(Ctz32 <t> x) => (SUB (MOVDconst [64]) (FLOGR (MOVWZreg (ANDW <t> (SUBWconst <t> [1] x) (NOTW <t> x)))))

(BitLen64 x) => (SUB (MOVDconst [64]) (FLOGR x))

// POPCNT treats the input register as a vector of 8 bytes, producing
// a population count for each individual byte. For inputs larger than
// a single byte we therefore need to sum the individual bytes produced
// by the POPCNT instruction. For example, the following instruction

	//     register, F = float register), in uppercase
	//  3. the word "Encoding"
	//
	// For example, rIIIEncoding indicates an R-type instruction with two
	// integer register inputs and an integer register output; sFEncoding
	// indicates an S-type instruction with rs2 being a float register.

	rIIIEncoding  = encoding{encode: encodeRIII, validate: validateRIII, length: 4}