Update OpenSSL to aosp/master

--HG--
extra : amend_source : 1d737bc919a18f072b1038b548a2cbad4cf76e22

11 files changed, 8530 insertions, 1363 deletions

diff --git a/main/openssl/crypto/sha/asm/sha1-armv4-large.pl b/main/openssl/crypto/sha/asm/sha1-armv4-large.pl
index 33da3e0e..50bd07b3 100644
--- a/main/openssl/crypto/sha/asm/sha1-armv4-large.pl
+++ b/main/openssl/crypto/sha/asm/sha1-armv4-large.pl
@@ -1,7 +1,7 @@
 #!/usr/bin/env perl
 
 # ====================================================================
-# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
+# 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/.
@@ -52,6 +52,20 @@
 # 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";
 
@@ -153,12 +167,22 @@ $code=<<___;
 #include "arm_arch.h"
 
 .text
+.code	32
 
 .global	sha1_block_data_order
 .type	sha1_block_data_order,%function
 
-.align	2
+.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}
@@ -233,16 +257,422 @@ $code.=<<___;
 	moveq	pc,lr			@ be binary compatible with V4, yet
 	bx	lr			@ interoperable with Thumb ISA:-)
 #endif
-.align	2
+.size	sha1_block_data_order,.-sha1_block_data_order
+
+.align	5
 .LK_00_19:	.word	0x5a827999
 .LK_20_39:	.word	0x6ed9eba1
 .LK_40_59:	.word	0x8f1bbcdc
 .LK_60_79:	.word	0xca62c1d6
-.size	sha1_block_data_order,.-sha1_block_data_order
-.asciz	"SHA1 block transform for ARMv4, CRYPTOGAMS by <appro\@openssl.org>"
-.align	2
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha1_block_data_order
+.asciz	"SHA1 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align	5
+___
+#####################################################################
+# NEON stuff
+#
+{{{
+my @V=($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 $_,$/;
+}
 
-$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm;	# make it possible to compile with -march=armv4
-print $code;
 close STDOUT; # enforce flush
diff --git a/main/openssl/crypto/sha/asm/sha1-armv4-large.s b/main/openssl/crypto/sha/asm/sha1-armv4-large.s
index 639ae78a..a1562883 100644
--- a/main/openssl/crypto/sha/asm/sha1-armv4-large.s
+++ b/main/openssl/crypto/sha/asm/sha1-armv4-large.s
@@ -1,12 +1,22 @@
 #include "arm_arch.h"
 
 .text
+.code	32
 
 .global	sha1_block_data_order
 .type	sha1_block_data_order,%function
 
-.align	2
+.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}
@@ -442,11 +452,999 @@ sha1_block_data_order:
 	moveq	pc,lr			@ be binary compatible with V4, yet
 	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
 #endif
-.align	2
+.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
-.size	sha1_block_data_order,.-sha1_block_data_order
-.asciz	"SHA1 block transform for ARMv4, CRYPTOGAMS by <appro@openssl.org>"
-.align	2
+.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/main/openssl/crypto/sha/asm/sha1-armv8.S b/main/openssl/crypto/sha/asm/sha1-armv8.S
new file mode 100644
index 00000000..f9d12625
--- /dev/null
+++ b/main/openssl/crypto/sha/asm/sha1-armv8.S
@@ -0,0 +1,1211 @@
+#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/main/openssl/crypto/sha/asm/sha1-armv8.pl b/main/openssl/crypto/sha/asm/sha1-armv8.pl
new file mode 100644
index 00000000..c1f552b6
--- /dev/null
+++ b/main/openssl/crypto/sha/asm/sha1-armv8.pl
@@ -0,0 +1,333 @@
+#!/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/main/openssl/crypto/sha/asm/sha256-armv4.pl b/main/openssl/crypto/sha/asm/sha256-armv4.pl
index 9c84e8d9..505ca8f3 100644
--- a/main/openssl/crypto/sha/asm/sha256-armv4.pl
+++ b/main/openssl/crypto/sha/asm/sha256-armv4.pl
@@ -1,7 +1,7 @@
 #!/usr/bin/env perl
 
 # ====================================================================
-# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
+# 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/.
@@ -21,15 +21,27 @@
 # February 2011.
 #
 # Profiler-assisted and platform-specific optimization resulted in 16%
-# improvement on Cortex A8 core and ~17 cycles per processed byte.
+# 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";	$t3="r1";
+$inp="r1";	$t4="r1";
 $len="r2";	$t1="r2";
-$T1="r3";
+$T1="r3";	$t3="r3";
 $A="r4";
 $B="r5";
 $C="r6";
@@ -52,71 +64,88 @@ my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_;
 
