mirror of
https://github.com/golang/go
synced 2024-11-23 09:30:03 -07:00
a19a83c8ef
Use float <-> int register moves without conversion instead of stores and loads to move float <-> int values. Math package benchmark results. name old time/op new time/op delta Acosh 153ns ± 0% 147ns ± 0% -3.92% (p=0.000 n=10+10) Asinh 183ns ± 0% 177ns ± 0% -3.28% (p=0.000 n=10+10) Atanh 157ns ± 0% 155ns ± 0% -1.27% (p=0.000 n=10+10) Atan2 118ns ± 0% 117ns ± 1% -0.59% (p=0.003 n=10+10) Cbrt 119ns ± 0% 114ns ± 0% -4.20% (p=0.000 n=10+10) Copysign 7.51ns ± 0% 6.51ns ± 0% -13.32% (p=0.000 n=9+10) Cos 73.1ns ± 0% 70.6ns ± 0% -3.42% (p=0.000 n=10+10) Cosh 119ns ± 0% 121ns ± 0% +1.68% (p=0.000 n=10+9) ExpGo 154ns ± 0% 149ns ± 0% -3.05% (p=0.000 n=9+10) Expm1 101ns ± 0% 99ns ± 0% -1.88% (p=0.000 n=10+10) Exp2Go 150ns ± 0% 146ns ± 0% -2.67% (p=0.000 n=10+10) Abs 7.01ns ± 0% 6.01ns ± 0% -14.27% (p=0.000 n=10+9) Mod 234ns ± 0% 212ns ± 0% -9.40% (p=0.000 n=9+10) Frexp 34.5ns ± 0% 30.0ns ± 0% -13.04% (p=0.000 n=10+10) Gamma 112ns ± 0% 111ns ± 0% -0.89% (p=0.000 n=10+10) Hypot 73.6ns ± 0% 68.6ns ± 0% -6.79% (p=0.000 n=10+10) HypotGo 77.1ns ± 0% 72.1ns ± 0% -6.49% (p=0.000 n=10+10) Ilogb 31.0ns ± 0% 28.0ns ± 0% -9.68% (p=0.000 n=10+10) J0 437ns ± 0% 434ns ± 0% -0.62% (p=0.000 n=10+10) J1 433ns ± 0% 431ns ± 0% -0.46% (p=0.000 n=10+10) Jn 927ns ± 0% 922ns ± 0% -0.54% (p=0.000 n=10+10) Ldexp 41.5ns ± 0% 37.0ns ± 0% -10.84% (p=0.000 n=9+10) Log 124ns ± 0% 118ns ± 0% -4.84% (p=0.000 n=10+9) Logb 34.0ns ± 0% 32.0ns ± 0% -5.88% (p=0.000 n=10+10) Log1p 110ns ± 0% 108ns ± 0% -1.82% (p=0.000 n=10+10) Log10 136ns ± 0% 132ns ± 0% -2.94% (p=0.000 n=10+10) Log2 51.6ns ± 0% 47.1ns ± 0% -8.72% (p=0.000 n=10+10) Nextafter32 33.0ns ± 0% 30.5ns ± 0% -7.58% (p=0.000 n=10+10) Nextafter64 29.0ns ± 0% 26.5ns ± 0% -8.62% (p=0.000 n=10+10) PowInt 169ns ± 0% 160ns ± 0% -5.33% (p=0.000 n=10+10) PowFrac 375ns ± 0% 361ns ± 0% -3.73% (p=0.000 n=10+10) RoundToEven 14.0ns ± 0% 12.5ns ± 0% -10.71% (p=0.000 n=10+10) Remainder 206ns ± 0% 192ns ± 0% -6.80% (p=0.000 n=10+9) Signbit 6.01ns ± 0% 5.51ns ± 0% -8.32% (p=0.000 n=10+9) Sin 70.1ns ± 0% 69.6ns ± 0% -0.71% (p=0.000 n=10+10) Sincos 99.1ns ± 0% 99.6ns ± 0% +0.50% (p=0.000 n=9+10) SqrtGoLatency 178ns ± 0% 146ns ± 0% -17.70% (p=0.000 n=8+10) SqrtPrime 9.19µs ± 0% 9.20µs ± 0% +0.01% (p=0.000 n=9+9) Tanh 125ns ± 1% 127ns ± 0% +1.36% (p=0.000 n=10+10) Y0 428ns ± 0% 426ns ± 0% -0.47% (p=0.000 n=10+10) Y1 431ns ± 0% 429ns ± 0% -0.46% (p=0.000 n=10+9) Yn 906ns ± 0% 901ns ± 0% -0.55% (p=0.000 n=10+10) Float64bits 4.50ns ± 0% 3.50ns ± 0% -22.22% (p=0.000 