wolfssl/wolfcrypt/src/sha256_asm.S

/* sha256_asm
 *
 * Copyright (C) 2006-2022 wolfSSL Inc.
 *
 * This file is part of wolfSSL.
 *
 * wolfSSL is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * wolfSSL is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1335, USA
 */

#ifndef HAVE_INTEL_AVX1
#define HAVE_INTEL_AVX1
#endif /* HAVE_INTEL_AVX1 */
#ifndef NO_AVX2_SUPPORT
#define HAVE_INTEL_AVX2
#endif /* NO_AVX2_SUPPORT */

#ifdef HAVE_INTEL_AVX1
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
L_avx1_sha256_k:
.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long	0xe49b69c1,0xefbe4786,0xfc19dc6,0x240ca1cc
.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long	0xc6e00bf3,0xd5a79147,0x6ca6351,0x14292967
.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
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	16
#else
.p2align	4
#endif /* __APPLE__ */
L_avx1_sha256_shuf_00BA:
.quad	0xb0a090803020100, 0xffffffffffffffff
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	16
#else
.p2align	4
#endif /* __APPLE__ */
L_avx1_sha256_shuf_DC00:
.quad	0xffffffffffffffff, 0xb0a090803020100
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	16
#else
.p2align	4
#endif /* __APPLE__ */
L_avx1_sha256_flip_mask:
.quad	0x405060700010203, 0xc0d0e0f08090a0b
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX1
.type	Transform_Sha256_AVX1,@function
.align	16
Transform_Sha256_AVX1:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX1
.p2align	4
_Transform_Sha256_AVX1:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        subq	$0x40, %rsp
        leaq	32(%rdi), %rax
        vmovdqa	L_avx1_sha256_flip_mask(%rip), %xmm13
        vmovdqa	L_avx1_sha256_shuf_00BA(%rip), %xmm11
        vmovdqa	L_avx1_sha256_shuf_DC00(%rip), %xmm12
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rax), %xmm0
        vmovdqu	16(%rax), %xmm1
        vpshufb	%xmm13, %xmm0, %xmm0
        vpshufb	%xmm13, %xmm1, %xmm1
        vmovdqu	32(%rax), %xmm2
        vmovdqu	48(%rax), %xmm3
        vpshufb	%xmm13, %xmm2, %xmm2
        vpshufb	%xmm13, %xmm3, %xmm3
        movl	%r9d, %ebx
        movl	%r12d, %edx
        xorl	%r10d, %ebx
        # set_w_k_xfer_4: 0
        vpaddd	0+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	16+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	32+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	48+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	16(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	20(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	24(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	28(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	32(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	36(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	40(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	44(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	48(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	52(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	56(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	60(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 4
        vpaddd	64+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	80+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	96+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	112+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	16(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	20(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	24(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	28(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	32(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	36(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	40(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	44(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	48(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	52(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	56(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	60(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 8
        vpaddd	128+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	144+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	160+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	176+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	16(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	20(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	24(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	28(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	32(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	36(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	40(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	44(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	48(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	52(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	56(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	60(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 12
        vpaddd	192+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	208+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	224+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	240+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # rnd_all_4: 0-3
        addl	(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	4(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	8(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	12(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 1-4
        addl	16(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	20(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	24(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	28(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 2-5
        addl	32(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	36(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	40(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	44(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 3-6
        addl	48(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	52(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	56(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	60(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        addl	%r8d, (%rdi)
        addl	%r9d, 4(%rdi)
        addl	%r10d, 8(%rdi)
        addl	%r11d, 12(%rdi)
        addl	%r12d, 16(%rdi)
        addl	%r13d, 20(%rdi)
        addl	%r14d, 24(%rdi)
        addl	%r15d, 28(%rdi)
        xorq	%rax, %rax
        vzeroupper
        addq	$0x40, %rsp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX1,.-Transform_Sha256_AVX1
#endif /* __APPLE__ */
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX1_Len
.type	Transform_Sha256_AVX1_Len,@function
.align	16
Transform_Sha256_AVX1_Len:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX1_Len
.p2align	4
_Transform_Sha256_AVX1_Len:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        pushq	%rbp
        movq	%rsi, %rbp
        movq	%rdx, %rsi
        subq	$0x40, %rsp
        vmovdqa	L_avx1_sha256_flip_mask(%rip), %xmm13
        vmovdqa	L_avx1_sha256_shuf_00BA(%rip), %xmm11
        vmovdqa	L_avx1_sha256_shuf_DC00(%rip), %xmm12
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        # Start of loop processing a block
L_sha256_len_avx1_start:
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rbp), %xmm0
        vmovdqu	16(%rbp), %xmm1
        vpshufb	%xmm13, %xmm0, %xmm0
        vpshufb	%xmm13, %xmm1, %xmm1
        vmovdqu	32(%rbp), %xmm2
        vmovdqu	48(%rbp), %xmm3
        vpshufb	%xmm13, %xmm2, %xmm2
        vpshufb	%xmm13, %xmm3, %xmm3
        movl	%r9d, %ebx
        movl	%r12d, %edx
        xorl	%r10d, %ebx
        # set_w_k_xfer_4: 0
        vpaddd	0+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	16+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	32+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	48+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	16(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	20(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	24(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	28(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	32(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	36(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	40(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	44(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	48(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	52(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	56(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	60(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 4
        vpaddd	64+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	80+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	96+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	112+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	16(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	20(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	24(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	28(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	32(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	36(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	40(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	44(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	48(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	52(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	56(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	60(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 8
        vpaddd	128+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	144+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	160+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	176+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	16(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	20(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	24(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	28(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	32(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	36(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	40(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	44(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	48(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %xmm5, %xmm8
        vpslld	$14, %xmm5, %xmm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%xmm6, %xmm7, %xmm6
        vpor	%xmm8, %xmm9, %xmm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	52(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %xmm5, %xmm9
        vpxor	%xmm6, %xmm8, %xmm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%xmm6, %xmm9, %xmm5
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	56(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%xmm6, %xmm7, %xmm6
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	60(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %xmm6, %xmm8
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %xmm6, %xmm9
        vpxor	%xmm8, %xmm7, %xmm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%xmm9, %xmm8, %xmm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 12
        vpaddd	192+L_avx1_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	208+L_avx1_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	224+L_avx1_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	240+L_avx1_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # rnd_all_4: 0-3
        addl	(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	4(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	8(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	12(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 1-4
        addl	16(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	20(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	24(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	28(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 2-5
