1
0
mirror of https://github.com/golang/go synced 2024-11-27 02:11:17 -07:00
go/test/codegen/math.go
Ben Shi c683ab8128 cmd/compile: optimize ARM's math.Abs
This CL optimizes math.Abs to an inline ABSD instruction on ARM.

The benchmark results of src/math/ show big improvements.
name                   old time/op  new time/op  delta
Acos-4                  181ns ± 0%   182ns ± 0%   +0.30%  (p=0.000 n=40+40)
Acosh-4                 202ns ± 0%   202ns ± 0%     ~     (all equal)
Asin-4                  163ns ± 0%   163ns ± 0%     ~     (all equal)
Asinh-4                 242ns ± 0%   242ns ± 0%     ~     (all equal)
Atan-4                  120ns ± 0%   121ns ± 0%   +0.83%  (p=0.000 n=40+40)
Atanh-4                 202ns ± 0%   202ns ± 0%     ~     (all equal)
Atan2-4                 173ns ± 0%   173ns ± 0%     ~     (all equal)
Cbrt-4                 1.06µs ± 0%  1.06µs ± 0%   +0.09%  (p=0.000 n=39+37)
Ceil-4                 72.9ns ± 0%  72.8ns ± 0%     ~     (p=0.237 n=40+40)
Copysign-4             13.2ns ± 0%  13.2ns ± 0%     ~     (all equal)
Cos-4                   193ns ± 0%   183ns ± 0%   -5.18%  (p=0.000 n=40+40)
Cosh-4                  254ns ± 0%   239ns ± 0%   -5.91%  (p=0.000 n=40+40)
Erf-4                   112ns ± 0%   112ns ± 0%     ~     (all equal)
Erfc-4                  117ns ± 0%   117ns ± 0%     ~     (all equal)
Erfinv-4                127ns ± 0%   127ns ± 1%     ~     (p=0.492 n=40+40)
Erfcinv-4               128ns ± 0%   128ns ± 0%     ~     (all equal)
Exp-4                   212ns ± 0%   206ns ± 0%   -3.05%  (p=0.000 n=40+40)
ExpGo-4                 216ns ± 0%   209ns ± 0%   -3.24%  (p=0.000 n=40+40)
Expm1-4                 142ns ± 0%   142ns ± 0%     ~     (all equal)
Exp2-4                  191ns ± 0%   184ns ± 0%   -3.45%  (p=0.000 n=40+40)
Exp2Go-4                194ns ± 0%   187ns ± 0%   -3.61%  (p=0.000 n=40+40)
Abs-4                  14.4ns ± 0%   6.3ns ± 0%  -56.39%  (p=0.000 n=38+39)
Dim-4                  12.6ns ± 0%  12.6ns ± 0%     ~     (all equal)
Floor-4                49.6ns ± 0%  49.6ns ± 0%     ~     (all equal)
Max-4                  27.6ns ± 0%  27.6ns ± 0%     ~     (all equal)
Min-4                  27.0ns ± 0%  27.0ns ± 0%     ~     (all equal)
Mod-4                   349ns ± 0%   305ns ± 1%  -12.55%  (p=0.000 n=33+40)
Frexp-4                54.0ns ± 0%  47.1ns ± 0%  -12.78%  (p=0.000 n=38+38)
Gamma-4                 242ns ± 0%   234ns ± 0%   -3.16%  (p=0.000 n=36+40)
Hypot-4                84.8ns ± 0%  67.8ns ± 0%  -20.05%  (p=0.000 n=31+35)
HypotGo-4              88.5ns ± 0%  71.6ns ± 0%  -19.12%  (p=0.000 n=40+38)
Ilogb-4                45.8ns ± 0%  38.9ns ± 0%  -15.12%  (p=0.000 n=40+32)
J0-4                    821ns ± 0%   802ns ± 0%   -2.33%  (p=0.000 n=33+40)
J1-4                    816ns ± 0%   807ns ± 0%   -1.05%  (p=0.000 n=40+29)
Jn-4                   1.67µs ± 0%  1.65µs ± 0%   -1.45%  (p=0.000 n=40+39)
Ldexp-4                61.5ns ± 0%  54.6ns ± 0%  -11.27%  (p=0.000 n=40+32)
Lgamma-4                188ns ± 0%   188ns ± 0%     ~     (all equal)
