diff --git a/src/internal/bytealg/count_amd64.s b/src/internal/bytealg/count_amd64.s
index efb17f84b7..807c289113 100644
--- a/src/internal/bytealg/count_amd64.s
+++ b/src/internal/bytealg/count_amd64.s
@@ -57,6 +57,7 @@ sse:
 	LEAQ	-16(SI)(BX*1), AX	// AX = address of last 16 bytes
 	JMP	sseloopentry
 
+	PCALIGN $16
 sseloop:
 	// Move the next 16-byte chunk of the data into X1.
 	MOVOU	(DI), X1
@@ -163,6 +164,7 @@ avx2:
 	MOVD AX, X0
 	LEAQ -32(SI)(BX*1), R11
 	VPBROADCASTB  X0, Y1
+	PCALIGN $32
 avx2_loop:
 	VMOVDQU (DI), Y2
 	VPCMPEQB Y1, Y2, Y3