n=10+10) Float64frombits 4.00ns ± 0% 3.50ns ± 0% -12.50% (p=0.000 n=10+9) Float32bits 4.50ns ± 0% 3.50ns ± 0% -22.22% (p=0.002 n=8+10) Float32frombits 4.00ns ± 0% 3.50ns ± 0% -12.50% (p=0.000 n=10+10) Change-Id: Iba829e15d5624962fe0c699139ea783efeefabc2 Reviewed-on: https://go-review.googlesource.com/129715 Reviewed-by: Cherry Zhang <cherryyz@google.com> Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org>
156 lines
4.0 KiB
Go
156 lines
4.0 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
|
|
|
|
import "math"
|
|
|
|
var sink64 [8]float64
|
|
|
|
func approx(x float64) {
|
|
// s390x:"FIDBR\t[$]6"
|
|
// arm64:"FRINTPD"
|
|
// ppc64le:"FRIP"
|
|
sink64[0] = math.Ceil(x)
|
|
|
|
// s390x:"FIDBR\t[$]7"
|
|
// arm64:"FRINTMD"
|
|
// ppc64le:"FRIM"
|
|
sink64[1] = math.Floor(x)
|
|
|
|
// s390x:"FIDBR\t[$]1"
|
|
// arm64:"FRINTAD"
|
|
// ppc64le:"FRIN"
|
|
sink64[2] = math.Round(x)
|
|
|
|
// s390x:"FIDBR\t[$]5"
|
|
// arm64:"FRINTZD"
|
|
// ppc64le:"FRIZ"
|
|
sink64[3] = math.Trunc(x)
|
|
|
|
// s390x:"FIDBR\t[$]4"
|
|
// arm64:"FRINTND"
|
|
sink64[4] = math.RoundToEven(x)
|
|
}
|
|
|
|
func sqrt(x float64) float64 {
|
|
// amd64:"SQRTSD"
|
|
// 386/387:"FSQRT" 386/sse2:"SQRTSD"
|
|
// arm64:"FSQRTD"
|
|
// arm/7:"SQRTD"
|
|
// mips/hardfloat:"SQRTD" mips/softfloat:-"SQRTD"
|
|
// mips64/hardfloat:"SQRTD" mips64/softfloat:-"SQRTD"
|
|
return math.Sqrt(x)
|
|
}
|
|
|
|
// Check that it's using integer registers
|
|
func abs(x, y float64) {
|
|
// amd64:"BTRQ\t[$]63"
|
|
// arm64:"FABSD\t"
|
|
// s390x:"LPDFR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64le:"FABS\t"
|
|
sink64[0] = math.Abs(x)
|
|
|
|
// amd64:"BTRQ\t[$]63","PXOR" (TODO: this should be BTSQ)
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64le:"FNABS\t"
|
|
sink64[1] = -math.Abs(y)
|
|
}
|
|
|
|
// Check that it's using integer registers
|
|
func abs32(x float32) float32 {
|
|
// s390x:"LPDFR",-"LDEBR",-"LEDBR" (no float64 conversion)
|
|
return float32(math.Abs(float64(x)))
|
|
}
|
|
|
|
// Check that it's using integer registers
|
|
func copysign(a, b, c float64) {
|
|
// amd64:"BTRQ\t[$]63","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
|
|
// s390x:"CPSDR",-"MOVD" (no integer load/store)
|
|
// ppc64le:"FCPSGN"
|
|
sink64[0] = math.Copysign(a, b)
|
|
|
|
// amd64:"BTSQ\t[$]63"
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64le:"FCPSGN"
|
|
// arm64:"ORR", -"AND"
|
|
sink64[1] = math.Copysign(c, -1)
|
|
|
|
// Like math.Copysign(c, -1), but with integer operations. Useful
|
|
// for platforms that have a copysign opcode to see if it's detected.
