1
0
mirror of https://github.com/golang/go synced 2024-11-23 15:30:05 -07:00
go/test/codegen/math.go

178 lines
4.4 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) {
// s390x:"FIDBR\t[$]6"
// arm64:"FRINTPD"
// ppc64:"FRIP"
// ppc64le:"FRIP"
// wasm:"F64Ceil"
sink64[0] = math.Ceil(x)
// s390x:"FIDBR\t[$]7"
// arm64:"FRINTMD"
// ppc64:"FRIM"
// ppc64le:"FRIM"
// wasm:"F64Floor"
sink64[1] = math.Floor(x)
// s390x:"FIDBR\t[$]1"
// arm64:"FRINTAD"
// ppc64:"FRIN"
// ppc64le:"FRIN"
sink64[2] = math.Round(x)
// s390x:"FIDBR\t[$]5"
// arm64:"FRINTZD"
// ppc64:"FRIZ"
// ppc64le:"FRIZ"
// wasm:"F64Trunc"
sink64[3] = math.Trunc(x)
// s390x:"FIDBR\t[$]4"
// arm64:"FRINTND"
// wasm:"F64Nearest"
sink64[4] = math.RoundToEven(x)
}
func sqrt(x float64) float64 {
// amd64:"SQRTSD"
// 386/387:"FSQRT" 386/sse2:"SQRTSD"
// arm64:"FSQRTD"
// arm/7:"SQRTD"
// mips/hardfloat:"SQRTD" mips/softfloat:-"SQRTD"
// mips64/hardfloat:"SQRTD" mips64/softfloat:-"SQRTD"
// wasm:"F64Sqrt"
return math.Sqrt(x)
}
// Check that it's using integer registers
func abs(x, y float64) {
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)
// ppc64:"FABS\t"
// ppc64le:"FABS\t"
// wasm:"F64Abs"
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)
// ppc64:"FNABS\t"
// ppc64le:"FNABS\t"
sink64[1] = -math.Abs(y)
}
// Check that it's using integer registers
func abs32(x float32) float32 {
// s390x:"LPDFR",-"LDEBR",-"LEDBR" (no float64 conversion)
return float32(math.Abs(float64(x)))
}
// Check that it's using integer registers
func copysign(a, b, c float64) {
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","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
// s390x:"CPSDR",-"MOVD" (no integer load/store)
// ppc64:"FCPSGN"
// ppc64le:"FCPSGN"
// wasm:"F64Copysign"
sink64[0] = math.Copysign(a, b)
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)
// ppc64:"FCPSGN"
// ppc64le:"FCPSGN"
// arm64:"ORR", -"AND"
sink64[1] = math.Copysign(c, -1)
// Like math.Copysign(c, -1), but with integer operations. Useful
// for platforms that have a copysign opcode to see if it's detected.
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
sink64[2] = math.Float64frombits(math.Float64bits(a) | 1<<63)
// amd64:-"SHLQ\t[$]1",-"SHRQ\t[$]1","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
// s390x:"CPSDR\t",-"MOVD\t" (no integer load/store)
// ppc64:"FCPSGN"
// ppc64le:"FCPSGN"
sink64[3] = math.Copysign(-1, c)
}
func fromFloat64(f64 float64) uint64 {
// amd64:"MOVQ\tX.*, [^X].*"
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.*"
// ppc64:"MFVSRD"
// ppc64le:"MFVSRD"
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.*"
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.*"
// ppc64:"MTVSRD"
// ppc64le:"MTVSRD"
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.*"
return math.Float32frombits(u32+1) + 1
}
// Test that comparisons with constants converted to float
// are evaluated at compile-time
func constantCheck64() bool {
// amd64:"MOVB\t[$]0",-"FCMP",-"MOVB\t[$]1"
// s390x:"MOV(B|BZ|D)\t[$]0,",-"FCMPU",-"MOV(B|BZ|D)\t[$]1,"
return 0.5 == float64(uint32(1)) || 1.5 > float64(uint64(1<<63)) || math.NaN() == math.NaN()
}
func constantCheck32() bool {
// amd64:"MOVB\t[$]1",-"FCMP",-"MOVB\t[$]0"
// s390x:"MOV(B|BZ|D)\t[$]1,",-"FCMPU",-"MOV(B|BZ|D)\t[$]0,"
return float32(0.5) <= float32(int64(1)) && float32(1.5) >= float32(int32(-1<<31)) && float32(math.NaN()) != float32(math.NaN())
}
// Test that integer constants are converted to floating point constants
// at compile-time
func constantConvert32(x float32) float32 {
// amd64:"MOVSS\t[$]f32.3f800000\\(SB\\)"
// s390x:"FMOVS\t[$]f32.3f800000\\(SB\\)"
// ppc64:"FMOVS\t[$]f32.3f800000\\(SB\\)"
// ppc64le:"FMOVS\t[$]f32.3f800000\\(SB\\)"
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"
// ppc64:-"FMOVS"
// ppc64le:-"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
}