/*
 * ====================================================================
 * Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
 * project. Rights for redistribution and usage in source and binary
 * forms are granted according to the OpenSSL license.
 * ====================================================================
 *
 * sha256/512_block procedure for x86_64.
 *
 * 40% improvement over compiler-generated code on Opteron. On EM64T
 * sha256 was observed to run >80% faster and sha512 - >40%. No magical
 * tricks, just straight implementation... I really wonder why gcc
 * [being armed with inline assembler] fails to generate as fast code.
 * The only thing which is cool about this module is that it's very
 * same instruction sequence used for both SHA-256 and SHA-512. In
 * former case the instructions operate on 32-bit operands, while in
 * latter - on 64-bit ones. All I had to do is to get one flavor right,
 * the other one passed the test right away:-)
 *
 * sha256_block runs in ~1005 cycles on Opteron, which gives you
 * asymptotic performance of 64*1000/1005=63.7MBps times CPU clock
 * frequency in GHz. sha512_block runs in ~1275 cycles, which results
 * in 128*1000/1275=100MBps per GHz. Is there room for improvement?
 * Well, if you compare it to IA-64 implementation, which maintains
 * X[16] in register bank[!], tends to 4 instructions per CPU clock
 * cycle and runs in 1003 cycles, 1275 is very good result for 3-way
 * issue Opteron pipeline and X[16] maintained in memory. So that *if*
 * there is a way to improve it, *then* the only way would be to try to
 * offload X[16] updates to SSE unit, but that would require "deeper"
 * loop unroll, which in turn would naturally cause size blow-up, not
 * to mention increased complexity! And once again, only *if* it's
 * actually possible to noticeably improve overall ILP, instruction
 * level parallelism, on a given CPU implementation in this case.
 *
 * Special note on Intel EM64T. While Opteron CPU exhibits perfect
 * performance ratio of 1.5 between 64- and 32-bit flavors [see above],
 * [currently available] EM64T CPUs apparently are far from it. On the
 * contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit
 * sha256_block:-( This is presumably because 64-bit shifts/rotates
 * apparently are not atomic instructions, but implemented in microcode.
 */

/*
 * OpenSolaris OS modifications
 *
 * Sun elects to use this software under the BSD license.
 *
 * This source originates from OpenSSL file sha512-x86_64.pl at
 * ftp://ftp.openssl.org/snapshot/openssl-0.9.8-stable-SNAP-20080131.tar.gz
 * (presumably for future OpenSSL release 0.9.8h), with these changes:
 *
 * 1. Added perl "use strict" and declared variables.
 *
 * 2. Added OpenSolaris ENTRY_NP/SET_SIZE macros from
 * /usr/include/sys/asm_linkage.h, .ident keywords, and lint(1B) guards.
 *
 * 3. Removed x86_64-xlate.pl script (not needed for as(1) or gas(1)
 * assemblers).  Replaced the .picmeup macro with assembler code.
 *
 * 4. Added 8 to $ctx, as OpenSolaris OS has an extra 4-byte field, "algotype",
 * at the beginning of SHA2_CTX (the next field is 8-byte aligned).
 */

/*
 * This file was generated by a perl script (sha512-x86_64.pl) that were
 * used to generate sha256 and sha512 variants from the same code base.
 * The comments from the original file have been pasted above.
 */


#if defined(lint) || defined(__lint)
#include <sys/stdint.h>
#include <sha2/sha2.h>

/* ARGSUSED */
void
SHA512TransformBlocks(SHA2_CTX *ctx, const void *in, size_t num)
{
}


#else
#define _ASM
#include <sys/asm_linkage.h>

ENTRY_NP(SHA512TransformBlocks)
.cfi_startproc
	ENDBR
	movq	%rsp, %rax
.cfi_def_cfa_register %rax
	push	%rbx
.cfi_offset	%rbx,-16
	push	%rbp
.cfi_offset	%rbp,-24
	push	%r12
.cfi_offset	%r12,-32
	push	%r13
.cfi_offset	%r13,-40
	push	%r14
.cfi_offset	%r14,-48
	push	%r15
.cfi_offset	%r15,-56
	mov	%rsp,%rbp		# copy %rsp
	shl	$4,%rdx		# num*16
	sub	$16*8+4*8,%rsp
	lea	(%rsi,%rdx,8),%rdx	# inp+num*16*8
	and	$-64,%rsp		# align stack frame
	add	$8,%rdi		# Skip OpenSolaris field, "algotype"
	mov	%rdi,16*8+0*8(%rsp)		# save ctx, 1st arg
	mov	%rsi,16*8+1*8(%rsp)		# save inp, 2nd arg
	mov	%rdx,16*8+2*8(%rsp)		# save end pointer, "3rd" arg
	mov	%rbp,16*8+3*8(%rsp)		# save copy of %rsp
# echo ".cfi_cfa_expression %rsp+152,deref,+56" |
#	openssl/crypto/perlasm/x86_64-xlate.pl
.cfi_escape	0x0f,0x06,0x77,0x98,0x01,0x06,0x23,0x38