 $code.=<<___ if ($i<16);
 #if __ARM_ARCH__>=7
-	ldr	$T1,[$inp],#4
+	@ 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
+	@ ldrb	$t1,[$inp,#3]			@ $i
+	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
 	ldrb	$t2,[$inp,#2]
-	ldrb	$t1,[$inp,#1]
-	ldrb	$t0,[$inp],#4
-	orr	$T1,$T1,$t2,lsl#8
-	orr	$T1,$T1,$t1,lsl#16
-	orr	$T1,$T1,$t0,lsl#24
+	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.=<<___;
-	mov	$t0,$e,ror#$Sigma1[0]
 	ldr	$t2,[$Ktbl],#4			@ *K256++
-	eor	$t0,$t0,$e,ror#$Sigma1[1]
+	add	$h,$h,$t1			@ h+=X[i]
+	str	$t1,[sp,#`$i%16`*4]
 	eor	$t1,$f,$g
-#if $i>=16
-	add	$T1,$T1,$t3			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	$T1,$T1
-#endif
-#if $i==15
-	str	$inp,[sp,#17*4]			@ leave room for $t3
-#endif
-	eor	$t0,$t0,$e,ror#$Sigma1[2]	@ Sigma1(e)
+	add	$h,$h,$t0,ror#$Sigma1[0]	@ h+=Sigma1(e)
 	and	$t1,$t1,$e
-	str	$T1,[sp,#`$i%16`*4]
-	add	$T1,$T1,$t0
+	add	$h,$h,$t2			@ h+=K256[i]
 	eor	$t1,$t1,$g			@ Ch(e,f,g)
-	add	$T1,$T1,$h
-	mov	$h,$a,ror#$Sigma0[0]
-	add	$T1,$T1,$t1
-	eor	$h,$h,$a,ror#$Sigma0[1]
-	add	$T1,$T1,$t2
-	eor	$h,$h,$a,ror#$Sigma0[2]		@ Sigma0(a)
-#if $i>=15
-	ldr	$t3,[sp,#`($i+2)%16`*4]		@ from BODY_16_xx
+	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
-	orr	$t0,$a,$b
-	and	$t1,$a,$b
-	and	$t0,$t0,$c
-	add	$h,$h,$T1
-	orr	$t0,$t0,$t1			@ Maj(a,b,c)
-	add	$d,$d,$T1
-	add	$h,$h,$t0
+#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	$t3,[sp,#`($i+1)%16`*4]		@ $i
-	ldr	$t2,[sp,#`($i+14)%16`*4]
-	mov	$t0,$t3,ror#$sigma0[0]
-	ldr	$T1,[sp,#`($i+0)%16`*4]
-	eor	$t0,$t0,$t3,ror#$sigma0[1]
-	ldr	$t1,[sp,#`($i+9)%16`*4]
-	eor	$t0,$t0,$t3,lsr#$sigma0[2]	@ sigma0(X[i+1])
-	mov	$t3,$t2,ror#$sigma1[0]
-	add	$T1,$T1,$t0
-	eor	$t3,$t3,$t2,ror#$sigma1[1]
-	add	$T1,$T1,$t1
-	eor	$t3,$t3,$t2,lsr#$sigma1[2]	@ sigma1(X[i+14])
-	@ add	$T1,$T1,$t3
+	@ 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(@_);
 }
@@ -147,46 +176,64 @@ K256:
 .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		@ K256
+	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.=<<___;
-	and	$t2,$t2,#0xff
-	cmp	$t2,#0xf2
+	ldreq	$t3,[sp,#16*4]		@ pull ctx
 	bne	.Lrounds_16_xx
 
-	ldr	$T1,[sp,#16*4]		@ pull ctx
-	ldr	$t0,[$T1,#0]
-	ldr	$t1,[$T1,#4]
-	ldr	$t2,[$T1,#8]
+	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	$t0,[$T1,#12]
+	ldr	$t0,[$t3,#12]
 	add	$B,$B,$t1
-	ldr	$t1,[$T1,#16]
+	ldr	$t1,[$t3,#16]
 	add	$C,$C,$t2
-	ldr	$t2,[$T1,#20]
+	ldr	$t2,[$t3,#20]
 	add	$D,$D,$t0
-	ldr	$t0,[$T1,#24]
+	ldr	$t0,[$t3,#24]
 	add	$E,$E,$t1
-	ldr	$t1,[$T1,#28]
+	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	$T1,{$A,$B,$C,$D,$E,$F,$G,$H}
+	stmia	$t3,{$A,$B,$C,$D,$E,$F,$G,$H}
 	cmp	$inp,$t2
 	sub	$Ktbl,$Ktbl,#256	@ rewind Ktbl
 	bne	.Loop
@@ -200,12 +247,410 @@ $code.=<<___;
 	moveq	pc,lr			@ be binary compatible with V4, yet
 	bx	lr			@ interoperable with Thumb ISA:-)
 #endif
-.size   sha256_block_data_order,.-sha256_block_data_order
-.asciz  "SHA256 block transform for ARMv4, CRYPTOGAMS by <appro\@openssl.org>"
+.size	sha256_block_data_order,.-sha256_block_data_order
+___
+######################################################################
+# NEON stuff
+#
+{{{
+my @X=map("q$_",(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
 ___
 