        addl	32(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	36(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	40(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	44(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 3-6
        addl	48(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	52(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	56(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	60(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        addl	(%rdi), %r8d
        addl	4(%rdi), %r9d
        addl	8(%rdi), %r10d
        addl	12(%rdi), %r11d
        addl	16(%rdi), %r12d
        addl	20(%rdi), %r13d
        addl	24(%rdi), %r14d
        addl	28(%rdi), %r15d
        addq	$0x40, %rbp
        subl	$0x40, %esi
        movl	%r8d, (%rdi)
        movl	%r9d, 4(%rdi)
        movl	%r10d, 8(%rdi)
        movl	%r11d, 12(%rdi)
        movl	%r12d, 16(%rdi)
        movl	%r13d, 20(%rdi)
        movl	%r14d, 24(%rdi)
        movl	%r15d, 28(%rdi)
        jnz	L_sha256_len_avx1_start
        xorq	%rax, %rax
        vzeroupper
        addq	$0x40, %rsp
        popq	%rbp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX1_Len,.-Transform_Sha256_AVX1_Len
#endif /* __APPLE__ */
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
L_avx1_rorx_sha256_k:
.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long	0xe49b69c1,0xefbe4786,0xfc19dc6,0x240ca1cc
.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long	0xc6e00bf3,0xd5a79147,0x6ca6351,0x14292967
.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
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	16
#else
.p2align	4
#endif /* __APPLE__ */
L_avx1_rorx_sha256_shuf_00BA:
.quad	0xb0a090803020100, 0xffffffffffffffff
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	16
#else
.p2align	4
#endif /* __APPLE__ */
L_avx1_rorx_sha256_shuf_DC00:
.quad	0xffffffffffffffff, 0xb0a090803020100
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	16
#else
.p2align	4
#endif /* __APPLE__ */
L_avx1_rorx_sha256_flip_mask:
.quad	0x405060700010203, 0xc0d0e0f08090a0b
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX1_RORX
.type	Transform_Sha256_AVX1_RORX,@function
.align	16
Transform_Sha256_AVX1_RORX:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX1_RORX
.p2align	4
_Transform_Sha256_AVX1_RORX:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        subq	$0x40, %rsp
        vmovdqa	L_avx1_rorx_sha256_flip_mask(%rip), %xmm13
        vmovdqa	L_avx1_rorx_sha256_shuf_00BA(%rip), %xmm11
        vmovdqa	L_avx1_rorx_sha256_shuf_DC00(%rip), %xmm12
        leaq	32(%rdi), %rax
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rax), %xmm0
        vmovdqu	16(%rax), %xmm1
        vpshufb	%xmm13, %xmm0, %xmm0
        vpshufb	%xmm13, %xmm1, %xmm1
        vmovdqu	32(%rax), %xmm2
        vmovdqu	48(%rax), %xmm3
        vpshufb	%xmm13, %xmm2, %xmm2
        vpshufb	%xmm13, %xmm3, %xmm3
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        # set_w_k_xfer_4: 0
        vpaddd	0+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	16+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	32+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	48+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        movl	%r9d, %ebx
        rorxl	$6, %r12d, %edx
        xorl	%r10d, %ebx
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	16(%rsp), %r11d
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	20(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	24(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	28(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	32(%rsp), %r15d
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	36(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	40(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	44(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	48(%rsp), %r11d
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	52(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	56(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	60(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 4
        vpaddd	64+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	80+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	96+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	112+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	16(%rsp), %r11d
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	20(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	24(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	28(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	32(%rsp), %r15d
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	36(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	40(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	44(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	48(%rsp), %r11d
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	52(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	56(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	60(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 8
        vpaddd	128+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	144+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	160+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	176+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	16(%rsp), %r11d
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	20(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	24(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	28(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	32(%rsp), %r15d
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	36(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	40(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	44(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	48(%rsp), %r11d
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	52(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	56(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	60(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 12
        vpaddd	192+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	208+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	224+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	240+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        xorl	%eax, %eax
        # rnd_all_4: 0-3
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        addl	%eax, %r8d
        addl	(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	4(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        addl	%eax, %r14d
        addl	8(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	12(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        # rnd_all_4: 1-4
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        addl	%eax, %r12d
        addl	16(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	20(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        addl	%eax, %r10d
        addl	24(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	28(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        # rnd_all_4: 2-5
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        addl	%eax, %r8d
        addl	32(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	36(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        addl	%eax, %r14d
        addl	40(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	44(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        # rnd_all_4: 3-6
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        addl	%eax, %r12d
        addl	48(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	52(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        addl	%eax, %r10d
        addl	56(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	60(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        addl	%eax, %r8d
        addl	%r8d, (%rdi)
        addl	%r9d, 4(%rdi)
        addl	%r10d, 8(%rdi)
        addl	%r11d, 12(%rdi)
        addl	%r12d, 16(%rdi)
        addl	%r13d, 20(%rdi)
        addl	%r14d, 24(%rdi)
        addl	%r15d, 28(%rdi)
        xorq	%rax, %rax
        vzeroupper
        addq	$0x40, %rsp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX1_RORX,.-Transform_Sha256_AVX1_RORX
#endif /* __APPLE__ */
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX1_RORX_Len
.type	Transform_Sha256_AVX1_RORX_Len,@function
.align	16
Transform_Sha256_AVX1_RORX_Len:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX1_RORX_Len
.p2align	4
_Transform_Sha256_AVX1_RORX_Len:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        pushq	%rbp
        movq	%rsi, %rbp
        movq	%rdx, %rsi
        subq	$0x40, %rsp
        vmovdqa	L_avx1_rorx_sha256_flip_mask(%rip), %xmm13
        vmovdqa	L_avx1_rorx_sha256_shuf_00BA(%rip), %xmm11
        vmovdqa	L_avx1_rorx_sha256_shuf_DC00(%rip), %xmm12
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        # Start of loop processing a block
L_sha256_len_avx1_len_rorx_start:
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rbp), %xmm0
        vmovdqu	16(%rbp), %xmm1
        vpshufb	%xmm13, %xmm0, %xmm0
        vpshufb	%xmm13, %xmm1, %xmm1
        vmovdqu	32(%rbp), %xmm2
        vmovdqu	48(%rbp), %xmm3
        vpshufb	%xmm13, %xmm2, %xmm2
        vpshufb	%xmm13, %xmm3, %xmm3
        # set_w_k_xfer_4: 0
        vpaddd	0+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	16+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	32+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	48+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        movl	%r9d, %ebx
        rorxl	$6, %r12d, %edx
        xorl	%r10d, %ebx
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	16(%rsp), %r11d
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	20(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	24(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	28(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	32(%rsp), %r15d
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	36(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	40(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	44(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	48(%rsp), %r11d
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	52(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	56(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	60(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 4
        vpaddd	64+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	80+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	96+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	112+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	16(%rsp), %r11d
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	20(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	24(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	28(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	32(%rsp), %r15d
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	36(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	40(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	44(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	48(%rsp), %r11d
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	52(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	56(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	60(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 8
        vpaddd	128+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	144+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	160+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	176+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %xmm2, %xmm3, %xmm4
        vpalignr	$4, %xmm0, %xmm1, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm3, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm0, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm0
        # msg_sched done: 0-3
        # msg_sched: 4-7
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	16(%rsp), %r11d
