From 394451dbae3e71282611058e00b5fd16c865f147 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Parm=C3=A9nides=20GV?= Date: Fri, 26 Sep 2014 09:46:26 +0200 Subject: Revert "Updated native subprojects from ics-openvpn." This reverts commit d0e7ba3029b2fd42582413aa95773fe7dbdede90. I'll postpone this work for the next cycle, it's not trivial because it doesn't link properly. --- app/openssl/crypto/bn/asm/armv4-mont.pl | 483 +------------------------------- 1 file changed, 6 insertions(+), 477 deletions(-) (limited to 'app/openssl/crypto/bn/asm/armv4-mont.pl') diff --git a/app/openssl/crypto/bn/asm/armv4-mont.pl b/app/openssl/crypto/bn/asm/armv4-mont.pl index 72bad8e3..f78a8b5f 100644 --- a/app/openssl/crypto/bn/asm/armv4-mont.pl +++ b/app/openssl/crypto/bn/asm/armv4-mont.pl @@ -1,7 +1,7 @@ #!/usr/bin/env perl # ==================================================================== -# Written by Andy Polyakov for the OpenSSL +# Written by Andy Polyakov 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/. @@ -23,21 +23,6 @@ # than 1/2KB. Windows CE port would be trivial, as it's exclusively # about decorations, ABI and instruction syntax are identical. -# November 2013 -# -# Add NEON code path, which handles lengths divisible by 8. RSA/DSA -# performance improvement on Cortex-A8 is ~45-100% depending on key -# length, more for longer keys. On Cortex-A15 the span is ~10-105%. -# On Snapdragon S4 improvement was measured to vary from ~70% to -# incredible ~380%, yes, 4.8x faster, for RSA4096 sign. But this is -# rather because original integer-only code seems to perform -# suboptimally on S4. Situation on Cortex-A9 is unfortunately -# different. It's being looked into, but the trouble is that -# performance for vectors longer than 256 bits is actually couple -# of percent worse than for integer-only code. The code is chosen -# for execution on all NEON-capable processors, because gain on -# others outweighs the marginal loss on Cortex-A9. - while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} open STDOUT,">$output"; @@ -67,40 +52,16 @@ $_n0="$num,#14*4"; $_num="$num,#15*4"; $_bpend=$_num; $code=<<___; -#include "arm_arch.h" - .text -.code 32 - -#if __ARM_ARCH__>=7 -.align 5 -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-bn_mul_mont -#endif .global bn_mul_mont .type bn_mul_mont,%function -.align 5 +.align 2 bn_mul_mont: - ldr ip,[sp,#4] @ load num stmdb sp!,{r0,r2} @ sp points at argument block -#if __ARM_ARCH__>=7 - tst ip,#7 - bne .Lialu - adr r0,bn_mul_mont - ldr r2,.LOPENSSL_armcap - ldr r0,[r0,r2] - tst r0,#1 @ NEON available? - ldmia sp, {r0,r2} - beq .Lialu - add sp,sp,#8 - b bn_mul8x_mont_neon -.align 4 -.Lialu: -#endif - cmp ip,#2 - mov $num,ip @ load num + ldr $num,[sp,#3*4] @ load num + cmp $num,#2 movlt r0,#0 addlt sp,sp,#2*4 blt .Labrt @@ -230,446 +191,14 @@ bn_mul_mont: ldmia sp!,{r4-r12,lr} @ restore registers add sp,sp,#2*4 @ skip over {r0,r2} mov r0,#1 -.Labrt: -#if __ARM_ARCH__>=5 - ret @ bx lr -#else - tst lr,#1 +.Labrt: tst lr,#1 moveq pc,lr @ be binary compatible with V4, yet bx lr @ interoperable with Thumb ISA:-) -#endif .size bn_mul_mont,.-bn_mul_mont -___ -{ -sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; } -sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; } - -my ($A0,$A1,$A2,$A3)=map("d$_",(0..3)); -my ($N0,$N1,$N2,$N3)=map("d$_",(4..7)); -my ($Z,$Temp)=("q4","q5"); -my ($A0xB,$A1xB,$A2xB,$A3xB,$A4xB,$A5xB,$A6xB,$A7xB)=map("q$_",(6..13)); -my ($Bi,$Ni,$M0)=map("d$_",(28..31)); -my $zero=&Dlo($Z); -my $temp=&Dlo($Temp); - -my ($rptr,$aptr,$bptr,$nptr,$n0,$num)=map("r$_",(0..5)); -my ($tinptr,$toutptr,$inner,$outer)=map("r$_",(6..9)); - -$code.=<<___; -#if __ARM_ARCH__>=7 -.fpu neon - -.type bn_mul8x_mont_neon,%function -.align 5 -bn_mul8x_mont_neon: - mov ip,sp - stmdb sp!,{r4-r11} - vstmdb sp!,{d8-d15} @ ABI specification says so - ldmia ip,{r4-r5} @ load rest of parameter block - - sub $toutptr,sp,#16 - vld1.32 {${Bi}[0]}, [$bptr,:32]! - sub $toutptr,$toutptr,$num,lsl#4 - vld1.32 {$A0-$A3}, [$aptr]! @ can't specify :32 :-( - and $toutptr,$toutptr,#-64 - vld1.32 {${M0}[0]}, [$n0,:32] - mov sp,$toutptr @ alloca - veor $zero,$zero,$zero - subs $inner,$num,#8 - vzip.16 $Bi,$zero - - vmull.u32 $A0xB,$Bi,${A0}[0] - vmull.u32 $A1xB,$Bi,${A0}[1] - vmull.u32 $A2xB,$Bi,${A1}[0] - vshl.i64 $temp,`&Dhi("$A0xB")`,#16 - vmull.u32 $A3xB,$Bi,${A1}[1] - - vadd.u64 $temp,$temp,`&Dlo("$A0xB")` - veor $zero,$zero,$zero - vmul.u32 $Ni,$temp,$M0 - - vmull.u32 $A4xB,$Bi,${A2}[0] - vld1.32 {$N0-$N3}, [$nptr]! - vmull.u32 $A5xB,$Bi,${A2}[1] - vmull.u32 $A6xB,$Bi,${A3}[0] - vzip.16 $Ni,$zero - vmull.u32 $A7xB,$Bi,${A3}[1] - - bne .LNEON_1st - - @ special case for num=8, everything is in register bank... - - vmlal.u32 $A0xB,$Ni,${N0}[0] - sub $outer,$num,#1 - vmlal.u32 $A1xB,$Ni,${N0}[1] - vmlal.u32 $A2xB,$Ni,${N1}[0] - vmlal.u32 $A3xB,$Ni,${N1}[1] - - vmlal.u32 $A4xB,$Ni,${N2}[0] - vmov $Temp,$A0xB - vmlal.u32 $A5xB,$Ni,${N2}[1] - vmov $A0xB,$A1xB - vmlal.u32 $A6xB,$Ni,${N3}[0] - vmov $A1xB,$A2xB - vmlal.u32 $A7xB,$Ni,${N3}[1] - vmov $A2xB,$A3xB - vmov $A3xB,$A4xB - vshr.u64 $temp,$temp,#16 - vmov $A4xB,$A5xB - vmov $A5xB,$A6xB - vadd.u64 $temp,$temp,`&Dhi("$Temp")` - vmov $A6xB,$A7xB - veor $A7xB,$A7xB - vshr.u64 $temp,$temp,#16 - - b .LNEON_outer8 - -.align 4 -.LNEON_outer8: - vld1.32 {${Bi}[0]}, [$bptr,:32]! - veor $zero,$zero,$zero - vzip.16 $Bi,$zero - vadd.u64 `&Dlo("$A0xB")`,`&Dlo("$A0xB")`,$temp - - vmlal.u32 $A0xB,$Bi,${A0}[0] - vmlal.u32 $A1xB,$Bi,${A0}[1] - vmlal.u32 $A2xB,$Bi,${A1}[0] - vshl.i64 $temp,`&Dhi("$A0xB")`,#16 - vmlal.u32 $A3xB,$Bi,${A1}[1] - - vadd.u64 $temp,$temp,`&Dlo("$A0xB")` - veor $zero,$zero,$zero - subs $outer,$outer,#1 - vmul.u32 $Ni,$temp,$M0 - - vmlal.u32 $A4xB,$Bi,${A2}[0] - vmlal.u32 $A5xB,$Bi,${A2}[1] - vmlal.u32 $A6xB,$Bi,${A3}[0] - vzip.16 $Ni,$zero - vmlal.u32 $A7xB,$Bi,${A3}[1] - - vmlal.u32 $A0xB,$Ni,${N0}[0] - vmlal.u32 $A1xB,$Ni,${N0}[1] - vmlal.u32 $A2xB,$Ni,${N1}[0] - vmlal.u32 $A3xB,$Ni,${N1}[1] - - vmlal.u32 $A4xB,$Ni,${N2}[0] - vmov $Temp,$A0xB - vmlal.u32 $A5xB,$Ni,${N2}[1] - vmov $A0xB,$A1xB - vmlal.u32 $A6xB,$Ni,${N3}[0] - vmov $A1xB,$A2xB - vmlal.u32 $A7xB,$Ni,${N3}[1] - vmov $A2xB,$A3xB - vmov $A3xB,$A4xB - vshr.u64 $temp,$temp,#16 - vmov $A4xB,$A5xB - vmov $A5xB,$A6xB - vadd.u64 $temp,$temp,`&Dhi("$Temp")` - vmov $A6xB,$A7xB - veor $A7xB,$A7xB - vshr.u64 $temp,$temp,#16 - - bne .LNEON_outer8 - - vadd.u64 `&Dlo("$A0xB")`,`&Dlo("$A0xB")`,$temp - mov $toutptr,sp - vshr.u64 $temp,`&Dlo("$A0xB")`,#16 - mov $inner,$num - vadd.u64 `&Dhi("$A0xB")`,`&Dhi("$A0xB")`,$temp - add $tinptr,sp,#16 - vshr.u64 $temp,`&Dhi("$A0xB")`,#16 - vzip.16 `&Dlo("$A0xB")`,`&Dhi("$A0xB")` - - b .LNEON_tail2 - -.align 4 -.LNEON_1st: - vmlal.u32 $A0xB,$Ni,${N0}[0] - vld1.32 {$A0-$A3}, [$aptr]! - vmlal.u32 $A1xB,$Ni,${N0}[1] - subs $inner,$inner,#8 - vmlal.u32 $A2xB,$Ni,${N1}[0] - vmlal.u32 $A3xB,$Ni,${N1}[1] - - vmlal.u32 $A4xB,$Ni,${N2}[0] - vld1.32 {$N0-$N1}, [$nptr]! - vmlal.u32 $A5xB,$Ni,${N2}[1] - vst1.64 {$A0xB-$A1xB}, [$toutptr,:256]! - vmlal.u32 $A6xB,$Ni,${N3}[0] - vmlal.u32 $A7xB,$Ni,${N3}[1] - vst1.64 {$A2xB-$A3xB}, [$toutptr,:256]! - - vmull.u32 $A0xB,$Bi,${A0}[0] - vld1.32 {$N2-$N3}, [$nptr]! - vmull.u32 $A1xB,$Bi,${A0}[1] - vst1.64 {$A4xB-$A5xB}, [$toutptr,:256]! - vmull.u32 $A2xB,$Bi,${A1}[0] - vmull.u32 $A3xB,$Bi,${A1}[1] - vst1.64 {$A6xB-$A7xB}, [$toutptr,:256]! - - vmull.u32 $A4xB,$Bi,${A2}[0] - vmull.u32 $A5xB,$Bi,${A2}[1] - vmull.u32 $A6xB,$Bi,${A3}[0] - vmull.u32 $A7xB,$Bi,${A3}[1] - - bne .LNEON_1st - - vmlal.u32 $A0xB,$Ni,${N0}[0] - add $tinptr,sp,#16 - vmlal.u32 $A1xB,$Ni,${N0}[1] - sub $aptr,$aptr,$num,lsl#2 @ rewind $aptr - vmlal.u32 $A2xB,$Ni,${N1}[0] - vld1.64 {$Temp}, [sp,:128] - vmlal.u32 $A3xB,$Ni,${N1}[1] - sub $outer,$num,#1 - - vmlal.u32 $A4xB,$Ni,${N2}[0] - vst1.64 {$A0xB-$A1xB}, [$toutptr,:256]! - vmlal.u32 $A5xB,$Ni,${N2}[1] - vshr.u64 $temp,$temp,#16 - vld1.64 {$A0xB}, [$tinptr, :128]! - vmlal.u32 $A6xB,$Ni,${N3}[0] - vst1.64 {$A2xB-$A3xB}, [$toutptr,:256]! - vmlal.u32 $A7xB,$Ni,${N3}[1] - - vst1.64 {$A4xB-$A5xB}, [$toutptr,:256]! - vadd.u64 $temp,$temp,`&Dhi("$Temp")` - veor $Z,$Z,$Z - vst1.64 {$A6xB-$A7xB}, [$toutptr,:256]! - vld1.64 {$A1xB-$A2xB}, [$tinptr, :256]! - vst1.64 {$Z}, [$toutptr,:128] - vshr.u64 $temp,$temp,#16 - - b .LNEON_outer - -.align 4 -.LNEON_outer: - vld1.32 {${Bi}[0]}, [$bptr,:32]! - sub $nptr,$nptr,$num,lsl#2 @ rewind $nptr - vld1.32 {$A0-$A3}, [$aptr]! - veor $zero,$zero,$zero - mov $toutptr,sp - vzip.16 $Bi,$zero - sub $inner,$num,#8 - vadd.u64 `&Dlo("$A0xB")`,`&Dlo("$A0xB")`,$temp - - vmlal.u32 $A0xB,$Bi,${A0}[0] - vld1.64 {$A3xB-$A4xB},[$tinptr,:256]! - vmlal.u32 $A1xB,$Bi,${A0}[1] - vmlal.u32 $A2xB,$Bi,${A1}[0] - vld1.64 {$A5xB-$A6xB},[$tinptr,:256]! - vmlal.u32 $A3xB,$Bi,${A1}[1] - - vshl.i64 $temp,`&Dhi("$A0xB")`,#16 - veor $zero,$zero,$zero - vadd.u64 $temp,$temp,`&Dlo("$A0xB")` - vld1.64 {$A7xB},[$tinptr,:128]! - vmul.u32 $Ni,$temp,$M0 - - vmlal.u32 $A4xB,$Bi,${A2}[0] - vld1.32 {$N0-$N3}, [$nptr]! - vmlal.u32 $A5xB,$Bi,${A2}[1] - vmlal.u32 $A6xB,$Bi,${A3}[0] - vzip.16 $Ni,$zero - vmlal.u32 $A7xB,$Bi,${A3}[1] - -.LNEON_inner: - vmlal.u32 $A0xB,$Ni,${N0}[0] - vld1.32 {$A0-$A3}, [$aptr]! - vmlal.u32 $A1xB,$Ni,${N0}[1] - subs $inner,$inner,#8 - vmlal.u32 $A2xB,$Ni,${N1}[0] - vmlal.u32 $A3xB,$Ni,${N1}[1] - vst1.64 {$A0xB-$A1xB}, [$toutptr,:256]! - - vmlal.u32 $A4xB,$Ni,${N2}[0] - vld1.64 {$A0xB}, [$tinptr, :128]! - vmlal.u32 $A5xB,$Ni,${N2}[1] - vst1.64 {$A2xB-$A3xB}, [$toutptr,:256]! - vmlal.u32 $A6xB,$Ni,${N3}[0] - vld1.64 {$A1xB-$A2xB}, [$tinptr, :256]! - vmlal.u32 $A7xB,$Ni,${N3}[1] - vst1.64 {$A4xB-$A5xB}, [$toutptr,:256]! - - vmlal.u32 $A0xB,$Bi,${A0}[0] - vld1.64 {$A3xB-$A4xB}, [$tinptr, :256]! - vmlal.u32 $A1xB,$Bi,${A0}[1] - vst1.64 {$A6xB-$A7xB}, [$toutptr,:256]! - vmlal.u32 $A2xB,$Bi,${A1}[0] - vld1.64 {$A5xB-$A6xB}, [$tinptr, :256]! - vmlal.u32 $A3xB,$Bi,${A1}[1] - vld1.32 {$N0-$N3}, [$nptr]! - - vmlal.u32 $A4xB,$Bi,${A2}[0] - vld1.64 {$A7xB}, [$tinptr, :128]! - vmlal.u32 $A5xB,$Bi,${A2}[1] - vmlal.u32 $A6xB,$Bi,${A3}[0] - vmlal.u32 $A7xB,$Bi,${A3}[1] - - bne .LNEON_inner - - vmlal.u32 $A0xB,$Ni,${N0}[0] - add $tinptr,sp,#16 - vmlal.u32 $A1xB,$Ni,${N0}[1] - sub $aptr,$aptr,$num,lsl#2 @ rewind $aptr - vmlal.u32 $A2xB,$Ni,${N1}[0] - vld1.64 {$Temp}, [sp,:128] - vmlal.u32 $A3xB,$Ni,${N1}[1] - subs $outer,$outer,#1 - - vmlal.u32 $A4xB,$Ni,${N2}[0] - vst1.64 {$A0xB-$A1xB}, [$toutptr,:256]! - vmlal.u32 $A5xB,$Ni,${N2}[1] - vld1.64 {$A0xB}, [$tinptr, :128]! - vshr.u64 $temp,$temp,#16 - vst1.64 {$A2xB-$A3xB}, [$toutptr,:256]! - vmlal.u32 $A6xB,$Ni,${N3}[0] - vld1.64 {$A1xB-$A2xB}, [$tinptr, :256]! - vmlal.u32 $A7xB,$Ni,${N3}[1] - - vst1.64 {$A4xB-$A5xB}, [$toutptr,:256]! - vadd.u64 $temp,$temp,`&Dhi("$Temp")` - vst1.64 {$A6xB-$A7xB}, [$toutptr,:256]! - vshr.u64 $temp,$temp,#16 - - bne .LNEON_outer - - mov $toutptr,sp - mov $inner,$num - -.LNEON_tail: - vadd.u64 `&Dlo("$A0xB")`,`&Dlo("$A0xB")`,$temp - vld1.64 {$A3xB-$A4xB}, [$tinptr, :256]! - vshr.u64 $temp,`&Dlo("$A0xB")`,#16 - vadd.u64 `&Dhi("$A0xB")`,`&Dhi("$A0xB")`,$temp - vld1.64 {$A5xB-$A6xB}, [$tinptr, :256]! - vshr.u64 $temp,`&Dhi("$A0xB")`,#16 - vld1.64 {$A7xB}, [$tinptr, :128]! - vzip.16 `&Dlo("$A0xB")`,`&Dhi("$A0xB")` - -.LNEON_tail2: - vadd.u64 `&Dlo("$A1xB")`,`&Dlo("$A1xB")`,$temp - vst1.32 {`&Dlo("$A0xB")`[0]}, [$toutptr, :32]! - vshr.u64 $temp,`&Dlo("$A1xB")`,#16 - vadd.u64 `&Dhi("$A1xB")`,`&Dhi("$A1xB")`,$temp - vshr.u64 $temp,`&Dhi("$A1xB")`,#16 - vzip.16 `&Dlo("$A1xB")`,`&Dhi("$A1xB")` - - vadd.u64 `&Dlo("$A2xB")`,`&Dlo("$A2xB")`,$temp - vst1.32 {`&Dlo("$A1xB")`[0]}, [$toutptr, :32]! - vshr.u64 $temp,`&Dlo("$A2xB")`,#16 - vadd.u64 `&Dhi("$A2xB")`,`&Dhi("$A2xB")`,$temp - vshr.u64 $temp,`&Dhi("$A2xB")`,#16 - vzip.16 `&Dlo("$A2xB")`,`&Dhi("$A2xB")` - - vadd.u64 `&Dlo("$A3xB")`,`&Dlo("$A3xB")`,$temp - vst1.32 {`&Dlo("$A2xB")`[0]}, [$toutptr, :32]! - vshr.u64 $temp,`&Dlo("$A3xB")`,#16 - vadd.u64 `&Dhi("$A3xB")`,`&Dhi("$A3xB")`,$temp - vshr.u64 $temp,`&Dhi("$A3xB")`,#16 - vzip.16 `&Dlo("$A3xB")`,`&Dhi("$A3xB")` - - vadd.u64 `&Dlo("$A4xB")`,`&Dlo("$A4xB")`,$temp - vst1.32 {`&Dlo("$A3xB")`[0]}, [$toutptr, :32]! - vshr.u64 $temp,`&Dlo("$A4xB")`,#16 - vadd.u64 `&Dhi("$A4xB")`,`&Dhi("$A4xB")`,$temp - vshr.u64 $temp,`&Dhi("$A4xB")`,#16 - vzip.16 `&Dlo("$A4xB")`,`&Dhi("$A4xB")` - - vadd.u64 `&Dlo("$A5xB")`,`&Dlo("$A5xB")`,$temp - vst1.32 {`&Dlo("$A4xB")`[0]}, [$toutptr, :32]! - vshr.u64 $temp,`&Dlo("$A5xB")`,#16 - vadd.u64 `&Dhi("$A5xB")`,`&Dhi("$A5xB")`,$temp - vshr.u64 $temp,`&Dhi("$A5xB")`,#16 - vzip.16 `&Dlo("$A5xB")`,`&Dhi("$A5xB")` - - vadd.u64 `&Dlo("$A6xB")`,`&Dlo("$A6xB")`,$temp - vst1.32 {`&Dlo("$A5xB")`[0]}, [$toutptr, :32]! - vshr.u64 $temp,`&Dlo("$A6xB")`,#16 - vadd.u64 `&Dhi("$A6xB")`,`&Dhi("$A6xB")`,$temp - vld1.64 {$A0xB}, [$tinptr, :128]! - vshr.u64 $temp,`&Dhi("$A6xB")`,#16 - vzip.16 `&Dlo("$A6xB")`,`&Dhi("$A6xB")` - - vadd.u64 `&Dlo("$A7xB")`,`&Dlo("$A7xB")`,$temp - vst1.32 {`&Dlo("$A6xB")`[0]}, [$toutptr, :32]! - vshr.u64 $temp,`&Dlo("$A7xB")`,#16 - vadd.u64 `&Dhi("$A7xB")`,`&Dhi("$A7xB")`,$temp - vld1.64 {$A1xB-$A2xB}, [$tinptr, :256]! - vshr.u64 $temp,`&Dhi("$A7xB")`,#16 - vzip.16 `&Dlo("$A7xB")`,`&Dhi("$A7xB")` - subs $inner,$inner,#8 - vst1.32 {`&Dlo("$A7xB")`[0]}, [$toutptr, :32]! - - bne .LNEON_tail - - vst1.32 {${temp}[0]}, [$toutptr, :32] @ top-most bit - sub $nptr,$nptr,$num,lsl#2 @ rewind $nptr - subs $aptr,sp,#0 @ clear carry flag - add $bptr,sp,$num,lsl#2 - -.LNEON_sub: - ldmia $aptr!, {r4-r7} - ldmia $nptr!, {r8-r11} - sbcs r8, r4,r8 - sbcs r9, r5,r9 - sbcs r10,r6,r10 - sbcs r11,r7,r11 - teq $aptr,$bptr @ preserves carry - stmia $rptr!, {r8-r11} - bne .LNEON_sub - - ldr r10, [$aptr] @ load top-most bit - veor q0,q0,q0 - sub r11,$bptr,sp @ this is num*4 - veor q1,q1,q1 - mov $aptr,sp - sub $rptr,$rptr,r11 @ rewind $rptr - mov $nptr,$bptr @ second 3/4th of frame - sbcs r10,r10,#0 @ result is carry flag - -.LNEON_copy_n_zap: - ldmia $aptr!, {r4-r7} - ldmia $rptr, {r8-r11} - movcc r8, r4 - vst1.64 {q0-q1}, [$nptr,:256]! @ wipe - movcc r9, r5 - movcc r10,r6 - vst1.64 {q0-q1}, [$nptr,:256]! @ wipe - movcc r11,r7 - ldmia $aptr, {r4-r7} - stmia $rptr!, {r8-r11} - sub $aptr,$aptr,#16 - ldmia $rptr, {r8-r11} - movcc r8, r4 - vst1.64 {q0-q1}, [$aptr,:256]! @ wipe - movcc r9, r5 - movcc r10,r6 - vst1.64 {q0-q1}, [$nptr,:256]! @ wipe - movcc r11,r7 - teq $aptr,$bptr @ preserves carry - stmia $rptr!, {r8-r11} - bne .LNEON_copy_n_zap - - sub sp,ip,#96 - vldmia sp!,{d8-d15} - ldmia sp!,{r4-r11} - ret @ bx lr -.size bn_mul8x_mont_neon,.-bn_mul8x_mont_neon -#endif -___ -} -$code.=<<___; -.asciz "Montgomery multiplication for ARMv4/NEON, CRYPTOGAMS by " +.asciz "Montgomery multiplication for ARMv4, CRYPTOGAMS by " .align 2 -#if __ARM_ARCH__>=7 -.comm OPENSSL_armcap_P,4,4 -#endif ___ -$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; -- cgit v1.2.3