1
0
mirror of https://github.com/golang/go synced 2024-11-14 07:50:21 -07:00
go/test/codegen/comparisons.go

539 lines
10 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 "unsafe"
// This file contains code generation tests related to the comparison
// operators.
// -------------- //
// Equality //
// -------------- //
// Check that compare to constant string use 2/4/8 byte compares
func CompareString1(s string) bool {
// amd64:`CMPW\t\(.*\), [$]`
// arm64:`MOVHU\t\(.*\), [R]`,`CMPW\t[$]`
// ppc64le:`MOVHZ\t\(.*\), [R]`,`CMPW\t.*, [$]`
// s390x:`MOVHBR\t\(.*\), [R]`,`CMPW\t.*, [$]`
return s == "xx"
}
func CompareString2(s string) bool {
// amd64:`CMPL\t\(.*\), [$]`
// arm64:`MOVWU\t\(.*\), [R]`,`CMPW\t.*, [R]`
// ppc64le:`MOVWZ\t\(.*\), [R]`,`CMPW\t.*, [R]`
// s390x:`MOVWBR\t\(.*\), [R]`,`CMPW\t.*, [$]`
return s == "xxxx"
}
func CompareString3(s string) bool {
// amd64:`CMPQ\t\(.*\), [A-Z]`
// arm64:-`CMPW\t`
// ppc64:-`CMPW\t`
// ppc64le:-`CMPW\t`
// s390x:-`CMPW\t`
return s == "xxxxxxxx"
}
// Check that arrays compare use 2/4/8 byte compares
func CompareArray1(a, b [2]byte) bool {
// amd64:`CMPW\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// arm64:-`MOVBU\t`
// ppc64le:-`MOVBZ\t`
// s390x:-`MOVBZ\t`
return a == b
}
func CompareArray2(a, b [3]uint16) bool {
// amd64:`CMPL\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPW\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray3(a, b [3]int16) bool {
// amd64:`CMPL\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPW\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray4(a, b [12]int8) bool {
// amd64:`CMPQ\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPL\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray5(a, b [15]byte) bool {
// amd64:`CMPQ\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
// This was a TODO in mapaccess1_faststr
func CompareArray6(a, b unsafe.Pointer) bool {
// amd64:`CMPL\t\(.*\), [A-Z]`
// arm64:`MOVWU\t\(.*\), [R]`,`CMPW\t.*, [R]`
// ppc64le:`MOVWZ\t\(.*\), [R]`,`CMPW\t.*, [R]`
// s390x:`MOVWBR\t\(.*\), [R]`,`CMPW\t.*, [R]`
return *((*[4]byte)(a)) != *((*[4]byte)(b))
}
// -------------- //
// Ordering //
// -------------- //
// Test that LEAQ/ADDQconst are folded into SETx ops
func CmpFold(x uint32) bool {
// amd64:`SETHI\t.*\(SP\)`
return x > 4
}
// Test that direct comparisons with memory are generated when
// possible
func CmpMem1(p int, q *int) bool {
// amd64:`CMPQ\t\(.*\), [A-Z]`
return p < *q
}
func CmpMem2(p *int, q int) bool {
// amd64:`CMPQ\t\(.*\), [A-Z]`
return *p < q
}
func CmpMem3(p *int) bool {
// amd64:`CMPQ\t\(.*\), [$]7`
return *p < 7
}
func CmpMem4(p *int) bool {
// amd64:`CMPQ\t\(.*\), [$]7`
return 7 < *p
}
func CmpMem5(p **int) {
// amd64:`CMPL\truntime.writeBarrier\(SB\), [$]0`
*p = nil
}
