diff --git a/xor_amd64.s b/xor_amd64.s
index f641c4a..c137b67 100644
--- a/xor_amd64.s
+++ b/xor_amd64.s
@@ -115,32 +115,32 @@ XOR_LOOP_256_AVX:
 	CMPQ     N, $256
 	JB       XOR_LOOP_128_AVX
 
-	VMOVDQU     (A), Y0
-	VMOVDQU   32(A), Y1
-	VMOVDQU   64(A), Y2
-	VMOVDQU   96(A), Y3
-	VMOVDQU  128(A), Y4
-	VMOVDQU  160(A), Y5
-	VMOVDQU  192(A), Y6
-	VMOVDQU  224(A), Y7
+	VMOVDQU  0*32(A), Y0
+	VMOVDQU  1*32(A), Y1
+	VMOVDQU  2*32(A), Y2
+	VMOVDQU  3*32(A), Y3
+	VMOVDQU  4*32(A), Y4
+	VMOVDQU  5*32(A), Y5
+	VMOVDQU  6*32(A), Y6
+	VMOVDQU  7*32(A), Y7
 
-	VPXOR       (B), Y0, Y0
-	VPXOR     32(B), Y1, Y1
-	VPXOR     64(B), Y2, Y2
-	VPXOR     96(B), Y3, Y3
-	VPXOR    128(B), Y4, Y4
-	VPXOR    160(B), Y5, Y5
-	VPXOR    192(B), Y6, Y6
-	VPXOR    224(B), Y7, Y7
+	VPXOR    0*32(B), Y0, Y0
+	VPXOR    1*32(B), Y1, Y1
+	VPXOR    2*32(B), Y2, Y2
+	VPXOR    3*32(B), Y3, Y3
+	VPXOR    4*32(B), Y4, Y4
+	VPXOR    5*32(B), Y5, Y5
+	VPXOR    6*32(B), Y6, Y6
+	VPXOR    7*32(B), Y7, Y7
 
-	VMOVDQU  Y0,    (Dst)
-	VMOVDQU  Y1,  32(Dst)
-	VMOVDQU  Y2,  64(Dst)
-	VMOVDQU  Y3,  96(Dst)
-	VMOVDQU  Y4, 128(Dst)
-	VMOVDQU  Y5, 160(Dst)
-	VMOVDQU  Y6, 192(Dst)
-	VMOVDQU  Y7, 224(Dst)
+	VMOVDQU  Y0, 0*32(Dst)
+	VMOVDQU  Y1, 1*32(Dst)
+	VMOVDQU  Y2, 2*32(Dst)
+	VMOVDQU  Y3, 3*32(Dst)
+	VMOVDQU  Y4, 4*32(Dst)
+	VMOVDQU  Y5, 5*32(Dst)
+	VMOVDQU  Y6, 6*32(Dst)
+	VMOVDQU  Y7, 7*32(Dst)
 
 	ADDQ     $256, A
 	ADDQ     $256, B
@@ -150,23 +150,23 @@ XOR_LOOP_256_AVX:
 	RET
 
 XOR_LOOP_128_AVX:
-	CMPQ   N, $128
-	JB     XOR_LOOP_64_AVX
+	CMPQ     N, $128
+	JB       XOR_LOOP_64_AVX
 
-	VMOVDQU    (A), Y0
-	VMOVDQU  32(A), Y1
-	VMOVDQU  64(A), Y2
-	VMOVDQU  96(A), Y3
+	VMOVDQU  0*32(A), Y0
+	VMOVDQU  1*32(A), Y1
+	VMOVDQU  2*32(A), Y2
+	VMOVDQU  3*32(A), Y3
 
-	VPXOR      (B), Y0, Y0
-	VPXOR    32(B), Y1, Y1
-	VPXOR    64(B), Y2, Y2
-	VPXOR    96(B), Y3, Y3
+	VPXOR    0*32(B), Y0, Y0
+	VPXOR    1*32(B), Y1, Y1
+	VPXOR    2*32(B), Y2, Y2
+	VPXOR    3*32(B), Y3, Y3
 
-	VMOVDQU  Y0,   (Dst)
-	VMOVDQU  Y1, 32(Dst)
-	VMOVDQU  Y2, 64(Dst)
-	VMOVDQU  Y3, 96(Dst)
+	VMOVDQU  Y0, 0*32(Dst)
+	VMOVDQU  Y1, 1*32(Dst)
+	VMOVDQU  Y2, 2*32(Dst)
+	VMOVDQU  Y3, 3*32(Dst)
 
 	ADDQ     $128, A
 	ADDQ     $128, B
@@ -179,14 +179,14 @@ XOR_LOOP_64_AVX:
 	CMPQ     N, $64
 	JB       XOR_LOOP_16_AVX
 
-	VMOVDQU    (A), Y0
-	VMOVDQU  32(A), Y1
+	VMOVDQU  0*32(A), Y0
+	VMOVDQU  1*32(A), Y1
 
-	VPXOR      (B), Y0, Y2
-	VPXOR    32(B), Y1, Y3
+	VPXOR    0*32(B), Y0, Y2
+	VPXOR    1*32(B), Y1, Y3
 
-	VMOVDQU  Y2,   (Dst)
-	VMOVDQU  Y3, 32(Dst)
+	VMOVDQU  Y2, 0*32(Dst)
+	VMOVDQU  Y3, 1*32(Dst)
 
 	ADDQ     $64, A
 	ADDQ     $64, B