Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(223)

Unified Diff: third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm

Issue 1938433002: Revert BoringSSL Roll (Closed) Base URL: git@github.com:dart-lang/sdk.git@master
Patch Set: Created 4 years, 8 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « third_party/boringssl/win-x86_64/crypto/sha/sha256-x86_64.asm ('k') | no next file » | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm
diff --git a/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm b/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm
index 71449cd24fd166bff2a5a25d3614e5c85d1dde4a..b76cc0edb96ea5793c2225df8c55260a9248f0ab 100644
--- a/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm
+++ b/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm
@@ -19,17 +19,6 @@ $L$SEH_begin_sha512_block_data_order:
mov rdx,r8
- lea r11,[OPENSSL_ia32cap_P]
- mov r9d,DWORD[r11]
- mov r10d,DWORD[4+r11]
- mov r11d,DWORD[8+r11]
- test r10d,2048
- jnz NEAR $L$xop_shortcut
- and r9d,1073741824
- and r10d,268435968
- or r10d,r9d
- cmp r10d,1342177792
- je NEAR $L$avx_shortcut
push rbx
push rbp
push r12
@@ -1812,2296 +1801,20 @@ DB 110,115,102,111,114,109,32,102,111,114,32,120,56,54,95,54
DB 52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121
DB 32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46
DB 111,114,103,62,0
+EXTERN __imp_RtlVirtualUnwind
-ALIGN 64
-sha512_block_data_order_xop:
- mov QWORD[8+rsp],rdi ;WIN64 prologue
- mov QWORD[16+rsp],rsi
- mov rax,rsp
-$L$SEH_begin_sha512_block_data_order_xop:
- mov rdi,rcx
- mov rsi,rdx
- mov rdx,r8
-
-
-$L$xop_shortcut:
+ALIGN 16
+se_handler:
+ push rsi
+ push rdi
push rbx
push rbp
push r12
push r13
push r14
push r15
- mov r11,rsp
- shl rdx,4
- sub rsp,256
- lea rdx,[rdx*8+rsi]
- and rsp,-64
- mov QWORD[((128+0))+rsp],rdi
- mov QWORD[((128+8))+rsp],rsi
- mov QWORD[((128+16))+rsp],rdx
- mov QWORD[((128+24))+rsp],r11
- movaps XMMWORD[(128+32)+rsp],xmm6
- movaps XMMWORD[(128+48)+rsp],xmm7
- movaps XMMWORD[(128+64)+rsp],xmm8
- movaps XMMWORD[(128+80)+rsp],xmm9
- movaps XMMWORD[(128+96)+rsp],xmm10
- movaps XMMWORD[(128+112)+rsp],xmm11
-$L$prologue_xop:
-
- vzeroupper
- mov rax,QWORD[rdi]
- mov rbx,QWORD[8+rdi]
- mov rcx,QWORD[16+rdi]
- mov rdx,QWORD[24+rdi]
- mov r8,QWORD[32+rdi]
- mov r9,QWORD[40+rdi]
- mov r10,QWORD[48+rdi]
- mov r11,QWORD[56+rdi]
- jmp NEAR $L$loop_xop
-ALIGN 16
-$L$loop_xop:
- vmovdqa xmm11,XMMWORD[((K512+1280))]
- vmovdqu xmm0,XMMWORD[rsi]
- lea rbp,[((K512+128))]
- vmovdqu xmm1,XMMWORD[16+rsi]
- vmovdqu xmm2,XMMWORD[32+rsi]
- vpshufb xmm0,xmm0,xmm11
- vmovdqu xmm3,XMMWORD[48+rsi]
- vpshufb xmm1,xmm1,xmm11
- vmovdqu xmm4,XMMWORD[64+rsi]
- vpshufb xmm2,xmm2,xmm11
- vmovdqu xmm5,XMMWORD[80+rsi]
- vpshufb xmm3,xmm3,xmm11
- vmovdqu xmm6,XMMWORD[96+rsi]
- vpshufb xmm4,xmm4,xmm11
- vmovdqu xmm7,XMMWORD[112+rsi]
- vpshufb xmm5,xmm5,xmm11
- vpaddq xmm8,xmm0,XMMWORD[((-128))+rbp]
- vpshufb xmm6,xmm6,xmm11
- vpaddq xmm9,xmm1,XMMWORD[((-96))+rbp]
- vpshufb xmm7,xmm7,xmm11
- vpaddq xmm10,xmm2,XMMWORD[((-64))+rbp]
- vpaddq xmm11,xmm3,XMMWORD[((-32))+rbp]
- vmovdqa XMMWORD[rsp],xmm8
- vpaddq xmm8,xmm4,XMMWORD[rbp]
- vmovdqa XMMWORD[16+rsp],xmm9
- vpaddq xmm9,xmm5,XMMWORD[32+rbp]
- vmovdqa XMMWORD[32+rsp],xmm10
- vpaddq xmm10,xmm6,XMMWORD[64+rbp]
- vmovdqa XMMWORD[48+rsp],xmm11
- vpaddq xmm11,xmm7,XMMWORD[96+rbp]
- vmovdqa XMMWORD[64+rsp],xmm8
- mov r14,rax
- vmovdqa XMMWORD[80+rsp],xmm9
- mov rdi,rbx
- vmovdqa XMMWORD[96+rsp],xmm10
- xor rdi,rcx
- vmovdqa XMMWORD[112+rsp],xmm11
- mov r13,r8
- jmp NEAR $L$xop_00_47
-
-ALIGN 16
-$L$xop_00_47:
- add rbp,256
- vpalignr xmm8,xmm1,xmm0,8
- ror r13,23
- mov rax,r14
- vpalignr xmm11,xmm5,xmm4,8
- mov r12,r9
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,r8
- xor r12,r10
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,rax
- vpaddq xmm0,xmm0,xmm11
- and r12,r8
- xor r13,r8
- add r11,QWORD[rsp]
- mov r15,rax
-DB 143,72,120,195,209,7
- xor r12,r10
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,rbx
- add r11,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,223,3
- xor r14,rax
- add r11,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rbx
- ror r14,28
- vpsrlq xmm10,xmm7,6
- add rdx,r11
- add r11,rdi
- vpaddq xmm0,xmm0,xmm8
- mov r13,rdx
- add r14,r11
-DB 143,72,120,195,203,42
- ror r13,23
- mov r11,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,r8
- ror r14,5
- xor r13,rdx
- xor r12,r9
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,r11
- and r12,rdx
- xor r13,rdx
- vpaddq xmm0,xmm0,xmm11
- add r10,QWORD[8+rsp]
- mov rdi,r11
- xor r12,r9
- ror r14,6
- vpaddq xmm10,xmm0,XMMWORD[((-128))+rbp]
- xor rdi,rax
- add r10,r12
- ror r13,14
- and r15,rdi
- xor r14,r11
- add r10,r13
- xor r15,rax
- ror r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- vmovdqa XMMWORD[rsp],xmm10
- vpalignr xmm8,xmm2,xmm1,8
- ror r13,23
- mov r10,r14
- vpalignr xmm11,xmm6,xmm5,8
- mov r12,rdx
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,rcx
- xor r12,r8
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,r10
- vpaddq xmm1,xmm1,xmm11
- and r12,rcx
- xor r13,rcx
- add r9,QWORD[16+rsp]
- mov r15,r10
-DB 143,72,120,195,209,7
- xor r12,r8
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,r11
- add r9,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,216,3