	#.picmeup %rbp
	# The .picmeup pseudo-directive, from perlasm/x86_64_xlate.pl, puts
	# the address of the "next" instruction into the target register
	# (%rbp).  This generates these 2 instructions:
	lea	.Llea(%rip),%rbp
	#nop	# .picmeup generates a nop for mod 8 alignment--not needed here

.Llea:
	lea	K512-.(%rbp),%rbp

	mov	8*0(%rdi),%rax
	mov	8*1(%rdi),%rbx
	mov	8*2(%rdi),%rcx
	mov	8*3(%rdi),%rdx
	mov	8*4(%rdi),%r8
	mov	8*5(%rdi),%r9
	mov	8*6(%rdi),%r10
	mov	8*7(%rdi),%r11
	jmp	.Lloop

.align	16
.Lloop:
	xor	%rdi,%rdi
	mov	8*0(%rsi),%r12
	bswap	%r12
	mov	%r8,%r13
	mov	%r8,%r14
	mov	%r9,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r10,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r8,%r15			# (f^g)&e
	mov	%r12,0(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r11,%r12			# T1+=h

	mov	%rax,%r11
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rax,%r13
	mov	%rax,%r14

	ror	$28,%r11
	ror	$34,%r13
	mov	%rax,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r11
	ror	$5,%r13
	or	%rcx,%r14			# a|c

	xor	%r13,%r11			# h=Sigma0(a)
	and	%rcx,%r15			# a&c
	add	%r12,%rdx			# d+=T1

	and	%rbx,%r14			# (a|c)&b
	add	%r12,%r11			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r11			# h+=Maj(a,b,c)
	mov	8*1(%rsi),%r12
	bswap	%r12
	mov	%rdx,%r13
	mov	%rdx,%r14
	mov	%r8,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r9,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rdx,%r15			# (f^g)&e
	mov	%r12,8(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r10,%r12			# T1+=h

	mov	%r11,%r10
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r11,%r13
	mov	%r11,%r14

	ror	$28,%r10
	ror	$34,%r13
	mov	%r11,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r10
	ror	$5,%r13
	or	%rbx,%r14			# a|c

	xor	%r13,%r10			# h=Sigma0(a)
	and	%rbx,%r15			# a&c
	add	%r12,%rcx			# d+=T1

	and	%rax,%r14			# (a|c)&b
	add	%r12,%r10			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r10			# h+=Maj(a,b,c)
	mov	8*2(%rsi),%r12
	bswap	%r12
	mov	%rcx,%r13
	mov	%rcx,%r14
	mov	%rdx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r8,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rcx,%r15			# (f^g)&e
	mov	%r12,16(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r9,%r12			# T1+=h

	mov	%r10,%r9
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r10,%r13
	mov	%r10,%r14

	ror	$28,%r9
	ror	$34,%r13
	mov	%r10,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r9
	ror	$5,%r13
	or	%rax,%r14			# a|c

	xor	%r13,%r9			# h=Sigma0(a)
	and	%rax,%r15			# a&c
	add	%r12,%rbx			# d+=T1

	and	%r11,%r14			# (a|c)&b
	add	%r12,%r9			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r9			# h+=Maj(a,b,c)
	mov	8*3(%rsi),%r12
	bswap	%r12
	mov	%rbx,%r13
	mov	%rbx,%r14
	mov	%rcx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rdx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rbx,%r15			# (f^g)&e
	mov	%r12,24(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r8,%r12			# T1+=h

	mov	%r9,%r8
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r9,%r13
	mov	%r9,%r14

	ror	$28,%r8
	ror	$34,%r13
	mov	%r9,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r8
	ror	$5,%r13
	or	%r11,%r14			# a|c

	xor	%r13,%r8			# h=Sigma0(a)
	and	%r11,%r15			# a&c
	add	%r12,%rax			# d+=T1

	and	%r10,%r14			# (a|c)&b
	add	%r12,%r8			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r8			# h+=Maj(a,b,c)
	mov	8*4(%rsi),%r12
	bswap	%r12
	mov	%rax,%r13
	mov	%rax,%r14
	mov	%rbx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rcx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rax,%r15			# (f^g)&e
	mov	%r12,32(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rdx,%r12			# T1+=h

	mov	%r8,%rdx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r8,%r13
	mov	%r8,%r14

