diff --git a/SM3性能优化.md b/SM3性能优化.md
index 11b13cb..d01670c 100644
--- a/SM3性能优化.md
+++ b/SM3性能优化.md
@@ -268,23 +268,19 @@ VEOR XTMP4.B16, XTMP0.B16, XTMP2.B16;         // XTMP2 = {..., ..., W[1], W[0]}
 // Prepare P1 parameters
 VEXT $4, XTMP2.B16, XWORD3.B16, XTMP3.B16;    // XTMP3 = W[-3] {W[0],w15, w14, w13}, Vm = XTMP2, Vn = XWORD3
 VSHL $15, XTMP3.S4, XTMP4.S4;
-VSRI $17, XTMP3.S4, XTMP4.S4;                 // XTMP4 = W[-3] rol 15 {DCxx}
-VEOR XTMP1.B16, XTMP4.B16, XTMP4.B16;         // XTMP4 = W[-9] XOR W[-16] XOR (W[-3] rol 15) {DCxx}
+VSRI $17, XTMP3.S4, XTMP4.S4;                 // XTMP4 = W[-3] rol 15 {DCBA}
+VEOR XTMP1.B16, XTMP4.B16, XTMP4.B16;         // XTMP4 = W[-9] XOR W[-16] XOR (W[-3] rol 15) {DCBA}
 
 // P1
 VSHL $15, XTMP4.S4, XTMP3.S4;
-VSRI $17, XTMP4.S4, XTMP3.S4;                 // XTMP3 = XTMP4 rol 15 {DCxx}
+VSRI $17, XTMP4.S4, XTMP3.S4;                 // XTMP3 = XTMP4 rol 15 {DCBA}
 VSHL $8, XTMP3.S4, XTMP1.S4;
-VSRI $24, XTMP3.S4, XTMP1.S4;                 // XTMP1 = XTMP4 rol 23 {DCxx}
-VEOR XTMP3.B16, XTMP4.B16, XTMP3.B16;         // XTMP3 = XTMP4 XOR (XTMP4 rol 15 {DCxx})
-VEOR XTMP3.B16, XTMP1.B16, XTMP1.B16;         // XTMP1 = XTMP4 XOR (XTMP4 rol 15 {DCxx}) XOR (XTMP4 rol 23 {DCxx})
+VSRI $24, XTMP3.S4, XTMP1.S4;                 // XTMP1 = XTMP4 rol 23 {DCBA}
+VEOR XTMP3.B16, XTMP4.B16, XTMP3.B16;         // XTMP3 = XTMP4 XOR (XTMP4 rol 15 {DCBA})
+VEOR XTMP3.B16, XTMP1.B16, XTMP1.B16;         // XTMP1 = XTMP4 XOR (XTMP4 rol 15 {DCBA}) XOR (XTMP4 rol 23 {DCBA})
 
-// Last 2 words message schedule result
-VEOR XTMP1.B16, XTMP0.B16, XTMP1.B16;         // XTMP1 = {W[3], W[2], ..., ...}
-
-// 拼接结果
-VEXT $8, XTMP2.B16, XTMP1.B16, XTMP3.B16;     // XTMP3 = {W[1], W[0], W[3], W[2]}, Vm = XTMP2, Vn = XTMP1
-VEXT $8, XTMP3.B16, XTMP3.B16, XWORD0.B16;    // XWORD0 = {W[3], W[2], W[1], W[0]}
+// 4 words message schedule result
+VEOR XTMP1.B16, XTMP0.B16, XTMP1.B16;         // XTMP1 = {W[3], W[2], W[1], W[0]}
 ```
 
 由于要算**52**个DWORDs，所以