Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(833)

Issues Search
    My Issues | Starred     Open | Closed | All

Unified Diff: third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S

Issue 862133002: Update from https://crrev.com/312398 (Closed) Base URL: git@github.com:domokit/mojo.git@master
Patch Set: Created 5 years, 11 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
« shell/BUILD.gn ('K') | « third_party/boringssl/linux-arm/crypto/sha/sha1-armv4-large.S ('k') | third_party/boringssl/linux-arm/crypto/sha/sha512-armv4.S » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S
diff --git a/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S b/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S
index c105f51664b8804f589ddd3837c5125bd56ced7e..289b58ff4a99ea4cea0d8979b8e79538197b51ea 100644
--- a/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S
+++ b/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S
@@ -1,4 +1,3 @@
-#if defined(__arm__)
#include "arm_arch.h"
.text
@@ -25,20 +24,23 @@ K256:
.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
.size K256,.-K256
.word 0 @ terminator
+#if __ARM_MAX_ARCH__>=7
.LOPENSSL_armcap:
.word OPENSSL_armcap_P-sha256_block_data_order
+#endif
.align 5
.global sha256_block_data_order
-.hidden sha256_block_data_order
.type sha256_block_data_order,%function
sha256_block_data_order:
sub r3,pc,#8 @ sha256_block_data_order
add r2,r1,r2,lsl#6 @ len to point at the end of inp
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
ldr r12,.LOPENSSL_armcap
ldr r12,[r3,r12] @ OPENSSL_armcap_P
- tst r12,#1
+ tst r12,#ARMV8_SHA256
+ bne .LARMv8
+ tst r12,#ARMV7_NEON
bne .LNEON
#endif
stmdb sp!,{r0,r1,r2,r4-r11,lr}
@@ -1770,9 +1772,14 @@ sha256_block_data_order:
moveq pc,lr @ be binary compatible with V4, yet
.word 0xe12fff1e @ interoperable with Thumb ISA:-)
#endif
-#if __ARM_ARCH__>=7
+.size sha256_block_data_order,.-sha256_block_data_order
+#if __ARM_MAX_ARCH__>=7
+.arch armv7-a
.fpu neon
+
+.type sha256_block_data_order_neon,%function
.align 4
+sha256_block_data_order_neon:
.LNEON:
stmdb sp!,{r4-r12,lr}
@@ -2543,10 +2550,146 @@ sha256_block_data_order:
bne .L_00_48
ldmia sp!,{r4-r12,pc}
+.size sha256_block_data_order_neon,.-sha256_block_data_order_neon
+#endif
+#if __ARM_MAX_ARCH__>=7
+.type sha256_block_data_order_armv8,%function
+.align 5
+sha256_block_data_order_armv8:
+.LARMv8:
+ vld1.32 {q0,q1},[r0]
+ sub r3,r3,#sha256_block_data_order-K256
+
+.Loop_v8:
+ vld1.8 {q8-q9},[r1]!
+ vld1.8 {q10-q11},[r1]!
+ vld1.32 {q12},[r3]!
+ vrev32.8 q8,q8
+ vrev32.8 q9,q9
+ vrev32.8 q10,q10
+ vrev32.8 q11,q11
+ vmov q14,q0 @ offload
+ vmov q15,q1
+ teq r1,r2
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ .byte 0xe2,0x03,0xfa,0xf3 @ sha256su0 q8,q9
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+ .byte 0xe6,0x0c,0x64,0xf3 @ sha256su1 q8,q10,q11
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ .byte 0xe4,0x23,0xfa,0xf3 @ sha256su0 q9,q10
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+ .byte 0xe0,0x2c,0x66,0xf3 @ sha256su1 q9,q11,q8
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q10
+ .byte 0xe6,0x43,0xfa,0xf3 @ sha256su0 q10,q11
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+ .byte 0xe2,0x4c,0x60,0xf3 @ sha256su1 q10,q8,q9
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q11
+ .byte 0xe0,0x63,0xfa,0xf3 @ sha256su0 q11,q8
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+ .byte 0xe4,0x6c,0x62,0xf3 @ sha256su1 q11,q9,q10
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ .byte 0xe2,0x03,0xfa,0xf3 @ sha256su0 q8,q9
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+ .byte 0xe6,0x0c,0x64,0xf3 @ sha256su1 q8,q10,q11
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ .byte 0xe4,0x23,0xfa,0xf3 @ sha256su0 q9,q10
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+ .byte 0xe0,0x2c,0x66,0xf3 @ sha256su1 q9,q11,q8
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q10
+ .byte 0xe6,0x43,0xfa,0xf3 @ sha256su0 q10,q11
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+ .byte 0xe2,0x4c,0x60,0xf3 @ sha256su1 q10,q8,q9
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q11
+ .byte 0xe0,0x63,0xfa,0xf3 @ sha256su0 q11,q8
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+ .byte 0xe4,0x6c,0x62,0xf3 @ sha256su1 q11,q9,q10
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ .byte 0xe2,0x03,0xfa,0xf3 @ sha256su0 q8,q9
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+ .byte 0xe6,0x0c,0x64,0xf3 @ sha256su1 q8,q10,q11
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ .byte 0xe4,0x23,0xfa,0xf3 @ sha256su0 q9,q10
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+ .byte 0xe0,0x2c,0x66,0xf3 @ sha256su1 q9,q11,q8
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q10
+ .byte 0xe6,0x43,0xfa,0xf3 @ sha256su0 q10,q11
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+ .byte 0xe2,0x4c,0x60,0xf3 @ sha256su1 q10,q8,q9
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q11
+ .byte 0xe0,0x63,0xfa,0xf3 @ sha256su0 q11,q8
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+ .byte 0xe4,0x6c,0x62,0xf3 @ sha256su1 q11,q9,q10
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+
+ vld1.32 {q13},[r3]
+ vadd.i32 q12,q12,q10
+ sub r3,r3,#256-16 @ rewind
+ vmov q2,q0
+ .byte 0x68,0x0c,0x02,0xf3 @ sha256h q0,q1,q12
+ .byte 0x68,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q12
+
+ vadd.i32 q13,q13,q11
+ vmov q2,q0
+ .byte 0x6a,0x0c,0x02,0xf3 @ sha256h q0,q1,q13
+ .byte 0x6a,0x2c,0x14,0xf3 @ sha256h2 q1,q2,q13
+
+ vadd.i32 q0,q0,q14
+ vadd.i32 q1,q1,q15
+ bne .Loop_v8
+
+ vst1.32 {q0,q1},[r0]
+
+ bx lr @ bx lr
+.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
#endif
-.size sha256_block_data_order,.-sha256_block_data_order
-.asciz "SHA256 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>"
+.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro@openssl.org>"
.align 2
+#if __ARM_MARCH_ARCH__>=7
.comm OPENSSL_armcap_P,4,4
-
#endif
« shell/BUILD.gn ('K') | « third_party/boringssl/linux-arm/crypto/sha/sha1-armv4-large.S ('k') | third_party/boringssl/linux-arm/crypto/sha/sha512-armv4.S » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698