diff --git a/src/runtime/asm_power64x.s b/src/runtime/asm_power64x.s
index b489f6accb..21220e5cb8 100644
--- a/src/runtime/asm_power64x.s
+++ b/src/runtime/asm_power64x.s
@@ -557,13 +557,27 @@ TEXT runtime·atomicstore64(SB), NOSPLIT, $0-16
 
 // void	runtime·atomicor8(byte volatile*, byte);
 TEXT runtime·atomicor8(SB), NOSPLIT, $0-9
-	MOVD	0(FP), R3
-	MOVD	8(FP), R4
+	MOVD	ptr+0(FP), R3
+	MOVBZ	val+8(FP), R4
+	// Align ptr down to 4 bytes so we can use 32-bit load/store.
+	// R5 = (R3 << 0) & ~3
+	RLDCR	$0, R3, $~3, R5
+	// Compute val shift.
+#ifdef GOARCH_power64
+	// Big endian.  ptr = ptr ^ 3
+	XOR	$3, R3
+#endif
+	// R6 = ((ptr & 3) * 8) = (ptr << 3) & (3*8)
+	RLDC	$3, R3, $(3*8), R6
+	// Shift val for aligned ptr.  R4 = val << R6
+	SLD	R6, R4, R4
+
+atomicor8_again:
 	SYNC
-	LWAR	(R3), R5
-	OR	R4, R5
-	STWCCC	R5, (R3)
-	BNE	-3(PC)
+	LWAR	(R5), R6
+	OR	R4, R6
+	STWCCC	R6, (R5)
+	BNE	atomicor8_again
 	SYNC
 	ISYNC
 	RETURN
diff --git a/src/runtime/runtime.c b/src/runtime/runtime.c
index b3503fb909..d984983ce2 100644
--- a/src/runtime/runtime.c
+++ b/src/runtime/runtime.c
@@ -185,6 +185,7 @@ runtime·check(void)
 	float64 j, j1;
 	byte *k, *k1;
 	uint16* l;
+	byte m[4];
 	struct x1 {
 		byte x;
 	};
@@ -236,6 +237,11 @@ runtime·check(void)
 	if(k != k1)
 		runtime·throw("casp3");
 
+	m[0] = m[1] = m[2] = m[3] = 0x1;
+	runtime·atomicor8(&m[1], 0xf0);
+	if (m[0] != 0x1 || m[1] != 0xf1 || m[2] != 0x1 || m[3] != 0x1)
+		runtime·throw("atomicor8");
+
 	*(uint64*)&j = ~0ULL;
 	if(j == j)
 		runtime·throw("float64nan");