diff --git a/SM3性能优化.md b/SM3性能优化.md
index 5d57c5d..7061efc 100644
--- a/SM3性能优化.md
+++ b/SM3性能优化.md
@@ -162,6 +162,46 @@ 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]}
 ```
 
+ARM64 NEON 版（没有用VTBL表查询指令）：
+```
+VEXT $12, XWORD1.B16, XWORD0.B16, XTMP0.B16;  // XTMP0 = W[-13] = {w6,w5,w4,w3}, Vm = XWORD1, Vn = XWORD0
+VSHL $7, XTMP0.S4, XTMP1.S4;
+VSRI $25, XTMP0.S4, XTMP1.S4;                 // XTMP1 = W[-13] rol 7
+VEXT $8, XWORD3.B16, XWORD2.B16, XTMP0.B16;   // XTMP0 = W[-6] = {w13,w12,w11,w10}
+VEOR XTMP1.B16, XTMP0.B16, XTMP0.B16;         // XTMP0 = W[-6] ^ (W[-13] rol 7)
+VEXT $12, XWORD2.B16, XWORD1.B16, XTMP1.B16;  // XTMP1 = W[-9] = {w10,w9,w8,w7}, Vm = XWORD2, Vn = XWORD1
+VEOR XWORD0.B16, XTMP1.B16, XTMP1.B16;        // XTMP1 = W[-9] ^ W[-16]
+
+VEXT $4, XWORD2.B16, XWORD3.B16, XTMP3.B16;   // XTMP3 = W[-3] {w11,w15,w14,w13}
+VSHL $15, XTMP3.S4, XTMP2.S4;                 
+VSRI $17, XTMP3.S4, XTMP2.S4;                 // XTMP2 = W[-3] rol 15 {xxBA}
+VEOR XTMP1.B16, XTMP2.B16, XTMP2.B16;         // XTMP2 = W[-9] ^ W[-16] ^ (W[-3] rol 15) {xxBA}
+
+VSHL $15, XTMP2.S4, XTMP4.S4;
+VSRI $17, XTMP2.S4, XTMP4.S4;                 // XTMP4 =  = XTMP2 rol 15 {xxBA}
+VSHL $8, XTMP4.S4, XTMP3.S4;
+VSRI $24, XTMP4.S4, XTMP3.S4;                 // XTMP3 = XTMP2 rol 23 {xxBA}
+VEOR XTMP2.B16, XTMP4.B16, XTMP4.B16;         // XTMP4 = XTMP2 XOR (XTMP2 rol 15 {xxBA})
+VEOR XTMP4.B16, XTMP3.B16, XTMP4.B16;         // XTMP4 = XTMP2 XOR (XTMP2 rol 15 {xxBA}) XOR (XTMP2 rol 23 {xxBA})
+VEOR XTMP4.B16, XTMP0.B16, XTMP2.B16;         // XTMP2 = {..., ..., W[1], W[0]}
+
+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}
+
+VSHL $15, XTMP4.S4, XTMP3.S4;
+VSRI $17, XTMP4.S4, XTMP3.S4;                 // XTMP3 = XTMP4 rol 15 {DCxx}
+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})
+VEOR XTMP1.B16, XTMP0.B16, XTMP1.B16;         // XTMP1 = {W[3], W[2], ..., ...}
+
+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]}
+```
+
 由于要算**52**个DWORDs，所以
 
 | Ingteger Execution     | SIMD Execution               |