	ror	$28,%rdx
	ror	$34,%r13
	mov	%r8,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rdx
	ror	$5,%r13
	or	%r10,%r14			# a|c

	xor	%r13,%rdx			# h=Sigma0(a)
	and	%r10,%r15			# a&c
	add	%r12,%r11			# d+=T1

	and	%r9,%r14			# (a|c)&b
	add	%r12,%rdx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rdx			# h+=Maj(a,b,c)
	mov	8*5(%rsi),%r12
	bswap	%r12
	mov	%r11,%r13
	mov	%r11,%r14
	mov	%rax,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rbx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r11,%r15			# (f^g)&e
	mov	%r12,40(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rcx,%r12			# T1+=h

	mov	%rdx,%rcx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rdx,%r13
	mov	%rdx,%r14

	ror	$28,%rcx
	ror	$34,%r13
	mov	%rdx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rcx
	ror	$5,%r13
	or	%r9,%r14			# a|c

	xor	%r13,%rcx			# h=Sigma0(a)
	and	%r9,%r15			# a&c
	add	%r12,%r10			# d+=T1

	and	%r8,%r14			# (a|c)&b
	add	%r12,%rcx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rcx			# h+=Maj(a,b,c)
	mov	8*6(%rsi),%r12
	bswap	%r12
	mov	%r10,%r13
	mov	%r10,%r14
	mov	%r11,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rax,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r10,%r15			# (f^g)&e
	mov	%r12,48(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rbx,%r12			# T1+=h

	mov	%rcx,%rbx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rcx,%r13
	mov	%rcx,%r14

	ror	$28,%rbx
	ror	$34,%r13
	mov	%rcx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rbx
	ror	$5,%r13
	or	%r8,%r14			# a|c

	xor	%r13,%rbx			# h=Sigma0(a)
	and	%r8,%r15			# a&c
	add	%r12,%r9			# d+=T1

	and	%rdx,%r14			# (a|c)&b
	add	%r12,%rbx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rbx			# h+=Maj(a,b,c)
	mov	8*7(%rsi),%r12
	bswap	%r12
	mov	%r9,%r13
	mov	%r9,%r14
	mov	%r10,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r11,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r9,%r15			# (f^g)&e
	mov	%r12,56(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rax,%r12			# T1+=h

	mov	%rbx,%rax
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rbx,%r13
	mov	%rbx,%r14

	ror	$28,%rax
	ror	$34,%r13
	mov	%rbx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rax
	ror	$5,%r13
	or	%rdx,%r14			# a|c

	xor	%r13,%rax			# h=Sigma0(a)
	and	%rdx,%r15			# a&c
	add	%r12,%r8			# d+=T1

	and	%rcx,%r14			# (a|c)&b
	add	%r12,%rax			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rax			# h+=Maj(a,b,c)
	mov	8*8(%rsi),%r12
	bswap	%r12
	mov	%r8,%r13
	mov	%r8,%r14
	mov	%r9,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r10,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r8,%r15			# (f^g)&e
	mov	%r12,64(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r11,%r12			# T1+=h

	mov	%rax,%r11
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rax,%r13
	mov	%rax,%r14

	ror	$28,%r11
	ror	$34,%r13
	mov	%rax,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r11
	ror	$5,%r13
	or	%rcx,%r14			# a|c

	xor	%r13,%r11			# h=Sigma0(a)
	and	%rcx,%r15			# a&c
	add	%r12,%rdx			# d+=T1

	and	%rbx,%r14			# (a|c)&b
	add	%r12,%r11			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r11			# h+=Maj(a,b,c)
	mov	8*9(%rsi),%r12
	bswap	%r12
	mov	%rdx,%r13
	mov	%rdx,%r14
	mov	%r8,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r9,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rdx,%r15			# (f^g)&e
	mov	%r12,72(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r10,%r12			# T1+=h

	mov	%r11,%r10
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r11,%r13
	mov	%r11,%r14

	ror	$28,%r10
	ror	$34,%r13
	mov	%r11,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r10
	ror	$5,%r13
	or	%rbx,%r14			# a|c

	xor	%r13,%r10			# h=Sigma0(a)
	and	%rbx,%r15			# a&c
	add	%r12,%rcx			# d+=T1

	and	%rax,%r14			# (a|c)&b
	add	%r12,%r10			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r10			# h+=Maj(a,b,c)
	mov	8*10(%rsi),%r12
	bswap	%r12
	mov	%rcx,%r13
	mov	%rcx,%r14
	mov	%rdx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r8,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rcx,%r15			# (f^g)&e
	mov	%r12,80(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r9,%r12			# T1+=h