- xor r14,r10
- add r9,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r11
- ror r14,28
- vpsrlq xmm10,xmm0,6
- add rbx,r9
- add r9,rdi
- vpaddq xmm1,xmm1,xmm8
- mov r13,rbx
- add r14,r9
-DB 143,72,120,195,203,42
- ror r13,23
- mov r9,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,rcx
- ror r14,5
- xor r13,rbx
- xor r12,rdx
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,r9
- and r12,rbx
- xor r13,rbx
- vpaddq xmm1,xmm1,xmm11
- add r8,QWORD[24+rsp]
- mov rdi,r9
- xor r12,rdx
- ror r14,6
- vpaddq xmm10,xmm1,XMMWORD[((-96))+rbp]
- xor rdi,r10
- add r8,r12
- ror r13,14
- and r15,rdi
- xor r14,r9
- add r8,r13
- xor r15,r10
- ror r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- vmovdqa XMMWORD[16+rsp],xmm10
- vpalignr xmm8,xmm3,xmm2,8
- ror r13,23
- mov r8,r14
- vpalignr xmm11,xmm7,xmm6,8
- mov r12,rbx
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,rax
- xor r12,rcx
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,r8
- vpaddq xmm2,xmm2,xmm11
- and r12,rax
- xor r13,rax
- add rdx,QWORD[32+rsp]
- mov r15,r8
-DB 143,72,120,195,209,7
- xor r12,rcx
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,r9
- add rdx,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,217,3
- xor r14,r8
- add rdx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r9
- ror r14,28
- vpsrlq xmm10,xmm1,6
- add r11,rdx
- add rdx,rdi
- vpaddq xmm2,xmm2,xmm8
- mov r13,r11
- add r14,rdx
-DB 143,72,120,195,203,42
- ror r13,23
- mov rdx,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,rax
- ror r14,5
- xor r13,r11
- xor r12,rbx
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,rdx
- and r12,r11
- xor r13,r11
- vpaddq xmm2,xmm2,xmm11
- add rcx,QWORD[40+rsp]
- mov rdi,rdx
- xor r12,rbx
- ror r14,6
- vpaddq xmm10,xmm2,XMMWORD[((-64))+rbp]
- xor rdi,r8
- add rcx,r12
- ror r13,14
- and r15,rdi
- xor r14,rdx
- add rcx,r13
- xor r15,r8
- ror r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- vmovdqa XMMWORD[32+rsp],xmm10
- vpalignr xmm8,xmm4,xmm3,8
- ror r13,23
- mov rcx,r14
- vpalignr xmm11,xmm0,xmm7,8
- mov r12,r11
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,r10
- xor r12,rax
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,rcx
- vpaddq xmm3,xmm3,xmm11
- and r12,r10
- xor r13,r10
- add rbx,QWORD[48+rsp]
- mov r15,rcx
-DB 143,72,120,195,209,7
- xor r12,rax
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,rdx
- add rbx,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,218,3
- xor r14,rcx
- add rbx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rdx
- ror r14,28
- vpsrlq xmm10,xmm2,6
- add r9,rbx
- add rbx,rdi
- vpaddq xmm3,xmm3,xmm8
- mov r13,r9
- add r14,rbx
-DB 143,72,120,195,203,42
- ror r13,23
- mov rbx,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,r10
- ror r14,5
- xor r13,r9
- xor r12,r11
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,rbx
- and r12,r9
- xor r13,r9
- vpaddq xmm3,xmm3,xmm11
- add rax,QWORD[56+rsp]
- mov rdi,rbx
- xor r12,r11
- ror r14,6
- vpaddq xmm10,xmm3,XMMWORD[((-32))+rbp]
- xor rdi,rcx
- add rax,r12
- ror r13,14
- and r15,rdi
- xor r14,rbx
- add rax,r13
- xor r15,rcx
- ror r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- vmovdqa XMMWORD[48+rsp],xmm10
- vpalignr xmm8,xmm5,xmm4,8
- ror r13,23
- mov rax,r14
- vpalignr xmm11,xmm1,xmm0,8
- mov r12,r9
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,r8
- xor r12,r10
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,rax
- vpaddq xmm4,xmm4,xmm11
- and r12,r8
- xor r13,r8
- add r11,QWORD[64+rsp]
- mov r15,rax
-DB 143,72,120,195,209,7
- xor r12,r10
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,rbx
- add r11,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,219,3
- xor r14,rax
- add r11,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rbx
- ror r14,28
- vpsrlq xmm10,xmm3,6
- add rdx,r11
- add r11,rdi
- vpaddq xmm4,xmm4,xmm8
- mov r13,rdx
- add r14,r11
-DB 143,72,120,195,203,42
- ror r13,23
- mov r11,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,r8
- ror r14,5
- xor r13,rdx
- xor r12,r9
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,r11
- and r12,rdx
- xor r13,rdx
- vpaddq xmm4,xmm4,xmm11
- add r10,QWORD[72+rsp]
- mov rdi,r11
- xor r12,r9
- ror r14,6
- vpaddq xmm10,xmm4,XMMWORD[rbp]
- xor rdi,rax
- add r10,r12
- ror r13,14
- and r15,rdi
- xor r14,r11
- add r10,r13
- xor r15,rax
- ror r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- vmovdqa XMMWORD[64+rsp],xmm10
- vpalignr xmm8,xmm6,xmm5,8
- ror r13,23
- mov r10,r14
- vpalignr xmm11,xmm2,xmm1,8
- mov r12,rdx
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,rcx
- xor r12,r8
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,r10
- vpaddq xmm5,xmm5,xmm11
- and r12,rcx
- xor r13,rcx
- add r9,QWORD[80+rsp]
- mov r15,r10
-DB 143,72,120,195,209,7
- xor r12,r8
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,r11
- add r9,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,220,3
- xor r14,r10
- add r9,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r11
- ror r14,28
- vpsrlq xmm10,xmm4,6
- add rbx,r9
- add r9,rdi
- vpaddq xmm5,xmm5,xmm8
- mov r13,rbx
- add r14,r9
-DB 143,72,120,195,203,42
- ror r13,23
- mov r9,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,rcx
- ror r14,5
- xor r13,rbx
- xor r12,rdx
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,r9
