1
0
mirror of https://github.com/golang/go synced 2024-11-15 02:50:31 -07:00
go/test/codegen/math.go

260 lines
6.4 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
import "math"
var sink64 [8]float64
func approx(x float64) {
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
// amd64:"ROUNDSD\t[$]2"
// s390x:"FIDBR\t[$]6"
// arm64:"FRINTPD"
// ppc64x:"FRIP"
// wasm:"F64Ceil"
sink64[0] = math.Ceil(x)
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
// amd64:"ROUNDSD\t[$]1"
// s390x:"FIDBR\t[$]7"
// arm64:"FRINTMD"
// ppc64x:"FRIM"
// wasm:"F64Floor"
sink64[1] = math.Floor(x)
// s390x:"FIDBR\t[$]1"
// arm64:"FRINTAD"
// ppc64x:"FRIN"
sink64[2] = math.Round(x)
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
// amd64:"ROUNDSD\t[$]3"
// s390x:"FIDBR\t[$]5"
// arm64:"FRINTZD"
// ppc64x:"FRIZ"
// wasm:"F64Trunc"
sink64[3] = math.Trunc(x)
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
// amd64:"ROUNDSD\t[$]0"
// s390x:"FIDBR\t[$]4"
// arm64:"FRINTND"
// wasm:"F64Nearest"
sink64[4] = math.RoundToEven(x)
}
func sqrt(x float64) float64 {
// amd64:"SQRTSD"
// 386/sse2:"SQRTSD" 386/softfloat:-"SQRTD"
// arm64:"FSQRTD"
// arm/7:"SQRTD"
// mips/hardfloat:"SQRTD" mips/softfloat:-"SQRTD"
// mips64/hardfloat:"SQRTD" mips64/softfloat:-"SQRTD"
// wasm:"F64Sqrt"
// ppc64x:"FSQRT"
// riscv64: "FSQRTD"
return math.Sqrt(x)
}
func sqrt32(x float32) float32 {
// amd64:"SQRTSS"
// 386/sse2:"SQRTSS" 386/softfloat:-"SQRTS"
// arm64:"FSQRTS"
// arm/7:"SQRTF"
// mips/hardfloat:"SQRTF" mips/softfloat:-"SQRTF"
// mips64/hardfloat:"SQRTF" mips64/softfloat:-"SQRTF"
// wasm:"F32Sqrt"
// ppc64x:"FSQRTS"
// riscv64: "FSQRTS"
return float32(math.Sqrt(float64(x)))
}
// Check that it's using integer registers
func abs(x, y float64) {
cmd/compile: add patterns for bit set/clear/complement on amd64 This patch completes implementation of BT(Q|L), and adds support for BT(S|R|C)(Q|L). Example of code changes from time.(*Time).addSec: if t.wall&hasMonotonic != 0 { 0x1073465 488b08 MOVQ 0(AX), CX 0x1073468 4889ca MOVQ CX, DX 0x107346b 48c1e93f SHRQ $0x3f, CX 0x107346f 48c1e13f SHLQ $0x3f, CX 0x1073473 48f7c1ffffffff TESTQ $-0x1, CX 0x107347a 746b JE 0x10734e7 if t.wall&hasMonotonic != 0 { 0x1073435 488b08 MOVQ 0(AX), CX 0x1073438 480fbae13f BTQ $0x3f, CX 0x107343d 7363 JAE 0x10734a2 Another example: t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x10734c8 4881e1ffffff3f ANDQ $0x3fffffff, CX 0x10734cf 48c1e61e SHLQ $0x1e, SI 0x10734d3 4809ce ORQ CX, SI 0x10734d6 48b90000000000000080 MOVQ $0x8000000000000000, CX 0x10734e0 4809f1 ORQ SI, CX 0x10734e3 488908 MOVQ CX, 0(AX) t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x107348b 4881e2ffffff3f ANDQ $0x3fffffff, DX 0x1073492 48c1e61e SHLQ $0x1e, SI 0x1073496 4809f2 ORQ SI, DX 0x1073499 480fbaea3f BTSQ $0x3f, DX 0x107349e 488910 MOVQ DX, 0(AX) Go1 benchmarks seem unaffected, and I would be surprised otherwise: name old time/op new time/op delta BinaryTree17-4 2.64s ± 4% 2.56s ± 9% -2.92% (p=0.008 n=9+9) Fannkuch11-4 2.90s ± 1% 2.95s ± 3% +1.76% (p=0.010 n=10+9) FmtFprintfEmpty-4 35.3ns ± 1% 34.5ns ± 2% -2.34% (p=0.004 n=9+8) FmtFprintfString-4 57.0ns ± 1% 58.4ns ± 5% +2.52% (p=0.029 n=9+10) FmtFprintfInt-4 59.8ns ± 3% 59.8ns ± 6% ~ (p=0.565 n=10+10) FmtFprintfIntInt-4 93.9ns ± 3% 91.2ns ± 5% -2.94% (p=0.014 n=10+9) FmtFprintfPrefixedInt-4 107ns ± 6% 104ns ± 6% ~ (p=0.099 n=10+10) FmtFprintfFloat-4 187ns ± 3% 188ns ± 3% ~ (p=0.505 n=10+9) FmtManyArgs-4 410ns ± 1% 415ns ± 6% ~ (p=0.649 n=8+10) GobDecode-4 5.30ms ± 3% 5.27ms ± 3% ~ (p=0.436 n=10+10) GobEncode-4 4.62ms ± 5% 4.47ms ± 2% -3.24% (p=0.001 n=9+10) Gzip-4 197ms ± 4% 193ms ± 3% ~ (p=0.123 n=10+10) Gunzip-4 30.4ms ± 3% 30.1ms ± 3% ~ (p=0.481 n=10+10) HTTPClientServer-4 76.3µs ± 1% 76.0µs ± 1% ~ (p=0.236 n=8+9) JSONEncode-4 10.5ms ± 9% 10.3ms ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 42.3ms ±10% 41.3ms ± 2% ~ (p=0.053 n=9+10) Mandelbrot200-4 3.80ms ± 2% 3.72ms ± 2% -2.15% (p=0.001 n=9+10) GoParse-4 2.88ms ±10% 2.81ms ± 2% ~ (p=0.247 n=10+10) RegexpMatchEasy0_32-4 69.5ns ± 4% 68.6ns ± 2% ~ (p=0.171 n=10+10) RegexpMatchEasy0_1K-4 165ns ± 3% 162ns ± 3% ~ (p=0.137 n=10+10) RegexpMatchEasy1_32-4 65.7ns ± 6% 64.4ns ± 2% -2.02% (p=0.037 n=10+10) RegexpMatchEasy1_1K-4 278ns ± 2% 279ns ± 3% ~ (p=0.991 n=8+9) RegexpMatchMedium_32-4 99.3ns ± 3% 98.5ns ± 4% ~ (p=0.457 n=10+9) RegexpMatchMedium_1K-4 30.1µs ± 1% 30.4µs ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 1.40µs ± 2% 1.41µs ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 42.5µs ± 1% 41.5µs ± 3% -2.13% (p=0.002 n=8+9) Revcomp-4 332ms ± 4% 328ms ± 5% ~ (p=0.720 n=9+10) Template-4 48.3ms ± 2% 49.6ms ± 3% +2.56% (p=0.002 n=8+10) TimeParse-4 252ns ± 2% 249ns ± 3% ~ (p=0.116 n=9+10) TimeFormat-4 262ns ± 4% 252ns ± 3% -4.01% (p=0.000 n=9+10) name old speed new speed delta GobDecode-4 145MB/s ± 3% 146MB/s ± 3% ~ (p=0.436 n=10+10) GobEncode-4 166MB/s ± 5% 172MB/s ± 2% +3.28% (p=0.001 n=9+10) Gzip-4 98.6MB/s ± 4% 100.4MB/s ± 3% ~ (p=0.123 n=10+10) Gunzip-4 639MB/s ± 3% 645MB/s ± 3% ~ (p=0.481 n=10+10) JSONEncode-4 185MB/s ± 8% 189MB/s ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 46.0MB/s ± 9% 47.0MB/s ± 2% +2.21% (p=0.046 n=9+10) GoParse-4 20.1MB/s ± 9% 20.6MB/s ± 2% ~ (p=0.239 n=10+10) RegexpMatchEasy0_32-4 460MB/s ± 4% 467MB/s ± 2% ~ (p=0.165 n=10+10) RegexpMatchEasy0_1K-4 6.19GB/s ± 3% 6.28GB/s ± 3% ~ (p=0.165 n=10+10) RegexpMatchEasy1_32-4 487MB/s ± 5% 497MB/s ± 2% +2.00% (p=0.043 n=10+10) RegexpMatchEasy1_1K-4 3.67GB/s ± 2% 3.67GB/s ± 3% ~ (p=0.963 n=8+9) RegexpMatchMedium_32-4 10.1MB/s ± 3% 10.1MB/s ± 4% ~ (p=0.435 n=10+9) RegexpMatchMedium_1K-4 34.0MB/s ± 1% 33.7MB/s ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 22.9MB/s ± 2% 22.7MB/s ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 24.0MB/s ± 3% 24.7MB/s ± 3% +2.64% (p=0.001 n=9+9) Revcomp-4 766MB/s ± 4% 775MB/s ± 5% ~ (p=0.720 n=9+10) Template-4 40.2MB/s ± 2% 39.2MB/s ± 3% -2.47% (p=0.002 n=8+10) The rules match ~1800 times during all.bash. Fixes #18943 Change-Id: I64be1ada34e89c486dfd935bf429b35652117ed4 Reviewed-on: https://go-review.googlesource.com/94766 Run-TryBot: Giovanni Bajo <rasky@develer.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-02-17 05:54:03 -07:00
// amd64:"BTRQ\t[$]63"
// arm64:"FABSD\t"
// s390x:"LPDFR\t",-"MOVD\t" (no integer load/store)
// ppc64x:"FABS\t"
// riscv64:"FABSD\t"
// wasm:"F64Abs"
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>
2019-08-01 20:41:59 -06:00
// arm/6:"ABSD\t"
math: optimize math.Abs on mips64x This commit optimized math.Abs function implementation on mips64x. Tested on loongson 3A2000. goos: linux goarch: mips64le pkg: math │ oldmath │ newmath │ │ sec/op │ sec/op vs base │ Acos-4 258.0n ± ∞ ¹ 257.1n ± ∞ ¹ -0.35% (p=0.008 n=5) Acosh-4 417.0n ± ∞ ¹ 377.9n ± ∞ ¹ -9.38% (p=0.008 n=5) Asin-4 248.0n ± ∞ ¹ 259.9n ± ∞ ¹ +4.80% (p=0.008 n=5) Asinh-4 439.6n ± ∞ ¹ 408.3n ± ∞ ¹ -7.12% (p=0.008 n=5) Atan-4 189.6n ± ∞ ¹ 188.8n ± ∞ ¹ ~ (p=0.056 n=5) Atanh-4 390.0n ± ∞ ¹ 356.4n ± ∞ ¹ -8.62% (p=0.008 n=5) Atan2-4 279.0n ± ∞ ¹ 263.9n ± ∞ ¹ -5.41% (p=0.008 n=5) Cbrt-4 314.2n ± ∞ ¹ 322.3n ± ∞ ¹ +2.58% (p=0.008 n=5) Ceil-4 139.7n ± ∞ ¹ 136.6n ± ∞ ¹ -2.22% (p=0.008 n=5) Compare-4 21.11n ± ∞ ¹ 21.09n ± ∞ ¹ ~ (p=0.405 n=5) Compare32-4 20.10n ± ∞ ¹ 20.12n ± ∞ ¹ ~ (p=0.206 n=5) Copysign-4 32.17n ± ∞ ¹ 35.71n ± ∞ ¹ +11.00% (p=0.008 n=5) Cos-4 222.8n ± ∞ ¹ 169.8n ± ∞ ¹ -23.79% (p=0.008 n=5) Cosh-4 550.2n ± ∞ ¹ 477.4n ± ∞ ¹ -13.23% (p=0.008 n=5) Erf-4 171.6n ± ∞ ¹ 174.5n ± ∞ ¹ ~ (p=0.635 n=5) Erfc-4 182.6n ± ∞ ¹ 170.2n ± ∞ ¹ -6.79% (p=0.008 n=5) Erfinv-4 177.6n ± ∞ ¹ 196.6n ± ∞ ¹ +10.70% (p=0.008 n=5) Erfcinv-4 177.8n ± ∞ ¹ 197.8n ± ∞ ¹ +11.25% (p=0.008 n=5) Exp-4 422.8n ± ∞ ¹ 382.1n ± ∞ ¹ -9.63% (p=0.008 n=5) ExpGo-4 416.1n ± ∞ ¹ 383.2n ± ∞ ¹ -7.91% (p=0.008 n=5) Expm1-4 232.9n ± ∞ ¹ 252.2n ± ∞ ¹ +8.29% (p=0.008 n=5) Exp2-4 404.8n ± ∞ ¹ 389.1n ± ∞ ¹ -3.88% (p=0.008 n=5) Exp2Go-4 407.0n ± ∞ ¹ 372.3n ± ∞ ¹ -8.53% (p=0.008 n=5) Abs-4 30.120n ± ∞ ¹ 3.014n ± ∞ ¹ -89.99% (p=0.008 n=5) Dim-4 5.021n ± ∞ ¹ 5.023n ± ∞ ¹ ~ (p=0.071 n=5) Floor-4 127.8n ± ∞ ¹ 127.1n ± ∞ ¹ -0.55% (p=0.008 n=5) Max-4 77.69n ± ∞ ¹ 76.33n ± ∞ ¹ -1.75% (p=0.008 n=5) Min-4 83.27n ± ∞ ¹ 77.87n ± ∞ ¹ -6.48% (p=0.008 n=5) Mod-4 906.2n ± ∞ ¹ 692.9n ± ∞ ¹ -23.54% (p=0.008 n=5) Frexp-4 150.6n ± ∞ ¹ 108.6n ± ∞ ¹ -27.89% (p=0.008 n=5) Gamma-4 418.4n ± ∞ ¹ 386.1n ± ∞ ¹ -7.72% (p=0.008 n=5) Hypot-4 148.20n ± ∞ ¹ 93.78n ± ∞ ¹ -36.72% (p=0.008 n=5) HypotGo-4 148.20n ± ∞ ¹ 94.47n ± ∞ ¹ -36.26% (p=0.008 n=5) Ilogb-4 135.50n ± ∞ ¹ 92.38n ± ∞ ¹ -31.82% (p=0.008 n=5) J0-4 937.7n ± ∞ ¹ 861.7n ± ∞ ¹ -8.10% (p=0.008 n=5) J1-4 915.4n ± ∞ ¹ 875.9n ± ∞ ¹ -4.32% (p=0.008 n=5) Jn-4 1.974µ ± ∞ ¹ 1.863µ ± ∞ ¹ -5.62% (p=0.008 n=5) Ldexp-4 158.5n ± ∞ ¹ 129.3n ± ∞ ¹ -18.42% (p=0.008 n=5) Lgamma-4 209.0n ± ∞ ¹ 211.8n ± ∞ ¹ ~ (p=0.095 n=5) Log-4 326.4n ± ∞ ¹ 295.2n ± ∞ ¹ -9.56% (p=0.008 n=5) Logb-4 147.7n ± ∞ ¹ 105.0n ± ∞ ¹ -28.91% (p=0.008 n=5) Log1p-4 303.4n ± ∞ ¹ 266.3n ± ∞ ¹ -12.23% (p=0.008 n=5) Log10-4 329.2n ± ∞ ¹ 298.3n ± ∞ ¹ -9.39% (p=0.008 n=5) Log2-4 187.4n ± ∞ ¹ 153.0n ± ∞ ¹ -18.36% (p=0.008 n=5) Modf-4 110.5n ± ∞ ¹ 103.5n ± ∞ ¹ -6.33% (p=0.008 n=5) Nextafter32-4 128.4n ± ∞ ¹ 121.5n ± ∞ ¹ -5.37% (p=0.016 n=5) Nextafter64-4 109.5n ± ∞ ¹ 110.5n ± ∞ ¹ +0.91% (p=0.008 n=5) PowInt-4 603.3n ± ∞ ¹ 516.4n ± ∞ ¹ -14.40% (p=0.008 n=5) PowFrac-4 1.365µ ± ∞ ¹ 1.183µ ± ∞ ¹ -13.33% (p=0.008 n=5) Pow10Pos-4 15.07n ± ∞ ¹ 15.07n ± ∞ ¹ ~ (p=0.738 n=5) Pow10Neg-4 21.11n ± ∞ ¹ 21.10n ± ∞ ¹ ~ (p=0.190 n=5) Round-4 44.23n ± ∞ ¹ 44.22n ± ∞ ¹ ~ (p=0.635 n=5) RoundToEven-4 50.25n ± ∞ ¹ 46.27n ± ∞ ¹ -7.92% (p=0.008 n=5) Remainder-4 675.6n ± ∞ ¹ 530.4n ± ∞ ¹ -21.49% (p=0.008 n=5) Signbit-4 17.07n ± ∞ ¹ 17.95n ± ∞ ¹ +5.16% (p=0.008 n=5) Sin-4 171.6n ± ∞ ¹ 189.1n ± ∞ ¹ +10.20% (p=0.008 n=5) Sincos-4 201.5n ± ∞ ¹ 200.5n ± ∞ ¹ ~ (p=0.421 n=5) Sinh-4 529.6n ± ∞ ¹ 484.6n ± ∞ ¹ -8.50% (p=0.008 n=5) SqrtIndirect-4 5.021n ± ∞ ¹ 5.023n ± ∞ ¹ +0.04% (p=0.048 n=5) SqrtLatency-4 8.032n ± ∞ ¹ 8.039n ± ∞ ¹ +0.09% (p=0.024 n=5) SqrtIndirectLatency-4 8.036n ± ∞ ¹ 8.038n ± ∞ ¹ ~ (p=0.056 n=5) SqrtGoLatency-4 338.8n ± ∞ ¹ 338.7n ± ∞ ¹ ~ (p=0.841 n=5) SqrtPrime-4 5.379µ ± ∞ ¹ 5.382µ ± ∞ ¹ +0.06% (p=0.048 n=5) Tan-4 182.7n ± ∞ ¹ 191.8n ± ∞ ¹ +4.98% (p=0.008 n=5) Tanh-4 558.7n ± ∞ ¹ 497.6n ± ∞ ¹ -10.94% (p=0.008 n=5) Trunc-4 122.5n ± ∞ ¹ 122.6n ± ∞ ¹ ~ (p=0.405 n=5) Y0-4 892.8n ± ∞ ¹ 851.7n ± ∞ ¹ -4.60% (p=0.008 n=5) Y1-4 887.2n ± ∞ ¹ 863.2n ± ∞ ¹ -2.71% (p=0.008 n=5) Yn-4 1.889µ ± ∞ ¹ 1.832µ ± ∞ ¹ -3.02% (p=0.008 n=5) Float64bits-4 13.05n ± ∞ ¹ 13.06n ± ∞ ¹ +0.08% (p=0.040 n=5) Float64frombits-4 13.05n ± ∞ ¹ 13.06n ± ∞ ¹ ~ (p=0.143 n=5) Float32bits-4 13.05n ± ∞ ¹ 13.06n ± ∞ ¹ +0.08% (p=0.008 n=5) Float32frombits-4 13.05n ± ∞ ¹ 13.08n ± ∞ ¹ +0.23% (p=0.016 n=5) FMA-4 445.7n ± ∞ ¹ 448.1n ± ∞ ¹ +0.54% (p=0.008 n=5) geomean 157.2n 142.8n -9.17% Change-Id: I9bf104848b588c9ecf79401a81d483d7fcdb0a79 Reviewed-on: https://go-review.googlesource.com/c/go/+/481575 Reviewed-by: M Zhuo <mzh@golangcn.org> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Auto-Submit: Than McIntosh <thanm@google.com> Reviewed-by: Bryan Mills <bcmills@google.com> Run-TryBot: Than McIntosh <thanm@google.com> Reviewed-by: Rong Zhang <rongrong@oss.cipunited.com>