	mov	%r10,%r9
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r10,%r13
	mov	%r10,%r14

	ror	$28,%r9
	ror	$34,%r13
	mov	%r10,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r9
	ror	$5,%r13
	or	%rax,%r14			# a|c

	xor	%r13,%r9			# h=Sigma0(a)
	and	%rax,%r15			# a&c
	add	%r12,%rbx			# d+=T1

	and	%r11,%r14			# (a|c)&b
	add	%r12,%r9			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r9			# h+=Maj(a,b,c)
	mov	8*11(%rsi),%r12
	bswap	%r12
	mov	%rbx,%r13
	mov	%rbx,%r14
	mov	%rcx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rdx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rbx,%r15			# (f^g)&e
	mov	%r12,88(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r8,%r12			# T1+=h

	mov	%r9,%r8
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r9,%r13
	mov	%r9,%r14

	ror	$28,%r8
	ror	$34,%r13
	mov	%r9,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r8
	ror	$5,%r13
	or	%r11,%r14			# a|c

	xor	%r13,%r8			# h=Sigma0(a)
	and	%r11,%r15			# a&c
	add	%r12,%rax			# d+=T1

	and	%r10,%r14			# (a|c)&b
	add	%r12,%r8			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r8			# h+=Maj(a,b,c)
	mov	8*12(%rsi),%r12
	bswap	%r12
	mov	%rax,%r13
	mov	%rax,%r14
	mov	%rbx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rcx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rax,%r15			# (f^g)&e
	mov	%r12,96(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rdx,%r12			# T1+=h

	mov	%r8,%rdx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r8,%r13
	mov	%r8,%r14

	ror	$28,%rdx
	ror	$34,%r13
	mov	%r8,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rdx
	ror	$5,%r13
	or	%r10,%r14			# a|c

	xor	%r13,%rdx			# h=Sigma0(a)
	and	%r10,%r15			# a&c
	add	%r12,%r11			# d+=T1

	and	%r9,%r14			# (a|c)&b
	add	%r12,%rdx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rdx			# h+=Maj(a,b,c)
	mov	8*13(%rsi),%r12
	bswap	%r12
	mov	%r11,%r13
	mov	%r11,%r14
	mov	%rax,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rbx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r11,%r15			# (f^g)&e
	mov	%r12,104(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rcx,%r12			# T1+=h

	mov	%rdx,%rcx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rdx,%r13
	mov	%rdx,%r14

	ror	$28,%rcx
	ror	$34,%r13
	mov	%rdx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rcx
	ror	$5,%r13
	or	%r9,%r14			# a|c

	xor	%r13,%rcx			# h=Sigma0(a)
	and	%r9,%r15			# a&c
	add	%r12,%r10			# d+=T1

	and	%r8,%r14			# (a|c)&b
	add	%r12,%rcx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rcx			# h+=Maj(a,b,c)
	mov	8*14(%rsi),%r12
	bswap	%r12
	mov	%r10,%r13
	mov	%r10,%r14
	mov	%r11,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rax,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r10,%r15			# (f^g)&e
	mov	%r12,112(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rbx,%r12			# T1+=h

	mov	%rcx,%rbx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rcx,%r13
	mov	%rcx,%r14

	ror	$28,%rbx
	ror	$34,%r13
	mov	%rcx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rbx
	ror	$5,%r13
	or	%r8,%r14			# a|c

	xor	%r13,%rbx			# h=Sigma0(a)
	and	%r8,%r15			# a&c
	add	%r12,%r9			# d+=T1

	and	%rdx,%r14			# (a|c)&b
	add	%r12,%rbx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rbx			# h+=Maj(a,b,c)
	mov	8*15(%rsi),%r12
	bswap	%r12
	mov	%r9,%r13
	mov	%r9,%r14
	mov	%r10,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r11,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r9,%r15			# (f^g)&e
	mov	%r12,120(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rax,%r12			# T1+=h

	mov	%rbx,%rax
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rbx,%r13
	mov	%rbx,%r14

	ror	$28,%rax
	ror	$34,%r13
	mov	%rbx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rax
	ror	$5,%r13
	or	%rdx,%r14			# a|c

	xor	%r13,%rax			# h=Sigma0(a)
	and	%rdx,%r15			# a&c
	add	%r12,%r8			# d+=T1

	and	%rcx,%r14			# (a|c)&b
	add	%r12,%rax			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rax			# h+=Maj(a,b,c)
	jmp	.Lrounds_16_xx
.align	16
.Lrounds_16_xx:
	mov	8(%rsp),%r13
	mov	112(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	72(%rsp),%r12

