// The three-operand SHL/SHR forms, which go tool asm encodes as SHLD/SHRD:
// immediate and CL (or its CX spelling) counts at the Q and W widths, next
// to the two-operand CX-count spelling GOROOT's bignum kernels use.  Every
// result is folded back so no instruction is dead.

#include "textflag.h"

// func dblshift(x, y uint64) uint64
TEXT ·dblshift(SB), NOSPLIT, $0-24
	MOVQ x+0(FP), SI
	MOVQ y+8(FP), DI
	MOVQ $12, CX
	SHLQ $13, SI, DI
	SHRQ $7, DI, SI
	SHLQ CX, SI, DI
	SHRQ CX, DI, SI
	SHLQ CX, SI
	SHLQ $9, DI
	SHLW $1, SI, DI
	SHRW $3, DI, SI
	XORQ DI, SI
	MOVQ SI, ret+16(FP)
	RET

// func dblshift32(a, b uint32) uint32
TEXT ·dblshift32(SB), NOSPLIT, $0-12
	MOVL a+0(FP), SI
	MOVL b+4(FP), DI
	SHLL $5, SI, DI
	SHRL $2, DI, SI
	XORL SI, DI
	MOVL DI, ret+8(FP)
	RET