diff options
Diffstat (limited to 'secure/lib/libcrypto/amd64/sha1-x86_64.S')
-rw-r--r-- | secure/lib/libcrypto/amd64/sha1-x86_64.S | 2808 |
1 files changed, 2807 insertions, 1 deletions
diff --git a/secure/lib/libcrypto/amd64/sha1-x86_64.S b/secure/lib/libcrypto/amd64/sha1-x86_64.S index 25c27e5..0edab29 100644 --- a/secure/lib/libcrypto/amd64/sha1-x86_64.S +++ b/secure/lib/libcrypto/amd64/sha1-x86_64.S @@ -1,4 +1,5 @@ - # $FreeBSD$ +# $FreeBSD$ +# Do not modify. This file is auto-generated from sha1-x86_64.pl. .text @@ -13,6 +14,14 @@ sha1_block_data_order: jz .Lialu testl $536870912,%r10d jnz _shaext_shortcut + andl $296,%r10d + cmpl $296,%r10d + je _avx2_shortcut + andl $268435456,%r8d + andl $1073741824,%r9d + orl %r9d,%r8d + cmpl $1342177280,%r8d + je _avx_shortcut jmp _ssse3_shortcut .align 16 @@ -2575,6 +2584,2803 @@ _ssse3_shortcut: .Lepilogue_ssse3: .byte 0xf3,0xc3 .size sha1_block_data_order_ssse3,.-sha1_block_data_order_ssse3 +.type sha1_block_data_order_avx,@function +.align 16 +sha1_block_data_order_avx: +_avx_shortcut: + movq %rsp,%rax + pushq %rbx + pushq %rbp + pushq %r12 + pushq %r13 + pushq %r14 + leaq -64(%rsp),%rsp + vzeroupper + movq %rax,%r14 + andq $-64,%rsp + movq %rdi,%r8 + movq %rsi,%r9 + movq %rdx,%r10 + + shlq $6,%r10 + addq %r9,%r10 + leaq K_XX_XX+64(%rip),%r11 + + movl 0(%r8),%eax + movl 4(%r8),%ebx + movl 8(%r8),%ecx + movl 12(%r8),%edx + movl %ebx,%esi + movl 16(%r8),%ebp + movl %ecx,%edi + xorl %edx,%edi + andl %edi,%esi + + vmovdqa 64(%r11),%xmm6 + vmovdqa -64(%r11),%xmm11 + vmovdqu 0(%r9),%xmm0 + vmovdqu 16(%r9),%xmm1 + vmovdqu 32(%r9),%xmm2 + vmovdqu 48(%r9),%xmm3 + vpshufb %xmm6,%xmm0,%xmm0 + addq $64,%r9 + vpshufb %xmm6,%xmm1,%xmm1 + vpshufb %xmm6,%xmm2,%xmm2 + vpshufb %xmm6,%xmm3,%xmm3 + vpaddd %xmm11,%xmm0,%xmm4 + vpaddd %xmm11,%xmm1,%xmm5 + vpaddd %xmm11,%xmm2,%xmm6 + vmovdqa %xmm4,0(%rsp) + vmovdqa %xmm5,16(%rsp) + vmovdqa %xmm6,32(%rsp) + jmp .Loop_avx +.align 16 +.Loop_avx: + shrdl $2,%ebx,%ebx + xorl %edx,%esi + vpalignr $8,%xmm0,%xmm1,%xmm4 + movl %eax,%edi + addl 0(%rsp),%ebp + vpaddd %xmm3,%xmm11,%xmm9 + xorl %ecx,%ebx + shldl $5,%eax,%eax + vpsrldq $4,%xmm3,%xmm8 + addl %esi,%ebp + andl %ebx,%edi + vpxor %xmm0,%xmm4,%xmm4 + xorl %ecx,%ebx + addl %eax,%ebp + vpxor %xmm2,%xmm8,%xmm8 + shrdl $7,%eax,%eax + xorl %ecx,%edi + movl %ebp,%esi + addl 4(%rsp),%edx + vpxor %xmm8,%xmm4,%xmm4 + xorl %ebx,%eax + shldl $5,%ebp,%ebp + vmovdqa %xmm9,48(%rsp) + addl %edi,%edx + andl %eax,%esi + vpsrld $31,%xmm4,%xmm8 + xorl %ebx,%eax + addl %ebp,%edx + shrdl $7,%ebp,%ebp + xorl %ebx,%esi + vpslldq $12,%xmm4,%xmm10 + vpaddd %xmm4,%xmm4,%xmm4 + movl %edx,%edi + addl 8(%rsp),%ecx + xorl %eax,%ebp + shldl $5,%edx,%edx + vpsrld $30,%xmm10,%xmm9 + vpor %xmm8,%xmm4,%xmm4 + addl %esi,%ecx + andl %ebp,%edi + xorl %eax,%ebp + addl %edx,%ecx + vpslld $2,%xmm10,%xmm10 + vpxor %xmm9,%xmm4,%xmm4 + shrdl $7,%edx,%edx + xorl %eax,%edi + movl %ecx,%esi + addl 12(%rsp),%ebx + vpxor %xmm10,%xmm4,%xmm4 + xorl %ebp,%edx + shldl $5,%ecx,%ecx + addl %edi,%ebx + andl %edx,%esi + xorl %ebp,%edx + addl %ecx,%ebx + shrdl $7,%ecx,%ecx + xorl %ebp,%esi + vpalignr $8,%xmm1,%xmm2,%xmm5 + movl %ebx,%edi + addl 16(%rsp),%eax + vpaddd %xmm4,%xmm11,%xmm9 + xorl %edx,%ecx + shldl $5,%ebx,%ebx + vpsrldq $4,%xmm4,%xmm8 + addl %esi,%eax + andl %ecx,%edi + vpxor %xmm1,%xmm5,%xmm5 + xorl %edx,%ecx + addl %ebx,%eax + vpxor %xmm3,%xmm8,%xmm8 + shrdl $7,%ebx,%ebx + xorl %edx,%edi + movl %eax,%esi + addl 20(%rsp),%ebp + vpxor %xmm8,%xmm5,%xmm5 + xorl %ecx,%ebx + shldl $5,%eax,%eax + vmovdqa %xmm9,0(%rsp) + addl %edi,%ebp + andl %ebx,%esi + vpsrld $31,%xmm5,%xmm8 + xorl %ecx,%ebx + addl %eax,%ebp + shrdl $7,%eax,%eax + xorl %ecx,%esi + vpslldq $12,%xmm5,%xmm10 + vpaddd %xmm5,%xmm5,%xmm5 + movl %ebp,%edi + addl 24(%rsp),%edx + xorl %ebx,%eax + shldl $5,%ebp,%ebp + vpsrld $30,%xmm10,%xmm9 + vpor %xmm8,%xmm5,%xmm5 + addl %esi,%edx + andl %eax,%edi + xorl %ebx,%eax + addl %ebp,%edx + vpslld $2,%xmm10,%xmm10 + vpxor %xmm9,%xmm5,%xmm5 + shrdl $7,%ebp,%ebp + xorl %ebx,%edi + movl %edx,%esi + addl 28(%rsp),%ecx + vpxor %xmm10,%xmm5,%xmm5 + xorl %eax,%ebp + shldl $5,%edx,%edx + vmovdqa -32(%r11),%xmm11 + addl %edi,%ecx + andl %ebp,%esi + xorl %eax,%ebp + addl %edx,%ecx + shrdl $7,%edx,%edx + xorl %eax,%esi + vpalignr $8,%xmm2,%xmm3,%xmm6 + movl %ecx,%edi + addl 32(%rsp),%ebx + vpaddd %xmm5,%xmm11,%xmm9 + xorl %ebp,%edx + shldl $5,%ecx,%ecx + vpsrldq $4,%xmm5,%xmm8 + addl %esi,%ebx + andl %edx,%edi + vpxor %xmm2,%xmm6,%xmm6 + xorl %ebp,%edx + addl %ecx,%ebx + vpxor %xmm4,%xmm8,%xmm8 + shrdl $7,%ecx,%ecx + xorl %ebp,%edi + movl %ebx,%esi + addl 36(%rsp),%eax + vpxor %xmm8,%xmm6,%xmm6 + xorl %edx,%ecx + shldl $5,%ebx,%ebx + vmovdqa %xmm9,16(%rsp) + addl %edi,%eax + andl %ecx,%esi + vpsrld $31,%xmm6,%xmm8 + xorl %edx,%ecx + addl %ebx,%eax + shrdl $7,%ebx,%ebx + xorl %edx,%esi + vpslldq $12,%xmm6,%xmm10 + vpaddd %xmm6,%xmm6,%xmm6 + movl %eax,%edi + addl 40(%rsp),%ebp + xorl %ecx,%ebx + shldl $5,%eax,%eax + vpsrld $30,%xmm10,%xmm9 + vpor %xmm8,%xmm6,%xmm6 + addl %esi,%ebp + andl %ebx,%edi + xorl %ecx,%ebx + addl %eax,%ebp + vpslld $2,%xmm10,%xmm10 + vpxor %xmm9,%xmm6,%xmm6 + shrdl $7,%eax,%eax + xorl %ecx,%edi + movl %ebp,%esi + addl 44(%rsp),%edx + vpxor %xmm10,%xmm6,%xmm6 + xorl %ebx,%eax + shldl $5,%ebp,%ebp + addl %edi,%edx + andl %eax,%esi + xorl %ebx,%eax + addl %ebp,%edx + shrdl $7,%ebp,%ebp + xorl %ebx,%esi + vpalignr $8,%xmm3,%xmm4,%xmm7 + movl %edx,%edi + addl 48(%rsp),%ecx + vpaddd %xmm6,%xmm11,%xmm9 + xorl %eax,%ebp + shldl $5,%edx,%edx + vpsrldq $4,%xmm6,%xmm8 + addl %esi,%ecx + andl %ebp,%edi + vpxor %xmm3,%xmm7,%xmm7 + xorl %eax,%ebp + addl %edx,%ecx + vpxor %xmm5,%xmm8,%xmm8 + shrdl $7,%edx,%edx + xorl %eax,%edi + movl %ecx,%esi + addl 52(%rsp),%ebx + vpxor %xmm8,%xmm7,%xmm7 + xorl %ebp,%edx + shldl $5,%ecx,%ecx + vmovdqa %xmm9,32(%rsp) + addl %edi,%ebx + andl %edx,%esi + vpsrld $31,%xmm7,%xmm8 + xorl %ebp,%edx + addl %ecx,%ebx + shrdl $7,%ecx,%ecx + xorl %ebp,%esi + vpslldq $12,%xmm7,%xmm10 + vpaddd %xmm7,%xmm7,%xmm7 + movl %ebx,%edi + addl 56(%rsp),%eax + xorl %edx,%ecx + shldl $5,%ebx,%ebx + vpsrld $30,%xmm10,%xmm9 + vpor %xmm8,%xmm7,%xmm7 + addl %esi,%eax + andl %ecx,%edi + xorl %edx,%ecx + addl %ebx,%eax + vpslld $2,%xmm10,%xmm10 + vpxor %xmm9,%xmm7,%xmm7 + shrdl $7,%ebx,%ebx + xorl %edx,%edi + movl %eax,%esi + addl 60(%rsp),%ebp + vpxor %xmm10,%xmm7,%xmm7 + xorl %ecx,%ebx + shldl $5,%eax,%eax + addl %edi,%ebp + andl %ebx,%esi + xorl %ecx,%ebx + addl %eax,%ebp + vpalignr $8,%xmm6,%xmm7,%xmm8 + vpxor %xmm4,%xmm0,%xmm0 + shrdl $7,%eax,%eax + xorl %ecx,%esi + movl %ebp,%edi + addl 0(%rsp),%edx + vpxor %xmm1,%xmm0,%xmm0 + xorl %ebx,%eax + shldl $5,%ebp,%ebp + vpaddd %xmm7,%xmm11,%xmm9 + addl %esi,%edx + andl %eax,%edi + vpxor %xmm8,%xmm0,%xmm0 + xorl %ebx,%eax + addl %ebp,%edx + shrdl $7,%ebp,%ebp + xorl %ebx,%edi + vpsrld $30,%xmm0,%xmm8 + vmovdqa %xmm9,48(%rsp) + movl %edx,%esi + addl 4(%rsp),%ecx + xorl %eax,%ebp + shldl $5,%edx,%edx + vpslld $2,%xmm0,%xmm0 + addl %edi,%ecx + andl %ebp,%esi + xorl %eax,%ebp + addl %edx,%ecx + shrdl $7,%edx,%edx + xorl %eax,%esi + movl %ecx,%edi + addl 8(%rsp),%ebx + vpor %xmm8,%xmm0,%xmm0 + xorl %ebp,%edx + shldl $5,%ecx,%ecx + addl %esi,%ebx + andl %edx,%edi + xorl %ebp,%edx + addl %ecx,%ebx + addl 12(%rsp),%eax + xorl %ebp,%edi + movl %ebx,%esi + shldl $5,%ebx,%ebx + addl %edi,%eax + xorl %edx,%esi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + vpalignr $8,%xmm7,%xmm0,%xmm8 + vpxor %xmm5,%xmm1,%xmm1 + addl 16(%rsp),%ebp + xorl %ecx,%esi + movl %eax,%edi + shldl $5,%eax,%eax + vpxor %xmm2,%xmm1,%xmm1 + addl %esi,%ebp + xorl %ecx,%edi + vpaddd %xmm0,%xmm11,%xmm9 + shrdl $7,%ebx,%ebx + addl %eax,%ebp + vpxor %xmm8,%xmm1,%xmm1 + addl 20(%rsp),%edx + xorl %ebx,%edi + movl %ebp,%esi + shldl $5,%ebp,%ebp + vpsrld $30,%xmm1,%xmm8 + vmovdqa %xmm9,0(%rsp) + addl %edi,%edx + xorl %ebx,%esi + shrdl $7,%eax,%eax + addl %ebp,%edx + vpslld $2,%xmm1,%xmm1 + addl 24(%rsp),%ecx + xorl %eax,%esi + movl %edx,%edi + shldl $5,%edx,%edx + addl %esi,%ecx + xorl %eax,%edi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + vpor %xmm8,%xmm1,%xmm1 + addl 28(%rsp),%ebx + xorl %ebp,%edi + movl %ecx,%esi + shldl $5,%ecx,%ecx + addl %edi,%ebx + xorl %ebp,%esi + shrdl $7,%edx,%edx + addl %ecx,%ebx + vpalignr $8,%xmm0,%xmm1,%xmm8 + vpxor %xmm6,%xmm2,%xmm2 + addl 32(%rsp),%eax + xorl %edx,%esi + movl %ebx,%edi + shldl $5,%ebx,%ebx + vpxor %xmm3,%xmm2,%xmm2 + addl %esi,%eax + xorl %edx,%edi + vpaddd %xmm1,%xmm11,%xmm9 + vmovdqa 0(%r11),%xmm11 + shrdl $7,%ecx,%ecx + addl %ebx,%eax + vpxor %xmm8,%xmm2,%xmm2 + addl 36(%rsp),%ebp + xorl %ecx,%edi + movl %eax,%esi + shldl $5,%eax,%eax + vpsrld $30,%xmm2,%xmm8 + vmovdqa %xmm9,16(%rsp) + addl %edi,%ebp + xorl %ecx,%esi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + vpslld $2,%xmm2,%xmm2 + addl 40(%rsp),%edx + xorl %ebx,%esi + movl %ebp,%edi + shldl $5,%ebp,%ebp + addl %esi,%edx + xorl %ebx,%edi + shrdl $7,%eax,%eax + addl %ebp,%edx + vpor %xmm8,%xmm2,%xmm2 + addl 44(%rsp),%ecx + xorl %eax,%edi + movl %edx,%esi + shldl $5,%edx,%edx + addl %edi,%ecx + xorl %eax,%esi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + vpalignr $8,%xmm1,%xmm2,%xmm8 + vpxor %xmm7,%xmm3,%xmm3 + addl 48(%rsp),%ebx + xorl %ebp,%esi + movl %ecx,%edi + shldl $5,%ecx,%ecx + vpxor %xmm4,%xmm3,%xmm3 + addl %esi,%ebx + xorl %ebp,%edi + vpaddd %xmm2,%xmm11,%xmm9 + shrdl $7,%edx,%edx + addl %ecx,%ebx + vpxor %xmm8,%xmm3,%xmm3 + addl 52(%rsp),%eax + xorl %edx,%edi + movl %ebx,%esi + shldl $5,%ebx,%ebx + vpsrld $30,%xmm3,%xmm8 + vmovdqa %xmm9,32(%rsp) + addl %edi,%eax + xorl %edx,%esi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + vpslld $2,%xmm3,%xmm3 + addl 56(%rsp),%ebp + xorl %ecx,%esi + movl %eax,%edi + shldl $5,%eax,%eax + addl %esi,%ebp + xorl %ecx,%edi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + vpor %xmm8,%xmm3,%xmm3 + addl 60(%rsp),%edx + xorl %ebx,%edi + movl %ebp,%esi + shldl $5,%ebp,%ebp + addl %edi,%edx + xorl %ebx,%esi + shrdl $7,%eax,%eax + addl %ebp,%edx + vpalignr $8,%xmm2,%xmm3,%xmm8 + vpxor %xmm0,%xmm4,%xmm4 + addl 0(%rsp),%ecx + xorl %eax,%esi + movl %edx,%edi + shldl $5,%edx,%edx + vpxor %xmm5,%xmm4,%xmm4 + addl %esi,%ecx + xorl %eax,%edi + vpaddd %xmm3,%xmm11,%xmm9 + shrdl $7,%ebp,%ebp + addl %edx,%ecx + vpxor %xmm8,%xmm4,%xmm4 + addl 4(%rsp),%ebx + xorl %ebp,%edi + movl %ecx,%esi + shldl $5,%ecx,%ecx + vpsrld $30,%xmm4,%xmm8 + vmovdqa %xmm9,48(%rsp) + addl %edi,%ebx + xorl %ebp,%esi + shrdl $7,%edx,%edx + addl %ecx,%ebx + vpslld $2,%xmm4,%xmm4 + addl 8(%rsp),%eax + xorl %edx,%esi + movl %ebx,%edi + shldl $5,%ebx,%ebx + addl %esi,%eax + xorl %edx,%edi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + vpor %xmm8,%xmm4,%xmm4 + addl 12(%rsp),%ebp + xorl %ecx,%edi + movl %eax,%esi + shldl $5,%eax,%eax + addl %edi,%ebp + xorl %ecx,%esi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + vpalignr $8,%xmm3,%xmm4,%xmm8 + vpxor %xmm1,%xmm5,%xmm5 + addl 16(%rsp),%edx + xorl %ebx,%esi + movl %ebp,%edi + shldl $5,%ebp,%ebp + vpxor %xmm6,%xmm5,%xmm5 + addl %esi,%edx + xorl %ebx,%edi + vpaddd %xmm4,%xmm11,%xmm9 + shrdl $7,%eax,%eax + addl %ebp,%edx + vpxor %xmm8,%xmm5,%xmm5 + addl 20(%rsp),%ecx + xorl %eax,%edi + movl %edx,%esi + shldl $5,%edx,%edx + vpsrld $30,%xmm5,%xmm8 + vmovdqa %xmm9,0(%rsp) + addl %edi,%ecx + xorl %eax,%esi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + vpslld $2,%xmm5,%xmm5 + addl 24(%rsp),%ebx + xorl %ebp,%esi + movl %ecx,%edi + shldl $5,%ecx,%ecx + addl %esi,%ebx + xorl %ebp,%edi + shrdl $7,%edx,%edx + addl %ecx,%ebx + vpor %xmm8,%xmm5,%xmm5 + addl 28(%rsp),%eax + shrdl $7,%ecx,%ecx + movl %ebx,%esi + xorl %edx,%edi + shldl $5,%ebx,%ebx + addl %edi,%eax + xorl %ecx,%esi + xorl %edx,%ecx + addl %ebx,%eax + vpalignr $8,%xmm4,%xmm5,%xmm8 + vpxor %xmm2,%xmm6,%xmm6 + addl 32(%rsp),%ebp + andl %ecx,%esi + xorl %edx,%ecx + shrdl $7,%ebx,%ebx + vpxor %xmm7,%xmm6,%xmm6 + movl %eax,%edi + xorl %ecx,%esi + vpaddd %xmm5,%xmm11,%xmm9 + shldl $5,%eax,%eax + addl %esi,%ebp + vpxor %xmm8,%xmm6,%xmm6 + xorl %ebx,%edi + xorl %ecx,%ebx + addl %eax,%ebp + addl 36(%rsp),%edx + vpsrld $30,%xmm6,%xmm8 + vmovdqa %xmm9,16(%rsp) + andl %ebx,%edi + xorl %ecx,%ebx + shrdl $7,%eax,%eax + movl %ebp,%esi + vpslld $2,%xmm6,%xmm6 + xorl %ebx,%edi + shldl $5,%ebp,%ebp + addl %edi,%edx + xorl %eax,%esi + xorl %ebx,%eax + addl %ebp,%edx + addl 40(%rsp),%ecx + andl %eax,%esi + vpor %xmm8,%xmm6,%xmm6 + xorl %ebx,%eax + shrdl $7,%ebp,%ebp + movl %edx,%edi + xorl %eax,%esi + shldl $5,%edx,%edx + addl %esi,%ecx + xorl %ebp,%edi + xorl %eax,%ebp + addl %edx,%ecx + addl 44(%rsp),%ebx + andl %ebp,%edi + xorl %eax,%ebp + shrdl $7,%edx,%edx + movl %ecx,%esi + xorl %ebp,%edi + shldl $5,%ecx,%ecx + addl %edi,%ebx + xorl %edx,%esi + xorl %ebp,%edx + addl %ecx,%ebx + vpalignr $8,%xmm5,%xmm6,%xmm8 + vpxor %xmm3,%xmm7,%xmm7 + addl 48(%rsp),%eax + andl %edx,%esi + xorl %ebp,%edx + shrdl $7,%ecx,%ecx + vpxor %xmm0,%xmm7,%xmm7 + movl %ebx,%edi + xorl %edx,%esi + vpaddd %xmm6,%xmm11,%xmm9 + vmovdqa 32(%r11),%xmm11 + shldl $5,%ebx,%ebx + addl %esi,%eax + vpxor %xmm8,%xmm7,%xmm7 + xorl %ecx,%edi + xorl %edx,%ecx + addl %ebx,%eax + addl 52(%rsp),%ebp + vpsrld $30,%xmm7,%xmm8 + vmovdqa %xmm9,32(%rsp) + andl %ecx,%edi + xorl %edx,%ecx + shrdl $7,%ebx,%ebx + movl %eax,%esi + vpslld $2,%xmm7,%xmm7 + xorl %ecx,%edi + shldl $5,%eax,%eax + addl %edi,%ebp + xorl %ebx,%esi + xorl %ecx,%ebx + addl %eax,%ebp + addl 56(%rsp),%edx + andl %ebx,%esi + vpor %xmm8,%xmm7,%xmm7 + xorl %ecx,%ebx + shrdl $7,%eax,%eax + movl %ebp,%edi + xorl %ebx,%esi + shldl $5,%ebp,%ebp + addl %esi,%edx + xorl %eax,%edi + xorl %ebx,%eax + addl %ebp,%edx + addl 60(%rsp),%ecx + andl %eax,%edi + xorl %ebx,%eax + shrdl $7,%ebp,%ebp + movl %edx,%esi + xorl %eax,%edi + shldl $5,%edx,%edx + addl %edi,%ecx + xorl %ebp,%esi + xorl %eax,%ebp + addl %edx,%ecx + vpalignr $8,%xmm6,%xmm7,%xmm8 + vpxor %xmm4,%xmm0,%xmm0 + addl 0(%rsp),%ebx + andl %ebp,%esi + xorl %eax,%ebp + shrdl $7,%edx,%edx + vpxor %xmm1,%xmm0,%xmm0 + movl %ecx,%edi + xorl %ebp,%esi + vpaddd %xmm7,%xmm11,%xmm9 + shldl $5,%ecx,%ecx + addl %esi,%ebx + vpxor %xmm8,%xmm0,%xmm0 + xorl %edx,%edi + xorl %ebp,%edx + addl %ecx,%ebx + addl 4(%rsp),%eax + vpsrld $30,%xmm0,%xmm8 + vmovdqa %xmm9,48(%rsp) + andl %edx,%edi + xorl %ebp,%edx + shrdl $7,%ecx,%ecx + movl %ebx,%esi + vpslld $2,%xmm0,%xmm0 + xorl %edx,%edi + shldl $5,%ebx,%ebx + addl %edi,%eax + xorl %ecx,%esi + xorl %edx,%ecx + addl %ebx,%eax + addl 8(%rsp),%ebp + andl %ecx,%esi + vpor %xmm8,%xmm0,%xmm0 + xorl %edx,%ecx + shrdl $7,%ebx,%ebx + movl %eax,%edi + xorl %ecx,%esi + shldl $5,%eax,%eax + addl %esi,%ebp + xorl %ebx,%edi + xorl %ecx,%ebx + addl %eax,%ebp + addl 12(%rsp),%edx + andl %ebx,%edi + xorl %ecx,%ebx + shrdl $7,%eax,%eax + movl %ebp,%esi + xorl %ebx,%edi + shldl $5,%ebp,%ebp + addl %edi,%edx + xorl %eax,%esi + xorl %ebx,%eax + addl %ebp,%edx + vpalignr $8,%xmm7,%xmm0,%xmm8 + vpxor %xmm5,%xmm1,%xmm1 + addl 16(%rsp),%ecx + andl %eax,%esi + xorl %ebx,%eax + shrdl $7,%ebp,%ebp + vpxor %xmm2,%xmm1,%xmm1 + movl %edx,%edi + xorl %eax,%esi + vpaddd %xmm0,%xmm11,%xmm9 + shldl $5,%edx,%edx + addl %esi,%ecx + vpxor %xmm8,%xmm1,%xmm1 + xorl %ebp,%edi + xorl %eax,%ebp + addl %edx,%ecx + addl 20(%rsp),%ebx + vpsrld $30,%xmm1,%xmm8 + vmovdqa %xmm9,0(%rsp) + andl %ebp,%edi + xorl %eax,%ebp + shrdl $7,%edx,%edx + movl %ecx,%esi + vpslld $2,%xmm1,%xmm1 + xorl %ebp,%edi + shldl $5,%ecx,%ecx + addl %edi,%ebx + xorl %edx,%esi + xorl %ebp,%edx + addl %ecx,%ebx + addl 24(%rsp),%eax + andl %edx,%esi + vpor %xmm8,%xmm1,%xmm1 + xorl %ebp,%edx + shrdl $7,%ecx,%ecx + movl %ebx,%edi + xorl %edx,%esi + shldl $5,%ebx,%ebx + addl %esi,%eax + xorl %ecx,%edi + xorl %edx,%ecx + addl %ebx,%eax + addl 28(%rsp),%ebp + andl %ecx,%edi + xorl %edx,%ecx + shrdl $7,%ebx,%ebx + movl %eax,%esi + xorl %ecx,%edi + shldl $5,%eax,%eax + addl %edi,%ebp + xorl %ebx,%esi + xorl %ecx,%ebx + addl %eax,%ebp + vpalignr $8,%xmm0,%xmm1,%xmm8 + vpxor %xmm6,%xmm2,%xmm2 + addl 32(%rsp),%edx + andl %ebx,%esi + xorl %ecx,%ebx + shrdl $7,%eax,%eax + vpxor %xmm3,%xmm2,%xmm2 + movl %ebp,%edi + xorl %ebx,%esi + vpaddd %xmm1,%xmm11,%xmm9 + shldl $5,%ebp,%ebp + addl %esi,%edx + vpxor %xmm8,%xmm2,%xmm2 + xorl %eax,%edi + xorl %ebx,%eax + addl %ebp,%edx + addl 36(%rsp),%ecx + vpsrld $30,%xmm2,%xmm8 + vmovdqa %xmm9,16(%rsp) + andl %eax,%edi + xorl %ebx,%eax + shrdl $7,%ebp,%ebp + movl %edx,%esi + vpslld $2,%xmm2,%xmm2 + xorl %eax,%edi + shldl $5,%edx,%edx + addl %edi,%ecx + xorl %ebp,%esi + xorl %eax,%ebp + addl %edx,%ecx + addl 40(%rsp),%ebx + andl %ebp,%esi + vpor %xmm8,%xmm2,%xmm2 + xorl %eax,%ebp + shrdl $7,%edx,%edx + movl %ecx,%edi + xorl %ebp,%esi + shldl $5,%ecx,%ecx + addl %esi,%ebx + xorl %edx,%edi + xorl %ebp,%edx + addl %ecx,%ebx + addl 44(%rsp),%eax + andl %edx,%edi + xorl %ebp,%edx + shrdl $7,%ecx,%ecx + movl %ebx,%esi + xorl %edx,%edi + shldl $5,%ebx,%ebx + addl %edi,%eax + xorl %edx,%esi + addl %ebx,%eax + vpalignr $8,%xmm1,%xmm2,%xmm8 + vpxor %xmm7,%xmm3,%xmm3 + addl 48(%rsp),%ebp + xorl %ecx,%esi + movl %eax,%edi + shldl $5,%eax,%eax + vpxor %xmm4,%xmm3,%xmm3 + addl %esi,%ebp + xorl %ecx,%edi + vpaddd %xmm2,%xmm11,%xmm9 + shrdl $7,%ebx,%ebx + addl %eax,%ebp + vpxor %xmm8,%xmm3,%xmm3 + addl 52(%rsp),%edx + xorl %ebx,%edi + movl %ebp,%esi + shldl $5,%ebp,%ebp + vpsrld $30,%xmm3,%xmm8 + vmovdqa %xmm9,32(%rsp) + addl %edi,%edx + xorl %ebx,%esi + shrdl $7,%eax,%eax + addl %ebp,%edx + vpslld $2,%xmm3,%xmm3 + addl 56(%rsp),%ecx + xorl %eax,%esi + movl %edx,%edi + shldl $5,%edx,%edx + addl %esi,%ecx + xorl %eax,%edi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + vpor %xmm8,%xmm3,%xmm3 + addl 60(%rsp),%ebx + xorl %ebp,%edi + movl %ecx,%esi + shldl $5,%ecx,%ecx + addl %edi,%ebx + xorl %ebp,%esi + shrdl $7,%edx,%edx + addl %ecx,%ebx + addl 0(%rsp),%eax + vpaddd %xmm3,%xmm11,%xmm9 + xorl %edx,%esi + movl %ebx,%edi + shldl $5,%ebx,%ebx + addl %esi,%eax + vmovdqa %xmm9,48(%rsp) + xorl %edx,%edi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + addl 4(%rsp),%ebp + xorl %ecx,%edi + movl %eax,%esi + shldl $5,%eax,%eax + addl %edi,%ebp + xorl %ecx,%esi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + addl 8(%rsp),%edx + xorl %ebx,%esi + movl %ebp,%edi + shldl $5,%ebp,%ebp + addl %esi,%edx + xorl %ebx,%edi + shrdl $7,%eax,%eax + addl %ebp,%edx + addl 12(%rsp),%ecx + xorl %eax,%edi + movl %edx,%esi + shldl $5,%edx,%edx + addl %edi,%ecx + xorl %eax,%esi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + cmpq %r10,%r9 + je .Ldone_avx + vmovdqa 64(%r11),%xmm6 + vmovdqa -64(%r11),%xmm11 + vmovdqu 0(%r9),%xmm0 + vmovdqu 16(%r9),%xmm1 + vmovdqu 32(%r9),%xmm2 + vmovdqu 48(%r9),%xmm3 + vpshufb %xmm6,%xmm0,%xmm0 + addq $64,%r9 + addl 16(%rsp),%ebx + xorl %ebp,%esi + vpshufb %xmm6,%xmm1,%xmm1 + movl %ecx,%edi + shldl $5,%ecx,%ecx + vpaddd %xmm11,%xmm0,%xmm4 + addl %esi,%ebx + xorl %ebp,%edi + shrdl $7,%edx,%edx + addl %ecx,%ebx + vmovdqa %xmm4,0(%rsp) + addl 20(%rsp),%eax + xorl %edx,%edi + movl %ebx,%esi + shldl $5,%ebx,%ebx + addl %edi,%eax + xorl %edx,%esi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + addl 24(%rsp),%ebp + xorl %ecx,%esi + movl %eax,%edi + shldl $5,%eax,%eax + addl %esi,%ebp + xorl %ecx,%edi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + addl 28(%rsp),%edx + xorl %ebx,%edi + movl %ebp,%esi + shldl $5,%ebp,%ebp + addl %edi,%edx + xorl %ebx,%esi + shrdl $7,%eax,%eax + addl %ebp,%edx + addl 32(%rsp),%ecx + xorl %eax,%esi + vpshufb %xmm6,%xmm2,%xmm2 + movl %edx,%edi + shldl $5,%edx,%edx + vpaddd %xmm11,%xmm1,%xmm5 + addl %esi,%ecx + xorl %eax,%edi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + vmovdqa %xmm5,16(%rsp) + addl 36(%rsp),%ebx + xorl %ebp,%edi + movl %ecx,%esi + shldl $5,%ecx,%ecx + addl %edi,%ebx + xorl %ebp,%esi + shrdl $7,%edx,%edx + addl %ecx,%ebx + addl 40(%rsp),%eax + xorl %edx,%esi + movl %ebx,%edi + shldl $5,%ebx,%ebx + addl %esi,%eax + xorl %edx,%edi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + addl 44(%rsp),%ebp + xorl %ecx,%edi + movl %eax,%esi + shldl $5,%eax,%eax + addl %edi,%ebp + xorl %ecx,%esi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + addl 48(%rsp),%edx + xorl %ebx,%esi + vpshufb %xmm6,%xmm3,%xmm3 + movl %ebp,%edi + shldl $5,%ebp,%ebp + vpaddd %xmm11,%xmm2,%xmm6 + addl %esi,%edx + xorl %ebx,%edi + shrdl $7,%eax,%eax + addl %ebp,%edx + vmovdqa %xmm6,32(%rsp) + addl 52(%rsp),%ecx + xorl %eax,%edi + movl %edx,%esi + shldl $5,%edx,%edx + addl %edi,%ecx + xorl %eax,%esi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + addl 56(%rsp),%ebx + xorl %ebp,%esi + movl %ecx,%edi + shldl $5,%ecx,%ecx + addl %esi,%ebx + xorl %ebp,%edi + shrdl $7,%edx,%edx + addl %ecx,%ebx + addl 60(%rsp),%eax + xorl %edx,%edi + movl %ebx,%esi + shldl $5,%ebx,%ebx + addl %edi,%eax + shrdl $7,%ecx,%ecx + addl %ebx,%eax + addl 0(%r8),%eax + addl 4(%r8),%esi + addl 8(%r8),%ecx + addl 12(%r8),%edx + movl %eax,0(%r8) + addl 16(%r8),%ebp + movl %esi,4(%r8) + movl %esi,%ebx + movl %ecx,8(%r8) + movl %ecx,%edi + movl %edx,12(%r8) + xorl %edx,%edi + movl %ebp,16(%r8) + andl %edi,%esi + jmp .Loop_avx + +.align 16 +.Ldone_avx: + addl 16(%rsp),%ebx + xorl %ebp,%esi + movl %ecx,%edi + shldl $5,%ecx,%ecx + addl %esi,%ebx + xorl %ebp,%edi + shrdl $7,%edx,%edx + addl %ecx,%ebx + addl 20(%rsp),%eax + xorl %edx,%edi + movl %ebx,%esi + shldl $5,%ebx,%ebx + addl %edi,%eax + xorl %edx,%esi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + addl 24(%rsp),%ebp + xorl %ecx,%esi + movl %eax,%edi + shldl $5,%eax,%eax + addl %esi,%ebp + xorl %ecx,%edi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + addl 28(%rsp),%edx + xorl %ebx,%edi + movl %ebp,%esi + shldl $5,%ebp,%ebp + addl %edi,%edx + xorl %ebx,%esi + shrdl $7,%eax,%eax + addl %ebp,%edx + addl 32(%rsp),%ecx + xorl %eax,%esi + movl %edx,%edi + shldl $5,%edx,%edx + addl %esi,%ecx + xorl %eax,%edi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + addl 36(%rsp),%ebx + xorl %ebp,%edi + movl %ecx,%esi + shldl $5,%ecx,%ecx + addl %edi,%ebx + xorl %ebp,%esi + shrdl $7,%edx,%edx + addl %ecx,%ebx + addl 40(%rsp),%eax + xorl %edx,%esi + movl %ebx,%edi + shldl $5,%ebx,%ebx + addl %esi,%eax + xorl %edx,%edi + shrdl $7,%ecx,%ecx + addl %ebx,%eax + addl 44(%rsp),%ebp + xorl %ecx,%edi + movl %eax,%esi + shldl $5,%eax,%eax + addl %edi,%ebp + xorl %ecx,%esi + shrdl $7,%ebx,%ebx + addl %eax,%ebp + addl 48(%rsp),%edx + xorl %ebx,%esi + movl %ebp,%edi + shldl $5,%ebp,%ebp + addl %esi,%edx + xorl %ebx,%edi + shrdl $7,%eax,%eax + addl %ebp,%edx + addl 52(%rsp),%ecx + xorl %eax,%edi + movl %edx,%esi + shldl $5,%edx,%edx + addl %edi,%ecx + xorl %eax,%esi + shrdl $7,%ebp,%ebp + addl %edx,%ecx + addl 56(%rsp),%ebx + xorl %ebp,%esi + movl %ecx,%edi + shldl $5,%ecx,%ecx + addl %esi,%ebx + xorl %ebp,%edi + shrdl $7,%edx,%edx + addl %ecx,%ebx + addl 60(%rsp),%eax + xorl %edx,%edi + movl %ebx,%esi + shldl $5,%ebx,%ebx + addl %edi,%eax + shrdl $7,%ecx,%ecx + addl %ebx,%eax + vzeroupper + + addl 0(%r8),%eax + addl 4(%r8),%esi + addl 8(%r8),%ecx + movl %eax,0(%r8) + addl 12(%r8),%edx + movl %esi,4(%r8) + addl 16(%r8),%ebp + movl %ecx,8(%r8) + movl %edx,12(%r8) + movl %ebp,16(%r8) + leaq (%r14),%rsi + movq -40(%rsi),%r14 + movq -32(%rsi),%r13 + movq -24(%rsi),%r12 + movq -16(%rsi),%rbp + movq -8(%rsi),%rbx + leaq (%rsi),%rsp +.Lepilogue_avx: + .byte 0xf3,0xc3 +.size sha1_block_data_order_avx,.-sha1_block_data_order_avx +.type sha1_block_data_order_avx2,@function +.align 16 +sha1_block_data_order_avx2: +_avx2_shortcut: + movq %rsp,%rax + pushq %rbx + pushq %rbp + pushq %r12 + pushq %r13 + pushq %r14 + vzeroupper + movq %rax,%r14 + movq %rdi,%r8 + movq %rsi,%r9 + movq %rdx,%r10 + + leaq -640(%rsp),%rsp + shlq $6,%r10 + leaq 64(%r9),%r13 + andq $-128,%rsp + addq %r9,%r10 + leaq K_XX_XX+64(%rip),%r11 + + movl 0(%r8),%eax + cmpq %r10,%r13 + cmovaeq %r9,%r13 + movl 4(%r8),%ebp + movl 8(%r8),%ecx + movl 12(%r8),%edx + movl 16(%r8),%esi + vmovdqu 64(%r11),%ymm6 + + vmovdqu (%r9),%xmm0 + vmovdqu 16(%r9),%xmm1 + vmovdqu 32(%r9),%xmm2 + vmovdqu 48(%r9),%xmm3 + leaq 64(%r9),%r9 + vinserti128 $1,(%r13),%ymm0,%ymm0 + vinserti128 $1,16(%r13),%ymm1,%ymm1 + vpshufb %ymm6,%ymm0,%ymm0 + vinserti128 $1,32(%r13),%ymm2,%ymm2 + vpshufb %ymm6,%ymm1,%ymm1 + vinserti128 $1,48(%r13),%ymm3,%ymm3 + vpshufb %ymm6,%ymm2,%ymm2 + vmovdqu -64(%r11),%ymm11 + vpshufb %ymm6,%ymm3,%ymm3 + + vpaddd %ymm11,%ymm0,%ymm4 + vpaddd %ymm11,%ymm1,%ymm5 + vmovdqu %ymm4,0(%rsp) + vpaddd %ymm11,%ymm2,%ymm6 + vmovdqu %ymm5,32(%rsp) + vpaddd %ymm11,%ymm3,%ymm7 + vmovdqu %ymm6,64(%rsp) + vmovdqu %ymm7,96(%rsp) + vpalignr $8,%ymm0,%ymm1,%ymm4 + vpsrldq $4,%ymm3,%ymm8 + vpxor %ymm0,%ymm4,%ymm4 + vpxor %ymm2,%ymm8,%ymm8 + vpxor %ymm8,%ymm4,%ymm4 + vpsrld $31,%ymm4,%ymm8 + vpslldq $12,%ymm4,%ymm10 + vpaddd %ymm4,%ymm4,%ymm4 + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm4,%ymm4 + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm4,%ymm4 + vpxor %ymm10,%ymm4,%ymm4 + vpaddd %ymm11,%ymm4,%ymm9 + vmovdqu %ymm9,128(%rsp) + vpalignr $8,%ymm1,%ymm2,%ymm5 + vpsrldq $4,%ymm4,%ymm8 + vpxor %ymm1,%ymm5,%ymm5 + vpxor %ymm3,%ymm8,%ymm8 + vpxor %ymm8,%ymm5,%ymm5 + vpsrld $31,%ymm5,%ymm8 + vmovdqu -32(%r11),%ymm11 + vpslldq $12,%ymm5,%ymm10 + vpaddd %ymm5,%ymm5,%ymm5 + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm5,%ymm5 + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm5,%ymm5 + vpxor %ymm10,%ymm5,%ymm5 + vpaddd %ymm11,%ymm5,%ymm9 + vmovdqu %ymm9,160(%rsp) + vpalignr $8,%ymm2,%ymm3,%ymm6 + vpsrldq $4,%ymm5,%ymm8 + vpxor %ymm2,%ymm6,%ymm6 + vpxor %ymm4,%ymm8,%ymm8 + vpxor %ymm8,%ymm6,%ymm6 + vpsrld $31,%ymm6,%ymm8 + vpslldq $12,%ymm6,%ymm10 + vpaddd %ymm6,%ymm6,%ymm6 + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm6,%ymm6 + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm6,%ymm6 + vpxor %ymm10,%ymm6,%ymm6 + vpaddd %ymm11,%ymm6,%ymm9 + vmovdqu %ymm9,192(%rsp) + vpalignr $8,%ymm3,%ymm4,%ymm7 + vpsrldq $4,%ymm6,%ymm8 + vpxor %ymm3,%ymm7,%ymm7 + vpxor %ymm5,%ymm8,%ymm8 + vpxor %ymm8,%ymm7,%ymm7 + vpsrld $31,%ymm7,%ymm8 + vpslldq $12,%ymm7,%ymm10 + vpaddd %ymm7,%ymm7,%ymm7 + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm7,%ymm7 + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm7,%ymm7 + vpxor %ymm10,%ymm7,%ymm7 + vpaddd %ymm11,%ymm7,%ymm9 + vmovdqu %ymm9,224(%rsp) + leaq 128(%rsp),%r13 + jmp .Loop_avx2 +.align 32 +.Loop_avx2: + rorxl $2,%ebp,%ebx + andnl %edx,%ebp,%edi + andl %ecx,%ebp + xorl %edi,%ebp + jmp .Lalign32_1 +.align 32 +.Lalign32_1: + vpalignr $8,%ymm6,%ymm7,%ymm8 + vpxor %ymm4,%ymm0,%ymm0 + addl -128(%r13),%esi + andnl %ecx,%eax,%edi + vpxor %ymm1,%ymm0,%ymm0 + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + vpxor %ymm8,%ymm0,%ymm0 + andl %ebx,%eax + addl %r12d,%esi + xorl %edi,%eax + vpsrld $30,%ymm0,%ymm8 + vpslld $2,%ymm0,%ymm0 + addl -124(%r13),%edx + andnl %ebx,%esi,%edi + addl %eax,%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + andl %ebp,%esi + vpor %ymm8,%ymm0,%ymm0 + addl %r12d,%edx + xorl %edi,%esi + addl -120(%r13),%ecx + andnl %ebp,%edx,%edi + vpaddd %ymm11,%ymm0,%ymm9 + addl %esi,%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + andl %eax,%edx + vmovdqu %ymm9,256(%rsp) + addl %r12d,%ecx + xorl %edi,%edx + addl -116(%r13),%ebx + andnl %eax,%ecx,%edi + addl %edx,%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + andl %esi,%ecx + addl %r12d,%ebx + xorl %edi,%ecx + addl -96(%r13),%ebp + andnl %esi,%ebx,%edi + addl %ecx,%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + andl %edx,%ebx + addl %r12d,%ebp + xorl %edi,%ebx + vpalignr $8,%ymm7,%ymm0,%ymm8 + vpxor %ymm5,%ymm1,%ymm1 + addl -92(%r13),%eax + andnl %edx,%ebp,%edi + vpxor %ymm2,%ymm1,%ymm1 + addl %ebx,%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + vpxor %ymm8,%ymm1,%ymm1 + andl %ecx,%ebp + addl %r12d,%eax + xorl %edi,%ebp + vpsrld $30,%ymm1,%ymm8 + vpslld $2,%ymm1,%ymm1 + addl -88(%r13),%esi + andnl %ecx,%eax,%edi + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + andl %ebx,%eax + vpor %ymm8,%ymm1,%ymm1 + addl %r12d,%esi + xorl %edi,%eax + addl -84(%r13),%edx + andnl %ebx,%esi,%edi + vpaddd %ymm11,%ymm1,%ymm9 + addl %eax,%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + andl %ebp,%esi + vmovdqu %ymm9,288(%rsp) + addl %r12d,%edx + xorl %edi,%esi + addl -64(%r13),%ecx + andnl %ebp,%edx,%edi + addl %esi,%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + andl %eax,%edx + addl %r12d,%ecx + xorl %edi,%edx + addl -60(%r13),%ebx + andnl %eax,%ecx,%edi + addl %edx,%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + andl %esi,%ecx + addl %r12d,%ebx + xorl %edi,%ecx + vpalignr $8,%ymm0,%ymm1,%ymm8 + vpxor %ymm6,%ymm2,%ymm2 + addl -56(%r13),%ebp + andnl %esi,%ebx,%edi + vpxor %ymm3,%ymm2,%ymm2 + vmovdqu 0(%r11),%ymm11 + addl %ecx,%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + vpxor %ymm8,%ymm2,%ymm2 + andl %edx,%ebx + addl %r12d,%ebp + xorl %edi,%ebx + vpsrld $30,%ymm2,%ymm8 + vpslld $2,%ymm2,%ymm2 + addl -52(%r13),%eax + andnl %edx,%ebp,%edi + addl %ebx,%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + andl %ecx,%ebp + vpor %ymm8,%ymm2,%ymm2 + addl %r12d,%eax + xorl %edi,%ebp + addl -32(%r13),%esi + andnl %ecx,%eax,%edi + vpaddd %ymm11,%ymm2,%ymm9 + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + andl %ebx,%eax + vmovdqu %ymm9,320(%rsp) + addl %r12d,%esi + xorl %edi,%eax + addl -28(%r13),%edx + andnl %ebx,%esi,%edi + addl %eax,%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + andl %ebp,%esi + addl %r12d,%edx + xorl %edi,%esi + addl -24(%r13),%ecx + andnl %ebp,%edx,%edi + addl %esi,%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + andl %eax,%edx + addl %r12d,%ecx + xorl %edi,%edx + vpalignr $8,%ymm1,%ymm2,%ymm8 + vpxor %ymm7,%ymm3,%ymm3 + addl -20(%r13),%ebx + andnl %eax,%ecx,%edi + vpxor %ymm4,%ymm3,%ymm3 + addl %edx,%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + vpxor %ymm8,%ymm3,%ymm3 + andl %esi,%ecx + addl %r12d,%ebx + xorl %edi,%ecx + vpsrld $30,%ymm3,%ymm8 + vpslld $2,%ymm3,%ymm3 + addl 0(%r13),%ebp + andnl %esi,%ebx,%edi + addl %ecx,%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + andl %edx,%ebx + vpor %ymm8,%ymm3,%ymm3 + addl %r12d,%ebp + xorl %edi,%ebx + addl 4(%r13),%eax + andnl %edx,%ebp,%edi + vpaddd %ymm11,%ymm3,%ymm9 + addl %ebx,%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + andl %ecx,%ebp + vmovdqu %ymm9,352(%rsp) + addl %r12d,%eax + xorl %edi,%ebp + addl 8(%r13),%esi + andnl %ecx,%eax,%edi + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + andl %ebx,%eax + addl %r12d,%esi + xorl %edi,%eax + addl 12(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + vpalignr $8,%ymm2,%ymm3,%ymm8 + vpxor %ymm0,%ymm4,%ymm4 + addl 32(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + vpxor %ymm5,%ymm4,%ymm4 + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + vpxor %ymm8,%ymm4,%ymm4 + addl %r12d,%ecx + xorl %ebp,%edx + addl 36(%r13),%ebx + vpsrld $30,%ymm4,%ymm8 + vpslld $2,%ymm4,%ymm4 + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + vpor %ymm8,%ymm4,%ymm4 + addl 40(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + vpaddd %ymm11,%ymm4,%ymm9 + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl 44(%r13),%eax + vmovdqu %ymm9,384(%rsp) + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl 64(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + vpalignr $8,%ymm3,%ymm4,%ymm8 + vpxor %ymm1,%ymm5,%ymm5 + addl 68(%r13),%edx + leal (%rdx,%rax,1),%edx + vpxor %ymm6,%ymm5,%ymm5 + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + vpxor %ymm8,%ymm5,%ymm5 + addl %r12d,%edx + xorl %ebx,%esi + addl 72(%r13),%ecx + vpsrld $30,%ymm5,%ymm8 + vpslld $2,%ymm5,%ymm5 + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + vpor %ymm8,%ymm5,%ymm5 + addl 76(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + vpaddd %ymm11,%ymm5,%ymm9 + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl 96(%r13),%ebp + vmovdqu %ymm9,416(%rsp) + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl 100(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + vpalignr $8,%ymm4,%ymm5,%ymm8 + vpxor %ymm2,%ymm6,%ymm6 + addl 104(%r13),%esi + leal (%rsi,%rbp,1),%esi + vpxor %ymm7,%ymm6,%ymm6 + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + vpxor %ymm8,%ymm6,%ymm6 + addl %r12d,%esi + xorl %ecx,%eax + addl 108(%r13),%edx + leaq 256(%r13),%r13 + vpsrld $30,%ymm6,%ymm8 + vpslld $2,%ymm6,%ymm6 + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + vpor %ymm8,%ymm6,%ymm6 + addl -128(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + vpaddd %ymm11,%ymm6,%ymm9 + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl -124(%r13),%ebx + vmovdqu %ymm9,448(%rsp) + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl -120(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + vpalignr $8,%ymm5,%ymm6,%ymm8 + vpxor %ymm3,%ymm7,%ymm7 + addl -116(%r13),%eax + leal (%rax,%rbx,1),%eax + vpxor %ymm0,%ymm7,%ymm7 + vmovdqu 32(%r11),%ymm11 + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + vpxor %ymm8,%ymm7,%ymm7 + addl %r12d,%eax + xorl %edx,%ebp + addl -96(%r13),%esi + vpsrld $30,%ymm7,%ymm8 + vpslld $2,%ymm7,%ymm7 + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + vpor %ymm8,%ymm7,%ymm7 + addl -92(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + vpaddd %ymm11,%ymm7,%ymm9 + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl -88(%r13),%ecx + vmovdqu %ymm9,480(%rsp) + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl -84(%r13),%ebx + movl %esi,%edi + xorl %eax,%edi + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + andl %edi,%ecx + jmp .Lalign32_2 +.align 32 +.Lalign32_2: + vpalignr $8,%ymm6,%ymm7,%ymm8 + vpxor %ymm4,%ymm0,%ymm0 + addl -64(%r13),%ebp + xorl %esi,%ecx + vpxor %ymm1,%ymm0,%ymm0 + movl %edx,%edi + xorl %esi,%edi + leal (%rcx,%rbp,1),%ebp + vpxor %ymm8,%ymm0,%ymm0 + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + vpsrld $30,%ymm0,%ymm8 + vpslld $2,%ymm0,%ymm0 + addl %r12d,%ebp + andl %edi,%ebx + addl -60(%r13),%eax + xorl %edx,%ebx + movl %ecx,%edi + xorl %edx,%edi + vpor %ymm8,%ymm0,%ymm0 + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + vpaddd %ymm11,%ymm0,%ymm9 + addl %r12d,%eax + andl %edi,%ebp + addl -56(%r13),%esi + xorl %ecx,%ebp + vmovdqu %ymm9,512(%rsp) + movl %ebx,%edi + xorl %ecx,%edi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + andl %edi,%eax + addl -52(%r13),%edx + xorl %ebx,%eax + movl %ebp,%edi + xorl %ebx,%edi + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + andl %edi,%esi + addl -32(%r13),%ecx + xorl %ebp,%esi + movl %eax,%edi + xorl %ebp,%edi + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + andl %edi,%edx + vpalignr $8,%ymm7,%ymm0,%ymm8 + vpxor %ymm5,%ymm1,%ymm1 + addl -28(%r13),%ebx + xorl %eax,%edx + vpxor %ymm2,%ymm1,%ymm1 + movl %esi,%edi + xorl %eax,%edi + leal (%rbx,%rdx,1),%ebx + vpxor %ymm8,%ymm1,%ymm1 + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + vpsrld $30,%ymm1,%ymm8 + vpslld $2,%ymm1,%ymm1 + addl %r12d,%ebx + andl %edi,%ecx + addl -24(%r13),%ebp + xorl %esi,%ecx + movl %edx,%edi + xorl %esi,%edi + vpor %ymm8,%ymm1,%ymm1 + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + vpaddd %ymm11,%ymm1,%ymm9 + addl %r12d,%ebp + andl %edi,%ebx + addl -20(%r13),%eax + xorl %edx,%ebx + vmovdqu %ymm9,544(%rsp) + movl %ecx,%edi + xorl %edx,%edi + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + andl %edi,%ebp + addl 0(%r13),%esi + xorl %ecx,%ebp + movl %ebx,%edi + xorl %ecx,%edi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + andl %edi,%eax + addl 4(%r13),%edx + xorl %ebx,%eax + movl %ebp,%edi + xorl %ebx,%edi + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + andl %edi,%esi + vpalignr $8,%ymm0,%ymm1,%ymm8 + vpxor %ymm6,%ymm2,%ymm2 + addl 8(%r13),%ecx + xorl %ebp,%esi + vpxor %ymm3,%ymm2,%ymm2 + movl %eax,%edi + xorl %ebp,%edi + leal (%rcx,%rsi,1),%ecx + vpxor %ymm8,%ymm2,%ymm2 + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + vpsrld $30,%ymm2,%ymm8 + vpslld $2,%ymm2,%ymm2 + addl %r12d,%ecx + andl %edi,%edx + addl 12(%r13),%ebx + xorl %eax,%edx + movl %esi,%edi + xorl %eax,%edi + vpor %ymm8,%ymm2,%ymm2 + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + vpaddd %ymm11,%ymm2,%ymm9 + addl %r12d,%ebx + andl %edi,%ecx + addl 32(%r13),%ebp + xorl %esi,%ecx + vmovdqu %ymm9,576(%rsp) + movl %edx,%edi + xorl %esi,%edi + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + andl %edi,%ebx + addl 36(%r13),%eax + xorl %edx,%ebx + movl %ecx,%edi + xorl %edx,%edi + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + andl %edi,%ebp + addl 40(%r13),%esi + xorl %ecx,%ebp + movl %ebx,%edi + xorl %ecx,%edi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + andl %edi,%eax + vpalignr $8,%ymm1,%ymm2,%ymm8 + vpxor %ymm7,%ymm3,%ymm3 + addl 44(%r13),%edx + xorl %ebx,%eax + vpxor %ymm4,%ymm3,%ymm3 + movl %ebp,%edi + xorl %ebx,%edi + leal (%rdx,%rax,1),%edx + vpxor %ymm8,%ymm3,%ymm3 + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + vpsrld $30,%ymm3,%ymm8 + vpslld $2,%ymm3,%ymm3 + addl %r12d,%edx + andl %edi,%esi + addl 64(%r13),%ecx + xorl %ebp,%esi + movl %eax,%edi + xorl %ebp,%edi + vpor %ymm8,%ymm3,%ymm3 + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + vpaddd %ymm11,%ymm3,%ymm9 + addl %r12d,%ecx + andl %edi,%edx + addl 68(%r13),%ebx + xorl %eax,%edx + vmovdqu %ymm9,608(%rsp) + movl %esi,%edi + xorl %eax,%edi + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + andl %edi,%ecx + addl 72(%r13),%ebp + xorl %esi,%ecx + movl %edx,%edi + xorl %esi,%edi + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + andl %edi,%ebx + addl 76(%r13),%eax + xorl %edx,%ebx + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl 96(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + addl 100(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl 104(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl 108(%r13),%ebx + leaq 256(%r13),%r13 + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl -128(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl -124(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl -120(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + addl -116(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl -96(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl -92(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl -88(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl -84(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl -64(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + addl -60(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl -56(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl -52(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl -32(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl -28(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl -24(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + addl -20(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + addl %r12d,%edx + leaq 128(%r9),%r13 + leaq 128(%r9),%rdi + cmpq %r10,%r13 + cmovaeq %r9,%r13 + + + addl 0(%r8),%edx + addl 4(%r8),%esi + addl 8(%r8),%ebp + movl %edx,0(%r8) + addl 12(%r8),%ebx + movl %esi,4(%r8) + movl %edx,%eax + addl 16(%r8),%ecx + movl %ebp,%r12d + movl %ebp,8(%r8) + movl %ebx,%edx + + movl %ebx,12(%r8) + movl %esi,%ebp + movl %ecx,16(%r8) + + movl %ecx,%esi + movl %r12d,%ecx + + + cmpq %r10,%r9 + je .Ldone_avx2 + vmovdqu 64(%r11),%ymm6 + cmpq %r10,%rdi + ja .Last_avx2 + + vmovdqu -64(%rdi),%xmm0 + vmovdqu -48(%rdi),%xmm1 + vmovdqu -32(%rdi),%xmm2 + vmovdqu -16(%rdi),%xmm3 + vinserti128 $1,0(%r13),%ymm0,%ymm0 + vinserti128 $1,16(%r13),%ymm1,%ymm1 + vinserti128 $1,32(%r13),%ymm2,%ymm2 + vinserti128 $1,48(%r13),%ymm3,%ymm3 + jmp .Last_avx2 + +.align 32 +.Last_avx2: + leaq 128+16(%rsp),%r13 + rorxl $2,%ebp,%ebx + andnl %edx,%ebp,%edi + andl %ecx,%ebp + xorl %edi,%ebp + subq $-128,%r9 + addl -128(%r13),%esi + andnl %ecx,%eax,%edi + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + andl %ebx,%eax + addl %r12d,%esi + xorl %edi,%eax + addl -124(%r13),%edx + andnl %ebx,%esi,%edi + addl %eax,%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + andl %ebp,%esi + addl %r12d,%edx + xorl %edi,%esi + addl -120(%r13),%ecx + andnl %ebp,%edx,%edi + addl %esi,%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + andl %eax,%edx + addl %r12d,%ecx + xorl %edi,%edx + addl -116(%r13),%ebx + andnl %eax,%ecx,%edi + addl %edx,%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + andl %esi,%ecx + addl %r12d,%ebx + xorl %edi,%ecx + addl -96(%r13),%ebp + andnl %esi,%ebx,%edi + addl %ecx,%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + andl %edx,%ebx + addl %r12d,%ebp + xorl %edi,%ebx + addl -92(%r13),%eax + andnl %edx,%ebp,%edi + addl %ebx,%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + andl %ecx,%ebp + addl %r12d,%eax + xorl %edi,%ebp + addl -88(%r13),%esi + andnl %ecx,%eax,%edi + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + andl %ebx,%eax + addl %r12d,%esi + xorl %edi,%eax + addl -84(%r13),%edx + andnl %ebx,%esi,%edi + addl %eax,%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + andl %ebp,%esi + addl %r12d,%edx + xorl %edi,%esi + addl -64(%r13),%ecx + andnl %ebp,%edx,%edi + addl %esi,%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + andl %eax,%edx + addl %r12d,%ecx + xorl %edi,%edx + addl -60(%r13),%ebx + andnl %eax,%ecx,%edi + addl %edx,%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + andl %esi,%ecx + addl %r12d,%ebx + xorl %edi,%ecx + addl -56(%r13),%ebp + andnl %esi,%ebx,%edi + addl %ecx,%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + andl %edx,%ebx + addl %r12d,%ebp + xorl %edi,%ebx + addl -52(%r13),%eax + andnl %edx,%ebp,%edi + addl %ebx,%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + andl %ecx,%ebp + addl %r12d,%eax + xorl %edi,%ebp + addl -32(%r13),%esi + andnl %ecx,%eax,%edi + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + andl %ebx,%eax + addl %r12d,%esi + xorl %edi,%eax + addl -28(%r13),%edx + andnl %ebx,%esi,%edi + addl %eax,%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + andl %ebp,%esi + addl %r12d,%edx + xorl %edi,%esi + addl -24(%r13),%ecx + andnl %ebp,%edx,%edi + addl %esi,%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + andl %eax,%edx + addl %r12d,%ecx + xorl %edi,%edx + addl -20(%r13),%ebx + andnl %eax,%ecx,%edi + addl %edx,%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + andl %esi,%ecx + addl %r12d,%ebx + xorl %edi,%ecx + addl 0(%r13),%ebp + andnl %esi,%ebx,%edi + addl %ecx,%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + andl %edx,%ebx + addl %r12d,%ebp + xorl %edi,%ebx + addl 4(%r13),%eax + andnl %edx,%ebp,%edi + addl %ebx,%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + andl %ecx,%ebp + addl %r12d,%eax + xorl %edi,%ebp + addl 8(%r13),%esi + andnl %ecx,%eax,%edi + addl %ebp,%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + andl %ebx,%eax + addl %r12d,%esi + xorl %edi,%eax + addl 12(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl 32(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl 36(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl 40(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl 44(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl 64(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + vmovdqu -64(%r11),%ymm11 + vpshufb %ymm6,%ymm0,%ymm0 + addl 68(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl 72(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl 76(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl 96(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl 100(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + vpshufb %ymm6,%ymm1,%ymm1 + vpaddd %ymm11,%ymm0,%ymm8 + addl 104(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + addl 108(%r13),%edx + leaq 256(%r13),%r13 + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl -128(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl -124(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl -120(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + vmovdqu %ymm8,0(%rsp) + vpshufb %ymm6,%ymm2,%ymm2 + vpaddd %ymm11,%ymm1,%ymm9 + addl -116(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl -96(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + addl -92(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + addl -88(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl -84(%r13),%ebx + movl %esi,%edi + xorl %eax,%edi + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + andl %edi,%ecx + vmovdqu %ymm9,32(%rsp) + vpshufb %ymm6,%ymm3,%ymm3 + vpaddd %ymm11,%ymm2,%ymm6 + addl -64(%r13),%ebp + xorl %esi,%ecx + movl %edx,%edi + xorl %esi,%edi + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + andl %edi,%ebx + addl -60(%r13),%eax + xorl %edx,%ebx + movl %ecx,%edi + xorl %edx,%edi + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + andl %edi,%ebp + addl -56(%r13),%esi + xorl %ecx,%ebp + movl %ebx,%edi + xorl %ecx,%edi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + andl %edi,%eax + addl -52(%r13),%edx + xorl %ebx,%eax + movl %ebp,%edi + xorl %ebx,%edi + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + andl %edi,%esi + addl -32(%r13),%ecx + xorl %ebp,%esi + movl %eax,%edi + xorl %ebp,%edi + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + andl %edi,%edx + jmp .Lalign32_3 +.align 32 +.Lalign32_3: + vmovdqu %ymm6,64(%rsp) + vpaddd %ymm11,%ymm3,%ymm7 + addl -28(%r13),%ebx + xorl %eax,%edx + movl %esi,%edi + xorl %eax,%edi + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + andl %edi,%ecx + addl -24(%r13),%ebp + xorl %esi,%ecx + movl %edx,%edi + xorl %esi,%edi + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + andl %edi,%ebx + addl -20(%r13),%eax + xorl %edx,%ebx + movl %ecx,%edi + xorl %edx,%edi + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + andl %edi,%ebp + addl 0(%r13),%esi + xorl %ecx,%ebp + movl %ebx,%edi + xorl %ecx,%edi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + andl %edi,%eax + addl 4(%r13),%edx + xorl %ebx,%eax + movl %ebp,%edi + xorl %ebx,%edi + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + andl %edi,%esi + vmovdqu %ymm7,96(%rsp) + addl 8(%r13),%ecx + xorl %ebp,%esi + movl %eax,%edi + xorl %ebp,%edi + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + andl %edi,%edx + addl 12(%r13),%ebx + xorl %eax,%edx + movl %esi,%edi + xorl %eax,%edi + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + andl %edi,%ecx + addl 32(%r13),%ebp + xorl %esi,%ecx + movl %edx,%edi + xorl %esi,%edi + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + andl %edi,%ebx + addl 36(%r13),%eax + xorl %edx,%ebx + movl %ecx,%edi + xorl %edx,%edi + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + andl %edi,%ebp + addl 40(%r13),%esi + xorl %ecx,%ebp + movl %ebx,%edi + xorl %ecx,%edi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + andl %edi,%eax + vpalignr $8,%ymm0,%ymm1,%ymm4 + addl 44(%r13),%edx + xorl %ebx,%eax + movl %ebp,%edi + xorl %ebx,%edi + vpsrldq $4,%ymm3,%ymm8 + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + vpxor %ymm0,%ymm4,%ymm4 + vpxor %ymm2,%ymm8,%ymm8 + xorl %ebp,%esi + addl %r12d,%edx + vpxor %ymm8,%ymm4,%ymm4 + andl %edi,%esi + addl 64(%r13),%ecx + xorl %ebp,%esi + movl %eax,%edi + vpsrld $31,%ymm4,%ymm8 + xorl %ebp,%edi + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + vpslldq $12,%ymm4,%ymm10 + vpaddd %ymm4,%ymm4,%ymm4 + rorxl $2,%edx,%esi + xorl %eax,%edx + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm4,%ymm4 + addl %r12d,%ecx + andl %edi,%edx + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm4,%ymm4 + addl 68(%r13),%ebx + xorl %eax,%edx + vpxor %ymm10,%ymm4,%ymm4 + movl %esi,%edi + xorl %eax,%edi + leal (%rbx,%rdx,1),%ebx + vpaddd %ymm11,%ymm4,%ymm9 + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + vmovdqu %ymm9,128(%rsp) + addl %r12d,%ebx + andl %edi,%ecx + addl 72(%r13),%ebp + xorl %esi,%ecx + movl %edx,%edi + xorl %esi,%edi + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + andl %edi,%ebx + addl 76(%r13),%eax + xorl %edx,%ebx + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + vpalignr $8,%ymm1,%ymm2,%ymm5 + addl 96(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + vpsrldq $4,%ymm4,%ymm8 + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + vpxor %ymm1,%ymm5,%ymm5 + vpxor %ymm3,%ymm8,%ymm8 + addl 100(%r13),%edx + leal (%rdx,%rax,1),%edx + vpxor %ymm8,%ymm5,%ymm5 + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + xorl %ebp,%esi + addl %r12d,%edx + vpsrld $31,%ymm5,%ymm8 + vmovdqu -32(%r11),%ymm11 + xorl %ebx,%esi + addl 104(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + vpslldq $12,%ymm5,%ymm10 + vpaddd %ymm5,%ymm5,%ymm5 + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm5,%ymm5 + xorl %eax,%edx + addl %r12d,%ecx + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm5,%ymm5 + xorl %ebp,%edx + addl 108(%r13),%ebx + leaq 256(%r13),%r13 + vpxor %ymm10,%ymm5,%ymm5 + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + vpaddd %ymm11,%ymm5,%ymm9 + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + vmovdqu %ymm9,160(%rsp) + addl -128(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + vpalignr $8,%ymm2,%ymm3,%ymm6 + addl -124(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + vpsrldq $4,%ymm5,%ymm8 + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + vpxor %ymm2,%ymm6,%ymm6 + vpxor %ymm4,%ymm8,%ymm8 + addl -120(%r13),%esi + leal (%rsi,%rbp,1),%esi + vpxor %ymm8,%ymm6,%ymm6 + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + vpsrld $31,%ymm6,%ymm8 + xorl %ecx,%eax + addl -116(%r13),%edx + leal (%rdx,%rax,1),%edx + vpslldq $12,%ymm6,%ymm10 + vpaddd %ymm6,%ymm6,%ymm6 + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm6,%ymm6 + xorl %ebp,%esi + addl %r12d,%edx + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm6,%ymm6 + xorl %ebx,%esi + addl -96(%r13),%ecx + vpxor %ymm10,%ymm6,%ymm6 + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + vpaddd %ymm11,%ymm6,%ymm9 + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + vmovdqu %ymm9,192(%rsp) + addl -92(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + vpalignr $8,%ymm3,%ymm4,%ymm7 + addl -88(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + vpsrldq $4,%ymm6,%ymm8 + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + vpxor %ymm3,%ymm7,%ymm7 + vpxor %ymm5,%ymm8,%ymm8 + addl -84(%r13),%eax + leal (%rax,%rbx,1),%eax + vpxor %ymm8,%ymm7,%ymm7 + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + vpsrld $31,%ymm7,%ymm8 + xorl %edx,%ebp + addl -64(%r13),%esi + leal (%rsi,%rbp,1),%esi + vpslldq $12,%ymm7,%ymm10 + vpaddd %ymm7,%ymm7,%ymm7 + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + vpsrld $30,%ymm10,%ymm9 + vpor %ymm8,%ymm7,%ymm7 + xorl %ebx,%eax + addl %r12d,%esi + vpslld $2,%ymm10,%ymm10 + vpxor %ymm9,%ymm7,%ymm7 + xorl %ecx,%eax + addl -60(%r13),%edx + vpxor %ymm10,%ymm7,%ymm7 + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + rorxl $2,%esi,%eax + vpaddd %ymm11,%ymm7,%ymm9 + xorl %ebp,%esi + addl %r12d,%edx + xorl %ebx,%esi + vmovdqu %ymm9,224(%rsp) + addl -56(%r13),%ecx + leal (%rcx,%rsi,1),%ecx + rorxl $27,%edx,%r12d + rorxl $2,%edx,%esi + xorl %eax,%edx + addl %r12d,%ecx + xorl %ebp,%edx + addl -52(%r13),%ebx + leal (%rbx,%rdx,1),%ebx + rorxl $27,%ecx,%r12d + rorxl $2,%ecx,%edx + xorl %esi,%ecx + addl %r12d,%ebx + xorl %eax,%ecx + addl -32(%r13),%ebp + leal (%rcx,%rbp,1),%ebp + rorxl $27,%ebx,%r12d + rorxl $2,%ebx,%ecx + xorl %edx,%ebx + addl %r12d,%ebp + xorl %esi,%ebx + addl -28(%r13),%eax + leal (%rax,%rbx,1),%eax + rorxl $27,%ebp,%r12d + rorxl $2,%ebp,%ebx + xorl %ecx,%ebp + addl %r12d,%eax + xorl %edx,%ebp + addl -24(%r13),%esi + leal (%rsi,%rbp,1),%esi + rorxl $27,%eax,%r12d + rorxl $2,%eax,%ebp + xorl %ebx,%eax + addl %r12d,%esi + xorl %ecx,%eax + addl -20(%r13),%edx + leal (%rdx,%rax,1),%edx + rorxl $27,%esi,%r12d + addl %r12d,%edx + leaq 128(%rsp),%r13 + + + addl 0(%r8),%edx + addl 4(%r8),%esi + addl 8(%r8),%ebp + movl %edx,0(%r8) + addl 12(%r8),%ebx + movl %esi,4(%r8) + movl %edx,%eax + addl 16(%r8),%ecx + movl %ebp,%r12d + movl %ebp,8(%r8) + movl %ebx,%edx + + movl %ebx,12(%r8) + movl %esi,%ebp + movl %ecx,16(%r8) + + movl %ecx,%esi + movl %r12d,%ecx + + + cmpq %r10,%r9 + jbe .Loop_avx2 + +.Ldone_avx2: + vzeroupper + leaq (%r14),%rsi + movq -40(%rsi),%r14 + movq -32(%rsi),%r13 + movq -24(%rsi),%r12 + movq -16(%rsi),%rbp + movq -8(%rsi),%rbx + leaq (%rsi),%rsp +.Lepilogue_avx2: + .byte 0xf3,0xc3 +.size sha1_block_data_order_avx2,.-sha1_block_data_order_avx2 .align 64 K_XX_XX: .long 0x5a827999,0x5a827999,0x5a827999,0x5a827999 |