cmd/compile: optimize 386's comparison CMPL/CMPW/CMPB can take a memory operand on 386, and this CL implements that optimization. 1. The total size of pkg/linux_386 decreases about 45KB, excluding cmd/compile. 2. The go1 benchmark shows a little improvement. name old time/op new time/op delta BinaryTree17-4 3.36s ± 2% 3.37s ± 3% ~ (p=0.537 n=40+40) Fannkuch11-4 3.59s ± 1% 3.53s ± 2% -1.58% (p=0.000 n=40+40) FmtFprintfEmpty-4 46.0ns ± 3% 45.8ns ± 3% ~ (p=0.249 n=40+40) FmtFprintfString-4 80.0ns ± 4% 78.8ns ± 3% -1.49% (p=0.001 n=40+40) FmtFprintfInt-4 89.7ns ± 2% 90.3ns ± 2% +0.74% (p=0.003 n=40+40) FmtFprintfIntInt-4 144ns ± 3% 143ns ± 3% -0.95% (p=0.003 n=40+40) FmtFprintfPrefixedInt-4 181ns ± 4% 180ns ± 2% ~ (p=0.103 n=40+40) FmtFprintfFloat-4 412ns ± 3% 408ns ± 4% -0.97% (p=0.018 n=40+40) FmtManyArgs-4 607ns ± 4% 605ns ± 4% ~ (p=0.148 n=40+40) GobDecode-4 7.19ms ± 4% 7.24ms ± 5% ~ (p=0.340 n=40+40) GobEncode-4 7.04ms ± 9% 6.99ms ± 9% ~ (p=0.289 n=40+40) Gzip-4 400ms ± 6% 398ms ± 5% ~ (p=0.168 n=40+40) Gunzip-4 41.2ms ± 3% 41.7ms ± 3% +1.40% (p=0.001 n=40+40) HTTPClientServer-4 62.5µs ± 1% 62.1µs ± 2% -0.61% (p=0.000 n=37+37) JSONEncode-4 20.7ms ± 4% 20.4ms ± 3% -1.60% (p=0.000 n=40+40) JSONDecode-4 69.4ms ± 4% 69.2ms ± 6% ~ (p=0.177 n=40+40) Mandelbrot200-4 5.22ms ± 6% 5.21ms ± 3% ~ (p=0.531 n=40+40) GoParse-4 3.29ms ± 3% 3.28ms ± 3% ~ (p=0.321 n=40+39) RegexpMatchEasy0_32-4 104ns ± 4% 103ns ± 7% -0.89% (p=0.040 n=40+40) RegexpMatchEasy0_1K-4 852ns ± 3% 853ns ± 2% ~ (p=0.357 n=40+40) RegexpMatchEasy1_32-4 113ns ± 8% 113ns ± 3% ~ (p=0.906 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 5% ~ (p=0.326 n=40+40) RegexpMatchMedium_32-4 136ns ± 3% 133ns ± 3% -2.31% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 44.0µs ± 3% 43.7µs ± 3% ~ (p=0.053 n=40+40) RegexpMatchHard_32-4 2.27µs ± 3% 2.26µs ± 4% ~ (p=0.391 n=40+40) RegexpMatchHard_1K-4 68.0µs ± 3% 68.9µs ± 3% +1.28% (p=0.000 n=40+40) Revcomp-4 1.86s ± 5% 1.86s ± 2% ~ (p=0.950 n=40+40) Template-4 73.4ms ± 4% 69.9ms ± 7% -4.78% (p=0.000 n=40+40) TimeParse-4 449ns ± 4% 441ns ± 5% -1.76% (p=0.000 n=40+40) TimeFormat-4 416ns ± 3% 417ns ± 4% ~ (p=0.304 n=40+40) [Geo mean] 67.7µs 67.3µs -0.55% name old speed new speed delta GobDecode-4 107MB/s ± 4% 106MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 109MB/s ± 5% 110MB/s ± 9% ~ (p=0.142 n=38+40) Gzip-4 48.5MB/s ± 5% 48.8MB/s ± 5% ~ (p=0.172 n=40+40) Gunzip-4 472MB/s ± 3% 465MB/s ± 3% -1.39% (p=0.001 n=40+40) JSONEncode-4 93.6MB/s ± 4% 95.1MB/s ± 3% +1.61% (p=0.000 n=40+40) JSONDecode-4 28.0MB/s ± 3% 28.1MB/s ± 6% ~ (p=0.181 n=40+40) GoParse-4 17.6MB/s ± 3% 17.7MB/s ± 3% ~ (p=0.350 n=40+39) RegexpMatchEasy0_32-4 308MB/s ± 4% 311MB/s ± 6% +0.96% (p=0.025 n=40+40) RegexpMatchEasy0_1K-4 1.20GB/s ± 3% 1.20GB/s ± 2% ~ (p=0.317 