp X[13]=X[13],X[12],32 } -{ .mmi; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - shrp X[12]=X[12],X[11],32 };; -{ .mii; $LDW T1=[input] - shrp X[11]=X[11],X[10],32 - shrp X[10]=X[10],X[ 9],32 } -{ .mii; shrp X[ 9]=X[ 9],X[ 8],32 - shrp X[ 8]=X[ 8],X[ 7],32 };; -{ .mii; shrp X[ 7]=X[ 7],X[ 6],32 - shrp X[ 6]=X[ 6],X[ 5],32 } -{ .mii; shrp X[ 5]=X[ 5],X[ 4],32 - shrp X[ 4]=X[ 4],X[ 3],32 } -{ .mii; shrp X[ 3]=X[ 3],X[ 2],32 - shrp X[ 2]=X[ 2],X[ 1],32 } -{ .mii; shrp X[ 1]=X[ 1],X[ 0],32 - shrp X[ 0]=X[ 0],T1,32 } -{ .mfb; br.many .L_first16 };; -.L5byte: -{ .mmi; $LDW X[ 5]=[r9],4*$SZ - $LDW X[ 4]=[r10],4*$SZ - shrp X[15]=X[15],X[14],24 };; -{ .mmi; $LDW X[ 3]=[input],4*$SZ - $LDW X[ 2]=[r8],4*$SZ - shrp X[14]=X[14],X[13],24 } -{ .mmi; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - shrp X[13]=X[13],X[12],24 };; -{ .mii; $LDW T1=[input] - shrp X[12]=X[12],X[11],24 - shrp X[11]=X[11],X[10],24 } -{ .mii; shrp X[10]=X[10],X[ 9],24 - shrp X[ 9]=X[ 9],X[ 8],24 };; -{ .mii; shrp X[ 8]=X[ 8],X[ 7],24 - shrp X[ 7]=X[ 7],X[ 6],24 } -{ .mii; shrp X[ 6]=X[ 6],X[ 5],24 - shrp X[ 5]=X[ 5],X[ 4],24 } -{ .mii; shrp X[ 4]=X[ 4],X[ 3],24 - shrp X[ 3]=X[ 3],X[ 2],24 } -{ .mii; shrp X[ 2]=X[ 2],X[ 1],24 - shrp X[ 1]=X[ 1],X[ 0],24 } -{ .mib; shrp X[ 0]=X[ 0],T1,24 - br.many .L_first16 };; -.L6byte: -{ .mmi; $LDW X[ 3]=[input],4*$SZ - $LDW X[ 2]=[r8],4*$SZ - shrp X[15]=X[15],X[14],16 } -{ .mmi; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - shrp X[14]=X[14],X[13],16 };; -{ .mii; $LDW T1=[input] - shrp X[13]=X[13],X[12],16 - shrp X[12]=X[12],X[11],16 } -{ .mii; shrp X[11]=X[11],X[10],16 - shrp X[10]=X[10],X[ 9],16 };; -{ .mii; shrp X[ 9]=X[ 9],X[ 8],16 - shrp X[ 8]=X[ 8],X[ 7],16 } -{ .mii; shrp X[ 7]=X[ 7],X[ 6],16 - shrp X[ 6]=X[ 6],X[ 5],16 } -{ .mii; shrp X[ 5]=X[ 5],X[ 4],16 - shrp X[ 4]=X[ 4],X[ 3],16 } -{ .mii; shrp X[ 3]=X[ 3],X[ 2],16 - shrp X[ 2]=X[ 2],X[ 1],16 } -{ .mii; shrp X[ 1]=X[ 1],X[ 0],16 - shrp X[ 0]=X[ 0],T1,16 } -{ .mfb; br.many .L_first16 };; -.L7byte: -{ .mmi; $LDW X[ 1]=[r9],4*$SZ - $LDW X[ 0]=[r10],4*$SZ - shrp X[15]=X[15],X[14],8 };; -{ .mii; $LDW T1=[input] - shrp X[14]=X[14],X[13],8 - shrp X[13]=X[13],X[12],8 } -{ .mii; shrp X[12]=X[12],X[11],8 - shrp X[11]=X[11],X[10],8 };; -{ .mii; shrp X[10]=X[10],X[ 9],8 - shrp X[ 9]=X[ 9],X[ 8],8 } -{ .mii; shrp X[ 8]=X[ 8],X[ 7],8 - shrp X[ 7]=X[ 7],X[ 6],8 } -{ .mii; shrp X[ 6]=X[ 6],X[ 5],8 - shrp X[ 5]=X[ 5],X[ 4],8 } -{ .mii; shrp X[ 4]=X[ 4],X[ 3],8 - shrp X[ 3]=X[ 3],X[ 2],8 } -{ .mii; shrp X[ 2]=X[ 2],X[ 1],8 - shrp X[ 1]=X[ 1],X[ 0],8 } -{ .mib; shrp X[ 0]=X[ 0],T1,8 - br.many .L_first16 };; - -.align 32 -.L_first16: -{ .mmi; $LDW K=[Ktbl],$SZ - and T1=F,E - and T2=A,B } -{ .mmi; //$LDW X[15]=[input],$SZ // X[i]=*input++ - andcm r8=G,E - and r9=A,C };; -{ .mmi; xor T1=T1,r8 //T1=((e & f) ^ (~e & g)) - and r10=B,C - _rotr r11=$t1,$Sigma1[0] } // ROTR(e,14) -{ .mmi; xor T2=T2,r9 - mux1 X[15]=X[15],\@rev };; // eliminated in big-endian -___ -$code.=<<___; -{ .mib; add T1=T1,H // T1=Ch(e,f,g)+h - _rotr r8=$t1,$Sigma1[1] } // ROTR(e,18) -{ .mib; xor T2=T2,r10 // T2=((a & b) ^ (a & c) ^ (b & c)) - mov H=G };; -{ .mib; xor r11=r8,r11 - _rotr r9=$t1,$Sigma1[2] } // ROTR(e,41) -{ .mib; mov G=F - mov F=E };; -{ .mib; xor r9=r9,r11 // r9=Sigma1(e) - _rotr r10=$t0,$Sigma0[0] } // ROTR(a,28) -{ .mib; add T1=T1,K // T1=Ch(e,f,g)+h+K512[i] - mov E=D };; -{ .mib; add T1=T1,r9 // T1+=Sigma1(e) - _rotr r11=$t0,$Sigma0[1] } // ROTR(a,34) -{ .mib; mov D=C - mov C=B };; -{ .mib; add T1=T1,X[15] // T1+=X[i] - _rotr r8=$t0,$Sigma0[2] } // ROTR(a,39) -{ .mib; xor r10=r10,r11 - mux2 X[15]=X[15],0x44 };; // eliminated in 64-bit -{ .mmi; xor r10=r8,r10 // r10=Sigma0(a) - mov B=A - add A=T1,T2 };; -{ .mib; add E=E,T1 - add A=A,r10 // T2=Maj(a,b,c)+Sigma0(a) - br.ctop.sptk .L_first16 };; -.L_first16_end: - -{ .mii; mov ar.lc=$rounds-17 - mov ar.ec=1 };; - -.align 32 -.L_rest: -.rotr X[16] -{ .mib; $LDW K=[Ktbl],$SZ - _rotr r8=X[15-1],$sigma0[0] } // ROTR(s0,1) -{ .mib; $ADD X[15]=X[15],X[15-9] // X[i&0xF]+=X[(i+9)&0xF] - $SHRU s0=X[15-1],sgm0 };; // s0=X[(i+1)&0xF]>>7 -{ .mib; and T1=F,E - _rotr r9=X[15-1],$sigma0[1] } // ROTR(s0,8) -{ .mib; andcm r10=G,E - $SHRU s1=X[15-14],sgm1 };; // s1=X[(i+14)&0xF]>>6 -{ .mmi; xor T1=T1,r10 // T1=((e & f) ^ (~e & g)) - xor r9=r8,r9 - _rotr r10=X[15-14],$sigma1[0] };;// ROTR(s1,19) -{ .mib; and T2=A,B - _rotr r11=X[15-14],$sigma1[1] }// ROTR(s1,61) -{ .mib; and r8=A,C };; -___ -$t0="t0", $t1="t1", $code.=<<___ if ($BITS==32); -// I adhere to mmi; in order to hold Itanium 1 back and avoid 6 cycle -// pipeline flush in last bundle. Note that even on Itanium2 the -// latter stalls for one clock cycle... -{ .mmi; xor s0=s0,r9 // s0=sigma0(X[(i+1)&0xF]) - dep.z $t1=E,32,32 } -{ .mmi; xor r10=r11,r10 - zxt4 E=E };; -{ .mmi; or $t1=$t1,E - xor s1=s1,r10 // s1=sigma1(X[(i+14)&0xF]) - mux2 $t0=A,0x44 };; // copy lower half to upper -{ .mmi; xor T2=T2,r8 - _rotr r9=$t1,$Sigma1[0] } // ROTR(e,14) -{ .mmi; and r10=B,C - add T1=T1,H // T1=Ch(e,f,g)+h - $ADD X[15]=X[15],s0 };; // X[i&0xF]+=sigma0(X[(i+1)&0xF]) -___ -$t0="A", $t1="E", $code.=<<___ if ($BITS==64); -{ .mib; xor s0=s0,r9 // s0=sigma0(X[(i+1)&0xF]) - _rotr r9=$t1,$Sigma1[0] } // ROTR(e,14) -{ .mib; xor r10=r11,r10 - xor T2=T2,r8 };; -{ .mib; xor s1=s1,r10 // s1=sigma1(X[(i+14)&0xF]) - add T1=T1,H } -{ .mib; and r10=B,C - $ADD X[15]=X[15],s0 };; // X[i&0xF]+=sigma0(X[(i+1)&0xF]) -___ -$code.=<<___; -{ .mmi; xor T2=T2,r10 // T2=((a & b) ^ (a & c) ^ (b & c)) - mov H=G - _rotr r8=$t1,$Sigma1[1] };; // ROTR(e,18) -{ .mmi; xor r11=r8,r9 - $ADD X[15]=X[15],s1 // X[i&0xF]+=sigma1(X[(i+14)&0xF]) - _rotr r9=$t1,$Sigma1[2] } // ROTR(e,41) -{ .mmi; mov G=F - mov F=E };; -{ .mib; xor r9=r9,r11 // r9=Sigma1(e) - _rotr r10=$t0,$Sigma0[0] } // ROTR(a,28) -{ .mib; add T1=T1,K // T1=Ch(e,f,g)+h+K512[i] - mov E=D };; -{ .mib; add T1=T1,r9 // T1+=Sigma1(e) - _rotr r11=$t0,$Sigma0[1] } // ROTR(a,34) -{ .mib; mov D=C - mov C=B };; -{ .mmi; add T1=T1,X[15] // T1+=X[i] - xor r10=r10,r11 - _rotr r8=$t0,$Sigma0[2] };; // ROTR(a,39) -{ .mmi; xor r10=r8,r10 // r10=Sigma0(a) - mov B=A - add A=T1,T2 };; -{ .mib; add E=E,T1 - add A=A,r10 // T2=Maj(a,b,c)+Sigma0(a) - br.ctop.sptk .L_rest };; -.L_rest_end: - -{ .mmi; add A_=A_,A - add B_=B_,B - add C_=C_,C } -{ .mmi; add D_=D_,D - add E_=E_,E - cmp.ltu p16,p0=1,num };; -{ .mmi; add F_=F_,F - add G_=G_,G - add H_=H_,H } -{ .mmb; add Ktbl=-$SZ*$rounds,Ktbl -(p16) add num=-1,num -(p16) br.dptk.many .L_outer };; - -{ .mib; add r8=0*$SZ,ctx - add r9=1*$SZ,ctx } -{ .mib; add r10=2*$SZ,ctx - add r11=3*$SZ,ctx };; -{ .mmi; $STW [r8]=A_,4*$SZ - $STW [r9]=B_,4*$SZ - mov ar.lc=lcsave } -{ .mmi; $STW [r10]=C_,4*$SZ - $STW [r11]=D_,4*$SZ - mov pr=prsave,0x1ffff };; -{ .mmb; $STW [r8]=E_ - $STW [r9]=F_ } -{ .mmb; $STW [r10]=G_ - $STW [r11]=H_ - br.ret.sptk.many b0 };; -.endp $func# -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -$code =~ s/_rotr(\s+)([^=]+)=([^,]+),([0-9]+)/shrp$1$2=$3,$3,$4/gm; -if ($BITS==64) { - $code =~ s/mux2(\s+)\S+/nop.i$1 0x0/gm; - $code =~ s/mux1(\s+)\S+/nop.i$1 0x0/gm if ($big_endian); - $code =~ s/(shrp\s+X\[[^=]+)=([^,]+),([^,]+),([1-9]+)/$1=$3,$2,64-$4/gm - if (!$big_endian); - $code =~ s/ld1(\s+)X\[\S+/nop.m$1 0x0/gm; -} - -print $code; - -print<<___ if ($BITS==32); -.align 64 -.type K256#,\@object -K256: data4 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 - data4 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 - data4 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 - data4 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 - data4 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc - data4 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da - data4 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 - data4 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 - data4 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 - data4 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 - data4 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 - data4 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 - data4 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 - data4 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 - data4 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 - data4 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -.size K256#,$SZ*$rounds -stringz "SHA256 block transform for IA64, CRYPTOGAMS by <appro\@openssl.org>" -___ -print<<___ if ($BITS==64); -.align 64 -.type K512#,\@object -K512: data8 0x428a2f98d728ae22,0x7137449123ef65cd - data8 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc - data8 0x3956c25bf348b538,0x59f111f1b605d019 - data8 0x923f82a4af194f9b,0xab1c5ed5da6d8118 - data8 0xd807aa98a3030242,0x12835b0145706fbe - data8 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2 - data8 0x72be5d74f27b896f,0x80deb1fe3b1696b1 - data8 0x9bdc06a725c71235,0xc19bf174cf692694 - data8 0xe49b69c19ef14ad2,0xefbe4786384f25e3 - data8 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65 - data8 0x2de92c6f592b0275,0x4a7484aa6ea6e483 - data8 0x5cb0a9dcbd41fbd4,0x76f988da831153b5 - data8 0x983e5152ee66dfab,0xa831c66d2db43210 - data8 0xb00327c898fb213f,0xbf597fc7beef0ee4 - data8 0xc6e00bf33da88fc2,0xd5a79147930aa725 - data8 0x06ca6351e003826f,0x142929670a0e6e70 - data8 0x27b70a8546d22ffc,0x2e1b21385c26c926 - data8 0x4d2c6dfc5ac42aed,0x53380d139d95b3df - data8 0x650a73548baf63de,0x766a0abb3c77b2a8 - data8 0x81c2c92e47edaee6,0x92722c851482353b - data8 0xa2bfe8a14cf10364,0xa81a664bbc423001 - data8 0xc24b8b70d0f89791,0xc76c51a30654be30 - data8 0xd192e819d6ef5218,0xd69906245565a910 - data8 0xf40e35855771202a,0x106aa07032bbd1b8 - data8 0x19a4c116b8d2d0c8,0x1e376c085141ab53 - data8 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8 - data8 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb - data8 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3 - data8 0x748f82ee5defb2fc,0x78a5636f43172f60 - data8 0x84c87814a1f0ab72,0x8cc702081a6439ec - data8 0x90befffa23631e28,0xa4506cebde82bde9 - data8 0xbef9a3f7b2c67915,0xc67178f2e372532b - data8 0xca273eceea26619c,0xd186b8c721c0c207 - data8 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178 - data8 0x06f067aa72176fba,0x0a637dc5a2c898a6 - data8 0x113f9804bef90dae,0x1b710b35131c471b - data8 0x28db77f523047d84,0x32caab7b40c72493 - data8 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c - data8 0x4cc5d4becb3e42b6,0x597f299cfc657e2a - data8 0x5fcb6fab3ad6faec,0x6c44198c4a475817 -.size K512#,$SZ*$rounds -stringz "SHA512 block transform for IA64, CRYPTOGAMS by <appro\@openssl.org>" -___ diff --git a/app/openssl/crypto/sha/asm/sha512-mips.pl b/app/openssl/crypto/sha/asm/sha512-mips.pl deleted file mode 100644 index ffa053bb..00000000 --- a/app/openssl/crypto/sha/asm/sha512-mips.pl +++ /dev/null @@ -1,455 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA2 block procedures for MIPS. - -# October 2010. -# -# SHA256 performance improvement on MIPS R5000 CPU is ~27% over gcc- -# generated code in o32 build and ~55% in n32/64 build. SHA512 [which -# for now can only be compiled for MIPS64 ISA] improvement is modest -# ~17%, but it comes for free, because it's same instruction sequence. -# Improvement coefficients are for aligned input. - -###################################################################### -# There is a number of MIPS ABI in use, O32 and N32/64 are most -# widely used. Then there is a new contender: NUBI. It appears that if -# one picks the latter, it's possible to arrange code in ABI neutral -# manner. Therefore let's stick to NUBI register layout: -# -($zero,$at,$t0,$t1,$t2)=map("\$$_",(0..2,24,25)); -($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11)); -($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7,$s8,$s9,$s10,$s11)=map("\$$_",(12..23)); -($gp,$tp,$sp,$fp,$ra)=map("\$$_",(3,28..31)); -# -# The return value is placed in $a0. Following coding rules facilitate -# interoperability: -# -# - never ever touch $tp, "thread pointer", former $gp [o32 can be -# excluded from the rule, because it's specified volatile]; -# - copy return value to $t0, former $v0 [or to $a0 if you're adapting -# old code]; -# - on O32 populate $a4-$a7 with 'lw $aN,4*N($sp)' if necessary; -# -# For reference here is register layout for N32/64 MIPS ABIs: -# -# ($zero,$at,$v0,$v1)=map("\$$_",(0..3)); -# ($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11)); -# ($t0,$t1,$t2,$t3,$t8,$t9)=map("\$$_",(12..15,24,25)); -# ($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7)=map("\$$_",(16..23)); -# ($gp,$sp,$fp,$ra)=map("\$$_",(28..31)); -# -$flavour = shift; # supported flavours are o32,n32,64,nubi32,nubi64 - -if ($flavour =~ /64|n32/i) { - $PTR_ADD="dadd"; # incidentally works even on n32 - $PTR_SUB="dsub"; # incidentally works even on n32 - $REG_S="sd"; - $REG_L="ld"; - $PTR_SLL="dsll"; # incidentally works even on n32 - $SZREG=8; -} else { - $PTR_ADD="add"; - $PTR_SUB="sub"; - $REG_S="sw"; - $REG_L="lw"; - $PTR_SLL="sll"; - $SZREG=4; -} -$pf = ($flavour =~ /nubi/i) ? $t0 : $t2; -# -# <appro@openssl.org> -# -###################################################################### - -$big_endian=(`echo MIPSEL | $ENV{CC} -E -P -`=~/MIPSEL/)?1:0; - -for (@ARGV) { $output=$_ if (/^\w[\w\-]*\.\w+$/); } -open STDOUT,">$output"; - -if (!defined($big_endian)) { $big_endian=(unpack('L',pack('N',1))==1); } - -if ($output =~ /512/) { - $label="512"; - $SZ=8; - $LD="ld"; # load from memory - $ST="sd"; # store to memory - $SLL="dsll"; # shift left logical - $SRL="dsrl"; # shift right logical - $ADDU="daddu"; - @Sigma0=(28,34,39); - @Sigma1=(14,18,41); - @sigma0=( 7, 1, 8); # right shift first - @sigma1=( 6,19,61); # right shift first - $lastK=0x817; - $rounds=80; -} else { - $label="256"; - $SZ=4; - $LD="lw"; # load from memory - $ST="sw"; # store to memory - $SLL="sll"; # shift left logical - $SRL="srl"; # shift right logical - $ADDU="addu"; - @Sigma0=( 2,13,22); - @Sigma1=( 6,11,25); - @sigma0=( 3, 7,18); # right shift first - @sigma1=(10,17,19); # right shift first - $lastK=0x8f2; - $rounds=64; -} - -$MSB = $big_endian ? 0 : ($SZ-1); -$LSB = ($SZ-1)&~$MSB; - -@V=($A,$B,$C,$D,$E,$F,$G,$H)=map("\$$_",(1,2,3,7,24,25,30,31)); -@X=map("\$$_",(8..23)); - -$ctx=$a0; -$inp=$a1; -$len=$a2; $Ktbl=$len; - -sub BODY_00_15 { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; -my ($T1,$tmp0,$tmp1,$tmp2)=(@X[4],@X[5],@X[6],@X[7]); - -$code.=<<___ if ($i<15); - ${LD}l @X[1],`($i+1)*$SZ+$MSB`($inp) - ${LD}r @X[1],`($i+1)*$SZ+$LSB`($inp) -___ -$code.=<<___ if (!$big_endian && $i<16 && $SZ==4); - srl $tmp0,@X[0],24 # byte swap($i) - srl $tmp1,@X[0],8 - andi $tmp2,@X[0],0xFF00 - sll @X[0],@X[0],24 - andi $tmp1,0xFF00 - sll $tmp2,$tmp2,8 - or @X[0],$tmp0 - or $tmp1,$tmp2 - or @X[0],$tmp1 -___ -$code.=<<___ if (!$big_endian && $i<16 && $SZ==8); - ori $tmp0,$zero,0xFF - dsll $tmp2,$tmp0,32 - or $tmp0,$tmp2 # 0x000000FF000000FF - and $tmp1,@X[0],$tmp0 # byte swap($i) - dsrl $tmp2,@X[0],24 - dsll $tmp1,24 - and $tmp2,$tmp0 - dsll $tmp0,8 # 0x0000FF000000FF00 - or $tmp1,$tmp2 - and $tmp2,@X[0],$tmp0 - dsrl @X[0],8 - dsll $tmp2,8 - and @X[0],$tmp0 - or $tmp1,$tmp2 - or @X[0],$tmp1 - dsrl $tmp1,@X[0],32 - dsll @X[0],32 - or @X[0],$tmp1 -___ -$code.