(Mod8          x y) => (I64RemS (SignExt8to64  x) (SignExt8to64  y))
(Mod64u ...) => (I64RemU ...)
(Mod32u x y) => (I64RemU (ZeroExt32to64 x) (ZeroExt32to64 y))
(Mod16u x y) => (I64RemU (ZeroExt16to64 x) (ZeroExt16to64 y))
(Mod8u  x y) => (I64RemU (ZeroExt8to64  x) (ZeroExt8to64  y))

(And(64|32|16|8|B) ...) => (I64And ...)

(Or(64|32|16|8|B) ...) => (I64Or ...)

(Xor(64|32|16|8) ...) => (I64Xor ...)

(Mod16 (Const16 [c]) (Const16 [d])) && d != 0 => (Const16 [c % d])
(Mod32 (Const32 [c]) (Const32 [d])) && d != 0 => (Const32 [c % d])
(Mod64 (Const64 [c]) (Const64 [d])) && d != 0 => (Const64 [c % d])

(Mod8u  (Const8 [c])  (Const8  [d])) && d != 0 => (Const8  [int8(uint8(c) % uint8(d))])
(Mod16u (Const16 [c]) (Const16 [d])) && d != 0 => (Const16 [int16(uint16(c) % uint16(d))])

(Mod32u x y) => (REMVU (ZeroExt32to64 x) (ZeroExt32to64 y))
(Mod16 x y) => (REMV (SignExt16to64 x) (SignExt16to64 y))
(Mod16u x y) => (REMVU (ZeroExt16to64 x) (ZeroExt16to64 y))
(Mod8 x y) => (REMV (SignExt8to64 x) (SignExt8to64 y))
(Mod8u x y) => (REMVU (ZeroExt8to64 x) (ZeroExt8to64 y))

(Select0 <t> (Add64carry x y c)) => (ADDV (ADDV <t> x y) c)
(Select1 <t> (Add64carry x y c)) =>
	(OR (SGTU <t> x s:(ADDV <t> x y)) (SGTU <t> s (ADDV <t> s c)))

(Mod32u ...) => (REMUW ...)
(Mod16 x y [false])  => (REMW  (SignExt16to32 x) (SignExt16to32 y))
(Mod16u x y) => (REMUW (ZeroExt16to32 x) (ZeroExt16to32 y))
(Mod8 x y)   => (REMW  (SignExt8to32  x) (SignExt8to32  y))
(Mod8u x y)  => (REMUW (ZeroExt8to32  x) (ZeroExt8to32  y))

(And(64|32|16|8) ...) => (AND ...)
(Or(64|32|16|8) ...) => (OR ...)
(Xor(64|32|16|8) ...) => (XOR ...)

(Neg(64|32|16|8) ...) => (NEG ...)

(Mod32u x y) => (Select0 (DIVU x y))
(Mod16 x y) => (Select0 (DIV (SignExt16to32 x) (SignExt16to32 y)))
(Mod16u x y) => (Select0 (DIVU (ZeroExt16to32 x) (ZeroExt16to32 y)))
(Mod8 x y) => (Select0 (DIV (SignExt8to32 x) (SignExt8to32 y)))
(Mod8u x y) => (Select0 (DIVU (ZeroExt8to32 x) (ZeroExt8to32 y)))

// math package intrinsics
(Abs ...) => (ABSD ...)

// (x + y) / 2 with x>=y  becomes  (x - y) / 2 + y

(Mod16 x y) => (Select0 (DIVV (SignExt16to64 x) (SignExt16to64 y)))
(Mod16u x y) => (Select0 (DIVVU (ZeroExt16to64 x) (ZeroExt16to64 y)))
(Mod8 x y) => (Select0 (DIVV (SignExt8to64 x) (SignExt8to64 y)))
(Mod8u x y) => (Select0 (DIVVU (ZeroExt8to64 x) (ZeroExt8to64 y)))

(Select0 <t> (Add64carry x y c)) => (ADDV (ADDV <t> x y) c)
(Select1 <t> (Add64carry x y c)) =>
	(OR (SGTU <t> x s:(ADDV <t> x y)) (SGTU <t> s (ADDV <t> s c)))

	// For Mod16, Mod32 and Mod64, AuxInt non-zero means that the divisor has been proved to be not -1.
	{name: "Mod8", argLength: 2},  // arg0 % arg1, signed
	{name: "Mod8u", argLength: 2}, // arg0 % arg1, unsigned
	{name: "Mod16", argLength: 2, aux: "Bool"},
	{name: "Mod16u", argLength: 2},
	{name: "Mod32", argLength: 2, aux: "Bool"},
	{name: "Mod32u", argLength: 2},

(Mod16 x y) => (Mod32 (SignExt16to32 x) (SignExt16to32 y))
(Mod16u x y) => (Mod32u (ZeroExt16to32 x) (ZeroExt16to32 y))
(Mod8 x y) => (Mod32 (SignExt8to32 x) (SignExt8to32 y))
(Mod8u x y) => (Mod32u (ZeroExt8to32 x) (ZeroExt8to32 y))
(Mod64 x y) && buildcfg.GOPPC64 >=9 => (MODSD x y)
(Mod64 x y) && buildcfg.GOPPC64 <=8 => (SUB x (MULLD y (DIVD x y)))
(Mod64u x y) && buildcfg.GOPPC64 >= 9 => (MODUD x y)

(Mod32  x y) => (MODW  (MOVWreg x) y)
(Mod32u x y) => (MODWU (MOVWZreg x) y)
(Mod16  x y) => (MODW  (MOVHreg x) (MOVHreg y))
(Mod16u x y) => (MODWU (MOVHZreg x) (MOVHZreg y))
(Mod8   x y) => (MODW  (MOVBreg x) (MOVBreg y))
(Mod8u  x y) => (MODWU (MOVBZreg x) (MOVBZreg y))

// (x + y) / 2 with x>=y -> (x - y) / 2 + y
(Avg64u <t> x y) => (ADD (SRDconst <t> (SUB <t> x y) [1]) y)

(And64 ...) => (AND ...)
(And(32|16|8) ...) => (ANDW ...)

(Avg64u ...) => (AVGQU ...)

(Mod(64|32|16) [a] x y) => (Select1 (DIV(Q|L|W) [a] x y))
(Mod8  x y) => (Select1 (DIVW  (SignExt8to16 x) (SignExt8to16 y)))
(Mod(64|32|16)u x y) => (Select1 (DIV(Q|L|W)U x y))
(Mod8u x y) => (Select1 (DIVWU (ZeroExt8to16 x) (ZeroExt8to16 y)))

(And(64|32|16|8) ...) => (AND(Q|L|L|L) ...)
(Or(64|32|16|8) ...) => (OR(Q|L|L|L) ...)
(Xor(64|32|16|8) ...) => (XOR(Q|L|L|L) ...)