n=40+40) RegexpMatchEasy1_32-4 282MB/s ± 7% 282MB/s ± 3% ~ (p=0.516 n=40+40) RegexpMatchEasy1_1K-4 994MB/s ± 4% 991MB/s ± 5% ~ (p=0.319 n=40+40) RegexpMatchMedium_32-4 7.31MB/s ± 3% 7.49MB/s ± 3% +2.46% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 23.3MB/s ± 3% 23.4MB/s ± 3% ~ (p=0.052 n=40+40) RegexpMatchHard_32-4 14.1MB/s ± 3% 14.1MB/s ± 4% ~ (p=0.391 n=40+40) RegexpMatchHard_1K-4 15.1MB/s ± 3% 14.9MB/s ± 3% -1.27% (p=0.000 n=40+40) Revcomp-4 137MB/s ± 5% 137MB/s ± 2% ~ (p=0.942 n=40+40) Template-4 26.5MB/s ± 4% 27.8MB/s ± 7% +5.03% (p=0.000 n=40+40) [Geo mean] 78.6MB/s 79.0MB/s +0.57% Change-Id: Idcacc6881ef57cd7dc33aa87b711282842b72a53 Reviewed-on: https://go-review.googlesource.com/126618 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-07-29 06:50:50 -06:00
func CmpMem6(a []int) int {
// 386:`CMPL\s8\([A-Z]+\),`
// amd64:`CMPQ\s16\([A-Z]+\),`
if a[1] > a[2] {
return 1
} else {
return 2
}
}
// Check tbz/tbnz are generated when comparing against zero on arm64
func CmpZero1(a int32, ptr *int) {
if a < 0 { // arm64:"TBZ"
*ptr = 0
}
}
func CmpZero2(a int64, ptr *int) {
if a < 0 { // arm64:"TBZ"
*ptr = 0
}
}
func CmpZero3(a int32, ptr *int) {
if a >= 0 { // arm64:"TBNZ"
*ptr = 0
}
}
func CmpZero4(a int64, ptr *int) {
if a >= 0 { // arm64:"TBNZ"
*ptr = 0
}
}
cmd/compile: optimize arm's comparison The CMP/CMN/TST/TEQ perform similar to SUB/ADD/AND/XOR except the result is abondoned, and only NZCV flags are affected. This CL implements further optimization with them. 1. A micro benchmark test gets more than 9% improvment. TSTTEQ-4 6.99ms ± 0% 6.35ms ± 0% -9.15% (p=0.000 n=33+36) (https://github.com/benshi001/ugo1/blob/master/tstteq2_test.go) 2. The go1 benckmark shows no regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 25.7s ± 1% 25.7s ± 1% ~ (p=0.830 n=40+40) Fannkuch11-4 13.3s ± 0% 13.2s ± 0% -0.65% (p=0.000 n=40+34) FmtFprintfEmpty-4 394ns ± 0% 394ns ± 0% ~ (p=0.819 n=40+40) FmtFprintfString-4 677ns ± 0% 677ns ± 0% +0.06% (p=0.039 n=39+40) FmtFprintfInt-4 707ns ± 0% 706ns ± 0% -0.14% (p=0.000 n=40+39) FmtFprintfIntInt-4 1.04µs ± 0% 1.04µs ± 0% +0.10% (p=0.000 n=29+31) FmtFprintfPrefixedInt-4 1.10µs ± 0% 1.11µs ± 0% +0.65% (p=0.000 n=39+37) FmtFprintfFloat-4 2.27µs ± 0% 2.26µs ± 0% -0.53% (p=0.000 n=39+40) FmtManyArgs-4 3.96µs ± 0% 3.96µs ± 0% +0.10% (p=0.000 n=39+40) GobDecode-4 53.4ms ± 1% 52.8ms ± 2% -1.10% (p=0.000 n=39+39) GobEncode-4 50.3ms ± 3% 50.4ms ± 2% ~ (p=0.089 n=40+39) Gzip-4 2.62s ± 0% 2.64s ± 0% +0.60% (p=0.000 n=40+39) Gunzip-4 312ms ± 0% 312ms ± 0% +0.02% (p=0.030 n=40+39) HTTPClientServer-4 1.01ms ± 7% 0.98ms ± 7% -2.37% (p=0.000 n=40+39) JSONEncode-4 126ms ± 1% 126ms ± 1% -0.38% (p=0.004 n=39+39) JSONDecode-4 423ms ± 0% 426ms ± 2% +0.72% (p=0.001 n=39+40) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% +0.04% (p=0.000 