-$code =~ s/\`([^\`]*)\`/eval $1/gem;
-$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm;	# make it possible to compile with -march=armv4
-print $code;
+{   my  %opcode = (
+	"sha256h"	=> 0xf3000c40,	"sha256h2"	=> 0xf3100c40,
+	"sha256su0"	=> 0xf3ba03c0,	"sha256su1"	=> 0xf3200c40	);
+
+    sub unsha256 {
+	my ($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/main/openssl/crypto/sha/asm/sha256-armv4.s b/main/openssl/crypto/sha/asm/sha256-armv4.s
index 9c20a63c..853d7da5 100644
--- a/main/openssl/crypto/sha/asm/sha256-armv4.s
+++ b/main/openssl/crypto/sha/asm/sha256-armv4.s
@@ -23,1463 +23,1721 @@ K256:
 .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		@ K256
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 0
+	@ ldrb	r2,[r1,#3]			@ 0
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r8,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r8,ror#11
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#0*4]
 	eor	r2,r9,r10
-#if 0>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 0==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r8,ror#25	@ Sigma1(e)
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r8
-	str	r3,[sp,#0*4]
-	add	r3,r3,r0
+	add	r11,r11,r12			@ h+=K256[i]
 	eor	r2,r2,r10			@ Ch(e,f,g)
-	add	r3,r3,r11
-	mov	r11,r4,ror#2
-	add	r3,r3,r2
-	eor	r11,r11,r4,ror#13
-	add	r3,r3,r12
-	eor	r11,r11,r4,ror#22		@ Sigma0(a)
-#if 0>=15
-	ldr	r1,[sp,#2*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r4,r5
-	and	r2,r4,r5
-	and	r0,r0,r6
-	add	r11,r11,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r7,r7,r3
-	add	r11,r11,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 1
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r7,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r7,ror#11
+	@ 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
-#if 1>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 1==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r7,ror#25	@ Sigma1(e)
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r7
-	str	r3,[sp,#1*4]
-	add	r3,r3,r0
+	add	r10,r10,r3			@ h+=K256[i]
 	eor	r2,r2,r9			@ Ch(e,f,g)
-	add	r3,r3,r10
-	mov	r10,r11,ror#2
-	add	r3,r3,r2
-	eor	r10,r10,r11,ror#13
-	add	r3,r3,r12
-	eor	r10,r10,r11,ror#22		@ Sigma0(a)
-#if 1>=15
-	ldr	r1,[sp,#3*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r11,r4
-	and	r2,r11,r4
-	and	r0,r0,r5
-	add	r10,r10,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r6,r6,r3
-	add	r10,r10,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 2
+	@ ldrb	r2,[r1,#3]			@ 2
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r6,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r6,ror#11
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#2*4]
 	eor	r2,r7,r8
-#if 2>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 2==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r6,ror#25	@ Sigma1(e)
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r6
-	str	r3,[sp,#2*4]
-	add	r3,r3,r0
+	add	r9,r9,r12			@ h+=K256[i]
 	eor	r2,r2,r8			@ Ch(e,f,g)
-	add	r3,r3,r9
-	mov	r9,r10,ror#2
-	add	r3,r3,r2
-	eor	r9,r9,r10,ror#13
-	add	r3,r3,r12
-	eor	r9,r9,r10,ror#22		@ Sigma0(a)
-#if 2>=15
-	ldr	r1,[sp,#4*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r10,r11
-	and	r2,r10,r11
-	and	r0,r0,r4
-	add	r9,r9,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r5,r5,r3
-	add	r9,r9,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 3
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r5,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r5,ror#11
+	@ 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
-#if 3>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 3==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r5,ror#25	@ Sigma1(e)
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r5
-	str	r3,[sp,#3*4]
-	add	r3,r3,r0
+	add	r8,r8,r3			@ h+=K256[i]
 	eor	r2,r2,r7			@ Ch(e,f,g)
-	add	r3,r3,r8
-	mov	r8,r9,ror#2
-	add	r3,r3,r2
-	eor	r8,r8,r9,ror#13
-	add	r3,r3,r12
-	eor	r8,r8,r9,ror#22		@ Sigma0(a)
-#if 3>=15
-	ldr	r1,[sp,#5*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r9,r10
-	and	r2,r9,r10
-	and	r0,r0,r11
-	add	r8,r8,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r4,r4,r3
-	add	r8,r8,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 4
+	@ ldrb	r2,[r1,#3]			@ 4
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r4,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r4,ror#11
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#4*4]
 	eor	r2,r5,r6
-#if 4>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 4==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r4,ror#25	@ Sigma1(e)
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r4
-	str	r3,[sp,#4*4]
-	add	r3,r3,r0
+	add	r7,r7,r12			@ h+=K256[i]
 	eor	r2,r2,r6			@ Ch(e,f,g)
-	add	r3,r3,r7
-	mov	r7,r8,ror#2
-	add	r3,r3,r2
-	eor	r7,r7,r8,ror#13
-	add	r3,r3,r12
-	eor	r7,r7,r8,ror#22		@ Sigma0(a)
-#if 4>=15
-	ldr	r1,[sp,#6*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r8,r9
-	and	r2,r8,r9
-	and	r0,r0,r10
-	add	r7,r7,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r11,r11,r3
-	add	r7,r7,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 5
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r11,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r11,ror#11
+	@ 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
-#if 5>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 5==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r11,ror#25	@ Sigma1(e)
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r11
-	str	r3,[sp,#5*4]
-	add	r3,r3,r0
+	add	r6,r6,r3			@ h+=K256[i]
 	eor	r2,r2,r5			@ Ch(e,f,g)
-	add	r3,r3,r6
-	mov	r6,r7,ror#2
-	add	r3,r3,r2
-	eor	r6,r6,r7,ror#13
-	add	r3,r3,r12
-	eor	r6,r6,r7,ror#22		@ Sigma0(a)
-#if 5>=15
-	ldr	r1,[sp,#7*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r7,r8
-	and	r2,r7,r8
-	and	r0,r0,r9
-	add	r6,r6,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r10,r10,r3
-	add	r6,r6,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 6
+	@ ldrb	r2,[r1,#3]			@ 6
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r10,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r10,ror#11
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#6*4]
 	eor	r2,r11,r4
