mirror of
https://github.com/golang/go.git
synced 2025-05-06 08:03:03 +00:00
561bf0457f
The compiler is currently zero extending 32 bit unsigned integers to
64 bits before right shifting them using a 64 bit shift instruction.
There's no need to do this as RISC-V has instructions for right
shifting 32 bit unsigned values (srlw and srliw) which zero extend
the result of the shift to 64 bits. Change the compiler so that
it uses srlw and srliw for 32 bit unsigned shifts reducing in most
cases the number of instructions needed to perform the shift.
Here are some examples of code sequences that are changed by this
patch:
uint32(a) >> 2
before:
sll x5,x10,0x20
srl x10,x5,0x22
after:
srlw x10,x10,0x2
uint32(a) >> int(b)
before:
sll x5,x10,0x20
srl x5,x5,0x20
srl x5,x5,x11
sltiu x6,x11,64
neg x6,x6
and x10,x5,x6
after:
srlw x5,x10,x11
sltiu x6,x11,32
neg x6,x6
and x10,x5,x6
bits.RotateLeft32(uint32(a), 1)
before:
sll x5,x10,0x1
sll x6,x10,0x20
srl x7,x6,0x3f
or x5,x5,x7
after:
sll x5,x10,0x1
srlw x6,x10,0x1f
or x10,x5,x6
bits.RotateLeft32(uint32(a), int(b))
before:
and x6,x11,31
sll x7,x10,x6
sll x8,x10,0x20
srl x8,x8,0x20
add x6,x6,-32
neg x6,x6
srl x9,x8,x6
sltiu x6,x6,64
neg x6,x6
and x6,x9,x6
or x6,x6,x7
after:
and x5,x11,31
sll x6,x10,x5
add x5,x5,-32
neg x5,x5
srlw x7,x10,x5
sltiu x5,x5,32
neg x5,x5
and x5,x7,x5
or x10,x6,x5
The one regression observed is the following case, an unbounded right
shift of a uint32 where the value we're shifting by is known to be
< 64 but > 31. As this is an unusual case this commit does not
optimize for it, although the existing code does.
uint32(a) >> (b & 63)
before:
sll x5,x10,0x20
srl x5,x5,0x20
and x6,x11,63
srl x10,x5,x6
after
and x5,x11,63
srlw x6,x10,x5
sltiu x5,x5,32
neg x5,x5
and x10,x6,x5
Here we have one extra instruction.
Some benchmark highlights, generated on a VisionFive2 8GB running
Ubuntu 23.04.
pkg: math/bits
LeadingZeros32-4 18.64n ± 0% 17.32n ± 0% -7.11% (p=0.000 n=10)
LeadingZeros64-4 15.47n ± 0% 15.51n ± 0% +0.26% (p=0.027 n=10)
TrailingZeros16-4 18.48n ± 0% 17.68n ± 0% -4.33% (p=0.000 n=10)
TrailingZeros32-4 16.87n ± 0% 16.07n ± 0% -4.74% (p=0.000 n=10)
TrailingZeros64-4 15.26n ± 0% 15.27n ± 0% +0.07% (p=0.043 n=10)
OnesCount32-4 20.08n ± 0% 19.29n ± 0% -3.96% (p=0.000 n=10)
RotateLeft-4 8.864n ± 0% 8.838n ± 0% -0.30% (p=0.006 n=10)
RotateLeft32-4 8.837n ± 0% 8.032n ± 0% -9.11% (p=0.000 n=10)
Reverse32-4 29.77n ± 0% 26.52n ± 0% -10.93% (p=0.000 n=10)
ReverseBytes32-4 9.640n ± 0% 8.838n ± 0% -8.32% (p=0.000 n=10)
Sub32-4 8.835n ± 0% 8.035n ± 0% -9.06% (p=0.000 n=10)
geomean 11.50n 11.33n -1.45%
pkg: crypto/md5
Hash8Bytes-4 1.486µ ± 0% 1.426µ ± 0% -4.04% (p=0.000 n=10)
Hash64-4 2.079µ ± 0% 1.968µ ± 0% -5.36% (p=0.000 n=10)