- and r12,rbx
- xor r13,rbx
- vpaddq xmm5,xmm5,xmm11
- add r8,QWORD[88+rsp]
- mov rdi,r9
- xor r12,rdx
- ror r14,6
- vpaddq xmm10,xmm5,XMMWORD[32+rbp]
- xor rdi,r10
- add r8,r12
- ror r13,14
- and r15,rdi
- xor r14,r9
- add r8,r13
- xor r15,r10
- ror r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- vmovdqa XMMWORD[80+rsp],xmm10
- vpalignr xmm8,xmm7,xmm6,8
- ror r13,23
- mov r8,r14
- vpalignr xmm11,xmm3,xmm2,8
- mov r12,rbx
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,rax
- xor r12,rcx
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,r8
- vpaddq xmm6,xmm6,xmm11
- and r12,rax
- xor r13,rax
- add rdx,QWORD[96+rsp]
- mov r15,r8
-DB 143,72,120,195,209,7
- xor r12,rcx
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,r9
- add rdx,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,221,3
- xor r14,r8
- add rdx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r9
- ror r14,28
- vpsrlq xmm10,xmm5,6
- add r11,rdx
- add rdx,rdi
- vpaddq xmm6,xmm6,xmm8
- mov r13,r11
- add r14,rdx
-DB 143,72,120,195,203,42
- ror r13,23
- mov rdx,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,rax
- ror r14,5
- xor r13,r11
- xor r12,rbx
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,rdx
- and r12,r11
- xor r13,r11
- vpaddq xmm6,xmm6,xmm11
- add rcx,QWORD[104+rsp]
- mov rdi,rdx
- xor r12,rbx
- ror r14,6
- vpaddq xmm10,xmm6,XMMWORD[64+rbp]
- xor rdi,r8
- add rcx,r12
- ror r13,14
- and r15,rdi
- xor r14,rdx
- add rcx,r13
- xor r15,r8
- ror r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- vmovdqa XMMWORD[96+rsp],xmm10
- vpalignr xmm8,xmm0,xmm7,8
- ror r13,23
- mov rcx,r14
- vpalignr xmm11,xmm4,xmm3,8
- mov r12,r11
- ror r14,5
-DB 143,72,120,195,200,56
- xor r13,r10
- xor r12,rax
- vpsrlq xmm8,xmm8,7
- ror r13,4
- xor r14,rcx
- vpaddq xmm7,xmm7,xmm11
- and r12,r10
- xor r13,r10
- add rbx,QWORD[112+rsp]
- mov r15,rcx
-DB 143,72,120,195,209,7
- xor r12,rax
- ror r14,6
- vpxor xmm8,xmm8,xmm9
- xor r15,rdx
- add rbx,r12
- ror r13,14
- and rdi,r15
-DB 143,104,120,195,222,3
- xor r14,rcx
- add rbx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rdx
- ror r14,28
- vpsrlq xmm10,xmm6,6
- add r9,rbx
- add rbx,rdi
- vpaddq xmm7,xmm7,xmm8
- mov r13,r9
- add r14,rbx
-DB 143,72,120,195,203,42
- ror r13,23
- mov rbx,r14
- vpxor xmm11,xmm11,xmm10
- mov r12,r10
- ror r14,5
- xor r13,r9
- xor r12,r11
- vpxor xmm11,xmm11,xmm9
- ror r13,4
- xor r14,rbx
- and r12,r9
- xor r13,r9
- vpaddq xmm7,xmm7,xmm11
- add rax,QWORD[120+rsp]
- mov rdi,rbx
- xor r12,r11
- ror r14,6
- vpaddq xmm10,xmm7,XMMWORD[96+rbp]
- xor rdi,rcx
- add rax,r12
- ror r13,14
- and r15,rdi
- xor r14,rbx
- add rax,r13
- xor r15,rcx
- ror r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- vmovdqa XMMWORD[112+rsp],xmm10
- cmp BYTE[135+rbp],0
- jne NEAR $L$xop_00_47
- ror r13,23
- mov rax,r14
- mov r12,r9
- ror r14,5
- xor r13,r8
- xor r12,r10
- ror r13,4
- xor r14,rax
- and r12,r8
- xor r13,r8
- add r11,QWORD[rsp]
- mov r15,rax
- xor r12,r10
- ror r14,6
- xor r15,rbx
- add r11,r12
- ror r13,14
- and rdi,r15
- xor r14,rax
- add r11,r13
- xor rdi,rbx
- ror r14,28
- add rdx,r11
- add r11,rdi
- mov r13,rdx
- add r14,r11
- ror r13,23
- mov r11,r14
- mov r12,r8
- ror r14,5
- xor r13,rdx
- xor r12,r9
- ror r13,4
- xor r14,r11
- and r12,rdx
- xor r13,rdx
- add r10,QWORD[8+rsp]
- mov rdi,r11
- xor r12,r9
- ror r14,6
- xor rdi,rax
- add r10,r12
- ror r13,14
- and r15,rdi
- xor r14,r11
- add r10,r13
- xor r15,rax
- ror r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- ror r13,23
- mov r10,r14
- mov r12,rdx
- ror r14,5
- xor r13,rcx
- xor r12,r8
- ror r13,4
- xor r14,r10
- and r12,rcx
- xor r13,rcx
- add r9,QWORD[16+rsp]
- mov r15,r10
- xor r12,r8
- ror r14,6
- xor r15,r11
- add r9,r12
- ror r13,14
- and rdi,r15
- xor r14,r10
- add r9,r13
- xor rdi,r11
- ror r14,28
- add rbx,r9
- add r9,rdi
- mov r13,rbx
- add r14,r9
- ror r13,23
- mov r9,r14
- mov r12,rcx
- ror r14,5
- xor r13,rbx
- xor r12,rdx
- ror r13,4
- xor r14,r9
- and r12,rbx
- xor r13,rbx
- add r8,QWORD[24+rsp]
- mov rdi,r9
- xor r12,rdx
- ror r14,6
- xor rdi,r10
- add r8,r12
- ror r13,14
- and r15,rdi
- xor r14,r9
- add r8,r13
- xor r15,r10
- ror r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- ror r13,23
- mov r8,r14
- mov r12,rbx
- ror r14,5
- xor r13,rax
- xor r12,rcx
- ror r13,4
- xor r14,r8
- and r12,rax
- xor r13,rax
- add rdx,QWORD[32+rsp]
- mov r15,r8
- xor r12,rcx
- ror r14,6
- xor r15,r9
- add rdx,r12
- ror r13,14
- and rdi,r15
- xor r14,r8
- add rdx,r13
- xor rdi,r9
- ror r14,28
- add r11,rdx
- add rdx,rdi
- mov r13,r11
- add r14,rdx
- ror r13,23
- mov rdx,r14
- mov r12,rax
- ror r14,5
- xor r13,r11
- xor r12,rbx
- ror r13,4
- xor r14,rdx
- and r12,r11
- xor r13,r11
- add rcx,QWORD[40+rsp]
- mov rdi,rdx
- xor r12,rbx
- ror r14,6
- xor rdi,r8
- add rcx,r12
- ror r13,14
- and r15,rdi
- xor r14,rdx
- add rcx,r13
- xor r15,r8
- ror r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- ror r13,23
- mov rcx,r14
- mov r12,r11
- ror r14,5
- xor r13,r10
- xor r12,rax
- ror r13,4
- xor r14,rcx
- and r12,r10
- xor r13,r10
- add rbx,QWORD[48+rsp]
- mov r15,rcx
- xor r12,rax
- ror r14,6
- xor r15,rdx
- add rbx,r12
- ror r13,14
- and rdi,r15
- xor r14,rcx
- add rbx,r13
- xor rdi,rdx
- ror r14,28
- add r9,rbx
- add rbx,rdi
- mov r13,r9