-#if 6>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 6==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r10,ror#25	@ Sigma1(e)
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r10
-	str	r3,[sp,#6*4]
-	add	r3,r3,r0
+	add	r5,r5,r12			@ h+=K256[i]
 	eor	r2,r2,r4			@ Ch(e,f,g)
-	add	r3,r3,r5
-	mov	r5,r6,ror#2
-	add	r3,r3,r2
-	eor	r5,r5,r6,ror#13
-	add	r3,r3,r12
-	eor	r5,r5,r6,ror#22		@ Sigma0(a)
-#if 6>=15
-	ldr	r1,[sp,#8*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r6,r7
-	and	r2,r6,r7
-	and	r0,r0,r8
-	add	r5,r5,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r9,r9,r3
-	add	r5,r5,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 7
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r9,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r9,ror#11
+	@ 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
-#if 7>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 7==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r9,ror#25	@ Sigma1(e)
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r9
-	str	r3,[sp,#7*4]
-	add	r3,r3,r0
+	add	r4,r4,r3			@ h+=K256[i]
 	eor	r2,r2,r11			@ Ch(e,f,g)
-	add	r3,r3,r4
-	mov	r4,r5,ror#2
-	add	r3,r3,r2
-	eor	r4,r4,r5,ror#13
-	add	r3,r3,r12
-	eor	r4,r4,r5,ror#22		@ Sigma0(a)
-#if 7>=15
-	ldr	r1,[sp,#9*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r5,r6
-	and	r2,r5,r6
-	and	r0,r0,r7
-	add	r4,r4,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r8,r8,r3
-	add	r4,r4,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 8
+	@ ldrb	r2,[r1,#3]			@ 8
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r8,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r8,ror#11
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#8*4]
 	eor	r2,r9,r10
-#if 8>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 8==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r8,ror#25	@ Sigma1(e)
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r8
-	str	r3,[sp,#8*4]
-	add	r3,r3,r0
+	add	r11,r11,r12			@ h+=K256[i]
 	eor	r2,r2,r10			@ Ch(e,f,g)
-	add	r3,r3,r11
-	mov	r11,r4,ror#2
-	add	r3,r3,r2
-	eor	r11,r11,r4,ror#13
-	add	r3,r3,r12
-	eor	r11,r11,r4,ror#22		@ Sigma0(a)
-#if 8>=15
-	ldr	r1,[sp,#10*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r4,r5
-	and	r2,r4,r5
-	and	r0,r0,r6
-	add	r11,r11,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r7,r7,r3
-	add	r11,r11,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 9
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r7,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r7,ror#11
+	@ 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
-#if 9>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 9==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r7,ror#25	@ Sigma1(e)
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r7
-	str	r3,[sp,#9*4]
-	add	r3,r3,r0
+	add	r10,r10,r3			@ h+=K256[i]
 	eor	r2,r2,r9			@ Ch(e,f,g)
-	add	r3,r3,r10
-	mov	r10,r11,ror#2
-	add	r3,r3,r2
-	eor	r10,r10,r11,ror#13
-	add	r3,r3,r12
-	eor	r10,r10,r11,ror#22		@ Sigma0(a)
-#if 9>=15
-	ldr	r1,[sp,#11*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r11,r4
-	and	r2,r11,r4
-	and	r0,r0,r5
-	add	r10,r10,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r6,r6,r3
-	add	r10,r10,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 10
+	@ ldrb	r2,[r1,#3]			@ 10
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r6,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r6,ror#11
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#10*4]
 	eor	r2,r7,r8
-#if 10>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 10==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r6,ror#25	@ Sigma1(e)
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r6
-	str	r3,[sp,#10*4]
-	add	r3,r3,r0
+	add	r9,r9,r12			@ h+=K256[i]
 	eor	r2,r2,r8			@ Ch(e,f,g)
-	add	r3,r3,r9
-	mov	r9,r10,ror#2
-	add	r3,r3,r2
-	eor	r9,r9,r10,ror#13
-	add	r3,r3,r12
-	eor	r9,r9,r10,ror#22		@ Sigma0(a)
-#if 10>=15
-	ldr	r1,[sp,#12*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r10,r11
-	and	r2,r10,r11
-	and	r0,r0,r4
-	add	r9,r9,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r5,r5,r3
-	add	r9,r9,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 11
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r5,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r5,ror#11
+	@ 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
-#if 11>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 11==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r5,ror#25	@ Sigma1(e)
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r5
-	str	r3,[sp,#11*4]
-	add	r3,r3,r0
+	add	r8,r8,r3			@ h+=K256[i]
 	eor	r2,r2,r7			@ Ch(e,f,g)
-	add	r3,r3,r8
-	mov	r8,r9,ror#2
-	add	r3,r3,r2
-	eor	r8,r8,r9,ror#13
-	add	r3,r3,r12
-	eor	r8,r8,r9,ror#22		@ Sigma0(a)
-#if 11>=15
-	ldr	r1,[sp,#13*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r9,r10
-	and	r2,r9,r10
-	and	r0,r0,r11
-	add	r8,r8,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r4,r4,r3
-	add	r8,r8,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 12
+	@ ldrb	r2,[r1,#3]			@ 12
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r4,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r4,ror#11
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#12*4]
 	eor	r2,r5,r6
-#if 12>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 12==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r4,ror#25	@ Sigma1(e)
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r4
-	str	r3,[sp,#12*4]
-	add	r3,r3,r0
+	add	r7,r7,r12			@ h+=K256[i]
 	eor	r2,r2,r6			@ Ch(e,f,g)
-	add	r3,r3,r7
-	mov	r7,r8,ror#2
-	add	r3,r3,r2
-	eor	r7,r7,r8,ror#13
-	add	r3,r3,r12
-	eor	r7,r7,r8,ror#22		@ Sigma0(a)
-#if 12>=15
-	ldr	r1,[sp,#14*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r8,r9
-	and	r2,r8,r9
-	and	r0,r0,r10
-	add	r7,r7,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r11,r11,r3
-	add	r7,r7,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 13
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r11,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r11,ror#11
+	@ 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
-#if 13>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 13==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r11,ror#25	@ Sigma1(e)
