diff --git a/SM2-WWMM-(2).md b/SM2-WWMM-(2).md
index 0317445..3abe98d 100644
--- a/SM2-WWMM-(2).md
+++ b/SM2-WWMM-(2).md
@@ -446,32 +446,34 @@ $T_3=t_7 \ast 2^{448} + t_6 \ast 2^{384} + t_5 \ast 2^{320} + (t_4+Y) \ast 2^{25
 
 **使用MULXQ**:  
 ```asm
-	// First reduction step, [ord3, ord2, ord1, ord0] = [1, -0x100000000, -1, ord1, ord0]
-	MOVQ acc0, DX
-	MULXQ p256ordK0<>(SB), t0, AX
-	// calculate the positive part first: [1, 0, 0, ord1, ord0] * t0 + [0, acc3, acc2, acc1, acc0]
-	// the result is [acc0, acc3, acc2, acc1], last lowest limb is dropped.
-	MOVQ t0, DX                 // Y = t0 = (k0 * acc0) mod 2^64
-	MULXQ p256ord<>+0x00(SB), AX, t1
-	ADDQ AX, acc0               // (carry1, acc0) = acc0 + L(t0 * ord0)
-	ADCQ t1, acc1               // (carry2, acc1) = acc1 + H(t0 * ord0) + carry1
-	MOVQ t0, acc0               // acc0 = t0 
+  // First reduction step, [ord3, ord2, ord1, ord0] = [1, -0x100000000, -1, ord1, ord0]
+  MOVQ acc0, DX
+  MULXQ p256ordK0<>(SB), t0, AX
+  // calculate the positive part first: [1, 0, 0, ord1, ord0] * t0 + [0, acc3, acc2, acc1, acc0]
+  // the result is [acc0, acc3, acc2, acc1], last lowest limb is dropped.
+  MOVQ t0, DX                 // Y = t0 = (k0 * acc0) mod 2^64
+  MULXQ p256ord<>+0x00(SB), AX, t1
+  ADDQ AX, acc0               // (carry1, acc0) = acc0 + L(t0 * ord0)
+  ADCQ t1, acc1               // (carry2, acc1) = acc1 + H(t0 * ord0) + carry1
+  MOVQ t0, acc0               // acc0 = t0 
 
-	MULXQ p256ord<>+0x08(SB), AX, t1
-	ADCQ $0, t1                 // t1 = carry2 + H(t0*ord1)
-	ADDQ AX, acc1               // (carry3, acc1) = acc1 + L(t0*ord1)
-	ADCQ t1, acc2               // (carry4, acc2) = acc2 + t1 + carry3
-	ADCQ $0, acc3               // (carry5, acc3) = acc3 + carry4
-	ADCQ $0, acc0               //           acc0 = t0 + carry5 
-	// calculate the negative part: [acc0, acc3, acc2, acc1] - [0, 0x100000000, 1, 0] * t0
-	MOVQ t0, AX
-	//MOVQ t0, DX              // This is not required due to t0=DX already
-	SHLQ $32, AX
-	SHRQ $32, DX
+  // calculate the negative part: [acc0, acc3, acc2, acc1] - [0, 0x100000000, 1, 0] * t0
+  MOVQ t0, AX
+  SHLQ $32, AX
+  SHRQ $32, DX
+
+  SUBQ t0, acc2
+  SBBQ AX, acc3
+  SBBQ DX, acc0
+
+  MOVQ t0, DX
+  MULXQ p256ord<>+0x08(SB), AX, t1
+  ADCQ $0, t1                 // t1 = carry2 + H(t0*ord1)
+  ADDQ AX, acc1               // (carry3, acc1) = acc1 + L(t0*ord1)
+  ADCQ t1, acc2               // (carry4, acc2) = acc2 + t1 + carry3
+  ADCQ $0, acc3               // (carry5, acc3) = acc3 + carry4
+  ADCQ $0, acc0               //           acc0 = t0 + carry5 
 
-	SUBQ t0, acc2
-	SBBQ AX, acc3
-	SBBQ DX, acc0
 ```
 乘法: 3  
 移位：2  
@@ -633,47 +635,48 @@ $t_5=t_5 - 0$
 乘法: 3  
 移位：2    
 加法：9  
-减法：4  
+减法：3  
 
 **使用MULXQ**:  
 ```asm
-	// First reduction step
-	MOVQ acc0, DX
-	MULXQ p256ordK0<>(SB), t0, AX 
+  // First reduction step
+  MOVQ acc0, DX
+  MULXQ p256ordK0<>(SB), t0, AX 
 
-	MOVQ t0, DX
-	MULXQ p256ord<>+0x00(SB), AX, BX
-	ADDQ AX, acc0
-	ADCQ BX, acc1
+  MOVQ t0, DX
+  MULXQ p256ord<>+0x00(SB), AX, BX
+  ADDQ AX, acc0
+  ADCQ BX, acc1
+  MOVQ t0, acc0
 
-	MULXQ p256ord<>+0x08(SB), AX, BX
-	ADCQ $0, BX
-	ADDQ AX, acc1
-	ADCQ BX, acc2
-	ADCQ $0, acc3
-	ADCQ t0, acc4
-	ADCQ $0, acc5
-
-	MOVQ t0, AX
-	//MOVQ t0, DX // This is not required due to t0=DX already
-	SHLQ $32, AX
-	SHRQ $32, DX
+  MOVQ t0, AX
+  SHLQ $32, AX
+  SHRQ $32, DX
 		
-	SUBQ t0, acc2
-	SBBQ AX, acc3
-	SBBQ DX, acc4
-	SBBQ $0, acc5
+  SUBQ t0, acc2
+  SBBQ AX, acc3
+  SBBQ DX, acc0
+
+  MOVQ t0, DX
+  MULXQ p256ord<>+0x08(SB), AX, BX
+  ADCQ $0, BX
+  ADDQ AX, acc1
+  ADCQ BX, acc2
+  ADCQ $0, acc3
+  ADCQ acc0, acc4
+  ADCQ $0, acc5
+
 ```
 乘法: 3  
 移位：2    
 加法：8  
-减法：4  
+减法：3  
 
 | 方案      | 乘法 | 移位 | 加法 | 减法 |
 | ----------- | ----------- | ----------- | ----------- | ----------- |
 | 方案一      | 5 | 0 | 15 | 0 |
 | 方案一（MULX/ADCX/ADOX）   | 5 | 0 | 10 | 0 |
 | 方案二   | 3 | 2 | 9 | 3 |  
-| 方案二（MULX）   | 3 | 2 | 8 | 4 |  
+| 方案二（MULX）   | 3 | 2 | 8 | 3 |  
 
 看来在支持**MULXQ/ADCXQ/ADOXQ**的情况下，使用方案一（MULX/ADCX/ADOX）更好！