- add r14,rbx
- ror r13,23
- mov rbx,r14
- mov r12,r10
- ror r14,5
- xor r13,r9
- xor r12,r11
- ror r13,4
- xor r14,rbx
- and r12,r9
- xor r13,r9
- add rax,QWORD[56+rsp]
- mov rdi,rbx
- xor r12,r11
- ror r14,6
- xor rdi,rcx
- add rax,r12
- ror r13,14
- and r15,rdi
- xor r14,rbx
- add rax,r13
- xor r15,rcx
- ror r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- ror r13,23
- mov rax,r14
- mov r12,r9
- ror r14,5
- xor r13,r8
- xor r12,r10
- ror r13,4
- xor r14,rax
- and r12,r8
- xor r13,r8
- add r11,QWORD[64+rsp]
- mov r15,rax
- xor r12,r10
- ror r14,6
- xor r15,rbx
- add r11,r12
- ror r13,14
- and rdi,r15
- xor r14,rax
- add r11,r13
- xor rdi,rbx
- ror r14,28
- add rdx,r11
- add r11,rdi
- mov r13,rdx
- add r14,r11
- ror r13,23
- mov r11,r14
- mov r12,r8
- ror r14,5
- xor r13,rdx
- xor r12,r9
- ror r13,4
- xor r14,r11
- and r12,rdx
- xor r13,rdx
- add r10,QWORD[72+rsp]
- mov rdi,r11
- xor r12,r9
- ror r14,6
- xor rdi,rax
- add r10,r12
- ror r13,14
- and r15,rdi
- xor r14,r11
- add r10,r13
- xor r15,rax
- ror r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- ror r13,23
- mov r10,r14
- mov r12,rdx
- ror r14,5
- xor r13,rcx
- xor r12,r8
- ror r13,4
- xor r14,r10
- and r12,rcx
- xor r13,rcx
- add r9,QWORD[80+rsp]
- mov r15,r10
- xor r12,r8
- ror r14,6
- xor r15,r11
- add r9,r12
- ror r13,14
- and rdi,r15
- xor r14,r10
- add r9,r13
- xor rdi,r11
- ror r14,28
- add rbx,r9
- add r9,rdi
- mov r13,rbx
- add r14,r9
- ror r13,23
- mov r9,r14
- mov r12,rcx
- ror r14,5
- xor r13,rbx
- xor r12,rdx
- ror r13,4
- xor r14,r9
- and r12,rbx
- xor r13,rbx
- add r8,QWORD[88+rsp]
- mov rdi,r9
- xor r12,rdx
- ror r14,6
- xor rdi,r10
- add r8,r12
- ror r13,14
- and r15,rdi
- xor r14,r9
- add r8,r13
- xor r15,r10
- ror r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- ror r13,23
- mov r8,r14
- mov r12,rbx
- ror r14,5
- xor r13,rax
- xor r12,rcx
- ror r13,4
- xor r14,r8
- and r12,rax
- xor r13,rax
- add rdx,QWORD[96+rsp]
- mov r15,r8
- xor r12,rcx
- ror r14,6
- xor r15,r9
- add rdx,r12
- ror r13,14
- and rdi,r15
- xor r14,r8
- add rdx,r13
- xor rdi,r9
- ror r14,28
- add r11,rdx
- add rdx,rdi
- mov r13,r11
- add r14,rdx
- ror r13,23
- mov rdx,r14
- mov r12,rax
- ror r14,5
- xor r13,r11
- xor r12,rbx
- ror r13,4
- xor r14,rdx
- and r12,r11
- xor r13,r11
- add rcx,QWORD[104+rsp]
- mov rdi,rdx
- xor r12,rbx
- ror r14,6
- xor rdi,r8
- add rcx,r12
- ror r13,14
- and r15,rdi
- xor r14,rdx
- add rcx,r13
- xor r15,r8
- ror r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- ror r13,23
- mov rcx,r14
- mov r12,r11
- ror r14,5
- xor r13,r10
- xor r12,rax
- ror r13,4
- xor r14,rcx
- and r12,r10
- xor r13,r10
- add rbx,QWORD[112+rsp]
- mov r15,rcx
- xor r12,rax
- ror r14,6
- xor r15,rdx
- add rbx,r12
- ror r13,14
- and rdi,r15
- xor r14,rcx
- add rbx,r13
- xor rdi,rdx
- ror r14,28
- add r9,rbx
- add rbx,rdi
- mov r13,r9
- add r14,rbx
- ror r13,23
- mov rbx,r14
- mov r12,r10
- ror r14,5
- xor r13,r9
- xor r12,r11
- ror r13,4
- xor r14,rbx
- and r12,r9
- xor r13,r9
- add rax,QWORD[120+rsp]
- mov rdi,rbx
- xor r12,r11
- ror r14,6
- xor rdi,rcx
- add rax,r12
- ror r13,14
- and r15,rdi
- xor r14,rbx
- add rax,r13
- xor r15,rcx
- ror r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- mov rdi,QWORD[((128+0))+rsp]
- mov rax,r14
-
- add rax,QWORD[rdi]
- lea rsi,[128+rsi]
- add rbx,QWORD[8+rdi]
- add rcx,QWORD[16+rdi]
- add rdx,QWORD[24+rdi]
- add r8,QWORD[32+rdi]
- add r9,QWORD[40+rdi]
- add r10,QWORD[48+rdi]
- add r11,QWORD[56+rdi]
-
- cmp rsi,QWORD[((128+16))+rsp]
-
- mov QWORD[rdi],rax
- mov QWORD[8+rdi],rbx
- mov QWORD[16+rdi],rcx
- mov QWORD[24+rdi],rdx
- mov QWORD[32+rdi],r8
- mov QWORD[40+rdi],r9
- mov QWORD[48+rdi],r10
- mov QWORD[56+rdi],r11
- jb NEAR $L$loop_xop
-
- mov rsi,QWORD[((128+24))+rsp]
- vzeroupper
- movaps xmm6,XMMWORD[((128+32))+rsp]
- movaps xmm7,XMMWORD[((128+48))+rsp]
- movaps xmm8,XMMWORD[((128+64))+rsp]
- movaps xmm9,XMMWORD[((128+80))+rsp]
- movaps xmm10,XMMWORD[((128+96))+rsp]
- movaps xmm11,XMMWORD[((128+112))+rsp]
- mov r15,QWORD[rsi]
- mov r14,QWORD[8+rsi]
- mov r13,QWORD[16+rsi]
- mov r12,QWORD[24+rsi]
- mov rbp,QWORD[32+rsi]
- mov rbx,QWORD[40+rsi]
- lea rsp,[48+rsi]
-$L$epilogue_xop:
- mov rdi,QWORD[8+rsp] ;WIN64 epilogue
- mov rsi,QWORD[16+rsp]
- DB 0F3h,0C3h ;repret
-$L$SEH_end_sha512_block_data_order_xop:
-
-ALIGN 64
-sha512_block_data_order_avx:
- mov QWORD[8+rsp],rdi ;WIN64 prologue
- mov QWORD[16+rsp],rsi
- mov rax,rsp
-$L$SEH_begin_sha512_block_data_order_avx:
- mov rdi,rcx
- mov rsi,rdx
- mov rdx,r8
-
-
-$L$avx_shortcut:
- push rbx
- push rbp
- push r12
- push r13
- push r14
- push r15
- mov r11,rsp
- shl rdx,4
- sub rsp,256
- lea rdx,[rdx*8+rsi]
- and rsp,-64
- mov QWORD[((128+0))+rsp],rdi
- mov QWORD[((128+8))+rsp],rsi
- mov QWORD[((128+16))+rsp],rdx
- mov QWORD[((128+24))+rsp],r11
- movaps XMMWORD[(128+32)+rsp],xmm6
- movaps XMMWORD[(128+48)+rsp],xmm7
- movaps XMMWORD[(128+64)+rsp],xmm8
- movaps XMMWORD[(128+80)+rsp],xmm9
- movaps XMMWORD[(128+96)+rsp],xmm10
- movaps XMMWORD[(128+112)+rsp],xmm11
-$L$prologue_avx:
-
- vzeroupper
- mov rax,QWORD[rdi]
- mov rbx,QWORD[8+rdi]
- mov rcx,QWORD[16+rdi]
- mov rdx,QWORD[24+rdi]
- mov r8,QWORD[32+rdi]
- mov r9,QWORD[40+rdi]
- mov r10,QWORD[48+rdi]
- mov r11,QWORD[56+rdi]
- jmp NEAR $L$loop_avx
-ALIGN 16
-$L$loop_avx:
