mirror/gmsm
1
0
Fork 0
mirror of https://github.com/emmansun/gmsm.git synced 2025-04-26 20:26:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

cipher: optimize gb gf(2^128) reduction

Browse Source
This commit is contained in:
emmansun 2023-08-20 12:05:48 +08:00
parent 4eacdccbf6
commit ddea8332fe
2 changed files with 10 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -23,7 +23,7 @@
* **CFCA** - some cfca specific implementations. * **CFCA** - some cfca specific implementations.
* **CIPHER** - ECB/CCM/XTS cipher modes. * **CIPHER** - ECB/CCM/XTS cipher modes, XTS mode also supports **GB/T 17964-2021**.
* **SMX509** - a fork of golang X509 that supports ShangMi. * **SMX509** - a fork of golang X509 that supports ShangMi.

27
cipher/xts_amd64.s
View File

@ -12,21 +12,16 @@ DATA gcmPoly<>+0x08(SB)/8, $0x0000000000000000
DATA gbGcmPoly<>+0x00(SB)/8, $0x0000000000000000 DATA gbGcmPoly<>+0x00(SB)/8, $0x0000000000000000
DATA gbGcmPoly<>+0x08(SB)/8, $0xe100000000000000 DATA gbGcmPoly<>+0x08(SB)/8, $0xe100000000000000
DATA one<>+0x00(SB)/8, $0x0000000000000001
DATA one<>+0x08(SB)/8, $0x0000000000000000
GLOBL bswapMask<>(SB), (NOPTR+RODATA), $16 GLOBL bswapMask<>(SB), (NOPTR+RODATA), $16
GLOBL gcmPoly<>(SB), (NOPTR+RODATA), $16 GLOBL gcmPoly<>(SB), (NOPTR+RODATA), $16
GLOBL gbGcmPoly<>(SB), (NOPTR+RODATA), $16 GLOBL gbGcmPoly<>(SB), (NOPTR+RODATA), $16
GLOBL one<>(SB), (NOPTR+RODATA), $16
#define POLY X0 #define POLY X0
#define BSWAP X1 #define BSWAP X1
#define ONE X2 #define B0 X2
#define B0 X3 #define T0 X3
#define T0 X4 #define T1 X4
#define T1 X5
// func mul2(tweak *[blockSize]byte, isGB bool) // func mul2(tweak *[blockSize]byte, isGB bool)
TEXT ·mul2(SB),NOSPLIT,$0 TEXT ·mul2(SB),NOSPLIT,$0
@ -58,8 +53,6 @@ TEXT ·mul2(SB),NOSPLIT,$0
gb_alg: gb_alg:
MOVOU bswapMask<>(SB), BSWAP MOVOU bswapMask<>(SB), BSWAP
MOVOU gbGcmPoly<>(SB), POLY MOVOU gbGcmPoly<>(SB), POLY
MOVOU one<>(SB), ONE
PXOR X6, X6
PSHUFB BSWAP, B0 PSHUFB BSWAP, B0
@ -72,10 +65,10 @@ gb_alg:
POR T0, B0 POR T0, B0
// reduction // reduction
PAND ONE, T1
PSHUFD $0, T1, T1 PSHUFD $0, T1, T1
PCMPEQL X6, T1 PSLLL $31, T1
PANDN POLY, T1 PSRAL $31, T1
PAND POLY, T1
PXOR T1, B0 PXOR T1, B0
PSHUFB BSWAP, B0 PSHUFB BSWAP, B0
@ -124,8 +117,6 @@ loop:
dt_gb_alg: dt_gb_alg:
MOVOU bswapMask<>(SB), BSWAP MOVOU bswapMask<>(SB), BSWAP
MOVOU gbGcmPoly<>(SB), POLY MOVOU gbGcmPoly<>(SB), POLY
MOVOU one<>(SB), ONE
PXOR X6, X6
gb_loop: gb_loop:
MOVOU B0, (0*16)(AX) MOVOU B0, (0*16)(AX)
@ -142,10 +133,10 @@ gb_loop:
POR T0, B0 POR T0, B0
// reduction // reduction
PAND ONE, T1
PSHUFD $0, T1, T1 PSHUFD $0, T1, T1
PCMPEQL X6, T1 PSLLL $31, T1
PANDN POLY, T1 PSRAL $31, T1
PAND POLY, T1
PXOR T1, B0 PXOR T1, B0
PSHUFB BSWAP, B0 PSHUFB BSWAP, B0