        vpalignr	$4, %xmm3, %xmm0, %xmm4
        vpalignr	$4, %xmm1, %xmm2, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	20(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm0, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	24(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm1, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	28(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm1
        # msg_sched done: 4-7
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	32(%rsp), %r15d
        vpalignr	$4, %xmm0, %xmm1, %xmm4
        vpalignr	$4, %xmm2, %xmm3, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	36(%rsp), %r14d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpshufd	$0xfa, %xmm1, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	40(%rsp), %r13d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm2, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	44(%rsp), %r12d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vpaddd	%xmm4, %xmm9, %xmm2
        # msg_sched done: 8-11
        # msg_sched: 12-15
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	48(%rsp), %r11d
        vpalignr	$4, %xmm1, %xmm2, %xmm4
        vpalignr	$4, %xmm3, %xmm0, %xmm5
        # rnd_0: 1 - 2
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %xmm5, %xmm6
        vpslld	$25, %xmm5, %xmm7
        # rnd_0: 3 - 4
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$3, %xmm5, %xmm8
        vpor	%xmm6, %xmm7, %xmm7
        # rnd_0: 5 - 7
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	52(%rsp), %r10d
        vpsrld	$18, %xmm5, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpslld	$14, %xmm5, %xmm5
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpxor	%xmm5, %xmm7, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%xmm6, %xmm7, %xmm7
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpshufd	$0xfa, %xmm2, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        vpxor	%xmm8, %xmm7, %xmm5
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrld	$10, %xmm6, %xmm8
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	56(%rsp), %r9d
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpsrlq	$0x11, %xmm6, %xmm6
        vpaddd	%xmm3, %xmm4, %xmm4
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%xmm5, %xmm4, %xmm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpxor	%xmm6, %xmm8, %xmm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufb	%xmm11, %xmm8, %xmm8
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpaddd	%xmm8, %xmm4, %xmm4
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	60(%rsp), %r8d
        vpshufd	$0x50, %xmm4, %xmm6
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpsrld	$10, %xmm6, %xmm9
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpsrlq	$19, %xmm6, %xmm7
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpsrlq	$0x11, %xmm6, %xmm6
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpxor	%xmm7, %xmm6, %xmm6
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        vpxor	%xmm6, %xmm9, %xmm9
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        vpshufb	%xmm12, %xmm9, %xmm9
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vpaddd	%xmm4, %xmm9, %xmm3
        # msg_sched done: 12-15
        # set_w_k_xfer_4: 12
        vpaddd	192+L_avx1_rorx_sha256_k(%rip), %xmm0, %xmm4
        vpaddd	208+L_avx1_rorx_sha256_k(%rip), %xmm1, %xmm5
        vmovdqu	%xmm4, (%rsp)
        vmovdqu	%xmm5, 16(%rsp)
        vpaddd	224+L_avx1_rorx_sha256_k(%rip), %xmm2, %xmm6
        vpaddd	240+L_avx1_rorx_sha256_k(%rip), %xmm3, %xmm7
        vmovdqu	%xmm6, 32(%rsp)
        vmovdqu	%xmm7, 48(%rsp)
        xorl	%eax, %eax
        xorl	%ecx, %ecx
        # rnd_all_4: 0-3
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        addl	%eax, %r8d
        addl	(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	4(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        addl	%eax, %r14d
        addl	8(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	12(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        # rnd_all_4: 1-4
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        addl	%eax, %r12d
        addl	16(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	20(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        addl	%eax, %r10d
        addl	24(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	28(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        # rnd_all_4: 2-5
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        addl	%eax, %r8d
        addl	32(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	36(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        addl	%r14d, %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        addl	%eax, %r14d
        addl	40(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	44(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        addl	%r12d, %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        # rnd_all_4: 3-6
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        addl	%eax, %r12d
        addl	48(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	52(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        addl	%r10d, %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        addl	%eax, %r10d
        addl	56(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	60(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        addl	%r8d, %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        addl	%eax, %r8d
        addl	(%rdi), %r8d
        addl	4(%rdi), %r9d
        addl	8(%rdi), %r10d
        addl	12(%rdi), %r11d
        addl	16(%rdi), %r12d
        addl	20(%rdi), %r13d
        addl	24(%rdi), %r14d
        addl	28(%rdi), %r15d
        addq	$0x40, %rbp
        subl	$0x40, %esi
        movl	%r8d, (%rdi)
        movl	%r9d, 4(%rdi)
        movl	%r10d, 8(%rdi)
        movl	%r11d, 12(%rdi)
        movl	%r12d, 16(%rdi)
        movl	%r13d, 20(%rdi)
        movl	%r14d, 24(%rdi)
        movl	%r15d, 28(%rdi)
        jnz	L_sha256_len_avx1_len_rorx_start
        xorq	%rax, %rax
        vzeroupper
        addq	$0x40, %rsp
        popq	%rbp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX1_RORX_Len,.-Transform_Sha256_AVX1_RORX_Len
#endif /* __APPLE__ */
#endif /* HAVE_INTEL_AVX1 */
#ifdef HAVE_INTEL_AVX2
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
L_avx2_sha256_k:
.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long	0xe49b69c1,0xefbe4786,0xfc19dc6,0x240ca1cc
.long	0xe49b69c1,0xefbe4786,0xfc19dc6,0x240ca1cc
.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long	0xc6e00bf3,0xd5a79147,0x6ca6351,0x14292967
.long	0xc6e00bf3,0xd5a79147,0x6ca6351,0x14292967
.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	32
#else
.p2align	5
#endif /* __APPLE__ */
L_avx2_sha256_shuf_00BA:
.quad	0xb0a090803020100, 0xffffffffffffffff
.quad	0xb0a090803020100, 0xffffffffffffffff
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	32
#else
.p2align	5
#endif /* __APPLE__ */
L_avx2_sha256_shuf_DC00:
.quad	0xffffffffffffffff, 0xb0a090803020100
.quad	0xffffffffffffffff, 0xb0a090803020100
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	32
#else
.p2align	5
#endif /* __APPLE__ */
L_avx2_sha256_flip_mask:
.quad	0x405060700010203, 0xc0d0e0f08090a0b
.quad	0x405060700010203, 0xc0d0e0f08090a0b
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX2
.type	Transform_Sha256_AVX2,@function
.align	16
Transform_Sha256_AVX2:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX2
.p2align	4
_Transform_Sha256_AVX2:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        subq	$0x200, %rsp
        leaq	32(%rdi), %rax
        vmovdqa	L_avx2_sha256_flip_mask(%rip), %xmm13
        vmovdqa	L_avx2_sha256_shuf_00BA(%rip), %ymm11
        vmovdqa	L_avx2_sha256_shuf_DC00(%rip), %ymm12
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rax), %xmm0
        vmovdqu	16(%rax), %xmm1
        vpshufb	%xmm13, %xmm0, %xmm0
        vpshufb	%xmm13, %xmm1, %xmm1
        vmovdqu	32(%rax), %xmm2
        vmovdqu	48(%rax), %xmm3
        vpshufb	%xmm13, %xmm2, %xmm2
        vpshufb	%xmm13, %xmm3, %xmm3
        movl	%r9d, %ebx
        movl	%r12d, %edx
        xorl	%r10d, %ebx
        # set_w_k_xfer_4: 0
        vpaddd	0+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	32+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, (%rsp)
        vmovdqu	%ymm5, 32(%rsp)
        vpaddd	64+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	96+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 64(%rsp)
        vmovdqu	%ymm5, 96(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm3, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # msg_sched done: 0-3
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	32(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	36(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm0, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	40(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	44(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # msg_sched done: 8-11
        # msg_sched: 16-19
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	64(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	68(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm1, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	72(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	76(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # msg_sched done: 16-19
        # msg_sched: 24-27
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	96(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	100(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm2, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	104(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	108(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # msg_sched done: 24-27
        # set_w_k_xfer_4: 4
        vpaddd	128+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	160+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, 128(%rsp)
        vmovdqu	%ymm5, 160(%rsp)
        vpaddd	192+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	224+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 192(%rsp)
        vmovdqu	%ymm5, 224(%rsp)
        # msg_sched: 32-35
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	128(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	132(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm3, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	136(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	140(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # msg_sched done: 32-35
        # msg_sched: 40-43
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	160(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	164(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm0, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	168(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	172(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # msg_sched done: 40-43
        # msg_sched: 48-51
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	192(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	196(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm1, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	200(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	204(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # msg_sched done: 48-51
        # msg_sched: 56-59
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	224(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	228(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm2, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	232(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	236(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # msg_sched done: 56-59
        # set_w_k_xfer_4: 8
        vpaddd	256+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	288+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, 256(%rsp)