2023-04-03 01:26:54 -06:00
// mips64/hardfloat:"ABSD\t"
math: optimize math.Abs on mipsx This commit optimized math.Abs function implementation on mipsx. Tested on loongson 3A2000. goos: linux goarch: mipsle pkg: math │ oldmath │ newmath │ │ sec/op │ sec/op vs base │ Acos-4 282.6n ± 0% 282.3n ± 0% ~ (p=0.140 n=7) Acosh-4 506.1n ± 0% 451.8n ± 0% -10.73% (p=0.001 n=7) Asin-4 272.3n ± 0% 272.2n ± 0% ~ (p=0.808 n=7) Asinh-4 529.7n ± 0% 475.3n ± 0% -10.27% (p=0.001 n=7) Atan-4 208.2n ± 0% 207.9n ± 0% ~ (p=0.134 n=7) Atanh-4 503.4n ± 1% 449.7n ± 0% -10.67% (p=0.001 n=7) Atan2-4 310.5n ± 0% 310.5n ± 0% ~ (p=0.928 n=7) Cbrt-4 359.3n ± 0% 358.8n ± 0% ~ (p=0.121 n=7) Ceil-4 203.9n ± 0% 204.0n ± 0% ~ (p=0.600 n=7) Compare-4 23.11n ± 0% 23.11n ± 0% ~ (p=0.702 n=7) Compare32-4 19.09n ± 0% 19.12n ± 0% ~ (p=0.070 n=7) Copysign-4 33.20n ± 0% 34.02n ± 0% +2.47% (p=0.001 n=7) Cos-4 422.5n ± 0% 385.4n ± 1% -8.78% (p=0.001 n=7) Cosh-4 628.0n ± 0% 545.5n ± 0% -13.14% (p=0.001 n=7) Erf-4 193.7n ± 2% 192.7n ± 1% ~ (p=0.430 n=7) Erfc-4 192.8n ± 1% 193.0n ± 0% ~ (p=0.245 n=7) Erfinv-4 220.7n ± 1% 221.5n ± 2% ~ (p=0.272 n=7) Erfcinv-4 221.3n ± 1% 220.4n ± 2% ~ (p=0.738 n=7) Exp-4 471.4n ± 0% 435.1n ± 0% -7.70% (p=0.001 n=7) ExpGo-4 470.6n ± 0% 434.0n ± 0% -7.78% (p=0.001 n=7) Expm1-4 243.1n ± 0% 243.4n ± 0% ~ (p=0.417 n=7) Exp2-4 463.1n ± 0% 427.0n ± 0% -7.80% (p=0.001 n=7) Exp2Go-4 462.4n ± 0% 426.2n ± 5% -7.83% (p=0.001 n=7) Abs-4 37.000n ± 0% 8.039n ± 9% -78.27% (p=0.001 n=7) Dim-4 18.09n ± 0% 18.11n ± 0% ~ (p=0.094 n=7) Floor-4 151.9n ± 0% 151.8n ± 0% ~ (p=0.190 n=7) Max-4 116.7n ± 1% 116.7n ± 1% ~ (p=0.842 n=7) Min-4 116.6n ± 1% 116.6n ± 0% ~ (p=0.464 n=7) Mod-4 1244.0n ± 0% 980.9n ± 0% -21.15% (p=0.001 n=7) Frexp-4 199.0n ± 0% 146.7n ± 0% -26.28% (p=0.001 n=7) Gamma-4 516.4n ± 0% 479.3n ± 1% -7.18% (p=0.001 n=7) Hypot-4 169.8n ± 0% 117.8n ± 2% -30.62% (p=0.001 n=7) HypotGo-4 170.8n ± 0% 117.5n ± 0% -31.21% (p=0.001 n=7) Ilogb-4 160.8n ± 0% 109.5n ± 0% -31.90% (p=0.001 n=7) J0-4 1.359µ ± 0% 1.305µ ± 0% -3.97% (p=0.001 n=7) J1-4 1.386µ ± 0% 1.334µ ± 0% -3.75% (p=0.001 n=7) Jn-4 2.864µ ± 0% 2.758µ ± 0% -3.70% (p=0.001 n=7) Ldexp-4 202.9n ± 0% 151.7n ± 0% -25.23% (p=0.001 n=7) Lgamma-4 234.0n ± 0% 234.3n ± 0% ~ (p=0.199 n=7) Log-4 444.1n ± 0% 407.9n ± 0% -8.15% (p=0.001 n=7) Logb-4 157.8n ± 0% 121.6n ± 0% -22.94% (p=0.001 n=7) Log1p-4 354.8n ± 0% 315.4n ± 0% -11.10% (p=0.001 n=7) Log10-4 453.9n ± 0% 417.9n ± 0% -7.93% (p=0.001 n=7) Log2-4 245.3n ± 0% 209.1n ± 0% -14.76% (p=0.001 n=7) Modf-4 126.6n ± 0% 126.6n ± 0% ~ (p=0.126 n=7) Nextafter32-4 112.5n ± 0% 112.5n ± 0% ~ (p=0.853 n=7) Nextafter64-4 141.7n ± 0% 141.6n ± 0% ~ (p=0.331 n=7) PowInt-4 878.8n ± 1% 758.3n ± 1% -13.71% (p=0.001 n=7) PowFrac-4 1.809µ ± 0% 1.615µ ± 0% -10.72% (p=0.001 n=7) Pow10Pos-4 18.10n ± 0% 18.12n ± 0% ~ (p=0.464 n=7) Pow10Neg-4 17.09n ± 0% 17.09n ± 0% ~ (p=0.263 n=7) Round-4 68.36n ± 0% 68.33n ± 0% ~ (p=0.325 n=7) RoundToEven-4 78.40n ± 0% 78.40n ± 0% ~ (p=0.934 n=7) Remainder-4 894.0n ± 1% 753.4n ± 1% -15.73% (p=0.001 n=7) Signbit-4 18.09n ± 0% 18.09n ± 0% ~ (p=0.761 n=7) Sin-4 389.8n ± 1% 389.8n ± 0% ~ (p=0.995 n=7) Sincos-4 416.0n ± 0% 415.9n ± 0% ~ (p=0.361 n=7) Sinh-4 634.6n ± 4% 585.6n ± 1% -7.72% (p=0.001 n=7) SqrtIndirect-4 8.035n ± 0% 8.036n ± 0% ~ (p=0.523 n=7) SqrtLatency-4 8.039n ± 0% 8.037n ± 0% ~ (p=0.218 n=7) SqrtIndirectLatency-4 8.040n ± 0% 8.040n ± 0% ~ (p=0.652 n=7) SqrtGoLatency-4 895.7n ± 0% 896.6n ± 0% +0.10% (p=0.004 n=7) SqrtPrime-4 5.406µ ± 0% 5.407µ ± 0% ~ (p=0.592 n=7) Tan-4 406.1n ± 0% 405.8n ± 1% ~ (p=0.435 n=7) Tanh-4 627.6n ± 0% 545.5n ± 0% -13.08% (p=0.001 n=7) Trunc-4 146.7n ± 1% 146.7n ± 0% ~ (p=0.755 n=7) Y0-4 1.359µ ± 0% 1.310µ ± 0% -3.61% (p=0.001 n=7) Y1-4 1.351µ ± 0% 1.301µ ± 0% -3.70% (p=0.001 n=7) Yn-4 2.829µ ± 0% 2.729µ ± 0% -3.53% (p=0.001 n=7) Float64bits-4 14.08n ± 0% 14.07n ± 0% ~ (p=0.069 n=7) Float64frombits-4 19.09n ± 0% 19.10n ± 0% ~ (p=0.755 n=7) Float32bits-4 13.06n ± 0% 13.07n ± 1% ~ (p=0.586 n=7) Float32frombits-4 13.06n ± 0% 13.06n ± 0% ~ (p=0.853 n=7) FMA-4 606.9n ± 0% 606.8n ± 0% ~ (p=0.393 n=7) geomean 201.1n 185.4n -7.81% Change-Id: I6d41a97ad3789ed5731588588859ac0b8b13b664 Reviewed-on: https://go-review.googlesource.com/c/go/+/484675 Reviewed-by: Rong Zhang <rongrong@oss.cipunited.com> Reviewed-by: Bryan Mills <bcmills@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Than McIntosh <thanm@google.com>
2023-04-14 02:06:40 -06:00
// mips/hardfloat:"ABSD\t"
sink64[0] = math.Abs(x)
cmd/compile: add patterns for bit set/clear/complement on amd64 This patch completes implementation of BT(Q|L), and adds support for BT(S|R|C)(Q|L). Example of code changes from time.(*Time).addSec: if t.wall&hasMonotonic != 0 { 0x1073465 488b08 MOVQ 0(AX), CX 0x1073468 4889ca MOVQ CX, DX 0x107346b 48c1e93f SHRQ $0x3f, CX 0x107346f 48c1e13f SHLQ $0x3f, CX 0x1073473 48f7c1ffffffff TESTQ $-0x1, CX 0x107347a 746b JE 0x10734e7 if t.wall&hasMonotonic != 0 { 0x1073435 488b08 MOVQ 0(AX), CX 0x1073438 480fbae13f BTQ $0x3f, CX 0x107343d 7363 JAE 0x10734a2 Another example: t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x10734c8 4881e1ffffff3f ANDQ $0x3fffffff, CX 0x10734cf 48c1e61e SHLQ $0x1e, SI 0x10734d3 4809ce ORQ CX, SI 0x10734d6 48b90000000000000080 MOVQ $0x8000000000000000, CX 0x10734e0 4809f1 ORQ SI, CX 0x10734e3 488908 MOVQ CX, 0(AX) t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x107348b 4881e2ffffff3f ANDQ $0x3fffffff, DX 0x1073492 48c1e61e SHLQ $0x1e, SI 0x1073496 4809f2 ORQ SI, DX 0x1073499 480fbaea3f BTSQ $0x3f, DX 0x107349e 488910 MOVQ DX, 0(AX) Go1 benchmarks seem unaffected, and I would be surprised otherwise: name old time/op new time/op delta BinaryTree17-4 2.64s ± 4% 2.56s ± 9% -2.92% (p=0.008 n=9+9) Fannkuch11-4 2.90s ± 1% 2.95s ± 3% +1.76% (p=0.010 n=10+9) FmtFprintfEmpty-4 35.3ns ± 1% 34.5ns ± 2% -2.34% (p=0.004 n=9+8) FmtFprintfString-4 57.0ns ± 1% 58.4ns ± 5% +2.52% (p=0.029 n=9+10) FmtFprintfInt-4 59.8ns ± 3% 59.8ns ± 6% ~ (p=0.565 n=10+10) FmtFprintfIntInt-4 93.9ns ± 3% 91.2ns ± 5% -2.94% (p=0.014 n=10+9) FmtFprintfPrefixedInt-4 107ns ± 6% 104ns ± 6% ~ (p=0.099 n=10+10) FmtFprintfFloat-4 187ns ± 3% 188ns ± 3% ~ (p=0.505 n=10+9) FmtManyArgs-4 410ns ± 1% 415ns ± 6% ~ (p=0.649 n=8+10) GobDecode-4 5.30ms ± 3% 5.27ms ± 3% ~ (p=0.436 n=10+10) GobEncode-4 4.62ms ± 5% 4.47ms ± 2% -3.24% (p=0.001 n=9+10) Gzip-4 197ms ± 4% 193ms ± 3% ~ (p=0.123 n=10+10) Gunzip-4 30.4ms ± 3% 30.1ms ± 3% ~ (p=0.481 n=10+10) HTTPClientServer-4 76.3µs ± 1% 76.0µs ± 1% ~ (p=0.236 n=8+9) JSONEncode-4 10.5ms ± 9% 10.3ms ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 42.3ms ±10% 41.3ms ± 2% ~ (p=0.053 n=9+10) Mandelbrot200-4 3.80ms ± 2% 3.72ms ± 2% -2.15% (p=0.001 n=9+10) GoParse-4 2.88ms ±10% 2.81ms ± 2% ~ (p=0.247 n=10+10) RegexpMatchEasy0_32-4 69.5ns ± 4% 68.6ns ± 2% ~ (p=0.171 n=10+10) RegexpMatchEasy0_1K-4 165ns ± 3% 162ns ± 3% ~ (p=0.137 n=10+10) RegexpMatchEasy1_32-4 65.7ns ± 6% 64.4ns ± 2% -2.02% (p=0.037 n=10+10) RegexpMatchEasy1_1K-4 278ns ± 2% 279ns ± 3% ~ (p=0.991 n=8+9) RegexpMatchMedium_32-4 99.3ns ± 3% 98.5ns ± 4% ~ (p=0.457 n=10+9) RegexpMatchMedium_1K-4 30.1µs ± 1% 30.4µs ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 1.40µs ± 2% 1.41µs ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 42.5µs ± 1% 41.5µs ± 3% -2.13% (p=0.002 n=8+9) Revcomp-4 332ms ± 4% 328ms ± 5% ~ (p=0.720 n=9+10) Template-4 48.3ms ± 2% 49.6ms ± 3% +2.56% (p=0.002 n=8+10) TimeParse-4 252ns ± 2% 249ns ± 3% ~ (p=0.116 n=9+10) TimeFormat-4 262ns ± 4% 252ns ± 3% -4.01% (p=0.000 n=9+10) name old speed new speed delta GobDecode-4 145MB/s ± 3% 146MB/s ± 3% ~ (p=0.436 n=10+10) GobEncode-4 166MB/s ± 5% 172MB/s ± 2% +3.28% (p=0.001 n=9+10) Gzip-4 98.6MB/s ± 4% 100.4MB/s ± 3% ~ (p=0.123 n=10+10) Gunzip-4 639MB/s ± 3% 645MB/s ± 3% ~ (p=0.481 n=10+10) JSONEncode-4 185MB/s ± 8% 189MB/s ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 46.0MB/s ± 9% 47.0MB/s ± 2% +2.21% (p=0.046 n=9+10) GoParse-4 20.1MB/s ± 9% 20.6MB/s ± 2% ~ (p=0.239 n=10+10) RegexpMatchEasy0_32-4 460MB/s ± 4% 467MB/s ± 2% ~ (p=0.165 n=10+10) RegexpMatchEasy0_1K-4 6.19GB/s ± 3% 6.28GB/s ± 3% ~ (p=0.165 n=10+10) RegexpMatchEasy1_32-4 487MB/s ± 5% 497MB/s ± 2% +2.00% (p=0.043 n=10+10) RegexpMatchEasy1_1K-4 3.67GB/s ± 2% 3.67GB/s ± 3% ~ (p=0.963 n=8+9) RegexpMatchMedium_32-4 10.1MB/s ± 3% 10.1MB/s ± 4% ~ (p=0.435 n=10+9) RegexpMatchMedium_1K-4 34.0MB/s ± 1% 33.7MB/s ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 22.9MB/s ± 2% 22.7MB/s ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 24.0MB/s ± 3% 24.7MB/s ± 3% +2.64% (p=0.001 n=9+9) Revcomp-4 766MB/s ± 4% 775MB/s ± 5% ~ (p=0.720 n=9+10) Template-4 40.2MB/s ± 2% 39.2MB/s ± 3% -2.47% (p=0.002 n=8+10) The rules match ~1800 times during all.bash. Fixes #18943 Change-Id: I64be1ada34e89c486dfd935bf429b35652117ed4 Reviewed-on: https://go-review.googlesource.com/94766 Run-TryBot: Giovanni Bajo <rasky@develer.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-02-17 05:54:03 -07:00
// amd64:"BTRQ\t[$]63","PXOR" (TODO: this should be BTSQ)
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
// ppc64x:"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) {
compile: prefer an AND instead of SHR+SHL instructions On modern 64bit CPUs a SHR, SHL or AND instruction take 1 cycle to execute. A pair of shifts that operate on the same register will take 2 cycles and needs to wait for the input register value to be available. Large constants used to mask the high bits of a register with an AND instruction can not be encoded as an immediate in the AND instruction on amd64 and therefore need to be loaded into a register with a MOV instruction. However that MOV instruction is not dependent on the output register and on many CPUs does not compete with the AND or shift instructions for execution ports. Using a pair of shifts to mask high bits instead of an AND to mask high bits of a register has a shorter encoding and uses one less general purpose register but is slower due to taking one clock cycle longer if there is no register pressure that would make the AND variant need to generate a spill. For example the instructions emitted for (x & 1 << 63) before this CL are: 48c1ea3f SHRQ $0x3f, DX 48c1e23f SHLQ $0x3f, DX after this CL the instructions are the same as GCC and LLVM use: 48b80000000000000080 MOVQ $0x8000000000000000, AX 4821d0 ANDQ DX, AX Some platforms such as arm64 already have SSA optimization rules to fuse two shift instructions back into an AND. Removing the general rule to rewrite AND to SHR+SHL speeds up this benchmark: var GlobalU uint func BenchmarkAndHighBits(b *testing.B) { x := uint(0) for i := 0; i < b.N; i++ { x &= 1 << 63 } GlobalU = x } amd64/darwin on Intel(R) Core(TM) i7-3520M CPU @ 2.90GHz: name old time/op new time/op delta AndHighBits-4 0.61ns ± 6% 0.42ns ± 6% -31.42% (p=0.000 n=25+25): 'go run run.go -all_codegen -v codegen' passes with following adjustments: ARM64: The BFXIL pattern ((x << lc) >> rc | y & ac) needed adjustment since ORshiftRL generation fusing '>> rc' and '|' interferes with matching ((x << lc) >> rc) to generate UBFX. Previously ORshiftLL was created first using the shifts generated for (y & ac). S390X: Add rules for abs and copysign to match use of AND instead of SHIFTs. Updates #33826 Updates #32781 Change-Id: I5a59f6239660d53c029cd22dfb44ddf39f93a56c Reviewed-on: https://go-review.googlesource.com/c/go/+/196810 Run-TryBot: Martin Möhrmann <moehrmann@google.com> Reviewed-by: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org>