Log-4                   154ns ± 0%   147ns ± 0%   -4.78%  (p=0.000 n=40+40)
Logb-4                 50.9ns ± 0%  42.7ns ± 0%  -16.11%  (p=0.000 n=34+39)
Log1p-4                 160ns ± 0%   159ns ± 0%     ~     (p=0.828 n=40+40)
Log10-4                 173ns ± 0%   166ns ± 0%   -4.05%  (p=0.000 n=40+40)
Log2-4                 65.3ns ± 0%  58.4ns ± 0%  -10.57%  (p=0.000 n=37+37)
Modf-4                 36.4ns ± 0%  36.4ns ± 0%     ~     (all equal)
Nextafter32-4          36.4ns ± 0%  36.4ns ± 0%     ~     (all equal)
Nextafter64-4          32.7ns ± 0%  32.6ns ± 0%     ~     (p=0.375 n=40+40)
PowInt-4                300ns ± 0%   277ns ± 0%   -7.78%  (p=0.000 n=40+40)
PowFrac-4               676ns ± 0%   635ns ± 0%   -6.00%  (p=0.000 n=40+35)
Pow10Pos-4             17.6ns ± 0%  17.6ns ± 0%     ~     (all equal)
Pow10Neg-4             22.0ns ± 0%  22.0ns ± 0%     ~     (all equal)
Round-4                30.1ns ± 0%  30.1ns ± 0%     ~     (all equal)
RoundToEven-4          38.9ns ± 0%  38.9ns ± 0%     ~     (all equal)
Remainder-4             291ns ± 0%   263ns ± 0%   -9.62%  (p=0.000 n=40+40)
Signbit-4              11.3ns ± 0%  11.3ns ± 0%     ~     (all equal)
Sin-4                   185ns ± 0%   185ns ± 0%     ~     (all equal)
Sincos-4                230ns ± 0%   230ns ± 0%     ~     (all equal)
Sinh-4                  253ns ± 0%   246ns ± 0%   -2.77%  (p=0.000 n=39+39)
SqrtIndirect-4         41.4ns ± 0%  41.4ns ± 0%     ~     (all equal)
SqrtLatency-4          13.8ns ± 0%  13.8ns ± 0%     ~     (all equal)
SqrtIndirectLatency-4  37.0ns ± 0%  37.0ns ± 0%     ~     (p=0.632 n=40+40)
SqrtGoLatency-4         911ns ± 0%   911ns ± 0%   +0.08%  (p=0.000 n=40+40)
SqrtPrime-4            13.2µs ± 0%  13.2µs ± 0%   +0.01%  (p=0.038 n=38+40)
Tan-4                   205ns ± 0%   205ns ± 0%     ~     (all equal)
Tanh-4                  264ns ± 0%   247ns ± 0%   -6.44%  (p=0.000 n=39+32)
Trunc-4                45.2ns ± 0%  45.2ns ± 0%     ~     (all equal)
Y0-4                    796ns ± 0%   792ns ± 0%   -0.55%  (p=0.000 n=35+40)
Y1-4                    804ns ± 0%   797ns ± 0%   -0.82%  (p=0.000 n=24+40)
Yn-4                   1.64µs ± 0%  1.62µs ± 0%   -1.27%  (p=0.000 n=40+39)
Float64bits-4          8.16ns ± 0%  8.16ns ± 0%   +0.04%  (p=0.000 n=35+40)
Float64frombits-4      10.7ns ± 0%  10.7ns ± 0%     ~     (all equal)
Float32bits-4          7.53ns ± 0%  7.53ns ± 0%     ~     (p=0.760 n=40+40)
Float32frombits-4      6.91ns ± 0%  6.91ns ± 0%   -0.04%  (p=0.002 n=32+38)
[Geo mean]              111ns        106ns        -3.98%

Change-Id: I54f4fd7f5160db020b430b556bde59cc0fdb996d
Reviewed-on: https://go-review.googlesource.com/c/go/+/188678
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
2019-08-28 15:41:28 +00:00

179 lines
4.4 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[$]6"
// arm64:"FRINTPD"
// ppc64:"FRIP"
// ppc64le:"FRIP"
// wasm:"F64Ceil"
sink64[0] = math.Ceil(x)
// s390x:"FIDBR\t[$]7"
// arm64:"FRINTMD"
// ppc64:"FRIM"
// ppc64le:"FRIM"
// wasm:"F64Floor"
sink64[1] = math.Floor(x)
// s390x:"FIDBR\t[$]1"
// arm64:"FRINTAD"
// ppc64:"FRIN"