- vmovdqa xmm11,XMMWORD[((K512+1280))]
- vmovdqu xmm0,XMMWORD[rsi]
- lea rbp,[((K512+128))]
- vmovdqu xmm1,XMMWORD[16+rsi]
- vmovdqu xmm2,XMMWORD[32+rsi]
- vpshufb xmm0,xmm0,xmm11
- vmovdqu xmm3,XMMWORD[48+rsi]
- vpshufb xmm1,xmm1,xmm11
- vmovdqu xmm4,XMMWORD[64+rsi]
- vpshufb xmm2,xmm2,xmm11
- vmovdqu xmm5,XMMWORD[80+rsi]
- vpshufb xmm3,xmm3,xmm11
- vmovdqu xmm6,XMMWORD[96+rsi]
- vpshufb xmm4,xmm4,xmm11
- vmovdqu xmm7,XMMWORD[112+rsi]
- vpshufb xmm5,xmm5,xmm11
- vpaddq xmm8,xmm0,XMMWORD[((-128))+rbp]
- vpshufb xmm6,xmm6,xmm11
- vpaddq xmm9,xmm1,XMMWORD[((-96))+rbp]
- vpshufb xmm7,xmm7,xmm11
- vpaddq xmm10,xmm2,XMMWORD[((-64))+rbp]
- vpaddq xmm11,xmm3,XMMWORD[((-32))+rbp]
- vmovdqa XMMWORD[rsp],xmm8
- vpaddq xmm8,xmm4,XMMWORD[rbp]
- vmovdqa XMMWORD[16+rsp],xmm9
- vpaddq xmm9,xmm5,XMMWORD[32+rbp]
- vmovdqa XMMWORD[32+rsp],xmm10
- vpaddq xmm10,xmm6,XMMWORD[64+rbp]
- vmovdqa XMMWORD[48+rsp],xmm11
- vpaddq xmm11,xmm7,XMMWORD[96+rbp]
- vmovdqa XMMWORD[64+rsp],xmm8
- mov r14,rax
- vmovdqa XMMWORD[80+rsp],xmm9
- mov rdi,rbx
- vmovdqa XMMWORD[96+rsp],xmm10
- xor rdi,rcx
- vmovdqa XMMWORD[112+rsp],xmm11
- mov r13,r8
- jmp NEAR $L$avx_00_47
-
-ALIGN 16
-$L$avx_00_47:
- add rbp,256
- vpalignr xmm8,xmm1,xmm0,8
- shrd r13,r13,23
- mov rax,r14
- vpalignr xmm11,xmm5,xmm4,8
- mov r12,r9
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,r8
- xor r12,r10
- vpaddq xmm0,xmm0,xmm11
- shrd r13,r13,4
- xor r14,rax
- vpsrlq xmm11,xmm8,7
- and r12,r8
- xor r13,r8
- vpsllq xmm9,xmm8,56
- add r11,QWORD[rsp]
- mov r15,rax
- vpxor xmm8,xmm11,xmm10
- xor r12,r10
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,rbx
- add r11,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,rax
- add r11,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rbx
- shrd r14,r14,28
- vpsrlq xmm11,xmm7,6
- add rdx,r11
- add r11,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,rdx
- add r14,r11
- vpsllq xmm10,xmm7,3
- shrd r13,r13,23
- mov r11,r14
- vpaddq xmm0,xmm0,xmm8
- mov r12,r8
- shrd r14,r14,5
- vpsrlq xmm9,xmm7,19
- xor r13,rdx
- xor r12,r9
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,r11
- vpsllq xmm10,xmm10,42
- and r12,rdx
- xor r13,rdx
- vpxor xmm11,xmm11,xmm9
- add r10,QWORD[8+rsp]
- mov rdi,r11
- vpsrlq xmm9,xmm9,42
- xor r12,r9
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,rax
- add r10,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm0,xmm0,xmm11
- xor r14,r11
- add r10,r13
- vpaddq xmm10,xmm0,XMMWORD[((-128))+rbp]
- xor r15,rax
- shrd r14,r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- vmovdqa XMMWORD[rsp],xmm10
- vpalignr xmm8,xmm2,xmm1,8
- shrd r13,r13,23
- mov r10,r14
- vpalignr xmm11,xmm6,xmm5,8
- mov r12,rdx
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,rcx
- xor r12,r8
- vpaddq xmm1,xmm1,xmm11
- shrd r13,r13,4
- xor r14,r10
- vpsrlq xmm11,xmm8,7
- and r12,rcx
- xor r13,rcx
- vpsllq xmm9,xmm8,56
- add r9,QWORD[16+rsp]
- mov r15,r10
- vpxor xmm8,xmm11,xmm10
- xor r12,r8
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,r11
- add r9,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,r10
- add r9,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r11
- shrd r14,r14,28
- vpsrlq xmm11,xmm0,6
- add rbx,r9
- add r9,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,rbx
- add r14,r9
- vpsllq xmm10,xmm0,3
- shrd r13,r13,23
- mov r9,r14
- vpaddq xmm1,xmm1,xmm8
- mov r12,rcx
- shrd r14,r14,5
- vpsrlq xmm9,xmm0,19
- xor r13,rbx
- xor r12,rdx
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,r9
- vpsllq xmm10,xmm10,42
- and r12,rbx
- xor r13,rbx
- vpxor xmm11,xmm11,xmm9
- add r8,QWORD[24+rsp]
- mov rdi,r9
- vpsrlq xmm9,xmm9,42
- xor r12,rdx
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,r10
- add r8,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm1,xmm1,xmm11
- xor r14,r9
- add r8,r13
- vpaddq xmm10,xmm1,XMMWORD[((-96))+rbp]
- xor r15,r10
- shrd r14,r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- vmovdqa XMMWORD[16+rsp],xmm10
- vpalignr xmm8,xmm3,xmm2,8
- shrd r13,r13,23
- mov r8,r14
- vpalignr xmm11,xmm7,xmm6,8
- mov r12,rbx
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,rax
- xor r12,rcx
- vpaddq xmm2,xmm2,xmm11
- shrd r13,r13,4
- xor r14,r8
- vpsrlq xmm11,xmm8,7
- and r12,rax
- xor r13,rax
- vpsllq xmm9,xmm8,56
- add rdx,QWORD[32+rsp]
- mov r15,r8
- vpxor xmm8,xmm11,xmm10
- xor r12,rcx
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,r9
- add rdx,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,r8
- add rdx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r9
- shrd r14,r14,28
- vpsrlq xmm11,xmm1,6
- add r11,rdx
- add rdx,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,r11
- add r14,rdx
- vpsllq xmm10,xmm1,3
- shrd r13,r13,23
- mov rdx,r14
- vpaddq xmm2,xmm2,xmm8
- mov r12,rax
- shrd r14,r14,5
- vpsrlq xmm9,xmm1,19
- xor r13,r11
- xor r12,rbx
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,rdx
- vpsllq xmm10,xmm10,42
- and r12,r11
- xor r13,r11
- vpxor xmm11,xmm11,xmm9
- add rcx,QWORD[40+rsp]
- mov rdi,rdx
- vpsrlq xmm9,xmm9,42
- xor r12,rbx
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,r8
- add rcx,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm2,xmm2,xmm11
- xor r14,rdx
- add rcx,r13
- vpaddq xmm10,xmm2,XMMWORD[((-64))+rbp]
- xor r15,r8
- shrd r14,r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- vmovdqa XMMWORD[32+rsp],xmm10