2019-09-09 09:50:35 -06:00
// amd64:"BTRQ\t[$]63","ANDQ","ORQ"
// s390x:"CPSDR",-"MOVD" (no integer load/store)
// ppc64x:"FCPSGN"
// riscv64:"FSGNJD"
// wasm:"F64Copysign"
sink64[0] = math.Copysign(a, b)
cmd/compile: add patterns for bit set/clear/complement on amd64 This patch completes implementation of BT(Q|L), and adds support for BT(S|R|C)(Q|L). Example of code changes from time.(*Time).addSec: if t.wall&hasMonotonic != 0 { 0x1073465 488b08 MOVQ 0(AX), CX 0x1073468 4889ca MOVQ CX, DX 0x107346b 48c1e93f SHRQ $0x3f, CX 0x107346f 48c1e13f SHLQ $0x3f, CX 0x1073473 48f7c1ffffffff TESTQ $-0x1, CX 0x107347a 746b JE 0x10734e7 if t.wall&hasMonotonic != 0 { 0x1073435 488b08 MOVQ 0(AX), CX 0x1073438 480fbae13f BTQ $0x3f, CX 0x107343d 7363 JAE 0x10734a2 Another example: t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x10734c8 4881e1ffffff3f ANDQ $0x3fffffff, CX 0x10734cf 48c1e61e SHLQ $0x1e, SI 0x10734d3 4809ce ORQ CX, SI 0x10734d6 48b90000000000000080 MOVQ $0x8000000000000000, CX 0x10734e0 4809f1 ORQ SI, CX 0x10734e3 488908 MOVQ CX, 0(AX) t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x107348b 4881e2ffffff3f ANDQ $0x3fffffff, DX 0x1073492 48c1e61e SHLQ $0x1e, SI 0x1073496 4809f2 ORQ SI, DX 0x1073499 480fbaea3f BTSQ $0x3f, DX 0x107349e 488910 MOVQ DX, 0(AX) Go1 benchmarks seem unaffected, and I would be surprised otherwise: name old time/op new time/op delta BinaryTree17-4 2.64s ± 4% 2.56s ± 9% -2.92% (p=0.008 n=9+9) Fannkuch11-4 2.90s ± 1% 2.95s ± 3% +1.76% (p=0.010 n=10+9) FmtFprintfEmpty-4 35.3ns ± 1% 34.5ns ± 2% -2.34% (p=0.004 n=9+8) FmtFprintfString-4 57.0ns ± 1% 58.4ns ± 5% +2.52% (p=0.029 n=9+10) FmtFprintfInt-4 59.8ns ± 3% 59.8ns ± 6% ~ (p=0.565 n=10+10) FmtFprintfIntInt-4 93.9ns ± 3% 91.2ns ± 5% -2.94% (p=0.014 n=10+9) FmtFprintfPrefixedInt-4 107ns ± 6% 104ns ± 6% ~ (p=0.099 n=10+10) FmtFprintfFloat-4 187ns ± 3% 188ns ± 3% ~ (p=0.505 n=10+9) FmtManyArgs-4 410ns ± 1% 415ns ± 6% ~ (p=0.649 n=8+10) GobDecode-4 5.30ms ± 3% 5.27ms ± 3% ~ (p=0.436 n=10+10) GobEncode-4 4.62ms ± 5% 4.47ms ± 2% -3.24% (p=0.001 n=9+10) Gzip-4 197ms ± 4% 193ms ± 3% ~ (p=0.123 n=10+10) Gunzip-4 30.4ms ± 3% 30.1ms ± 3% ~ (p=0.481 n=10+10) HTTPClientServer-4 76.3µs ± 1% 76.0µs ± 1% ~ (p=0.236 n=8+9) JSONEncode-4 10.5ms ± 9% 10.3ms ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 42.3ms ±10% 41.3ms ± 2% ~ (p=0.053 n=9+10) Mandelbrot200-4 3.80ms ± 2% 3.72ms ± 2% -2.15% (p=0.001 n=9+10) GoParse-4 2.88ms ±10% 2.81ms ± 2% ~ (p=0.247 n=10+10) RegexpMatchEasy0_32-4 69.5ns ± 4% 68.6ns ± 2% ~ (p=0.171 n=10+10) RegexpMatchEasy0_1K-4 165ns ± 3% 162ns ± 3% ~ (p=0.137 n=10+10) RegexpMatchEasy1_32-4 65.7ns ± 6% 64.4ns ± 2% -2.02% (p=0.037 n=10+10) RegexpMatchEasy1_1K-4 278ns ± 2% 279ns ± 3% ~ (p=0.991 n=8+9) RegexpMatchMedium_32-4 99.3ns ± 3% 98.5ns ± 4% ~ (p=0.457 n=10+9) RegexpMatchMedium_1K-4 30.1µs ± 1% 30.4µs ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 1.40µs ± 2% 1.41µs ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 42.5µs ± 1% 41.5µs ± 3% -2.13% (p=0.002 n=8+9) Revcomp-4 332ms ± 4% 328ms ± 5% ~ (p=0.720 n=9+10) Template-4 48.3ms ± 2% 49.6ms ± 3% +2.56% (p=0.002 n=8+10) TimeParse-4 252ns ± 2% 249ns ± 3% ~ (p=0.116 n=9+10) TimeFormat-4 262ns ± 4% 252ns ± 3% -4.01% (p=0.000 n=9+10) name old speed new speed delta GobDecode-4 145MB/s ± 3% 146MB/s ± 3% ~ (p=0.436 n=10+10) GobEncode-4 166MB/s ± 5% 172MB/s ± 2% +3.28% (p=0.001 n=9+10) Gzip-4 98.6MB/s ± 4% 100.4MB/s ± 3% ~ (p=0.123 n=10+10) Gunzip-4 639MB/s ± 3% 645MB/s ± 3% ~ (p=0.481 n=10+10) JSONEncode-4 185MB/s ± 8% 189MB/s ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 46.0MB/s ± 9% 47.0MB/s ± 2% +2.21% (p=0.046 n=9+10) GoParse-4 20.1MB/s ± 9% 20.6MB/s ± 2% ~ (p=0.239 n=10+10) RegexpMatchEasy0_32-4 460MB/s ± 4% 467MB/s ± 2% ~ (p=0.165 n=10+10) RegexpMatchEasy0_1K-4 6.19GB/s ± 3% 6.28GB/s ± 3% ~ (p=0.165 n=10+10) RegexpMatchEasy1_32-4 487MB/s ± 5% 497MB/s ± 2% +2.00% (p=0.043 n=10+10) RegexpMatchEasy1_1K-4 3.67GB/s ± 2% 3.67GB/s ± 3% ~ (p=0.963 n=8+9) RegexpMatchMedium_32-4 10.1MB/s ± 3% 10.1MB/s ± 4% ~ (p=0.435 n=10+9) RegexpMatchMedium_1K-4 34.0MB/s ± 1% 33.7MB/s ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 22.9MB/s ± 2% 22.7MB/s ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 24.0MB/s ± 3% 24.7MB/s ± 3% +2.64% (p=0.001 n=9+9) Revcomp-4 766MB/s ± 4% 775MB/s ± 5% ~ (p=0.720 n=9+10) Template-4 40.2MB/s ± 2% 39.2MB/s ± 3% -2.47% (p=0.002 n=8+10) The rules match ~1800 times during all.bash. Fixes #18943 Change-Id: I64be1ada34e89c486dfd935bf429b35652117ed4 Reviewed-on: https://go-review.googlesource.com/94766 Run-TryBot: Giovanni Bajo <rasky@develer.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-02-17 05:54:03 -07:00
// amd64:"BTSQ\t[$]63"
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
// ppc64x:"FCPSGN"
// riscv64:"FSGNJD"
// 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)
compile: prefer an AND instead of SHR+SHL instructions On modern 64bit CPUs a SHR, SHL or AND instruction take 1 cycle to execute. A pair of shifts that operate on the same register will take 2 cycles and needs to wait for the input register value to be available. Large constants used to mask the high bits of a register with an AND instruction can not be encoded as an immediate in the AND instruction on amd64 and therefore need to be loaded into a register with a MOV instruction. However that MOV instruction is not dependent on the output register and on many CPUs does not compete with the AND or shift instructions for execution ports. Using a pair of shifts to mask high bits instead of an AND to mask high bits of a register has a shorter encoding and uses one less general purpose register but is slower due to taking one clock cycle longer if there is no register pressure that would make the AND variant need to generate a spill. For example the instructions emitted for (x & 1 << 63) before this CL are: 48c1ea3f SHRQ $0x3f, DX 48c1e23f SHLQ $0x3f, DX after this CL the instructions are the same as GCC and LLVM use: 48b80000000000000080 MOVQ $0x8000000000000000, AX 4821d0 ANDQ DX, AX Some platforms such as arm64 already have SSA optimization rules to fuse two shift instructions back into an AND. Removing the general rule to rewrite AND to SHR+SHL speeds up this benchmark: var GlobalU uint func BenchmarkAndHighBits(b *testing.B) { x := uint(0) for i := 0; i < b.N; i++ { x &= 1 << 63 } GlobalU = x } amd64/darwin on Intel(R) Core(TM) i7-3520M CPU @ 2.90GHz: name old time/op new time/op delta AndHighBits-4 0.61ns ± 6% 0.42ns ± 6% -31.42% (p=0.000 n=25+25): 'go run run.go -all_codegen -v codegen' passes with following adjustments: ARM64: The BFXIL pattern ((x << lc) >> rc | y & ac) needed adjustment since ORshiftRL generation fusing '>> rc' and '|' interferes with matching ((x << lc) >> rc) to generate UBFX. Previously ORshiftLL was created first using the shifts generated for (y & ac). S390X: Add rules for abs and copysign to match use of AND instead of SHIFTs. Updates #33826 Updates #32781 Change-Id: I5a59f6239660d53c029cd22dfb44ddf39f93a56c Reviewed-on: https://go-review.googlesource.com/c/go/+/196810 Run-TryBot: Martin Möhrmann <moehrmann@google.com> Reviewed-by: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org>
2019-09-09 09:50:35 -06:00
// amd64:"ANDQ","ORQ"
// s390x:"CPSDR\t",-"MOVD\t" (no integer load/store)
// ppc64x:"FCPSGN"
// riscv64:"FSGNJD"
sink64[3] = math.Copysign(-1, c)
}
func fma(x, y, z float64) float64 {
// amd64/v3:-".*x86HasFMA"
// amd64:"VFMADD231SD"
// arm/6:"FMULAD"
// arm64:"FMADDD"
// s390x:"FMADD"
// ppc64x:"FMADD"
// riscv64:"FMADDD"
math, cmd/compile: rename Fma to FMA This API was added for #25819, where it was discussed as math.FMA. The commit adding it used math.Fma, presumably for consistency with the rest of the unusual names in package math (Sincos, Acosh, Erfcinv, Float32bits, etc). I believe that using an idiomatic Go name is more important here than consistency with these other names, most of which are historical baggage from C's standard library. Early additions like Float32frombits happened before "uppercase for export" (so they were originally like "float32frombits") and they were not properly reconsidered when we uppercased the symbols to export them. That's a mistake we live with. The names of functions we have added since then, and even a few that were legacy, are more properly Go-cased, such as IsNaN, IsInf, and RoundToEven, rather than Isnan, Isinf, and Roundtoeven. And also constants like MaxFloat32. For new API, we should keep using proper Go-cased symbols instead of minimally-upper-cased-C symbols. So math.FMA, not math.Fma. This API has not yet been released, so this change does not break the compatibility promise. This CL also modifies cmd/compile, since the compiler knows the name of the function. I could have stopped at changing the string constants, but it seemed to make more sense to use a consistent casing everywhere. Change-Id: I0f6f3407f41e99bfa8239467345c33945088896e Reviewed-on: https://go-review.googlesource.com/c/go/+/205317 Run-TryBot: Russ Cox <rsc@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2019-11-04 17:43:45 -07:00
return math.FMA(x, y, z)
}
func fms(x, y, z float64) float64 {
// riscv64:"FMSUBD"
return math.FMA(x, y, -z)
}
func fnms(x, y, z float64) float64 {
// riscv64:"FNMSUBD",-"FNMADDD"
return math.FMA(-x, y, z)
}
func fnma(x, y, z float64) float64 {
// riscv64:"FNMADDD",-"FNMSUBD"
return math.FMA(x, -y, -z)
}
func fromFloat64(f64 float64) uint64 {
// amd64:"MOVQ\tX.*, [^X].*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on arm64 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>
2018-07-15 22:45:25 -06:00