// ppc64le:"FRIN"
sink64[2] = math.Round(x)
// s390x:"FIDBR\t[$]5"
// arm64:"FRINTZD"
// ppc64:"FRIZ"
// ppc64le:"FRIZ"
// wasm:"F64Trunc"
sink64[3] = math.Trunc(x)
// s390x:"FIDBR\t[$]4"
// arm64:"FRINTND"
// wasm:"F64Nearest"
sink64[4] = math.RoundToEven(x)
}
func sqrt(x float64) float64 {
// amd64:"SQRTSD"
// 386/387:"FSQRT" 386/sse2:"SQRTSD"
// arm64:"FSQRTD"
// arm/7:"SQRTD"
// mips/hardfloat:"SQRTD" mips/softfloat:-"SQRTD"
// mips64/hardfloat:"SQRTD" mips64/softfloat:-"SQRTD"
// wasm:"F64Sqrt"
return math.Sqrt(x)
}
// Check that it's using integer registers
func abs(x, y float64) {
// amd64:"BTRQ\t[$]63"
// arm64:"FABSD\t"
// s390x:"LPDFR\t",-"MOVD\t" (no integer load/store)
// ppc64:"FABS\t"
// ppc64le:"FABS\t"
// wasm:"F64Abs"
// arm/6:"ABSD\t"
sink64[0] = math.Abs(x)
// amd64:"BTRQ\t[$]63","PXOR" (TODO: this should be BTSQ)
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
// ppc64:"FNABS\t"
// ppc64le:"FNABS\t"
sink64[1] = -math.Abs(y)
}
// Check that it's using integer registers
func abs32(x float32) float32 {
// s390x:"LPDFR",-"LDEBR",-"LEDBR" (no float64 conversion)
return float32(math.Abs(float64(x)))
}
// Check that it's using integer registers
func copysign(a, b, c float64) {
// amd64:"BTRQ\t[$]63","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
// s390x:"CPSDR",-"MOVD" (no integer load/store)
// ppc64:"FCPSGN"
// ppc64le:"FCPSGN"
// wasm:"F64Copysign"
sink64[0] = math.Copysign(a, b)
// amd64:"BTSQ\t[$]63"
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
// ppc64:"FCPSGN"
// ppc64le:"FCPSGN"
// arm64:"ORR", -"AND"
sink64[1] = math.Copysign(c, -1)
// Like math.Copysign(c, -1), but with integer operations. Useful
// for platforms that have a copysign opcode to see if it's detected.
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
sink64[2] = math.Float64frombits(math.Float64bits(a) | 1<<63)
// amd64:-"SHLQ\t[$]1",-"SHRQ\t[$]1","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
// s390x:"CPSDR\t",-"MOVD\t" (no integer load/store)
// ppc64:"FCPSGN"
// ppc64le:"FCPSGN"
sink64[3] = math.Copysign(-1, c)
}
func fromFloat64(f64 float64) uint64 {
// amd64:"MOVQ\tX.*, [^X].*"
// arm64:"FMOVD\tF.*, R.*"
// ppc64:"MFVSRD"
// ppc64le:"MFVSRD"
return math.Float64bits(f64+1) + 1
}
func fromFloat32(f32 float32) uint32 {
// amd64:"MOVL\tX.*, [^X].*"
// arm64:"FMOVS\tF.*, R.*"
return math.Float32bits(f32+1) + 1
}
func toFloat64(u64 uint64) float64 {
// amd64:"MOVQ\t[^X].*, X.*"
// arm64:"FMOVD\tR.*, F.*"
// ppc64:"MTVSRD"
// ppc64le:"MTVSRD"
return math.Float64frombits(u64+1) + 1
}
func toFloat32(u32 uint32) float32 {
// amd64:"MOVL\t[^X].*, X.*"
// arm64:"FMOVS\tR.*, F.*"
return math.Float32frombits(u32+1) + 1
}
// Test that comparisons with constants converted to float
// are evaluated at compile-time
func constantCheck64() bool {
// amd64:"MOVB\t[$]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[$]f32.3f800000\\(SB\\)"
// ppc64:"FMOVS\t[$]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"
// ppc64:-"FMOVS"
// ppc64le:-"FMOVS"
// arm64:-"FMOVS"
if x > math.Float32bits(1) {
return -x
}
return x
}