=<<___; - $ADDU $T1,$X[0],$h # $i - $SRL $h,$e,@Sigma1[0] - xor $tmp2,$f,$g - $SLL $tmp1,$e,`$SZ*8-@Sigma1[2]` - and $tmp2,$e - $SRL $tmp0,$e,@Sigma1[1] - xor $h,$tmp1 - $SLL $tmp1,$e,`$SZ*8-@Sigma1[1]` - xor $h,$tmp0 - $SRL $tmp0,$e,@Sigma1[2] - xor $h,$tmp1 - $SLL $tmp1,$e,`$SZ*8-@Sigma1[0]` - xor $h,$tmp0 - xor $tmp2,$g # Ch(e,f,g) - xor $tmp0,$tmp1,$h # Sigma1(e) - - $SRL $h,$a,@Sigma0[0] - $ADDU $T1,$tmp2 - $LD $tmp2,`$i*$SZ`($Ktbl) # K[$i] - $SLL $tmp1,$a,`$SZ*8-@Sigma0[2]` - $ADDU $T1,$tmp0 - $SRL $tmp0,$a,@Sigma0[1] - xor $h,$tmp1 - $SLL $tmp1,$a,`$SZ*8-@Sigma0[1]` - xor $h,$tmp0 - $SRL $tmp0,$a,@Sigma0[2] - xor $h,$tmp1 - $SLL $tmp1,$a,`$SZ*8-@Sigma0[0]` - xor $h,$tmp0 - $ST @X[0],`($i%16)*$SZ`($sp) # offload to ring buffer - xor $h,$tmp1 # Sigma0(a) - - or $tmp0,$a,$b - and $tmp1,$a,$b - and $tmp0,$c - or $tmp1,$tmp0 # Maj(a,b,c) - $ADDU $T1,$tmp2 # +=K[$i] - $ADDU $h,$tmp1 - - $ADDU $d,$T1 - $ADDU $h,$T1 -___ -$code.=<<___ if ($i>=13); - $LD @X[3],`(($i+3)%16)*$SZ`($sp) # prefetch from ring buffer -___ -} - -sub BODY_16_XX { -my $i=@_[0]; -my ($tmp0,$tmp1,$tmp2,$tmp3)=(@X[4],@X[5],@X[6],@X[7]); - -$code.=<<___; - $SRL $tmp2,@X[1],@sigma0[0] # Xupdate($i) - $ADDU @X[0],@X[9] # +=X[i+9] - $SLL $tmp1,@X[1],`$SZ*8-@sigma0[2]` - $SRL $tmp0,@X[1],@sigma0[1] - xor $tmp2,$tmp1 - $SLL $tmp1,`@sigma0[2]-@sigma0[1]` - xor $tmp2,$tmp0 - $SRL $tmp0,@X[1],@sigma0[2] - xor $tmp2,$tmp1 - - $SRL $tmp3,@X[14],@sigma1[0] - xor $tmp2,$tmp0 # sigma0(X[i+1]) - $SLL $tmp1,@X[14],`$SZ*8-@sigma1[2]` - $ADDU @X[0],$tmp2 - $SRL $tmp0,@X[14],@sigma1[1] - xor $tmp3,$tmp1 - $SLL $tmp1,`@sigma1[2]-@sigma1[1]` - xor $tmp3,$tmp0 - $SRL $tmp0,@X[14],@sigma1[2] - xor $tmp3,$tmp1 - - xor $tmp3,$tmp0 # sigma1(X[i+14]) - $ADDU @X[0],$tmp3 -___ - &BODY_00_15(@_); -} - -$FRAMESIZE=16*$SZ+16*$SZREG; -$SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? 0xc0fff008 : 0xc0ff0000; - -$code.=<<___; -#ifdef OPENSSL_FIPSCANISTER -# include <openssl/fipssyms.h> -#endif - -.text -.set noat -#if !defined(__vxworks) || defined(__pic__) -.option pic2 -#endif - -.align 5 -.globl sha${label}_block_data_order -.ent sha${label}_block_data_order -sha${label}_block_data_order: - .frame $sp,$FRAMESIZE,$ra - .mask $SAVED_REGS_MASK,-$SZREG - .set noreorder -___ -$code.=<<___ if ($flavour =~ /o32/i); # o32 PIC-ification - .cpload $pf -___ -$code.=<<___; - $PTR_SUB $sp,$FRAMESIZE - $REG_S $ra,$FRAMESIZE-1*$SZREG($sp) - $REG_S $fp,$FRAMESIZE-2*$SZREG($sp) - $REG_S $s11,$FRAMESIZE-3*$SZREG($sp) - $REG_S $s10,$FRAMESIZE-4*$SZREG($sp) - $REG_S $s9,$FRAMESIZE-5*$SZREG($sp) - $REG_S $s8,$FRAMESIZE-6*$SZREG($sp) - $REG_S $s7,$FRAMESIZE-7*$SZREG($sp) - $REG_S $s6,$FRAMESIZE-8*$SZREG($sp) - $REG_S $s5,$FRAMESIZE-9*$SZREG($sp) - $REG_S $s4,$FRAMESIZE-10*$SZREG($sp) -___ -$code.=<<___ if ($flavour =~ /nubi/i); # optimize non-nubi prologue - $REG_S $s3,$FRAMESIZE-11*$SZREG($sp) - $REG_S $s2,$FRAMESIZE-12*$SZREG($sp) - $REG_S $s1,$FRAMESIZE-13*$SZREG($sp) - $REG_S $s0,$FRAMESIZE-14*$SZREG($sp) - $REG_S $gp,$FRAMESIZE-15*$SZREG($sp) -___ -$code.=<<___; - $PTR_SLL @X[15],$len,`log(16*$SZ)/log(2)` -___ -$code.=<<___ if ($flavour !~ /o32/i); # non-o32 PIC-ification - .cplocal $Ktbl - .cpsetup $pf,$zero,sha${label}_block_data_order -___ -$code.=<<___; - .set reorder - la $Ktbl,K${label} # PIC-ified 'load address' - - $LD $A,0*$SZ($ctx) # load context - $LD $B,1*$SZ($ctx) - $LD $C,2*$SZ($ctx) - $LD $D,3*$SZ($ctx) - $LD $E,4*$SZ($ctx) - $LD $F,5*$SZ($ctx) - $LD $G,6*$SZ($ctx) - $LD $H,7*$SZ($ctx) - - $PTR_ADD @X[15],$inp # pointer to the end of input - $REG_S @X[15],16*$SZ($sp) - b .Loop - -.align 5 -.Loop: - ${LD}l @X[0],$MSB($inp) - ${LD}r @X[0],$LSB($inp) -___ -for ($i=0;$i<16;$i++) -{ &BODY_00_15($i,@V); unshift(@V,pop(@V)); push(@X,shift(@X)); } -$code.=<<___; - b .L16_xx -.align 4 -.L16_xx: -___ -for (;$i<32;$i++) -{ &BODY_16_XX($i,@V); unshift(@V,pop(@V)); push(@X,shift(@X)); } -$code.=<<___; - and @X[6],0xfff - li @X[7],$lastK - .set noreorder - bne @X[6],@X[7],.L16_xx - $PTR_ADD $Ktbl,16*$SZ # Ktbl+=16 - - $REG_L @X[15],16*$SZ($sp) # restore pointer to the end of input - $LD @X[0],0*$SZ($ctx) - $LD @X[1],1*$SZ($ctx) - $LD @X[2],2*$SZ($ctx) - $PTR_ADD $inp,16*$SZ - $LD @X[3],3*$SZ($ctx) - $ADDU $A,@X[0] - $LD @X[4],4*$SZ($ctx) - $ADDU $B,@X[1] - $LD @X[5],5*$SZ($ctx) - $ADDU $C,@X[2] - $LD @X[6],6*$SZ($ctx) - $ADDU $D,@X[3] - $LD @X[7],7*$SZ($ctx) - $ADDU $E,@X[4] - $ST $A,0*$SZ($ctx) - $ADDU $F,@X[5] - $ST $B,1*$SZ($ctx) - $ADDU $G,@X[6] - $ST $C,2*$SZ($ctx) - $ADDU $H,@X[7] - $ST $D,3*$SZ($ctx) - $ST $E,4*$SZ($ctx) - $ST $F,5*$SZ($ctx) - $ST $G,6*$SZ($ctx) - $ST $H,7*$SZ($ctx) - - bne $inp,@X[15],.Loop - $PTR_SUB $Ktbl,`($rounds-16)*$SZ` # rewind $Ktbl - - $REG_L $ra,$FRAMESIZE-1*$SZREG($sp) - $REG_L $fp,$FRAMESIZE-2*$SZREG($sp) - $REG_L $s11,$FRAMESIZE-3*$SZREG($sp) - $REG_L $s10,$FRAMESIZE-4*$SZREG($sp) - $REG_L $s9,$FRAMESIZE-5*$SZREG($sp) - $REG_L $s8,$FRAMESIZE-6*$SZREG($sp) - $REG_L $s7,$FRAMESIZE-7*$SZREG($sp) - $REG_L $s6,$FRAMESIZE-8*$SZREG($sp) - $REG_L $s5,$FRAMESIZE-9*$SZREG($sp) - $REG_L $s4,$FRAMESIZE-10*$SZREG($sp) -___ -$code.=<<___ if ($flavour =~ /nubi/i); - $REG_L $s3,$FRAMESIZE-11*$SZREG($sp) - $REG_L $s2,$FRAMESIZE-12*$SZREG($sp) - $REG_L $s1,$FRAMESIZE-13*$SZREG($sp) - $REG_L $s0,$FRAMESIZE-14*$SZREG($sp) - $REG_L $gp,$FRAMESIZE-15*$SZREG($sp) -___ -$code.=<<___; - jr $ra - $PTR_ADD $sp,$FRAMESIZE -.end sha${label}_block_data_order - -.rdata -.align 5 -K${label}: -___ -if ($SZ==4) { -$code.=<<___; - .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5 - .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5 - .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3 - .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174 - .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc - .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da - .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7 - .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967 - .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13 - .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85 - .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3 - .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070 - .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5 - .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3 - .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208 - .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 -___ -} else { -$code.=<<___; - .dword 0x428a2f98d728ae22, 0x7137449123ef65cd - .dword 0xb5c0fbcfec4d3b2f, 0xe9b5dba58189dbbc - .dword 0x3956c25bf348b538, 0x59f111f1b605d019 - .dword 0x923f82a4af194f9b, 0xab1c5ed5da6d8118 - .dword 0xd807aa98a3030242, 0x12835b0145706fbe - .dword 0x243185be4ee4b28c, 0x550c7dc3d5ffb4e2 - .dword 0x72be5d74f27b896f, 0x80deb1fe3b1696b1 - .dword 0x9bdc06a725c71235, 0xc19bf174cf692694 - .dword 0xe49b69c19ef14ad2, 0xefbe4786384f25e3 - .dword 0x0fc19dc68b8cd5b5, 0x240ca1cc77ac9c65 - .dword 0x2de92c6f592b0275, 0x4a7484aa6ea6e483 - .dword 0x5cb0a9dcbd41fbd4, 0x76f988da831153b5 - .dword 0x983e5152ee66dfab, 0xa831c66d2db43210 - .dword 0xb00327c898fb213f, 0xbf597fc7beef0ee4 - .dword 0xc6e00bf33da88fc2, 0xd5a79147930aa725 - .dword 0x06ca6351e003826f, 0x142929670a0e6e70 - .dword 0x27b70a8546d22ffc, 0x2e1b21385c26c926 - .dword 0x4d2c6dfc5ac42aed, 0x53380d139d95b3df - .dword 0x650a73548baf63de, 0x766a0abb3c77b2a8 - .dword 0x81c2c92e47edaee6, 0x92722c851482353b - .dword 0xa2bfe8a14cf10364, 0xa81a664bbc423001 - .dword 0xc24b8b70d0f89791, 0xc76c51a30654be30 - .dword 0xd192e819d6ef5218, 0xd69906245565a910 - .dword 0xf40e35855771202a, 0x106aa07032bbd1b8 - .dword 0x19a4c116b8d2d0c8, 0x1e376c085141ab53 - .dword 0x2748774cdf8eeb99, 0x34b0bcb5e19b48a8 - .dword 0x391c0cb3c5c95a63, 0x4ed8aa4ae3418acb - .dword 0x5b9cca4f7763e373, 0x682e6ff3d6b2b8a3 - .dword 0x748f82ee5defb2fc, 0x78a5636f43172f60 - .dword 0x84c87814a1f0ab72, 0x8cc702081a6439ec - .dword 0x90befffa23631e28, 0xa4506cebde82bde9 - .dword 0xbef9a3f7b2c67915, 0xc67178f2e372532b - .dword 0xca273eceea26619c, 0xd186b8c721c0c207 - .dword 0xeada7dd6cde0eb1e, 0xf57d4f7fee6ed178 - .dword 0x06f067aa72176fba, 0x0a637dc5a2c898a6 - .dword 0x113f9804bef90dae, 0x1b710b35131c471b - .dword 0x28db77f523047d84, 0x32caab7b40c72493 - .dword 0x3c9ebe0a15c9bebc, 0x431d67c49c100d4c - .dword 0x4cc5d4becb3e42b6, 0x597f299cfc657e2a - .dword 0x5fcb6fab3ad6faec, 0x6c44198c4a475817 -___ -} -$code.=<<___; -.asciiz "SHA${label} for MIPS, CRYPTOGAMS by <appro\@openssl.org>" -.align 5 - -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha512-parisc.pl b/app/openssl/crypto/sha/asm/sha512-parisc.pl deleted file mode 100755 index fc0e15b3..00000000 --- a/app/openssl/crypto/sha/asm/sha512-parisc.pl +++ /dev/null @@ -1,793 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA256/512 block procedure for PA-RISC. - -# June 2009. -# -# SHA256 performance is >75% better than gcc 3.2 generated code on -# PA-7100LC. Compared to code generated by vendor compiler this -# implementation is almost 70% faster in 64-bit build, but delivers -# virtually same performance in 32-bit build on PA-8600. -# -# SHA512 performance is >2.9x better than gcc 3.2 generated code on -# PA-7100LC, PA-RISC 1.1 processor. Then implementation detects if the -# code is executed on PA-RISC 2.0 processor and switches to 64-bit -# code path delivering adequate peformance even in "blended" 32-bit -# build. Though 64-bit code is not any faster than code generated by -# vendor compiler on PA-8600... -# -# Special thanks to polarhome.com for providing HP-UX account. - -$flavour = shift; -$output = shift; -open STDOUT,">$output"; - -if ($flavour =~ /64/) { - $LEVEL ="2.0W"; - $SIZE_T =8; - $FRAME_MARKER =80; - $SAVED_RP =16; - $PUSH ="std"; - $PUSHMA ="std,ma"; - $POP ="ldd"; - $POPMB ="ldd,mb"; -} else { - $LEVEL ="1.0"; - $SIZE_T =4; - $FRAME_MARKER =48; - $SAVED_RP =20; - $PUSH ="stw"; - $PUSHMA ="stwm"; - $POP ="ldw"; - $POPMB ="ldwm"; -} - -if ($output =~ /512/) { - $func="sha512_block_data_order"; - $SZ=8; - @Sigma0=(28,34,39); - @Sigma1=(14,18,41); - @sigma0=(1, 8, 7); - @sigma1=(19,61, 6); - $rounds=80; - $LAST10BITS=0x017; - $LD="ldd"; - $LDM="ldd,ma"; - $ST="std"; -} else { - $func="sha256_block_data_order"; - $SZ=4; - @Sigma0=( 2,13,22); - @Sigma1=( 6,11,25); - @sigma0=( 7,18, 3); - @sigma1=(17,19,10); - $rounds=64; - $LAST10BITS=0x0f2; - $LD="ldw"; - $LDM="ldwm"; - $ST="stw"; -} - -$FRAME=16*$SIZE_T+$FRAME_MARKER;# 16 saved regs + frame marker - # [+ argument transfer] -$XOFF=16*$SZ+32; # local variables -$FRAME+=$XOFF; -$XOFF+=$FRAME_MARKER; # distance between %sp and local variables - -$ctx="%r26"; # zapped by $a0 -$inp="%r25"; # zapped by $a1 -$num="%r24"; # zapped by $t0 - -$a0 ="%r26"; -$a1 ="%r25"; -$t0 ="%r24"; -$t1 ="%r29"; -$Tbl="%r31"; - -@V=($A,$B,$C,$D,$E,$F,$G,$H)=("%r17","%r18","%r19","%r20","%r21","%r22","%r23","%r28"); - -@X=("%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7", "%r8", - "%r9", "%r10","%r11","%r12","%r13","%r14","%r15","%r16",$inp); - -sub ROUND_00_15 { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; -$code.=<<___; - _ror $e,$Sigma1[0],$a0 - and $f,$e,$t0 - _ror $e,$Sigma1[1],$a1 - addl $t1,$h,$h - andcm $g,$e,$t1 - xor $a1,$a0,$a0 - _ror $a1,`$Sigma1[2]-$Sigma1[1]`,$a1 - or $t0,$t1,$t1 ; Ch(e,f,g) - addl @X[$i%16],$h,$h - xor $a0,$a1,$a1 ; Sigma1(e) - addl $t1,$h,$h - _ror $a,$Sigma0[0],$a0 - addl $a1,$h,$h - - _ror $a,$Sigma0[1],$a1 - and $a,$b,$t0 - and $a,$c,$t1 - xor $a1,$a0,$a0 - _ror $a1,`$Sigma0[2]-$Sigma0[1]`,$a1 - xor $t1,$t0,$t0 - and $b,$c,$t1 - xor $a0,$a1,$a1 ; Sigma0(a) - addl $h,$d,$d - xor $t1,$t0,$t0 ; Maj(a,b,c) - `"$LDM $SZ($Tbl),$t1" if ($i<15)` - addl $a1,$h,$h - addl $t0,$h,$h - -___ -} - -sub ROUND_16_xx { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; -$i-=16; -$code.=<<___; - _ror @X[($i+1)%16],$sigma0[0],$a0 - _ror @X[($i+1)%16],$sigma0[1],$a1 - addl @X[($i+9)%16],@X[$i],@X[$i] - _ror @X[($i+14)%16],$sigma1[0],$t0 - _ror @X[($i+14)%16],$sigma1[1],$t1 - xor $a1,$a0,$a0 - _shr @X[($i+1)%16],$sigma0[2],$a1 - xor $t1,$t0,$t0 - _shr @X[($i+14)%16],$sigma1[2],$t1 - xor $a1,$a0,$a0 ; sigma0(X[(i+1)&0x0f]) - xor $t1,$t0,$t0 ; sigma1(X[(i+14)&0x0f]) - $LDM $SZ($Tbl),$t1 - addl $a0,@X[$i],@X[$i] - addl $t0,@X[$i],@X[$i] -___ -$code.=<<___ if ($i==15); - extru $t1,31,10,$a1 - comiclr,<> $LAST10BITS,$a1,%r0 - ldo 1($Tbl),$Tbl ; signal end of $Tbl -___ -&ROUND_00_15($i+16,$a,$b,$c,$d,$e,$f,$g,$h); -} - -$code=<<___; - .LEVEL $LEVEL - .SPACE \$TEXT\$ - .SUBSPA \$CODE\$,QUAD=0,ALIGN=8,ACCESS=0x2C,CODE_ONLY - - .ALIGN 64 -L\$table -___ -$code.=<<___ if ($SZ==8); - .WORD 0x428a2f98,0xd728ae22,0x71374491,0x23ef65cd - .WORD 0xb5c0fbcf,0xec4d3b2f,0xe9b5dba5,0x8189dbbc - .WORD 0x3956c25b,0xf348b538,0x59f111f1,0xb605d019 - .WORD 0x923f82a4,0xaf194f9b,0xab1c5ed5,0xda6d8118 - .WORD 0xd807aa98,0xa3030242,0x12835b01,0x45706fbe - .WORD 0x243185be,0x4ee4b28c,0x550c7dc3,0xd5ffb4e2 - .WORD 0x72be5d74,0xf27b896f,0x80deb1fe,0x3b1696b1 - .WORD 0x9bdc06a7,0x25c71235,0xc19bf174,0xcf692694 - .WORD 0xe49b69c1,0x9ef14ad2,0xefbe4786,0x384f25e3 - .WORD 0x0fc19dc6,0x8b8cd5b5,0x240ca1cc,0x77ac9c65 - .WORD 0x2de92c6f,0x592b0275,0x4a7484aa,0x6ea6e483 - .WORD 0x5cb0a9dc,0xbd41fbd4,0x76f988da,0x831153b5 - .WORD 0x983e5152,0xee66dfab,0xa831c66d,0x2db43210 - .WORD 0xb00327c8,0x98fb213f,0xbf597fc7,0xbeef0ee4 - .WORD 0xc6e00bf3,0x3da88fc2,0xd5a79147,0x930aa725 - .WORD 0x06ca6351,0xe003826f,0x14292967,0x0a0e6e70 - .WORD 0x27b70a85,0x46d22ffc,0x2e1b2138,0x5c26c926 - .WORD 0x4d2c6dfc,0x5ac42aed,0x53380d13,0x9d95b3df - .WORD 0x650a7354,0x8baf63de,0x766a0abb,0x3c77b2a8 - .WORD 0x81c2c92e,0x47edaee6,0x92722c85,0x1482353b - .WORD 0xa2bfe8a1,0x4cf10364,0xa81a664b,0xbc423001 - .WORD 0xc24b8b70,0xd0f89791,0xc76c51a3,0x0654be30 - .WORD 0xd192e819,0xd6ef5218,0xd6990624,0x5565a910 - .WORD 0xf40e3585,0x5771202a,0x106aa070,0x32bbd1b8 - .WORD 0x19a4c116,0xb8d2d0c8,0x1e376c08,0x5141ab53 - .WORD 0x2748774c,0xdf8eeb99,0x34b0bcb5,0xe19b48a8 - .WORD 0x391c0cb3,0xc5c95a63,0x4ed8aa4a,0xe3418acb - .WORD 0x5b9cca4f,0x7763e373,0x682e6ff3,0xd6b2b8a3 - .WORD 0x748f82ee,0x5defb2fc,0x78a5636f,0x43172f60 - .WORD 0x84c87814,0xa1f0ab72,0x8cc70208,0x1a6439ec - .WORD 0x90befffa,0x23631e28,0xa4506ceb,0xde82bde9 - .WORD 0xbef9a3f7,0xb2c67915,0xc67178f2,0xe372532b - .WORD 0xca273ece,0xea26619c,0xd186b8c7,0x21c0c207 - .WORD 0xeada7dd6,0xcde0eb1e,0xf57d4f7f,0xee6ed178 - .WORD 0x06f067aa,0x72176fba,0x0a637dc5,0xa2c898a6 - .WORD 0x113f9804,0xbef90dae,0x1b710b35,0x131c471b - .WORD 0x28db77f5,0x23047d84,0x32caab7b,0x40c72493 - .WORD 0x3c9ebe0a,0x15c9bebc,0x431d67c4,0x9c100d4c - .WORD 0x4cc5d4be,0xcb3e42b6,0x597f299c,0xfc657e2a - .WORD 0x5fcb6fab,0x3ad6faec,0x6c44198c,0x4a475817 -___ -$code.=<<___ if ($SZ==4); - .WORD 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 - .WORD 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 - .WORD 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 - .WORD 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 - .WORD 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc - .WORD 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da - .WORD 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 - .WORD 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 - .WORD 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 - .WORD 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 - .WORD 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 - .WORD 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 - .WORD 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 - .WORD 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 - .WORD 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 - .WORD 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -___ -$code.