// arm64:"FMOVD\tF.*, R.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on loong64 Use float <-> int register moves without conversion instead of stores and loads to move float <-> int values like arm64 and mips64. goos: linux goarch: loong64 pkg: math cpu: Loongson-3A6000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 15.98n ± 0% 15.94n ± 0% -0.25% (p=0.000 n=20) Acosh 27.75n ± 0% 25.56n ± 0% -7.89% (p=0.000 n=20) Asin 15.85n ± 0% 15.76n ± 0% -0.57% (p=0.000 n=20) Asinh 39.79n ± 0% 37.69n ± 0% -5.28% (p=0.000 n=20) Atan 7.261n ± 0% 7.242n ± 0% -0.27% (p=0.000 n=20) Atanh 28.30n ± 0% 27.62n ± 0% -2.40% (p=0.000 n=20) Atan2 15.85n ± 0% 15.75n ± 0% -0.63% (p=0.000 n=20) Cbrt 27.02n ± 0% 21.08n ± 0% -21.98% (p=0.000 n=20) Ceil 2.830n ± 1% 2.896n ± 1% +2.31% (p=0.000 n=20) Copysign 0.8022n ± 0% 0.8004n ± 0% -0.22% (p=0.000 n=20) Cos 11.64n ± 0% 11.61n ± 0% -0.26% (p=0.000 n=20) Cosh 35.98n ± 0% 33.44n ± 0% -7.05% (p=0.000 n=20) Erf 10.09n ± 0% 10.08n ± 0% -0.10% (p=0.000 n=20) Erfc 11.40n ± 0% 11.35n ± 0% -0.44% (p=0.000 n=20) Erfinv 12.31n ± 0% 12.29n ± 0% -0.16% (p=0.000 n=20) Erfcinv 12.16n ± 0% 12.17n ± 0% +0.08% (p=0.000 n=20) Exp 28.41n ± 0% 26.44n ± 0% -6.95% (p=0.000 n=20) ExpGo 28.68n ± 0% 27.07n ± 0% -5.60% (p=0.000 n=20) Expm1 17.21n ± 0% 16.75n ± 0% -2.67% (p=0.000 n=20) Exp2 24.71n ± 0% 23.01n ± 0% -6.88% (p=0.000 n=20) Exp2Go 25.17n ± 0% 23.91n ± 0% -4.99% (p=0.000 n=20) Abs 0.8004n ± 0% 0.8004n ± 0% ~ (p=0.224 n=20) Dim 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ Floor 2.848n ± 0% 2.859n ± 0% +0.39% (p=0.000 n=20) Max 3.074n ± 0% 3.071n ± 0% ~ (p=0.481 n=20) Min 3.179n ± 0% 3.176n ± 0% -0.09% (p=0.003 n=20) Mod 49.62n ± 0% 44.82n ± 0% -9.67% (p=0.000 n=20) Frexp 7.604n ± 0% 6.803n ± 0% -10.53% (p=0.000 n=20) Gamma 18.01n ± 0% 17.61n ± 0% -2.22% (p=0.000 n=20) Hypot 7.204n ± 0% 7.604n ± 0% +5.55% (p=0.000 n=20) HypotGo 7.204n ± 0% 7.604n ± 0% +5.56% (p=0.000 n=20) Ilogb 6.003n ± 0% 6.003n ± 0% ~ (p=0.407 n=20) J0 76.43n ± 0% 76.24n ± 0% -0.25% (p=0.000 n=20) J1 76.44n ± 0% 76.44n ± 0% ~ (p=1.000 n=20) Jn 168.2n ± 0% 168.5n ± 0% +0.18% (p=0.000 n=20) Ldexp 8.804n ± 0% 7.604n ± 0% -13.63% (p=0.000 n=20) Lgamma 19.01n ± 0% 19.01n ± 0% ~ (p=0.695 n=20) Log 19.38n ± 0% 19.12n ± 0% -1.34% (p=0.000 n=20) Logb 6.003n ± 0% 6.003n ± 0% ~ (p=1.000 n=20) Log1p 18.57n ± 0% 16.72n ± 0% -9.96% (p=0.000 n=20) Log10 20.67n ± 0% 20.45n ± 0% -1.06% (p=0.000 n=20) Log2 9.605n ± 0% 8.804n ± 0% -8.34% (p=0.000 n=20) Modf 4.402n ± 0% 4.402n ± 0% ~ (p=1.000 n=20) Nextafter32 7.204n ± 0% 5.603n ± 0% -22.22% (p=0.000 n=20) Nextafter64 6.803n ± 0% 6.003n ± 0% -11.76% (p=0.000 n=20) PowInt 39.62n ± 0% 37.22n ± 0% -6.06% (p=0.000 n=20) PowFrac 120.9n ± 0% 108.9n ± 0% -9.93% (p=0.000 n=20) Pow10Pos 1.601n ± 0% 1.601n ± 0% ~ (p=0.487 n=20) Pow10Neg 2.675n ± 0% 2.675n ± 0% ~ (p=1.000 n=20) Round 3.018n ± 0% 2.401n ± 0% -20.46% (p=0.000 n=20) RoundToEven 3.822n ± 0% 3.001n ± 0% -21.48% (p=0.000 n=20) Remainder 45.62n ± 0% 42.42n ± 0% -7.01% (p=0.000 n=20) Signbit 0.9075n ± 0% 0.8004n ± 0% -11.81% (p=0.000 n=20) Sin 12.65n ± 0% 12.65n ± 0% ~ (p=0.503 n=20) Sincos 14.81n ± 0% 14.60n ± 0% -1.42% (p=0.000 n=20) Sinh 36.75n ± 0% 35.11n ± 0% -4.46% (p=0.000 n=20) SqrtIndirect 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ SqrtLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtIndirectLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtGoLatency 52.85n ± 0% 40.82n ± 0% -22.76% (p=0.000 n=20) SqrtPrime 887.4n ± 0% 887.4n ± 0% ~ (p=0.751 n=20) Tan 13.95n ± 0% 13.97n ± 0% +0.18% (p=0.000 n=20) Tanh 36.79n ± 0% 34.89n ± 0% -5.16% (p=0.000 n=20) Trunc 2.849n ± 0% 2.861n ± 0% +0.42% (p=0.000 n=20) Y0 77.44n ± 0% 77.64n ± 0% +0.26% (p=0.000 n=20) Y1 74.41n ± 0% 74.33n ± 0% -0.11% (p=0.000 n=20) Yn 158.7n ± 0% 159.0n ± 0% +0.19% (p=0.000 n=20) Float64bits 0.8774n ± 0% 0.4002n ± 0% -54.39% (p=0.000 n=20) Float64frombits 0.8042n ± 0% 0.4002n ± 0% -50.24% (p=0.000 n=20) Float32bits 1.1230n ± 0% 0.5336n ± 0% -52.48% (p=0.000 n=20) Float32frombits 1.0670n ± 0% 0.8004n ± 0% -24.99% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.605 n=20) geomean 10.87n 10.10n -7.15% ¹ all samples are equal goos: linux goarch: loong64 pkg: math cpu: Loongson-3A5000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 33.10n ± 0% 31.95n ± 2% -3.46% (p=0.000 n=20) Acosh 58.38n ± 0% 50.44n ± 0% -13.60% (p=0.000 n=20) Asin 32.70n ± 0% 31.94n ± 0% -2.32% (p=0.000 n=20) Asinh 57.65n ± 0% 50.83n ± 0% -11.82% (p=0.000 n=20) Atan 14.21n ± 0% 14.21n ± 0% ~ (p=0.501 n=20) Atanh 60.86n ± 0% 54.44n ± 0% -10.56% (p=0.000 n=20) Atan2 32.02n ± 0% 34.02n ± 0% +6.25% (p=0.000 n=20) Cbrt 55.58n ± 0% 40.64n ± 0% -26.88% (p=0.000 n=20) Ceil 9.566n ± 0% 9.566n ± 0% ~ (p=0.463 n=20) Copysign 0.8005n ± 0% 0.8005n ± 0% ~ (p=0.806 n=20) Cos 18.02n ± 0% 18.02n ± 0% ~ (p=0.191 n=20) Cosh 64.44n ± 0% 65.64n ± 0% +1.86% (p=0.000 n=20) Erf 16.15n ± 0% 16.16n ± 0% ~ (p=0.770 n=20) Erfc 18.71n ± 0% 18.83n ± 0% +0.61% (p=0.000 n=20) Erfinv 19.33n ± 0% 19.34n ± 0% ~ (p=0.513 n=20) Erfcinv 18.90n ± 0% 19.78n ± 0% +4.63% (p=0.000 n=20) Exp 50.04n ± 0% 49.66n ± 0% -0.75% (p=0.000 n=20) ExpGo 50.03n ± 0% 50.03n ± 0% ~ (p=0.723 n=20) Expm1 28.41n ± 0% 28.27n ± 0% -0.49% (p=0.000 n=20) Exp2 50.08n ± 0% 51.23n ± 0% +2.31% (p=0.000 n=20) Exp2Go 49.77n ± 0% 49.89n ± 0% +0.24% (p=0.000 n=20) Abs 0.8009n ± 0% 0.8006n ± 0% ~ (p=0.317 n=20) Dim 1.987n ± 0% 1.993n ± 0% +0.28% (p=0.001 n=20) Floor 8.543n ± 0% 8.548n ± 0% ~ (p=0.509 n=20) Max 6.670n ± 0% 6.672n ± 0% ~ (p=0.335 n=20) Min 6.694n ± 0% 6.694n ± 0% ~ (p=0.459 n=20) Mod 56.44n ± 0% 53.23n ± 0% -5.70% (p=0.000 n=20) Frexp 8.409n ± 0% 7.606n ± 0% -9.55% (p=0.000 n=20) Gamma 35.64n ± 0% 35.23n ± 0% -1.15% (p=0.000 n=20) Hypot 11.21n ± 0% 10.61n ± 0% -5.31% (p=0.000 n=20) HypotGo 11.50n ± 0% 11.01n ± 0% -4.30% (p=0.000 n=20) Ilogb 7.606n ± 0% 6.804n ± 0% -10.54% (p=0.000 n=20) J0 125.3n ± 0% 126.5n ± 0% +0.96% (p=0.000 n=20) J1 124.9n ± 0% 125.3n ± 0% +0.32% (p=0.000 n=20) Jn 264.3n ± 0% 265.9n ± 0% +0.61% (p=0.000 n=20) Ldexp 9.606n ± 0% 9.204n ± 0% -4.19% (p=0.000 n=20) Lgamma 38.82n ± 0% 38.85n ± 0% +0.06% (p=0.019 n=20) Log 38.44n ± 0% 28.04n ± 0% -27.06% (p=0.000 n=20) Logb 8.405n ± 0% 7.605n ± 0% -9.52% (p=0.000 n=20) Log1p 31.62n ± 0% 27.11n ± 0% -14.26% (p=0.000 n=20) Log10 38.83n ± 0% 28.42n ± 0% -26.81% (p=0.000 n=20) Log2 11.21n ± 0% 10.41n ± 0% -7.14% (p=0.000 n=20) Modf 5.204n ± 0% 5.205n ± 0% ~ (p=0.983 n=20) Nextafter32 8.809n ± 0% 7.208n ± 0% -18.18% (p=0.000 n=20) Nextafter64 8.405n ± 0% 8.406n ± 0% +0.01% (p=0.007 n=20) PowInt 48.83n ± 0% 44.78n ± 0% -8.28% (p=0.000 n=20) PowFrac 146.9n ± 0% 142.1n ± 0% -3.23% (p=0.000 n=20) Pow10Pos 2.334n ± 0% 2.333n ± 0% ~ (p=0.110 n=20) Pow10Neg 4.803n ± 0% 4.803n ± 0% ~ (p=0.130 n=20) Round 4.816n ± 0% 3.819n ± 0% -20.70% (p=0.000 n=20) RoundToEven 5.735n ± 0% 5.204n ± 0% -9.26% (p=0.000 n=20) Remainder 52.05n ± 0% 49.64n ± 0% -4.63% (p=0.000 n=20) Signbit 1.201n ± 0% 1.001n ± 0% -16.65% (p=0.000 n=20) Sin 20.63n ± 0% 20.64n ± 0% +0.05% (p=0.040 n=20) Sincos 23.82n ± 0% 24.62n ± 0% +3.36% (p=0.000 n=20) Sinh 71.25n ± 0% 68.44n ± 0% -3.94% (p=0.000 n=20) SqrtIndirect 2.001n ± 0% 2.001n ± 0% ~ (p=0.182 n=20) SqrtLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.754 n=20) SqrtIndirectLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.773 n=20) SqrtGoLatency 60.84n ± 0% 81.26n ± 0% +33.56% (p=0.000 n=20) SqrtPrime 1.791µ ± 0% 1.791µ ± 0% ~ (p=0.784 n=20) Tan 27.22n ± 0% 27.22n ± 0% ~ (p=0.819 n=20) Tanh 70.88n ± 0% 69.04n ± 0% -2.60% (p=0.000 n=20) Trunc 8.543n ± 0% 8.543n ± 0% ~ (p=0.784 n=20) Y0 122.9n ± 0% 122.9n ± 0% ~ (p=0.559 n=20) Y1 123.3n ± 0% 121.7n ± 0% -1.30% (p=0.000 n=20) Yn 263.0n ± 0% 262.6n ± 0% -0.15% (p=0.000 n=20) Float64bits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float64frombits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float32bits 1.7010n ± 0% 0.8005n ± 0% -52.94% (p=0.000 n=20) Float32frombits 1.5010n ± 0% 0.8005n ± 0% -46.67% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.238 n=20) geomean 17.41n 16.15n -7.19% Change-Id: I0a0c263af2f07203eab1782e69c706f20c689d8d Reviewed-on: https://go-review.googlesource.com/c/go/+/604737 Auto-Submit: Tim King <taking@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Meidan Li <limeidan@loongson.cn> Reviewed-by: Tim King <taking@google.com> Reviewed-by: abner chenc <chenguoqi@loongson.cn>
2024-08-12 02:41:11 -06:00
// loong64:"MOVV\tF.*, R.*"
// ppc64x:"MFVSRD"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on mips64x This CL use MFC1/MTC1 instructions to move data between GPR and FPR instead of stores and loads to move float/int values. goos: linux goarch: mips64le pkg: math │ oldmath │ newmath │ │ sec/op │ sec/op vs base │ Acos-4 258.2n ± 0% 258.2n ± 0% ~ (p=0.859 n=8) Acosh-4 378.7n ± 0% 323.9n ± 0% -14.47% (p=0.000 n=8) Asin-4 255.1n ± 2% 255.5n ± 0% +0.16% (p=0.002 n=8) Asinh-4 407.1n ± 0% 348.7n ± 0% -14.35% (p=0.000 n=8) Atan-4 189.5n ± 0% 189.9n ± 3% ~ (p=0.205 n=8) Atanh-4 355.6n ± 0% 323.4n ± 2% -9.03% (p=0.000 n=8) Atan2-4 284.1n ± 7% 280.1n ± 4% ~ (p=0.313 n=8) Cbrt-4 314.3n ± 0% 236.4n ± 0% -24.79% (p=0.000 n=8) Ceil-4 144.3n ± 3% 139.6n ± 0% ~ (p=0.069 n=8) Compare-4 21.100n ± 0% 7.035n ± 0% -66.66% (p=0.000 n=8) Compare32-4 20.100n ± 0% 6.030n ± 0% -70.00% (p=0.000 n=8) Copysign-4 34.970n ± 0% 6.221n ± 0% -82.21% (p=0.000 n=8) Cos-4 183.4n ± 3% 184.1n ± 5% ~ (p=0.159 n=8) Cosh-4 487.9n ± 2% 419.6n ± 0% -14.00% (p=0.000 n=8) Erf-4 160.6n ± 0% 157.9n ± 0% -1.68% (p=0.009 n=8) Erfc-4 183.7n ± 4% 169.8n ± 0% -7.54% (p=0.000 n=8) Erfinv-4 191.5n ± 4% 183.6n ± 0% -4.13% (p=0.023 n=8) Erfcinv-4 192.0n ± 7% 184.3n ± 0% ~ (p=0.425 n=8) Exp-4 398.2n ± 0% 340.1n ± 4% -14.58% (p=0.000 n=8) ExpGo-4 383.3n ± 0% 327.3n ± 0% -14.62% (p=0.000 n=8) Expm1-4 248.7n ± 5% 216.0n ± 0% -13.11% (p=0.000 n=8) Exp2-4 372.8n ± 0% 316.9n ± 3% -14.98% (p=0.000 n=8) Exp2Go-4 374.1n ± 0% 320.5n ± 0% -14.33% (p=0.000 n=8) Abs-4 3.013n ± 0% 3.016n ± 0% +0.10% (p=0.020 n=8) Dim-4 5.021n ± 0% 5.022n ± 0% ~ (p=0.270 n=8) Floor-4 127.5n ± 4% 126.2n ± 3% ~ (p=0.186 n=8) Max-4 72.32n ± 0% 61.33n ± 0% -15.20% (p=0.000 n=8) Min-4 83.33n ± 1% 61.36n ± 0% -26.37% (p=0.000 n=8) Mod-4 690.7n ± 0% 454.5n ± 0% -34.20% (p=0.000 n=8) Frexp-4 116.30n ± 1% 71.80n ± 1% -38.26% (p=0.000 n=8) Gamma-4 389.0n ± 0% 355.9n ± 1% -8.48% (p=0.000 n=8) Hypot-4 102.40n ± 0% 83.90n ± 0% -18.07% (p=0.000 n=8) HypotGo-4 105.45n ± 4% 84.82n ± 2% -19.56% (p=0.000 n=8) Ilogb-4 99.13n ± 4% 63.71n ± 2% -35.73% (p=0.000 n=8) J0-4 859.7n ± 0% 854.8n ± 0% -0.57% (p=0.000 n=8) J1-4 873.9n ± 0% 875.7n ± 0% +0.21% (p=0.007 n=8) Jn-4 1.855µ ± 0% 1.867µ ± 0% +0.65% (p=0.000 n=8) Ldexp-4 130.50n ± 2% 64.35n ± 0% -50.69% (p=0.000 n=8) Lgamma-4 208.8n ± 0% 200.9n ± 0% -3.78% (p=0.000 n=8) Log-4 294.1n ± 0% 255.2n ± 3% -13.22% (p=0.000 n=8) Logb-4 105.45n ± 1% 66.81n ± 1% -36.64% (p=0.000 n=8) Log1p-4 268.2n ± 0% 211.3n ± 0% -21.21% (p=0.000 n=8) Log10-4 295.4n ± 0% 255.2n ± 2% -13.59% (p=0.000 n=8) Log2-4 152.9n ± 1% 127.5n ± 0% -16.61% (p=0.000 n=8) Modf-4 103.40n ± 0% 75.36n ± 0% -27.12% (p=0.000 n=8) Nextafter32-4 121.20n ± 1% 78.40n ± 0% -35.31% (p=0.000 n=8) Nextafter64-4 110.40n ± 1% 64.91n ± 0% -41.20% (p=0.000 n=8) PowInt-4 509.8n ± 1% 369.3n ± 1% -27.56% (p=0.000 n=8) PowFrac-4 1189.0n ± 0% 947.8n ± 0% -20.29% (p=0.000 n=8) Pow10Pos-4 15.07n ± 0% 15.07n ± 0% ~ (p=0.733 n=8) Pow10Neg-4 20.10n ± 0% 20.10n ± 