        vmovdqu	%ymm5, 288(%rsp)
        vpaddd	320+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	352+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 320(%rsp)
        vmovdqu	%ymm5, 352(%rsp)
        # msg_sched: 64-67
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	256(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	260(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm3, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	264(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	268(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # msg_sched done: 64-67
        # msg_sched: 72-75
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	288(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	292(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm0, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	296(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	300(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # msg_sched done: 72-75
        # msg_sched: 80-83
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	320(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	324(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm1, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	328(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	332(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # msg_sched done: 80-83
        # msg_sched: 88-91
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	352(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	356(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm2, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	360(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	364(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # msg_sched done: 88-91
        # set_w_k_xfer_4: 12
        vpaddd	384+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	416+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, 384(%rsp)
        vmovdqu	%ymm5, 416(%rsp)
        vpaddd	448+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	480+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 448(%rsp)
        vmovdqu	%ymm5, 480(%rsp)
        # rnd_all_4: 24-27
        addl	384(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	388(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	392(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	396(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 26-29
        addl	416(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	420(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	424(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	428(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 28-31
        addl	448(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	452(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	456(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	460(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 30-33
        addl	480(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	484(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	488(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	492(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        addl	%r8d, (%rdi)
        addl	%r9d, 4(%rdi)
        addl	%r10d, 8(%rdi)
        addl	%r11d, 12(%rdi)
        addl	%r12d, 16(%rdi)
        addl	%r13d, 20(%rdi)
        addl	%r14d, 24(%rdi)
        addl	%r15d, 28(%rdi)
        xorq	%rax, %rax
        vzeroupper
        addq	$0x200, %rsp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX2,.-Transform_Sha256_AVX2
#endif /* __APPLE__ */
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX2_Len
.type	Transform_Sha256_AVX2_Len,@function
.align	16
Transform_Sha256_AVX2_Len:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX2_Len
.p2align	4
_Transform_Sha256_AVX2_Len:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        pushq	%rbp
        movq	%rsi, %rbp
        movq	%rdx, %rsi
        subq	$0x200, %rsp
        testb	$0x40, %sil
        je	L_sha256_len_avx2_block
        vmovdqu	(%rbp), %ymm0
        vmovdqu	32(%rbp), %ymm1
        vmovups	%ymm0, 32(%rdi)
        vmovups	%ymm1, 64(%rdi)
#ifndef __APPLE__
        call	Transform_Sha256_AVX2@plt
#else
        call	_Transform_Sha256_AVX2
#endif /* __APPLE__ */
        addq	$0x40, %rbp
        subl	$0x40, %esi
        jz	L_sha256_len_avx2_done
L_sha256_len_avx2_block:
        vmovdqa	L_avx2_sha256_flip_mask(%rip), %ymm13
        vmovdqa	L_avx2_sha256_shuf_00BA(%rip), %ymm11
        vmovdqa	L_avx2_sha256_shuf_DC00(%rip), %ymm12
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        # Start of loop processing two blocks
L_sha256_len_avx2_start:
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rbp), %xmm0
        vmovdqu	16(%rbp), %xmm1
        vmovdqu	64(%rbp), %xmm4
        vmovdqu	80(%rbp), %xmm5
        vinserti128	$0x01, %xmm4, %ymm0, %ymm0
        vinserti128	$0x01, %xmm5, %ymm1, %ymm1
        vpshufb	%ymm13, %ymm0, %ymm0
        vpshufb	%ymm13, %ymm1, %ymm1
        vmovdqu	32(%rbp), %xmm2
        vmovdqu	48(%rbp), %xmm3
        vmovdqu	96(%rbp), %xmm6
        vmovdqu	112(%rbp), %xmm7
        vinserti128	$0x01, %xmm6, %ymm2, %ymm2
        vinserti128	$0x01, %xmm7, %ymm3, %ymm3
        vpshufb	%ymm13, %ymm2, %ymm2
        vpshufb	%ymm13, %ymm3, %ymm3
        movl	%r9d, %ebx
        movl	%r12d, %edx
        xorl	%r10d, %ebx
        # set_w_k_xfer_4: 0
        vpaddd	0+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	32+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, (%rsp)
        vmovdqu	%ymm5, 32(%rsp)
        vpaddd	64+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	96+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 64(%rsp)
        vmovdqu	%ymm5, 96(%rsp)
        # msg_sched: 0-3
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	4(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm3, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	8(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	12(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # msg_sched done: 0-3
        # msg_sched: 8-11
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	32(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	36(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm0, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	40(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	44(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # msg_sched done: 8-11
        # msg_sched: 16-19
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	64(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	68(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm1, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	72(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	76(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # msg_sched done: 16-19
        # msg_sched: 24-27
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	96(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	100(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm2, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	104(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	108(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # msg_sched done: 24-27
        # set_w_k_xfer_4: 4
        vpaddd	128+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	160+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, 128(%rsp)
        vmovdqu	%ymm5, 160(%rsp)
        vpaddd	192+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	224+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 192(%rsp)
        vmovdqu	%ymm5, 224(%rsp)
        # msg_sched: 32-35
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	128(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	132(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm3, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	136(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	140(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # msg_sched done: 32-35
        # msg_sched: 40-43
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	160(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	164(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm0, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	168(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	172(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # msg_sched done: 40-43
        # msg_sched: 48-51
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	192(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	196(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm1, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	200(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	204(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # msg_sched done: 48-51
        # msg_sched: 56-59
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	224(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	228(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm2, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	232(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	236(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # msg_sched done: 56-59
        # set_w_k_xfer_4: 8
        vpaddd	256+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	288+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, 256(%rsp)
        vmovdqu	%ymm5, 288(%rsp)
        vpaddd	320+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	352+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 320(%rsp)
        vmovdqu	%ymm5, 352(%rsp)
        # msg_sched: 64-67
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	256(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	260(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm3, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	264(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	268(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # msg_sched done: 64-67
        # msg_sched: 72-75
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	288(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	292(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm0, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	296(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	300(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # msg_sched done: 72-75
        # msg_sched: 80-83
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 1 - 2
        movl	%r9d, %eax
        movl	%r13d, %ecx
        addl	320(%rsp), %r15d
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        andl	%r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r14d, %ecx
        xorl	%r12d, %edx
        addl	%ecx, %r15d
        rorl	$6, %edx
        xorl	%r8d, %eax
        addl	%edx, %r15d
        movl	%r8d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r8d, %ebx
        movl	%r12d, %ecx
        addl	324(%rsp), %r14d
        xorl	%r13d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r11d, %edx
        andl	%r11d, %ecx
        rorl	$5, %edx
        xorl	%r13d, %ecx
        xorl	%r11d, %edx
        addl	%ecx, %r14d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm1, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        movl	%r15d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r15d, %eax
        movl	%r11d, %ecx
        addl	328(%rsp), %r13d
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        andl	%r10d, %ecx
        rorl	$5, %edx
        xorl	%r12d, %ecx
        xorl	%r10d, %edx
        addl	%ecx, %r13d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r14d, %eax
        addl	%edx, %r13d
        movl	%r14d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r14d, %ebx
        movl	%r10d, %ecx
        addl	332(%rsp), %r12d
        xorl	%r11d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r9d, %edx
        andl	%r9d, %ecx
        rorl	$5, %edx
        xorl	%r11d, %ecx
        xorl	%r9d, %edx
