diff --git a/SM3性能优化.md b/SM3性能优化.md
index 371659e..3c8a0d4 100644
--- a/SM3性能优化.md
+++ b/SM3性能优化.md
@@ -8,7 +8,7 @@
 # SHA256 SIMD Execution
 
 下面是SHA256 message scheduler SIMD实现，四轮算出下一个4个DWORDs.
-
+```asm
     // Wt = SIGMA1(Wt-2) + Wt-7 + SIGMA0(Wt-15) + Wt-16; for 16 <= t <= 63
     //   SIGMA0(x) = ROTR(7,x) XOR ROTR(18,x) XOR SHR(3,x)
     //   SIGMA1(x) = ROTR(17,x) XOR ROTR(19,x) XOR SHR(10,x)
@@ -52,6 +52,7 @@
     VPXOR   XTMP2, XTMP5, XTMP5;         \ // XTMP5 = s1 {xDxC}
     VPSHUFB shuff_DC00<>(SB), XTMP5, XTMP5;\ // XTMP5 = s1 {DC00}
     VPADDD  XTMP0, XTMP5, XDWORD0;       \ // XDWORD0 = {W[3], W[2], W[1], W[0]}
+```
 
 SM3的message scheduler有两个显著差别：
 
@@ -64,7 +65,7 @@ https://software.intel.com/sites/landingpage/IntrinsicsGuide/
 # SM3 SIMD Execution
 
 SM3的第一版，比SHA256复杂，不知道有没有继续优化的空间。
-
+```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
@@ -112,6 +113,7 @@ SM3的第一版，比SHA256复杂，不知道有没有继续优化的空间。
     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