// 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

MOVL $48, BX JMP addMulVVWx(SB) // func addMulVVW2048(z, x *uint, y uint) (c uint) TEXT ·addMulVVW2048(SB), $0-16 MOVL $64, BX JMP addMulVVWx(SB) TEXT addMulVVWx(SB), NOFRAME|NOSPLIT, $0 MOVL z+0(FP), DI MOVL x+4(FP), SI MOVL y+8(FP), BP LEAL (DI)(BX*4), DI LEAL (SI)(BX*4), SI NEGL BX // i = -n MOVL $0, CX // c = 0 JMP E6 L6: MOVL (SI)(BX*4), AX MULL BP ADDL CX, AX ADCL $0, DX ADDL AX, (DI)(BX*4) ADCL $0, DX MOVL DX, CX ADDL $1, BX // i++ E6: CMPL BX, $0 // i < 0 JL L6 MOVL CX, c+12(FP) RET gola...

MOVL $48, BX JMP addMulVVWx(SB) // func addMulVVW2048(z, x *uint, y uint) (c uint) TEXT ·addMulVVW2048(SB), $0-16 MOVL $64, BX JMP addMulVVWx(SB) TEXT addMulVVWx(SB), NOFRAME|NOSPLIT, $0 MOVL z+0(FP), DI MOVL x+4(FP), SI MOVL y+8(FP), BP LEAL (DI)(BX*4), DI LEAL (SI)(BX*4), SI NEGL BX // i = -n MOVL $0, CX // c = 0 JMP E6 L6: MOVL (SI)(BX*4), AX MULL BP ADDL CX, AX ADCL $0, DX ADDL AX, (DI)(BX*4) ADCL $0, DX MOVL DX, CX ADDL $1, BX // i++ E6: CMPL BX, $0 // i < 0 JL L6 MOVL CX, c+12(FP) RET gola...