	add	0(%rsp),%r12
	mov	%r8,%r13
	mov	%r8,%r14
	mov	%r9,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r10,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r8,%r15			# (f^g)&e
	mov	%r12,0(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r11,%r12			# T1+=h

	mov	%rax,%r11
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rax,%r13
	mov	%rax,%r14

	ror	$28,%r11
	ror	$34,%r13
	mov	%rax,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r11
	ror	$5,%r13
	or	%rcx,%r14			# a|c

	xor	%r13,%r11			# h=Sigma0(a)
	and	%rcx,%r15			# a&c
	add	%r12,%rdx			# d+=T1

	and	%rbx,%r14			# (a|c)&b
	add	%r12,%r11			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r11			# h+=Maj(a,b,c)
	mov	16(%rsp),%r13
	mov	120(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	80(%rsp),%r12

	add	8(%rsp),%r12
	mov	%rdx,%r13
	mov	%rdx,%r14
	mov	%r8,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r9,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rdx,%r15			# (f^g)&e
	mov	%r12,8(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r10,%r12			# T1+=h

	mov	%r11,%r10
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r11,%r13
	mov	%r11,%r14

	ror	$28,%r10
	ror	$34,%r13
	mov	%r11,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r10
	ror	$5,%r13
	or	%rbx,%r14			# a|c

	xor	%r13,%r10			# h=Sigma0(a)
	and	%rbx,%r15			# a&c
	add	%r12,%rcx			# d+=T1

	and	%rax,%r14			# (a|c)&b
	add	%r12,%r10			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r10			# h+=Maj(a,b,c)
	mov	24(%rsp),%r13
	mov	0(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	88(%rsp),%r12

	add	16(%rsp),%r12
	mov	%rcx,%r13
	mov	%rcx,%r14
	mov	%rdx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r8,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rcx,%r15			# (f^g)&e
	mov	%r12,16(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r9,%r12			# T1+=h

	mov	%r10,%r9
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r10,%r13
	mov	%r10,%r14

	ror	$28,%r9
	ror	$34,%r13
	mov	%r10,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r9
	ror	$5,%r13
	or	%rax,%r14			# a|c

	xor	%r13,%r9			# h=Sigma0(a)
	and	%rax,%r15			# a&c
	add	%r12,%rbx			# d+=T1

	and	%r11,%r14			# (a|c)&b
	add	%r12,%r9			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r9			# h+=Maj(a,b,c)
	mov	32(%rsp),%r13
	mov	8(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	96(%rsp),%r12

	add	24(%rsp),%r12
	mov	%rbx,%r13
	mov	%rbx,%r14
	mov	%rcx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rdx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rbx,%r15			# (f^g)&e
	mov	%r12,24(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r8,%r12			# T1+=h

	mov	%r9,%r8
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r9,%r13
	mov	%r9,%r14

	ror	$28,%r8
	ror	$34,%r13
	mov	%r9,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r8
	ror	$5,%r13
	or	%r11,%r14			# a|c

	xor	%r13,%r8			# h=Sigma0(a)
	and	%r11,%r15			# a&c
	add	%r12,%rax			# d+=T1

	and	%r10,%r14			# (a|c)&b
	add	%r12,%r8			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r8			# h+=Maj(a,b,c)
	mov	40(%rsp),%r13
	mov	16(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	104(%rsp),%r12

	add	32(%rsp),%r12
	mov	%rax,%r13
	mov	%rax,%r14
	mov	%rbx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rcx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rax,%r15			# (f^g)&e
	mov	%r12,32(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rdx,%r12			# T1+=h

	mov	%r8,%rdx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r8,%r13
	mov	%r8,%r14

	ror	$28,%rdx
	ror	$34,%r13
	mov	%r8,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rdx
	ror	$5,%r13
	or	%r10,%r14			# a|c

	xor	%r13,%rdx			# h=Sigma0(a)
	and	%r10,%r15			# a&c
	add	%r12,%r11			# d+=T1

	and	%r9,%r14			# (a|c)&b
	add	%r12,%rdx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rdx			# h+=Maj(a,b,c)
	mov	48(%rsp),%r13
	mov	24(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	112(%rsp),%r12

	add	40(%rsp),%r12
	mov	%r11,%r13
	mov	%r11,%r14
	mov	%rax,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rbx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r11,%r15			# (f^g)&e
	mov	%r12,40(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rcx,%r12			# T1+=h

	mov	%rdx,%rcx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rdx,%r13
	mov	%rdx,%r14

	ror	$28,%rcx
	ror	$34,%r13
	mov	%rdx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rcx
	ror	$5,%r13
	or	%r9,%r14			# a|c