        addl	%ecx, %r12d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        movl	%r13d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # msg_sched done: 80-83
        # msg_sched: 88-91
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 1 - 2
        movl	%r13d, %eax
        movl	%r9d, %ecx
        addl	352(%rsp), %r11d
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        andl	%r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 3 - 4
        rorl	$5, %edx
        xorl	%r10d, %ecx
        xorl	%r8d, %edx
        addl	%ecx, %r11d
        rorl	$6, %edx
        xorl	%r12d, %eax
        addl	%edx, %r11d
        movl	%r12d, %ecx
        vpsrld	$18, %ymm5, %ymm8
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 5 - 6
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        vpor	%ymm6, %ymm7, %ymm6
        vpor	%ymm8, %ymm9, %ymm8
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        # rnd_1: 0 - 1
        rorl	$14, %edx
        movl	%r12d, %ebx
        movl	%r8d, %ecx
        addl	356(%rsp), %r10d
        xorl	%r9d, %ecx
        vpsrld	$3, %ymm5, %ymm9
        vpxor	%ymm6, %ymm8, %ymm6
        # rnd_1: 2 - 3
        xorl	%r15d, %edx
        andl	%r15d, %ecx
        rorl	$5, %edx
        xorl	%r9d, %ecx
        xorl	%r15d, %edx
        addl	%ecx, %r10d
        vpxor	%ymm6, %ymm9, %ymm5
        vpshufd	$0xfa, %ymm2, %ymm6
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        movl	%r11d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        vpsrld	$10, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 6 - 7
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        # rnd_0: 0 - 0
        rorl	$14, %edx
        vpsrlq	$0x11, %ymm6, %ymm6
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 1 - 3
        movl	%r11d, %eax
        movl	%r15d, %ecx
        addl	360(%rsp), %r9d
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        andl	%r14d, %ecx
        rorl	$5, %edx
        xorl	%r8d, %ecx
        xorl	%r14d, %edx
        addl	%ecx, %r9d
        vpxor	%ymm6, %ymm7, %ymm6
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 4 - 4
        rorl	$6, %edx
        xorl	%r10d, %eax
        addl	%edx, %r9d
        movl	%r10d, %ecx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 5 - 5
        andl	%eax, %ebx
        rorl	$9, %ecx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 6 - 6
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 7 - 7
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        # rnd_1: 0 - 0
        rorl	$14, %edx
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_1: 1 - 1
        movl	%r10d, %ebx
        movl	%r14d, %ecx
        addl	364(%rsp), %r8d
        xorl	%r15d, %ecx
        vpsrlq	$0x11, %ymm6, %ymm8
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 2 - 3
        xorl	%r13d, %edx
        andl	%r13d, %ecx
        rorl	$5, %edx
        xorl	%r15d, %ecx
        xorl	%r13d, %edx
        addl	%ecx, %r8d
        vpsrld	$10, %ymm6, %ymm9
        vpxor	%ymm8, %ymm7, %ymm8
        # rnd_1: 4 - 5
        rorl	$6, %edx
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        movl	%r9d, %ecx
        andl	%ebx, %eax
        rorl	$9, %ecx
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        vpxor	%ymm9, %ymm8, %ymm9
        # rnd_1: 6 - 6
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 7 - 7
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # msg_sched done: 88-91
        # set_w_k_xfer_4: 12
        vpaddd	384+L_avx2_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	416+L_avx2_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, 384(%rsp)
        vmovdqu	%ymm5, 416(%rsp)
        vpaddd	448+L_avx2_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	480+L_avx2_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 448(%rsp)
        vmovdqu	%ymm5, 480(%rsp)
        # rnd_all_4: 24-27
        addl	384(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	388(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	392(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	396(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 26-29
        addl	416(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	420(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	424(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	428(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 28-31
        addl	448(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	452(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	456(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	460(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 30-33
        addl	480(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	484(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	488(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	492(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        addl	(%rdi), %r8d
        addl	4(%rdi), %r9d
        addl	8(%rdi), %r10d
        addl	12(%rdi), %r11d
        addl	16(%rdi), %r12d
        addl	20(%rdi), %r13d
        addl	24(%rdi), %r14d
        addl	28(%rdi), %r15d
        movl	%r8d, (%rdi)
        movl	%r9d, 4(%rdi)
        movl	%r10d, 8(%rdi)
        movl	%r11d, 12(%rdi)
        movl	%r12d, 16(%rdi)
        movl	%r13d, 20(%rdi)
        movl	%r14d, 24(%rdi)
        movl	%r15d, 28(%rdi)
        movl	%r9d, %ebx
        movl	%r12d, %edx
        xorl	%r10d, %ebx
        # rnd_all_4: 1-4
        addl	16(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	20(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	24(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	28(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 3-6
        addl	48(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	52(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	56(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	60(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 5-8
        addl	80(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	84(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	88(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	92(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 7-10
        addl	112(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	116(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	120(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	124(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 9-12
        addl	144(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	148(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	152(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	156(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 11-14
        addl	176(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	180(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	184(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	188(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 13-16
        addl	208(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	212(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	216(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	220(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 15-18
        addl	240(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	244(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	248(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	252(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 17-20
        addl	272(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	276(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	280(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	284(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 19-22
        addl	304(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	308(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	312(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	316(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 21-24
        addl	336(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	340(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	344(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	348(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 23-26
        addl	368(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	372(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	376(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	380(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 25-28
        addl	400(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	404(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	408(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	412(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 27-30
        addl	432(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	436(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	440(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	444(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        # rnd_all_4: 29-32
        addl	464(%rsp), %r15d
        movl	%r13d, %ecx
        movl	%r9d, %eax
        xorl	%r14d, %ecx
        rorl	$14, %edx
        andl	%r12d, %ecx
        xorl	%r12d, %edx
        xorl	%r14d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r15d
        xorl	%r12d, %edx
        xorl	%r8d, %eax
        rorl	$6, %edx
        movl	%r8d, %ecx
        addl	%edx, %r15d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r8d, %ecx
        xorl	%r9d, %ebx
        rorl	$11, %ecx
        addl	%r15d, %r11d
        xorl	%r8d, %ecx
        addl	%ebx, %r15d
        rorl	$2, %ecx
        movl	%r11d, %edx
        addl	%ecx, %r15d
        addl	468(%rsp), %r14d
        movl	%r12d, %ecx
        movl	%r8d, %ebx
        xorl	%r13d, %ecx
        rorl	$14, %edx
        andl	%r11d, %ecx
        xorl	%r11d, %edx
        xorl	%r13d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r14d
        xorl	%r11d, %edx
        xorl	%r15d, %ebx
        rorl	$6, %edx
        movl	%r15d, %ecx
        addl	%edx, %r14d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r15d, %ecx
        xorl	%r8d, %eax
        rorl	$11, %ecx
        addl	%r14d, %r10d
        xorl	%r15d, %ecx
        addl	%eax, %r14d
        rorl	$2, %ecx
        movl	%r10d, %edx
        addl	%ecx, %r14d
        addl	472(%rsp), %r13d
        movl	%r11d, %ecx
        movl	%r15d, %eax
        xorl	%r12d, %ecx
        rorl	$14, %edx
        andl	%r10d, %ecx
        xorl	%r10d, %edx
        xorl	%r12d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r13d
        xorl	%r10d, %edx
        xorl	%r14d, %eax
        rorl	$6, %edx
        movl	%r14d, %ecx
        addl	%edx, %r13d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r14d, %ecx
        xorl	%r15d, %ebx
        rorl	$11, %ecx
        addl	%r13d, %r9d
        xorl	%r14d, %ecx
        addl	%ebx, %r13d
        rorl	$2, %ecx
        movl	%r9d, %edx
        addl	%ecx, %r13d
        addl	476(%rsp), %r12d
        movl	%r10d, %ecx
        movl	%r14d, %ebx
        xorl	%r11d, %ecx
        rorl	$14, %edx
        andl	%r9d, %ecx
        xorl	%r9d, %edx
        xorl	%r11d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r12d
        xorl	%r9d, %edx
        xorl	%r13d, %ebx
        rorl	$6, %edx
        movl	%r13d, %ecx
        addl	%edx, %r12d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r13d, %ecx
        xorl	%r14d, %eax
        rorl	$11, %ecx
        addl	%r12d, %r8d
        xorl	%r13d, %ecx
        addl	%eax, %r12d
        rorl	$2, %ecx
        movl	%r8d, %edx
        addl	%ecx, %r12d
        # rnd_all_4: 31-34
        addl	496(%rsp), %r11d
        movl	%r9d, %ecx
        movl	%r13d, %eax
        xorl	%r10d, %ecx
        rorl	$14, %edx
        andl	%r8d, %ecx
        xorl	%r8d, %edx
        xorl	%r10d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r11d
        xorl	%r8d, %edx
        xorl	%r12d, %eax
        rorl	$6, %edx
        movl	%r12d, %ecx
        addl	%edx, %r11d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r12d, %ecx
        xorl	%r13d, %ebx
        rorl	$11, %ecx