Hash128-4 2.720µ ± 0% 2.557µ ± 0% -5.99% (p=0.000 n=10)
Hash256-4 3.996µ ± 0% 3.733µ ± 0% -6.58% (p=0.000 n=10)
Hash512-4 6.541µ ± 0% 6.072µ ± 0% -7.18% (p=0.000 n=10)
Hash1K-4 11.64µ ± 0% 10.75µ ± 0% -7.58% (p=0.000 n=10)
Hash8K-4 82.95µ ± 0% 76.32µ ± 0% -7.99% (p=0.000 n=10)
Hash1M-4 10.436m ± 0% 9.591m ± 0% -8.10% (p=0.000 n=10)
Hash8M-4 83.50m ± 0% 76.73m ± 0% -8.10% (p=0.000 n=10)
Hash8BytesUnaligned-4 1.494µ ± 0% 1.434µ ± 0% -4.02% (p=0.000 n=10)
Hash1KUnaligned-4 11.64µ ± 0% 10.76µ ± 0% -7.52% (p=0.000 n=10)
Hash8KUnaligned-4 83.01µ ± 0% 76.32µ ± 0% -8.07% (p=0.000 n=10)
geomean 28.32µ 26.42µ -6.72%
Change-Id: I20483a6668cca1b53fe83944bee3706aadcf8693
Reviewed-on: https://go-review.googlesource.com/c/go/+/528975
Reviewed-by: Michael Pratt <mpratt@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Reviewed-by: Joel Sing <joel@sing.id.au>
Run-TryBot: Joel Sing <joel@sing.id.au>
TryBot-Result: Gopher Robot <gobot@golang.org>
442 lines
10 KiB
Go
442 lines
10 KiB
Go
// asmcheck
|
|
|
|
// Copyright 2018 The Go Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style
|
|
// license that can be found in the LICENSE file.
|
|
|
|
package codegen
|
|
|
|
// ------------------ //
|
|
// constant shifts //
|
|
// ------------------ //
|
|
|
|
func lshConst64x64(v int64) int64 {
|
|
// ppc64x:"SLD"
|
|
// riscv64:"SLLI",-"AND",-"SLTIU"
|
|
return v << uint64(33)
|
|
}
|
|
|
|
func rshConst64Ux64(v uint64) uint64 {
|
|
// ppc64x:"SRD"
|
|
// riscv64:"SRLI\t",-"AND",-"SLTIU"
|
|
return v >> uint64(33)
|
|
}
|
|
|
|
func rshConst64x64(v int64) int64 {
|
|
// ppc64x:"SRAD"
|
|
// riscv64:"SRAI",-"OR",-"SLTIU"
|
|
return v >> uint64(33)
|
|
}
|
|
|
|
func lshConst32x64(v int32) int32 {
|
|
// ppc64x:"SLW"
|
|
// riscv64:"SLLI",-"AND",-"SLTIU", -"MOVW"
|
|
return v << uint64(29)
|
|
}
|
|
|
|
func rshConst32Ux64(v uint32) uint32 {
|
|
// ppc64x:"SRW"
|
|
// riscv64:"SRLIW",-"AND",-"SLTIU", -"MOVW"
|
|
return v >> uint64(29)
|
|
}
|
|
|
|
func rshConst32x64(v int32) int32 {
|
|
// ppc64x:"SRAW"
|
|
// riscv64:"SRAI",-"OR",-"SLTIU", -"MOVW"
|
|
return v >> uint64(29)
|
|
}
|
|
|
|
func lshConst64x32(v int64) int64 {
|
|
// ppc64x:"SLD"
|
|
// riscv64:"SLLI",-"AND",-"SLTIU"
|
|
return v << uint32(33)
|
|
}
|
|
|
|
func rshConst64Ux32(v uint64) uint64 {
|
|
// ppc64x:"SRD"
|
|
// riscv64:"SRLI\t",-"AND",-"SLTIU"
|
|
return v >> uint32(33)
|
|
}
|
|
|
|
func rshConst64x32(v int64) int64 {
|
|
// ppc64x:"SRAD"
|
|
// riscv64:"SRAI",-"OR",-"SLTIU"
|
|
return v >> uint32(33)
|
|
}
|
|
|
|
// ------------------ //
|
|
// masked shifts //
|
|
// ------------------ //
|
|
|
|
func lshMask64x64(v int64, s uint64) int64 {
|
|
// arm64:"LSL",-"AND"
|
|
// ppc64x:"ANDCC",-"ORN",-"ISEL"
|
|