	xor	%r13,%rcx			# h=Sigma0(a)
	and	%r9,%r15			# a&c
	add	%r12,%r10			# d+=T1

	and	%r8,%r14			# (a|c)&b
	add	%r12,%rcx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rcx			# h+=Maj(a,b,c)
	mov	56(%rsp),%r13
	mov	32(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	120(%rsp),%r12

	add	48(%rsp),%r12
	mov	%r10,%r13
	mov	%r10,%r14
	mov	%r11,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rax,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r10,%r15			# (f^g)&e
	mov	%r12,48(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rbx,%r12			# T1+=h

	mov	%rcx,%rbx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rcx,%r13
	mov	%rcx,%r14

	ror	$28,%rbx
	ror	$34,%r13
	mov	%rcx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rbx
	ror	$5,%r13
	or	%r8,%r14			# a|c

	xor	%r13,%rbx			# h=Sigma0(a)
	and	%r8,%r15			# a&c
	add	%r12,%r9			# d+=T1

	and	%rdx,%r14			# (a|c)&b
	add	%r12,%rbx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rbx			# h+=Maj(a,b,c)
	mov	64(%rsp),%r13
	mov	40(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	0(%rsp),%r12

	add	56(%rsp),%r12
	mov	%r9,%r13
	mov	%r9,%r14
	mov	%r10,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r11,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r9,%r15			# (f^g)&e
	mov	%r12,56(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rax,%r12			# T1+=h

	mov	%rbx,%rax
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rbx,%r13
	mov	%rbx,%r14

	ror	$28,%rax
	ror	$34,%r13
	mov	%rbx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rax
	ror	$5,%r13
	or	%rdx,%r14			# a|c

	xor	%r13,%rax			# h=Sigma0(a)
	and	%rdx,%r15			# a&c
	add	%r12,%r8			# d+=T1

	and	%rcx,%r14			# (a|c)&b
	add	%r12,%rax			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rax			# h+=Maj(a,b,c)
	mov	72(%rsp),%r13
	mov	48(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	8(%rsp),%r12

	add	64(%rsp),%r12
	mov	%r8,%r13
	mov	%r8,%r14
	mov	%r9,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r10,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r8,%r15			# (f^g)&e
	mov	%r12,64(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r11,%r12			# T1+=h

	mov	%rax,%r11
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rax,%r13
	mov	%rax,%r14

	ror	$28,%r11
	ror	$34,%r13
	mov	%rax,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r11
	ror	$5,%r13
	or	%rcx,%r14			# a|c

	xor	%r13,%r11			# h=Sigma0(a)
	and	%rcx,%r15			# a&c
	add	%r12,%rdx			# d+=T1

	and	%rbx,%r14			# (a|c)&b
	add	%r12,%r11			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r11			# h+=Maj(a,b,c)
	mov	80(%rsp),%r13
	mov	56(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	16(%rsp),%r12

	add	72(%rsp),%r12
	mov	%rdx,%r13
	mov	%rdx,%r14
	mov	%r8,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r9,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rdx,%r15			# (f^g)&e
	mov	%r12,72(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r10,%r12			# T1+=h

	mov	%r11,%r10
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r11,%r13
	mov	%r11,%r14

	ror	$28,%r10
	ror	$34,%r13
	mov	%r11,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r10
	ror	$5,%r13
	or	%rbx,%r14			# a|c

	xor	%r13,%r10			# h=Sigma0(a)
	and	%rbx,%r15			# a&c
	add	%r12,%rcx			# d+=T1

	and	%rax,%r14			# (a|c)&b
	add	%r12,%r10			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r10			# h+=Maj(a,b,c)
	mov	88(%rsp),%r13
	mov	64(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	24(%rsp),%r12

	add	80(%rsp),%r12
	mov	%rcx,%r13
	mov	%rcx,%r14
	mov	%rdx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r8,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rcx,%r15			# (f^g)&e
	mov	%r12,80(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r9,%r12			# T1+=h

	mov	%r10,%r9
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r10,%r13
	mov	%r10,%r14

	ror	$28,%r9
	ror	$34,%r13
	mov	%r10,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r9
	ror	$5,%r13
	or	%rax,%r14			# a|c

	xor	%r13,%r9			# h=Sigma0(a)
	and	%rax,%r15			# a&c
	add	%r12,%rbx			# d+=T1

	and	%r11,%r14			# (a|c)&b
	add	%r12,%r9			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r9			# h+=Maj(a,b,c)
	mov	96(%rsp),%r13
	mov	72(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	32(%rsp),%r12

	add	88(%rsp),%r12
	mov	%rbx,%r13
	mov	%rbx,%r14
	mov	%rcx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rdx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rbx,%r15			# (f^g)&e
	mov	%r12,88(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%r8,%r12			# T1+=h

