// so actually
// void atomicload64(uint64 *res, uint64 volatile *addr);
TEXT runtime·atomicload64(SB), NOSPLIT, $0-12
	MOVL	ptr+0(FP), AX
	TESTL	$7, AX
	JZ	2(PC)
	MOVL	0, AX // crash with nil ptr deref
	LEAL	ret_lo+4(FP), BX
	// MOVQ (%EAX), %MM0
	BYTE $0x0f; BYTE $0x6f; BYTE $0x00
	// MOVQ %MM0, 0(%EBX)
	BYTE $0x0f; BYTE $0x7f; BYTE $0x03
	// EMMS
	BYTE $0x0F; BYTE $0x77
	RET