=<<___; - - .EXPORT $func,ENTRY,ARGW0=GR,ARGW1=GR,ARGW2=GR - .ALIGN 64 -$func - .PROC - .CALLINFO FRAME=`$FRAME-16*$SIZE_T`,NO_CALLS,SAVE_RP,ENTRY_GR=18 - .ENTRY - $PUSH %r2,-$SAVED_RP(%sp) ; standard prologue - $PUSHMA %r3,$FRAME(%sp) - $PUSH %r4,`-$FRAME+1*$SIZE_T`(%sp) - $PUSH %r5,`-$FRAME+2*$SIZE_T`(%sp) - $PUSH %r6,`-$FRAME+3*$SIZE_T`(%sp) - $PUSH %r7,`-$FRAME+4*$SIZE_T`(%sp) - $PUSH %r8,`-$FRAME+5*$SIZE_T`(%sp) - $PUSH %r9,`-$FRAME+6*$SIZE_T`(%sp) - $PUSH %r10,`-$FRAME+7*$SIZE_T`(%sp) - $PUSH %r11,`-$FRAME+8*$SIZE_T`(%sp) - $PUSH %r12,`-$FRAME+9*$SIZE_T`(%sp) - $PUSH %r13,`-$FRAME+10*$SIZE_T`(%sp) - $PUSH %r14,`-$FRAME+11*$SIZE_T`(%sp) - $PUSH %r15,`-$FRAME+12*$SIZE_T`(%sp) - $PUSH %r16,`-$FRAME+13*$SIZE_T`(%sp) - $PUSH %r17,`-$FRAME+14*$SIZE_T`(%sp) - $PUSH %r18,`-$FRAME+15*$SIZE_T`(%sp) - - _shl $num,`log(16*$SZ)/log(2)`,$num - addl $inp,$num,$num ; $num to point at the end of $inp - - $PUSH $num,`-$FRAME_MARKER-4*$SIZE_T`(%sp) ; save arguments - $PUSH $inp,`-$FRAME_MARKER-3*$SIZE_T`(%sp) - $PUSH $ctx,`-$FRAME_MARKER-2*$SIZE_T`(%sp) - - blr %r0,$Tbl - ldi 3,$t1 -L\$pic - andcm $Tbl,$t1,$Tbl ; wipe privilege level - ldo L\$table-L\$pic($Tbl),$Tbl -___ -$code.=<<___ if ($SZ==8 && $SIZE_T==4); - ldi 31,$t1 - mtctl $t1,%cr11 - extrd,u,*= $t1,%sar,1,$t1 ; executes on PA-RISC 1.0 - b L\$parisc1 - nop -___ -$code.=<<___; - $LD `0*$SZ`($ctx),$A ; load context - $LD `1*$SZ`($ctx),$B - $LD `2*$SZ`($ctx),$C - $LD `3*$SZ`($ctx),$D - $LD `4*$SZ`($ctx),$E - $LD `5*$SZ`($ctx),$F - $LD `6*$SZ`($ctx),$G - $LD `7*$SZ`($ctx),$H - - extru $inp,31,`log($SZ)/log(2)`,$t0 - sh3addl $t0,%r0,$t0 - subi `8*$SZ`,$t0,$t0 - mtctl $t0,%cr11 ; load %sar with align factor - -L\$oop - ldi `$SZ-1`,$t0 - $LDM $SZ($Tbl),$t1 - andcm $inp,$t0,$t0 ; align $inp -___ - for ($i=0;$i<15;$i++) { # load input block - $code.="\t$LD `$SZ*$i`($t0),@X[$i]\n"; } -$code.=<<___; - cmpb,*= $inp,$t0,L\$aligned - $LD `$SZ*15`($t0),@X[15] - $LD `$SZ*16`($t0),@X[16] -___ - for ($i=0;$i<16;$i++) { # align data - $code.="\t_align @X[$i],@X[$i+1],@X[$i]\n"; } -$code.=<<___; -L\$aligned - nop ; otherwise /usr/ccs/bin/as is confused by below .WORD -___ - -for($i=0;$i<16;$i++) { &ROUND_00_15($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; -L\$rounds - nop ; otherwise /usr/ccs/bin/as is confused by below .WORD -___ -for(;$i<32;$i++) { &ROUND_16_xx($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - bb,>= $Tbl,31,L\$rounds ; end of $Tbl signalled? - nop - - $POP `-$FRAME_MARKER-2*$SIZE_T`(%sp),$ctx ; restore arguments - $POP `-$FRAME_MARKER-3*$SIZE_T`(%sp),$inp - $POP `-$FRAME_MARKER-4*$SIZE_T`(%sp),$num - ldo `-$rounds*$SZ-1`($Tbl),$Tbl ; rewind $Tbl - - $LD `0*$SZ`($ctx),@X[0] ; load context - $LD `1*$SZ`($ctx),@X[1] - $LD `2*$SZ`($ctx),@X[2] - $LD `3*$SZ`($ctx),@X[3] - $LD `4*$SZ`($ctx),@X[4] - $LD `5*$SZ`($ctx),@X[5] - addl @X[0],$A,$A - $LD `6*$SZ`($ctx),@X[6] - addl @X[1],$B,$B - $LD `7*$SZ`($ctx),@X[7] - ldo `16*$SZ`($inp),$inp ; advance $inp - - $ST $A,`0*$SZ`($ctx) ; save context - addl @X[2],$C,$C - $ST $B,`1*$SZ`($ctx) - addl @X[3],$D,$D - $ST $C,`2*$SZ`($ctx) - addl @X[4],$E,$E - $ST $D,`3*$SZ`($ctx) - addl @X[5],$F,$F - $ST $E,`4*$SZ`($ctx) - addl @X[6],$G,$G - $ST $F,`5*$SZ`($ctx) - addl @X[7],$H,$H - $ST $G,`6*$SZ`($ctx) - $ST $H,`7*$SZ`($ctx) - - cmpb,*<>,n $inp,$num,L\$oop - $PUSH $inp,`-$FRAME_MARKER-3*$SIZE_T`(%sp) ; save $inp -___ -if ($SZ==8 && $SIZE_T==4) # SHA512 for 32-bit PA-RISC 1.0 -{{ -$code.=<<___; - b L\$done - nop - - .ALIGN 64 -L\$parisc1 -___ - -@V=( $Ahi, $Alo, $Bhi, $Blo, $Chi, $Clo, $Dhi, $Dlo, - $Ehi, $Elo, $Fhi, $Flo, $Ghi, $Glo, $Hhi, $Hlo) = - ( "%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7", "%r8", - "%r9","%r10","%r11","%r12","%r13","%r14","%r15","%r16"); -$a0 ="%r17"; -$a1 ="%r18"; -$a2 ="%r19"; -$a3 ="%r20"; -$t0 ="%r21"; -$t1 ="%r22"; -$t2 ="%r28"; -$t3 ="%r29"; -$Tbl="%r31"; - -@X=("%r23","%r24","%r25","%r26"); # zaps $num,$inp,$ctx - -sub ROUND_00_15_pa1 { -my ($i,$ahi,$alo,$bhi,$blo,$chi,$clo,$dhi,$dlo, - $ehi,$elo,$fhi,$flo,$ghi,$glo,$hhi,$hlo,$flag)=@_; -my ($Xhi,$Xlo,$Xnhi,$Xnlo) = @X; - -$code.=<<___ if (!$flag); - ldw `-$XOFF+8*(($i+1)%16)`(%sp),$Xnhi - ldw `-$XOFF+8*(($i+1)%16)+4`(%sp),$Xnlo ; load X[i+1] -___ -$code.=<<___; - shd $ehi,$elo,$Sigma1[0],$t0 - add $Xlo,$hlo,$hlo - shd $elo,$ehi,$Sigma1[0],$t1 - addc $Xhi,$hhi,$hhi ; h += X[i] - shd $ehi,$elo,$Sigma1[1],$t2 - ldwm 8($Tbl),$Xhi - shd $elo,$ehi,$Sigma1[1],$t3 - ldw -4($Tbl),$Xlo ; load K[i] - xor $t2,$t0,$t0 - xor $t3,$t1,$t1 - and $flo,$elo,$a0 - and $fhi,$ehi,$a1 - shd $ehi,$elo,$Sigma1[2],$t2 - andcm $glo,$elo,$a2 - shd $elo,$ehi,$Sigma1[2],$t3 - andcm $ghi,$ehi,$a3 - xor $t2,$t0,$t0 - xor $t3,$t1,$t1 ; Sigma1(e) - add $Xlo,$hlo,$hlo - xor $a2,$a0,$a0 - addc $Xhi,$hhi,$hhi ; h += K[i] - xor $a3,$a1,$a1 ; Ch(e,f,g) - - add $t0,$hlo,$hlo - shd $ahi,$alo,$Sigma0[0],$t0 - addc $t1,$hhi,$hhi ; h += Sigma1(e) - shd $alo,$ahi,$Sigma0[0],$t1 - add $a0,$hlo,$hlo - shd $ahi,$alo,$Sigma0[1],$t2 - addc $a1,$hhi,$hhi ; h += Ch(e,f,g) - shd $alo,$ahi,$Sigma0[1],$t3 - - xor $t2,$t0,$t0 - xor $t3,$t1,$t1 - shd $ahi,$alo,$Sigma0[2],$t2 - and $alo,$blo,$a0 - shd $alo,$ahi,$Sigma0[2],$t3 - and $ahi,$bhi,$a1 - xor $t2,$t0,$t0 - xor $t3,$t1,$t1 ; Sigma0(a) - - and $alo,$clo,$a2 - and $ahi,$chi,$a3 - xor $a2,$a0,$a0 - add $hlo,$dlo,$dlo - xor $a3,$a1,$a1 - addc $hhi,$dhi,$dhi ; d += h - and $blo,$clo,$a2 - add $t0,$hlo,$hlo - and $bhi,$chi,$a3 - addc $t1,$hhi,$hhi ; h += Sigma0(a) - xor $a2,$a0,$a0 - add $a0,$hlo,$hlo - xor $a3,$a1,$a1 ; Maj(a,b,c) - addc $a1,$hhi,$hhi ; h += Maj(a,b,c) - -___ -$code.=<<___ if ($i==15 && $flag); - extru $Xlo,31,10,$Xlo - comiclr,= $LAST10BITS,$Xlo,%r0 - b L\$rounds_pa1 - nop -___ -push(@X,shift(@X)); push(@X,shift(@X)); -} - -sub ROUND_16_xx_pa1 { -my ($Xhi,$Xlo,$Xnhi,$Xnlo) = @X; -my ($i)=shift; -$i-=16; -$code.=<<___; - ldw `-$XOFF+8*(($i+1)%16)`(%sp),$Xnhi - ldw `-$XOFF+8*(($i+1)%16)+4`(%sp),$Xnlo ; load X[i+1] - ldw `-$XOFF+8*(($i+9)%16)`(%sp),$a1 - ldw `-$XOFF+8*(($i+9)%16)+4`(%sp),$a0 ; load X[i+9] - ldw `-$XOFF+8*(($i+14)%16)`(%sp),$a3 - ldw `-$XOFF+8*(($i+14)%16)+4`(%sp),$a2 ; load X[i+14] - shd $Xnhi,$Xnlo,$sigma0[0],$t0 - shd $Xnlo,$Xnhi,$sigma0[0],$t1 - add $a0,$Xlo,$Xlo - shd $Xnhi,$Xnlo,$sigma0[1],$t2 - addc $a1,$Xhi,$Xhi - shd $Xnlo,$Xnhi,$sigma0[1],$t3 - xor $t2,$t0,$t0 - shd $Xnhi,$Xnlo,$sigma0[2],$t2 - xor $t3,$t1,$t1 - extru $Xnhi,`31-$sigma0[2]`,`32-$sigma0[2]`,$t3 - xor $t2,$t0,$t0 - shd $a3,$a2,$sigma1[0],$a0 - xor $t3,$t1,$t1 ; sigma0(X[i+1)&0x0f]) - shd $a2,$a3,$sigma1[0],$a1 - add $t0,$Xlo,$Xlo - shd $a3,$a2,$sigma1[1],$t2 - addc $t1,$Xhi,$Xhi - shd $a2,$a3,$sigma1[1],$t3 - xor $t2,$a0,$a0 - shd $a3,$a2,$sigma1[2],$t2 - xor $t3,$a1,$a1 - extru $a3,`31-$sigma1[2]`,`32-$sigma1[2]`,$t3 - xor $t2,$a0,$a0 - xor $t3,$a1,$a1 ; sigma0(X[i+14)&0x0f]) - add $a0,$Xlo,$Xlo - addc $a1,$Xhi,$Xhi - - stw $Xhi,`-$XOFF+8*($i%16)`(%sp) - stw $Xlo,`-$XOFF+8*($i%16)+4`(%sp) -___ -&ROUND_00_15_pa1($i,@_,1); -} -$code.=<<___; - ldw `0*4`($ctx),$Ahi ; load context - ldw `1*4`($ctx),$Alo - ldw `2*4`($ctx),$Bhi - ldw `3*4`($ctx),$Blo - ldw `4*4`($ctx),$Chi - ldw `5*4`($ctx),$Clo - ldw `6*4`($ctx),$Dhi - ldw `7*4`($ctx),$Dlo - ldw `8*4`($ctx),$Ehi - ldw `9*4`($ctx),$Elo - ldw `10*4`($ctx),$Fhi - ldw `11*4`($ctx),$Flo - ldw `12*4`($ctx),$Ghi - ldw `13*4`($ctx),$Glo - ldw `14*4`($ctx),$Hhi - ldw `15*4`($ctx),$Hlo - - extru $inp,31,2,$t0 - sh3addl $t0,%r0,$t0 - subi 32,$t0,$t0 - mtctl $t0,%cr11 ; load %sar with align factor - -L\$oop_pa1 - extru $inp,31,2,$a3 - comib,= 0,$a3,L\$aligned_pa1 - sub $inp,$a3,$inp - - ldw `0*4`($inp),$X[0] - ldw `1*4`($inp),$X[1] - ldw `2*4`($inp),$t2 - ldw `3*4`($inp),$t3 - ldw `4*4`($inp),$a0 - ldw `5*4`($inp),$a1 - ldw `6*4`($inp),$a2 - ldw `7*4`($inp),$a3 - vshd $X[0],$X[1],$X[0] - vshd $X[1],$t2,$X[1] - stw $X[0],`-$XOFF+0*4`(%sp) - ldw `8*4`($inp),$t0 - vshd $t2,$t3,$t2 - stw $X[1],`-$XOFF+1*4`(%sp) - ldw `9*4`($inp),$t1 - vshd $t3,$a0,$t3 -___ -{ -my @t=($t2,$t3,$a0,$a1,$a2,$a3,$t0,$t1); -for ($i=2;$i<=(128/4-8);$i++) { -$code.=<<___; - stw $t[0],`-$XOFF+$i*4`(%sp) - ldw `(8+$i)*4`($inp),$t[0] - vshd $t[1],$t[2],$t[1] -___ -push(@t,shift(@t)); -} -for (;$i<(128/4-1);$i++) { -$code.=<<___; - stw $t[0],`-$XOFF+$i*4`(%sp) - vshd $t[1],$t[2],$t[1] -___ -push(@t,shift(@t)); -} -$code.=<<___; - b L\$collected_pa1 - stw $t[0],`-$XOFF+$i*4`(%sp) - -___ -} -$code.=<<___; -L\$aligned_pa1 - ldw `0*4`($inp),$X[0] - ldw `1*4`($inp),$X[1] - ldw `2*4`($inp),$t2 - ldw `3*4`($inp),$t3 - ldw `4*4`($inp),$a0 - ldw `5*4`($inp),$a1 - ldw `6*4`($inp),$a2 - ldw `7*4`($inp),$a3 - stw $X[0],`-$XOFF+0*4`(%sp) - ldw `8*4`($inp),$t0 - stw $X[1],`-$XOFF+1*4`(%sp) - ldw `9*4`($inp),$t1 -___ -{ -my @t=($t2,$t3,$a0,$a1,$a2,$a3,$t0,$t1); -for ($i=2;$i<(128/4-8);$i++) { -$code.=<<___; - stw $t[0],`-$XOFF+$i*4`(%sp) - ldw `(8+$i)*4`($inp),$t[0] -___ -push(@t,shift(@t)); -} -for (;$i<128/4;$i++) { -$code.=<<___; - stw $t[0],`-$XOFF+$i*4`(%sp) -___ -push(@t,shift(@t)); -} -$code.="L\$collected_pa1\n"; -} - -for($i=0;$i<16;$i++) { &ROUND_00_15_pa1($i,@V); unshift(@V,pop(@V)); unshift(@V,pop(@V)); } -$code.="L\$rounds_pa1\n"; -for(;$i<32;$i++) { &ROUND_16_xx_pa1($i,@V); unshift(@V,pop(@V)); unshift(@V,pop(@V)); } - -$code.=<<___; - $POP `-$FRAME_MARKER-2*$SIZE_T`(%sp),$ctx ; restore arguments - $POP `-$FRAME_MARKER-3*$SIZE_T`(%sp),$inp - $POP `-$FRAME_MARKER-4*$SIZE_T`(%sp),$num - ldo `-$rounds*$SZ`($Tbl),$Tbl ; rewind $Tbl - - ldw `0*4`($ctx),$t1 ; update context - ldw `1*4`($ctx),$t0 - ldw `2*4`($ctx),$t3 - ldw `3*4`($ctx),$t2 - ldw `4*4`($ctx),$a1 - ldw `5*4`($ctx),$a0 - ldw `6*4`($ctx),$a3 - add $t0,$Alo,$Alo - ldw `7*4`($ctx),$a2 - addc $t1,$Ahi,$Ahi - ldw `8*4`($ctx),$t1 - add $t2,$Blo,$Blo - ldw `9*4`($ctx),$t0 - addc $t3,$Bhi,$Bhi - ldw `10*4`($ctx),$t3 - add $a0,$Clo,$Clo - ldw `11*4`($ctx),$t2 - addc $a1,$Chi,$Chi - ldw `12*4`($ctx),$a1 - add $a2,$Dlo,$Dlo - ldw `13*4`($ctx),$a0 - addc $a3,$Dhi,$Dhi - ldw `14*4`($ctx),$a3 - add $t0,$Elo,$Elo - ldw `15*4`($ctx),$a2 - addc $t1,$Ehi,$Ehi - stw $Ahi,`0*4`($ctx) - add $t2,$Flo,$Flo - stw $Alo,`1*4`($ctx) - addc $t3,$Fhi,$Fhi - stw $Bhi,`2*4`($ctx) - add $a0,$Glo,$Glo - stw $Blo,`3*4`($ctx) - addc $a1,$Ghi,$Ghi - stw $Chi,`4*4`($ctx) - add $a2,$Hlo,$Hlo - stw $Clo,`5*4`($ctx) - addc $a3,$Hhi,$Hhi - stw $Dhi,`6*4`($ctx) - ldo `16*$SZ`($inp),$inp ; advance $inp - stw $Dlo,`7*4`($ctx) - stw $Ehi,`8*4`($ctx) - stw $Elo,`9*4`($ctx) - stw $Fhi,`10*4`($ctx) - stw $Flo,`11*4`($ctx) - stw $Ghi,`12*4`($ctx) - stw $Glo,`13*4`($ctx) - stw $Hhi,`14*4`($ctx) - comb,= $inp,$num,L\$done - stw $Hlo,`15*4`($ctx) - b L\$oop_pa1 - $PUSH $inp,`-$FRAME_MARKER-3*$SIZE_T`(%sp) ; save $inp -L\$done -___ -}} -$code.=<<___; - $POP `-$FRAME-$SAVED_RP`(%sp),%r2 ; standard epilogue - $POP `-$FRAME+1*$SIZE_T`(%sp),%r4 - $POP `-$FRAME+2*$SIZE_T`(%sp),%r5 - $POP `-$FRAME+3*$SIZE_T`(%sp),%r6 - $POP `-$FRAME+4*$SIZE_T`(%sp),%r7 - $POP `-$FRAME+5*$SIZE_T`(%sp),%r8 - $POP `-$FRAME+6*$SIZE_T`(%sp),%r9 - $POP `-$FRAME+7*$SIZE_T`(%sp),%r10 - $POP `-$FRAME+8*$SIZE_T`(%sp),%r11 - $POP `-$FRAME+9*$SIZE_T`(%sp),%r12 - $POP `-$FRAME+10*$SIZE_T`(%sp),%r13 - $POP `-$FRAME+11*$SIZE_T`(%sp),%r14 - $POP `-$FRAME+12*$SIZE_T`(%sp),%r15 - $POP `-$FRAME+13*$SIZE_T`(%sp),%r16 - $POP `-$FRAME+14*$SIZE_T`(%sp),%r17 - $POP `-$FRAME+15*$SIZE_T`(%sp),%r18 - bv (%r2) - .EXIT - $POPMB -$FRAME(%sp),%r3 - .PROCEND - .STRINGZ "SHA`64*$SZ` block transform for PA-RISC, CRYPTOGAMS by <appro\@openssl.org>" -___ - -# Explicitly encode PA-RISC 2.0 instructions used in this module, so -# that it can be compiled with .LEVEL 1.0. It should be noted that I -# wouldn't have to do this, if GNU assembler understood .ALLOW 2.0 -# directive... - -my $ldd = sub { - my ($mod,$args) = @_; - my $orig = "ldd$mod\t$args"; - - if ($args =~ /(\-?[0-9]+)\(%r([0-9]+)\),%r([0-9]+)/) # format 3 suffices - { my $opcode=(0x14<<26)|($2<<21)|($3<<16)|(($1&0x1FF8)<<1)|(($1>>13)&1); - $opcode|=(1<<3) if ($mod =~ /^,m/); - $opcode|=(1<<2) if ($mod =~ /^,mb/); - sprintf "\t.WORD\t0x%08x\t; %s",$opcode,$orig; - } - else { "\t".$orig; } -}; - -my $std = sub { - my ($mod,$args) = @_; - my $orig = "std$mod\t$args"; - - if ($args =~ /%r([0-9]+),(\-?[0-9]+)\(%r([0-9]+)\)/) # format 3 suffices - { my $opcode=(0x1c<<26)|($3<<21)|($1<<16)|(($2&0x1FF8)<<1)|(($2>>13)&1); - sprintf "\t.WORD\t0x%08x\t; %s",$opcode,$orig; - } - else { "\t".$orig; } -}; - -my $extrd = sub { - my ($mod,$args) = @_; - my $orig = "extrd$mod\t$args"; - - # I only have ",u" completer, it's implicitly encoded... - if ($args =~ /%r([0-9]+),([0-9]+),([0-9]+),%r([0-9]+)/) # format 15 - { my $opcode=(0x36<<26)|($1<<21)|($4<<16); - my $len=32-$3; - $opcode |= (($2&0x20)<<6)|(($2&0x1f)<<5); # encode pos - $opcode |= (($len&0x20)<<7)|($len&0x1f); # encode len - sprintf "\t.WORD\t0x%08x\t; %s",$opcode,$orig; - } - elsif ($args =~ /%r([0-9]+),%sar,([0-9]+),%r([0-9]+)/) # format 12 - { my $opcode=(0x34<<26)|($1<<21)|($3<<16)|(2<<11)|(1<<9); - my $len=32-$2; - $opcode |= (($len&0x20)<<3)|($len&0x1f); # encode len - $opcode |= (1<<13) if ($mod =~ /,\**=/); - sprintf "\t.WORD\t0x%08x\t; %s",$opcode,$orig; - } - else { "\t".$orig; } -}; - -my $shrpd = sub { - my ($mod,$args) = @_; - my $orig = "shrpd$mod\t$args"; - - if ($args =~ /%r([0-9]+),%r([0-9]+),([0-9]+),%r([0-9]+)/) # format 14 - { my $opcode=(0x34<<26)|($2<<21)|($1<<16)|(1<<10)|$4; - my $cpos=63-$3; - $opcode |= (($cpos&0x20)<<6)|(($cpos&0x1f)<<5); # encode sa - sprintf "\t.WORD\t0x%08x\t; %s",$opcode,$orig; - } - elsif ($args =~ /%r([0-9]+),%r([0-9]+),%sar,%r([0-9]+)/) # format 11 - { sprintf "\t.WORD\t0x%08x\t; %s", - (0x34<<26)|($2<<21)|($1<<16)|(1<<9)|$3,$orig; - } - else { "\t".$orig; } -}; - -sub assemble { - my ($mnemonic,$mod,$args)=@_; - my $opcode = eval("\$$mnemonic"); - - ref($opcode) eq 'CODE' ? &$opcode($mod,$args) : "\t$mnemonic$mod\t$args"; -} - -foreach (split("\n",$code)) { - s/\`([^\`]*)\`/eval $1/ge; - - s/shd\s+(%r[0-9]+),(%r[0-9]+),([0-9]+)/ - $3>31 ? sprintf("shd\t%$2,%$1,%d",$3-32) # rotation for >=32 - : sprintf("shd\t%$1,%$2,%d",$3)/e or - # translate made up instructons: _ror, _shr, _align, _shl - s/_ror(\s+)(%r[0-9]+),/ - ($SZ==4 ? "shd" : "shrpd")."