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r11
-	str	r3,[sp,#13*4]
-	add	r3,r3,r0
+	add	r6,r6,r3			@ h+=K256[i]
 	eor	r2,r2,r5			@ Ch(e,f,g)
-	add	r3,r3,r6
-	mov	r6,r7,ror#2
-	add	r3,r3,r2
-	eor	r6,r6,r7,ror#13
-	add	r3,r3,r12
-	eor	r6,r6,r7,ror#22		@ Sigma0(a)
-#if 13>=15
-	ldr	r1,[sp,#15*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r7,r8
-	and	r2,r7,r8
-	and	r0,r0,r9
-	add	r6,r6,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r10,r10,r3
-	add	r6,r6,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 14
+	@ ldrb	r2,[r1,#3]			@ 14
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
 	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
+	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
-	mov	r0,r10,ror#6
 	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r10,ror#11
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#14*4]
 	eor	r2,r11,r4
-#if 14>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 14==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r10,ror#25	@ Sigma1(e)
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r10
-	str	r3,[sp,#14*4]
-	add	r3,r3,r0
+	add	r5,r5,r12			@ h+=K256[i]
 	eor	r2,r2,r4			@ Ch(e,f,g)
-	add	r3,r3,r5
-	mov	r5,r6,ror#2
-	add	r3,r3,r2
-	eor	r5,r5,r6,ror#13
-	add	r3,r3,r12
-	eor	r5,r5,r6,ror#22		@ Sigma0(a)
-#if 14>=15
-	ldr	r1,[sp,#0*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r6,r7
-	and	r2,r6,r7
-	and	r0,r0,r8
-	add	r5,r5,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r9,r9,r3
-	add	r5,r5,r0
+	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	r3,[r1],#4
+	@ 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	r3,[r1,#3]			@ 15
-	ldrb	r12,[r1,#2]
-	ldrb	r2,[r1,#1]
-	ldrb	r0,[r1],#4
-	orr	r3,r3,r12,lsl#8
-	orr	r3,r3,r2,lsl#16
-	orr	r3,r3,r0,lsl#24
-#endif
-	mov	r0,r9,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r9,ror#11
+	@ 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
-#if 15>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 15==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r9,ror#25	@ Sigma1(e)
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r9
-	str	r3,[sp,#15*4]
-	add	r3,r3,r0
+	add	r4,r4,r3			@ h+=K256[i]
 	eor	r2,r2,r11			@ Ch(e,f,g)
-	add	r3,r3,r4
-	mov	r4,r5,ror#2
-	add	r3,r3,r2
-	eor	r4,r4,r5,ror#13
-	add	r3,r3,r12
-	eor	r4,r4,r5,ror#22		@ Sigma0(a)
-#if 15>=15
-	ldr	r1,[sp,#1*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r5,r6
-	and	r2,r5,r6
-	and	r0,r0,r7
-	add	r4,r4,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r8,r8,r3
-	add	r4,r4,r0
+	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	r1,[sp,#1*4]		@ 16
-	ldr	r12,[sp,#14*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#0*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#9*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r8,ror#6
+	@ 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++
-	eor	r0,r0,r8,ror#11
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#0*4]
 	eor	r2,r9,r10
-#if 16>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 16==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r8,ror#25	@ Sigma1(e)
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r8
-	str	r3,[sp,#0*4]
-	add	r3,r3,r0
+	add	r11,r11,r12			@ h+=K256[i]
 	eor	r2,r2,r10			@ Ch(e,f,g)
-	add	r3,r3,r11
-	mov	r11,r4,ror#2
-	add	r3,r3,r2
-	eor	r11,r11,r4,ror#13
-	add	r3,r3,r12
-	eor	r11,r11,r4,ror#22		@ Sigma0(a)
-#if 16>=15
-	ldr	r1,[sp,#2*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r4,r5
-	and	r2,r4,r5
-	and	r0,r0,r6
-	add	r11,r11,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r7,r7,r3
-	add	r11,r11,r0
-	@ ldr	r1,[sp,#2*4]		@ 17
-	ldr	r12,[sp,#15*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#1*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#10*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r7,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r7,ror#11
+	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
-#if 17>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 17==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r7,ror#25	@ Sigma1(e)
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r7
-	str	r3,[sp,#1*4]
-	add	r3,r3,r0
+	add	r10,r10,r3			@ h+=K256[i]
 	eor	r2,r2,r9			@ Ch(e,f,g)
-	add	r3,r3,r10
-	mov	r10,r11,ror#2
-	add	r3,r3,r2
-	eor	r10,r10,r11,ror#13
-	add	r3,r3,r12
-	eor	r10,r10,r11,ror#22		@ Sigma0(a)
-#if 17>=15
-	ldr	r1,[sp,#3*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r11,r4
-	and	r2,r11,r4
-	and	r0,r0,r5
-	add	r10,r10,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r6,r6,r3
-	add	r10,r10,r0
-	@ ldr	r1,[sp,#3*4]		@ 18
-	ldr	r12,[sp,#0*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#2*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#11*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r6,ror#6
+	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++
-	eor	r0,r0,r6,ror#11
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#2*4]
 	eor	r2,r7,r8
-#if 18>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 18==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r6,ror#25	@ Sigma1(e)
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r6
-	str	r3,[sp,#2*4]
-	add	r3,r3,r0
+	add	r9,r9,r12			@ h+=K256[i]
 	eor	r2,r2,r8			@ Ch(e,f,g)
-	add	r3,r3,r9
-	mov	r9,r10,ror#2
-	add	r3,r3,r2
-	eor	r9,r9,r10,ror#13
-	add	r3,r3,r12
-	eor	r9,r9,r10,ror#22		@ Sigma0(a)
-#if 18>=15
-	ldr	r1,[sp,#4*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r10,r11
-	and	r2,r10,r11
-	and	r0,r0,r4
-	add	r9,r9,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r5,r5,r3
-	add	r9,r9,r0
-	@ ldr	r1,[sp,#4*4]		@ 19
-	ldr	r12,[sp,#1*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#3*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#12*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r5,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r5,ror#11
+	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
-#if 19>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 19==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r5,ror#25	@ Sigma1(e)
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r5
-	str	r3,[sp,#3*4]
-	add	r3,r3,r0
+	add	r8,r8,r3			@ h+=K256[i]
 	eor	r2,r2,r7			@ Ch(e,f,g)
