Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(478)

Issues Search
    My Issues | Starred     Open | Closed | All

Unified Diff: mac-x86_64/crypto/ec/p256-x86_64-asm.S

Issue 2569253003: BoringSSL: Roll generated files forward. (Closed)
Patch Set: Created 4 years 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 | « mac-x86/crypto/rc4/rc4-586.S ('k') | mac-x86_64/crypto/rc4/rc4-x86_64.S » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: mac-x86_64/crypto/ec/p256-x86_64-asm.S
diff --git a/mac-x86_64/crypto/ec/p256-x86_64-asm.S b/mac-x86_64/crypto/ec/p256-x86_64-asm.S
index 1cd0cc3f5c68fe14b3f0d587eca132931bd52cc5..97fb75a72205c2e9a544f2a5663e17151460bf50 100644
--- a/mac-x86_64/crypto/ec/p256-x86_64-asm.S
+++ b/mac-x86_64/crypto/ec/p256-x86_64-asm.S
@@ -23,6 +23,7 @@ ecp_nistz256_mul_by_2:
pushq %r13
movq 0(%rsi),%r8
+ xorq %r13,%r13
movq 8(%rsi),%r9
addq %r8,%r8
movq 16(%rsi),%r10
@@ -33,7 +34,7 @@ ecp_nistz256_mul_by_2:
adcq %r10,%r10
adcq %r11,%r11
movq %r9,%rdx
- sbbq %r13,%r13
+ adcq $0,%r13
subq 0(%rsi),%r8
movq %r10,%rcx
@@ -41,14 +42,14 @@ ecp_nistz256_mul_by_2:
sbbq 16(%rsi),%r10
movq %r11,%r12
sbbq 24(%rsi),%r11
- testq %r13,%r13
+ sbbq $0,%r13
- cmovzq %rax,%r8
- cmovzq %rdx,%r9
+ cmovcq %rax,%r8
+ cmovcq %rdx,%r9
movq %r8,0(%rdi)
- cmovzq %rcx,%r10
+ cmovcq %rcx,%r10
movq %r9,8(%rdi)
- cmovzq %r12,%r11
+ cmovcq %r12,%r11
movq %r10,16(%rdi)
movq %r11,24(%rdi)
@@ -624,6 +625,8 @@ _ecp_nistz256_from_mont:
movq %r9,%rsi
adcq $0,%rdx
+
+
subq $-1,%r8
movq %r10,%rax
sbbq %r12,%r9
@@ -764,13 +767,14 @@ _ecp_nistz256_avx2_select_w7:
.p2align 5
__ecp_nistz256_add_toq:
+ xorq %r11,%r11
addq 0(%rbx),%r12
adcq 8(%rbx),%r13
movq %r12,%rax
adcq 16(%rbx),%r8
adcq 24(%rbx),%r9
movq %r13,%rbp
- sbbq %r11,%r11
+ adcq $0,%r11
subq $-1,%r12
movq %r8,%rcx
@@ -778,14 +782,14 @@ __ecp_nistz256_add_toq:
sbbq $0,%r8
movq %r9,%r10
sbbq %r15,%r9
- testq %r11,%r11
+ sbbq $0,%r11
- cmovzq %rax,%r12
- cmovzq %rbp,%r13
+ cmovcq %rax,%r12
+ cmovcq %rbp,%r13
movq %r12,0(%rdi)
- cmovzq %rcx,%r8
+ cmovcq %rcx,%r8
movq %r13,8(%rdi)
- cmovzq %r10,%r9
+ cmovcq %r10,%r9
movq %r8,16(%rdi)
movq %r9,24(%rdi)
@@ -853,13 +857,14 @@ __ecp_nistz256_subq:
.p2align 5
__ecp_nistz256_mul_by_2q:
+ xorq %r11,%r11
addq %r12,%r12
adcq %r13,%r13
movq %r12,%rax
adcq %r8,%r8
adcq %r9,%r9
movq %r13,%rbp
- sbbq %r11,%r11
+ adcq $0,%r11
subq $-1,%r12
movq %r8,%rcx
@@ -867,14 +872,14 @@ __ecp_nistz256_mul_by_2q:
sbbq $0,%r8
movq %r9,%r10
sbbq %r15,%r9
- testq %r11,%r11
+ sbbq $0,%r11
- cmovzq %rax,%r12
- cmovzq %rbp,%r13
+ cmovcq %rax,%r12
+ cmovcq %rbp,%r13
movq %r12,0(%rdi)
- cmovzq %rcx,%r8
+ cmovcq %rcx,%r8
movq %r13,8(%rdi)
- cmovzq %r10,%r9
+ cmovcq %r10,%r9
movq %r8,16(%rdi)
movq %r9,24(%rdi)
@@ -1106,16 +1111,14 @@ _ecp_nistz256_point_add:
movq %rdx,%rsi
movdqa %xmm0,384(%rsp)
movdqa %xmm1,384+16(%rsp)