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
|
sink64[2] = math.Float64frombits(math.Float64bits(a) | 1<<63)
|
|
|
|
// amd64:-"SHLQ\t[$]1",-"SHRQ\t[$]1","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
|
|
// s390x:"CPSDR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64le:"FCPSGN"
|
|
sink64[3] = math.Copysign(-1, c)
|
|
}
|
|
|
|
func fromFloat64(f64 float64) uint64 {
|
|
// amd64:"MOVQ\tX.*, [^X].*"
|
|
// arm64:"FMOVD\tF.*, R.*"
|
|
return math.Float64bits(f64+1) + 1
|
|
}
|
|
|
|
func fromFloat32(f32 float32) uint32 {
|
|
// amd64:"MOVL\tX.*, [^X].*"
|
|
// arm64:"FMOVS\tF.*, R.*"
|
|
return math.Float32bits(f32+1) + 1
|
|
}
|
|
|
|
func toFloat64(u64 uint64) float64 {
|
|
// amd64:"MOVQ\t[^X].*, X.*"
|
|
// arm64:"FMOVD\tR.*, F.*"
|
|
return math.Float64frombits(u64+1) + 1
|
|
}
|
|
|
|
func toFloat32(u32 uint32) float32 {
|
|
// amd64:"MOVL\t[^X].*, X.*"
|
|
// arm64:"FMOVS\tR.*, F.*"
|
|
return math.Float32frombits(u32+1) + 1
|
|
}
|
|
|
|
// Test that comparisons with constants converted to float
|
|
// are evaluated at compile-time
|
|
|
|
func constantCheck64() bool {
|
|
// amd64:"MOVB\t[$]0",-"FCMP",-"MOVB\t[$]1"
|
|
// s390x:"MOV(B|BZ|D)\t[$]0,",-"FCMPU",-"MOV(B|BZ|D)\t[$]1,"
|
|
return 0.5 == float64(uint32(1)) || 1.5 > float64(uint64(1<<63)) || math.NaN() == math.NaN()
|
|
}
|
|
|
|
func constantCheck32() bool {
|
|
// amd64:"MOVB\t[$]1",-"FCMP",-"MOVB\t[$]0"
|
|
// s390x:"MOV(B|BZ|D)\t[$]1,",-"FCMPU",-"MOV(B|BZ|D)\t[$]0,"
|
|
return float32(0.5) <= float32(int64(1)) && float32(1.5) >= float32(int32(-1<<31)) && float32(math.NaN()) != float32(math.NaN())
|
|
}
|
|
|
|
// Test that integer constants are converted to floating point constants
|
|
// at compile-time
|
|
|
|
func constantConvert32(x float32) float32 {
|
|
// amd64:"MOVSS\t[$]f32.3f800000\\(SB\\)"
|
|
// s390x:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
|
// ppc64le:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
|
// arm64:"FMOVS\t[$]\\(1.0\\)"
|
|
if x > math.Float32frombits(0x3f800000) {
|
|
return -x
|
|
}
|
|
return x
|
|
}
|
|
|
|
func constantConvertInt32(x uint32) uint32 {
|
|
// amd64:-"MOVSS"
|
|
// s390x:-"FMOVS"
|
|
// ppc64le:-"FMOVS"
|
|
// arm64:-"FMOVS"
|
|
if x > math.Float32bits(1) {
|
|
return -x
|
|
}
|
|
return x
|
|
}
|