$1$2,$2,"/e or - - s/_shr(\s+%r[0-9]+),([0-9]+),/ - $SZ==4 ? sprintf("extru%s,%d,%d,",$1,31-$2,32-$2) - : sprintf("extrd,u%s,%d,%d,",$1,63-$2,64-$2)/e or - - s/_align(\s+%r[0-9]+,%r[0-9]+),/ - ($SZ==4 ? "vshd$1," : "shrpd$1,%sar,")/e or - - s/_shl(\s+%r[0-9]+),([0-9]+),/ - $SIZE_T==4 ? sprintf("zdep%s,%d,%d,",$1,31-$2,32-$2) - : sprintf("depd,z%s,%d,%d,",$1,63-$2,64-$2)/e; - - s/^\s+([a-z]+)([\S]*)\s+([\S]*)/&assemble($1,$2,$3)/e if ($SIZE_T==4); - - s/cmpb,\*/comb,/ if ($SIZE_T==4); - - s/\bbv\b/bve/ if ($SIZE_T==8); - - print $_,"\n"; -} - -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha512-ppc.pl b/app/openssl/crypto/sha/asm/sha512-ppc.pl deleted file mode 100755 index 6b44a68e..00000000 --- a/app/openssl/crypto/sha/asm/sha512-ppc.pl +++ /dev/null @@ -1,460 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# I let hardware handle unaligned input, except on page boundaries -# (see below for details). Otherwise straightforward implementation -# with X vector in register bank. The module is big-endian [which is -# not big deal as there're no little-endian targets left around]. - -# sha256 | sha512 -# -m64 -m32 | -m64 -m32 -# --------------------------------------+----------------------- -# PPC970,gcc-4.0.0 +50% +38% | +40% +410%(*) -# Power6,xlc-7 +150% +90% | +100% +430%(*) -# -# (*) 64-bit code in 32-bit application context, which actually is -# on TODO list. It should be noted that for safe deployment in -# 32-bit *mutli-threaded* context asyncronous signals should be -# blocked upon entry to SHA512 block routine. This is because -# 32-bit signaling procedure invalidates upper halves of GPRs. -# Context switch procedure preserves them, but not signaling:-( - -# Second version is true multi-thread safe. Trouble with the original -# version was that it was using thread local storage pointer register. -# Well, it scrupulously preserved it, but the problem would arise the -# moment asynchronous signal was delivered and signal handler would -# dereference the TLS pointer. While it's never the case in openssl -# application or test suite, we have to respect this scenario and not -# use TLS pointer register. Alternative would be to require caller to -# block signals prior calling this routine. For the record, in 32-bit -# context R2 serves as TLS pointer, while in 64-bit context - R13. - -$flavour=shift; -$output =shift; - -if ($flavour =~ /64/) { - $SIZE_T=8; - $LRSAVE=2*$SIZE_T; - $STU="stdu"; - $UCMP="cmpld"; - $SHL="sldi"; - $POP="ld"; - $PUSH="std"; -} elsif ($flavour =~ /32/) { - $SIZE_T=4; - $LRSAVE=$SIZE_T; - $STU="stwu"; - $UCMP="cmplw"; - $SHL="slwi"; - $POP="lwz"; - $PUSH="stw"; -} else { die "nonsense $flavour"; } - -$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; -( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or -( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or -die "can't locate ppc-xlate.pl"; - -open STDOUT,"| $^X $xlate $flavour $output" || die "can't call $xlate: $!"; - -if ($output =~ /512/) { - $func="sha512_block_data_order"; - $SZ=8; - @Sigma0=(28,34,39); - @Sigma1=(14,18,41); - @sigma0=(1, 8, 7); - @sigma1=(19,61, 6); - $rounds=80; - $LD="ld"; - $ST="std"; - $ROR="rotrdi"; - $SHR="srdi"; -} else { - $func="sha256_block_data_order"; - $SZ=4; - @Sigma0=( 2,13,22); - @Sigma1=( 6,11,25); - @sigma0=( 7,18, 3); - @sigma1=(17,19,10); - $rounds=64; - $LD="lwz"; - $ST="stw"; - $ROR="rotrwi"; - $SHR="srwi"; -} - -$FRAME=32*$SIZE_T+16*$SZ; -$LOCALS=6*$SIZE_T; - -$sp ="r1"; -$toc="r2"; -$ctx="r3"; # zapped by $a0 -$inp="r4"; # zapped by $a1 -$num="r5"; # zapped by $t0 - -$T ="r0"; -$a0 ="r3"; -$a1 ="r4"; -$t0 ="r5"; -$t1 ="r6"; -$Tbl="r7"; - -$A ="r8"; -$B ="r9"; -$C ="r10"; -$D ="r11"; -$E ="r12"; -$F ="r13"; $F="r2" if ($SIZE_T==8);# reassigned to exempt TLS pointer -$G ="r14"; -$H ="r15"; - -@V=($A,$B,$C,$D,$E,$F,$G,$H); -@X=("r16","r17","r18","r19","r20","r21","r22","r23", - "r24","r25","r26","r27","r28","r29","r30","r31"); - -$inp="r31"; # reassigned $inp! aliases with @X[15] - -sub ROUND_00_15 { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; -$code.=<<___; - $LD $T,`$i*$SZ`($Tbl) - $ROR $a0,$e,$Sigma1[0] - $ROR $a1,$e,$Sigma1[1] - and $t0,$f,$e - andc $t1,$g,$e - add $T,$T,$h - xor $a0,$a0,$a1 - $ROR $a1,$a1,`$Sigma1[2]-$Sigma1[1]` - or $t0,$t0,$t1 ; Ch(e,f,g) - add $T,$T,@X[$i] - xor $a0,$a0,$a1 ; Sigma1(e) - add $T,$T,$t0 - add $T,$T,$a0 - - $ROR $a0,$a,$Sigma0[0] - $ROR $a1,$a,$Sigma0[1] - and $t0,$a,$b - and $t1,$a,$c - xor $a0,$a0,$a1 - $ROR $a1,$a1,`$Sigma0[2]-$Sigma0[1]` - xor $t0,$t0,$t1 - and $t1,$b,$c - xor $a0,$a0,$a1 ; Sigma0(a) - add $d,$d,$T - xor $t0,$t0,$t1 ; Maj(a,b,c) - add $h,$T,$a0 - add $h,$h,$t0 - -___ -} - -sub ROUND_16_xx { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; -$i-=16; -$code.=<<___; - $ROR $a0,@X[($i+1)%16],$sigma0[0] - $ROR $a1,@X[($i+1)%16],$sigma0[1] - $ROR $t0,@X[($i+14)%16],$sigma1[0] - $ROR $t1,@X[($i+14)%16],$sigma1[1] - xor $a0,$a0,$a1 - $SHR $a1,@X[($i+1)%16],$sigma0[2] - xor $t0,$t0,$t1 - $SHR $t1,@X[($i+14)%16],$sigma1[2] - add @X[$i],@X[$i],@X[($i+9)%16] - xor $a0,$a0,$a1 ; sigma0(X[(i+1)&0x0f]) - xor $t0,$t0,$t1 ; sigma1(X[(i+14)&0x0f]) - add @X[$i],@X[$i],$a0 - add @X[$i],@X[$i],$t0 -___ -&ROUND_00_15($i,$a,$b,$c,$d,$e,$f,$g,$h); -} - -$code=<<___; -.machine "any" -.text - -.globl $func -.align 6 -$func: - $STU $sp,-$FRAME($sp) - mflr r0 - $SHL $num,$num,`log(16*$SZ)/log(2)` - - $PUSH $ctx,`$FRAME-$SIZE_T*22`($sp) - - $PUSH $toc,`$FRAME-$SIZE_T*20`($sp) - $PUSH r13,`$FRAME-$SIZE_T*19`($sp) - $PUSH r14,`$FRAME-$SIZE_T*18`($sp) - $PUSH r15,`$FRAME-$SIZE_T*17`($sp) - $PUSH r16,`$FRAME-$SIZE_T*16`($sp) - $PUSH r17,`$FRAME-$SIZE_T*15`($sp) - $PUSH r18,`$FRAME-$SIZE_T*14`($sp) - $PUSH r19,`$FRAME-$SIZE_T*13`($sp) - $PUSH r20,`$FRAME-$SIZE_T*12`($sp) - $PUSH r21,`$FRAME-$SIZE_T*11`($sp) - $PUSH r22,`$FRAME-$SIZE_T*10`($sp) - $PUSH r23,`$FRAME-$SIZE_T*9`($sp) - $PUSH r24,`$FRAME-$SIZE_T*8`($sp) - $PUSH r25,`$FRAME-$SIZE_T*7`($sp) - $PUSH r26,`$FRAME-$SIZE_T*6`($sp) - $PUSH r27,`$FRAME-$SIZE_T*5`($sp) - $PUSH r28,`$FRAME-$SIZE_T*4`($sp) - $PUSH r29,`$FRAME-$SIZE_T*3`($sp) - $PUSH r30,`$FRAME-$SIZE_T*2`($sp) - $PUSH r31,`$FRAME-$SIZE_T*1`($sp) - $PUSH r0,`$FRAME+$LRSAVE`($sp) - - $LD $A,`0*$SZ`($ctx) - mr $inp,r4 ; incarnate $inp - $LD $B,`1*$SZ`($ctx) - $LD $C,`2*$SZ`($ctx) - $LD $D,`3*$SZ`($ctx) - $LD $E,`4*$SZ`($ctx) - $LD $F,`5*$SZ`($ctx) - $LD $G,`6*$SZ`($ctx) - $LD $H,`7*$SZ`($ctx) - - bl LPICmeup -LPICedup: - andi. r0,$inp,3 - bne Lunaligned -Laligned: - add $num,$inp,$num - $PUSH $num,`$FRAME-$SIZE_T*24`($sp) ; end pointer - $PUSH $inp,`$FRAME-$SIZE_T*23`($sp) ; inp pointer - bl Lsha2_block_private - b Ldone - -; PowerPC specification allows an implementation to be ill-behaved -; upon unaligned access which crosses page boundary. "Better safe -; than sorry" principle makes me treat it specially. But I don't -; look for particular offending word, but rather for the input -; block which crosses the boundary. Once found that block is aligned -; and hashed separately... -.align 4 -Lunaligned: - subfic $t1,$inp,4096 - andi. $t1,$t1,`4096-16*$SZ` ; distance to closest page boundary - beq Lcross_page - $UCMP $num,$t1 - ble- Laligned ; didn't cross the page boundary - subfc $num,$t1,$num - add $t1,$inp,$t1 - $PUSH $num,`$FRAME-$SIZE_T*25`($sp) ; save real remaining num - $PUSH $t1,`$FRAME-$SIZE_T*24`($sp) ; intermediate end pointer - $PUSH $inp,`$FRAME-$SIZE_T*23`($sp) ; inp pointer - bl Lsha2_block_private - ; $inp equals to the intermediate end pointer here - $POP $num,`$FRAME-$SIZE_T*25`($sp) ; restore real remaining num -Lcross_page: - li $t1,`16*$SZ/4` - mtctr $t1 - addi r20,$sp,$LOCALS ; aligned spot below the frame -Lmemcpy: - lbz r16,0($inp) - lbz r17,1($inp) - lbz r18,2($inp) - lbz r19,3($inp) - addi $inp,$inp,4 - stb r16,0(r20) - stb r17,1(r20) - stb r18,2(r20) - stb r19,3(r20) - addi r20,r20,4 - bdnz Lmemcpy - - $PUSH $inp,`$FRAME-$SIZE_T*26`($sp) ; save real inp - addi $t1,$sp,`$LOCALS+16*$SZ` ; fictitious end pointer - addi $inp,$sp,$LOCALS ; fictitious inp pointer - $PUSH $num,`$FRAME-$SIZE_T*25`($sp) ; save real num - $PUSH $t1,`$FRAME-$SIZE_T*24`($sp) ; end pointer - $PUSH $inp,`$FRAME-$SIZE_T*23`($sp) ; inp pointer - bl Lsha2_block_private - $POP $inp,`$FRAME-$SIZE_T*26`($sp) ; restore real inp - $POP $num,`$FRAME-$SIZE_T*25`($sp) ; restore real num - addic. $num,$num,`-16*$SZ` ; num-- - bne- Lunaligned - -Ldone: - $POP r0,`$FRAME+$LRSAVE`($sp) - $POP $toc,`$FRAME-$SIZE_T*20`($sp) - $POP r13,`$FRAME-$SIZE_T*19`($sp) - $POP r14,`$FRAME-$SIZE_T*18`($sp) - $POP r15,`$FRAME-$SIZE_T*17`($sp) - $POP r16,`$FRAME-$SIZE_T*16`($sp) - $POP r17,`$FRAME-$SIZE_T*15`($sp) - $POP r18,`$FRAME-$SIZE_T*14`($sp) - $POP r19,`$FRAME-$SIZE_T*13`($sp) - $POP r20,`$FRAME-$SIZE_T*12`($sp) - $POP r21,`$FRAME-$SIZE_T*11`($sp) - $POP r22,`$FRAME-$SIZE_T*10`($sp) - $POP r23,`$FRAME-$SIZE_T*9`($sp) - $POP r24,`$FRAME-$SIZE_T*8`($sp) - $POP r25,`$FRAME-$SIZE_T*7`($sp) - $POP r26,`$FRAME-$SIZE_T*6`($sp) - $POP r27,`$FRAME-$SIZE_T*5`($sp) - $POP r28,`$FRAME-$SIZE_T*4`($sp) - $POP r29,`$FRAME-$SIZE_T*3`($sp) - $POP r30,`$FRAME-$SIZE_T*2`($sp) - $POP r31,`$FRAME-$SIZE_T*1`($sp) - mtlr r0 - addi $sp,$sp,$FRAME - blr - .long 0 - .byte 0,12,4,1,0x80,18,3,0 - .long 0 - -.align 4 -Lsha2_block_private: -___ -for($i=0;$i<16;$i++) { -$code.=<<___ if ($SZ==4); - lwz @X[$i],`$i*$SZ`($inp) -___ -# 64-bit loads are split to 2x32-bit ones, as CPU can't handle -# unaligned 64-bit loads, only 32-bit ones... -$code.=<<___ if ($SZ==8); - lwz $t0,`$i*$SZ`($inp) - lwz @X[$i],`$i*$SZ+4`($inp) - insrdi @X[$i],$t0,32,0 -___ - &ROUND_00_15($i,@V); - unshift(@V,pop(@V)); -} -$code.=<<___; - li $T,`$rounds/16-1` - mtctr $T -.align 4 -Lrounds: - addi $Tbl,$Tbl,`16*$SZ` -___ -for(;$i<32;$i++) { - &ROUND_16_xx($i,@V); - unshift(@V,pop(@V)); -} -$code.=<<___; - bdnz- Lrounds - - $POP $ctx,`$FRAME-$SIZE_T*22`($sp) - $POP $inp,`$FRAME-$SIZE_T*23`($sp) ; inp pointer - $POP $num,`$FRAME-$SIZE_T*24`($sp) ; end pointer - subi $Tbl,$Tbl,`($rounds-16)*$SZ` ; rewind Tbl - - $LD r16,`0*$SZ`($ctx) - $LD r17,`1*$SZ`($ctx) - $LD r18,`2*$SZ`($ctx) - $LD r19,`3*$SZ`($ctx) - $LD r20,`4*$SZ`($ctx) - $LD r21,`5*$SZ`($ctx) - $LD r22,`6*$SZ`($ctx) - addi $inp,$inp,`16*$SZ` ; advance inp - $LD r23,`7*$SZ`($ctx) - add $A,$A,r16 - add $B,$B,r17 - $PUSH $inp,`$FRAME-$SIZE_T*23`($sp) - add $C,$C,r18 - $ST $A,`0*$SZ`($ctx) - add $D,$D,r19 - $ST $B,`1*$SZ`($ctx) - add $E,$E,r20 - $ST $C,`2*$SZ`($ctx) - add $F,$F,r21 - $ST $D,`3*$SZ`($ctx) - add $G,$G,r22 - $ST $E,`4*$SZ`($ctx) - add $H,$H,r23 - $ST $F,`5*$SZ`($ctx) - $ST $G,`6*$SZ`($ctx) - $UCMP $inp,$num - $ST $H,`7*$SZ`($ctx) - bne Lsha2_block_private - blr - .long 0 - .byte 0,12,0x14,0,0,0,0,0 -___ - -# Ugly hack here, because PPC assembler syntax seem to vary too -# much from platforms to platform... -$code.=<<___; -.align 6 -LPICmeup: - mflr r0 - bcl 20,31,\$+4 - mflr $Tbl ; vvvvvv "distance" between . and 1st data entry - addi $Tbl,$Tbl,`64-8` - mtlr r0 - blr - .long 0 - .byte 0,12,0x14,0,0,0,0,0 - .space `64-9*4` -___ -$code.=<<___ if ($SZ==8); - .long 0x428a2f98,0xd728ae22,0x71374491,0x23ef65cd - .long 0xb5c0fbcf,0xec4d3b2f,0xe9b5dba5,0x8189dbbc - .long 0x3956c25b,0xf348b538,0x59f111f1,0xb605d019 - .long 0x923f82a4,0xaf194f9b,0xab1c5ed5,0xda6d8118 - .long 0xd807aa98,0xa3030242,0x12835b01,0x45706fbe - .long 0x243185be,0x4ee4b28c,0x550c7dc3,0xd5ffb4e2 - .long 0x72be5d74,0xf27b896f,0x80deb1fe,0x3b1696b1 - .long 0x9bdc06a7,0x25c71235,0xc19bf174,0xcf692694 - .long 0xe49b69c1,0x9ef14ad2,0xefbe4786,0x384f25e3 - .long 0x0fc19dc6,0x8b8cd5b5,0x240ca1cc,0x77ac9c65 - .long 0x2de92c6f,0x592b0275,0x4a7484aa,0x6ea6e483 - .long 0x5cb0a9dc,0xbd41fbd4,0x76f988da,0x831153b5 - .long 0x983e5152,0xee66dfab,0xa831c66d,0x2db43210 - .long 0xb00327c8,0x98fb213f,0xbf597fc7,0xbeef0ee4 - .long 0xc6e00bf3,0x3da88fc2,0xd5a79147,0x930aa725 - .long 0x06ca6351,0xe003826f,0x14292967,0x0a0e6e70 - .long 0x27b70a85,0x46d22ffc,0x2e1b2138,0x5c26c926 - .long 0x4d2c6dfc,0x5ac42aed,0x53380d13,0x9d95b3df - .long 0x650a7354,0x8baf63de,0x766a0abb,0x3c77b2a8 - .long 0x81c2c92e,0x47edaee6,0x92722c85,0x1482353b - .long 0xa2bfe8a1,0x4cf10364,0xa81a664b,0xbc423001 - .long 0xc24b8b70,0xd0f89791,0xc76c51a3,0x0654be30 - .long 0xd192e819,0xd6ef5218,0xd6990624,0x5565a910 - .long 0xf40e3585,0x5771202a,0x106aa070,0x32bbd1b8 - .long 0x19a4c116,0xb8d2d0c8,0x1e376c08,0x5141ab53 - .long 0x2748774c,0xdf8eeb99,0x34b0bcb5,0xe19b48a8 - .long 0x391c0cb3,0xc5c95a63,0x4ed8aa4a,0xe3418acb - .long 0x5b9cca4f,0x7763e373,0x682e6ff3,0xd6b2b8a3 - .long 0x748f82ee,0x5defb2fc,0x78a5636f,0x43172f60 - .long 0x84c87814,0xa1f0ab72,0x8cc70208,0x1a6439ec - .long 0x90befffa,0x23631e28,0xa4506ceb,0xde82bde9 - .long 0xbef9a3f7,0xb2c67915,0xc67178f2,0xe372532b - .long 0xca273ece,0xea26619c,0xd186b8c7,0x21c0c207 - .long 0xeada7dd6,0xcde0eb1e,0xf57d4f7f,0xee6ed178 - .long 0x06f067aa,0x72176fba,0x0a637dc5,0xa2c898a6 - .long 0x113f9804,0xbef90dae,0x1b710b35,0x131c471b - .long 0x28db77f5,0x23047d84,0x32caab7b,0x40c72493 - .long 0x3c9ebe0a,0x15c9bebc,0x431d67c4,0x9c100d4c - .long 0x4cc5d4be,0xcb3e42b6,0x597f299c,0xfc657e2a - .long 0x5fcb6fab,0x3ad6faec,0x6c44198c,0x4a475817 -___ -$code.=<<___ if ($SZ==4); - .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 - .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 - .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 - .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 - .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc - .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da - .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 - .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 - .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 - .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 - .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 - .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 - .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 - .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 - .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 - .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha512-s390x.pl b/app/openssl/crypto/sha/asm/sha512-s390x.pl deleted file mode 100644 index 079a3fc7..00000000 --- a/app/openssl/crypto/sha/asm/sha512-s390x.pl +++ /dev/null @@ -1,322 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA256/512 block procedures for s390x. - -# April 2007. -# -# sha256_block_data_order is reportedly >3 times faster than gcc 3.3 -# generated code (must be a bug in compiler, as improvement is -# "pathologically" high, in particular in comparison to other SHA -# modules). But the real twist is that it detects if hardware support -# for SHA256 is available and in such case utilizes it. Then the -# performance can reach >6.5x of assembler one for larger chunks. -# -# sha512_block_data_order is ~70% faster than gcc 3.3 generated code. - -# January 2009. -# -# Add support for hardware SHA512 and reschedule instructions to -# favour dual-issue z10 pipeline. Hardware SHA256/512 is ~4.7x faster -# than software. - -# November 2010. -# -# Adapt for -m31 build. If kernel supports what's called "highgprs" -# feature on Linux [see /proc/cpuinfo], it's possible to use 64-bit -# instructions and achieve "64-bit" performance even in 31-bit legacy -# application context. The feature is not specific to any particular -# processor, as long as it's "z-CPU". Latter implies that the code -# remains z/Architecture specific. On z900 SHA256 was measured to -# perform 2.4x and SHA512 - 13x better than code generated by gcc 4.3. - -$flavour = shift; - -if ($flavour =~ /3[12]/) { - $SIZE_T=4; - $g=""; -} else { - $SIZE_T=8; - $g="g"; -} - -$t0="%r0"; -$t1="%r1"; -$ctx="%r2"; $t2="%r2"; -$inp="%r3"; -$len="%r4"; # used as index in inner loop - -$A="%r5"; -$B="%r6"; -$C="%r7"; -$D="%r8"; -$E="%r9"; -$F="%r10"; -$G="%r11"; -$H="%r12"; @V=($A,$B,$C,$D,$E,$F,$G,$H); -$tbl="%r13"; -$T1="%r14"; -$sp="%r15"; - -while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} -open STDOUT,">$output"; - -if ($output =~ /512/) { - $label="512"; - $SZ=8; - $LD="lg"; # load from memory - $ST="stg"; # store to memory - $ADD="alg"; # add with memory operand - $ROT="rllg"; # rotate left - $SHR="srlg"; # logical right shift [see even at the end] - @Sigma0=(25,30,36); - @Sigma1=(23,46,50); - @sigma0=(56,63, 7); - @sigma1=( 3,45, 6); - $rounds=80; - $kimdfunc=3; # 0 means unknown/unsupported/unimplemented/disabled -} else { - $label="256"; - $SZ=4; - $LD="llgf"; # load from memory - $ST="st"; # store to memory - $ADD="al"; # add with memory operand - $ROT="rll"; # rotate left - $SHR="srl"; # logical right shift - @Sigma0=(10,19,30); - @Sigma1=( 7,21,26); - @sigma0=(14,25, 3); - @sigma1=(13,15,10); - $rounds=64; - $kimdfunc=2; # magic function code for kimd instruction -} -$Func="sha${label}_block_data_order"; -$Table="K${label}"; -$stdframe=16*$SIZE_T+4*8; -$frame=$stdframe+16*$SZ; - -sub BODY_00_15 { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___ if ($i<16); - $LD $T1,`$i*$SZ`($inp) ### $i -___ -$code.