        addl	%r11d, %r15d
        xorl	%r12d, %ecx
        addl	%ebx, %r11d
        rorl	$2, %ecx
        movl	%r15d, %edx
        addl	%ecx, %r11d
        addl	500(%rsp), %r10d
        movl	%r8d, %ecx
        movl	%r12d, %ebx
        xorl	%r9d, %ecx
        rorl	$14, %edx
        andl	%r15d, %ecx
        xorl	%r15d, %edx
        xorl	%r9d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r10d
        xorl	%r15d, %edx
        xorl	%r11d, %ebx
        rorl	$6, %edx
        movl	%r11d, %ecx
        addl	%edx, %r10d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r11d, %ecx
        xorl	%r12d, %eax
        rorl	$11, %ecx
        addl	%r10d, %r14d
        xorl	%r11d, %ecx
        addl	%eax, %r10d
        rorl	$2, %ecx
        movl	%r14d, %edx
        addl	%ecx, %r10d
        addl	504(%rsp), %r9d
        movl	%r15d, %ecx
        movl	%r11d, %eax
        xorl	%r8d, %ecx
        rorl	$14, %edx
        andl	%r14d, %ecx
        xorl	%r14d, %edx
        xorl	%r8d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r9d
        xorl	%r14d, %edx
        xorl	%r10d, %eax
        rorl	$6, %edx
        movl	%r10d, %ecx
        addl	%edx, %r9d
        rorl	$9, %ecx
        andl	%eax, %ebx
        xorl	%r10d, %ecx
        xorl	%r11d, %ebx
        rorl	$11, %ecx
        addl	%r9d, %r13d
        xorl	%r10d, %ecx
        addl	%ebx, %r9d
        rorl	$2, %ecx
        movl	%r13d, %edx
        addl	%ecx, %r9d
        addl	508(%rsp), %r8d
        movl	%r14d, %ecx
        movl	%r10d, %ebx
        xorl	%r15d, %ecx
        rorl	$14, %edx
        andl	%r13d, %ecx
        xorl	%r13d, %edx
        xorl	%r15d, %ecx
        rorl	$5, %edx
        addl	%ecx, %r8d
        xorl	%r13d, %edx
        xorl	%r9d, %ebx
        rorl	$6, %edx
        movl	%r9d, %ecx
        addl	%edx, %r8d
        rorl	$9, %ecx
        andl	%ebx, %eax
        xorl	%r9d, %ecx
        xorl	%r10d, %eax
        rorl	$11, %ecx
        addl	%r8d, %r12d
        xorl	%r9d, %ecx
        addl	%eax, %r8d
        rorl	$2, %ecx
        movl	%r12d, %edx
        addl	%ecx, %r8d
        addl	(%rdi), %r8d
        addl	4(%rdi), %r9d
        addl	8(%rdi), %r10d
        addl	12(%rdi), %r11d
        addl	16(%rdi), %r12d
        addl	20(%rdi), %r13d
        addl	24(%rdi), %r14d
        addl	28(%rdi), %r15d
        addq	$0x80, %rbp
        subl	$0x80, %esi
        movl	%r8d, (%rdi)
        movl	%r9d, 4(%rdi)
        movl	%r10d, 8(%rdi)
        movl	%r11d, 12(%rdi)
        movl	%r12d, 16(%rdi)
        movl	%r13d, 20(%rdi)
        movl	%r14d, 24(%rdi)
        movl	%r15d, 28(%rdi)
        jnz	L_sha256_len_avx2_start
L_sha256_len_avx2_done:
        xorq	%rax, %rax
        vzeroupper
        addq	$0x200, %rsp
        popq	%rbp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX2_Len,.-Transform_Sha256_AVX2_Len
#endif /* __APPLE__ */
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
L_avx2_rorx_sha256_k:
.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long	0xe49b69c1,0xefbe4786,0xfc19dc6,0x240ca1cc
.long	0xe49b69c1,0xefbe4786,0xfc19dc6,0x240ca1cc
.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long	0xc6e00bf3,0xd5a79147,0x6ca6351,0x14292967
.long	0xc6e00bf3,0xd5a79147,0x6ca6351,0x14292967
.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	32
#else
.p2align	5
#endif /* __APPLE__ */
L_avx2_rorx_sha256_flip_mask:
.quad	0x405060700010203, 0xc0d0e0f08090a0b
.quad	0x405060700010203, 0xc0d0e0f08090a0b
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	32
#else
.p2align	5
#endif /* __APPLE__ */
L_avx2_rorx_sha256_shuf_00BA:
.quad	0xb0a090803020100, 0xffffffffffffffff
.quad	0xb0a090803020100, 0xffffffffffffffff
#ifndef __APPLE__
.data
#else
.section	__DATA,__data
#endif /* __APPLE__ */
#ifndef __APPLE__
.align	32
#else
.p2align	5
#endif /* __APPLE__ */
L_avx2_rorx_sha256_shuf_DC00:
.quad	0xffffffffffffffff, 0xb0a090803020100
.quad	0xffffffffffffffff, 0xb0a090803020100
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX2_RORX
.type	Transform_Sha256_AVX2_RORX,@function
.align	16
Transform_Sha256_AVX2_RORX:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX2_RORX
.p2align	4
_Transform_Sha256_AVX2_RORX:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        subq	$0x200, %rsp
        leaq	32(%rdi), %rax
        vmovdqa	L_avx2_rorx_sha256_flip_mask(%rip), %xmm13
        vmovdqa	L_avx2_rorx_sha256_shuf_00BA(%rip), %ymm11
        vmovdqa	L_avx2_rorx_sha256_shuf_DC00(%rip), %ymm12
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rax), %xmm0
        vmovdqu	16(%rax), %xmm1
        vpshufb	%xmm13, %xmm0, %xmm0
        vpshufb	%xmm13, %xmm1, %xmm1
        vpaddd	0+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	32+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, (%rsp)
        vmovdqu	%ymm5, 32(%rsp)
        vmovdqu	32(%rax), %xmm2
        vmovdqu	48(%rax), %xmm3
        vpshufb	%xmm13, %xmm2, %xmm2
        vpshufb	%xmm13, %xmm3, %xmm3
        vpaddd	64+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	96+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 64(%rsp)
        vmovdqu	%ymm5, 96(%rsp)
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        movl	%r9d, %ebx
        rorxl	$6, %r12d, %edx
        xorl	%r10d, %ebx
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm3, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	128+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 128(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	32(%rsp), %r11d
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	36(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm0, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	40(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	44(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	160+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 160(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	64(%rsp), %r15d
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	68(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm1, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	72(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	76(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	192+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 192(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	96(%rsp), %r11d
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	100(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm2, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	104(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	108(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	224+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 224(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	128(%rsp), %r15d
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	132(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm3, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	136(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	140(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	256+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 256(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	160(%rsp), %r11d
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	164(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm0, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	168(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	172(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	288+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 288(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	192(%rsp), %r15d
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	196(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm1, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	200(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	204(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	320+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 320(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	224(%rsp), %r11d
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	228(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm2, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	232(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	236(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	352+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 352(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	256(%rsp), %r15d
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	260(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm3, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	264(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	268(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	384+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 384(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	288(%rsp), %r11d
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	292(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm0, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	296(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	300(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	416+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 416(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	320(%rsp), %r15d
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	324(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm1, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	328(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	332(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	448+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 448(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	352(%rsp), %r11d
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	356(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm2, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	360(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	364(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	480+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 480(%rsp)
        xorl	%eax, %eax
        xorl	%ecx, %ecx
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	384(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	388(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	392(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	396(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	416(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	420(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	424(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	428(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	448(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	452(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	456(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	460(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	480(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	484(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	488(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	492(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        addl	%eax, %r8d
        addl	%r8d, (%rdi)
        addl	%r9d, 4(%rdi)
        addl	%r10d, 8(%rdi)
        addl	%r11d, 12(%rdi)
        addl	%r12d, 16(%rdi)
        addl	%r13d, 20(%rdi)
        addl	%r14d, 24(%rdi)
        addl	%r15d, 28(%rdi)
        xorq	%rax, %rax
        vzeroupper
        addq	$0x200, %rsp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX2_RORX,.-Transform_Sha256_AVX2_RORX
#endif /* __APPLE__ */
#ifndef __APPLE__
.text
.globl	Transform_Sha256_AVX2_RORX_Len
.type	Transform_Sha256_AVX2_RORX_Len,@function
.align	16
Transform_Sha256_AVX2_RORX_Len:
#else
.section	__TEXT,__text
.globl	_Transform_Sha256_AVX2_RORX_Len
.p2align	4
_Transform_Sha256_AVX2_RORX_Len:
#endif /* __APPLE__ */
        pushq	%rbx
        pushq	%r12
        pushq	%r13
        pushq	%r14
        pushq	%r15
        pushq	%rbp
        movq	%rsi, %rbp
        movq	%rdx, %rsi
        subq	$0x200, %rsp
        testb	$0x40, %sil
        je	L_sha256_len_avx2_rorx_block
