ARLDCL
	ARLDCLCC
	ARLDICL
	ARLDICLCC
	ARLDIC
	ARLDICCC
	ACLRLSLDI
	AROTL
	AROTLW
	ASLBIA
	ASLBIE
	ASLBMFEE
	ASLBMFEV
	ASLBMTE
	ASLD
	ASLDCC
	ASRD
	ASRAD
	ASRADCC
	ASRDCC
	AEXTSWSLI
	AEXTSWSLICC
	ASTDCCC
	ATD
	ASETB

	/* 64-bit pseudo operation */
	ADWORD
	AREMD
	AREMDU

	/* more 64-bit operations */
	AHRFID
	APOPCNTD

	// arm64:"TST\t[$]63",-"UDIV",-"ASR",-"AND"
	// ppc64x:"ANDCC",-"RLDICL",-"SRAD",-"CMP"
	a := n1%64 == 0 // signed divisible

	// 386:"TESTL\t[$]63",-"DIVL",-"SHRL"
	// amd64:"TESTQ\t[$]63",-"DIVQ",-"SHRQ"
	// arm:"AND\t[$]63",-".*udiv",-"SRA"
	// arm64:"TST\t[$]63",-"UDIV",-"ASR",-"AND"
	// ppc64x:"ANDCC",-"RLDICL",-"SRAD",-"CMP"
	b := n2%64 != 0 // signed indivisible

	return a, b
}

	return uint64(v) >> 16
}

func rshConst64Ux64Overflow8(v uint8) uint64 {
	// riscv64:"MOV\t\\$0,",-"SRL"
	return uint64(v) >> 8
}

func rshConst64x64(v int64) int64 {
	// ppc64x:"SRAD"
	// riscv64:"SRAI\t",-"OR",-"SLTIU"
	return v >> uint64(33)
}

func rshConst64x64Overflow32(v int32) int64 {
	// riscv64:"SRAIW",-"SLLI",-"SRAI\t"
	return int64(v) >> 32
}

		{name: "FMSUB", argLength: 3, reg: fp31, asm: "FMSUB"},   // arg0*arg1 - arg2
		{name: "FMSUBS", argLength: 3, reg: fp31, asm: "FMSUBS"}, // arg0*arg1 - arg2

		{name: "SRAD", argLength: 2, reg: gp21cxer, asm: "SRAD"}, // signed arg0 >> (arg1&127), 64 bit width (note: 127, not 63!)
		{name: "SRAW", argLength: 2, reg: gp21cxer, asm: "SRAW"}, // signed arg0 >> (arg1&63), 32 bit width

	CMP     $0,R6           // len == 0?
	BNE     start
	MOVW    R3,ret+40(FP)   // return crc
	RET

start:
	NOR     R3,R3,R7        // ^crc
	MOVWZ	R7,R7		// 32 bits
	CMP	R6,$16
	MOVD	R6,CTR
	BLT	short
	SRAD    $3,R6,R8        // 8 byte chunks
	MOVD    R8,CTR

loop:
	MOVWZ	0(R5),R8	// 0-3 bytes of p ?Endian?
	MOVWZ	4(R5),R9	// 4-7 bytes of p
	MOVD	R4,R10		// &tab[0]
	XOR	R7,R8,R7	// crc ^= byte[0:3]

	ADD     $-2, R4, R16
	PCALIGN $16
loopback:
	ADD     $-1, R8, R10
	SLD     $3, R10
	LXVD2X  (R6)(R10), VS32 // load x[i-1], x[i]
	SLD     $3, R8, R12
	LXVD2X  (R6)(R12), VS33 // load x[i], x[i+1]

	VSRD    V0, V4, V3      // x[i-1]>>s, x[i]>>s
	VSLD    V1, V2, V5      // x[i]<<ŝ, x[i+1]<<ŝ
	VOR     V3, V5, V5      // Or(|) the two registers together
	STXVD2X VS37, (R3)(R10) // store into z[i-1] and z[i]

	VADDUBM  XC2, XC2, XC2       // 0xc2...
	VSPLTISB $7, T2
	VOR      XC2, T1, XC2        // 0xc2....01
	VSPLTB   $0, H, T1           // most significant byte
	VSL      H, T0, H            // H<<=1
	VSRAB    T1, T2, T1          // broadcast carry bit
	VAND     T1, XC2, T1
	VXOR     H, T1, IN           // twisted H

	VSLDOI $8, IN, IN, H      // twist even more ...
	VSLDOI $8, ZERO, XC2, XC2 // 0xc2.0