=<<___; - $ROT $t0,$e,$Sigma1[0] - $ROT $t1,$e,$Sigma1[1] - lgr $t2,$f - xgr $t0,$t1 - $ROT $t1,$t1,`$Sigma1[2]-$Sigma1[1]` - xgr $t2,$g - $ST $T1,`$stdframe+$SZ*($i%16)`($sp) - xgr $t0,$t1 # Sigma1(e) - algr $T1,$h # T1+=h - ngr $t2,$e - lgr $t1,$a - algr $T1,$t0 # T1+=Sigma1(e) - $ROT $h,$a,$Sigma0[0] - xgr $t2,$g # Ch(e,f,g) - $ADD $T1,`$i*$SZ`($len,$tbl) # T1+=K[i] - $ROT $t0,$a,$Sigma0[1] - algr $T1,$t2 # T1+=Ch(e,f,g) - ogr $t1,$b - xgr $h,$t0 - lgr $t2,$a - ngr $t1,$c - $ROT $t0,$t0,`$Sigma0[2]-$Sigma0[1]` - xgr $h,$t0 # h=Sigma0(a) - ngr $t2,$b - algr $h,$T1 # h+=T1 - ogr $t2,$t1 # Maj(a,b,c) - algr $d,$T1 # d+=T1 - algr $h,$t2 # h+=Maj(a,b,c) -___ -} - -sub BODY_16_XX { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___; - $LD $T1,`$stdframe+$SZ*(($i+1)%16)`($sp) ### $i - $LD $t1,`$stdframe+$SZ*(($i+14)%16)`($sp) - $ROT $t0,$T1,$sigma0[0] - $SHR $T1,$sigma0[2] - $ROT $t2,$t0,`$sigma0[1]-$sigma0[0]` - xgr $T1,$t0 - $ROT $t0,$t1,$sigma1[0] - xgr $T1,$t2 # sigma0(X[i+1]) - $SHR $t1,$sigma1[2] - $ADD $T1,`$stdframe+$SZ*($i%16)`($sp) # +=X[i] - xgr $t1,$t0 - $ROT $t0,$t0,`$sigma1[1]-$sigma1[0]` - $ADD $T1,`$stdframe+$SZ*(($i+9)%16)`($sp) # +=X[i+9] - xgr $t1,$t0 # sigma1(X[i+14]) - algr $T1,$t1 # +=sigma1(X[i+14]) -___ - &BODY_00_15(@_); -} - -$code.=<<___; -.text -.align 64 -.type $Table,\@object -$Table: -___ -$code.=<<___ if ($SZ==4); - .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 - .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 - .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 - .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 - .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc - .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da - .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 - .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 - .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 - .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 - .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 - .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 - .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 - .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 - .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 - .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -___ -$code.=<<___ if ($SZ==8); - .quad 0x428a2f98d728ae22,0x7137449123ef65cd - .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc - .quad 0x3956c25bf348b538,0x59f111f1b605d019 - .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118 - .quad 0xd807aa98a3030242,0x12835b0145706fbe - .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2 - .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1 - .quad 0x9bdc06a725c71235,0xc19bf174cf692694 - .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3 - .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65 - .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483 - .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5 - .quad 0x983e5152ee66dfab,0xa831c66d2db43210 - .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4 - .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725 - .quad 0x06ca6351e003826f,0x142929670a0e6e70 - .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926 - .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df - .quad 0x650a73548baf63de,0x766a0abb3c77b2a8 - .quad 0x81c2c92e47edaee6,0x92722c851482353b - .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001 - .quad 0xc24b8b70d0f89791,0xc76c51a30654be30 - .quad 0xd192e819d6ef5218,0xd69906245565a910 - .quad 0xf40e35855771202a,0x106aa07032bbd1b8 - .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53 - .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8 - .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb - .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3 - .quad 0x748f82ee5defb2fc,0x78a5636f43172f60 - .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec - .quad 0x90befffa23631e28,0xa4506cebde82bde9 - .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b - .quad 0xca273eceea26619c,0xd186b8c721c0c207 - .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178 - .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6 - .quad 0x113f9804bef90dae,0x1b710b35131c471b - .quad 0x28db77f523047d84,0x32caab7b40c72493 - .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c - .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a - .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 -___ -$code.=<<___; -.size $Table,.-$Table -.globl $Func -.type $Func,\@function -$Func: - sllg $len,$len,`log(16*$SZ)/log(2)` -___ -$code.=<<___ if ($kimdfunc); - larl %r1,OPENSSL_s390xcap_P - lg %r0,0(%r1) - tmhl %r0,0x4000 # check for message-security assist - jz .Lsoftware - lghi %r0,0 - la %r1,`2*$SIZE_T`($sp) - .long 0xb93e0002 # kimd %r0,%r2 - lg %r0,`2*$SIZE_T`($sp) - tmhh %r0,`0x8000>>$kimdfunc` - jz .Lsoftware - lghi %r0,$kimdfunc - lgr %r1,$ctx - lgr %r2,$inp - lgr %r3,$len - .long 0xb93e0002 # kimd %r0,%r2 - brc 1,.-4 # pay attention to "partial completion" - br %r14 -.align 16 -.Lsoftware: -___ -$code.=<<___; - lghi %r1,-$frame - la $len,0($len,$inp) - stm${g} $ctx,%r15,`2*$SIZE_T`($sp) - lgr %r0,$sp - la $sp,0(%r1,$sp) - st${g} %r0,0($sp) - - larl $tbl,$Table - $LD $A,`0*$SZ`($ctx) - $LD $B,`1*$SZ`($ctx) - $LD $C,`2*$SZ`($ctx) - $LD $D,`3*$SZ`($ctx) - $LD $E,`4*$SZ`($ctx) - $LD $F,`5*$SZ`($ctx) - $LD $G,`6*$SZ`($ctx) - $LD $H,`7*$SZ`($ctx) - -.Lloop: - lghi $len,0 -___ -for ($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); } -$code.=".Lrounds_16_xx:\n"; -for (;$i<32;$i++) { &BODY_16_XX($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - aghi $len,`16*$SZ` - lghi $t0,`($rounds-16)*$SZ` - clgr $len,$t0 - jne .Lrounds_16_xx - - l${g} $ctx,`$frame+2*$SIZE_T`($sp) - la $inp,`16*$SZ`($inp) - $ADD $A,`0*$SZ`($ctx) - $ADD $B,`1*$SZ`($ctx) - $ADD $C,`2*$SZ`($ctx) - $ADD $D,`3*$SZ`($ctx) - $ADD $E,`4*$SZ`($ctx) - $ADD $F,`5*$SZ`($ctx) - $ADD $G,`6*$SZ`($ctx) - $ADD $H,`7*$SZ`($ctx) - $ST $A,`0*$SZ`($ctx) - $ST $B,`1*$SZ`($ctx) - $ST $C,`2*$SZ`($ctx) - $ST $D,`3*$SZ`($ctx) - $ST $E,`4*$SZ`($ctx) - $ST $F,`5*$SZ`($ctx) - $ST $G,`6*$SZ`($ctx) - $ST $H,`7*$SZ`($ctx) - cl${g} $inp,`$frame+4*$SIZE_T`($sp) - jne .Lloop - - lm${g} %r6,%r15,`$frame+6*$SIZE_T`($sp) - br %r14 -.size $Func,.-$Func -.string "SHA${label} block transform for s390x, CRYPTOGAMS by <appro\@openssl.org>" -.comm OPENSSL_s390xcap_P,16,8 -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -# unlike 32-bit shift 64-bit one takes three arguments -$code =~ s/(srlg\s+)(%r[0-9]+),/$1$2,$2,/gm; - -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha512-sparcv9.pl b/app/openssl/crypto/sha/asm/sha512-sparcv9.pl deleted file mode 100644 index 58574078..00000000 --- a/app/openssl/crypto/sha/asm/sha512-sparcv9.pl +++ /dev/null @@ -1,594 +0,0 @@ -#!/usr/bin/env perl - -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see http://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA256 performance improvement over compiler generated code varies -# from 40% for Sun C [32-bit build] to 70% for gcc [3.3, 64-bit -# build]. Just like in SHA1 module I aim to ensure scalability on -# UltraSPARC T1 by packing X[16] to 8 64-bit registers. - -# SHA512 on pre-T1 UltraSPARC. -# -# Performance is >75% better than 64-bit code generated by Sun C and -# over 2x than 32-bit code. X[16] resides on stack, but access to it -# is scheduled for L2 latency and staged through 32 least significant -# bits of %l0-%l7. The latter is done to achieve 32-/64-bit ABI -# duality. Nevetheless it's ~40% faster than SHA256, which is pretty -# good [optimal coefficient is 50%]. -# -# SHA512 on UltraSPARC T1. -# -# It's not any faster than 64-bit code generated by Sun C 5.8. This is -# because 64-bit code generator has the advantage of using 64-bit -# loads(*) to access X[16], which I consciously traded for 32-/64-bit -# ABI duality [as per above]. But it surpasses 32-bit Sun C generated -# code by 60%, not to mention that it doesn't suffer from severe decay -# when running 4 times physical cores threads and that it leaves gcc -# [3.4] behind by over 4x factor! If compared to SHA256, single thread -# performance is only 10% better, but overall throughput for maximum -# amount of threads for given CPU exceeds corresponding one of SHA256 -# by 30% [again, optimal coefficient is 50%]. -# -# (*) Unlike pre-T1 UltraSPARC loads on T1 are executed strictly -# in-order, i.e. load instruction has to complete prior next -# instruction in given thread is executed, even if the latter is -# not dependent on load result! This means that on T1 two 32-bit -# loads are always slower than one 64-bit load. Once again this -# is unlike pre-T1 UltraSPARC, where, if scheduled appropriately, -# 2x32-bit loads can be as fast as 1x64-bit ones. - -$bits=32; -for (@ARGV) { $bits=64 if (/\-m64/ || /\-xarch\=v9/); } -if ($bits==64) { $bias=2047; $frame=192; } -else { $bias=0; $frame=112; } - -$output=shift; -open STDOUT,">$output"; - -if ($output =~ /512/) { - $label="512"; - $SZ=8; - $LD="ldx"; # load from memory - $ST="stx"; # store to memory - $SLL="sllx"; # shift left logical - $SRL="srlx"; # shift right logical - @Sigma0=(28,34,39); - @Sigma1=(14,18,41); - @sigma0=( 7, 1, 8); # right shift first - @sigma1=( 6,19,61); # right shift first - $lastK=0x817; - $rounds=80; - $align=4; - - $locals=16*$SZ; # X[16] - - $A="%o0"; - $B="%o1"; - $C="%o2"; - $D="%o3"; - $E="%o4"; - $F="%o5"; - $G="%g1"; - $H="%o7"; - @V=($A,$B,$C,$D,$E,$F,$G,$H); -} else { - $label="256"; - $SZ=4; - $LD="ld"; # load from memory - $ST="st"; # store to memory - $SLL="sll"; # shift left logical - $SRL="srl"; # shift right logical - @Sigma0=( 2,13,22); - @Sigma1=( 6,11,25); - @sigma0=( 3, 7,18); # right shift first - @sigma1=(10,17,19); # right shift first - $lastK=0x8f2; - $rounds=64; - $align=8; - - $locals=0; # X[16] is register resident - @X=("%o0","%o1","%o2","%o3","%o4","%o5","%g1","%o7"); - - $A="%l0"; - $B="%l1"; - $C="%l2"; - $D="%l3"; - $E="%l4"; - $F="%l5"; - $G="%l6"; - $H="%l7"; - @V=($A,$B,$C,$D,$E,$F,$G,$H); -} -$T1="%g2"; -$tmp0="%g3"; -$tmp1="%g4"; -$tmp2="%g5"; - -$ctx="%i0"; -$inp="%i1"; -$len="%i2"; -$Ktbl="%i3"; -$tmp31="%i4"; -$tmp32="%i5"; - -########### SHA256 -$Xload = sub { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; - - if ($i==0) { -$code.=<<___; - ldx [$inp+0],@X[0] - ldx [$inp+16],@X[2] - ldx [$inp+32],@X[4] - ldx [$inp+48],@X[6] - ldx [$inp+8],@X[1] - ldx [$inp+24],@X[3] - subcc %g0,$tmp31,$tmp32 ! should be 64-$tmp31, but -$tmp31 works too - ldx [$inp+40],@X[5] - bz,pt %icc,.Laligned - ldx [$inp+56],@X[7] - - sllx @X[0],$tmp31,@X[0] - ldx [$inp+64],$T1 -___ -for($j=0;$j<7;$j++) -{ $code.=<<___; - srlx @X[$j+1],$tmp32,$tmp1 - sllx @X[$j+1],$tmp31,@X[$j+1] - or $tmp1,@X[$j],@X[$j] -___ -} -$code.=<<___; - srlx $T1,$tmp32,$T1 - or $T1,@X[7],@X[7] -.Laligned: -___ - } - - if ($i&1) { - $code.="\tadd @X[$i/2],$h,$T1\n"; - } else { - $code.="\tsrlx @X[$i/2],32,$T1\n\tadd $h,$T1,$T1\n"; - } -} if ($SZ==4); - -########### SHA512 -$Xload = sub { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; -my @pair=("%l".eval(($i*2)%8),"%l".eval(($i*2)%8+1),"%l".eval((($i+1)*2)%8)); - -$code.=<<___ if ($i==0); - ld [$inp+0],%l0 - ld [$inp+4],%l1 - ld [$inp+8],%l2 - ld [$inp+12],%l3 - ld [$inp+16],%l4 - ld [$inp+20],%l5 - ld [$inp+24],%l6 - ld [$inp+28],%l7 -___ -$code.=<<___ if ($i<15); - sllx @pair[1],$tmp31,$tmp2 ! Xload($i) - add $tmp31,32,$tmp0 - sllx @pair[0],$tmp0,$tmp1 - `"ld [$inp+".eval(32+0+$i*8)."],@pair[0]" if ($i<12)` - srlx @pair[2],$tmp32,@pair[1] - or $tmp1,$tmp2,$tmp2 - or @pair[1],$tmp2,$tmp2 - `"ld [$inp+".eval(32+4+$i*8)."],@pair[1]" if ($i<12)` - add $h,$tmp2,$T1 - $ST $tmp2,[%sp+`$bias+$frame+$i*$SZ`] -___ -$code.=<<___ if ($i==12); - brnz,a $tmp31,.+8 - ld [$inp+128],%l0 -___ -$code.=<<___ if ($i==15); - ld [%sp+`$bias+$frame+(($i+1+1)%16)*$SZ+0`],%l2 - sllx @pair[1],$tmp31,$tmp2 ! Xload($i) - add $tmp31,32,$tmp0 - ld [%sp+`$bias+$frame+(($i+1+1)%16)*$SZ+4`],%l3 - sllx @pair[0],$tmp0,$tmp1 - ld [%sp+`$bias+$frame+(($i+1+9)%16)*$SZ+0`],%l4 - srlx @pair[2],$tmp32,@pair[1] - or $tmp1,$tmp2,$tmp2 - ld [%sp+`$bias+$frame+(($i+1+9)%16)*$SZ+4`],%l5 - or @pair[1],$tmp2,$tmp2 - ld [%sp+`$bias+$frame+(($i+1+14)%16)*$SZ+0`],%l6 - add $h,$tmp2,$T1 - $ST $tmp2,[%sp+`$bias+$frame+$i*$SZ`] - ld [%sp+`$bias+$frame+(($i+1+14)%16)*$SZ+4`],%l7 - ld [%sp+`$bias+$frame+(($i+1+0)%16)*$SZ+0`],%l0 - ld [%sp+`$bias+$frame+(($i+1+0)%16)*$SZ+4`],%l1 -___ -} if ($SZ==8); - -########### common -sub BODY_00_15 { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_; - - if ($i<16) { - &$Xload(@_); - } else { - $code.="\tadd $h,$T1,$T1\n"; - } - -$code.=<<___; - $SRL $e,@Sigma1[0],$h !! $i - xor $f,$g,$tmp2 - $SLL $e,`$SZ*8-@Sigma1[2]`,$tmp1 - and $e,$tmp2,$tmp2 - $SRL $e,@Sigma1[1],$tmp0 - xor $tmp1,$h,$h - $SLL $e,`$SZ*8-@Sigma1[1]`,$tmp1 - xor $tmp0,$h,$h - $SRL $e,@Sigma1[2],$tmp0 - xor $tmp1,$h,$h - $SLL $e,`$SZ*8-@Sigma1[0]`,$tmp1 - xor $tmp0,$h,$h - xor $g,$tmp2,$tmp2 ! Ch(e,f,g) - xor $tmp1,$h,$tmp0 ! Sigma1(e) - - $SRL $a,@Sigma0[0],$h - add $tmp2,$T1,$T1 - $LD [$Ktbl+`$i*$SZ`],$tmp2 ! K[$i] - $SLL $a,`$SZ*8-@Sigma0[2]`,$tmp1 - add $tmp0,$T1,$T1 - $SRL $a,@Sigma0[1],$tmp0 - xor $tmp1,$h,$h - $SLL $a,`$SZ*8-@Sigma0[1]`,$tmp1 - xor $tmp0,$h,$h - $SRL $a,@Sigma0[2],$tmp0 - xor $tmp1,$h,$h - $SLL $a,`$SZ*8-@Sigma0[0]`,$tmp1 - xor $tmp0,$h,$h - xor $tmp1,$h,$h ! Sigma0(a) - - or $a,$b,$tmp0 - and $a,$b,$tmp1 - and $c,$tmp0,$tmp0 - or $tmp0,$tmp1,$tmp1 ! Maj(a,b,c) - add $tmp2,$T1,$T1 ! +=K[$i] - add $tmp1,$h,$h - - add $T1,$d,$d - add $T1,$h,$h -___ -} - -########### SHA256 -$BODY_16_XX = sub { -my $i=@_[0]; -my $xi; - - if ($i&1) { - $xi=$tmp32; - $code.="\tsrlx @X[(($i+1)/2)%8],32,$xi\n"; - } else { - $xi=@X[(($i+1)/2)%8]; - } -$code.=<<___; - srl $xi,@sigma0[0],$T1 !! Xupdate($i) - sll $xi,`32-@sigma0[2]`,$tmp1 - srl $xi,@sigma0[1],$tmp0 - xor $tmp1,$T1,$T1 - sll $tmp1,`@sigma0[2]-@sigma0[1]`,$tmp1 - xor $tmp0,$T1,$T1 - srl $xi,@sigma0[2],$tmp0 - xor $tmp1,$T1,$T1 -___ - if ($i&1) { - $xi=@X[(($i+14)/2)%8]; - } else { - $xi=$tmp32; - $code.="\tsrlx @X[(($i+14)/2)%8],32,$xi\n"; - } -$code.=<<___; - srl $xi,@sigma1[0],$tmp2 - xor $tmp0,$T1,$T1 ! T1=sigma0(X[i+1]) - sll $xi,`32-@sigma1[2]`,$tmp1 - srl $xi,@sigma1[1],$tmp0 - xor $tmp1,$tmp2,$tmp2 - sll $tmp1,`@sigma1[2]-@sigma1[1]`,$tmp1 - xor $tmp0,$tmp2,$tmp2 - srl $xi,@sigma1[2],$tmp0 - xor $tmp1,$tmp2,$tmp2 -___ - if ($i&1) { - $xi=@X[($i/2)%8]; -$code.=<<___; - srlx @X[(($i+9)/2)%8],32,$tmp1 ! X[i+9] - xor $tmp0,$tmp2,$tmp2 ! sigma1(X[i+14]) - srl @X[($i/2)%8],0,$tmp0 - add $tmp2,$tmp1,$tmp1 - add $xi,$T1,$T1 ! +=X[i] - xor $tmp0,@X[($i/2)%8],@X[($i/2)%8] - add $tmp1,$T1,$T1 - - srl $T1,0,$T1 - or $T1,@X[($i/2)%8],@X[($i/2)%8] -___ - } else { - $xi=@X[(($i+9)/2)%8]; -$code.=<<___; - srlx @X[($i/2)%8],32,$tmp1 ! X[i] - xor $tmp0,$tmp2,$tmp2 ! sigma1(X[i+14]) - add $xi,$T1,$T1 ! +=X[i+9] - add $tmp2,$tmp1,$tmp1 - srl @X[($i/2)%8],0,@X[($i/2)%8] - add $tmp1,$T1,$T1 - - sllx $T1,32,$tmp0 - or $tmp0,@X[($i/2)%8],@X[($i/2)%8] -___ - } - &BODY_00_15(@_); -} if ($SZ==4); - -########### SHA512 -$BODY_16_XX = sub { -my $i=@_[0]; -my @pair=("%l".eval(($i*2)%8),"%l".eval(($i*2)%8+1)); - -$code.