n=38+40) GoParse-4 22.8ms ± 0% 22.6ms ± 0% -0.68% (p=0.000 n=35+40) RegexpMatchEasy0_32-4 699ns ± 0% 704ns ± 0% +0.73% (p=0.000 n=27+40) RegexpMatchEasy0_1K-4 4.27µs ± 0% 4.26µs ± 0% -0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 741ns ± 0% 735ns ± 0% -0.85% (p=0.000 n=40+35) RegexpMatchEasy1_1K-4 5.53µs ± 0% 5.49µs ± 0% -0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 1.07µs ± 0% 1.04µs ± 2% -2.34% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 261µs ± 0% 261µs ± 0% -0.16% (p=0.000 n=40+39) RegexpMatchHard_32-4 14.9µs ± 0% 14.9µs ± 0% -0.18% (p=0.000 n=39+40) RegexpMatchHard_1K-4 445µs ± 0% 446µs ± 0% +0.09% (p=0.000 n=36+34) Revcomp-4 41.8ms ± 1% 41.8ms ± 1% ~ (p=0.595 n=39+38) Template-4 530ms ± 1% 528ms ± 1% -0.49% (p=0.000 n=40+40) TimeParse-4 3.39µs ± 0% 3.42µs ± 0% +0.98% (p=0.000 n=36+38) TimeFormat-4 6.12µs ± 0% 6.07µs ± 0% -0.81% (p=0.000 n=34+38) [Geo mean] 384µs 383µs -0.24% name old speed new speed delta GobDecode-4 14.4MB/s ± 1% 14.5MB/s ± 2% +1.11% (p=0.000 n=39+39) GobEncode-4 15.3MB/s ± 3% 15.2MB/s ± 2% ~ (p=0.104 n=40+39) Gzip-4 7.40MB/s ± 1% 7.36MB/s ± 0% -0.60% (p=0.000 n=40+39) Gunzip-4 62.2MB/s ± 0% 62.1MB/s ± 0% -0.02% (p=0.047 n=40+39) JSONEncode-4 15.4MB/s ± 1% 15.4MB/s ± 2% +0.39% (p=0.002 n=39+39) JSONDecode-4 4.59MB/s ± 0% 4.56MB/s ± 2% -0.71% (p=0.000 n=39+40) GoParse-4 2.54MB/s ± 0% 2.56MB/s ± 0% +0.72% (p=0.000 n=26+40) RegexpMatchEasy0_32-4 45.8MB/s ± 0% 45.4MB/s ± 0% -0.75% (p=0.000 n=38+40) RegexpMatchEasy0_1K-4 240MB/s ± 0% 240MB/s ± 0% +0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 43.1MB/s ± 0% 43.5MB/s ± 0% +0.84% (p=0.000 n=40+39) RegexpMatchEasy1_1K-4 185MB/s ± 0% 186MB/s ± 0% +0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 936kB/s ± 1% 959kB/s ± 2% +2.38% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 3.92MB/s ± 0% 3.93MB/s ± 0% +0.18% (p=0.000 n=39+40) RegexpMatchHard_32-4 2.15MB/s ± 0% 2.15MB/s ± 0% +0.19% (p=0.000 n=40+40) RegexpMatchHard_1K-4 2.30MB/s ± 0% 2.30MB/s ± 0% ~ (all equal) Revcomp-4 60.8MB/s ± 1% 60.8MB/s ± 1% ~ (p=0.600 n=39+38) Template-4 3.66MB/s ± 1% 3.68MB/s ± 1% +0.46% (p=0.000 n=40+40) [Geo mean] 12.8MB/s 12.8MB/s +0.27% Change-Id: I849161169ecf0876a04b7c1d3990fa8d1435215e Reviewed-on: https://go-review.googlesource.com/122855 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-09 19:48:55 -06:00