// riscv64:"SLL",-"AND\t",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v << (s & 63)
|
|
}
|
|
|
|
func rshMask64Ux64(v uint64, s uint64) uint64 {
|
|
// arm64:"LSR",-"AND",-"CSEL"
|
|
// ppc64x:"ANDCC",-"ORN",-"ISEL"
|
|
// riscv64:"SRL\t",-"AND\t",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> (s & 63)
|
|
}
|
|
|
|
func rshMask64x64(v int64, s uint64) int64 {
|
|
// arm64:"ASR",-"AND",-"CSEL"
|
|
// ppc64x:"ANDCC",-"ORN",-"ISEL"
|
|
// riscv64:"SRA",-"OR",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> (s & 63)
|
|
}
|
|
|
|
func lshMask32x64(v int32, s uint64) int32 {
|
|
// arm64:"LSL",-"AND"
|
|
// ppc64x:"ISEL",-"ORN"
|
|
// riscv64:"SLL",-"AND\t",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v << (s & 63)
|
|
}
|
|
|
|
func rshMask32Ux64(v uint32, s uint64) uint32 {
|
|
// arm64:"LSR",-"AND"
|
|
// ppc64x:"ISEL",-"ORN"
|
|
// riscv64:"SRLW","SLTIU","NEG","AND\t",-"SRL\t"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> (s & 63)
|
|
}
|
|
|
|
func rsh5Mask32Ux64(v uint32, s uint64) uint32 {
|
|
// riscv64:"SRLW",-"AND\t",-"SLTIU",-"SRL\t"
|
|
return v >> (s & 31)
|
|
}
|
|
|
|
func rshMask32x64(v int32, s uint64) int32 {
|
|
// arm64:"ASR",-"AND"
|
|
// ppc64x:"ISEL",-"ORN"
|
|
// riscv64:"SRA",-"OR",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> (s & 63)
|
|
}
|
|
|
|
func lshMask64x32(v int64, s uint32) int64 {
|
|
// arm64:"LSL",-"AND"
|
|
// ppc64x:"ANDCC",-"ORN"
|
|
// riscv64:"SLL",-"AND\t",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v << (s & 63)
|
|
}
|
|
|
|
func rshMask64Ux32(v uint64, s uint32) uint64 {
|
|
// arm64:"LSR",-"AND",-"CSEL"
|
|
// ppc64x:"ANDCC",-"ORN"
|
|
// riscv64:"SRL\t",-"AND\t",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> (s & 63)
|
|
}
|
|
|
|
func rshMask64x32(v int64, s uint32) int64 {
|
|
// arm64:"ASR",-"AND",-"CSEL"
|
|
// ppc64x:"ANDCC",-"ORN",-"ISEL"
|
|
// riscv64:"SRA",-"OR",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> (s & 63)
|
|
}
|
|
|
|
func lshMask64x32Ext(v int64, s int32) int64 {
|
|
// ppc64x:"ANDCC",-"ORN",-"ISEL"
|
|
// riscv64:"SLL",-"AND\t",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v << uint(s&63)
|
|
}
|
|
|
|
func rshMask64Ux32Ext(v uint64, s int32) uint64 {
|
|
// ppc64x:"ANDCC",-"ORN",-"ISEL"
|
|
// riscv64:"SRL\t",-"AND\t",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> uint(s&63)
|
|
}
|
|
|
|
func rshMask64x32Ext(v int64, s int32) int64 {
|
|
// ppc64x:"ANDCC",-"ORN",-"ISEL"
|
|
// riscv64:"SRA",-"OR",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
return v >> uint(s&63)
|
|
}
|
|
|
|
// --------------- //
|
|
// signed shifts //
|
|
// --------------- //
|
|
|
|
// We do want to generate a test + panicshift for these cases.