=<<___; - sllx %l2,32,$tmp0 !! Xupdate($i) - or %l3,$tmp0,$tmp0 - - srlx $tmp0,@sigma0[0],$T1 - ld [%sp+`$bias+$frame+(($i+1+1)%16)*$SZ+0`],%l2 - sllx $tmp0,`64-@sigma0[2]`,$tmp1 - ld [%sp+`$bias+$frame+(($i+1+1)%16)*$SZ+4`],%l3 - srlx $tmp0,@sigma0[1],$tmp0 - xor $tmp1,$T1,$T1 - sllx $tmp1,`@sigma0[2]-@sigma0[1]`,$tmp1 - xor $tmp0,$T1,$T1 - srlx $tmp0,`@sigma0[2]-@sigma0[1]`,$tmp0 - xor $tmp1,$T1,$T1 - sllx %l6,32,$tmp2 - xor $tmp0,$T1,$T1 ! sigma0(X[$i+1]) - or %l7,$tmp2,$tmp2 - - srlx $tmp2,@sigma1[0],$tmp1 - ld [%sp+`$bias+$frame+(($i+1+14)%16)*$SZ+0`],%l6 - sllx $tmp2,`64-@sigma1[2]`,$tmp0 - ld [%sp+`$bias+$frame+(($i+1+14)%16)*$SZ+4`],%l7 - srlx $tmp2,@sigma1[1],$tmp2 - xor $tmp0,$tmp1,$tmp1 - sllx $tmp0,`@sigma1[2]-@sigma1[1]`,$tmp0 - xor $tmp2,$tmp1,$tmp1 - srlx $tmp2,`@sigma1[2]-@sigma1[1]`,$tmp2 - xor $tmp0,$tmp1,$tmp1 - sllx %l4,32,$tmp0 - xor $tmp2,$tmp1,$tmp1 ! sigma1(X[$i+14]) - ld [%sp+`$bias+$frame+(($i+1+9)%16)*$SZ+0`],%l4 - or %l5,$tmp0,$tmp0 - ld [%sp+`$bias+$frame+(($i+1+9)%16)*$SZ+4`],%l5 - - sllx %l0,32,$tmp2 - add $tmp1,$T1,$T1 - ld [%sp+`$bias+$frame+(($i+1+0)%16)*$SZ+0`],%l0 - or %l1,$tmp2,$tmp2 - add $tmp0,$T1,$T1 ! +=X[$i+9] - ld [%sp+`$bias+$frame+(($i+1+0)%16)*$SZ+4`],%l1 - add $tmp2,$T1,$T1 ! +=X[$i] - $ST $T1,[%sp+`$bias+$frame+($i%16)*$SZ`] -___ - &BODY_00_15(@_); -} if ($SZ==8); - -$code.=<<___ if ($bits==64); -.register %g2,#scratch -.register %g3,#scratch -___ -$code.=<<___; -.section ".text",#alloc,#execinstr - -.align 64 -K${label}: -.type K${label},#object -___ -if ($SZ==4) { -$code.=<<___; - .long 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5 - .long 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5 - .long 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3 - .long 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174 - .long 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc - .long 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da - .long 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7 - .long 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967 - .long 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13 - .long 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85 - .long 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3 - .long 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070 - .long 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5 - .long 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3 - .long 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208 - .long 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 -___ -} else { -$code.=<<___; - .long 0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd - .long 0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc - .long 0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019 - .long 0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118 - .long 0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe - .long 0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2 - .long 0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1 - .long 0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694 - .long 0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3 - .long 0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65 - .long 0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483 - .long 0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5 - .long 0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210 - .long 0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4 - .long 0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725 - .long 0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70 - .long 0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926 - .long 0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df - .long 0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8 - .long 0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b - .long 0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001 - .long 0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30 - .long 0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910 - .long 0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8 - .long 0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53 - .long 0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8 - .long 0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb - .long 0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3 - .long 0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60 - .long 0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec - .long 0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9 - .long 0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b - .long 0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207 - .long 0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178 - .long 0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6 - .long 0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b - .long 0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493 - .long 0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c - .long 0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a - .long 0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817 -___ -} -$code.=<<___; -.size K${label},.-K${label} -.globl sha${label}_block_data_order -sha${label}_block_data_order: - save %sp,`-$frame-$locals`,%sp - and $inp,`$align-1`,$tmp31 - sllx $len,`log(16*$SZ)/log(2)`,$len - andn $inp,`$align-1`,$inp - sll $tmp31,3,$tmp31 - add $inp,$len,$len -___ -$code.=<<___ if ($SZ==8); # SHA512 - mov 32,$tmp32 - sub $tmp32,$tmp31,$tmp32 -___ -$code.=<<___; -.Lpic: call .+8 - add %o7,K${label}-.Lpic,$Ktbl - - $LD [$ctx+`0*$SZ`],$A - $LD [$ctx+`1*$SZ`],$B - $LD [$ctx+`2*$SZ`],$C - $LD [$ctx+`3*$SZ`],$D - $LD [$ctx+`4*$SZ`],$E - $LD [$ctx+`5*$SZ`],$F - $LD [$ctx+`6*$SZ`],$G - $LD [$ctx+`7*$SZ`],$H - -.Lloop: -___ -for ($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); } -$code.=".L16_xx:\n"; -for (;$i<32;$i++) { &$BODY_16_XX($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; - and $tmp2,0xfff,$tmp2 - cmp $tmp2,$lastK - bne .L16_xx - add $Ktbl,`16*$SZ`,$Ktbl ! Ktbl+=16 - -___ -$code.=<<___ if ($SZ==4); # SHA256 - $LD [$ctx+`0*$SZ`],@X[0] - $LD [$ctx+`1*$SZ`],@X[1] - $LD [$ctx+`2*$SZ`],@X[2] - $LD [$ctx+`3*$SZ`],@X[3] - $LD [$ctx+`4*$SZ`],@X[4] - $LD [$ctx+`5*$SZ`],@X[5] - $LD [$ctx+`6*$SZ`],@X[6] - $LD [$ctx+`7*$SZ`],@X[7] - - add $A,@X[0],$A - $ST $A,[$ctx+`0*$SZ`] - add $B,@X[1],$B - $ST $B,[$ctx+`1*$SZ`] - add $C,@X[2],$C - $ST $C,[$ctx+`2*$SZ`] - add $D,@X[3],$D - $ST $D,[$ctx+`3*$SZ`] - add $E,@X[4],$E - $ST $E,[$ctx+`4*$SZ`] - add $F,@X[5],$F - $ST $F,[$ctx+`5*$SZ`] - add $G,@X[6],$G - $ST $G,[$ctx+`6*$SZ`] - add $H,@X[7],$H - $ST $H,[$ctx+`7*$SZ`] -___ -$code.=<<___ if ($SZ==8); # SHA512 - ld [$ctx+`0*$SZ+0`],%l0 - ld [$ctx+`0*$SZ+4`],%l1 - ld [$ctx+`1*$SZ+0`],%l2 - ld [$ctx+`1*$SZ+4`],%l3 - ld [$ctx+`2*$SZ+0`],%l4 - ld [$ctx+`2*$SZ+4`],%l5 - ld [$ctx+`3*$SZ+0`],%l6 - - sllx %l0,32,$tmp0 - ld [$ctx+`3*$SZ+4`],%l7 - sllx %l2,32,$tmp1 - or %l1,$tmp0,$tmp0 - or %l3,$tmp1,$tmp1 - add $tmp0,$A,$A - add $tmp1,$B,$B - $ST $A,[$ctx+`0*$SZ`] - sllx %l4,32,$tmp2 - $ST $B,[$ctx+`1*$SZ`] - sllx %l6,32,$T1 - or %l5,$tmp2,$tmp2 - or %l7,$T1,$T1 - add $tmp2,$C,$C - $ST $C,[$ctx+`2*$SZ`] - add $T1,$D,$D - $ST $D,[$ctx+`3*$SZ`] - - ld [$ctx+`4*$SZ+0`],%l0 - ld [$ctx+`4*$SZ+4`],%l1 - ld [$ctx+`5*$SZ+0`],%l2 - ld [$ctx+`5*$SZ+4`],%l3 - ld [$ctx+`6*$SZ+0`],%l4 - ld [$ctx+`6*$SZ+4`],%l5 - ld [$ctx+`7*$SZ+0`],%l6 - - sllx %l0,32,$tmp0 - ld [$ctx+`7*$SZ+4`],%l7 - sllx %l2,32,$tmp1 - or %l1,$tmp0,$tmp0 - or %l3,$tmp1,$tmp1 - add $tmp0,$E,$E - add $tmp1,$F,$F - $ST $E,[$ctx+`4*$SZ`] - sllx %l4,32,$tmp2 - $ST $F,[$ctx+`5*$SZ`] - sllx %l6,32,$T1 - or %l5,$tmp2,$tmp2 - or %l7,$T1,$T1 - add $tmp2,$G,$G - $ST $G,[$ctx+`6*$SZ`] - add $T1,$H,$H - $ST $H,[$ctx+`7*$SZ`] -___ -$code.=<<___; - add $inp,`16*$SZ`,$inp ! advance inp - cmp $inp,$len - bne `$bits==64?"%xcc":"%icc"`,.Lloop - sub $Ktbl,`($rounds-16)*$SZ`,$Ktbl ! rewind Ktbl - - ret - restore -.type sha${label}_block_data_order,#function -.size sha${label}_block_data_order,(.-sha${label}_block_data_order) -.asciz "SHA${label} block transform for SPARCv9, CRYPTOGAMS by <appro\@openssl.org>" -.align 4 -___ - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -print $code; -close STDOUT; diff --git a/app/openssl/crypto/sha/asm/sha512-x86_64.S b/app/openssl/crypto/sha/asm/sha512-x86_64.S deleted file mode 100644 index 2d3294e0..00000000 --- a/app/openssl/crypto/sha/asm/sha512-x86_64.S +++ /dev/null @@ -1,1802 +0,0 @@ -.text - -.globl sha512_block_data_order -.type sha512_block_data_order,@function -.align 16 -sha512_block_data_order: - pushq %rbx - pushq %rbp - pushq %r12 - pushq %r13 - pushq %r14 - pushq %r15 - movq %rsp,%r11 - shlq $4,%rdx - subq $128+32,%rsp - leaq (%rsi,%rdx,8),%rdx - andq $-64,%rsp - movq %rdi,128+0(%rsp) - movq %rsi,128+8(%rsp) - movq %rdx,128+16(%rsp) - movq %r11,128+24(%rsp) -.Lprologue: - - leaq K512(%rip),%rbp - - movq 0(%rdi),%rax - movq 8(%rdi),%rbx - movq 16(%rdi),%rcx - movq 24(%rdi),%rdx - movq 32(%rdi),%r8 - movq 40(%rdi),%r9 - movq 48(%rdi),%r10 - movq 56(%rdi),%r11 - jmp .Lloop - -.align 16 -.Lloop: - xorq %rdi,%rdi - movq 0(%rsi),%r12 - movq %r8,%r13 - movq %rax,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r9,%r15 - movq %r12,0(%rsp) - - rorq $5,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - rorq $4,%r13 - addq %r11,%r12 - xorq %rax,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r8,%r15 - movq %rbx,%r11 - - rorq $6,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - xorq %rcx,%r11 - xorq %rax,%r14 - addq %r15,%r12 - movq %rbx,%r15 - - rorq $14,%r13 - andq %rax,%r11 - andq %rcx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r11 - - addq %r12,%rdx - addq %r12,%r11 - leaq 1(%rdi),%rdi - addq %r14,%r11 - - movq 8(%rsi),%r12 - movq %rdx,%r13 - movq %r11,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r8,%r15 - movq %r12,8(%rsp) - - rorq $5,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - rorq $4,%r13 - addq %r10,%r12 - xorq %r11,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rdx,%r15 - movq %rax,%r10 - - rorq $6,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - xorq %rbx,%r10 - xorq %r11,%r14 - addq %r15,%r12 - movq %rax,%r15 - - rorq $14,%r13 - andq %r11,%r10 - andq %rbx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r10 - - addq %r12,%rcx - addq %r12,%r10 - leaq 1(%rdi),%rdi - addq %r14,%r10 - - movq 16(%rsi),%r12 - movq %rcx,%r13 - movq %r10,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rdx,%r15 - movq %r12,16(%rsp) - - rorq $5,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - rorq $4,%r13 - addq %r9,%r12 - xorq %r10,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rcx,%r15 - movq %r11,%r9 - - rorq $6,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - xorq %rax,%r9 - xorq %r10,%r14 - addq %r15,%r12 - movq %r11,%r15 - - rorq $14,%r13 - andq %r10,%r9 - andq %rax,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r9 - - addq %r12,%rbx - addq %r12,%r9 - leaq 1(%rdi),%rdi - addq %r14,%r9 - - movq 24(%rsi),%r12 - movq %rbx,%r13 - movq %r9,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rcx,%r15 - movq %r12,24(%rsp) - - rorq $5,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - rorq $4,%r13 - addq %r8,%r12 - xorq %r9,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rbx,%r15 - movq %r10,%r8 - - rorq $6,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - xorq %r11,%r8 - xorq %r9,%r14 - addq %r15,%r12 - movq %r10,%r15 - - rorq $14,%r13 - andq %r9,%r8 - andq %r11,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r8 - - addq %r12,%rax - addq %r12,%r8 - leaq 1(%rdi),%rdi - addq %r14,%r8 - - movq 32(%rsi),%r12 - movq %rax,%r13 - movq %r8,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rbx,%r15 - movq %r12,32(%rsp) - - rorq $5,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - rorq $4,%r13 - addq %rdx,%r12 - xorq %r8,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rax,%r15 - movq %r9,%rdx - - rorq $6,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - xorq %r10,%rdx - xorq %r8,%r14 - addq %r15,%r12 - movq %r9,%r15 - - rorq $14,%r13 - andq %r8,%rdx - andq %r10,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rdx - - addq %r12,%r11 - addq %r12,%rdx - leaq 1(%rdi),%rdi - addq %r14,%rdx - - movq 40(%rsi),%r12 - movq %r11,%r13 - movq %rdx,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rax,%r15 - movq %r12,40(%rsp) - - rorq $5,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - rorq $4,%r13 - addq %rcx,%r12 - xorq %rdx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r11,%r15 - movq %r8,%rcx - - rorq $6,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - xorq %r9,%rcx - xorq %rdx,%r14 - addq %r15,%r12 - movq %r8,%r15 - - rorq $14,%r13 - andq %rdx,%rcx - andq %r9,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rcx - - addq %r12,%r10 - addq %r12,%rcx - leaq 1(%rdi),%rdi - addq %r14,%rcx - - movq 48(%rsi),%r12 - movq %r10,%r13 - movq %rcx,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r11,%r15 - movq %r12,48(%rsp) - - rorq $5,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - rorq $4,%r13 - addq %rbx,%r12 - xorq %rcx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r10,%r15 - movq %rdx,%rbx - - rorq $6,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - xorq %r8,%rbx - xorq %rcx,%r14 - addq %r15,%r12 - movq %rdx,%r15 - - rorq $14,%r13 - andq %rcx,%rbx - andq %r8,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rbx - - addq %r12,%r9 - addq %r12,%rbx - leaq 1(%rdi),%rdi - addq %r14,%rbx - - movq 56(%rsi),%r12 - movq %r9,%r13 - movq %rbx,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r10,%r15 - movq %r12,56(%rsp) - - rorq $5,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - rorq $4,%r13 - addq %rax,%r12 - xorq %rbx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r9,%r15 - movq %rcx,%rax - - rorq $6,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - xorq %rdx,%rax - xorq %rbx,%r14 - addq %r15,%r12 - movq %rcx,%r15 - - rorq $14,%r13 - andq %rbx,%rax - andq %rdx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rax - - addq %r12,%r8 - addq %r12,%rax - leaq 1(%rdi),%rdi - addq %r14,%rax - - movq 64(%rsi),%r12 - movq %r8,%r13 - movq %rax,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r9,%r15 - movq %r12,64(%rsp) - - rorq $5,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - rorq $4,%r13 - addq %r11,%r12 - xorq %rax,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r8,%r15 - movq %rbx,%r11 - - rorq $6,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - xorq %rcx,%r11 - xorq %rax,%r14 - addq %r15,%r12 - movq %rbx,%r15 - - rorq $14,%r13 - andq %rax,%r11 - andq %rcx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r11 - - addq %r12,%rdx - addq %r12,%r11 - leaq 1(%rdi),%rdi - addq %r14,%r11 - - movq 72(%rsi),%r12 - movq %rdx,%r13 - movq %r11,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r8,%r15 - movq %r12,72(%rsp) - - rorq $5,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - rorq $4,%r13 - addq %r10,%r12 - xorq %r11,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rdx,%r15 - movq %rax,%r10 - - rorq $6,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - xorq %rbx,%r10 - xorq %r11,%r14 - addq %r15,%r12 - movq %rax,%r15 - - rorq $14,%r13 - andq %r11,%r10 - andq %rbx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r10 - - addq %r12,%rcx - addq %r12,%r10 - leaq 1(%rdi),%rdi - addq %r14,%r10 - - movq 80(%rsi),%r12 - movq %rcx,%r13 - movq %r10,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rdx,%r15 - movq %r12,80(%rsp) - - rorq $5,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - rorq $4,%r13 - addq %r9,%r12 - xorq %r10,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rcx,%r15 - movq %r11,%r9 - - rorq $6,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - xorq %rax,%r9 - xorq %r10,%r14 - addq %r15,%r12 - movq %r11,%r15 - - rorq $14,%r13 - andq %r10,%r9 - andq %rax,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r9 - - addq %r12,%rbx - addq %r12,%r9 - leaq 1(%rdi),%rdi - addq %r14,%r9 - - movq 88(%rsi),%r12 - movq %rbx,%r13 - movq %r9,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rcx,%r15 - movq %r12,88(%rsp) - - rorq $5,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - rorq $4,%r13 - addq %r8,%r12 - xorq %r9,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rbx,%r15 - movq %r10,%r8 - - rorq $6,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - xorq %r11,%r8 - xorq %r9,%r14 - addq %r15,%r12 - movq %r10,%r15 - - rorq $14,%r13 - andq %r9,%r8 - andq %r11,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r8 - - addq %r12,%rax - addq %r12,%r8 - leaq 1(%rdi),%rdi - addq %r14,%r8 - - movq 96(%rsi),%r12 - movq %rax,%r13 - movq %r8,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rbx,%r15 - movq %r12,96(%rsp) - - rorq $5,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - rorq $4,%r13 - addq %rdx,%r12 - xorq %r8,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rax,%r15 - movq %r9,%rdx - - rorq $6,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - xorq %r10,%rdx - xorq %r8,%r14 - addq %r15,%r12 - movq %r9,%r15 - - rorq $14,%r13 - andq %r8,%rdx - andq %r10,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rdx - - addq %r12,%r11 - addq %r12,%rdx - leaq 1(%rdi),%rdi - addq %r14,%rdx - - movq 104(%rsi),%r12 - movq %r11,%r13 - movq %rdx,%r14 - bswapq %r12 - rorq $23,%r13 - movq %rax,%r15 - movq %r12,104(%rsp) - - rorq $5,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - rorq $4,%r13 - addq %rcx,%r12 - xorq %rdx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r11,%r15 - movq %r8,%rcx - - rorq $6,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - xorq %r9,%rcx - xorq %rdx,%r14 - addq %r15,%r12 - movq %r8,%r15 - - rorq $14,%r13 - andq %rdx,%rcx - andq %r9,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rcx - - addq %r12,%r10 - addq %r12,%rcx - leaq 1(%rdi),%rdi - addq %r14,%rcx - - movq 112(%rsi),%r12 - movq %r10,%r13 - movq %rcx,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r11,%r15 - movq %r12,112(%rsp) - - rorq $5,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - rorq $4,%r13 - addq %rbx,%r12 - xorq %rcx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r10,%r15 - movq %rdx,%rbx - - rorq $6,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - xorq %r8,%rbx - xorq %rcx,%r14 - addq %r15,%r12 - movq %rdx,%r15 - - rorq $14,%r13 - andq %rcx,%rbx - andq %r8,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rbx - - addq %r12,%r9 - addq %r12,%rbx - leaq 1(%rdi),%rdi - addq %r14,%rbx - - movq 120(%rsi),%r12 - movq %r9,%r13 - movq %rbx,%r14 - bswapq %r12 - rorq $23,%r13 - movq %r10,%r15 - movq %r12,120(%rsp) - - rorq $5,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - rorq $4,%r13 - addq %rax,%r12 - xorq %rbx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r9,%r15 - movq %rcx,%rax - - rorq $6,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - xorq %rdx,%rax - xorq %rbx,%r14 - addq %r15,%r12 - movq %rcx,%r15 - - rorq $14,%r13 - andq %rbx,%rax - andq %rdx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rax - - addq %r12,%r8 - addq %r12,%rax - leaq 1(%rdi),%rdi - addq %r14,%rax - - jmp .Lrounds_16_xx -.align 16 -.Lrounds_16_xx: - movq 8(%rsp),%r13 - movq 112(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 72(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 0(%rsp),%r12 - movq %r8,%r13 - addq %r14,%r12 - movq %rax,%r14 - rorq $23,%r13 - movq %r9,%r15 - movq %r12,0(%rsp) - - rorq $5,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - rorq $4,%r13 - addq %r11,%r12 - xorq %rax,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r8,%r15 - movq %rbx,%r11 - - rorq $6,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - xorq %rcx,%r11 - xorq %rax,%r14 - addq %r15,%r12 - movq %rbx,%r15 - - rorq $14,%r13 - andq %rax,%r11 - andq %rcx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r11 - - addq %r12,%rdx - addq %r12,%r11 - leaq 1(%rdi),%rdi - addq %r14,%r11 - - movq 16(%rsp),%r13 - movq 120(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 80(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 8(%rsp),%r12 - movq %rdx,%r13 - addq %r14,%r12 - movq %r11,%r14 - rorq $23,%r13 - movq %r8,%r15 - movq %r12,8(%rsp) - - rorq $5,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - rorq $4,%r13 - addq %r10,%r12 - xorq %r11,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rdx,%r15 - movq %rax,%r10 - - rorq $6,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - xorq %rbx,%r10 - xorq %r11,%r14 - addq %r15,%r12 - movq %rax,%r15 - - rorq $14,%r13 - andq %r11,%r10 - andq %rbx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r10 - - addq %r12,%rcx - addq %r12,%r10 - leaq 1(%rdi),%rdi - addq %r14,%r10 - - movq 24(%rsp),%r13 - movq 0(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 88(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 16(%rsp),%r12 - movq %rcx,%r13 - addq %r14,%r12 - movq %r10,%r14 - rorq $23,%r13 - movq %rdx,%r15 - movq %r12,16(%rsp) - - rorq $5,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - rorq $4,%r13 - addq %r9,%r12 - xorq %r10,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rcx,%r15 - movq %r11,%r9 - - rorq $6,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - xorq %rax,%r9 - xorq %r10,%r14 - addq %r15,%r12 - movq %r11,%r15 - - rorq $14,%r13 - andq %r10,%r9 - andq %rax,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r9 - - addq %r12,%rbx - addq %r12,%r9 - leaq 1(%rdi),%rdi - addq %r14,%r9 - - movq 32(%rsp),%r13 - movq 8(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 96(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 24(%rsp),%r12 - movq %rbx,%r13 - addq %r14,%r12 - movq %r9,%r14 - rorq $23,%r13 - movq %rcx,%r15 - movq %r12,24(%rsp) - - rorq $5,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - rorq $4,%r13 - addq %r8,%r12 - xorq %r9,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rbx,%r15 - movq %r10,%r8 - - rorq $6,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - xorq %r11,%r8 - xorq %r9,%r14 - addq %r15,%r12 - movq %r10,%r15 - - rorq $14,%r13 - andq %r9,%r8 - andq %r11,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r8 - - addq %r12,%rax - addq %r12,%r8 - leaq 1(%rdi),%rdi - addq %r14,%r8 - - movq 40(%rsp),%r13 - movq 16(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 104(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 32(%rsp),%r12 - movq %rax,%r13 - addq %r14,%r12 - movq %r8,%r14 - rorq $23,%r13 - movq %rbx,%r15 - movq %r12,32(%rsp) - - rorq $5,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - rorq $4,%r13 - addq %rdx,%r12 - xorq %r8,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rax,%r15 - movq %r9,%rdx - - rorq $6,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - xorq %r10,%rdx - xorq %r8,%r14 - addq %r15,%r12 - movq %r9,%r15 - - rorq $14,%r13 - andq %r8,%rdx - andq %r10,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rdx - - addq %r12,%r11 - addq %r12,%rdx - leaq 1(%rdi),%rdi - addq %r14,%rdx - - movq 48(%rsp),%r13 - movq 24(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 112(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 40(%rsp),%r12 - movq %r11,%r13 - addq %r14,%r12 - movq %rdx,%r14 - rorq $23,%r13 - movq %rax,%r15 - movq %r12,40(%rsp) - - rorq $5,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - rorq $4,%r13 - addq %rcx,%r12 - xorq %rdx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r11,%r15 - movq %r8,%rcx - - rorq $6,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - xorq %r9,%rcx - xorq %rdx,%r14 - addq %r15,%r12 - movq %r8,%r15 - - rorq $14,%r13 - andq %rdx,%rcx - andq %r9,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rcx - - addq %r12,%r10 - addq %r12,%rcx - leaq 1(%rdi),%rdi - addq %r14,%rcx - - movq 56(%rsp),%r13 - movq 32(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 120(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 48(%rsp),%r12 - movq %r10,%r13 - addq %r14,%r12 - movq %rcx,%r14 - rorq $23,%r13 - movq %r11,%r15 - movq %r12,48(%rsp) - - rorq $5,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - rorq $4,%r13 - addq %rbx,%r12 - xorq %rcx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r10,%r15 - movq %rdx,%rbx - - rorq $6,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - xorq %r8,%rbx - xorq %rcx,%r14 - addq %r15,%r12 - movq %rdx,%r15 - - rorq $14,%r13 - andq %rcx,%rbx - andq %r8,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rbx - - addq %r12,%r9 - addq %r12,%rbx - leaq 1(%rdi),%rdi - addq %r14,%rbx - - movq 64(%rsp),%r13 - movq 40(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 0(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 56(%rsp),%r12 - movq %r9,%r13 - addq %r14,%r12 - movq %rbx,%r14 - rorq $23,%r13 - movq %r10,%r15 - movq %r12,56(%rsp) - - rorq $5,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - rorq $4,%r13 - addq %rax,%r12 - xorq %rbx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r9,%r15 - movq %rcx,%rax - - rorq $6,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - xorq %rdx,%rax - xorq %rbx,%r14 - addq %r15,%r12 - movq %rcx,%r15 - - rorq $14,%r13 - andq %rbx,%rax - andq %rdx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rax - - addq %r12,%r8 - addq %r12,%rax - leaq 1(%rdi),%rdi - addq %r14,%rax - - movq 72(%rsp),%r13 - movq 48(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 8(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 64(%rsp),%r12 - movq %r8,%r13 - addq %r14,%r12 - movq %rax,%r14 - rorq $23,%r13 - movq %r9,%r15 - movq %r12,64(%rsp) - - rorq $5,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - rorq $4,%r13 - addq %r11,%r12 - xorq %rax,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r8,%r15 - movq %rbx,%r11 - - rorq $6,%r14 - xorq %r8,%r13 - xorq %r10,%r15 - - xorq %rcx,%r11 - xorq %rax,%r14 - addq %r15,%r12 - movq %rbx,%r15 - - rorq $14,%r13 - andq %rax,%r11 - andq %rcx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r11 - - addq %r12,%rdx - addq %r12,%r11 - leaq 1(%rdi),%rdi - addq %r14,%r11 - - movq 80(%rsp),%r13 - movq 56(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 16(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 72(%rsp),%r12 - movq %rdx,%r13 - addq %r14,%r12 - movq %r11,%r14 - rorq $23,%r13 - movq %r8,%r15 - movq %r12,72(%rsp) - - rorq $5,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - rorq $4,%r13 - addq %r10,%r12 - xorq %r11,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rdx,%r15 - movq %rax,%r10 - - rorq $6,%r14 - xorq %rdx,%r13 - xorq %r9,%r15 - - xorq %rbx,%r10 - xorq %r11,%r14 - addq %r15,%r12 - movq %rax,%r15 - - rorq $14,%r13 - andq %r11,%r10 - andq %rbx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r10 - - addq %r12,%rcx - addq %r12,%r10 - leaq 1(%rdi),%rdi - addq %r14,%r10 - - movq 88(%rsp),%r13 - movq 64(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 24(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 80(%rsp),%r12 - movq %rcx,%r13 - addq %r14,%r12 - movq %r10,%r14 - rorq $23,%r13 - movq %rdx,%r15 - movq %r12,80(%rsp) - - rorq $5,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - rorq $4,%r13 - addq %r9,%r12 - xorq %r10,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rcx,%r15 - movq %r11,%r9 - - rorq $6,%r14 - xorq %rcx,%r13 - xorq %r8,%r15 - - xorq %rax,%r9 - xorq %r10,%r14 - addq %r15,%r12 - movq %r11,%r15 - - rorq $14,%r13 - andq %r10,%r9 - andq %rax,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r9 - - addq %r12,%rbx - addq %r12,%r9 - leaq 1(%rdi),%rdi - addq %r14,%r9 - - movq 96(%rsp),%r13 - movq 72(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 32(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 88(%rsp),%r12 - movq %rbx,%r13 - addq %r14,%r12 - movq %r9,%r14 - rorq $23,%r13 - movq %rcx,%r15 - movq %r12,88(%rsp) - - rorq $5,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - rorq $4,%r13 - addq %r8,%r12 - xorq %r9,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rbx,%r15 - movq %r10,%r8 - - rorq $6,%r14 - xorq %rbx,%r13 - xorq %rdx,%r15 - - xorq %r11,%r8 - xorq %r9,%r14 - addq %r15,%r12 - movq %r10,%r15 - - rorq $14,%r13 - andq %r9,%r8 - andq %r11,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%r8 - - addq %r12,%rax - addq %r12,%r8 - leaq 1(%rdi),%rdi - addq %r14,%r8 - - movq 104(%rsp),%r13 - movq 80(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 40(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 96(%rsp),%r12 - movq %rax,%r13 - addq %r14,%r12 - movq %r8,%r14 - rorq $23,%r13 - movq %rbx,%r15 - movq %r12,96(%rsp) - - rorq $5,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - rorq $4,%r13 - addq %rdx,%r12 - xorq %r8,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %rax,%r15 - movq %r9,%rdx - - rorq $6,%r14 - xorq %rax,%r13 - xorq %rcx,%r15 - - xorq %r10,%rdx - xorq %r8,%r14 - addq %r15,%r12 - movq %r9,%r15 - - rorq $14,%r13 - andq %r8,%rdx - andq %r10,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rdx - - addq %r12,%r11 - addq %r12,%rdx - leaq 1(%rdi),%rdi - addq %r14,%rdx - - movq 112(%rsp),%r13 - movq 88(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 48(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 104(%rsp),%r12 - movq %r11,%r13 - addq %r14,%r12 - movq %rdx,%r14 - rorq $23,%r13 - movq %rax,%r15 - movq %r12,104(%rsp) - - rorq $5,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - rorq $4,%r13 - addq %rcx,%r12 - xorq %rdx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r11,%r15 - movq %r8,%rcx - - rorq $6,%r14 - xorq %r11,%r13 - xorq %rbx,%r15 - - xorq %r9,%rcx - xorq %rdx,%r14 - addq %r15,%r12 - movq %r8,%r15 - - rorq $14,%r13 - andq %rdx,%rcx - andq %r9,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rcx - - addq %r12,%r10 - addq %r12,%rcx - leaq 1(%rdi),%rdi - addq %r14,%rcx - - movq 120(%rsp),%r13 - movq 96(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 56(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 112(%rsp),%r12 - movq %r10,%r13 - addq %r14,%r12 - movq %rcx,%r14 - rorq $23,%r13 - movq %r11,%r15 - movq %r12,112(%rsp) - - rorq $5,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - rorq $4,%r13 - addq %rbx,%r12 - xorq %rcx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r10,%r15 - movq %rdx,%rbx - - rorq $6,%r14 - xorq %r10,%r13 - xorq %rax,%r15 - - xorq %r8,%rbx - xorq %rcx,%r14 - addq %r15,%r12 - movq %rdx,%r15 - - rorq $14,%r13 - andq %rcx,%rbx - andq %r8,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rbx - - addq %r12,%r9 - addq %r12,%rbx - leaq 1(%rdi),%rdi - addq %r14,%rbx - - movq 0(%rsp),%r13 - movq 104(%rsp),%r14 - movq %r13,%r12 - movq %r14,%r15 - - rorq $7,%r12 - xorq %r13,%r12 - shrq $7,%r13 - - rorq $1,%r12 - xorq %r12,%r13 - movq 64(%rsp),%r12 - - rorq $42,%r15 - xorq %r14,%r15 - shrq $6,%r14 - - rorq $19,%r15 - addq %r13,%r12 - xorq %r15,%r14 - - addq 120(%rsp),%r12 - movq %r9,%r13 - addq %r14,%r12 - movq %rbx,%r14 - rorq $23,%r13 - movq %r10,%r15 - movq %r12,120(%rsp) - - rorq $5,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - rorq $4,%r13 - addq %rax,%r12 - xorq %rbx,%r14 - - addq (%rbp,%rdi,8),%r12 - andq %r9,%r15 - movq %rcx,%rax - - rorq $6,%r14 - xorq %r9,%r13 - xorq %r11,%r15 - - xorq %rdx,%rax - xorq %rbx,%r14 - addq %r15,%r12 - movq %rcx,%r15 - - rorq $14,%r13 - andq %rbx,%rax - andq %rdx,%r15 - - rorq $28,%r14 - addq %r13,%r12 - addq %r15,%rax - - addq %r12,%r8 - addq %r12,%rax - leaq 1(%rdi),%rdi - addq %r14,%rax - - cmpq $80,%rdi - jb .Lrounds_16_xx - - movq 128+0(%rsp),%rdi - leaq 128(%rsi),%rsi - - addq 0(%rdi),%rax - addq 8(%rdi),%rbx - addq 16(%rdi),%rcx - addq 24(%rdi),%rdx - addq 32(%rdi),%r8 - addq 40(%rdi),%r9 - addq 48(%rdi),%r10 - addq 56(%rdi),%r11 - - cmpq 128+16(%rsp),%rsi - - movq %rax,0(%rdi) - movq %rbx,8(%rdi) - movq %rcx,16(%rdi) - movq %rdx,24(%rdi) - movq %r8,32(%rdi) - movq %r9,40(%rdi) - movq %r10,48(%rdi) - movq %r11,56(%rdi) - jb .Lloop - - movq 128+24(%rsp),%rsi - movq (%rsi),%r15 - movq 8(%rsi),%r14 - movq 16(%rsi),%r13 - movq 24(%rsi),%r12 - movq 32(%rsi),%rbp - movq 40(%rsi),%rbx - leaq 48(%rsi),%rsp -.Lepilogue: - .byte 0xf3,0xc3 -.size sha512_block_data_order,.