1
0
mirror of https://github.com/golang/go synced 2024-11-12 13:10:33 -07:00
go/test/codegen/floats.go

157 lines
3.2 KiB
Go
Raw Normal View History

// 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
// This file contains codegen tests related to arithmetic
// simplifications and optimizations on float types.
// For codegen tests on integer types, see arithmetic.go.
// --------------------- //
// Strength-reduce //
// --------------------- //
func Mul2(f float64) float64 {
// 386/sse2:"ADDSD",-"MULSD"
// amd64:"ADDSD",-"MULSD"
// arm/7:"ADDD",-"MULD"
// arm64:"FADDD",-"FMULD"
// ppc64:"FADD",-"FMUL"
// ppc64le:"FADD",-"FMUL"
return f * 2.0
}
func DivPow2(f1, f2, f3 float64) (float64, float64, float64) {
// 386/sse2:"MULSD",-"DIVSD"
// amd64:"MULSD",-"DIVSD"
// arm/7:"MULD",-"DIVD"
// arm64:"FMULD",-"FDIVD"
// ppc64:"FMUL",-"FDIV"
// ppc64le:"FMUL",-"FDIV"
x := f1 / 16.0
// 386/sse2:"MULSD",-"DIVSD"
// amd64:"MULSD",-"DIVSD"
// arm/7:"MULD",-"DIVD"
// arm64:"FMULD",-"FDIVD"
// ppc64:"FMUL",-"FDIVD"
// ppc64le:"FMUL",-"FDIVD"
y := f2 / 0.125
// 386/sse2:"ADDSD",-"DIVSD",-"MULSD"
// amd64:"ADDSD",-"DIVSD",-"MULSD"
// arm/7:"ADDD",-"MULD",-"DIVD"
// arm64:"FADDD",-"FMULD",-"FDIVD"
// ppc64:"FADD",-"FMUL",-"FDIV"
// ppc64le:"FADD",-"FMUL",-"FDIV"
z := f3 / 0.5
return x, y, z
}
cmd/compile: optimize arm64 with indexed FP load/store The FP load/store on arm64 have register indexed forms. And this CL implements this optimization. 1. The total size of pkg/android_arm64 (excluding cmd/compile) decreases about 400 bytes. 2. There is no regression in the go1 benchmark, the test case GobEncode even gets slight improvement, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.0s ± 0% 19.0s ± 1% ~ (p=0.817 n=29+29) Fannkuch11-4 9.94s ± 0% 9.95s ± 0% +0.03% (p=0.010 n=24+30) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% ~ (all equal) FmtFprintfString-4 427ns ± 0% 427ns ± 0% ~ (p=0.649 n=30+30) FmtFprintfInt-4 471ns ± 0% 471ns ± 0% ~ (all equal) FmtFprintfIntInt-4 730ns ± 0% 730ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 889ns ± 0% ~ (all equal) FmtFprintfFloat-4 1.21µs ± 0% 1.21µs ± 0% +0.04% (p=0.012 n=20+30) FmtManyArgs-4 2.99µs ± 0% 2.99µs ± 0% ~ (p=0.651 n=29+29) GobDecode-4 42.4ms ± 1% 42.3ms ± 1% -0.27% (p=0.001 n=29+28) GobEncode-4 37.8ms ±11% 36.0ms ± 0% -4.67% (p=0.000 n=30+26) Gzip-4 1.98s ± 1% 1.96s ± 1% -1.26% (p=0.000 n=30+30) Gunzip-4 175ms ± 0% 175ms ± 0% ~ (p=0.988 n=29+29) HTTPClientServer-4 854µs ± 5% 860µs ± 5% ~ (p=0.236 n=28+29) JSONEncode-4 88.8ms ± 0% 87.9ms ± 0% -1.00% (p=0.000 n=24+26) JSONDecode-4 390ms ± 1% 392ms ± 2% +0.48% (p=0.025 n=30+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.894 n=24+29) GoParse-4 20.3ms ± 0% 20.1ms ± 1% -0.94% (p=0.000 n=27+26) RegexpMatchEasy0_32-4 451ns ± 0% 451ns ± 0% ~ (p=0.578 n=30+30) RegexpMatchEasy0_1K-4 