- por %xmm0,%xmm1
movdqa %xmm2,416(%rsp)
movdqa %xmm3,416+16(%rsp)
- por %xmm2,%xmm3
movdqa %xmm4,448(%rsp)
movdqa %xmm5,448+16(%rsp)
- por %xmm1,%xmm3
+ por %xmm4,%xmm5
movdqu 0(%rsi),%xmm0
- pshufd $0xb1,%xmm3,%xmm5
+ pshufd $0xb1,%xmm5,%xmm3
movdqu 16(%rsi),%xmm1
movdqu 32(%rsi),%xmm2
por %xmm3,%xmm5
@@ -1127,14 +1130,14 @@ _ecp_nistz256_point_add:
movdqa %xmm0,480(%rsp)
pshufd $0x1e,%xmm5,%xmm4
movdqa %xmm1,480+16(%rsp)
- por %xmm0,%xmm1
-.byte 102,72,15,110,199
+ movdqu 64(%rsi),%xmm0
+ movdqu 80(%rsi),%xmm1
movdqa %xmm2,512(%rsp)
movdqa %xmm3,512+16(%rsp)
- por %xmm2,%xmm3
por %xmm4,%xmm5
pxor %xmm4,%xmm4
- por %xmm1,%xmm3
+ por %xmm0,%xmm1
+.byte 102,72,15,110,199
leaq 64-0(%rsi),%rsi
movq %rax,544+0(%rsp)
@@ -1145,8 +1148,8 @@ _ecp_nistz256_point_add:
call __ecp_nistz256_sqr_montq
pcmpeqd %xmm4,%xmm5
- pshufd $0xb1,%xmm3,%xmm4
- por %xmm3,%xmm4
+ pshufd $0xb1,%xmm1,%xmm4
+ por %xmm1,%xmm4
pshufd $0,%xmm5,%xmm5
pshufd $0x1e,%xmm4,%xmm3
por %xmm3,%xmm4
@@ -1329,6 +1332,7 @@ L$add_proceedq:
+ xorq %r11,%r11
addq %r12,%r12
leaq 96(%rsp),%rsi
adcq %r13,%r13
@@ -1336,7 +1340,7 @@ L$add_proceedq:
adcq %r8,%r8
adcq %r9,%r9
movq %r13,%rbp
- sbbq %r11,%r11
+ adcq $0,%r11
subq $-1,%r12
movq %r8,%rcx
@@ -1344,15 +1348,15 @@ L$add_proceedq:
sbbq $0,%r8
movq %r9,%r10
sbbq %r15,%r9
- testq %r11,%r11
+ sbbq $0,%r11
- cmovzq %rax,%r12
+ cmovcq %rax,%r12
movq 0(%rsi),%rax
- cmovzq %rbp,%r13
+ cmovcq %rbp,%r13
movq 8(%rsi),%rbp
- cmovzq %rcx,%r8
+ cmovcq %rcx,%r8
movq 16(%rsi),%rcx
- cmovzq %r10,%r9
+ cmovcq %r10,%r9
movq 24(%rsi),%r10
call __ecp_nistz256_subq
@@ -1507,16 +1511,14 @@ _ecp_nistz256_point_add_affine:
movq 64+24(%rsi),%r8
movdqa %xmm0,320(%rsp)
movdqa %xmm1,320+16(%rsp)
- por %xmm0,%xmm1
movdqa %xmm2,352(%rsp)
movdqa %xmm3,352+16(%rsp)
- por %xmm2,%xmm3
movdqa %xmm4,384(%rsp)
movdqa %xmm5,384+16(%rsp)
- por %xmm1,%xmm3
+ por %xmm4,%xmm5
movdqu 0(%rbx),%xmm0
- pshufd $0xb1,%xmm3,%xmm5
+ pshufd $0xb1,%xmm5,%xmm3
movdqu 16(%rbx),%xmm1
movdqu 32(%rbx),%xmm2
por %xmm3,%xmm5
@@ -1634,6 +1636,7 @@ _ecp_nistz256_point_add_affine:
+ xorq %r11,%r11
addq %r12,%r12
leaq 192(%rsp),%rsi
adcq %r13,%r13
@@ -1641,7 +1644,7 @@ _ecp_nistz256_point_add_affine:
adcq %r8,%r8
adcq %r9,%r9
movq %r13,%rbp
- sbbq %r11,%r11
+ adcq $0,%r11
subq $-1,%r12
movq %r8,%rcx
@@ -1649,15 +1652,15 @@ _ecp_nistz256_point_add_affine:
sbbq $0,%r8
movq %r9,%r10
sbbq %r15,%r9
- testq %r11,%r11
+ sbbq $0,%r11
- cmovzq %rax,%r12
+ cmovcq %rax,%r12
movq 0(%rsi),%rax
- cmovzq %rbp,%r13
+ cmovcq %rbp,%r13
movq 8(%rsi),%rbp
- cmovzq %rcx,%r8
+ cmovcq %rcx,%r8
movq 16(%rsi),%rcx
- cmovzq %r10,%r9
+ cmovcq %r10,%r9
movq 24(%rsi),%r10
call __ecp_nistz256_subq
« no previous file with comments | « mac-x86/crypto/rc4/rc4-586.S ('k') | mac-x86_64/crypto/rc4/rc4-x86_64.S » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698