emo/busybox
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

libbb/sha256: code shrink in 64-bit x86

Browse Source 
function                                             old     new   delta
sha256_process_block64_shaNI                         730     706     -24

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
This commit is contained in:
Denys Vlasenko 2022-02-03 15:17:42 +01:00
parent de6cb4bed8
commit a1429fbb8c
1 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
libbb/hash_md5_sha256_x86-64_shaNI.S
View File

@ -50,7 +50,7 @@ sha256_process_block64_shaNI:
pblendw $0xF0, MSGTMP4, STATE1 /* CDGH */
mova128 PSHUFFLE_BSWAP32_FLIP_MASK(%rip), SHUF_MASK
lea K256(%rip), SHA256CONSTANTS
leaq K256+8*16(%rip), SHA256CONSTANTS
/* Save hash values for addition after rounds */
mova128 STATE0, ABEF_SAVE
@ -60,7 +60,7 @@ sha256_process_block64_shaNI:
movu128 0*16(DATA_PTR), MSG
pshufb SHUF_MASK, MSG
mova128 MSG, MSGTMP0
paddd 0*16(SHA256CONSTANTS), MSG
paddd 0*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
shuf128_32 $0x0E, MSG, MSG
sha256rnds2 STATE1, STATE0
@ -69,7 +69,7 @@ sha256_process_block64_shaNI:
movu128 1*16(DATA_PTR), MSG
pshufb SHUF_MASK, MSG
mova128 MSG, MSGTMP1
paddd 1*16(SHA256CONSTANTS), MSG
paddd 1*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
shuf128_32 $0x0E, MSG, MSG
sha256rnds2 STATE1, STATE0
@ -79,7 +79,7 @@ sha256_process_block64_shaNI:
movu128 2*16(DATA_PTR), MSG
pshufb SHUF_MASK, MSG
mova128 MSG, MSGTMP2
paddd 2*16(SHA256CONSTANTS), MSG
paddd 2*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
shuf128_32 $0x0E, MSG, MSG
sha256rnds2 STATE1, STATE0
@ -89,7 +89,7 @@ sha256_process_block64_shaNI:
movu128 3*16(DATA_PTR), MSG
pshufb SHUF_MASK, MSG
mova128 MSG, MSGTMP3
paddd 3*16(SHA256CONSTANTS), MSG
paddd 3*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP3, MSGTMP4
palignr $4, MSGTMP2, MSGTMP4
@ -101,7 +101,7 @@ sha256_process_block64_shaNI:
/* Rounds 16-19 */
mova128 MSGTMP0, MSG
paddd 4*16(SHA256CONSTANTS), MSG
paddd 4*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP0, MSGTMP4
palignr $4, MSGTMP3, MSGTMP4
@ -113,7 +113,7 @@ sha256_process_block64_shaNI:
/* Rounds 20-23 */
mova128 MSGTMP1, MSG
paddd 5*16(SHA256CONSTANTS), MSG
paddd 5*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP1, MSGTMP4
palignr $4, MSGTMP0, MSGTMP4
@ -125,7 +125,7 @@ sha256_process_block64_shaNI:
/* Rounds 24-27 */
mova128 MSGTMP2, MSG
paddd 6*16(SHA256CONSTANTS), MSG
paddd 6*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP2, MSGTMP4
palignr $4, MSGTMP1, MSGTMP4
@ -137,7 +137,7 @@ sha256_process_block64_shaNI:
/* Rounds 28-31 */
mova128 MSGTMP3, MSG
paddd 7*16(SHA256CONSTANTS), MSG
paddd 7*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP3, MSGTMP4
palignr $4, MSGTMP2, MSGTMP4
@ -149,7 +149,7 @@ sha256_process_block64_shaNI:
/* Rounds 32-35 */
mova128 MSGTMP0, MSG
paddd 8*16(SHA256CONSTANTS), MSG
paddd 8*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP0, MSGTMP4
palignr $4, MSGTMP3, MSGTMP4
@ -161,7 +161,7 @@ sha256_process_block64_shaNI:
/* Rounds 36-39 */
mova128 MSGTMP1, MSG
paddd 9*16(SHA256CONSTANTS), MSG
paddd 9*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP1, MSGTMP4
palignr $4, MSGTMP0, MSGTMP4
@ -173,7 +173,7 @@ sha256_process_block64_shaNI:
/* Rounds 40-43 */
mova128 MSGTMP2, MSG
paddd 10*16(SHA256CONSTANTS), MSG
paddd 10*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP2, MSGTMP4
palignr $4, MSGTMP1, MSGTMP4
@ -185,7 +185,7 @@ sha256_process_block64_shaNI:
/* Rounds 44-47 */
mova128 MSGTMP3, MSG
paddd 11*16(SHA256CONSTANTS), MSG
paddd 11*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP3, MSGTMP4
palignr $4, MSGTMP2, MSGTMP4
@ -197,7 +197,7 @@ sha256_process_block64_shaNI:
/* Rounds 48-51 */
mova128 MSGTMP0, MSG
paddd 12*16(SHA256CONSTANTS), MSG
paddd 12*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP0, MSGTMP4
palignr $4, MSGTMP3, MSGTMP4
@ -209,7 +209,7 @@ sha256_process_block64_shaNI:
/* Rounds 52-55 */
mova128 MSGTMP1, MSG
paddd 13*16(SHA256CONSTANTS), MSG
paddd 13*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP1, MSGTMP4
palignr $4, MSGTMP0, MSGTMP4
@ -220,7 +220,7 @@ sha256_process_block64_shaNI:
/* Rounds 56-59 */
mova128 MSGTMP2, MSG
paddd 14*16(SHA256CONSTANTS), MSG
paddd 14*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
mova128 MSGTMP2, MSGTMP4
palignr $4, MSGTMP1, MSGTMP4
@ -231,7 +231,7 @@ sha256_process_block64_shaNI:
/* Rounds 60-63 */
mova128 MSGTMP3, MSG
paddd 15*16(SHA256CONSTANTS), MSG
paddd 15*16-8*16(SHA256CONSTANTS), MSG
sha256rnds2 STATE0, STATE1
shuf128_32 $0x0E, MSG, MSG
sha256rnds2 STATE1, STATE0