diff options
Diffstat (limited to 'linux-x86_64/crypto/sha/sha256-x86_64.S')
-rw-r--r-- | linux-x86_64/crypto/sha/sha256-x86_64.S | 54 |
1 files changed, 27 insertions, 27 deletions
diff --git a/linux-x86_64/crypto/sha/sha256-x86_64.S b/linux-x86_64/crypto/sha/sha256-x86_64.S index 445b497e..273b7a5e 100644 --- a/linux-x86_64/crypto/sha/sha256-x86_64.S +++ b/linux-x86_64/crypto/sha/sha256-x86_64.S @@ -19,13 +19,13 @@ sha256_block_data_order: je .Lavx_shortcut testl $512,%r10d jnz .Lssse3_shortcut + movq %rsp,%rax pushq %rbx pushq %rbp pushq %r12 pushq %r13 pushq %r14 pushq %r15 - movq %rsp,%r11 shlq $4,%rdx subq $64+32,%rsp leaq (%rsi,%rdx,4),%rdx @@ -33,7 +33,7 @@ sha256_block_data_order: movq %rdi,64+0(%rsp) movq %rsi,64+8(%rsp) movq %rdx,64+16(%rsp) - movq %r11,64+24(%rsp) + movq %rax,64+24(%rsp) .Lprologue: movl 0(%rdi),%eax @@ -1698,13 +1698,13 @@ sha256_block_data_order: jb .Lloop movq 64+24(%rsp),%rsi - movq (%rsi),%r15 - movq 8(%rsi),%r14 - movq 16(%rsi),%r13 - movq 24(%rsi),%r12 - movq 32(%rsi),%rbp - movq 40(%rsi),%rbx - leaq 48(%rsi),%rsp + movq -48(%rsi),%r15 + movq -40(%rsi),%r14 + movq -32(%rsi),%r13 + movq -24(%rsi),%r12 + movq -16(%rsi),%rbp + movq -8(%rsi),%rbx + leaq (%rsi),%rsp .Lepilogue: .byte 0xf3,0xc3 .size sha256_block_data_order,.-sha256_block_data_order @@ -1755,13 +1755,13 @@ K256: .align 64 sha256_block_data_order_ssse3: .Lssse3_shortcut: + movq %rsp,%rax pushq %rbx pushq %rbp pushq %r12 pushq %r13 pushq %r14 pushq %r15 - movq %rsp,%r11 shlq $4,%rdx subq $96,%rsp leaq (%rsi,%rdx,4),%rdx @@ -1769,7 +1769,7 @@ sha256_block_data_order_ssse3: movq %rdi,64+0(%rsp) movq %rsi,64+8(%rsp) movq %rdx,64+16(%rsp) - movq %r11,64+24(%rsp) + movq %rax,64+24(%rsp) .Lprologue_ssse3: movl 0(%rdi),%eax @@ -2836,13 +2836,13 @@ sha256_block_data_order_ssse3: jb .Lloop_ssse3 movq 64+24(%rsp),%rsi - movq (%rsi),%r15 - movq 8(%rsi),%r14 - movq 16(%rsi),%r13 - movq 24(%rsi),%r12 - movq 32(%rsi),%rbp - movq 40(%rsi),%rbx - leaq 48(%rsi),%rsp + movq -48(%rsi),%r15 + movq -40(%rsi),%r14 + movq -32(%rsi),%r13 + movq -24(%rsi),%r12 + movq -16(%rsi),%rbp + movq -8(%rsi),%rbx + leaq (%rsi),%rsp .Lepilogue_ssse3: .byte 0xf3,0xc3 .size sha256_block_data_order_ssse3,.-sha256_block_data_order_ssse3 @@ -2850,13 +2850,13 @@ sha256_block_data_order_ssse3: .align 64 sha256_block_data_order_avx: .Lavx_shortcut: + movq %rsp,%rax pushq %rbx pushq %rbp pushq %r12 pushq %r13 pushq %r14 pushq %r15 - movq %rsp,%r11 shlq $4,%rdx subq $96,%rsp leaq (%rsi,%rdx,4),%rdx @@ -2864,7 +2864,7 @@ sha256_block_data_order_avx: movq %rdi,64+0(%rsp) movq %rsi,64+8(%rsp) movq %rdx,64+16(%rsp) - movq %r11,64+24(%rsp) + movq %rax,64+24(%rsp) .Lprologue_avx: vzeroupper @@ -3893,13 +3893,13 @@ sha256_block_data_order_avx: movq 64+24(%rsp),%rsi vzeroupper - movq (%rsi),%r15 - movq 8(%rsi),%r14 - movq 16(%rsi),%r13 - movq 24(%rsi),%r12 - movq 32(%rsi),%rbp - movq 40(%rsi),%rbx - leaq 48(%rsi),%rsp + movq -48(%rsi),%r15 + 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 sha256_block_data_order_avx,.-sha256_block_data_order_avx |