|
|
func lshSigned(v8 int8, v16 int16, v32 int32, v64 int64, x int) {
|
|
// amd64:"TESTB"
|
|
_ = x << v8
|
|
// amd64:"TESTW"
|
|
_ = x << v16
|
|
// amd64:"TESTL"
|
|
_ = x << v32
|
|
// amd64:"TESTQ"
|
|
_ = x << v64
|
|
}
|
|
|
|
// We want to avoid generating a test + panicshift for these cases.
|
|
func lshSignedMasked(v8 int8, v16 int16, v32 int32, v64 int64, x int) {
|
|
// amd64:-"TESTB"
|
|
_ = x << (v8 & 7)
|
|
// amd64:-"TESTW"
|
|
_ = x << (v16 & 15)
|
|
// amd64:-"TESTL"
|
|
_ = x << (v32 & 31)
|
|
// amd64:-"TESTQ"
|
|
_ = x << (v64 & 63)
|
|
}
|
|
|
|
// ------------------ //
|
|
// bounded shifts //
|
|
// ------------------ //
|
|
|
|
func lshGuarded64(v int64, s uint) int64 {
|
|
if s < 64 {
|
|
// riscv64:"SLL",-"AND",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
// wasm:-"Select",-".*LtU"
|
|
// arm64:"LSL",-"CSEL"
|
|
return v << s
|
|
}
|
|
panic("shift too large")
|
|
}
|
|
|
|
func rshGuarded64U(v uint64, s uint) uint64 {
|
|
if s < 64 {
|
|
// riscv64:"SRL\t",-"AND",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
// wasm:-"Select",-".*LtU"
|
|
// arm64:"LSR",-"CSEL"
|
|
return v >> s
|
|
}
|
|
panic("shift too large")
|
|
}
|
|
|
|
func rshGuarded64(v int64, s uint) int64 {
|
|
if s < 64 {
|
|
// riscv64:"SRA",-"OR",-"SLTIU"
|
|
// s390x:-"RISBGZ",-"AND",-"LOCGR"
|
|
// wasm:-"Select",-".*LtU"
|
|
// arm64:"ASR",-"CSEL"
|
|
return v >> s
|
|
}
|
|
panic("shift too large")
|
|
}
|
|
|
|
func provedUnsignedShiftLeft(val64 uint64, val32 uint32, val16 uint16, val8 uint8, shift int) (r1 uint64, r2 uint32, r3 uint16, r4 uint8) {
|
|
if shift >= 0 && shift < 64 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r1 = val64 << shift
|
|
}
|
|
if shift >= 0 && shift < 32 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r2 = val32 << shift
|
|
}
|
|
if shift >= 0 && shift < 16 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r3 = val16 << shift
|
|
}
|
|
if shift >= 0 && shift < 8 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r4 = val8 << shift
|
|
}
|
|
return r1, r2, r3, r4
|
|
}
|
|
|
|
func provedSignedShiftLeft(val64 int64, val32 int32, val16 int16, val8 int8, shift int) (r1 int64, r2 int32, r3 int16, r4 int8) {
|
|
if shift >= 0 && shift < 64 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r1 = val64 << shift
|
|
}
|
|
if shift >= 0 && shift < 32 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r2 = val32 << shift
|
|
}
|
|
if shift >= 0 && shift < 16 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r3 = val16 << shift
|
|
}
|
|