1.63µs ± 0% 1.63µs ± 0% ~ (p=0.298 n=30+28) RegexpMatchEasy1_32-4 431ns ± 0% 434ns ± 0% +0.67% (p=0.000 n=30+29) RegexpMatchEasy1_1K-4 2.60µs ± 0% 2.64µs ± 0% +1.36% (p=0.000 n=28+26) RegexpMatchMedium_32-4 744ns ± 0% 744ns ± 0% ~ (p=0.474 n=29+29) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% -0.08% (p=0.038 n=26+30) RegexpMatchHard_32-4 12.2µs ± 0% 12.3µs ± 0% +0.27% (p=0.000 n=29+30) RegexpMatchHard_1K-4 373µs ± 0% 373µs ± 0% ~ (p=0.219 n=29+28) Revcomp-4 2.84s ± 0% 2.84s ± 0% ~ (p=0.130 n=28+28) Template-4 394ms ± 1% 392ms ± 1% -0.52% (p=0.001 n=30+30) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.587 n=29+30) TimeFormat-4 2.00µs ± 0% 2.00µs ± 0% +0.07% (p=0.001 n=28+27) [Geo mean] 306µs 305µs -0.17% name old speed new speed delta GobDecode-4 18.1MB/s ± 1% 18.2MB/s ± 1% +0.27% (p=0.001 n=29+28) GobEncode-4 20.3MB/s ±10% 21.3MB/s ± 0% +4.64% (p=0.000 n=30+26) Gzip-4 9.79MB/s ± 1% 9.91MB/s ± 1% +1.28% (p=0.000 n=30+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% ~ (p=0.988 n=29+29) JSONEncode-4 21.8MB/s ± 0% 22.1MB/s ± 0% +1.02% (p=0.000 n=24+26) JSONDecode-4 4.97MB/s ± 1% 4.95MB/s ± 2% -0.45% (p=0.031 n=30+30) GoParse-4 2.85MB/s ± 1% 2.88MB/s ± 1% +1.03% (p=0.000 n=30+26) RegexpMatchEasy0_32-4 70.9MB/s ± 0% 70.9MB/s ± 0% ~ (p=0.904 n=29+28) RegexpMatchEasy0_1K-4 627MB/s ± 0% 627MB/s ± 0% ~ (p=0.156 n=30+30) RegexpMatchEasy1_32-4 74.2MB/s ± 0% 73.7MB/s ± 0% -0.67% (p=0.000 n=30+29) RegexpMatchEasy1_1K-4 393MB/s ± 0% 388MB/s ± 0% -1.34% (p=0.000 n=28+26) RegexpMatchMedium_32-4 1.34MB/s ± 0% 1.34MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.59MB/s ± 0% 4.59MB/s ± 0% +0.07% (p=0.035 n=25+30) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% -0.11% (p=0.002 n=28+30) RegexpMatchHard_1K-4 2.75MB/s ± 0% 2.75MB/s ± 0% +0.15% (p=0.001 n=30+24) Revcomp-4 89.4MB/s ± 0% 89.4MB/s ± 0% ~ (p=0.140 n=28+28) Template-4 4.93MB/s ± 1% 4.95MB/s ± 1% +0.51% (p=0.001 n=30+30) [Geo mean] 18.4MB/s 18.4MB/s +0.37% Change-Id: I9a6b521a971b21cfb51064e8e9b853cef8a1d071 Reviewed-on: https://go-review.googlesource.com/124636 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-18 03:31:35 -06:00
func indexLoad(b0 []float32, b1 float32, idx int) float32 {
// arm64:`FMOVS\s\(R[0-9]+\)\(R[0-9]+\),\sF[0-9]+`
return b0[idx] * b1
}
func indexStore(b0 []float64, b1 float64, idx int) {
// arm64:`FMOVD\sF[0-9]+,\s\(R[0-9]+\)\(R[0-9]+\)`
b0[idx] = b1
}
// ----------- //
// Fused //
// ----------- //
func FusedAdd32(x, y, z float32) float32 {
// s390x:"FMADDS\t"
// ppc64:"FMADDS\t"
// ppc64le:"FMADDS\t"
// arm64:"FMADDS"
return x*y + z
}
func FusedSub32_a(x, y, z float32) float32 {
// s390x:"FMSUBS\t"
// ppc64:"FMSUBS\t"
// ppc64le:"FMSUBS\t"
return x*y - z
}
func FusedSub32_b(x, y, z float32) float32 {
// arm64:"FMSUBS"
return z - x*y
}
