"VSRAW",
	"VSRAD",
	"VSOI",
	"VSLDOI",
	"VCLZ",
	"VCLZB",
	"VCLZH",
	"VCLZW",
	"VCLZD",
	"VPOPCNT",
	"VPOPCNTB",
	"VPOPCNTH",
	"VPOPCNTW",
	"VPOPCNTD",
	"VCMPEQ",
	"VCMPEQUB",
	"VCMPEQUBCC",
	"VCMPEQUH",
	"VCMPEQUHCC",
	"VCMPEQUW",
	"VCMPEQUWCC",
	"VCMPEQUD",
	"VCMPEQUDCC",
	"VCMPGT",
	"VCMPGTUB",
	"VCMPGTUBCC",
	"VCMPGTUH",
	"VCMPGTUHCC",

	"BEQ",
	"BFPF",
	"BFPT",
	"BGEZ",
	"BGEZAL",
	"BGTZ",
	"BLEZ",
	"BLTZ",
	"BLTZAL",
	"BNE",
	"BREAK",
	"CLO",
	"CLZ",
	"CMOVF",
	"CMOVN",
	"CMOVT",
	"CMOVZ",
	"CMPEQD",
	"CMPEQF",
	"CMPGED",
	"CMPGEF",
	"CMPGTD",
	"CMPGTF",
	"DIV",
	"DIVD",
	"DIVF",
	"DIVU",
	"DIVW",
	"GOK",
	"LL",
	"LLV",
	"LUI",
	"MADD",
	"MOVB",
	"MOVBU",
	"MOVD",

	"ABSF",
	"ADD",
	"ADDD",
	"ADDF",
	"ADDU",
	"ADDW",
	"AND",
	"BEQ",
	"BGEZ",
	"BLEZ",
	"BGTZ",
	"BLTZ",
	"BFPF",
	"BFPT",
	"BNE",
	"BREAK",
	"CLO",
	"CLZ",
	"CMPEQD",
	"CMPEQF",
	"CMPGED",
	"CMPGEF",
	"CMPGTD",
	"CMPGTF",
	"LU12IW",
	"LU32ID",
	"LU52ID",
	"PCALAU12I",
	"PCADDU12I",
	"JIRL",
	"BGE",
	"BLT",
	"BLTU",
	"BGEU",
	"DIV",
	"DIVD",

}

// IsLoong64CMP reports whether the op (as defined by an loong64.A* constant) is
// one of the CMP instructions that require special handling.
func IsLoong64CMP(op obj.As) bool {
	switch op {
	case loong64.ACMPEQF, loong64.ACMPEQD, loong64.ACMPGEF, loong64.ACMPGED,
		loong64.ACMPGTF, loong64.ACMPGTD:
		return true
	}
	return false
}

// IsLoong64MUL reports whether the op (as defined by an loong64.A* constant) is

	return false
}

// IsMIPSCMP reports whether the op (as defined by an mips.A* constant) is
// one of the CMP instructions that require special handling.
func IsMIPSCMP(op obj.As) bool {
	switch op {
	case mips.ACMPEQF, mips.ACMPEQD, mips.ACMPGEF, mips.ACMPGED,
		mips.ACMPGTF, mips.ACMPGTD:
		return true
	}
	return false
}

// IsMIPSMUL reports whether the op (as defined by an mips.A* constant) is

	JMP	bigloop
#endif
	MOVOU	(SI), X0
	MOVOU	(DI), X1
	MOVOU	16(SI), X2
	MOVOU	16(DI), X3
	MOVOU	32(SI), X4
	MOVOU	32(DI), X5
	MOVOU	48(SI), X6
	MOVOU	48(DI), X7
	PCMPEQB	X1, X0
	PCMPEQB	X3, X2
	PCMPEQB	X5, X4
	PCMPEQB	X7, X6
	PAND	X2, X0
	PAND	X6, X4
	PAND	X4, X0
	PMOVMSKB X0, DX
	ADDL	$64, SI
	ADDL	$64, DI
	SUBL	$64, BX
	CMPL	DX, $0xffff
	JEQ	hugeloop
	MOVB	$0, (AX)
	RET

	MOVOU	48(SI), X6
	MOVOU	48(DI), X7
	PCMPEQB	X1, X0
	PCMPEQB	X3, X2
	PCMPEQB	X5, X4
	PCMPEQB	X7, X6
	PAND	X2, X0
	PAND	X6, X4
	PAND	X4, X0
	PMOVMSKB X0, DX
	ADDQ	$64, SI
	ADDQ	$64, DI
	SUBQ	$64, BX
	CMPL	DX, $0xffff
	JEQ	hugeloop
	XORQ	AX, AX	// return 0
	RET
#endif

	// 64 bytes at a time using ymm registers
	PCALIGN $16
hugeloop_avx2:
	CMPQ	BX, $64
	JB	bigloop_avx2
	VMOVDQU	(SI), Y0

TEXT cmpbody<>(SB),NOSPLIT,$0-0
	CMPQ	SI, DI
	JEQ	allsame
	CMPQ	BX, DX
	MOVQ	DX, R8
	CMOVQLT	BX, R8 // R8 = min(alen, blen) = # of bytes to compare
	CMPQ	R8, $8
	JB	small

	CMPQ	R8, $63
	JBE	loop
#ifndef hasAVX2
	CMPB	internal∕cpu·X86+const_offsetX86HasAVX2(SB), $1
	JEQ     big_loop_avx2
	JMP	big_loop
#else
	JMP	big_loop_avx2
#endif
loop:
	CMPQ	R8, $16
	JBE	_0through16
	MOVOU	(SI), X0

	PUNPCKLBW X0, X0
	PUNPCKLBW X0, X0
	PSHUFL $0, X0, X0

	CMPQ BX, $16
	JLT small

	MOVQ SI, DI

	CMPQ BX, $32
	JA avx2
sse:
	LEAQ	-16(SI)(BX*1), AX	// AX = address of last 16 bytes
	JMP	sseloopentry

	PCALIGN $16
sseloop:
	// Move the next 16-byte chunk of the data into X1.
	MOVOU	(DI), X1
	// Compare bytes in X0 to X1.
	PCMPEQB	X0, X1
	// Take the top bit of each byte in X1 and put the result in DX.

	SLLV	R4, R5, R6		// a6901800
	ROTRV	R4, R5			// a5901b00
	ROTRV	R4, R5, R6		// a6901b00
	CLO	R4, R5			// 85100000
	CLZ	R4, R5			// 85140000
	ADDF	F4, F5			// a5900001
	ADDF	F4, R5, F6		// a6900001
	CMPEQF	F4, R5			// a010120c
	ABSF	F4, F5			// 85041401
	MOVVF	F4, F5			// 85181d01
	MOVF	F4, F5			// 85941401
	MOVD	F4, F5			// 85981401
	MOVW	R4, result+16(FP)	// 64608029
	MOVWU	R4, result+16(FP)	// 64608029