- vpalignr xmm8,xmm4,xmm3,8
- shrd r13,r13,23
- mov rcx,r14
- vpalignr xmm11,xmm0,xmm7,8
- mov r12,r11
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,r10
- xor r12,rax
- vpaddq xmm3,xmm3,xmm11
- shrd r13,r13,4
- xor r14,rcx
- vpsrlq xmm11,xmm8,7
- and r12,r10
- xor r13,r10
- vpsllq xmm9,xmm8,56
- add rbx,QWORD[48+rsp]
- mov r15,rcx
- vpxor xmm8,xmm11,xmm10
- xor r12,rax
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,rdx
- add rbx,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,rcx
- add rbx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rdx
- shrd r14,r14,28
- vpsrlq xmm11,xmm2,6
- add r9,rbx
- add rbx,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,r9
- add r14,rbx
- vpsllq xmm10,xmm2,3
- shrd r13,r13,23
- mov rbx,r14
- vpaddq xmm3,xmm3,xmm8
- mov r12,r10
- shrd r14,r14,5
- vpsrlq xmm9,xmm2,19
- xor r13,r9
- xor r12,r11
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,rbx
- vpsllq xmm10,xmm10,42
- and r12,r9
- xor r13,r9
- vpxor xmm11,xmm11,xmm9
- add rax,QWORD[56+rsp]
- mov rdi,rbx
- vpsrlq xmm9,xmm9,42
- xor r12,r11
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,rcx
- add rax,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm3,xmm3,xmm11
- xor r14,rbx
- add rax,r13
- vpaddq xmm10,xmm3,XMMWORD[((-32))+rbp]
- xor r15,rcx
- shrd r14,r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- vmovdqa XMMWORD[48+rsp],xmm10
- vpalignr xmm8,xmm5,xmm4,8
- shrd r13,r13,23
- mov rax,r14
- vpalignr xmm11,xmm1,xmm0,8
- mov r12,r9
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,r8
- xor r12,r10
- vpaddq xmm4,xmm4,xmm11
- shrd r13,r13,4
- xor r14,rax
- vpsrlq xmm11,xmm8,7
- and r12,r8
- xor r13,r8
- vpsllq xmm9,xmm8,56
- add r11,QWORD[64+rsp]
- mov r15,rax
- vpxor xmm8,xmm11,xmm10
- xor r12,r10
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,rbx
- add r11,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,rax
- add r11,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rbx
- shrd r14,r14,28
- vpsrlq xmm11,xmm3,6
- add rdx,r11
- add r11,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,rdx
- add r14,r11
- vpsllq xmm10,xmm3,3
- shrd r13,r13,23
- mov r11,r14
- vpaddq xmm4,xmm4,xmm8
- mov r12,r8
- shrd r14,r14,5
- vpsrlq xmm9,xmm3,19
- xor r13,rdx
- xor r12,r9
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,r11
- vpsllq xmm10,xmm10,42
- and r12,rdx
- xor r13,rdx
- vpxor xmm11,xmm11,xmm9
- add r10,QWORD[72+rsp]
- mov rdi,r11
- vpsrlq xmm9,xmm9,42
- xor r12,r9
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,rax
- add r10,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm4,xmm4,xmm11
- xor r14,r11
- add r10,r13
- vpaddq xmm10,xmm4,XMMWORD[rbp]
- xor r15,rax
- shrd r14,r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- vmovdqa XMMWORD[64+rsp],xmm10
- vpalignr xmm8,xmm6,xmm5,8
- shrd r13,r13,23
- mov r10,r14
- vpalignr xmm11,xmm2,xmm1,8
- mov r12,rdx
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,rcx
- xor r12,r8
- vpaddq xmm5,xmm5,xmm11
- shrd r13,r13,4
- xor r14,r10
- vpsrlq xmm11,xmm8,7
- and r12,rcx
- xor r13,rcx
- vpsllq xmm9,xmm8,56
- add r9,QWORD[80+rsp]
- mov r15,r10
- vpxor xmm8,xmm11,xmm10
- xor r12,r8
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,r11
- add r9,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,r10
- add r9,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r11
- shrd r14,r14,28
- vpsrlq xmm11,xmm4,6
- add rbx,r9
- add r9,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,rbx
- add r14,r9
- vpsllq xmm10,xmm4,3
- shrd r13,r13,23
- mov r9,r14
- vpaddq xmm5,xmm5,xmm8
- mov r12,rcx
- shrd r14,r14,5
- vpsrlq xmm9,xmm4,19
- xor r13,rbx
- xor r12,rdx
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,r9
- vpsllq xmm10,xmm10,42
- and r12,rbx
- xor r13,rbx
- vpxor xmm11,xmm11,xmm9
- add r8,QWORD[88+rsp]
- mov rdi,r9
- vpsrlq xmm9,xmm9,42
- xor r12,rdx
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,r10
- add r8,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm5,xmm5,xmm11
- xor r14,r9
- add r8,r13
- vpaddq xmm10,xmm5,XMMWORD[32+rbp]
- xor r15,r10
- shrd r14,r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- vmovdqa XMMWORD[80+rsp],xmm10
- vpalignr xmm8,xmm7,xmm6,8
- shrd r13,r13,23
- mov r8,r14
- vpalignr xmm11,xmm3,xmm2,8
- mov r12,rbx
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,rax
- xor r12,rcx
- vpaddq xmm6,xmm6,xmm11
- shrd r13,r13,4
- xor r14,r8
- vpsrlq xmm11,xmm8,7
- and r12,rax
- xor r13,rax
- vpsllq xmm9,xmm8,56
- add rdx,QWORD[96+rsp]
- mov r15,r8
- vpxor xmm8,xmm11,xmm10
- xor r12,rcx
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,r9
- add rdx,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,r8
- add rdx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,r9
- shrd r14,r14,28
- vpsrlq xmm11,xmm5,6
- add r11,rdx
- add rdx,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,r11
- add r14,rdx
- vpsllq xmm10,xmm5,3
- shrd r13,r13,23
- mov rdx,r14
- vpaddq xmm6,xmm6,xmm8
- mov r12,rax
- shrd r14,r14,5
- vpsrlq xmm9,xmm5,19
- xor r13,r11
- xor r12,rbx
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,rdx
- vpsllq xmm10,xmm10,42
- and r12,r11
- xor r13,r11
- vpxor xmm11,xmm11,xmm9
- add rcx,QWORD[104+rsp]
- mov rdi,rdx
- vpsrlq xmm9,xmm9,42
- xor r12,rbx
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,r8