-	add	r3,r3,r8
-	mov	r8,r9,ror#2
-	add	r3,r3,r2
-	eor	r8,r8,r9,ror#13
-	add	r3,r3,r12
-	eor	r8,r8,r9,ror#22		@ Sigma0(a)
-#if 19>=15
-	ldr	r1,[sp,#5*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r9,r10
-	and	r2,r9,r10
-	and	r0,r0,r11
-	add	r8,r8,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r4,r4,r3
-	add	r8,r8,r0
-	@ ldr	r1,[sp,#5*4]		@ 20
-	ldr	r12,[sp,#2*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#4*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#13*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r4,ror#6
+	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++
-	eor	r0,r0,r4,ror#11
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#4*4]
 	eor	r2,r5,r6
-#if 20>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 20==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r4,ror#25	@ Sigma1(e)
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r4
-	str	r3,[sp,#4*4]
-	add	r3,r3,r0
+	add	r7,r7,r12			@ h+=K256[i]
 	eor	r2,r2,r6			@ Ch(e,f,g)
-	add	r3,r3,r7
-	mov	r7,r8,ror#2
-	add	r3,r3,r2
-	eor	r7,r7,r8,ror#13
-	add	r3,r3,r12
-	eor	r7,r7,r8,ror#22		@ Sigma0(a)
-#if 20>=15
-	ldr	r1,[sp,#6*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r8,r9
-	and	r2,r8,r9
-	and	r0,r0,r10
-	add	r7,r7,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r11,r11,r3
-	add	r7,r7,r0
-	@ ldr	r1,[sp,#6*4]		@ 21
-	ldr	r12,[sp,#3*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#5*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#14*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r11,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r11,ror#11
+	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
-#if 21>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 21==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r11,ror#25	@ Sigma1(e)
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r11
-	str	r3,[sp,#5*4]
-	add	r3,r3,r0
+	add	r6,r6,r3			@ h+=K256[i]
 	eor	r2,r2,r5			@ Ch(e,f,g)
-	add	r3,r3,r6
-	mov	r6,r7,ror#2
-	add	r3,r3,r2
-	eor	r6,r6,r7,ror#13
-	add	r3,r3,r12
-	eor	r6,r6,r7,ror#22		@ Sigma0(a)
-#if 21>=15
-	ldr	r1,[sp,#7*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r7,r8
-	and	r2,r7,r8
-	and	r0,r0,r9
-	add	r6,r6,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r10,r10,r3
-	add	r6,r6,r0
-	@ ldr	r1,[sp,#7*4]		@ 22
-	ldr	r12,[sp,#4*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#6*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#15*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r10,ror#6
+	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++
-	eor	r0,r0,r10,ror#11
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#6*4]
 	eor	r2,r11,r4
-#if 22>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 22==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r10,ror#25	@ Sigma1(e)
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r10
-	str	r3,[sp,#6*4]
-	add	r3,r3,r0
+	add	r5,r5,r12			@ h+=K256[i]
 	eor	r2,r2,r4			@ Ch(e,f,g)
-	add	r3,r3,r5
-	mov	r5,r6,ror#2
-	add	r3,r3,r2
-	eor	r5,r5,r6,ror#13
-	add	r3,r3,r12
-	eor	r5,r5,r6,ror#22		@ Sigma0(a)
-#if 22>=15
-	ldr	r1,[sp,#8*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r6,r7
-	and	r2,r6,r7
-	and	r0,r0,r8
-	add	r5,r5,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r9,r9,r3
-	add	r5,r5,r0
-	@ ldr	r1,[sp,#8*4]		@ 23
-	ldr	r12,[sp,#5*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#7*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#0*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r9,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r9,ror#11
+	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
-#if 23>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 23==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r9,ror#25	@ Sigma1(e)
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r9
-	str	r3,[sp,#7*4]
-	add	r3,r3,r0
+	add	r4,r4,r3			@ h+=K256[i]
 	eor	r2,r2,r11			@ Ch(e,f,g)
-	add	r3,r3,r4
-	mov	r4,r5,ror#2
-	add	r3,r3,r2
-	eor	r4,r4,r5,ror#13
-	add	r3,r3,r12
-	eor	r4,r4,r5,ror#22		@ Sigma0(a)
-#if 23>=15
-	ldr	r1,[sp,#9*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r5,r6
-	and	r2,r5,r6
-	and	r0,r0,r7
-	add	r4,r4,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r8,r8,r3
-	add	r4,r4,r0
-	@ ldr	r1,[sp,#9*4]		@ 24
-	ldr	r12,[sp,#6*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#8*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#1*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r8,ror#6
+	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++
-	eor	r0,r0,r8,ror#11
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#8*4]
 	eor	r2,r9,r10
-#if 24>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 24==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r8,ror#25	@ Sigma1(e)
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r8
-	str	r3,[sp,#8*4]
-	add	r3,r3,r0
+	add	r11,r11,r12			@ h+=K256[i]
 	eor	r2,r2,r10			@ Ch(e,f,g)
-	add	r3,r3,r11
-	mov	r11,r4,ror#2
-	add	r3,r3,r2
-	eor	r11,r11,r4,ror#13
-	add	r3,r3,r12
-	eor	r11,r11,r4,ror#22		@ Sigma0(a)
-#if 24>=15
-	ldr	r1,[sp,#10*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r4,r5
-	and	r2,r4,r5
-	and	r0,r0,r6
-	add	r11,r11,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r7,r7,r3
-	add	r11,r11,r0
-	@ ldr	r1,[sp,#10*4]		@ 25
-	ldr	r12,[sp,#7*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#9*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#2*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r7,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r7,ror#11
+	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
-#if 25>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 25==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r7,ror#25	@ Sigma1(e)
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r7
-	str	r3,[sp,#9*4]
-	add	r3,r3,r0
+	add	r10,r10,r3			@ h+=K256[i]
 	eor	r2,r2,r9			@ Ch(e,f,g)
-	add	r3,r3,r10
-	mov	r10,r11,ror#2
-	add	r3,r3,r2
-	eor	r10,r10,r11,ror#13
-	add	r3,r3,r12
-	eor	r10,r10,r11,ror#22		@ Sigma0(a)
-#if 25>=15
-	ldr	r1,[sp,#11*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r11,r4
-	and	r2,r11,r4
-	and	r0,r0,r5
-	add	r10,r10,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r6,r6,r3
-	add	r10,r10,r0
