func ptrEqual() {
	// amd64:-"JEQ",-"JNE"
	// ppc64x:-"BEQ",-"BNE"
	// s390x:-"BEQ",-"BNE"
	copy(x[:], x[:])
}

func ptrOneOffset() {
	// amd64:-"JEQ",-"JNE"
	// ppc64x:-"BEQ",-"BNE"
	// s390x:-"BEQ",-"BNE"
	copy(x[1:], x[:])
}

func ptrBothOffset() {
	// amd64:-"JEQ",-"JNE"
	// ppc64x:-"BEQ",-"BNE"
	// s390x:-"BEQ",-"BNE"
	copy(x[1:], x[2:])
}

aligned:
	MOVQ $0, AX // position in slices

	PCALIGN $16
loop16b:
	MOVOU (SI)(AX*1), X0   // XOR 16byte forwards.
	MOVOU (CX)(AX*1), X1
	PXOR  X1, X0
	MOVOU X0, (BX)(AX*1)
	ADDQ  $16, AX
	CMPQ  DX, AX
	JNE   loop16b
	RET

	PCALIGN $16
loop_1b:
	SUBQ  $1, DX           // XOR 1byte backwards.
	MOVB  (SI)(DX*1), DI
	MOVB  (CX)(DX*1), AX
	XORB  AX, DI
	MOVB  DI, (BX)(DX*1)

	MOVL	(_INTERRUPT_TIME+time_hi2), DI
	CMPL	AX, DI
	JNE	loop

	// w = DI:CX
	// multiply by 100
	MOVL	$100, AX
	MULL	CX
	IMULL	$100, DI
	ADDL	DI, DX
	// w*100 = DX:AX
	MOVL	AX, mono+12(FP)
	MOVL	DX, mono+16(FP)

wall:
	MOVL	(_SYSTEM_TIME+time_hi1), CX
	MOVL	(_SYSTEM_TIME+time_lo), AX
	MOVL	(_SYSTEM_TIME+time_hi2), DX
	CMPL	CX, DX
	JNE	wall

	// w = DX:AX

	// CX = size (want in BX)
	CMPQ	AX, BX
	JNE	neq
	MOVQ	$1, AX	// return 1
	RET
neq:
	MOVQ	AX, SI
	MOVQ	BX, DI
	MOVQ	CX, BX
	JMP	memeqbody<>(SB)

// memequal_varlen(a, b unsafe.Pointer) bool
TEXT runtime·memequal_varlen<ABIInternal>(SB),NOSPLIT,$0-17
	// AX = a       (want in SI)
	// BX = b       (want in DI)
	// 8(DX) = size (want in BX)
	CMPQ	AX, BX
	JNE	neq
	MOVQ	$1, AX	// return 1
	RET
neq:

	BSFL	DX, DX	// Find first set bit.
	JZ	failure	// No set bit, failure.
	MOVQ	DX, (R8)
	RET

avx2:
#ifndef hasAVX2
	CMPB   internal∕cpu·X86+const_offsetX86HasAVX2(SB), $1
	JNE sse
#endif
	MOVD AX, X0
	LEAQ -32(SI)(BX*1), R11
	VPBROADCASTB  X0, Y1

	PCALIGN $32
avx2_loop:
	VMOVDQU (DI), Y2
	VPCMPEQB Y1, Y2, Y3
	VPTEST Y3, Y3
	JNZ avx2success
	ADDQ $32, DI

	// Directly return DX, we don't need to accumulate
	// since we have <16 bytes.
	POPCNTL DX, DX
	MOVQ	DX, (R8)
	RET

avx2:
#ifndef hasAVX2
	CMPB   internal∕cpu·X86+const_offsetX86HasAVX2(SB), $1
	JNE sse
#endif
	MOVD AX, X0
	LEAQ -64(SI)(BX*1), R11
	LEAQ (SI)(BX*1), R13
	VPBROADCASTB  X0, Y1
	PCALIGN $32
avx2_loop:
	VMOVDQU (DI), Y2
	VMOVDQU 32(DI), Y4
	VPCMPEQB Y1, Y2, Y3

	JB loop33to63
fail_avx2:
	VZEROUPPER
fail:
	MOVQ $-1, (R11)
	RET
success_avx2:
	VZEROUPPER
	JMP success
sse42:
#ifndef hasSSE42
	CMPB internal∕cpu·X86+const_offsetX86HasSSE42(SB), $1
	JNE no_sse42
#endif
	CMPQ AX, $12
	// PCMPESTRI is slower than normal compare,
	// so using it makes sense only if we advance 4+ bytes per compare
	// This value was determined experimentally and is the ~same

	MOVL	DX, 0(CX)(FS)
	RET

TEXT runtime·nanotime1(SB),NOSPLIT,$0-8
loop:
	MOVL	(_INTERRUPT_TIME+time_hi1), AX
	MOVL	(_INTERRUPT_TIME+time_lo), CX
	MOVL	(_INTERRUPT_TIME+time_hi2), DI
	CMPL	AX, DI
	JNE	loop

	// wintime = DI:CX, multiply by 100
	MOVL	$100, AX
	MULL	CX
	IMULL	$100, DI
	ADDL	DI, DX
	// wintime*100 = DX:AX
	MOVL	AX, ret_lo+0(FP)
	MOVL	DX, ret_hi+4(FP)
	RET

cat >umod-amd64.s <<'EOF'
# tu_int __umodti3(tu_int x, tu_int y)
# x is rsi:rdi, y is rcx:rdx, return result is rdx:rax.
.globl __umodti3
__umodti3:
	# specialized to u128 % u64, so verify that
	test %rcx,%rcx
	jne 1f

	# save divisor
	movq %rdx, %r8

	# reduce top 64 bits mod divisor
	movq %rsi, %rax
	xorl %edx, %edx
	divq %r8

	# reduce full 128-bit mod divisor

	// DX: ULONG64 EstablisherFrame
	// R8: PCONTEXT ContextRecord
	// R9: PDISPATCHER_CONTEXT DispatcherContext
	// Switch from the host ABI to the Go ABI.
	PUSH_REGS_HOST_TO_ABI0()

	get_tls(AX)
	CMPQ	AX, $0
	JNE	2(PC)
	// This shouldn't happen, sehtramp is only attached to functions
	// called from Go, and exception handlers are only called from
	// the thread that threw the exception.
	INT	$3