	mov	%r9,%r8
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r9,%r13
	mov	%r9,%r14

	ror	$28,%r8
	ror	$34,%r13
	mov	%r9,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%r8
	ror	$5,%r13
	or	%r11,%r14			# a|c

	xor	%r13,%r8			# h=Sigma0(a)
	and	%r11,%r15			# a&c
	add	%r12,%rax			# d+=T1

	and	%r10,%r14			# (a|c)&b
	add	%r12,%r8			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%r8			# h+=Maj(a,b,c)
	mov	104(%rsp),%r13
	mov	80(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	40(%rsp),%r12

	add	96(%rsp),%r12
	mov	%rax,%r13
	mov	%rax,%r14
	mov	%rbx,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rcx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%rax,%r15			# (f^g)&e
	mov	%r12,96(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rdx,%r12			# T1+=h

	mov	%r8,%rdx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%r8,%r13
	mov	%r8,%r14

	ror	$28,%rdx
	ror	$34,%r13
	mov	%r8,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rdx
	ror	$5,%r13
	or	%r10,%r14			# a|c

	xor	%r13,%rdx			# h=Sigma0(a)
	and	%r10,%r15			# a&c
	add	%r12,%r11			# d+=T1

	and	%r9,%r14			# (a|c)&b
	add	%r12,%rdx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rdx			# h+=Maj(a,b,c)
	mov	112(%rsp),%r13
	mov	88(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	48(%rsp),%r12

	add	104(%rsp),%r12
	mov	%r11,%r13
	mov	%r11,%r14
	mov	%rax,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rbx,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r11,%r15			# (f^g)&e
	mov	%r12,104(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rcx,%r12			# T1+=h

	mov	%rdx,%rcx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rdx,%r13
	mov	%rdx,%r14

	ror	$28,%rcx
	ror	$34,%r13
	mov	%rdx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rcx
	ror	$5,%r13
	or	%r9,%r14			# a|c

	xor	%r13,%rcx			# h=Sigma0(a)
	and	%r9,%r15			# a&c
	add	%r12,%r10			# d+=T1

	and	%r8,%r14			# (a|c)&b
	add	%r12,%rcx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rcx			# h+=Maj(a,b,c)
	mov	120(%rsp),%r13
	mov	96(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	56(%rsp),%r12

	add	112(%rsp),%r12
	mov	%r10,%r13
	mov	%r10,%r14
	mov	%r11,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%rax,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r10,%r15			# (f^g)&e
	mov	%r12,112(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rbx,%r12			# T1+=h

	mov	%rcx,%rbx
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rcx,%r13
	mov	%rcx,%r14

	ror	$28,%rbx
	ror	$34,%r13
	mov	%rcx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rbx
	ror	$5,%r13
	or	%r8,%r14			# a|c

	xor	%r13,%rbx			# h=Sigma0(a)
	and	%r8,%r15			# a&c
	add	%r12,%r9			# d+=T1

	and	%rdx,%r14			# (a|c)&b
	add	%r12,%rbx			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rbx			# h+=Maj(a,b,c)
	mov	0(%rsp),%r13
	mov	104(%rsp),%r12

	mov	%r13,%r15

	shr	$7,%r13
	ror	$1,%r15

	xor	%r15,%r13
	ror	$7,%r15

	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
	mov	%r12,%r14

	shr	$6,%r12
	ror	$19,%r14

	xor	%r14,%r12
	ror	$42,%r14

	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])

	add	%r13,%r12

	add	64(%rsp),%r12

	add	120(%rsp),%r12
	mov	%r9,%r13
	mov	%r9,%r14
	mov	%r10,%r15

	ror	$14,%r13
	ror	$18,%r14
	xor	%r11,%r15			# f^g

	xor	%r14,%r13
	ror	$23,%r14
	and	%r9,%r15			# (f^g)&e
	mov	%r12,120(%rsp)

	xor	%r14,%r13			# Sigma1(e)
	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
	add	%rax,%r12			# T1+=h

	mov	%rbx,%rax
	add	%r13,%r12			# T1+=Sigma1(e)

	add	%r15,%r12			# T1+=Ch(e,f,g)
	mov	%rbx,%r13
	mov	%rbx,%r14

	ror	$28,%rax
	ror	$34,%r13
	mov	%rbx,%r15
	add	(%rbp,%rdi,8),%r12	# T1+=K[round]

	xor	%r13,%rax
	ror	$5,%r13
	or	%rdx,%r14			# a|c

	xor	%r13,%rax			# h=Sigma0(a)
	and	%rdx,%r15			# a&c
	add	%r12,%r8			# d+=T1

	and	%rcx,%r14			# (a|c)&b
	add	%r12,%rax			# h+=T1

	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
	lea	1(%rdi),%rdi	# round++