if shift >= 0 && shift < 8 {
|
|
// arm64:"LSL",-"CSEL"
|
|
r4 = val8 << shift
|
|
}
|
|
return r1, r2, r3, r4
|
|
}
|
|
|
|
func provedUnsignedShiftRight(val64 uint64, val32 uint32, val16 uint16, val8 uint8, shift int) (r1 uint64, r2 uint32, r3 uint16, r4 uint8) {
|
|
if shift >= 0 && shift < 64 {
|
|
// arm64:"LSR",-"CSEL"
|
|
r1 = val64 >> shift
|
|
}
|
|
if shift >= 0 && shift < 32 {
|
|
// arm64:"LSR",-"CSEL"
|
|
r2 = val32 >> shift
|
|
}
|
|
if shift >= 0 && shift < 16 {
|
|
// arm64:"LSR",-"CSEL"
|
|
r3 = val16 >> shift
|
|
}
|
|
if shift >= 0 && shift < 8 {
|
|
// arm64:"LSR",-"CSEL"
|
|
r4 = val8 >> shift
|
|
}
|
|
return r1, r2, r3, r4
|
|
}
|
|
|
|
func provedSignedShiftRight(val64 int64, val32 int32, val16 int16, val8 int8, shift int) (r1 int64, r2 int32, r3 int16, r4 int8) {
|
|
if shift >= 0 && shift < 64 {
|
|
// arm64:"ASR",-"CSEL"
|
|
r1 = val64 >> shift
|
|
}
|
|
if shift >= 0 && shift < 32 {
|
|
// arm64:"ASR",-"CSEL"
|
|
r2 = val32 >> shift
|
|
}
|
|
if shift >= 0 && shift < 16 {
|
|
// arm64:"ASR",-"CSEL"
|
|
r3 = val16 >> shift
|
|
}
|
|
if shift >= 0 && shift < 8 {
|
|
// arm64:"ASR",-"CSEL"
|
|
r4 = val8 >> shift
|
|
}
|
|
return r1, r2, r3, r4
|
|
}
|
|
|
|
func checkUnneededTrunc(tab *[100000]uint32, d uint64, v uint32, h uint16, b byte) (uint32, uint64) {
|
|
|
|
// ppc64x:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
|
|
f := tab[byte(v)^b]
|
|
// ppc64x:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
|
|
f += tab[byte(v)&b]
|
|
// ppc64x:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
|
|
f += tab[byte(v)|b]
|
|
// ppc64x:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
|
|
f += tab[uint16(v)&h]
|
|
// ppc64x:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
|
|
f += tab[uint16(v)^h]
|
|
// ppc64x:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
|
|
f += tab[uint16(v)|h]
|
|
// ppc64x:-".*AND",-"RLDICR",".*CLRLSLDI"
|
|
f += tab[v&0xff]
|
|
// ppc64x:-".*AND",".*CLRLSLWI"
|
|
f += 2 * uint32(uint16(d))
|
|
// ppc64x:-".*AND",-"RLDICR",".*CLRLSLDI"
|
|
g := 2 * uint64(uint32(d))
|
|
return f, g
|
|
}
|
|
|
|
func checkCombinedShifts(v8 uint8, v16 uint16, v32 uint32, x32 int32, v64 uint64) (uint8, uint16, uint32, uint64, int64) {
|
|
|
|
// ppc64x:-"AND","CLRLSLWI"
|
|
f := (v8 & 0xF) << 2
|
|
// ppc64x:"CLRLSLWI"
|
|
f += byte(v16) << 3
|
|
// ppc64x:-"AND","CLRLSLWI"
|
|
g := (v16 & 0xFF) << 3
|
|
// ppc64x:-"AND","CLRLSLWI"
|
|
h := (v32 & 0xFFFFF) << 2
|
|
// ppc64x:"CLRLSLDI"
|
|
i := (v64 & 0xFFFFFFFF) << 5
|
|
// ppc64x:-"CLRLSLDI"
|