- add rcx,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm6,xmm6,xmm11
- xor r14,rdx
- add rcx,r13
- vpaddq xmm10,xmm6,XMMWORD[64+rbp]
- xor r15,r8
- shrd r14,r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- vmovdqa XMMWORD[96+rsp],xmm10
- vpalignr xmm8,xmm0,xmm7,8
- shrd r13,r13,23
- mov rcx,r14
- vpalignr xmm11,xmm4,xmm3,8
- mov r12,r11
- shrd r14,r14,5
- vpsrlq xmm10,xmm8,1
- xor r13,r10
- xor r12,rax
- vpaddq xmm7,xmm7,xmm11
- shrd r13,r13,4
- xor r14,rcx
- vpsrlq xmm11,xmm8,7
- and r12,r10
- xor r13,r10
- vpsllq xmm9,xmm8,56
- add rbx,QWORD[112+rsp]
- mov r15,rcx
- vpxor xmm8,xmm11,xmm10
- xor r12,rax
- shrd r14,r14,6
- vpsrlq xmm10,xmm10,7
- xor r15,rdx
- add rbx,r12
- vpxor xmm8,xmm8,xmm9
- shrd r13,r13,14
- and rdi,r15
- vpsllq xmm9,xmm9,7
- xor r14,rcx
- add rbx,r13
- vpxor xmm8,xmm8,xmm10
- xor rdi,rdx
- shrd r14,r14,28
- vpsrlq xmm11,xmm6,6
- add r9,rbx
- add rbx,rdi
- vpxor xmm8,xmm8,xmm9
- mov r13,r9
- add r14,rbx
- vpsllq xmm10,xmm6,3
- shrd r13,r13,23
- mov rbx,r14
- vpaddq xmm7,xmm7,xmm8
- mov r12,r10
- shrd r14,r14,5
- vpsrlq xmm9,xmm6,19
- xor r13,r9
- xor r12,r11
- vpxor xmm11,xmm11,xmm10
- shrd r13,r13,4
- xor r14,rbx
- vpsllq xmm10,xmm10,42
- and r12,r9
- xor r13,r9
- vpxor xmm11,xmm11,xmm9
- add rax,QWORD[120+rsp]
- mov rdi,rbx
- vpsrlq xmm9,xmm9,42
- xor r12,r11
- shrd r14,r14,6
- vpxor xmm11,xmm11,xmm10
- xor rdi,rcx
- add rax,r12
- vpxor xmm11,xmm11,xmm9
- shrd r13,r13,14
- and r15,rdi
- vpaddq xmm7,xmm7,xmm11
- xor r14,rbx
- add rax,r13
- vpaddq xmm10,xmm7,XMMWORD[96+rbp]
- xor r15,rcx
- shrd r14,r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- vmovdqa XMMWORD[112+rsp],xmm10
- cmp BYTE[135+rbp],0
- jne NEAR $L$avx_00_47
- shrd r13,r13,23
- mov rax,r14
- mov r12,r9
- shrd r14,r14,5
- xor r13,r8
- xor r12,r10
- shrd r13,r13,4
- xor r14,rax
- and r12,r8
- xor r13,r8
- add r11,QWORD[rsp]
- mov r15,rax
- xor r12,r10
- shrd r14,r14,6
- xor r15,rbx
- add r11,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,rax
- add r11,r13
- xor rdi,rbx
- shrd r14,r14,28
- add rdx,r11
- add r11,rdi
- mov r13,rdx
- add r14,r11
- shrd r13,r13,23
- mov r11,r14
- mov r12,r8
- shrd r14,r14,5
- xor r13,rdx
- xor r12,r9
- shrd r13,r13,4
- xor r14,r11
- and r12,rdx
- xor r13,rdx
- add r10,QWORD[8+rsp]
- mov rdi,r11
- xor r12,r9
- shrd r14,r14,6
- xor rdi,rax
- add r10,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,r11
- add r10,r13
- xor r15,rax
- shrd r14,r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- shrd r13,r13,23
- mov r10,r14
- mov r12,rdx
- shrd r14,r14,5
- xor r13,rcx
- xor r12,r8
- shrd r13,r13,4
- xor r14,r10
- and r12,rcx
- xor r13,rcx
- add r9,QWORD[16+rsp]
- mov r15,r10
- xor r12,r8
- shrd r14,r14,6
- xor r15,r11
- add r9,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,r10
- add r9,r13
- xor rdi,r11
- shrd r14,r14,28
- add rbx,r9
- add r9,rdi
- mov r13,rbx
- add r14,r9
- shrd r13,r13,23
- mov r9,r14
- mov r12,rcx
- shrd r14,r14,5
- xor r13,rbx
- xor r12,rdx
- shrd r13,r13,4
- xor r14,r9
- and r12,rbx
- xor r13,rbx
- add r8,QWORD[24+rsp]
- mov rdi,r9
- xor r12,rdx
- shrd r14,r14,6
- xor rdi,r10
- add r8,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,r9
- add r8,r13
- xor r15,r10
- shrd r14,r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- shrd r13,r13,23
- mov r8,r14
- mov r12,rbx
- shrd r14,r14,5
- xor r13,rax
- xor r12,rcx
- shrd r13,r13,4
- xor r14,r8
- and r12,rax
- xor r13,rax
- add rdx,QWORD[32+rsp]
- mov r15,r8
- xor r12,rcx
- shrd r14,r14,6
- xor r15,r9
- add rdx,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,r8
- add rdx,r13
- xor rdi,r9
- shrd r14,r14,28
- add r11,rdx
- add rdx,rdi
- mov r13,r11
- add r14,rdx
- shrd r13,r13,23
- mov rdx,r14
- mov r12,rax
- shrd r14,r14,5
- xor r13,r11
- xor r12,rbx
- shrd r13,r13,4
- xor r14,rdx
- and r12,r11
- xor r13,r11
- add rcx,QWORD[40+rsp]
- mov rdi,rdx
- xor r12,rbx
- shrd r14,r14,6
- xor rdi,r8
- add rcx,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,rdx
- add rcx,r13
- xor r15,r8
- shrd r14,r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- shrd r13,r13,23
- mov rcx,r14
- mov r12,r11
- shrd r14,r14,5
- xor r13,r10
- xor r12,rax
- shrd r13,r13,4
- xor r14,rcx
- and r12,r10
- xor r13,r10
- add rbx,QWORD[48+rsp]
- mov r15,rcx
- xor r12,rax
- shrd r14,r14,6
- xor r15,rdx
- add rbx,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,rcx
- add rbx,r13
- xor rdi,rdx
- shrd r14,r14,28
- add r9,rbx
- add rbx,rdi
- mov r13,r9
- add r14,rbx
- shrd r13,r13,23
- mov rbx,r14
- mov r12,r10
- shrd r14,r14,5
- xor r13,r9
- xor r12,r11
- shrd r13,r13,4
- xor r14,rbx
- and r12,r9
- xor r13,r9
- add rax,QWORD[56+rsp]
- mov rdi,rbx
- xor r12,r11
- shrd r14,r14,6
- xor rdi,rcx
- add rax,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,rbx
- add rax,r13
- xor r15,rcx
- shrd r14,r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- shrd r13,r13,23
- mov rax,r14
- mov r12,r9
- shrd r14,r14,5
- xor r13,r8
- xor r12,r10
- shrd r13,r13,4
- xor r14,rax
- and r12,r8
- xor r13,r8
- add r11,QWORD[64+rsp]
- mov r15,rax
- xor r12,r10
- shrd r14,r14,6
- xor r15,rbx
- add r11,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,rax
- add r11,r13
- xor rdi,rbx
- shrd r14,r14,28
- add rdx,r11
- add r11,rdi
- mov r13,rdx
- add r14,r11
- shrd r13,r13,23
