mirror/gmsm
1
0
Fork 0
mirror of https://github.com/emmansun/gmsm.git synced 2025-05-11 03:26:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated SM3性能优化 (markdown)

Sun Yimin 2023-09-11 15:42:56 +08:00
parent a4c87b98b7
commit a98463ee7f
1 changed files with 47 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
SM3性能优化.md

@ -115,6 +115,53 @@ SM3的第一版，比SHA256复杂，不知道有没有继续优化的空间。
VPSHUFD $0x4E, XTMP3, XDWORD0; \ // XDWORD0 = {W[3], W[2], W[1], W[0]}
```
第二版（用VPSHUFB优化循环左移）：
```asm
// Wj ← P1(Wj−16 ⊕ Wj−9 ⊕ (Wj−3 ≪ 15)) ⊕ (Wj−13 ≪ 7) ⊕ Wj−6
// Transpose data into high/low parts
VPERM2I128 $0x20, XTMP2, XTMP0, XDWORD0 // w3, w2, w1, w0
VPERM2I128 $0x31, XTMP2, XTMP0, XDWORD1 // w7, w6, w5, w4
VPERM2I128 $0x20, XTMP3, XTMP1, XDWORD2 // w11, w10, w9, w8
VPERM2I128 $0x31, XTMP3, XTMP1, XDWORD3 // w15, w14, w13, w12
VPALIGNR $12, XDWORD0, XDWORD1, XTMP0; \ // XTMP0 = W[-13] = {w6,w5,w4,w3}
VPSLLD $7, XTMP0, XTMP1; \
VPSRLD $(32-7), XTMP0, XTMP0; \
VPOR XTMP0, XTMP1, XTMP1; \ // XTMP1 = W[-13] rol 7
VPALIGNR $8, XDWORD2, XDWORD3, XTMP0; \ // XTMP0 = W[-6] = {w13,w12,w11,w10}
VPXOR XTMP1, XTMP0, XTMP0; \ // XTMP0 = W[-6] XOR (W[-13] rol 7)
VPALIGNR $12, XDWORD1, XDWORD2, XTMP1; \ // XTMP1 = W[-9] = {w10,w9,w8,w7}
VPXOR XDWORD0, XTMP1, XTMP1; \ // XTMP1 = W[-9] XOR W[-16]
VPSHUFD $0xA5, XDWORD3, XTMP2; \ // XTMP2 = W[-3] {BBAA} {w14,w14,w13,w13}
VPSLLQ $15, XTMP2, XTMP2; \ // XTMP2 = W[-3] rol 15 {BxAx}
VPSHUFB shuff_00BA<>(SB), XTMP2, XTMP2;\ // XTMP2 = W[-3] rol 15 {00BA}
VPXOR XTMP1, XTMP2, XTMP2; \ // XTMP2 = W[-9] XOR W[-16] XOR (W[-3] rol 15) {xxBA}
VPSLLD $15, XTMP2, XTMP3; \
VPSRLD $(32-15), XTMP2, XTMP4; \
VPOR XTMP3, XTMP4, XTMP4; \ // XTMP4 = XTMP2 rol 15 {xxBA}
VPSHUFB r08_mask<>(SB), XTMP4, XTMP3; \ // XTMP3 = XTMP2 rol 23 {xxBA}
VPXOR XTMP2, XTMP4, XTMP4; \ // XTMP4 = XTMP2 XOR (XTMP2 rol 15 {xxBA})
VPXOR XTMP4, XTMP3, XTMP4; \ // XTMP4 = XTMP2 XOR (XTMP2 rol 15 {xxBA}) XOR (XTMP2 rol 23 {xxBA})
VPXOR XTMP4, XTMP0, XTMP2; \ // XTMP2 = {..., ..., W[1], W[0]}
VPALIGNR $12, XDWORD3, XTMP2, XTMP3; \ // XTMP3 = {..., W[1], W[0], w15}
VPSHUFD $80, XTMP3, XTMP4; \ // XTMP4 = = W[-3] {DDCC}
VPSLLQ $15, XTMP4, XTMP4; \ // XTMP4 = W[-3] rol 15 {DxCx}
VPSHUFB shuff_DC00<>(SB), XTMP4, XTMP4;\ // XTMP4 = W[-3] rol 15 {DC00}
VPXOR XTMP1, XTMP4, XTMP4; \ // XTMP4 = W[-9] XOR W[-16] XOR (W[-3] rol 15) {DCxx}
VPSLLD $15, XTMP4, XTMP5; \
VPSRLD $(32-15), XTMP4, XTMP3; \
VPOR XTMP3, XTMP5, XTMP3; \ // XTMP3 = XTMP4 rol 15 {DCxx}
VPSHUFB r08_mask<>(SB), XTMP3, XTMP1; \ // XTMP1 = XTMP4 rol 23 {DCxx}
VPXOR XTMP3, XTMP4, XTMP3; \ // XTMP3 = XTMP4 XOR (XTMP4 rol 15 {DCxx})
VPXOR XTMP3, XTMP1, XTMP1; \ // XTMP1 = XTMP4 XOR (XTMP4 rol 15 {DCxx}) XOR (XTMP4 rol 23 {DCxx})
VPXOR XTMP1, XTMP0, XTMP1; \ // XTMP1 = {W[3], W[2], ..., ...}
VPALIGNR $8, XTMP1, XTMP2, XTMP3; \ // XTMP3 = {W[1], W[0], W[3], W[2]}
VPSHUFD $0x4E, XTMP3, XDWORD0; \ // XDWORD0 = {W[3], W[2], W[1], W[0]}
```
由于要算**52**个DWORDs，所以
| Ingteger Execution | SIMD Execution |