func FusedAdd64(x, y, z float64) float64 {
// s390x:"FMADD\t"
// ppc64:"FMADD\t"
// ppc64le:"FMADD\t"
// arm64:"FMADDD"
return x*y + z
}
func FusedSub64_a(x, y, z float64) float64 {
// s390x:"FMSUB\t"
// ppc64:"FMSUB\t"
// ppc64le:"FMSUB\t"
return x*y - z
}
func FusedSub64_b(x, y, z float64) float64 {
// arm64:"FMSUBD"
return z - x*y
}
func Cmp(f float64) bool {
// arm64:"FCMPD","(BGT|BLE|BMI|BPL)",-"CSET\tGT",-"CBZ"
return f > 4 || f < -4
}
func CmpZero64(f float64) bool {
// s390x:"LTDBR",-"FCMPU"
return f <= 0
}
func CmpZero32(f float32) bool {
// s390x:"LTEBR",-"CEBR"
return f <= 0
}
cmd/compile: allow floating point Ops to produce flags on s390x On s390x, some floating point arithmetic instructions (FSUB, FADD) generate flag. This patch allows those related SSA ops to return a tuple, where the second argument of the tuple is the generated flag. We can use the flag and remove the subsequent comparison instruction (e.g: LTDBR). This CL also reduces the .text section for math.test binary by 0.4KB. Benchmarks: name old time/op new time/op delta Acos-18 12.1ns ± 0% 12.1ns ± 0% ~ (all equal) Acosh-18 18.5ns ± 0% 18.5ns ± 0% ~ (all equal) Asin-18 13.1ns ± 0% 13.1ns ± 0% ~ (all equal) Asinh-18 19.4ns ± 0% 19.5ns ± 1% ~ (p=0.444 n=5+5) Atan-18 10.0ns ± 0% 10.0ns ± 0% ~ (all equal) Atanh-18 19.1ns ± 1% 19.2ns ± 2% ~ (p=0.841 n=5+5) Atan2-18 16.4ns ± 0% 16.4ns ± 0% ~ (all equal) Cbrt-18 14.8ns ± 0% 14.8ns ± 0% ~ (all equal) Ceil-18 0.78ns ± 0% 0.78ns ± 0% ~ (all equal) Copysign-18 0.80ns ± 0% 0.80ns ± 0% ~ (all equal) Cos-18 7.19ns ± 0% 7.19ns ± 0% ~ (p=0.556 n=4+5) Cosh-18 12.4ns ± 0% 12.4ns ± 0% ~ (all equal) Erf-18 10.8ns ± 0% 10.8ns ± 0% ~ (all equal) Erfc-18 11.0ns ± 0% 11.0ns ± 0% ~ (all equal) Erfinv-18 23.0ns ±16% 26.8ns ± 1% +16.90% (p=0.008 n=5+5) Erfcinv-18 23.3ns ±15% 26.1ns ± 7% ~ (p=0.087 n=5+5) Exp-18 8.67ns ± 0% 8.67ns ± 0% ~ (p=1.000 n=4+4) ExpGo-18 50.8ns ± 3% 52.4ns ± 2% ~ (p=0.063 n=5+5) Expm1-18 9.49ns ± 1% 9.47ns ± 0% ~ (p=1.000 n=5+5) Exp2-18 52.7ns ± 1% 50.5ns ± 3% -4.10% (p=0.024 n=5+5) Exp2Go-18 50.6ns ± 1% 48.4ns ± 3% -4.39% (p=0.008 n=5+5) Abs-18 0.67ns ± 0% 0.67ns ± 0% ~ (p=0.444 n=5+5) Dim-18 1.02ns ± 0% 1.03ns ± 0% +0.98% (p=0.008 n=5+5) Floor-18 0.78ns ± 0% 0.78ns ± 0% ~ (all equal) Max-18 3.09ns ± 1% 3.05ns ± 0% -1.42% (p=0.008 n=5+5) Min-18 3.32ns ± 1% 3.30ns ± 0% -0.72% (p=0.016 n=5+4) Mod-18 62.3ns ± 1% 65.8ns ± 3% +5.55% (p=0.008 n=5+5) Frexp-18 5.05ns ± 2% 4.98ns ± 0% ~ (p=0.683 n=5+5) Gamma-18 24.4ns ± 0% 24.1ns ± 0% -1.23% (p=0.008 n=5+5) Hypot-18 10.3ns ± 0% 10.3ns ± 0% ~ (all equal) HypotGo-18 10.2ns ± 0% 10.2ns ± 0% ~ (all equal) Ilogb-18 3.56ns ± 1% 3.54ns ± 0% ~ (p=0.595 n=5+5) J0-18 113ns ± 0% 108ns ± 1% -4.42% (p=0.016 n=4+5) J1-18 115ns ± 0% 109ns ± 1% -4.87% (p=0.016 n=4+5) Jn-18 240ns ± 0% 230ns ± 2% -4.41% (p=0.008 n=5+5) Ldexp-18 6.19ns ± 