-sha512_block_data_order -.align 64 -.type K512,@object -K512: -.quad 0x428a2f98d728ae22,0x7137449123ef65cd -.quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc -.quad 0x3956c25bf348b538,0x59f111f1b605d019 -.quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118 -.quad 0xd807aa98a3030242,0x12835b0145706fbe -.quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2 -.quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1 -.quad 0x9bdc06a725c71235,0xc19bf174cf692694 -.quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3 -.quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65 -.quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483 -.quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5 -.quad 0x983e5152ee66dfab,0xa831c66d2db43210 -.quad 0xb00327c898fb213f,0xbf597fc7beef0ee4 -.quad 0xc6e00bf33da88fc2,0xd5a79147930aa725 -.quad 0x06ca6351e003826f,0x142929670a0e6e70 -.quad 0x27b70a8546d22ffc,0x2e1b21385c26c926 -.quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df -.quad 0x650a73548baf63de,0x766a0abb3c77b2a8 -.quad 0x81c2c92e47edaee6,0x92722c851482353b -.quad 0xa2bfe8a14cf10364,0xa81a664bbc423001 -.quad 0xc24b8b70d0f89791,0xc76c51a30654be30 -.quad 0xd192e819d6ef5218,0xd69906245565a910 -.quad 0xf40e35855771202a,0x106aa07032bbd1b8 -.quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53 -.quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8 -.quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb -.quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3 -.quad 0x748f82ee5defb2fc,0x78a5636f43172f60 -.quad 0x84c87814a1f0ab72,0x8cc702081a6439ec -.quad 0x90befffa23631e28,0xa4506cebde82bde9 -.quad 0xbef9a3f7b2c67915,0xc67178f2e372532b -.quad 0xca273eceea26619c,0xd186b8c721c0c207 -.quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178 -.quad 0x06f067aa72176fba,0x0a637dc5a2c898a6 -.quad 0x113f9804bef90dae,0x1b710b35131c471b -.quad 0x28db77f523047d84,0x32caab7b40c72493 -.quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c -.quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a -.quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 diff --git a/app/openssl/crypto/sha/asm/sha512-x86_64.pl b/app/openssl/crypto/sha/asm/sha512-x86_64.pl deleted file mode 100755 index 8d516785..00000000 --- a/app/openssl/crypto/sha/asm/sha512-x86_64.pl +++ /dev/null @@ -1,451 +0,0 @@ -#!/usr/bin/env perl -# -# ==================================================================== -# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL -# project. Rights for redistribution and usage in source and binary -# forms are granted according to the OpenSSL license. -# ==================================================================== -# -# sha256/512_block procedure for x86_64. -# -# 40% improvement over compiler-generated code on Opteron. On EM64T -# sha256 was observed to run >80% faster and sha512 - >40%. No magical -# tricks, just straight implementation... I really wonder why gcc -# [being armed with inline assembler] fails to generate as fast code. -# The only thing which is cool about this module is that it's very -# same instruction sequence used for both SHA-256 and SHA-512. In -# former case the instructions operate on 32-bit operands, while in -# latter - on 64-bit ones. All I had to do is to get one flavor right, -# the other one passed the test right away:-) -# -# sha256_block runs in ~1005 cycles on Opteron, which gives you -# asymptotic performance of 64*1000/1005=63.7MBps times CPU clock -# frequency in GHz. sha512_block runs in ~1275 cycles, which results -# in 128*1000/1275=100MBps per GHz. Is there room for improvement? -# Well, if you compare it to IA-64 implementation, which maintains -# X[16] in register bank[!], tends to 4 instructions per CPU clock -# cycle and runs in 1003 cycles, 1275 is very good result for 3-way -# issue Opteron pipeline and X[16] maintained in memory. So that *if* -# there is a way to improve it, *then* the only way would be to try to -# offload X[16] updates to SSE unit, but that would require "deeper" -# loop unroll, which in turn would naturally cause size blow-up, not -# to mention increased complexity! And once again, only *if* it's -# actually possible to noticeably improve overall ILP, instruction -# level parallelism, on a given CPU implementation in this case. -# -# Special note on Intel EM64T. While Opteron CPU exhibits perfect -# perfromance ratio of 1.5 between 64- and 32-bit flavors [see above], -# [currently available] EM64T CPUs apparently are far from it. On the -# contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit -# sha256_block:-( This is presumably because 64-bit shifts/rotates -# apparently are not atomic instructions, but implemented in microcode. - -$flavour = shift; -$output = shift; -if ($flavour =~ /\./) { $output = $flavour; undef $flavour; } - -$win64=0; $win64=1 if ($flavour =~ /[nm]asm|mingw64/ || $output =~ /\.asm$/); - -$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; -( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or -( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or -die "can't locate x86_64-xlate.pl"; - -open OUT,"| \"$^X\" $xlate $flavour $output"; -*STDOUT=*OUT; - -if ($output =~ /512/) { - $func="sha512_block_data_order"; - $TABLE="K512"; - $SZ=8; - @ROT=($A,$B,$C,$D,$E,$F,$G,$H)=("%rax","%rbx","%rcx","%rdx", - "%r8", "%r9", "%r10","%r11"); - ($T1,$a0,$a1,$a2)=("%r12","%r13","%r14","%r15"); - @Sigma0=(28,34,39); - @Sigma1=(14,18,41); - @sigma0=(1, 8, 7); - @sigma1=(19,61, 6); - $rounds=80; -} else { - $func="sha256_block_data_order"; - $TABLE="K256"; - $SZ=4; - @ROT=($A,$B,$C,$D,$E,$F,$G,$H)=("%eax","%ebx","%ecx","%edx", - "%r8d","%r9d","%r10d","%r11d"); - ($T1,$a0,$a1,$a2)=("%r12d","%r13d","%r14d","%r15d"); - @Sigma0=( 2,13,22); - @Sigma1=( 6,11,25); - @sigma0=( 7,18, 3); - @sigma1=(17,19,10); - $rounds=64; -} - -$ctx="%rdi"; # 1st arg -$round="%rdi"; # zaps $ctx -$inp="%rsi"; # 2nd arg -$Tbl="%rbp"; - -$_ctx="16*$SZ+0*8(%rsp)"; -$_inp="16*$SZ+1*8(%rsp)"; -$_end="16*$SZ+2*8(%rsp)"; -$_rsp="16*$SZ+3*8(%rsp)"; -$framesz="16*$SZ+4*8"; - - -sub ROUND_00_15() -{ my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___; - ror \$`$Sigma1[2]-$Sigma1[1]`,$a0 - mov $f,$a2 - mov $T1,`$SZ*($i&0xf)`(%rsp) - - ror \$`$Sigma0[2]-$Sigma0[1]`,$a1 - xor $e,$a0 - xor $g,$a2 # f^g - - ror \$`$Sigma1[1]-$Sigma1[0]`,$a0 - add $h,$T1 # T1+=h - xor $a,$a1 - - add ($Tbl,$round,$SZ),$T1 # T1+=K[round] - and $e,$a2 # (f^g)&e - mov $b,$h - - ror \$`$Sigma0[1]-$Sigma0[0]`,$a1 - xor $e,$a0 - xor $g,$a2 # Ch(e,f,g)=((f^g)&e)^g - - xor $c,$h # b^c - xor $a,$a1 - add $a2,$T1 # T1+=Ch(e,f,g) - mov $b,$a2 - - ror \$$Sigma1[0],$a0 # Sigma1(e) - and $a,$h # h=(b^c)&a - and $c,$a2 # b&c - - ror \$$Sigma0[0],$a1 # Sigma0(a) - add $a0,$T1 # T1+=Sigma1(e) - add $a2,$h # h+=b&c (completes +=Maj(a,b,c) - - add $T1,$d # d+=T1 - add $T1,$h # h+=T1 - lea 1($round),$round # round++ - add $a1,$h # h+=Sigma0(a) - -___ -} - -sub ROUND_16_XX() -{ my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___; - mov `$SZ*(($i+1)&0xf)`(%rsp),$a0 - mov `$SZ*(($i+14)&0xf)`(%rsp),$a1 - mov $a0,$T1 - mov $a1,$a2 - - ror \$`$sigma0[1]-$sigma0[0]`,$T1 - xor $a0,$T1 - shr \$$sigma0[2],$a0 - - ror \$$sigma0[0],$T1 - xor $T1,$a0 # sigma0(X[(i+1)&0xf]) - mov `$SZ*(($i+9)&0xf)`(%rsp),$T1 - - ror \$`$sigma1[1]-$sigma1[0]`,$a2 - xor $a1,$a2 - shr \$$sigma1[2],$a1 - - ror \$$sigma1[0],$a2 - add $a0,$T1 - xor $a2,$a1 # sigma1(X[(i+14)&0xf]) - - add `$SZ*($i&0xf)`(%rsp),$T1 - mov $e,$a0 - add $a1,$T1 - mov $a,$a1 -___ - &ROUND_00_15(@_); -} - -$code=<<___; -.text - -.globl $func -.type $func,\@function,4 -.align 16 -$func: - push %rbx - push %rbp - push %r12 - push %r13 - push %r14 - push %r15 - mov %rsp,%r11 # copy %rsp - shl \$4,%rdx # num*16 - sub \$$framesz,%rsp - lea ($inp,%rdx,$SZ),%rdx # inp+num*16*$SZ - and \$-64,%rsp # align stack frame - mov $ctx,$_ctx # save ctx, 1st arg - mov $inp,$_inp # save inp, 2nd arh - mov %rdx,$_end # save end pointer, "3rd" arg - mov %r11,$_rsp # save copy of %rsp -.Lprologue: - - lea $TABLE(%rip),$Tbl - - mov $SZ*0($ctx),$A - mov $SZ*1($ctx),$B - mov $SZ*2($ctx),$C - mov $SZ*3($ctx),$D - mov $SZ*4($ctx),$E - mov $SZ*5($ctx),$F - mov $SZ*6($ctx),$G - mov $SZ*7($ctx),$H - jmp .Lloop - -.align 16 -.Lloop: - xor $round,$round -___ - for($i=0;$i<16;$i++) { - $code.=" mov $SZ*$i($inp),$T1\n"; - $code.=" mov @ROT[4],$a0\n"; - $code.=" mov @ROT[0],$a1\n"; - $code.=" bswap $T1\n"; - &ROUND_00_15($i,@ROT); - unshift(@ROT,pop(@ROT)); - } -$code.=<<___; - jmp .Lrounds_16_xx -.align 16 -.Lrounds_16_xx: -___ - for(;$i<32;$i++) { - &ROUND_16_XX($i,@ROT); - unshift(@ROT,pop(@ROT)); - } - -$code.=<<___; - cmp \$$rounds,$round - jb .Lrounds_16_xx - - mov $_ctx,$ctx - lea 16*$SZ($inp),$inp - - add $SZ*0($ctx),$A - add $SZ*1($ctx),$B - add $SZ*2($ctx),$C - add $SZ*3($ctx),$D - add $SZ*4($ctx),$E - add $SZ*5($ctx),$F - add $SZ*6($ctx),$G - add $SZ*7($ctx),$H - - cmp $_end,$inp - - mov $A,$SZ*0($ctx) - mov $B,$SZ*1($ctx) - mov $C,$SZ*2($ctx) - mov $D,$SZ*3($ctx) - mov $E,$SZ*4($ctx) - mov $F,$SZ*5($ctx) - mov $G,$SZ*6($ctx) - mov $H,$SZ*7($ctx) - jb .Lloop - - mov $_rsp,%rsi - mov (%rsi),%r15 - mov 8(%rsi),%r14 - mov 16(%rsi),%r13 - mov 24(%rsi),%r12 - mov 32(%rsi),%rbp - mov 40(%rsi),%rbx - lea 48(%rsi),%rsp -.Lepilogue: - ret -.size $func,.-$func -___ - -if ($SZ==4) { -$code.=<<___; -.align 64 -.type $TABLE,\@object -$TABLE: - .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 - .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 - .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 - .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 - .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc - .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da - .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 - .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 - .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 - .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 - .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 - .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 - .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 - .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 - .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 - .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -___ -} else { -$code.=<<___; -.align 64 -.type $TABLE,\@object -$TABLE: - .quad 0x428a2f98d728ae22,0x7137449123ef65cd - .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc - .quad 0x3956c25bf348b538,0x59f111f1b605d019 - .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118 - .quad 0xd807aa98a3030242,0x12835b0145706fbe - .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2 - .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1 - .quad 0x9bdc06a725c71235,0xc19bf174cf692694 - .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3 - .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65 - .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483 - .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5 - .quad 0x983e5152ee66dfab,0xa831c66d2db43210 - .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4 - .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725 - .quad 0x06ca6351e003826f,0x142929670a0e6e70 - .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926 - .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df - .quad 0x650a73548baf63de,0x766a0abb3c77b2a8 - .quad 0x81c2c92e47edaee6,0x92722c851482353b - .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001 - .quad 0xc24b8b70d0f89791,0xc76c51a30654be30 - .quad 0xd192e819d6ef5218,0xd69906245565a910 - .quad 0xf40e35855771202a,0x106aa07032bbd1b8 - .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53 - .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8 - .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb - .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3 - .quad 0x748f82ee5defb2fc,0x78a5636f43172f60 - .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec - .quad 0x90befffa23631e28,0xa4506cebde82bde9 - .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b - .quad 0xca273eceea26619c,0xd186b8c721c0c207 - .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178 - .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6 - .quad 0x113f9804bef90dae,0x1b710b35131c471b - .quad 0x28db77f523047d84,0x32caab7b40c72493 - .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c - .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a - .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 -___ -} - -# EXCEPTION_DISPOSITION handler (EXCEPTION_RECORD *rec,ULONG64 frame, -# CONTEXT *context,DISPATCHER_CONTEXT *disp) -if ($win64) { -$rec="%rcx"; -$frame="%rdx"; -$context="%r8"; -$disp="%r9"; - -$code.=<<___; -.extern __imp_RtlVirtualUnwind -.type se_handler,\@abi-omnipotent -.align 16 -se_handler: - push %rsi - push %rdi - push %rbx - push %rbp - push %r12 - push %r13 - push %r14 - push %r15 - pushfq - sub \$64,%rsp - - mov 120($context),%rax # pull context->Rax - mov 248($context),%rbx # pull context->Rip - - lea .Lprologue(%rip),%r10 - cmp %r10,%rbx # context->Rip<.Lprologue - jb .Lin_prologue - - mov 152($context),%rax # pull context->Rsp - - lea .Lepilogue(%rip),%r10 - cmp %r10,%rbx # context->Rip>=.Lepilogue - jae .Lin_prologue - - mov 16*$SZ+3*8(%rax),%rax # pull $_rsp - lea 48(%rax),%rax - - mov -8(%rax),%rbx - mov -16(%rax),%rbp - mov -24(%rax),%r12 - mov -32(%rax),%r13 - mov -40(%rax),%r14 - mov -48(%rax),%r15 - mov %rbx,144($context) # restore context->Rbx - mov %rbp,160($context) # restore context->Rbp - mov %r12,216($context) # restore context->R12 - mov %r13,224($context) # restore context->R13 - mov %r14,232($context) # restore context->R14 - mov %r15,240($context) # restore context->R15 - -.Lin_prologue: - mov 8(%rax),%rdi - mov 16(%rax),%rsi - mov %rax,152($context) # restore context->Rsp - mov %rsi,168($context) # restore context->Rsi - mov %rdi,176($context) # restore context->Rdi - - mov 40($disp),%rdi # disp->ContextRecord - mov $context,%rsi # context - mov \$154,%ecx # sizeof(CONTEXT) - .long 0xa548f3fc # cld; rep movsq - - mov $disp,%rsi - xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER - mov 8(%rsi),%rdx # arg2, disp->ImageBase - mov 0(%rsi),%r8 # arg3, disp->ControlPc - mov 16(%rsi),%r9 # arg4, disp->FunctionEntry - mov 40(%rsi),%r10 # disp->ContextRecord - lea 56(%rsi),%r11 # &disp->HandlerData - lea 24(%rsi),%r12 # &disp->EstablisherFrame - mov %r10,32(%rsp) # arg5 - mov %r11,40(%rsp) # arg6 - mov %r12,48(%rsp) # arg7 - mov %rcx,56(%rsp) # arg8, (NULL) - call *__imp_RtlVirtualUnwind(%rip) - - mov \$1,%eax # ExceptionContinueSearch - add \$64,%rsp - popfq - pop %r15 - pop %r14 - pop %r13 - pop %r12 - pop %rbp - pop %rbx - pop %rdi - pop %rsi - ret -.size se_handler,.-se_handler - -.section .pdata -.align 4 - .rva .LSEH_begin_$func - .rva .LSEH_end_$func - .rva .LSEH_info_$func - -.section .xdata -.align 8 -.LSEH_info_$func: - .byte 9,0,0,0 - .rva se_handler -___ -} - -$code =~ s/\`([^\`]*)\`/eval $1/gem; -print $code; -close STDOUT; |