- mov r11,r14
- mov r12,r8
- shrd r14,r14,5
- xor r13,rdx
- xor r12,r9
- shrd r13,r13,4
- xor r14,r11
- and r12,rdx
- xor r13,rdx
- add r10,QWORD[72+rsp]
- mov rdi,r11
- xor r12,r9
- shrd r14,r14,6
- xor rdi,rax
- add r10,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,r11
- add r10,r13
- xor r15,rax
- shrd r14,r14,28
- add rcx,r10
- add r10,r15
- mov r13,rcx
- add r14,r10
- shrd r13,r13,23
- mov r10,r14
- mov r12,rdx
- shrd r14,r14,5
- xor r13,rcx
- xor r12,r8
- shrd r13,r13,4
- xor r14,r10
- and r12,rcx
- xor r13,rcx
- add r9,QWORD[80+rsp]
- mov r15,r10
- xor r12,r8
- shrd r14,r14,6
- xor r15,r11
- add r9,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,r10
- add r9,r13
- xor rdi,r11
- shrd r14,r14,28
- add rbx,r9
- add r9,rdi
- mov r13,rbx
- add r14,r9
- shrd r13,r13,23
- mov r9,r14
- mov r12,rcx
- shrd r14,r14,5
- xor r13,rbx
- xor r12,rdx
- shrd r13,r13,4
- xor r14,r9
- and r12,rbx
- xor r13,rbx
- add r8,QWORD[88+rsp]
- mov rdi,r9
- xor r12,rdx
- shrd r14,r14,6
- xor rdi,r10
- add r8,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,r9
- add r8,r13
- xor r15,r10
- shrd r14,r14,28
- add rax,r8
- add r8,r15
- mov r13,rax
- add r14,r8
- shrd r13,r13,23
- mov r8,r14
- mov r12,rbx
- shrd r14,r14,5
- xor r13,rax
- xor r12,rcx
- shrd r13,r13,4
- xor r14,r8
- and r12,rax
- xor r13,rax
- add rdx,QWORD[96+rsp]
- mov r15,r8
- xor r12,rcx
- shrd r14,r14,6
- xor r15,r9
- add rdx,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,r8
- add rdx,r13
- xor rdi,r9
- shrd r14,r14,28
- add r11,rdx
- add rdx,rdi
- mov r13,r11
- add r14,rdx
- shrd r13,r13,23
- mov rdx,r14
- mov r12,rax
- shrd r14,r14,5
- xor r13,r11
- xor r12,rbx
- shrd r13,r13,4
- xor r14,rdx
- and r12,r11
- xor r13,r11
- add rcx,QWORD[104+rsp]
- mov rdi,rdx
- xor r12,rbx
- shrd r14,r14,6
- xor rdi,r8
- add rcx,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,rdx
- add rcx,r13
- xor r15,r8
- shrd r14,r14,28
- add r10,rcx
- add rcx,r15
- mov r13,r10
- add r14,rcx
- shrd r13,r13,23
- mov rcx,r14
- mov r12,r11
- shrd r14,r14,5
- xor r13,r10
- xor r12,rax
- shrd r13,r13,4
- xor r14,rcx
- and r12,r10
- xor r13,r10
- add rbx,QWORD[112+rsp]
- mov r15,rcx
- xor r12,rax
- shrd r14,r14,6
- xor r15,rdx
- add rbx,r12
- shrd r13,r13,14
- and rdi,r15
- xor r14,rcx
- add rbx,r13
- xor rdi,rdx
- shrd r14,r14,28
- add r9,rbx
- add rbx,rdi
- mov r13,r9
- add r14,rbx
- shrd r13,r13,23
- mov rbx,r14
- mov r12,r10
- shrd r14,r14,5
- xor r13,r9
- xor r12,r11
- shrd r13,r13,4
- xor r14,rbx
- and r12,r9
- xor r13,r9
- add rax,QWORD[120+rsp]
- mov rdi,rbx
- xor r12,r11
- shrd r14,r14,6
- xor rdi,rcx
- add rax,r12
- shrd r13,r13,14
- and r15,rdi
- xor r14,rbx
- add rax,r13
- xor r15,rcx
- shrd r14,r14,28
- add r8,rax
- add rax,r15
- mov r13,r8
- add r14,rax
- mov rdi,QWORD[((128+0))+rsp]
- mov rax,r14
-
- add rax,QWORD[rdi]
- lea rsi,[128+rsi]
- add rbx,QWORD[8+rdi]
- add rcx,QWORD[16+rdi]
- add rdx,QWORD[24+rdi]
- add r8,QWORD[32+rdi]
- add r9,QWORD[40+rdi]
- add r10,QWORD[48+rdi]
- add r11,QWORD[56+rdi]
-
- cmp rsi,QWORD[((128+16))+rsp]
-
- mov QWORD[rdi],rax
- mov QWORD[8+rdi],rbx
- mov QWORD[16+rdi],rcx
- mov QWORD[24+rdi],rdx
- mov QWORD[32+rdi],r8
- mov QWORD[40+rdi],r9
- mov QWORD[48+rdi],r10
- mov QWORD[56+rdi],r11
- jb NEAR $L$loop_avx
-
- mov rsi,QWORD[((128+24))+rsp]
- vzeroupper
- movaps xmm6,XMMWORD[((128+32))+rsp]
- movaps xmm7,XMMWORD[((128+48))+rsp]
- movaps xmm8,XMMWORD[((128+64))+rsp]
- movaps xmm9,XMMWORD[((128+80))+rsp]
- movaps xmm10,XMMWORD[((128+96))+rsp]
- movaps xmm11,XMMWORD[((128+112))+rsp]
- mov r15,QWORD[rsi]
- mov r14,QWORD[8+rsi]
- mov r13,QWORD[16+rsi]
- mov r12,QWORD[24+rsi]
- mov rbp,QWORD[32+rsi]
- mov rbx,QWORD[40+rsi]
- lea rsp,[48+rsi]
-$L$epilogue_avx:
- mov rdi,QWORD[8+rsp] ;WIN64 epilogue
- mov rsi,QWORD[16+rsp]
- DB 0F3h,0C3h ;repret
-$L$SEH_end_sha512_block_data_order_avx:
-EXTERN __imp_RtlVirtualUnwind
-
-ALIGN 16
-se_handler:
- push rsi
- push rdi
- push rbx
- push rbp
- push r12
- push r13
- push r14
- push r15
- pushfq
- sub rsp,64
+ pushfq
+ sub rsp,64
mov rax,QWORD[120+r8]
mov rbx,QWORD[248+r8]
@@ -4190,23 +1903,9 @@ ALIGN 4
DD $L$SEH_begin_sha512_block_data_order wrt ..imagebase
DD $L$SEH_end_sha512_block_data_order wrt ..imagebase
DD $L$SEH_info_sha512_block_data_order wrt ..imagebase
- DD $L$SEH_begin_sha512_block_data_order_xop wrt ..imagebase
- DD $L$SEH_end_sha512_block_data_order_xop wrt ..imagebase
- DD $L$SEH_info_sha512_block_data_order_xop wrt ..imagebase
- DD $L$SEH_begin_sha512_block_data_order_avx wrt ..imagebase
- DD $L$SEH_end_sha512_block_data_order_avx wrt ..imagebase
- DD $L$SEH_info_sha512_block_data_order_avx wrt ..imagebase
section .xdata rdata align=8
ALIGN 8
$L$SEH_info_sha512_block_data_order:
DB 9,0,0,0
DD se_handler wrt ..imagebase
DD $L$prologue wrt ..imagebase,$L$epilogue wrt ..imagebase
-$L$SEH_info_sha512_block_data_order_xop:
-DB 9,0,0,0
- DD se_handler wrt ..imagebase
- DD $L$prologue_xop wrt ..imagebase,$L$epilogue_xop wrt ..imagebase
-$L$SEH_info_sha512_block_data_order_avx:
-DB 9,0,0,0
- DD se_handler wrt ..imagebase
- DD $L$prologue_avx wrt ..imagebase,$L$epilogue_avx wrt ..imagebase
« no previous file with comments | « third_party/boringssl/win-x86_64/crypto/sha/sha256-x86_64.asm ('k') | no next file » | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698