0% 6.19ns ± 0% ~ (p=0.444 n=5+5) Lgamma-18 32.2ns ± 0% 32.2ns ± 0% ~ (all equal) Log-18 13.1ns ± 0% 13.1ns ± 0% ~ (all equal) Logb-18 4.23ns ± 0% 4.22ns ± 0% ~ (p=0.444 n=5+5) Log1p-18 12.7ns ± 0% 12.7ns ± 0% ~ (all equal) Log10-18 18.1ns ± 0% 18.2ns ± 0% ~ (p=0.167 n=5+5) Log2-18 14.0ns ± 0% 14.0ns ± 0% ~ (all equal) Modf-18 10.4ns ± 0% 10.5ns ± 0% +0.96% (p=0.016 n=4+5) Nextafter32-18 11.3ns ± 0% 11.3ns ± 0% ~ (all equal) Nextafter64-18 4.01ns ± 1% 3.97ns ± 0% ~ (p=0.333 n=5+4) PowInt-18 32.7ns ± 0% 32.7ns ± 0% ~ (all equal) PowFrac-18 33.2ns ± 0% 33.1ns ± 0% ~ (p=0.095 n=4+5) Pow10Pos-18 1.58ns ± 0% 1.58ns ± 0% ~ (all equal) Pow10Neg-18 5.81ns ± 0% 5.81ns ± 0% ~ (all equal) Round-18 0.78ns ± 0% 0.78ns ± 0% ~ (all equal) RoundToEven-18 0.78ns ± 0% 0.78ns ± 0% ~ (all equal) Remainder-18 40.6ns ± 0% 40.7ns ± 0% ~ (p=0.238 n=5+4) Signbit-18 1.57ns ± 0% 1.57ns ± 0% ~ (all equal) Sin-18 6.75ns ± 0% 6.74ns ± 0% ~ (p=0.333 n=5+4) Sincos-18 29.5ns ± 0% 29.5ns ± 0% ~ (all equal) Sinh-18 14.4ns ± 0% 14.4ns ± 0% ~ (all equal) SqrtIndirect-18 3.97ns ± 0% 4.15ns ± 0% +4.59% (p=0.008 n=5+5) SqrtLatency-18 8.01ns ± 0% 8.01ns ± 0% ~ (all equal) SqrtIndirectLatency-18 11.6ns ± 0% 11.6ns ± 0% ~ (all equal) SqrtGoLatency-18 44.7ns ± 0% 45.0ns ± 0% +0.67% (p=0.008 n=5+5) SqrtPrime-18 1.26µs ± 0% 1.27µs ± 0% +0.63% (p=0.029 n=4+4) Tan-18 11.1ns ± 0% 11.1ns ± 0% ~ (all equal) Tanh-18 15.8ns ± 0% 15.8ns ± 0% ~ (all equal) Trunc-18 0.78ns ± 0% 0.78ns ± 0% ~ (all equal) Y0-18 113ns ± 2% 108ns ± 3% -5.11% (p=0.008 n=5+5) Y1-18 112ns ± 3% 107ns ± 0% -4.29% (p=0.000 n=5+4) Yn-18 229ns ± 0% 220ns ± 1% -3.76% (p=0.016 n=4+5) Float64bits-18 1.09ns ± 0% 1.09ns ± 0% ~ (all equal) Float64frombits-18 0.55ns ± 0% 0.55ns ± 0% ~ (all equal) Float32bits-18 0.96ns ±16% 0.86ns ± 0% ~ (p=0.563 n=5+5) Float32frombits-18 1.03ns ±28% 0.84ns ± 0% ~ (p=0.167 n=5+5) FMA-18 1.60ns ± 0% 1.60ns ± 0% ~ (all equal) [Geo mean] 10.0ns 9.9ns -0.41% Change-Id: Ief7e63ea5a8ba404b0a4696e12b9b7e0b05a9a03 Reviewed-on: https://go-review.googlesource.com/c/go/+/209160 Reviewed-by: Michael Munday <mike.munday@ibm.com> Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org>
2019-11-21 08:44:23 -07:00
func CmpWithSub(a float64, b float64) bool {
f := a - b
// s390x:-"LTDBR"
return f <= 0
}
func CmpWithAdd(a float64, b float64) bool {
f := a + b
// s390x:-"LTDBR"
return f <= 0
}
// ---------------- //
// Non-floats //
// ---------------- //
// We should make sure that the compiler doesn't generate floating point
// instructions for non-float operations on Plan 9, because floating point
// operations are not allowed in the note handler.
func ArrayZero() [16]byte {
// amd64:"MOVUPS"
// plan9/amd64/:-"MOVUPS"
var a [16]byte
return a
}
func ArrayCopy(a [16]byte) (b [16]byte) {
// amd64:"MOVUPS"
// plan9/amd64/:-"MOVUPS"
b = a
return
}