0% ~ (p=0.576 n=8) Round-4 44.22n ± 0% 26.12n ± 0% -40.92% (p=0.000 n=8) RoundToEven-4 46.22n ± 0% 27.12n ± 0% -41.31% (p=0.000 n=8) Remainder-4 539.0n ± 1% 417.1n ± 1% -22.62% (p=0.000 n=8) Signbit-4 17.985n ± 0% 5.694n ± 0% -68.34% (p=0.000 n=8) Sin-4 185.7n ± 5% 172.9n ± 0% -6.89% (p=0.001 n=8) Sincos-4 176.6n ± 0% 200.9n ± 0% +13.76% (p=0.000 n=8) Sinh-4 495.8n ± 0% 435.9n ± 0% -12.09% (p=0.000 n=8) SqrtIndirect-4 5.022n ± 0% 5.024n ± 0% ~ (p=0.083 n=8) SqrtLatency-4 8.038n ± 0% 8.044n ± 0% ~ (p=0.524 n=8) SqrtIndirectLatency-4 8.035n ± 0% 8.039n ± 0% +0.06% (p=0.017 n=8) SqrtGoLatency-4 340.1n ± 0% 278.3n ± 0% -18.19% (p=0.000 n=8) SqrtPrime-4 5.381µ ± 0% 5.386µ ± 0% ~ (p=0.662 n=8) Tan-4 198.6n ± 1% 183.1n ± 0% -7.85% (p=0.000 n=8) Tanh-4 491.3n ± 1% 440.8n ± 1% -10.29% (p=0.000 n=8) Trunc-4 121.7n ± 0% 121.7n ± 0% ~ (p=0.769 n=8) Y0-4 855.1n ± 0% 859.8n ± 0% +0.54% (p=0.007 n=8) Y1-4 862.3n ± 0% 865.1n ± 0% +0.32% (p=0.007 n=8) Yn-4 1.830µ ± 0% 1.837µ ± 0% +0.36% (p=0.011 n=8) Float64bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float64frombits-4 13.060n ± 0% 3.018n ± 0% -76.90% (p=0.000 n=8) Float32bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float32frombits-4 13.070n ± 0% 3.013n ± 0% -76.94% (p=0.000 n=8) FMA-4 446.0n ± 0% 413.1n ± 1% -7.38% (p=0.000 n=8) geomean 143.4n 108.3n -24.49% Change-Id: I2067f7a5ae1126ada7ab3fb2083710e8212535e9 Reviewed-on: https://go-review.googlesource.com/c/go/+/493815 Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Keith Randall <khr@golang.org> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@google.com> Run-TryBot: Dmitri Shuralyov <dmitshur@golang.org>
2023-05-09 03:40:06 -06:00
// mips64/hardfloat:"MOVV\tF.*, R.*"
return math.Float64bits(f64+1) + 1
}
func fromFloat32(f32 float32) uint32 {
// amd64:"MOVL\tX.*, [^X].*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on arm64 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>
2018-07-15 22:45:25 -06:00
// arm64:"FMOVS\tF.*, R.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on loong64 Use float <-> int register moves without conversion instead of stores and loads to move float <-> int values like arm64 and mips64. goos: linux goarch: loong64 pkg: math cpu: Loongson-3A6000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 15.98n ± 0% 15.94n ± 0% -0.25% (p=0.000 n=20) Acosh 27.75n ± 0% 25.56n ± 0% -7.89% (p=0.000 n=20) Asin 15.85n ± 0% 15.76n ± 0% -0.57% (p=0.000 n=20) Asinh 39.79n ± 0% 37.69n ± 0% -5.28% (p=0.000 n=20) Atan 7.261n ± 0% 7.242n ± 0% -0.27% (p=0.000 n=20) Atanh 28.30n ± 0% 27.62n ± 0% -2.40% (p=0.000 n=20) Atan2 15.85n ± 0% 15.75n ± 0% -0.63% (p=0.000 n=20) Cbrt 27.02n ± 0% 21.08n ± 0% -21.98% (p=0.000 n=20) Ceil 2.830n ± 1% 2.896n ± 1% +2.31% (p=0.000 n=20) Copysign 0.8022n ± 0% 0.8004n ± 0% -0.22% (p=0.000 n=20) Cos 11.64n ± 0% 11.61n ± 0% -0.26% (p=0.000 n=20) Cosh 35.98n ± 0% 33.44n ± 0% -7.05% (p=0.000 n=20) Erf 10.09n ± 0% 10.08n ± 0% -0.10% (p=0.000 n=20) Erfc 11.40n ± 0% 11.35n ± 0% -0.44% (p=0.000 n=20) Erfinv 12.31n ± 0% 12.29n ± 0% -0.16% (p=0.000 n=20) Erfcinv 12.16n ± 0% 12.17n ± 0% +0.08% (p=0.000 n=20) Exp 28.41n ± 0% 26.44n ± 0% -6.95% (p=0.000 n=20) ExpGo 28.68n ± 0% 27.07n ± 0% -5.60% (p=0.000 n=20) Expm1 17.21n ± 0% 16.75n ± 0% -2.67% (p=0.000 n=20) Exp2 24.71n ± 0% 23.01n ± 0% -6.88% (p=0.000 n=20) Exp2Go 25.17n ± 0% 23.91n ± 0% -4.99% (p=0.000 n=20) Abs 0.8004n ± 0% 0.8004n ± 0% ~ (p=0.224 n=20) Dim 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ Floor 2.848n ± 0% 2.859n ± 0% +0.39% (p=0.000 n=20) Max 3.074n ± 0% 3.071n ± 0% ~ (p=0.481 n=20) Min 3.179n ± 0% 3.176n ± 0% -0.09% (p=0.003 n=20) Mod 49.62n ± 0% 44.82n ± 0% -9.67% (p=0.000 n=20) Frexp 7.604n ± 0% 6.803n ± 0% -10.53% (p=0.000 n=20) Gamma 18.01n ± 0% 17.61n ± 0% -2.22% (p=0.000 n=20) Hypot 7.204n ± 0% 7.604n ± 0% +5.55% (p=0.000 n=20) HypotGo 7.204n ± 0% 7.604n ± 0% +5.56% (p=0.000 n=20) Ilogb 6.003n ± 0% 6.003n ± 0% ~ (p=0.407 n=20) J0 76.43n ± 0% 76.24n ± 0% -0.25% (p=0.000 n=20) J1 76.44n ± 0% 76.44n ± 0% ~ (p=1.000 n=20) Jn 168.2n ± 0% 168.5n ± 0% +0.18% (p=0.000 n=20) Ldexp 8.804n ± 0% 7.604n ± 0% -13.63% (p=0.000 n=20) Lgamma 19.01n ± 0% 19.01n ± 0% ~ (p=0.695 n=20) Log 19.38n ± 0% 19.12n ± 0% -1.34% (p=0.000 n=20) Logb 6.003n ± 0% 6.003n ± 0% ~ (p=1.000 n=20) Log1p 18.57n ± 0% 16.72n ± 0% -9.96% (p=0.000 n=20) Log10 20.67n ± 0% 20.45n ± 0% -1.06% (p=0.000 n=20) Log2 9.605n ± 0% 8.804n ± 0% -8.34% (p=0.000 n=20) Modf 4.402n ± 0% 4.402n ± 0% ~ (p=1.000 n=20) Nextafter32 7.204n ± 0% 5.603n ± 0% -22.22% (p=0.000 n=20) Nextafter64 6.803n ± 0% 6.003n ± 0% -11.76% (p=0.000 n=20) PowInt 39.62n ± 0% 37.22n ± 0% -6.06% (p=0.000 n=20) PowFrac 120.9n ± 0% 108.9n ± 0% -9.93% (p=0.000 n=20) Pow10Pos 1.601n ± 0% 1.601n ± 0% ~ (p=0.487 n=20) Pow10Neg 2.675n ± 0% 2.675n ± 0% ~ (p=1.000 n=20) Round 3.018n ± 0% 2.401n ± 0% -20.46% (p=0.000 n=20) RoundToEven 3.822n ± 0% 3.001n ± 0% -21.48% (p=0.000 n=20) Remainder 45.62n ± 0% 42.42n ± 0% -7.01% (p=0.000 n=20) Signbit 0.9075n ± 0% 0.8004n ± 0% -11.81% (p=0.000 n=20) Sin 12.65n ± 0% 12.65n ± 0% ~ (p=0.503 n=20) Sincos 14.81n ± 0% 14.60n ± 0% -1.42% (p=0.000 n=20) Sinh 36.75n ± 0% 35.11n ± 0% -4.46% (p=0.000 n=20) SqrtIndirect 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ SqrtLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtIndirectLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtGoLatency 52.85n ± 0% 40.82n ± 0% -22.76% (p=0.000 n=20) SqrtPrime 887.4n ± 0% 887.4n ± 0% ~ (p=0.751 n=20) Tan 13.95n ± 0% 13.97n ± 0% +0.18% (p=0.000 n=20) Tanh 36.79n ± 0% 34.89n ± 0% -5.16% (p=0.000 n=20) Trunc 2.849n ± 0% 2.861n ± 0% +0.42% (p=0.000 n=20) Y0 77.44n ± 0% 77.64n ± 0% +0.26% (p=0.000 n=20) Y1 74.41n ± 0% 74.33n ± 0% -0.11% (p=0.000 n=20) Yn 158.7n ± 0% 159.0n ± 0% +0.19% (p=0.000 n=20) Float64bits 0.8774n ± 0% 0.4002n ± 0% -54.39% (p=0.000 n=20) Float64frombits 0.8042n ± 0% 0.4002n ± 0% -50.24% (p=0.000 n=20) Float32bits 1.1230n ± 0% 0.5336n ± 0% -52.48% (p=0.000 n=20) Float32frombits 1.0670n ± 0% 0.8004n ± 0% -24.99% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.605 n=20) geomean 10.87n 10.10n -7.15% ¹ all samples are equal goos: linux goarch: loong64 pkg: math cpu: Loongson-3A5000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 33.10n ± 0% 31.95n ± 2% -3.46% (p=0.000 n=20) Acosh 58.38n ± 0% 50.44n ± 0% -13.60% (p=0.000 n=20) Asin 32.70n ± 0% 31.94n ± 0% -2.32% (p=0.000 n=20) Asinh 57.65n ± 0% 50.83n ± 0% -11.82% (p=0.000 n=20) Atan 14.21n ± 0% 14.21n ± 0% ~ (p=0.501 n=20) Atanh 60.86n ± 0% 54.44n ± 0% -10.56% (p=0.000 n=20) Atan2 32.02n ± 0% 34.02n ± 0% +6.25% (p=0.000 n=20) Cbrt 55.58n ± 0% 40.64n ± 0% -26.88% (p=0.000 n=20) Ceil 9.566n ± 0% 9.566n ± 0% ~ (p=0.463 n=20) Copysign 0.8005n ± 0% 0.8005n ± 0% ~ (p=0.806 n=20) Cos 18.02n ± 0% 18.02n ± 0% ~ (p=0.191 n=20) Cosh 64.44n ± 0% 65.64n ± 0% +1.86% (p=0.000 n=20) Erf 16.15n ± 0% 16.16n ± 0% ~ (p=0.770 n=20) Erfc 18.71n ± 0% 18.83n ± 0% +0.61% (p=0.000 n=20) Erfinv 19.33n ± 0% 19.34n ± 0% ~ (p=0.513 n=20) Erfcinv 18.90n ± 0% 19.78n ± 0% +4.63% (p=0.000 n=20) Exp 50.04n ± 0% 49.66n ± 0% -0.75% (p=0.000 n=20) ExpGo 50.03n ± 0% 50.03n ± 0% ~ (p=0.723 n=20) Expm1 28.41n ± 0% 28.27n ± 0% -0.49% (p=0.000 n=20) Exp2 50.08n ± 0% 51.23n ± 0% +2.31% (p=0.000 n=20) Exp2Go 49.77n ± 0% 49.89n ± 0% +0.24% (p=0.000 n=20) Abs 0.8009n ± 0% 0.8006n ± 0% ~ (p=0.317 n=20) Dim 1.987n ± 0% 1.993n ± 0% +0.28% (p=0.001 n=20) Floor 8.543n ± 0% 8.548n ± 0% ~ (p=0.509 n=20) Max 6.670n ± 0% 6.672n ± 0% ~ (p=0.335 n=20) Min 6.694n ± 0% 6.694n ± 0% ~ (p=0.459 n=20) Mod 56.44n ± 0% 53.23n ± 0% -5.70% (p=0.000 n=20) Frexp 8.409n ± 0% 7.606n ± 0% -9.55% (p=0.000 n=20) Gamma 35.64n ± 0% 35.23n ± 0% -1.15% (p=0.000 n=20) Hypot 11.21n ± 0% 10.61n ± 0% -5.31% (p=0.000 n=20) HypotGo 11.50n ± 0% 11.01n ± 0% -4.30% (p=0.000 n=20) Ilogb 7.606n ± 0% 6.804n ± 0% -10.54% (p=0.000 n=20) J0 125.3n ± 0% 126.5n ± 0% +0.96% (p=0.000 n=20) J1 124.9n ± 0% 125.3n ± 0% +0.32% (p=0.000 n=20) Jn 264.3n ± 0% 265.9n ± 0% +0.61% (p=0.000 n=20) Ldexp 9.606n ± 0% 9.204n ± 0% -4.19% (p=0.000 n=20) Lgamma 38.82n ± 0% 38.85n ± 0% +0.06% (p=0.019 n=20) Log 38.44n ± 0% 28.04n ± 0% -27.06% (p=0.000 n=20) Logb 8.405n ± 0% 7.605n ± 0% -9.52% (p=0.000 n=20) Log1p 31.62n ± 0% 27.11n ± 0% -14.26% (p=0.000 n=20) Log10 38.83n ± 0% 28.42n ± 0% -26.81% (p=0.000 n=20) Log2 11.21n ± 0% 10.41n ± 0% -7.14% (p=0.000 n=20) Modf 5.204n ± 0% 5.205n ± 0% ~ (p=0.983 n=20) Nextafter32 8.809n ± 0% 7.208n ± 0% -18.18% (p=0.000 n=20) Nextafter64 8.405n ± 0% 8.406n ± 0% +0.01% (p=0.007 n=20) PowInt 48.83n ± 0% 44.78n ± 0% -8.28% (p=0.000 n=20) PowFrac 146.9n ± 0% 142.1n ± 0% -3.23% (p=0.000 n=20) Pow10Pos 2.334n ± 0% 2.333n ± 0% ~ (p=0.110 n=20) Pow10Neg 4.803n ± 0% 4.803n ± 0% ~ (p=0.130 n=20) Round 4.816n ± 0% 3.819n ± 0% -20.70% (p=0.000 n=20) RoundToEven 5.735n ± 0% 5.204n ± 0% -9.26% (p=0.000 n=20) Remainder 52.05n ± 0% 49.64n ± 0% -4.63% (p=0.000 n=20) Signbit 1.201n ± 0% 1.001n ± 0% -16.65% (p=0.000 n=20) Sin 20.63n ± 0% 20.64n ± 0% +0.05% (p=0.040 n=20) Sincos 23.82n ± 0% 24.62n ± 0% +3.36% (p=0.000 n=20) Sinh 71.25n ± 0% 68.44n ± 0% -3.94% (p=0.000 n=20) SqrtIndirect 2.001n ± 0% 2.001n ± 0% ~ (p=0.182 n=20) SqrtLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.754 n=20) SqrtIndirectLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.773 n=20) SqrtGoLatency 60.84n ± 0% 81.26n ± 0% +33.56% (p=0.000 n=20) SqrtPrime 1.791µ ± 0% 1.791µ ± 0% ~ (p=0.784 n=20) Tan 27.22n ± 0% 27.22n ± 0% ~ (p=0.819 n=20) Tanh 70.88n ± 0% 69.04n ± 0% -2.60% (p=0.000 n=20) Trunc 8.543n ± 0% 8.543n ± 0% ~ (p=0.784 n=20) Y0 122.9n ± 0% 122.9n ± 0% ~ (p=0.559 n=20) Y1 123.3n ± 0% 121.7n ± 0% -1.30% (p=0.000 n=20) Yn 263.0n ± 0% 262.6n ± 0% -0.15% (p=0.000 n=20) Float64bits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float64frombits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float32bits 1.7010n ± 0% 0.8005n ± 0% -52.94% (p=0.000 n=20) Float32frombits 1.5010n ± 0% 0.8005n ± 0% -46.67% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.238 n=20) geomean 17.41n 16.15n -7.19% Change-Id: I0a0c263af2f07203eab1782e69c706f20c689d8d Reviewed-on: https://go-review.googlesource.com/c/go/+/604737 Auto-Submit: Tim King <taking@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Meidan Li <limeidan@loongson.cn> Reviewed-by: Tim King <taking@google.com> Reviewed-by: abner chenc <chenguoqi@loongson.cn>
2024-08-12 02:41:11 -06:00