cmd/compile: optimize ARM's comparision Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits when the result of the addition is no longer used, otherwise there might be even performance drop. And this CL fixes that issue for CMP/CMN/TST/TEQ. There is little regression in the go1 benchmark (excluding noise), and the test case JSONDecode-4 even gets improvement. name old time/op new time/op delta BinaryTree17-4 21.6s ± 1% 21.6s ± 0% -0.22% (p=0.013 n=30+30) Fannkuch11-4 11.1s ± 0% 11.1s ± 0% +0.11% (p=0.000 n=30+29) FmtFprintfEmpty-4 297ns ± 0% 297ns ± 0% +0.08% (p=0.007 n=26+28) FmtFprintfString-4 589ns ± 1% 589ns ± 0% ~ (p=0.659 n=30+25) FmtFprintfInt-4 644ns ± 1% 650ns ± 0% +0.88% (p=0.000 n=30+24) FmtFprintfIntInt-4 964ns ± 0% 977ns ± 0% +1.33% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.06µs ± 0% 1.07µs ± 0% +1.31% (p=0.000 n=29+27) FmtFprintfFloat-4 1.89µs ± 0% 1.92µs ± 0% +1.25% (p=0.000 n=29+29) FmtManyArgs-4 3.63µs ± 0% 3.67µs ± 0% +1.33% (p=0.000 n=29+27) GobDecode-4 38.1ms ± 1% 37.9ms ± 1% -0.60% (p=0.000 n=29+29) GobEncode-4 35.3ms ± 2% 35.2ms ± 1% ~ (p=0.286 n=30+30) Gzip-4 2.36s ± 0% 2.37s ± 2% ~ (p=0.277 n=24+28) Gunzip-4 264ms ± 1% 264ms ± 1% ~ (p=0.104 n=28+30) HTTPClientServer-4 1.04ms ± 4% 1.02ms ± 4% -1.65% (p=0.000 n=28+28) JSONEncode-4 78.5ms ± 1% 79.6ms ± 1% +1.34% (p=0.000 n=27+28) JSONDecode-4 379ms ± 4% 352ms ± 5% -7.09% (p=0.000 n=29+30) Mandelbrot200-4 17.6ms ± 0% 17.6ms ± 0% ~ (p=0.206 n=28+29) GoParse-4 21.9ms ± 1% 22.1ms ± 1% +0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 631ns ± 0% 641ns ± 0% +1.63% (p=0.000 n=29+30) RegexpMatchEasy0_1K-4 4.11µs ± 0% 4.11µs ± 0% ~ (p=0.700 n=30+30) RegexpMatchEasy1_32-4 670ns ± 0% 679ns ± 0% +1.37% (p=0.000 n=21+30) RegexpMatchEasy1_1K-4 5.31µs ± 0% 5.26µs ± 0% -1.03% (p=0.000 n=25+28) RegexpMatchMedium_32-4 905ns ± 0% 906ns ± 0% +0.14% (p=0.001 n=30+30) RegexpMatchMedium_1K-4 192µs ± 0% 191µs ± 0% -0.45% (p=0.000 n=29+27) RegexpMatchHard_32-4 11.8µs ± 0% 11.7µs ± 0% -0.39% (p=0.000 n=29+28) RegexpMatchHard_1K-4 347µs ± 0% 347µs ± 0% ~ (p=0.084 n=29+30) Revcomp-4 37.5ms ± 1% 37.5ms ± 1% ~ (p=0.279 n=29+29) Template-4 519ms ± 2% 519ms ± 2% ~ (p=0.652 n=28+29) TimeParse-4 2.83µs ± 0% 2.78µs ± 0% -1.90% (p=0.000 n=27+28) TimeFormat-4 5.79µs ± 0% 5.60µs ± 0% -3.23% (p=0.000 n=29+29) [Geo mean] 331µs 330µs -0.16% name old speed new speed delta GobDecode-4 20.1MB/s ± 1% 20.3MB/s ± 1% +0.61% (p=0.000 n=29+29) GobEncode-4 21.7MB/s ± 2% 21.8MB/s ± 1% ~ (p=0.294 n=30+30) Gzip-4 8.23MB/s ± 1% 8.20MB/s ± 2% ~ (p=0.099 n=26+28) Gunzip-4 73.5MB/s ± 1% 73.4MB/s ± 1% ~ (p=0.107 n=28+30) JSONEncode-4 24.7MB/s ± 1% 24.4MB/s ± 1% -1.32% (p=0.000 n=27+28) JSONDecode-4 5.13MB/s ± 4% 5.52MB/s ± 5% +7.65% (p=0.000 n=29+30) GoParse-4 2.65MB/s ± 1% 2.63MB/s ± 1% -0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 50.7MB/s ± 0% 49.9MB/s ± 0% -1.58% (p=0.000 n=29+29) RegexpMatchEasy0_1K-4 249MB/s ± 0% 249MB/s ± 0% ~ (p=0.342 n=30+28) RegexpMatchEasy1_32-4 47.7MB/s ± 0% 47.1MB/s ± 0% -1.39% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 193MB/s ± 0% 195MB/s ± 0% +1.04% (p=0.000 n=25+28) RegexpMatchMedium_32-4 1.10MB/s ± 0% 1.10MB/s ± 0% -0.42% (p=0.000 