-	@ ldr	r1,[sp,#11*4]		@ 26
-	ldr	r12,[sp,#8*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#10*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#3*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r6,ror#6
+	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++
-	eor	r0,r0,r6,ror#11
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#10*4]
 	eor	r2,r7,r8
-#if 26>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 26==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r6,ror#25	@ Sigma1(e)
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r6
-	str	r3,[sp,#10*4]
-	add	r3,r3,r0
+	add	r9,r9,r12			@ h+=K256[i]
 	eor	r2,r2,r8			@ Ch(e,f,g)
-	add	r3,r3,r9
-	mov	r9,r10,ror#2
-	add	r3,r3,r2
-	eor	r9,r9,r10,ror#13
-	add	r3,r3,r12
-	eor	r9,r9,r10,ror#22		@ Sigma0(a)
-#if 26>=15
-	ldr	r1,[sp,#12*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r10,r11
-	and	r2,r10,r11
-	and	r0,r0,r4
-	add	r9,r9,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r5,r5,r3
-	add	r9,r9,r0
-	@ ldr	r1,[sp,#12*4]		@ 27
-	ldr	r12,[sp,#9*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#11*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#4*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r5,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r5,ror#11
+	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
-#if 27>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 27==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r5,ror#25	@ Sigma1(e)
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r5
-	str	r3,[sp,#11*4]
-	add	r3,r3,r0
+	add	r8,r8,r3			@ h+=K256[i]
 	eor	r2,r2,r7			@ Ch(e,f,g)
-	add	r3,r3,r8
-	mov	r8,r9,ror#2
-	add	r3,r3,r2
-	eor	r8,r8,r9,ror#13
-	add	r3,r3,r12
-	eor	r8,r8,r9,ror#22		@ Sigma0(a)
-#if 27>=15
-	ldr	r1,[sp,#13*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r9,r10
-	and	r2,r9,r10
-	and	r0,r0,r11
-	add	r8,r8,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r4,r4,r3
-	add	r8,r8,r0
-	@ ldr	r1,[sp,#13*4]		@ 28
-	ldr	r12,[sp,#10*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#12*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#5*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r4,ror#6
+	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++
-	eor	r0,r0,r4,ror#11
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#12*4]
 	eor	r2,r5,r6
-#if 28>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 28==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r4,ror#25	@ Sigma1(e)
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r4
-	str	r3,[sp,#12*4]
-	add	r3,r3,r0
+	add	r7,r7,r12			@ h+=K256[i]
 	eor	r2,r2,r6			@ Ch(e,f,g)
-	add	r3,r3,r7
-	mov	r7,r8,ror#2
-	add	r3,r3,r2
-	eor	r7,r7,r8,ror#13
-	add	r3,r3,r12
-	eor	r7,r7,r8,ror#22		@ Sigma0(a)
-#if 28>=15
-	ldr	r1,[sp,#14*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r8,r9
-	and	r2,r8,r9
-	and	r0,r0,r10
-	add	r7,r7,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r11,r11,r3
-	add	r7,r7,r0
-	@ ldr	r1,[sp,#14*4]		@ 29
-	ldr	r12,[sp,#11*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#13*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#6*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r11,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r11,ror#11
+	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
-#if 29>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 29==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r11,ror#25	@ Sigma1(e)
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r11
-	str	r3,[sp,#13*4]
-	add	r3,r3,r0
+	add	r6,r6,r3			@ h+=K256[i]
 	eor	r2,r2,r5			@ Ch(e,f,g)
-	add	r3,r3,r6
-	mov	r6,r7,ror#2
-	add	r3,r3,r2
-	eor	r6,r6,r7,ror#13
-	add	r3,r3,r12
-	eor	r6,r6,r7,ror#22		@ Sigma0(a)
-#if 29>=15
-	ldr	r1,[sp,#15*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r7,r8
-	and	r2,r7,r8
-	and	r0,r0,r9
-	add	r6,r6,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r10,r10,r3
-	add	r6,r6,r0
-	@ ldr	r1,[sp,#15*4]		@ 30
-	ldr	r12,[sp,#12*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#14*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#7*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
-	add	r3,r3,r0
-	eor	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r10,ror#6
+	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++
-	eor	r0,r0,r10,ror#11
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#14*4]
 	eor	r2,r11,r4
-#if 30>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 30==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r10,ror#25	@ Sigma1(e)
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r10
-	str	r3,[sp,#14*4]
-	add	r3,r3,r0
+	add	r5,r5,r12			@ h+=K256[i]
 	eor	r2,r2,r4			@ Ch(e,f,g)
-	add	r3,r3,r5
-	mov	r5,r6,ror#2
-	add	r3,r3,r2
-	eor	r5,r5,r6,ror#13
-	add	r3,r3,r12
-	eor	r5,r5,r6,ror#22		@ Sigma0(a)
-#if 30>=15
-	ldr	r1,[sp,#0*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r6,r7
-	and	r2,r6,r7
-	and	r0,r0,r8
-	add	r5,r5,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r9,r9,r3
-	add	r5,r5,r0
-	@ ldr	r1,[sp,#0*4]		@ 31
-	ldr	r12,[sp,#13*4]
-	mov	r0,r1,ror#7
-	ldr	r3,[sp,#15*4]
-	eor	r0,r0,r1,ror#18
-	ldr	r2,[sp,#8*4]
-	eor	r0,r0,r1,lsr#3	@ sigma0(X[i+1])
-	mov	r1,r12,ror#17
+	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	r1,r1,r12,ror#19
-	add	r3,r3,r2
-	eor	r1,r1,r12,lsr#10	@ sigma1(X[i+14])
-	@ add	r3,r3,r1
-	mov	r0,r9,ror#6
-	ldr	r12,[r14],#4			@ *K256++
-	eor	r0,r0,r9,ror#11
+	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
-#if 31>=16
-	add	r3,r3,r1			@ from BODY_16_xx
-#elif __ARM_ARCH__>=7 && defined(__ARMEL__)
-	rev	r3,r3
-#endif
-#if 31==15
-	str	r1,[sp,#17*4]			@ leave room for r1
-#endif
-	eor	r0,r0,r9,ror#25	@ Sigma1(e)
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
 	and	r2,r2,r9
-	str	r3,[sp,#15*4]
-	add	r3,r3,r0
+	add	r4,r4,r3			@ h+=K256[i]
 	eor	r2,r2,r11			@ Ch(e,f,g)
-	add	r3,r3,r4
-	mov	r4,r5,ror#2
-	add	r3,r3,r2
-	eor	r4,r4,r5,ror#13
-	add	r3,r3,r12
-	eor	r4,r4,r5,ror#22		@ Sigma0(a)
-#if 31>=15
-	ldr	r1,[sp,#1*4]		@ from BODY_16_xx
-#endif
-	orr	r0,r5,r6
-	and	r2,r5,r6
-	and	r0,r0,r7
-	add	r4,r4,r3
-	orr	r0,r0,r2			@ Maj(a,b,c)
-	add	r8,r8,r3
-	add	r4,r4,r0
-	and	r12,r12,#0xff
-	cmp	r12,#0xf2
+	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
 