// loong64:"MOVW\tF.*, R.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on mips64x This CL use MFC1/MTC1 instructions to move data between GPR and FPR instead of stores and loads to move float/int values. goos: linux goarch: mips64le pkg: math │ oldmath │ newmath │ │ sec/op │ sec/op vs base │ Acos-4 258.2n ± 0% 258.2n ± 0% ~ (p=0.859 n=8) Acosh-4 378.7n ± 0% 323.9n ± 0% -14.47% (p=0.000 n=8) Asin-4 255.1n ± 2% 255.5n ± 0% +0.16% (p=0.002 n=8) Asinh-4 407.1n ± 0% 348.7n ± 0% -14.35% (p=0.000 n=8) Atan-4 189.5n ± 0% 189.9n ± 3% ~ (p=0.205 n=8) Atanh-4 355.6n ± 0% 323.4n ± 2% -9.03% (p=0.000 n=8) Atan2-4 284.1n ± 7% 280.1n ± 4% ~ (p=0.313 n=8) Cbrt-4 314.3n ± 0% 236.4n ± 0% -24.79% (p=0.000 n=8) Ceil-4 144.3n ± 3% 139.6n ± 0% ~ (p=0.069 n=8) Compare-4 21.100n ± 0% 7.035n ± 0% -66.66% (p=0.000 n=8) Compare32-4 20.100n ± 0% 6.030n ± 0% -70.00% (p=0.000 n=8) Copysign-4 34.970n ± 0% 6.221n ± 0% -82.21% (p=0.000 n=8) Cos-4 183.4n ± 3% 184.1n ± 5% ~ (p=0.159 n=8) Cosh-4 487.9n ± 2% 419.6n ± 0% -14.00% (p=0.000 n=8) Erf-4 160.6n ± 0% 157.9n ± 0% -1.68% (p=0.009 n=8) Erfc-4 183.7n ± 4% 169.8n ± 0% -7.54% (p=0.000 n=8) Erfinv-4 191.5n ± 4% 183.6n ± 0% -4.13% (p=0.023 n=8) Erfcinv-4 192.0n ± 7% 184.3n ± 0% ~ (p=0.425 n=8) Exp-4 398.2n ± 0% 340.1n ± 4% -14.58% (p=0.000 n=8) ExpGo-4 383.3n ± 0% 327.3n ± 0% -14.62% (p=0.000 n=8) Expm1-4 248.7n ± 5% 216.0n ± 0% -13.11% (p=0.000 n=8) Exp2-4 372.8n ± 0% 316.9n ± 3% -14.98% (p=0.000 n=8) Exp2Go-4 374.1n ± 0% 320.5n ± 0% -14.33% (p=0.000 n=8) Abs-4 3.013n ± 0% 3.016n ± 0% +0.10% (p=0.020 n=8) Dim-4 5.021n ± 0% 5.022n ± 0% ~ (p=0.270 n=8) Floor-4 127.5n ± 4% 126.2n ± 3% ~ (p=0.186 n=8) Max-4 72.32n ± 0% 61.33n ± 0% -15.20% (p=0.000 n=8) Min-4 83.33n ± 1% 61.36n ± 0% -26.37% (p=0.000 n=8) Mod-4 690.7n ± 0% 454.5n ± 0% -34.20% (p=0.000 n=8) Frexp-4 116.30n ± 1% 71.80n ± 1% -38.26% (p=0.000 n=8) Gamma-4 389.0n ± 0% 355.9n ± 1% -8.48% (p=0.000 n=8) Hypot-4 102.40n ± 0% 83.90n ± 0% -18.07% (p=0.000 n=8) HypotGo-4 105.45n ± 4% 84.82n ± 2% -19.56% (p=0.000 n=8) Ilogb-4 99.13n ± 4% 63.71n ± 2% -35.73% (p=0.000 n=8) J0-4 859.7n ± 0% 854.8n ± 0% -0.57% (p=0.000 n=8) J1-4 873.9n ± 0% 875.7n ± 0% +0.21% (p=0.007 n=8) Jn-4 1.855µ ± 0% 1.867µ ± 0% +0.65% (p=0.000 n=8) Ldexp-4 130.50n ± 2% 64.35n ± 0% -50.69% (p=0.000 n=8) Lgamma-4 208.8n ± 0% 200.9n ± 0% -3.78% (p=0.000 n=8) Log-4 294.1n ± 0% 255.2n ± 3% -13.22% (p=0.000 n=8) Logb-4 105.45n ± 1% 66.81n ± 1% -36.64% (p=0.000 n=8) Log1p-4 268.2n ± 0% 211.3n ± 0% -21.21% (p=0.000 n=8) Log10-4 295.4n ± 0% 255.2n ± 2% -13.59% (p=0.000 n=8) Log2-4 152.9n ± 1% 127.5n ± 0% -16.61% (p=0.000 n=8) Modf-4 103.40n ± 0% 75.36n ± 0% -27.12% (p=0.000 n=8) Nextafter32-4 121.20n ± 1% 78.40n ± 0% -35.31% (p=0.000 n=8) Nextafter64-4 110.40n ± 1% 64.91n ± 0% -41.20% (p=0.000 n=8) PowInt-4 509.8n ± 1% 369.3n ± 1% -27.56% (p=0.000 n=8) PowFrac-4 1189.0n ± 0% 947.8n ± 0% -20.29% (p=0.000 n=8) Pow10Pos-4 15.07n ± 0% 15.07n ± 0% ~ (p=0.733 n=8) Pow10Neg-4 20.10n ± 0% 20.10n ± 0% ~ (p=0.576 n=8) Round-4 44.22n ± 0% 26.12n ± 0% -40.92% (p=0.000 n=8) RoundToEven-4 46.22n ± 0% 27.12n ± 0% -41.31% (p=0.000 n=8) Remainder-4 539.0n ± 1% 417.1n ± 1% -22.62% (p=0.000 n=8) Signbit-4 17.985n ± 0% 5.694n ± 0% -68.34% (p=0.000 n=8) Sin-4 185.7n ± 5% 172.9n ± 0% -6.89% (p=0.001 n=8) Sincos-4 176.6n ± 0% 200.9n ± 0% +13.76% (p=0.000 n=8) Sinh-4 495.8n ± 0% 435.9n ± 0% -12.09% (p=0.000 n=8) SqrtIndirect-4 5.022n ± 0% 5.024n ± 0% ~ (p=0.083 n=8) SqrtLatency-4 8.038n ± 0% 8.044n ± 0% ~ (p=0.524 n=8) SqrtIndirectLatency-4 8.035n ± 0% 8.039n ± 0% +0.06% (p=0.017 n=8) SqrtGoLatency-4 340.1n ± 0% 278.3n ± 0% -18.19% (p=0.000 n=8) SqrtPrime-4 5.381µ ± 0% 5.386µ ± 0% ~ (p=0.662 n=8) Tan-4 198.6n ± 1% 183.1n ± 0% -7.85% (p=0.000 n=8) Tanh-4 491.3n ± 1% 440.8n ± 1% -10.29% (p=0.000 n=8) Trunc-4 121.7n ± 0% 121.7n ± 0% ~ (p=0.769 n=8) Y0-4 855.1n ± 0% 859.8n ± 0% +0.54% (p=0.007 n=8) Y1-4 862.3n ± 0% 865.1n ± 0% +0.32% (p=0.007 n=8) Yn-4 1.830µ ± 0% 1.837µ ± 0% +0.36% (p=0.011 n=8) Float64bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float64frombits-4 13.060n ± 0% 3.018n ± 0% -76.90% (p=0.000 n=8) Float32bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float32frombits-4 13.070n ± 0% 3.013n ± 0% -76.94% (p=0.000 n=8) FMA-4 446.0n ± 0% 413.1n ± 1% -7.38% (p=0.000 n=8) geomean 143.4n 108.3n -24.49% Change-Id: I2067f7a5ae1126ada7ab3fb2083710e8212535e9 Reviewed-on: https://go-review.googlesource.com/c/go/+/493815 Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Keith Randall <khr@golang.org> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@google.com> Run-TryBot: Dmitri Shuralyov <dmitshur@golang.org>
2023-05-09 03:40:06 -06:00
// mips64/hardfloat:"MOVW\tF.*, R.*"
return math.Float32bits(f32+1) + 1
}
func toFloat64(u64 uint64) float64 {
// amd64:"MOVQ\t[^X].*, X.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on arm64 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>
2018-07-15 22:45:25 -06:00
// arm64:"FMOVD\tR.*, F.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on loong64 Use float <-> int register moves without conversion instead of stores and loads to move float <-> int values like arm64 and mips64. goos: linux goarch: loong64 pkg: math cpu: Loongson-3A6000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 15.98n ± 0% 15.94n ± 0% -0.25% (p=0.000 n=20) Acosh 27.75n ± 0% 25.56n ± 0% -7.89% (p=0.000 n=20) Asin 15.85n ± 0% 15.76n ± 0% -0.57% (p=0.000 n=20) Asinh 39.79n ± 0% 37.69n ± 0% -5.28% (p=0.000 n=20) Atan 7.261n ± 0% 7.242n ± 0% -0.27% (p=0.000 n=20) Atanh 28.30n ± 0% 27.62n ± 0% -2.40% (p=0.000 n=20) Atan2 15.85n ± 0% 15.75n ± 0% -0.63% (p=0.000 n=20) Cbrt 27.02n ± 0% 21.08n ± 0% -21.98% (p=0.000 n=20) Ceil 2.830n ± 1% 2.896n ± 1% +2.31% (p=0.000 n=20) Copysign 0.8022n ± 0% 0.8004n ± 0% -0.22% (p=0.000 n=20) Cos 11.64n ± 0% 11.61n ± 0% -0.26% (p=0.000 n=20) Cosh 35.98n ± 0% 33.44n ± 0% -7.05% (p=0.000 n=20) Erf 10.09n ± 0% 10.08n ± 0% -0.10% (p=0.000 n=20) Erfc 11.40n ± 0% 11.35n ± 0% -0.44% (p=0.000 n=20) Erfinv 12.31n ± 0% 12.29n ± 0% -0.16% (p=0.000 n=20) Erfcinv 12.16n ± 0% 12.17n ± 0% +0.08% (p=0.000 n=20) Exp 28.41n ± 0% 26.44n ± 0% -6.95% (p=0.000 n=20) ExpGo 28.68n ± 0% 27.07n ± 0% -5.60% (p=0.000 n=20) Expm1 17.21n ± 0% 16.75n ± 0% -2.67% (p=0.000 n=20) Exp2 24.71n ± 0% 23.01n ± 0% -6.88% (p=0.000 n=20) Exp2Go 25.17n ± 0% 23.91n ± 0% -4.99% (p=0.000 n=20) Abs 0.8004n ± 0% 0.8004n ± 0% ~ (p=0.224 n=20) Dim 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ Floor 2.848n ± 0% 2.859n ± 0% +0.39% (p=0.000 n=20) Max 3.074n ± 0% 3.071n ± 0% ~ (p=0.481 n=20) Min 3.179n ± 0% 3.176n ± 0% -0.09% (p=0.003 n=20) Mod 49.62n ± 0% 44.82n ± 0% -9.67% (p=0.000 n=20) Frexp 7.604n ± 0% 6.803n ± 0% -10.53% (p=0.000 n=20) Gamma 18.01n ± 0% 17.61n ± 0% -2.22% (p=0.000 n=20) Hypot 7.204n ± 0% 7.604n ± 0% +5.55% (p=0.000 n=20) HypotGo 7.204n ± 0% 7.604n ± 0% +5.56% (p=0.000 n=20) Ilogb 6.003n ± 0% 6.003n ± 0% ~ (p=0.407 n=20) J0 76.43n ± 0% 76.24n ± 0% -0.25% (p=0.000 n=20) J1 76.44n ± 0% 76.44n ± 0% ~ (p=1.000 n=20) Jn 168.2n ± 0% 168.5n ± 0% +0.18% (p=0.000 n=20) Ldexp 8.804n ± 0% 7.604n ± 0% -13.63% (p=0.000 n=20) Lgamma 19.01n ± 0% 19.01n ± 0% ~ (p=0.695 n=20) Log 19.38n ± 0% 19.12n ± 0% -1.34% (p=0.000 n=20) Logb 6.003n ± 0% 6.003n ± 0% ~ (p=1.000 n=20) Log1p 18.57n ± 0% 16.72n ± 0% -9.96% (p=0.000 n=20) Log10 20.67n ± 0% 20.45n ± 0% -1.06% (p=0.000 n=20) Log2 9.605n ± 0% 8.804n ± 0% -8.34% (p=0.000 n=20) Modf 4.402n ± 0% 4.402n ± 0% ~ (p=1.000 n=20) Nextafter32 7.204n ± 0% 5.603n ± 0% -22.22% (p=0.000 n=20) Nextafter64 6.803n ± 0% 6.003n ± 0% -11.76% (p=0.000 n=20) PowInt 39.62n ± 0% 37.22n ± 0% -6.06% (p=0.000 n=20) PowFrac 120.9n ± 0% 108.9n ± 0% -9.93% (p=0.000 n=20) Pow10Pos 1.601n ± 0% 1.601n ± 0% ~ (p=0.487 n=20) Pow10Neg 2.675n ± 0% 2.675n ± 0% ~ (p=1.000 n=20) Round 3.018n ± 0% 2.401n ± 0% -20.46% (p=0.000 n=20) RoundToEven 3.822n ± 0% 3.001n ± 0% -21.48% (p=0.000 n=20) Remainder 45.62n ± 0% 42.42n ± 0% -7.01% (p=0.000 n=20) Signbit 0.9075n ± 0% 0.8004n ± 0% -11.81% (p=0.000 n=20) Sin 12.65n ± 0% 12.65n ± 0% ~ (p=0.503 n=20) Sincos 14.81n ± 0% 14.60n ± 0% -1.42% (p=0.000 n=20) Sinh 36.75n ± 0% 35.11n ± 0% -4.46% (p=0.000 n=20) SqrtIndirect 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ SqrtLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtIndirectLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtGoLatency 52.85n ± 0% 40.82n ± 0% -22.76% (p=0.000 n=20) SqrtPrime 887.4n ± 0% 887.4n ± 0% ~ (p=0.751 n=20) Tan 13.95n ± 0% 13.97n ± 0% +0.18% (p=0.000 n=20) Tanh 36.79n ± 0% 34.89n ± 0% -5.16% (p=0.000 n=20) Trunc 2.849n ± 0% 2.861n ± 0% +0.42% (p=0.000 n=20) Y0 77.44n ± 0% 77.64n ± 0% +0.26% (p=0.000 n=20) Y1 74.41n ± 0% 74.33n ± 0% -0.11% (p=0.000 n=20) Yn 158.7n ± 0% 159.0n ± 0% +0.19% (p=0.000 n=20) Float64bits 0.8774n ± 0% 0.4002n ± 0% -54.39% (p=0.000 n=20) Float64frombits 0.8042n ± 0% 0.4002n ± 0% -50.24% (p=0.000 n=20) Float32bits 1.1230n ± 0% 0.5336n ± 0% -52.48% (p=0.000 n=20) Float32frombits 1.0670n ± 0% 0.8004n ± 0% -24.99% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.605 n=20) geomean 10.87n 10.10n -7.15% ¹ all samples are equal goos: linux goarch: loong64 pkg: math cpu: Loongson-3A5000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 33.10n ± 0% 31.95n ± 2% -3.46% (p=0.000 n=20) Acosh 58.38n ± 0% 50.44n ± 0% -13.60% (p=0.000 n=20) Asin 32.70n ± 0% 31.94n ± 0% -2.32% (p=0.000 n=20) Asinh 57.65n ± 0% 50.83n ± 0% -11.82% (p=0.000 n=20) Atan 14.21n ± 0% 14.21n ± 0% ~ (p=0.501 n=20) Atanh 60.86n ± 0% 54.44n ± 0% -10.56% (p=0.000 n=20) Atan2 32.02n ± 0% 34.02n ± 0% +6.25% (p=0.000 n=20) Cbrt 55.58n ± 0% 40.64n ± 0% -26.88% (p=0.000 n=20) Ceil 9.566n ± 0% 9.566n ± 0% ~ (p=0.463 n=20) Copysign 0.8005n ± 0% 0.8005n ± 0% ~ (p=0.806 n=20) Cos 18.02n ± 0% 18.02n ± 0% ~ (p=0.191 n=20) Cosh 64.44n ± 0% 65.64n ± 0% +1.86% (p=0.000 n=20) Erf 16.15n ± 0% 16.16n ± 0% ~ (p=0.770 n=20) Erfc 18.71n ± 0% 18.83n ± 0% +0.61% (p=0.000 n=20) Erfinv 19.33n ± 0% 19.34n ± 0% ~ (p=0.513 n=20) Erfcinv 18.90n ± 0% 19.78n ± 0% +4.63% (p=0.000 n=20) Exp 50.04n ± 0% 49.66n ± 0% -0.75% (p=0.000 n=20) ExpGo 50.03n ± 0% 50.03n ± 0% ~ (p=0.723 n=20) Expm1 28.41n ± 0% 28.27n ± 0% -0.49% (p=0.000 n=20) Exp2 50.08n ± 0% 51.23n ± 0% +2.31% (p=0.000 n=20) Exp2Go 49.77n ± 0% 49.89n ± 0% +0.24% (p=0.000 n=20) Abs 0.8009n ± 0% 0.8006n ± 0% ~ (p=0.317 n=20) Dim 1.987n ± 0% 1.993n ± 0% +0.28% (p=0.001 n=20) Floor 8.543n ± 0% 8.548n ± 0% ~ (p=0.509 n=20) Max 6.670n ± 0% 6.672n ± 0% ~ (p=0.335 n=20) Min 6.694n ± 0% 6.694n ± 0% ~ (p=0.459 n=20) Mod 56.44n ± 0% 53.23n ± 0% -5.70% (p=0.000 n=20) Frexp 8.409n ± 0% 7.606n ± 0% -9.55% (p=0.000 n=20) Gamma 35.64n ± 0% 35.23n ± 0% -1.15% (p=0.000 n=20) Hypot 11.21n ± 0% 10.61n ± 0% -5.31% (p=0.000 n=20) HypotGo 11.50n ± 0% 11.01n ± 0% -4.30% (p=0.000 n=20) Ilogb 7.606n ± 0% 6.804n ± 0% -10.54% (p=0.000 n=20) J0 125.3n ± 0% 126.5n ± 0% +0.96% (p=0.000 n=20) J1 124.9n ± 0% 125.3n ± 0% +0.32% (p=0.000 n=20) Jn 264.3n ± 0% 265.9n ± 0% +0.61% (p=0.000 n=20) Ldexp 9.606n ± 0% 9.204n ± 0% -4.19% (p=0.000 n=20) Lgamma 38.82n ± 0% 38.85n ± 0% +0.06% (p=0.019 n=20) Log 38.44n ± 0% 28.04n ± 0% -27.06% (p=0.000 n=20) Logb 8.405n ± 0% 7.605n ± 0% -9.52% (p=0.000 n=20) Log1p 31.62n ± 0% 27.11n ± 0% -14.26% (p=0.000 n=20) Log10 38.83n ± 0% 28.42n ± 0% -26.81% (p=0.000 n=20) Log2 11.21n ± 0% 10.41n ± 0% -7.14% (p=0.000 n=20) Modf 5.204n ± 0% 5.205n ± 0% ~ (p=0.983 n=20) Nextafter32 8.809n ± 0% 7.208n ± 0% -18.18% (p=0.000 n=20) Nextafter64 8.405n ± 0% 8.406n ± 0% +0.01% (p=0.007 n=20) PowInt 48.83n ± 0% 