|
i += (v64 & 0xFFFFFFF) << 38
|
|
// ppc64x/power9:-"CLRLSLDI"
|
|
i += (v64 & 0xFFFF00) << 10
|
|
// ppc64x/power9:-"SLD","EXTSWSLI"
|
|
j := int64(x32+32) * 8
|
|
return f, g, h, i, j
|
|
}
|
|
|
|
func checkWidenAfterShift(v int64, u uint64) (int64, uint64) {
|
|
|
|
// ppc64x:-".*MOVW"
|
|
f := int32(v >> 32)
|
|
// ppc64x:".*MOVW"
|
|
f += int32(v >> 31)
|
|
// ppc64x:-".*MOVH"
|
|
g := int16(v >> 48)
|
|
// ppc64x:".*MOVH"
|
|
g += int16(v >> 30)
|
|
// ppc64x:-".*MOVH"
|
|
g += int16(f >> 16)
|
|
// ppc64x:-".*MOVB"
|
|
h := int8(v >> 56)
|
|
// ppc64x:".*MOVB"
|
|
h += int8(v >> 28)
|
|
// ppc64x:-".*MOVB"
|
|
h += int8(f >> 24)
|
|
// ppc64x:".*MOVB"
|
|
h += int8(f >> 16)
|
|
return int64(h), uint64(g)
|
|
}
|
|
|
|
func checkShiftAndMask32(v []uint32) {
|
|
i := 0
|
|
|
|
// ppc64x: "RLWNM\t[$]24, R[0-9]+, [$]12, [$]19, R[0-9]+"
|
|
v[i] = (v[i] & 0xFF00000) >> 8
|
|
i++
|
|
// ppc64x: "RLWNM\t[$]26, R[0-9]+, [$]22, [$]29, R[0-9]+"
|
|
v[i] = (v[i] & 0xFF00) >> 6
|
|
i++
|
|
// ppc64x: "MOVW\tR0"
|
|
v[i] = (v[i] & 0xFF) >> 8
|
|
i++
|
|
// ppc64x: "MOVW\tR0"
|
|
v[i] = (v[i] & 0xF000000) >> 28
|
|
i++
|
|
// ppc64x: "RLWNM\t[$]26, R[0-9]+, [$]24, [$]31, R[0-9]+"
|
|
v[i] = (v[i] >> 6) & 0xFF
|
|
i++
|
|
// ppc64x: "RLWNM\t[$]26, R[0-9]+, [$]12, [$]19, R[0-9]+"
|
|
v[i] = (v[i] >> 6) & 0xFF000
|
|
i++
|
|
// ppc64x: "MOVW\tR0"
|
|
v[i] = (v[i] >> 20) & 0xFF000
|
|
i++
|
|
// ppc64x: "MOVW\tR0"
|
|
v[i] = (v[i] >> 24) & 0xFF00
|
|
i++
|
|
}
|
|
|
|
func checkMergedShifts32(a [256]uint32, b [256]uint64, u uint32, v uint32) {
|
|
// ppc64x: -"CLRLSLDI", "RLWNM\t[$]10, R[0-9]+, [$]22, [$]29, R[0-9]+"
|
|
a[0] = a[uint8(v>>24)]
|
|
// ppc64x: -"CLRLSLDI", "RLWNM\t[$]11, R[0-9]+, [$]21, [$]28, R[0-9]+"
|
|
b[0] = b[uint8(v>>24)]
|
|
// ppc64x: -"CLRLSLDI", "RLWNM\t[$]15, R[0-9]+, [$]21, [$]28, R[0-9]+"
|
|
b[1] = b[(v>>20)&0xFF]
|
|
// ppc64x: -"SLD", "RLWNM\t[$]10, R[0-9]+, [$]22, [$]28, R[0-9]+"
|
|
b[2] = b[v>>25]
|
|
}
|
|
|
|
// 128 bit shifts
|
|
|
|
func check128bitShifts(x, y uint64, bits uint) (uint64, uint64) {
|
|
s := bits & 63
|
|
ŝ := (64 - bits) & 63
|
|
// check that the shift operation has two commas (three operands)
|
|
// amd64:"SHRQ.*,.*,"
|
|
shr := x>>s | y<<ŝ
|
|
// amd64:"SHLQ.*,.*,"
|
|
shl := x<<s | y>>ŝ
|
|
return shr, shl
|
|
}
|
|
|
|
func checkShiftToMask(u []uint64, s []int64) {
|
|
// amd64:-"SHR",-"SHL","ANDQ"
|
|
u[0] = u[0] >> 5 << 5
|
|
// amd64:-"SAR",-"SHL","ANDQ"
|
|
s[0] = s[0] >> 5 << 5
|
|
// amd64:-"SHR",-"SHL","ANDQ"
|
|
u[1] = u[1] << 5 >> 5
|
|
}
|