        vmovdqu	(%rbp), %ymm0
        vmovdqu	32(%rbp), %ymm1
        vmovups	%ymm0, 32(%rdi)
        vmovups	%ymm1, 64(%rdi)
#ifndef __APPLE__
        call	Transform_Sha256_AVX2_RORX@plt
#else
        call	_Transform_Sha256_AVX2_RORX
#endif /* __APPLE__ */
        addq	$0x40, %rbp
        subl	$0x40, %esi
        jz	L_sha256_len_avx2_rorx_done
L_sha256_len_avx2_rorx_block:
        vmovdqa	L_avx2_rorx_sha256_flip_mask(%rip), %ymm13
        vmovdqa	L_avx2_rorx_sha256_shuf_00BA(%rip), %ymm11
        vmovdqa	L_avx2_rorx_sha256_shuf_DC00(%rip), %ymm12
        movl	(%rdi), %r8d
        movl	4(%rdi), %r9d
        movl	8(%rdi), %r10d
        movl	12(%rdi), %r11d
        movl	16(%rdi), %r12d
        movl	20(%rdi), %r13d
        movl	24(%rdi), %r14d
        movl	28(%rdi), %r15d
        # Start of loop processing two blocks
L_sha256_len_avx2_rorx_start:
        # X0, X1, X2, X3 = W[0..15]
        vmovdqu	(%rbp), %xmm0
        vmovdqu	16(%rbp), %xmm1
        vinserti128	$0x01, 64(%rbp), %ymm0, %ymm0
        vinserti128	$0x01, 80(%rbp), %ymm1, %ymm1
        vpshufb	%ymm13, %ymm0, %ymm0
        vpshufb	%ymm13, %ymm1, %ymm1
        vpaddd	0+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        vpaddd	32+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm5
        vmovdqu	%ymm4, (%rsp)
        vmovdqu	%ymm5, 32(%rsp)
        vmovdqu	32(%rbp), %xmm2
        vmovdqu	48(%rbp), %xmm3
        vinserti128	$0x01, 96(%rbp), %ymm2, %ymm2
        vinserti128	$0x01, 112(%rbp), %ymm3, %ymm3
        vpshufb	%ymm13, %ymm2, %ymm2
        vpshufb	%ymm13, %ymm3, %ymm3
        vpaddd	64+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        vpaddd	96+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm5
        vmovdqu	%ymm4, 64(%rsp)
        vmovdqu	%ymm5, 96(%rsp)
        movl	%r9d, %ebx
        rorxl	$6, %r12d, %edx
        xorl	%r10d, %ebx
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	(%rsp), %r15d
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	4(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm3, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	8(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	12(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	128+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 128(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	32(%rsp), %r11d
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	36(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm0, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	40(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	44(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	160+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 160(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	64(%rsp), %r15d
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	68(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm1, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	72(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	76(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	192+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 192(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	96(%rsp), %r11d
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	100(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm2, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	104(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	108(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	224+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 224(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	128(%rsp), %r15d
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	132(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm3, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	136(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	140(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	256+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 256(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	160(%rsp), %r11d
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	164(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm0, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	168(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	172(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	288+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 288(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	192(%rsp), %r15d
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	196(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm1, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	200(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	204(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	320+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 320(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	224(%rsp), %r11d
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	228(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm2, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	232(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	236(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	352+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 352(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	256(%rsp), %r15d
        vpalignr	$4, %ymm0, %ymm1, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm2, %ymm3, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	260(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm3, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm0, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	264(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	268(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm0
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	384+L_avx2_rorx_sha256_k(%rip), %ymm0, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 384(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	288(%rsp), %r11d
        vpalignr	$4, %ymm1, %ymm2, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm3, %ymm0, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	292(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm0, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm1, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	296(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	300(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm1
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	416+L_avx2_rorx_sha256_k(%rip), %ymm1, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 416(%rsp)
        # rnd_0: 0 - 0
        movl	%r13d, %eax
        rorxl	$11, %r12d, %ecx
        addl	320(%rsp), %r15d
        vpalignr	$4, %ymm2, %ymm3, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        vpalignr	$4, %ymm0, %ymm1, %ymm4
        # rnd_0: 2 - 2
        andl	%r12d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r8d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        xorl	%r14d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r8d, %eax
        addl	%edx, %r15d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        addl	%ebx, %r15d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r12d, %ebx
        rorxl	$11, %r11d, %ecx
        addl	324(%rsp), %r14d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r11d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r15d, %ecx
        vpshufd	$0xfa, %ymm1, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        xorl	%r13d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r14d, %r10d
        movl	%r8d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r15d, %ebx
        addl	%edx, %r14d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        addl	%eax, %r14d
        vpaddd	%ymm2, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r11d, %eax
        rorxl	$11, %r10d, %ecx
        addl	328(%rsp), %r13d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r10d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r14d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        xorl	%r12d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r14d, %eax
        addl	%edx, %r13d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        addl	%ebx, %r13d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r10d, %ebx
        rorxl	$11, %r9d, %ecx
        addl	332(%rsp), %r12d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r9d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r13d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        xorl	%r11d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        vpaddd	%ymm4, %ymm9, %ymm2
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r12d, %r8d
        movl	%r14d, %ebx
        vpaddd	448+L_avx2_rorx_sha256_k(%rip), %ymm2, %ymm4
        # rnd_1: 6 - 6
        xorl	%r13d, %ebx
        addl	%edx, %r12d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        addl	%eax, %r12d
        vmovdqu	%ymm4, 448(%rsp)
        # rnd_0: 0 - 0
        movl	%r9d, %eax
        rorxl	$11, %r8d, %ecx
        addl	352(%rsp), %r11d
        vpalignr	$4, %ymm3, %ymm0, %ymm5
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        vpalignr	$4, %ymm1, %ymm2, %ymm4
        # rnd_0: 2 - 2
        andl	%r8d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r12d, %ecx
        vpsrld	$7, %ymm5, %ymm6
        # rnd_0: 3 - 3
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        xorl	%r10d, %eax
        vpslld	$25, %ymm5, %ymm7
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        vpsrld	$18, %ymm5, %ymm8
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        vpslld	$14, %ymm5, %ymm9
        # rnd_0: 6 - 6
        xorl	%r12d, %eax
        addl	%edx, %r11d
        andl	%eax, %ebx
        vpor	%ymm7, %ymm6, %ymm6
        # rnd_0: 7 - 7
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        addl	%ebx, %r11d
        vpor	%ymm9, %ymm8, %ymm8
        # rnd_1: 0 - 0
        movl	%r8d, %ebx
        rorxl	$11, %r15d, %ecx
        addl	356(%rsp), %r10d
        vpsrld	$3, %ymm5, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        vpxor	%ymm8, %ymm6, %ymm6
        # rnd_1: 2 - 2
        andl	%r15d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r11d, %ecx
        vpshufd	$0xfa, %ymm2, %ymm7
        # rnd_1: 3 - 3
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        xorl	%r9d, %ebx
        vpxor	%ymm6, %ymm9, %ymm5
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        vpsrld	$10, %ymm7, %ymm8
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r10d, %r14d
        movl	%r12d, %ebx
        vpsrlq	$19, %ymm7, %ymm6
        # rnd_1: 6 - 6
        xorl	%r11d, %ebx
        addl	%edx, %r10d
        andl	%ebx, %eax
        vpsrlq	$0x11, %ymm7, %ymm7
        # rnd_1: 7 - 7
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        addl	%eax, %r10d
        vpaddd	%ymm3, %ymm4, %ymm4
        # rnd_0: 0 - 0
        movl	%r15d, %eax
        rorxl	$11, %r14d, %ecx
        addl	360(%rsp), %r9d
        vpxor	%ymm7, %ymm6, %ymm6
        # rnd_0: 1 - 1
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        vpxor	%ymm6, %ymm8, %ymm8
        # rnd_0: 2 - 2
        andl	%r14d, %eax
        xorl	%ecx, %edx
        rorxl	$13, %r10d, %ecx
        vpaddd	%ymm5, %ymm4, %ymm4
        # rnd_0: 3 - 3
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        xorl	%r8d, %eax
        vpshufb	%ymm11, %ymm8, %ymm8
        # rnd_0: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        vpaddd	%ymm8, %ymm4, %ymm4
        # rnd_0: 5 - 5
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        vpshufd	$0x50, %ymm4, %ymm6
        # rnd_0: 6 - 6
        xorl	%r10d, %eax
        addl	%edx, %r9d
        andl	%eax, %ebx
        vpsrlq	$0x11, %ymm6, %ymm8
        # rnd_0: 7 - 7
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        addl	%ebx, %r9d
        vpsrlq	$19, %ymm6, %ymm7
        # rnd_1: 0 - 0
        movl	%r14d, %ebx
        rorxl	$11, %r13d, %ecx
        addl	364(%rsp), %r8d