44.78n ± 0% -8.28% (p=0.000 n=20) PowFrac 146.9n ± 0% 142.1n ± 0% -3.23% (p=0.000 n=20) Pow10Pos 2.334n ± 0% 2.333n ± 0% ~ (p=0.110 n=20) Pow10Neg 4.803n ± 0% 4.803n ± 0% ~ (p=0.130 n=20) Round 4.816n ± 0% 3.819n ± 0% -20.70% (p=0.000 n=20) RoundToEven 5.735n ± 0% 5.204n ± 0% -9.26% (p=0.000 n=20) Remainder 52.05n ± 0% 49.64n ± 0% -4.63% (p=0.000 n=20) Signbit 1.201n ± 0% 1.001n ± 0% -16.65% (p=0.000 n=20) Sin 20.63n ± 0% 20.64n ± 0% +0.05% (p=0.040 n=20) Sincos 23.82n ± 0% 24.62n ± 0% +3.36% (p=0.000 n=20) Sinh 71.25n ± 0% 68.44n ± 0% -3.94% (p=0.000 n=20) SqrtIndirect 2.001n ± 0% 2.001n ± 0% ~ (p=0.182 n=20) SqrtLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.754 n=20) SqrtIndirectLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.773 n=20) SqrtGoLatency 60.84n ± 0% 81.26n ± 0% +33.56% (p=0.000 n=20) SqrtPrime 1.791µ ± 0% 1.791µ ± 0% ~ (p=0.784 n=20) Tan 27.22n ± 0% 27.22n ± 0% ~ (p=0.819 n=20) Tanh 70.88n ± 0% 69.04n ± 0% -2.60% (p=0.000 n=20) Trunc 8.543n ± 0% 8.543n ± 0% ~ (p=0.784 n=20) Y0 122.9n ± 0% 122.9n ± 0% ~ (p=0.559 n=20) Y1 123.3n ± 0% 121.7n ± 0% -1.30% (p=0.000 n=20) Yn 263.0n ± 0% 262.6n ± 0% -0.15% (p=0.000 n=20) Float64bits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float64frombits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float32bits 1.7010n ± 0% 0.8005n ± 0% -52.94% (p=0.000 n=20) Float32frombits 1.5010n ± 0% 0.8005n ± 0% -46.67% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.238 n=20) geomean 17.41n 16.15n -7.19% Change-Id: I0a0c263af2f07203eab1782e69c706f20c689d8d Reviewed-on: https://go-review.googlesource.com/c/go/+/604737 Auto-Submit: Tim King <taking@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Meidan Li <limeidan@loongson.cn> Reviewed-by: Tim King <taking@google.com> Reviewed-by: abner chenc <chenguoqi@loongson.cn>
2024-08-12 02:41:11 -06:00
// loong64:"MOVV\tR.*, F.*"
// ppc64x:"MTVSRD"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on mips64x This CL use MFC1/MTC1 instructions to move data between GPR and FPR instead of stores and loads to move float/int values. goos: linux goarch: mips64le pkg: math │ oldmath │ newmath │ │ sec/op │ sec/op vs base │ Acos-4 258.2n ± 0% 258.2n ± 0% ~ (p=0.859 n=8) Acosh-4 378.7n ± 0% 323.9n ± 0% -14.47% (p=0.000 n=8) Asin-4 255.1n ± 2% 255.5n ± 0% +0.16% (p=0.002 n=8) Asinh-4 407.1n ± 0% 348.7n ± 0% -14.35% (p=0.000 n=8) Atan-4 189.5n ± 0% 189.9n ± 3% ~ (p=0.205 n=8) Atanh-4 355.6n ± 0% 323.4n ± 2% -9.03% (p=0.000 n=8) Atan2-4 284.1n ± 7% 280.1n ± 4% ~ (p=0.313 n=8) Cbrt-4 314.3n ± 0% 236.4n ± 0% -24.79% (p=0.000 n=8) Ceil-4 144.3n ± 3% 139.6n ± 0% ~ (p=0.069 n=8) Compare-4 21.100n ± 0% 7.035n ± 0% -66.66% (p=0.000 n=8) Compare32-4 20.100n ± 0% 6.030n ± 0% -70.00% (p=0.000 n=8) Copysign-4 34.970n ± 0% 6.221n ± 0% -82.21% (p=0.000 n=8) Cos-4 183.4n ± 3% 184.1n ± 5% ~ (p=0.159 n=8) Cosh-4 487.9n ± 2% 419.6n ± 0% -14.00% (p=0.000 n=8) Erf-4 160.6n ± 0% 157.9n ± 0% -1.68% (p=0.009 n=8) Erfc-4 183.7n ± 4% 169.8n ± 0% -7.54% (p=0.000 n=8) Erfinv-4 191.5n ± 4% 183.6n ± 0% -4.13% (p=0.023 n=8) Erfcinv-4 192.0n ± 7% 184.3n ± 0% ~ (p=0.425 n=8) Exp-4 398.2n ± 0% 340.1n ± 4% -14.58% (p=0.000 n=8) ExpGo-4 383.3n ± 0% 327.3n ± 0% -14.62% (p=0.000 n=8) Expm1-4 248.7n ± 5% 216.0n ± 0% -13.11% (p=0.000 n=8) Exp2-4 372.8n ± 0% 316.9n ± 3% -14.98% (p=0.000 n=8) Exp2Go-4 374.1n ± 0% 320.5n ± 0% -14.33% (p=0.000 n=8) Abs-4 3.013n ± 0% 3.016n ± 0% +0.10% (p=0.020 n=8) Dim-4 5.021n ± 0% 5.022n ± 0% ~ (p=0.270 n=8) Floor-4 127.5n ± 4% 126.2n ± 3% ~ (p=0.186 n=8) Max-4 72.32n ± 0% 61.33n ± 0% -15.20% (p=0.000 n=8) Min-4 83.33n ± 1% 61.36n ± 0% -26.37% (p=0.000 n=8) Mod-4 690.7n ± 0% 454.5n ± 0% -34.20% (p=0.000 n=8) Frexp-4 116.30n ± 1% 71.80n ± 1% -38.26% (p=0.000 n=8) Gamma-4 389.0n ± 0% 355.9n ± 1% -8.48% (p=0.000 n=8) Hypot-4 102.40n ± 0% 83.90n ± 0% -18.07% (p=0.000 n=8) HypotGo-4 105.45n ± 4% 84.82n ± 2% -19.56% (p=0.000 n=8) Ilogb-4 99.13n ± 4% 63.71n ± 2% -35.73% (p=0.000 n=8) J0-4 859.7n ± 0% 854.8n ± 0% -0.57% (p=0.000 n=8) J1-4 873.9n ± 0% 875.7n ± 0% +0.21% (p=0.007 n=8) Jn-4 1.855µ ± 0% 1.867µ ± 0% +0.65% (p=0.000 n=8) Ldexp-4 130.50n ± 2% 64.35n ± 0% -50.69% (p=0.000 n=8) Lgamma-4 208.8n ± 0% 200.9n ± 0% -3.78% (p=0.000 n=8) Log-4 294.1n ± 0% 255.2n ± 3% -13.22% (p=0.000 n=8) Logb-4 105.45n ± 1% 66.81n ± 1% -36.64% (p=0.000 n=8) Log1p-4 268.2n ± 0% 211.3n ± 0% -21.21% (p=0.000 n=8) Log10-4 295.4n ± 0% 255.2n ± 2% -13.59% (p=0.000 n=8) Log2-4 152.9n ± 1% 127.5n ± 0% -16.61% (p=0.000 n=8) Modf-4 103.40n ± 0% 75.36n ± 0% -27.12% (p=0.000 n=8) Nextafter32-4 121.20n ± 1% 78.40n ± 0% -35.31% (p=0.000 n=8) Nextafter64-4 110.40n ± 1% 64.91n ± 0% -41.20% (p=0.000 n=8) PowInt-4 509.8n ± 1% 369.3n ± 1% -27.56% (p=0.000 n=8) PowFrac-4 1189.0n ± 0% 947.8n ± 0% -20.29% (p=0.000 n=8) Pow10Pos-4 15.07n ± 0% 15.07n ± 0% ~ (p=0.733 n=8) Pow10Neg-4 20.10n ± 0% 20.10n ± 0% ~ (p=0.576 n=8) Round-4 44.22n ± 0% 26.12n ± 0% -40.92% (p=0.000 n=8) RoundToEven-4 46.22n ± 0% 27.12n ± 0% -41.31% (p=0.000 n=8) Remainder-4 539.0n ± 1% 417.1n ± 1% -22.62% (p=0.000 n=8) Signbit-4 17.985n ± 0% 5.694n ± 0% -68.34% (p=0.000 n=8) Sin-4 185.7n ± 5% 172.9n ± 0% -6.89% (p=0.001 n=8) Sincos-4 176.6n ± 0% 200.9n ± 0% +13.76% (p=0.000 n=8) Sinh-4 495.8n ± 0% 435.9n ± 0% -12.09% (p=0.000 n=8) SqrtIndirect-4 5.022n ± 0% 5.024n ± 0% ~ (p=0.083 n=8) SqrtLatency-4 8.038n ± 0% 8.044n ± 0% ~ (p=0.524 n=8) SqrtIndirectLatency-4 8.035n ± 0% 8.039n ± 0% +0.06% (p=0.017 n=8) SqrtGoLatency-4 340.1n ± 0% 278.3n ± 0% -18.19% (p=0.000 n=8) SqrtPrime-4 5.381µ ± 0% 5.386µ ± 0% ~ (p=0.662 n=8) Tan-4 198.6n ± 1% 183.1n ± 0% -7.85% (p=0.000 n=8) Tanh-4 491.3n ± 1% 440.8n ± 1% -10.29% (p=0.000 n=8) Trunc-4 121.7n ± 0% 121.7n ± 0% ~ (p=0.769 n=8) Y0-4 855.1n ± 0% 859.8n ± 0% +0.54% (p=0.007 n=8) Y1-4 862.3n ± 0% 865.1n ± 0% +0.32% (p=0.007 n=8) Yn-4 1.830µ ± 0% 1.837µ ± 0% +0.36% (p=0.011 n=8) Float64bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float64frombits-4 13.060n ± 0% 3.018n ± 0% -76.90% (p=0.000 n=8) Float32bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float32frombits-4 13.070n ± 0% 3.013n ± 0% -76.94% (p=0.000 n=8) FMA-4 446.0n ± 0% 413.1n ± 1% -7.38% (p=0.000 n=8) geomean 143.4n 108.3n -24.49% Change-Id: I2067f7a5ae1126ada7ab3fb2083710e8212535e9 Reviewed-on: https://go-review.googlesource.com/c/go/+/493815 Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Keith Randall <khr@golang.org> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@google.com> Run-TryBot: Dmitri Shuralyov <dmitshur@golang.org>
2023-05-09 03:40:06 -06:00
// mips64/hardfloat:"MOVV\tR.*, F.*"
return math.Float64frombits(u64+1) + 1
}
func toFloat32(u32 uint32) float32 {
// amd64:"MOVL\t[^X].*, X.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on arm64 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>
2018-07-15 22:45:25 -06:00
// arm64:"FMOVS\tR.*, F.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on loong64 Use float <-> int register moves without conversion instead of stores and loads to move float <-> int values like arm64 and mips64. goos: linux goarch: loong64 pkg: math cpu: Loongson-3A6000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 15.98n ± 0% 15.94n ± 0% -0.25% (p=0.000 n=20) Acosh 27.75n ± 0% 25.56n ± 0% -7.89% (p=0.000 n=20) Asin 15.85n ± 0% 15.76n ± 0% -0.57% (p=0.000 n=20) Asinh 39.79n ± 0% 37.69n ± 0% -5.28% (p=0.000 n=20) Atan 7.261n ± 0% 7.242n ± 0% -0.27% (p=0.000 n=20) Atanh 28.30n ± 0% 27.62n ± 0% -2.40% (p=0.000 n=20) Atan2 15.85n ± 0% 15.75n ± 0% -0.63% (p=0.000 n=20) Cbrt 27.02n ± 0% 21.08n ± 0% -21.98% (p=0.000 n=20) Ceil 2.830n ± 1% 2.896n ± 1% +2.31% (p=0.000 n=20) Copysign 0.8022n ± 0% 0.8004n ± 0% -0.22% (p=0.000 n=20) Cos 11.64n ± 0% 11.61n ± 0% -0.26% (p=0.000 n=20) Cosh 35.98n ± 0% 33.44n ± 0% -7.05% (p=0.000 n=20) Erf 10.09n ± 0% 10.08n ± 0% -0.10% (p=0.000 n=20) Erfc 11.40n ± 0% 11.35n ± 0% -0.44% (p=0.000 n=20) Erfinv 12.31n ± 0% 12.29n ± 0% -0.16% (p=0.000 n=20) Erfcinv 12.16n ± 0% 12.17n ± 0% +0.08% (p=0.000 n=20) Exp 28.41n ± 0% 26.44n ± 0% -6.95% (p=0.000 n=20) ExpGo 28.68n ± 0% 27.07n ± 0% -5.60% (p=0.000 n=20) Expm1 17.21n ± 0% 16.75n ± 0% -2.67% (p=0.000 n=20) Exp2 24.71n ± 0% 23.01n ± 0% -6.88% (p=0.000 n=20) Exp2Go 25.17n ± 0% 23.91n ± 0% -4.99% (p=0.000 n=20) Abs 0.8004n ± 0% 0.8004n ± 0% ~ (p=0.224 n=20) Dim 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ Floor 2.848n ± 0% 2.859n ± 0% +0.39% (p=0.000 n=20) Max 3.074n ± 0% 3.071n ± 0% ~ (p=0.481 n=20) Min 3.179n ± 0% 3.176n ± 0% -0.09% (p=0.003 n=20) Mod 49.62n ± 0% 44.82n ± 0% -9.67% (p=0.000 n=20) Frexp 7.604n ± 0% 6.803n ± 0% -10.53% (p=0.000 n=20) Gamma 18.01n ± 0% 17.61n ± 0% -2.22% (p=0.000 n=20) Hypot 7.204n ± 0% 7.604n ± 0% +5.55% (p=0.000 n=20) HypotGo 7.204n ± 0% 7.604n ± 0% +5.56% (p=0.000 n=20) Ilogb 6.003n ± 0% 6.003n ± 0% ~ (p=0.407 n=20) J0 76.43n ± 0% 76.24n ± 0% -0.25% (p=0.000 n=20) J1 76.44n ± 0% 76.44n ± 0% ~ (p=1.000 n=20) Jn 168.2n ± 0% 168.5n ± 0% +0.18% (p=0.000 n=20) Ldexp 8.804n ± 0% 7.604n ± 0% -13.63% (p=0.000 n=20) Lgamma 19.01n ± 0% 19.01n ± 0% ~ (p=0.695 n=20) Log 19.38n ± 0% 19.12n ± 0% -1.34% (p=0.000 n=20) Logb 6.003n ± 0% 6.003n ± 0% ~ (p=1.000 n=20) Log1p 18.57n ± 0% 16.72n ± 0% -9.96% (p=0.000 n=20) Log10 20.67n ± 0% 20.45n ± 0% -1.06% (p=0.000 n=20) Log2 9.605n ± 0% 8.804n ± 0% -8.34% (p=0.000 n=20) Modf 4.402n ± 0% 4.402n ± 0% ~ (p=1.000 n=20) Nextafter32 7.204n ± 0% 5.603n ± 0% -22.22% (p=0.000 n=20) Nextafter64 6.803n ± 0% 6.003n ± 0% -11.76% (p=0.000 n=20) PowInt 39.62n ± 0% 37.22n ± 0% -6.06% (p=0.000 n=20) PowFrac 120.9n ± 0% 108.9n ± 0% -9.93% (p=0.000 n=20) Pow10Pos 1.601n ± 0% 1.601n ± 0% ~ (p=0.487 n=20) Pow10Neg 2.675n ± 0% 2.675n ± 0% ~ (p=1.000 n=20) Round 3.018n ± 0% 2.401n ± 0% -20.46% (p=0.000 n=20) RoundToEven 3.822n ± 0% 3.001n ± 0% -21.48% (p=0.000 n=20) Remainder 45.62n ± 0% 42.42n ± 0% -7.01% (p=0.000 n=20) Signbit 0.9075n ± 0% 0.8004n ± 0% -11.81% (p=0.000 n=20) Sin 12.65n ± 0% 12.65n ± 0% ~ (p=0.503 n=20) Sincos 14.81n ± 0% 14.60n ± 0% -1.42% (p=0.000 n=20) Sinh 36.75n ± 0% 35.11n ± 0% -4.46% (p=0.000 n=20) SqrtIndirect 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ SqrtLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtIndirectLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtGoLatency 52.85n ± 0% 40.82n ± 0% -22.76% (p=0.000 n=20) SqrtPrime 887.4n ± 0% 887.4n ± 0% ~ (p=0.751 n=20) Tan 13.95n ± 0% 13.97n ± 0% +0.18% (p=0.000 n=20) Tanh 36.79n ± 0% 34.89n ± 0% -5.16% (p=0.000 n=20) Trunc 2.849n ± 0% 2.861n ± 0% +0.42% (p=0.000 n=20) Y0 77.44n ± 0% 77.64n ± 0% +0.26% (p=0.000 n=20) Y1 74.41n ± 0% 74.33n ± 0% -0.11% (p=0.000 n=20) Yn 158.7n ± 0% 159.0n ± 0% +0.19% (p=0.000 n=20) Float64bits 0.8774n ± 0% 0.4002n ± 0% -54.39% (p=0.000 n=20) Float64frombits 0.8042n ± 0% 0.4002n ± 0% -50.24% (p=0.000 n=20) Float32bits 1.1230n ± 0% 0.5336n ± 0% -52.48% (p=0.000 n=20) Float32frombits 1.0670n ± 0% 0.8004n ± 0% -24.99% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.605 n=20) geomean 10.87n 10.10n -7.15% ¹ all samples are equal goos: linux goarch: loong64 pkg: math cpu: Loongson-3A5000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 33.10n ± 0% 31.95n ± 2% -3.46% (p=0.000 n=20) Acosh 58.38n ± 0% 50.44n ± 0% -13.60% (p=0.000 n=20) Asin 32.70n ± 0% 31.94n ± 0% -2.32% (p=0.000 n=20) Asinh 57.65n ± 0% 50.83n ± 0% -11.82% (p=0.000 n=20) Atan 14.21n ± 0% 14.21n ± 0% ~ (p=0.501 n=20) Atanh 60.86n ± 0% 54.44n ± 0% -10.56% (p=0.000 n=20) Atan2 32.02n ± 0% 34.02n ± 0% +6.25% (p=0.000 n=20) Cbrt 55.58n ± 0% 40.64n ± 0% -26.88% (p=0.000 n=20) Ceil 9.566n ± 0% 9.566n ± 0% ~ (p=0.463 n=20) Copysign 0.8005n ± 0% 0.8005n ± 0% ~ (p=0.806 n=20) Cos 18.02n ± 0% 18.02n ± 0% ~ (p=0.191 n=20) Cosh 64.44n ± 0% 65.64n ± 0% +1.86% (p=0.000 n=20) Erf 16.15n ± 0% 16.16n ± 0% ~ (p=0.770 n=20) Erfc 18.71n ± 0% 18.83n ± 0% +0.61% (p=0.000 n=20) Erfinv 19.33n ± 0% 19.34n ± 0% ~ (p=0.513 n=20) Erfcinv 18.90n ± 0% 19.78n ± 0% +4.63% (p=0.000 n=20) Exp 50.04n ± 0% 49.66n ± 0% -0.75% (p=0.000 n=20) ExpGo 50.03n ± 0% 50.03n ± 0% ~ (p=0.723 n=20) Expm1 28.41n ± 0% 28.27n ± 0% -0.49% (p=0.000 n=20) Exp2 50.08n ± 0% 51.23n ± 0% +2.31% (p=0.000 n=20) Exp2Go 49.77n ± 0% 49.89n ± 0% +0.24% (p=0.000 n=20) Abs 0.8009n ± 0% 0.8006n ± 0% ~ (p=0.317 n=20) Dim 1.987n ± 0% 1.993n ± 0% +0.28% (p=0.001 n=20) Floor 8.543n ± 0% 8.548n ± 0% ~ (p=0.509 n=20) Max 6.670n ± 0% 6.672n ± 0% ~ (p=0.335 n=20) Min 6.694n ± 0% 6.694n ± 0% ~ (p=0.459 n=20) Mod 56.44n ± 0% 53.23n ± 0% -5.70% (p=0.000 n=20) Frexp 8.409n ± 0% 7.606n ± 0% -9.55% (p=0.000 n=20) Gamma 35.64n ± 0% 35.23n ± 0% -1.15% (p=0.000 n=20) Hypot 11.21n ± 0% 10.61n ± 0% -5.31% (p=0.000 n=20) HypotGo 11.50n ± 0% 11.01n ± 0% -4.30% (p=0.000 n=20) Ilogb 7.606n ± 0% 6.804n ± 0% -10.54% (p=0.000 n=20) J0 125.3n ± 0% 126.5n ± 0% +0.96% (p=0.000 n=20) J1 124.9n ± 0% 125.3n ± 0% +0.32% (p=0.000 n=20) Jn 264.3n ± 0% 265.9n ± 0% +0.61% (p=0.000 n=20) Ldexp 9.606n ± 0% 9.204n ± 0% -4.19% (p=0.000 n=20) Lgamma 38.82n ± 0% 38.85n ± 0% +0.06% (p=0.019 n=20) Log 38.44n ± 0% 28.04n ± 0% -27.06% (p=0.000 n=20) Logb 8.405n ± 0% 7.605n ± 0% -9.52% (p=0.000 n=20) Log1p 31.62n ± 0% 27.11n ± 0% -14.26% (p=0.000 n=20) Log10 38.83n ± 0% 28.42n ± 0% -26.81% (p=0.000 n=20) Log2 11.21n ± 0% 10.41n ± 0% -7.14% (p=0.000 n=20) Modf 5.204n ± 0% 5.205n ± 0% ~ (p=0.983 n=20) Nextafter32 8.809n ± 0% 7.208n ± 0% -18.18% (p=0.000 n=20) Nextafter64 8.405n ± 0% 8.406n ± 0% +0.01% (p=0.007 n=20) PowInt 48.83n ± 0% 44.78n ± 0% -8.28% (p=0.000 n=20) PowFrac 146.9n ± 0% 142.1n ± 0% -3.23% (p=0.000 n=20) Pow10Pos 2.334n ± 0% 2.333n ± 0% ~ (p=0.110 n=20) Pow10Neg 4.803n ± 0% 4.803n ± 0% ~ (p=0.130 n=20) Round 4.816n ± 0% 3.819n ± 0% -20.70% (p=0.000 n=20) RoundToEven 5.735n ± 0% 5.204n ± 0% -9.26% (p=0.000 n=20) Remainder 52.05n ± 0% 49.64n ± 0% -4.63% (p=0.000 n=20) Signbit 1.201n ± 0% 1.001n ± 0% -16.65% (p=0.000 n=20) Sin 20.63n ± 0% 20.64n ± 0% +0.05% (p=0.040 n=20) Sincos 23.82n ± 0% 24.62n ± 0% +3.36% (p=0.000 n=20) Sinh 71.25n ± 0% 68.44n ± 0% -3.94% (p=0.000 n=20) SqrtIndirect 2.001n ± 0% 2.001n ± 0% ~ (p=0.182 n=20) SqrtLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.754 n=20) SqrtIndirectLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.773 n=20) SqrtGoLatency 60.84n ± 0% 81.26n ± 0% +33.56% (p=0.000 n=20) SqrtPrime 1.791µ ± 0% 1.791µ ± 0% ~ (p=0.784 n=20) Tan 27.22n ± 0% 27.22n ± 0% ~ (p=0.819 n=20) Tanh 70.88n ± 0% 69.04n ± 0% -2.60% (p=0.000 n=20) Trunc 8.543n ± 0% 8.543n ± 0% ~ (p=0.784 n=20) Y0 122.9n ± 0% 122.9n ± 0% ~ (p=0.559 n=20) Y1 123.3n ± 0% 121.7n ± 0% -1.30% (p=0.000 n=20) Yn 263.0n ± 0% 262.6n ± 0% -0.15% (p=0.000 n=20) Float64bits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float64frombits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float32bits 1.7010n ± 0% 0.8005n ± 0% -52.94% (p=0.000 n=20) Float32frombits 1.5010n ± 0% 0.8005n ± 0% -46.67% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.238 n=20) geomean 17.41n 16.15n -7.19% Change-Id: I0a0c263af2f07203eab1782e69c706f20c689d8d Reviewed-on: https://go-review.googlesource.com/c/go/+/604737 Auto-Submit: Tim King <taking@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Meidan Li <limeidan@loongson.cn> Reviewed-by: Tim King <taking@google.com> Reviewed-by: abner chenc <chenguoqi@loongson.cn>
2024-08-12 02:41:11 -06:00
// loong64:"MOVW\tR.*, F.*"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on mips64x This CL use MFC1/MTC1 instructions to move data between GPR and FPR instead of stores and loads to move float/int values. goos: linux goarch: mips64le pkg: math │ oldmath │ newmath │ │ sec/op │ sec/op vs base │ Acos-4 258.2n ± 0% 258.2n ± 0% ~ (p=0.859 n=8) Acosh-4 378.7n ± 0% 323.9n ± 0% -14.47% (p=0.000 n=8) Asin-4 255.1n ± 2% 255.5n ± 0% +0.16% (p=0.002 n=8) Asinh-4 407.1n ± 0% 348.7n ± 0% -14.35% (p=0.000 n=8) Atan-4 189.5n ± 0% 189.9n ± 3% ~ (p=0.205 n=8) Atanh-4 355.6n ± 0% 323.4n ± 2% -9.03% (p=0.000 n=8) Atan2-4 284.1n ± 7% 280.1n ± 4% ~ (p=0.313 n=8) Cbrt-4 314.3n ± 0% 236.4n ± 0% -24.79% (p=0.000 n=8) Ceil-4 144.3n ± 3% 139.6n ± 0% ~ (p=0.069 n=8) Compare-4 21.100n ± 0% 7.035n ± 0% -66.66% (p=0.000 n=8) Compare32-4 20.100n ± 0% 6.030n ± 0% -70.00% (p=0.000 n=8) Copysign-4 34.970n ± 0% 6.221n ± 0% -82.21% (p=0.000 n=8) Cos-4 183.4n ± 3% 184.1n ± 5% ~ (p=0.159 n=8) Cosh-4 487.9n ± 2% 419.6n ± 0% -14.00% (p=0.000 n=8) Erf-4 160.6n ± 0% 157.9n ± 0% -1.68% (p=0.009 n=8) Erfc-4 183.7n ± 4% 169.8n ± 0% -7.54% (p=0.000 n=8) Erfinv-4 191.5n ± 4% 183.6n ± 0% -4.13% (p=0.023 n=8) Erfcinv-4 192.0n ± 7% 184.3n ± 0% ~ (p=0.425 n=8) Exp-4 398.2n ± 0% 340.1n ± 4% -14.58% (p=0.000 n=8) ExpGo-4 383.3n ± 0% 327.3n ± 0% -14.62% (p=0.000 n=8) Expm1-4 248.7n ± 5% 216.0n ± 0% -13.11% (p=0.000 n=8) Exp2-4 372.8n ± 0% 316.9n ± 3% -14.98% (p=0.000 n=8) Exp2Go-4 374.1n ± 0% 320.5n ± 0% -14.33% (p=0.000 n=8) Abs-4 3.013n ± 0% 3.016n ± 0% +0.10% (p=0.020 n=8) Dim-4 5.021n ± 0% 5.022n ± 0% ~ (p=0.270 n=8) Floor-4 127.5n ± 4% 126.2n ± 3% ~ (p=0.186 n=8) Max-4 72.32n ± 0% 61.33n ± 0% -15.20% (p=0.000 n=8) Min-4 83.33n ± 1% 61.36n ± 0% -26.37% (p=0.000 n=8) Mod-4 690.7n ± 0% 454.5n ± 0% -34.20% (p=0.000 n=8) Frexp-4 116.30n ± 1% 71.80n ± 1% -38.26% (p=0.000 n=8) Gamma-4 389.0n ± 0% 355.9n ± 1% -8.48% (p=0.000 n=8) Hypot-4 102.40n ± 0% 83.90n ± 0% -18.07% (p=0.000 n=8) HypotGo-4 105.45n ± 4% 84.82n ± 2% -19.56% (p=0.000 n=8) Ilogb-4 99.13n ± 4% 63.71n ± 2% -35.73% (p=0.000 n=8) J0-4 859.7n ± 0% 854.8n ± 0% -0.57% (p=0.000 n=8) J1-4 873.9n ± 0% 875.7n ± 0% +0.21% (p=0.007 n=8) Jn-4 1.855µ ± 0% 1.867µ ± 0% +0.65% (p=0.000 n=8) Ldexp-4 130.50n ± 2% 64.35n ± 0% -50.69% (p=0.000 n=8) Lgamma-4 208.8n ± 0% 200.9n ± 0% -3.78% (p=0.000 n=8) Log-4 294.1n ± 0% 255.2n ± 3% -13.22% (p=0.000 n=8) Logb-4 105.45n ± 1% 66.81n ± 1% -36.64% (p=0.000 n=8) Log1p-4 268.2n ± 0% 211.3n ± 0% -21.21% (p=0.000 n=8) Log10-4 295.4n ± 0% 255.2n ± 2% -13.59% (p=0.000 n=8) Log2-4 152.9n ± 1% 127.5n ± 0% -16.61% (p=0.000 n=8) Modf-4 103.40n ± 0% 75.36n ± 0% -27.12% (p=0.000 n=8) Nextafter32-4 121.20n ± 1% 78.40n ± 0% -35.31% (p=0.000 n=8) Nextafter64-4 110.40n ± 1% 64.91n ± 0% -41.20% (p=0.000 n=8) PowInt-4 509.8n ± 1% 369.3n ± 1% -27.56% (p=0.000 n=8) PowFrac-4 1189.0n ± 0% 947.8n ± 0% -20.29% (p=0.000 n=8) Pow10Pos-4 15.07n ± 0% 15.07n ± 0% ~ (p=0.733 n=8) Pow10Neg-4 20.10n ± 0% 20.10n ± 0% ~ (p=0.576 n=8) Round-4 44.22n ± 0% 26.12n ± 0% -40.92% (p=0.000 n=8) RoundToEven-4 46.22n ± 0% 27.12n ± 0% -41.31% (p=0.000 n=8) Remainder-4 539.0n ± 1% 417.1n ± 1% -22.62% (p=0.000 n=8) Signbit-4 17.985n ± 0% 5.694n ± 0% -68.34% (p=0.000 n=8) Sin-4 185.7n ± 5% 172.9n ± 0% -6.89% (p=0.001 n=8) Sincos-4 176.6n ± 0% 200.9n ± 0% +13.76% (p=0.000 n=8) Sinh-4 495.8n ± 0% 435.9n ± 0% -12.09% (p=0.000 n=8) SqrtIndirect-4 5.022n ± 0% 5.024n ± 0% ~ (p=0.083 n=8) SqrtLatency-4 8.038n ± 0% 8.044n ± 0% ~ (p=0.524 n=8) SqrtIndirectLatency-4 8.035n ± 0% 8.039n ± 0% +0.06% (p=0.017 n=8) SqrtGoLatency-4 340.1n ± 0% 278.3n ± 0% -18.19% (p=0.000 n=8) SqrtPrime-4 5.381µ ± 0% 5.386µ ± 0% ~ (p=0.662 n=8) Tan-4 198.6n ± 1% 183.1n ± 0% -7.85% (p=0.000 n=8) Tanh-4 491.3n ± 1% 440.8n ± 1% -10.29% (p=0.000 n=8) Trunc-4 121.7n ± 0% 121.7n ± 0% ~ (p=0.769 n=8) Y0-4 855.1n ± 0% 859.8n ± 0% +0.54% (p=0.007 n=8) Y1-4 862.3n ± 0% 865.1n ± 0% +0.32% (p=0.007 n=8) Yn-4 1.830µ ± 0% 1.837µ ± 0% +0.36% (p=0.011 n=8) Float64bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float64frombits-4 13.060n ± 0% 3.018n ± 0% -76.90% (p=0.000 n=8) Float32bits-4 13.060n ± 0% 3.016n ± 0% -76.91% (p=0.000 n=8) Float32frombits-4 13.070n ± 0% 3.013n ± 0% -76.94% (p=0.000 n=8) FMA-4 446.0n ± 0% 413.1n ± 1% -7.38% (p=0.000 n=8) geomean 143.4n 108.3n -24.49% Change-Id: I2067f7a5ae1126ada7ab3fb2083710e8212535e9 Reviewed-on: https://go-review.googlesource.com/c/go/+/493815 Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Keith Randall <khr@golang.org> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@google.com> Run-TryBot: Dmitri Shuralyov <dmitshur@golang.org>
2023-05-09 03:40:06 -06:00
// mips64/hardfloat:"MOVW\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)|(XORL\t[A-Z][A-Z0-9]+, [A-Z][A-Z0-9]+)",-"FCMP",-"MOVB\t[$]1"
// s390x:"MOV(B|BZ|D)\t[$]0,",-"FCMPU",-"MOV(B|BZ|D)\t[$]1,"
return 0.5 == float64(uint32(1)) || 1.5 > float64(uint64(1<<63))
}
func constantCheck32() bool {
// amd64:"MOV(B|L)\t[$]1",-"FCMP",-"MOV(B|L)\t[$]0"
// s390x:"MOV(B|BZ|D)\t[$]1,",-"FCMPU",-"MOV(B|BZ|D)\t[$]0,"
return float32(0.5) <= float32(int64(1)) && float32(1.5) >= float32(int32(-1<<31))
}
// Test that integer constants are converted to floating point constants
// at compile-time
func constantConvert32(x float32) float32 {
// amd64:"MOVSS\t[$]f32.3f800000\\(SB\\)"
// s390x:"FMOVS\t[$]f32.3f800000\\(SB\\)"
// ppc64x/power8:"FMOVS\t[$]f32.3f800000\\(SB\\)"
// ppc64x/power9:"FMOVS\t[$]f32.3f800000\\(SB\\)"
// ppc64x/power10:"XXSPLTIDP\t[$]1065353216, VS0"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on arm64 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>
2018-07-15 22:45:25 -06:00
// arm64:"FMOVS\t[$]\\(1.0\\)"
if x > math.Float32frombits(0x3f800000) {
return -x
}
return x
}
func constantConvertInt32(x uint32) uint32 {
// amd64:-"MOVSS"
// s390x:-"FMOVS"
// ppc64x:-"FMOVS"
cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on arm64 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>
2018-07-15 22:45:25 -06:00
// arm64:-"FMOVS"
if x > math.Float32bits(1) {
return -x
}
return x
}
func nanGenerate64() float64 {
// Test to make sure we don't generate a NaN while constant propagating.
// See issue 36400.
zero := 0.0
// amd64:-"DIVSD"
inf := 1 / zero // +inf. We can constant propagate this one.
negone := -1.0
// amd64:"DIVSD"
z0 := zero / zero
// amd64:"MULSD"
z1 := zero * inf
// amd64:"SQRTSD"
z2 := math.Sqrt(negone)
return z0 + z1 + z2
}
func nanGenerate32() float32 {
zero := float32(0.0)
// amd64:-"DIVSS"
inf := 1 / zero // +inf. We can constant propagate this one.
// amd64:"DIVSS"
z0 := zero / zero
// amd64:"MULSS"
z1 := zero * inf
return z0 + z1
}