-	ldr	r3,[sp,#16*4]		@ pull ctx
+	add	r4,r4,r12		@ h+=Maj(a,b,c) from the past
 	ldr	r0,[r3,#0]
 	ldr	r2,[r3,#4]
 	ldr	r12,[r3,#8]
@@ -1512,6 +1770,921 @@ sha256_block_data_order:
 	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
-.asciz  "SHA256 block transform for ARMv4, CRYPTOGAMS by <appro@openssl.org>"
+.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/main/openssl/crypto/sha/asm/sha256-armv8.S b/main/openssl/crypto/sha/asm/sha256-armv8.S
new file mode 100644
index 00000000..bd43b1fe
--- /dev/null
+++ b/main/openssl/crypto/sha/asm/sha256-armv8.S
@@ -0,0 +1,1141 @@
+#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/main/openssl/crypto/sha/asm/sha512-armv4.pl b/main/openssl/crypto/sha/asm/sha512-armv4.pl
index 7faf37b1..71aa9356 100644
--- a/main/openssl/crypto/sha/asm/sha512-armv4.pl
+++ b/main/openssl/crypto/sha/asm/sha512-armv4.pl
@@ -565,7 +565,7 @@ $code.=<<___;
 	bne		.Loop_neon
 
 	vldmia	sp!,{d8-d15}		@ epilogue
-	bx	lr
+	ret				@ bx lr
 #endif
 ___
 }
@@ -578,5 +578,6 @@ ___
 
 $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/main/openssl/crypto/sha/asm/sha512-armv4.s b/main/openssl/crypto/sha/asm/sha512-armv4.s
index 57301922..fd462771 100644
--- a/main/openssl/crypto/sha/asm/sha512-armv4.s
+++ b/main/openssl/crypto/sha/asm/sha512-armv4.s
@@ -1775,7 +1775,7 @@ sha512_block_data_order:
 	bne		.Loop_neon
 
 	vldmia	sp!,{d8-d15}		@ epilogue
-	.word	0xe12fff1e
+	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>"
diff --git a/main/openssl/crypto/sha/asm/sha512-armv8.S b/main/openssl/crypto/sha/asm/sha512-armv8.S
new file mode 100644
index 00000000..6b0d1940
--- /dev/null
+++ b/main/openssl/crypto/sha/asm/sha512-armv8.S
@@ -0,0 +1,1021 @@
+#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/main/openssl/crypto/sha/asm/sha512-armv8.pl b/main/openssl/crypto/sha/asm/sha512-armv8.pl
new file mode 100644
index 00000000..6935ed65
--- /dev/null
+++ b/main/openssl/crypto/sha/asm/sha512-armv8.pl
@@ -0,0 +1,414 @@
+#!/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;