diff --git a/contrib/arm-optimized-routines/string/aarch64/memcpy.S b/contrib/arm-optimized-routines/string/aarch64/memcpy.S
--- a/contrib/arm-optimized-routines/string/aarch64/memcpy.S
+++ b/contrib/arm-optimized-routines/string/aarch64/memcpy.S
@@ -133,12 +133,12 @@
 	stp	G_l, G_h, [dstend, -64]
 	stp	H_l, H_h, [dstend, -48]
 L(copy96):
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
 	stp	A_l, A_h, [dstin]
 	stp	B_l, B_h, [dstin, 16]
 	stp	E_l, E_h, [dstin, 32]
 	stp	F_l, F_h, [dstin, 48]
-	stp	C_l, C_h, [dstend, -32]
-	stp	D_l, D_h, [dstend, -16]
 	ret
 
 	.p2align 4
@@ -233,10 +233,10 @@
 	stp	C_l, C_h, [dstend, -48]
 	ldp	C_l, C_h, [src]
 	stp	D_l, D_h, [dstend, -64]
-	stp	G_l, G_h, [dstin, 48]
-	stp	A_l, A_h, [dstin, 32]
-	stp	B_l, B_h, [dstin, 16]
 	stp	C_l, C_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	A_l, A_h, [dstin, 32]
+	stp	G_l, G_h, [dstin, 48]
 	ret
 
 END (__memcpy_aarch64)
diff --git a/sys/arm64/arm64/memcpy.S b/sys/arm64/arm64/memcpy.S
--- a/sys/arm64/arm64/memcpy.S
+++ b/sys/arm64/arm64/memcpy.S
@@ -132,12 +133,12 @@
 	stp	G_l, G_h, [dstend, -64]
 	stp	H_l, H_h, [dstend, -48]
 L(copy96):
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
 	stp	A_l, A_h, [dstin]
 	stp	B_l, B_h, [dstin, 16]
 	stp	E_l, E_h, [dstin, 32]
 	stp	F_l, F_h, [dstin, 48]
-	stp	C_l, C_h, [dstend, -32]
-	stp	D_l, D_h, [dstend, -16]
 	ret
 
 	.p2align 4
@@ -232,10 +233,10 @@
 	stp	C_l, C_h, [dstend, -48]
 	ldp	C_l, C_h, [src]
 	stp	D_l, D_h, [dstend, -64]
-	stp	G_l, G_h, [dstin, 48]
-	stp	A_l, A_h, [dstin, 32]
-	stp	B_l, B_h, [dstin, 16]
 	stp	C_l, C_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	A_l, A_h, [dstin, 32]
+	stp	G_l, G_h, [dstin, 48]
 	ret
 EEND(memmove)
 END(memcpy)