        vpsrld	$10, %ymm6, %ymm9
        # rnd_1: 1 - 1
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        vpxor	%ymm7, %ymm8, %ymm8
        # rnd_1: 2 - 2
        andl	%r13d, %ebx
        xorl	%ecx, %edx
        rorxl	$13, %r9d, %ecx
        vpxor	%ymm8, %ymm9, %ymm9
        # rnd_1: 3 - 3
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        xorl	%r15d, %ebx
        vpshufb	%ymm12, %ymm9, %ymm9
        # rnd_1: 4 - 4
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        vpaddd	%ymm4, %ymm9, %ymm3
        # rnd_1: 5 - 5
        xorl	%ecx, %edx
        addl	%r8d, %r12d
        movl	%r10d, %ebx
        vpaddd	480+L_avx2_rorx_sha256_k(%rip), %ymm3, %ymm4
        # rnd_1: 6 - 6
        xorl	%r9d, %ebx
        addl	%edx, %r8d
        andl	%ebx, %eax
        # rnd_1: 7 - 7
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        addl	%eax, %r8d
        vmovdqu	%ymm4, 480(%rsp)
        xorl	%eax, %eax
        xorl	%ecx, %ecx
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	384(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	388(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	392(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	396(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	416(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	420(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	424(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	428(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	448(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	452(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	456(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	460(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	480(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	484(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	488(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	492(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        addl	%eax, %r8d
        xorl	%ecx, %ecx
        addl	(%rdi), %r8d
        addl	4(%rdi), %r9d
        addl	8(%rdi), %r10d
        addl	12(%rdi), %r11d
        addl	16(%rdi), %r12d
        addl	20(%rdi), %r13d
        addl	24(%rdi), %r14d
        addl	28(%rdi), %r15d
        movl	%r8d, (%rdi)
        movl	%r9d, 4(%rdi)
        movl	%r10d, 8(%rdi)
        movl	%r11d, 12(%rdi)
        movl	%r12d, 16(%rdi)
        movl	%r13d, 20(%rdi)
        movl	%r14d, 24(%rdi)
        movl	%r15d, 28(%rdi)
        movl	%r9d, %ebx
        xorl	%eax, %eax
        xorl	%r10d, %ebx
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	16(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	20(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	24(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	28(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	48(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	52(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	56(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	60(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	80(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	84(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	88(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	92(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	112(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	116(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	120(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	124(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	144(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	148(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	152(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	156(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	176(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	180(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	184(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	188(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	208(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	212(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	216(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	220(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	240(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	244(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	248(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	252(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	272(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	276(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	280(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	284(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	304(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	308(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	312(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	316(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	336(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	340(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	344(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	348(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	368(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	372(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	376(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	380(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	400(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	404(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	408(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	412(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	432(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	436(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	440(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	444(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        rorxl	$6, %r12d, %edx
        rorxl	$11, %r12d, %ecx
        leal	(%r8,%rax,1), %r8d
        addl	464(%rsp), %r15d
        movl	%r13d, %eax
        xorl	%edx, %ecx
        xorl	%r14d, %eax
        rorxl	$25, %r12d, %edx
        xorl	%ecx, %edx
        andl	%r12d, %eax
        addl	%edx, %r15d
        rorxl	$2, %r8d, %edx
        rorxl	$13, %r8d, %ecx
        xorl	%r14d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r8d, %edx
        addl	%eax, %r15d
        xorl	%ecx, %edx
        movl	%r9d, %eax
        addl	%r15d, %r11d
        xorl	%r8d, %eax
        andl	%eax, %ebx
        addl	%edx, %r15d
        xorl	%r9d, %ebx
        rorxl	$6, %r11d, %edx
        rorxl	$11, %r11d, %ecx
        addl	%ebx, %r15d
        addl	468(%rsp), %r14d
        movl	%r12d, %ebx
        xorl	%edx, %ecx
        xorl	%r13d, %ebx
        rorxl	$25, %r11d, %edx
        xorl	%ecx, %edx
        andl	%r11d, %ebx
        addl	%edx, %r14d
        rorxl	$2, %r15d, %edx
        rorxl	$13, %r15d, %ecx
        xorl	%r13d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r15d, %edx
        addl	%ebx, %r14d
        xorl	%ecx, %edx
        movl	%r8d, %ebx
        leal	(%r10,%r14,1), %r10d
        xorl	%r15d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r14d
        xorl	%r8d, %eax
        rorxl	$6, %r10d, %edx
        rorxl	$11, %r10d, %ecx
        leal	(%r14,%rax,1), %r14d
        addl	472(%rsp), %r13d
        movl	%r11d, %eax
        xorl	%edx, %ecx
        xorl	%r12d, %eax
        rorxl	$25, %r10d, %edx
        xorl	%ecx, %edx
        andl	%r10d, %eax
        addl	%edx, %r13d
        rorxl	$2, %r14d, %edx
        rorxl	$13, %r14d, %ecx
        xorl	%r12d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r14d, %edx
        addl	%eax, %r13d
        xorl	%ecx, %edx
        movl	%r15d, %eax
        addl	%r13d, %r9d
        xorl	%r14d, %eax
        andl	%eax, %ebx
        addl	%edx, %r13d
        xorl	%r15d, %ebx
        rorxl	$6, %r9d, %edx
        rorxl	$11, %r9d, %ecx
        addl	%ebx, %r13d
        addl	476(%rsp), %r12d
        movl	%r10d, %ebx
        xorl	%edx, %ecx
        xorl	%r11d, %ebx
        rorxl	$25, %r9d, %edx
        xorl	%ecx, %edx
        andl	%r9d, %ebx
        addl	%edx, %r12d
        rorxl	$2, %r13d, %edx
        rorxl	$13, %r13d, %ecx
        xorl	%r11d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r13d, %edx
        addl	%ebx, %r12d
        xorl	%ecx, %edx
        movl	%r14d, %ebx
        leal	(%r8,%r12,1), %r8d
        xorl	%r13d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r12d
        xorl	%r14d, %eax
        rorxl	$6, %r8d, %edx
        rorxl	$11, %r8d, %ecx
        leal	(%r12,%rax,1), %r12d
        addl	496(%rsp), %r11d
        movl	%r9d, %eax
        xorl	%edx, %ecx
        xorl	%r10d, %eax
        rorxl	$25, %r8d, %edx
        xorl	%ecx, %edx
        andl	%r8d, %eax
        addl	%edx, %r11d
        rorxl	$2, %r12d, %edx
        rorxl	$13, %r12d, %ecx
        xorl	%r10d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r12d, %edx
        addl	%eax, %r11d
        xorl	%ecx, %edx
        movl	%r13d, %eax
        addl	%r11d, %r15d
        xorl	%r12d, %eax
        andl	%eax, %ebx
        addl	%edx, %r11d
        xorl	%r13d, %ebx
        rorxl	$6, %r15d, %edx
        rorxl	$11, %r15d, %ecx
        addl	%ebx, %r11d
        addl	500(%rsp), %r10d
        movl	%r8d, %ebx
        xorl	%edx, %ecx
        xorl	%r9d, %ebx
        rorxl	$25, %r15d, %edx
        xorl	%ecx, %edx
        andl	%r15d, %ebx
        addl	%edx, %r10d
        rorxl	$2, %r11d, %edx
        rorxl	$13, %r11d, %ecx
        xorl	%r9d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r11d, %edx
        addl	%ebx, %r10d
        xorl	%ecx, %edx
        movl	%r12d, %ebx
        leal	(%r14,%r10,1), %r14d
        xorl	%r11d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r10d
        xorl	%r12d, %eax
        rorxl	$6, %r14d, %edx
        rorxl	$11, %r14d, %ecx
        leal	(%r10,%rax,1), %r10d
        addl	504(%rsp), %r9d
        movl	%r15d, %eax
        xorl	%edx, %ecx
        xorl	%r8d, %eax
        rorxl	$25, %r14d, %edx
        xorl	%ecx, %edx
        andl	%r14d, %eax
        addl	%edx, %r9d
        rorxl	$2, %r10d, %edx
        rorxl	$13, %r10d, %ecx
        xorl	%r8d, %eax
        xorl	%edx, %ecx
        rorxl	$22, %r10d, %edx
        addl	%eax, %r9d
        xorl	%ecx, %edx
        movl	%r11d, %eax
        addl	%r9d, %r13d
        xorl	%r10d, %eax
        andl	%eax, %ebx
        addl	%edx, %r9d
        xorl	%r11d, %ebx
        rorxl	$6, %r13d, %edx
        rorxl	$11, %r13d, %ecx
        addl	%ebx, %r9d
        addl	508(%rsp), %r8d
        movl	%r14d, %ebx
        xorl	%edx, %ecx
        xorl	%r15d, %ebx
        rorxl	$25, %r13d, %edx
        xorl	%ecx, %edx
        andl	%r13d, %ebx
        addl	%edx, %r8d
        rorxl	$2, %r9d, %edx
        rorxl	$13, %r9d, %ecx
        xorl	%r15d, %ebx
        xorl	%edx, %ecx
        rorxl	$22, %r9d, %edx
        addl	%ebx, %r8d
        xorl	%ecx, %edx
        movl	%r10d, %ebx
        leal	(%r12,%r8,1), %r12d
        xorl	%r9d, %ebx
        andl	%ebx, %eax
        addl	%edx, %r8d
        xorl	%r10d, %eax
        addl	%eax, %r8d
        addq	$0x80, %rbp
        addl	(%rdi), %r8d
        addl	4(%rdi), %r9d
        addl	8(%rdi), %r10d
        addl	12(%rdi), %r11d
        addl	16(%rdi), %r12d
        addl	20(%rdi), %r13d
        addl	24(%rdi), %r14d
        addl	28(%rdi), %r15d
        subl	$0x80, %esi
        movl	%r8d, (%rdi)
        movl	%r9d, 4(%rdi)
        movl	%r10d, 8(%rdi)
        movl	%r11d, 12(%rdi)
        movl	%r12d, 16(%rdi)
        movl	%r13d, 20(%rdi)
        movl	%r14d, 24(%rdi)
        movl	%r15d, 28(%rdi)
        jnz	L_sha256_len_avx2_rorx_start
L_sha256_len_avx2_rorx_done:
        xorq	%rax, %rax
        vzeroupper
        addq	$0x200, %rsp
        popq	%rbp
        popq	%r15
        popq	%r14
        popq	%r13
        popq	%r12
        popq	%rbx
        repz retq
#ifndef __APPLE__
.size	Transform_Sha256_AVX2_RORX_Len,.-Transform_Sha256_AVX2_RORX_Len
#endif /* __APPLE__ */
#endif /* HAVE_INTEL_AVX2 */

#if defined(__linux__) && defined(__ELF__)
.section	.note.GNU-stack,"",%progbits
#endif