// ROL16 rotates the uint32s in register R left by 16, using temporary T if needed.
#ifdef GOAMD64_v2
#define ROL16(R, T) PSHUFB ·rol16<>(SB), R
#else
#define ROL16(R, T) ROL(16, R, T)
#endif

// ROL8 rotates the uint32s in register R left by 8, using temporary T if needed.
#ifdef GOAMD64_v2
#define ROL8(R, T) PSHUFB ·rol8<>(SB), R
#else
#define ROL8(R, T) ROL(8, R, T)
#endif

	MOVL AX, retA+96(FP)
	MOVL CX, retB+100(FP)
	MOVL DX, retC+104(FP)
	RET

// CRC32 polynomial data
//
// These constants are lifted from the
// Linux kernel, since they avoid the costly
// PSHUFB 16 byte reversal proposed in the
// original Intel paper.
DATA r2r1<>+0(SB)/8, $0x154442bd4
DATA r2r1<>+8(SB)/8, $0x1c6e41596
DATA r4r3<>+0(SB)/8, $0x1751997d0
DATA r4r3<>+8(SB)/8, $0x0ccaa009e