diff --git a/kernel/x86_64/cgemm_kernel_4x8_sandy.S b/kernel/x86_64/cgemm_kernel_4x8_sandy.S
index 56ebee120..5987b8e61 100644
--- a/kernel/x86_64/cgemm_kernel_4x8_sandy.S
+++ b/kernel/x86_64/cgemm_kernel_4x8_sandy.S
@@ -3578,7 +3578,7 @@ ADDQ	$8*SIZE, ptrba;
 ADDQ	$16*SIZE, ptrbb;
 DECQ	k;
 JG	.L241_bodyB;
-.align
+ALIGN_5
 .L241_loopE:
 #ifndef	TRMMKERNEL
 TEST $2, bk;
diff --git a/kernel/x86_64/sgemm_kernel_8x8_sandy.S b/kernel/x86_64/sgemm_kernel_8x8_sandy.S
index 4d16a60d0..23eda3af8 100644
--- a/kernel/x86_64/sgemm_kernel_8x8_sandy.S
+++ b/kernel/x86_64/sgemm_kernel_8x8_sandy.S
@@ -2412,7 +2412,7 @@ ADDQ	$4*SIZE, ptrba;
 ADDQ	$16*SIZE, ptrbb;
 DECQ	k;
 JG .L241_bodyB;
-.align
+ALIGN_4
 .L241_loopE:
 #ifndef	TRMMKERNEL
 TEST $2, bk;