// find out information about the processor we're on
	MOVL	$0, AX
	CPUID
	CMPL	AX, $0
	JE	nocpuinfo

	CMPL	BX, $0x756E6547  // "Genu"
	JNE	notintel
	CMPL	DX, $0x49656E69  // "ineI"
	JNE	notintel
	CMPL	CX, $0x6C65746E  // "ntel"
	JNE	notintel
	MOVB	$1, runtime·isIntel(SB)

notintel:
	// Load EAX=1 cpuid flags
	MOVL	$1, AX
	CPUID
	MOVL	AX, runtime·processorVersionInfo(SB)

has_cpuid:
	MOVL	$0, AX
	CPUID
	MOVL	AX, SI
	CMPL	AX, $0
	JE	nocpuinfo

	CMPL	BX, $0x756E6547  // "Genu"
	JNE	notintel
	CMPL	DX, $0x49656E69  // "ineI"
	JNE	notintel
	CMPL	CX, $0x6C65746E  // "ntel"
	JNE	notintel
	MOVB	$1, runtime·isIntel(SB)
notintel:

	// Load EAX=1 cpuid flags
	MOVL	$1, AX
	CPUID
	MOVL	CX, DI // Move to global variable clobbers CX when generating PIC

	MOVQ    BX, 24(SP)
	MOVQ    BP, 32(SP)
	MOVQ	R12, 40(SP)
	MOVQ	R13, 48(SP)
	MOVQ	R14, 56(SP)
	MOVQ	R15, 64(SP)

	get_tls(BX)
	// check that g exists
	MOVQ	g(BX), R10
	CMPQ	R10, $0
	JNE	allgood
	MOVQ	SI, 72(SP)
	MOVQ	DX, 80(SP)
	LEAQ	72(SP), AX
	MOVQ	DI, 0(SP)
	MOVQ	AX, 8(SP)
	MOVQ	$runtime·badsignal(SB), AX
	CALL	AX
	JMP	exit

allgood:

	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

TEXT polyHashADInternal<>(SB), NOSPLIT, $0
	// adp points to beginning of additional data
	// itr2 holds ad length
	XORQ acc0, acc0
	XORQ acc1, acc1
	XORQ acc2, acc2
	CMPQ itr2, $13
	JNE  hashADLoop

openFastTLSAD:
	// Special treatment for the TLS case of 13 bytes
	MOVQ (adp), acc0
	MOVQ 5(adp), acc1
	SHRQ $24, acc1
	MOVQ $1, acc2
	polyMul
	RET

hashADLoop:

		p.To.Type = obj.TYPE_REG
		p.To.Reg = regEntryTmp0
		if ctxt.Arch.Family == sys.I386 {
			p.As = ATESTL
		}

		// JNE checkargp (checkargp to be resolved later)
		jne := obj.Appendp(p, newprog)
		jne.As = AJNE
		jne.To.Type = obj.TYPE_BRANCH

		// end:
		//  NOP
		end := obj.Appendp(jne, newprog)
		end.As = obj.ANOP

		// Fast forward to end of function.
		var last *obj.Prog

	// 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

TEXT runtime·settls(SB),NOSPLIT,$0
	RET

// void sigtramp(void *ureg, int8 *note)
TEXT runtime·sigtramp(SB),NOSPLIT|NOFRAME,$0
	get_tls(AX)

	// check that g exists
	MOVQ	g(AX), BX
	CMPQ	BX, $0
	JNE	3(PC)
	CALL	runtime·badsignal2(SB) // will exit
	RET

	// save args
	MOVQ	ureg+0(FP), CX
	MOVQ	note+8(FP), DX

	// change stack
	MOVQ	g_m(BX), BX
	MOVQ	m_gsignal(BX), R10

	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