	add	%r14,%rax			# h+=Maj(a,b,c)
	cmp	$80,%rdi
	jb	.Lrounds_16_xx

	mov	16*8+0*8(%rsp),%rdi
	lea	16*8(%rsi),%rsi

	add	8*0(%rdi),%rax
	add	8*1(%rdi),%rbx
	add	8*2(%rdi),%rcx
	add	8*3(%rdi),%rdx
	add	8*4(%rdi),%r8
	add	8*5(%rdi),%r9
	add	8*6(%rdi),%r10
	add	8*7(%rdi),%r11

	cmp	16*8+2*8(%rsp),%rsi

	mov	%rax,8*0(%rdi)
	mov	%rbx,8*1(%rdi)
	mov	%rcx,8*2(%rdi)
	mov	%rdx,8*3(%rdi)
	mov	%r8,8*4(%rdi)
	mov	%r9,8*5(%rdi)
	mov	%r10,8*6(%rdi)
	mov	%r11,8*7(%rdi)
	jb	.Lloop

	mov	16*8+3*8(%rsp),%rsp
.cfi_def_cfa	%rsp,56
	pop	%r15
.cfi_adjust_cfa_offset -8
.cfi_restore	%r15
	pop	%r14
.cfi_adjust_cfa_offset -8
.cfi_restore	%r14
	pop	%r13
.cfi_adjust_cfa_offset -8
.cfi_restore	%r13
	pop	%r12
.cfi_adjust_cfa_offset -8
.cfi_restore	%r12
	pop	%rbp
.cfi_adjust_cfa_offset -8
.cfi_restore	%rbp
	pop	%rbx
.cfi_adjust_cfa_offset -8
.cfi_restore	%rbx

	RET
.cfi_endproc
SET_SIZE(SHA512TransformBlocks)

.data
.align	64
.type	K512,@object
K512:
	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
	.quad	0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
	.quad	0x3956c25bf348b538,0x59f111f1b605d019
	.quad	0x923f82a4af194f9b,0xab1c5ed5da6d8118
	.quad	0xd807aa98a3030242,0x12835b0145706fbe
	.quad	0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
	.quad	0x72be5d74f27b896f,0x80deb1fe3b1696b1
	.quad	0x9bdc06a725c71235,0xc19bf174cf692694
	.quad	0xe49b69c19ef14ad2,0xefbe4786384f25e3
	.quad	0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
	.quad	0x2de92c6f592b0275,0x4a7484aa6ea6e483
	.quad	0x5cb0a9dcbd41fbd4,0x76f988da831153b5
	.quad	0x983e5152ee66dfab,0xa831c66d2db43210
	.quad	0xb00327c898fb213f,0xbf597fc7beef0ee4
	.quad	0xc6e00bf33da88fc2,0xd5a79147930aa725
	.quad	0x06ca6351e003826f,0x142929670a0e6e70
	.quad	0x27b70a8546d22ffc,0x2e1b21385c26c926
	.quad	0x4d2c6dfc5ac42aed,0x53380d139d95b3df
	.quad	0x650a73548baf63de,0x766a0abb3c77b2a8
	.quad	0x81c2c92e47edaee6,0x92722c851482353b
	.quad	0xa2bfe8a14cf10364,0xa81a664bbc423001
	.quad	0xc24b8b70d0f89791,0xc76c51a30654be30
	.quad	0xd192e819d6ef5218,0xd69906245565a910
	.quad	0xf40e35855771202a,0x106aa07032bbd1b8
	.quad	0x19a4c116b8d2d0c8,0x1e376c085141ab53
	.quad	0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
	.quad	0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
	.quad	0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
	.quad	0x748f82ee5defb2fc,0x78a5636f43172f60
	.quad	0x84c87814a1f0ab72,0x8cc702081a6439ec
	.quad	0x90befffa23631e28,0xa4506cebde82bde9
	.quad	0xbef9a3f7b2c67915,0xc67178f2e372532b
	.quad	0xca273eceea26619c,0xd186b8c721c0c207
	.quad	0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
	.quad	0x06f067aa72176fba,0x0a637dc5a2c898a6
	.quad	0x113f9804bef90dae,0x1b710b35131c471b
	.quad	0x28db77f523047d84,0x32caab7b40c72493
	.quad	0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
	.quad	0x4cc5d4becb3e42b6,0x597f299cfc657e2a
	.quad	0x5fcb6fab3ad6faec,0x6c44198c4a475817
#endif /* !lint && !__lint */

#ifdef __ELF__
.section .note.GNU-stack,"",%progbits
#endif