n=30+26) RegexpMatchMedium_1K-4 5.33MB/s ± 0% 5.36MB/s ± 0% +0.43% (p=0.000 n=29+29) RegexpMatchHard_32-4 2.72MB/s ± 0% 2.73MB/s ± 0% +0.37% (p=0.000 n=29+30) RegexpMatchHard_1K-4 2.95MB/s ± 0% 2.95MB/s ± 0% ~ (all equal) Revcomp-4 67.8MB/s ± 1% 67.7MB/s ± 1% ~ (p=0.273 n=29+29) Template-4 3.74MB/s ± 2% 3.74MB/s ± 2% ~ (p=0.665 n=28+29) [Geo mean] 15.2MB/s 15.2MB/s +0.21% Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a Reviewed-on: https://go-review.googlesource.com/132115 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-29 19:19:58 -06:00
func CmpToZero(a, b, d int32, e, f int64) int32 {
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
// arm:`TST`,-`AND`
// arm64:`TSTW`,-`AND`
cmd/compile: optimize ARM's comparision Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits when the result of the addition is no longer used, otherwise there might be even performance drop. And this CL fixes that issue for CMP/CMN/TST/TEQ. There is little regression in the go1 benchmark (excluding noise), and the test case JSONDecode-4 even gets improvement. name old time/op new time/op delta BinaryTree17-4 21.6s ± 1% 21.6s ± 0% -0.22% (p=0.013 n=30+30) Fannkuch11-4 11.1s ± 0% 11.1s ± 0% +0.11% (p=0.000 n=30+29) FmtFprintfEmpty-4 297ns ± 0% 297ns ± 0% +0.08% (p=0.007 n=26+28) FmtFprintfString-4 589ns ± 1% 589ns ± 0% ~ (p=0.659 n=30+25) FmtFprintfInt-4 644ns ± 1% 650ns ± 0% +0.88% (p=0.000 n=30+24) FmtFprintfIntInt-4 964ns ± 0% 977ns ± 0% +1.33% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.06µs ± 0% 1.07µs ± 0% +1.31% (p=0.000 n=29+27) FmtFprintfFloat-4 1.89µs ± 0% 1.92µs ± 0% +1.25% (p=0.000 n=29+29) FmtManyArgs-4 3.63µs ± 0% 3.67µs ± 0% +1.33% (p=0.000 n=29+27) GobDecode-4 38.1ms ± 1% 37.9ms ± 1% -0.60% (p=0.000 n=29+29) GobEncode-4 35.3ms ± 2% 35.2ms ± 1% ~ (p=0.286 n=30+30) Gzip-4 2.36s ± 0% 2.37s ± 2% ~ (p=0.277 n=24+28) Gunzip-4 264ms ± 1% 264ms ± 1% ~ (p=0.104 n=28+30) HTTPClientServer-4 1.04ms ± 4% 1.02ms ± 4% -1.65% (p=0.000 n=28+28) JSONEncode-4 78.5ms ± 1% 79.6ms ± 1% +1.34% (p=0.000 n=27+28) JSONDecode-4 379ms ± 4% 352ms ± 5% -7.09% (p=0.000 n=29+30) Mandelbrot200-4 17.6ms ± 0% 17.6ms ± 0% ~ (p=0.206 n=28+29) GoParse-4 21.9ms ± 1% 22.1ms ± 1% +0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 631ns ± 0% 641ns ± 0% +1.63% (p=0.000 n=29+30) RegexpMatchEasy0_1K-4 4.11µs ± 0% 4.11µs ± 0% ~ (p=0.700 n=30+30) RegexpMatchEasy1_32-4 670ns ± 0% 679ns ± 0% +1.37% (p=0.000 n=21+30) RegexpMatchEasy1_1K-4 5.31µs ± 0% 5.26µs ± 0% -1.03% (p=0.000 n=25+28) RegexpMatchMedium_32-4 905ns ± 0% 906ns ± 0% +0.14% (p=0.001 n=30+30) RegexpMatchMedium_1K-4 192µs ± 0% 191µs ± 0% -0.45% (p=0.000 n=29+27) RegexpMatchHard_32-4 11.8µs ± 0% 11.7µs ± 0% -0.39% (p=0.000 n=29+28) RegexpMatchHard_1K-4 347µs ± 0% 347µs ± 0% ~ (p=0.084 n=29+30) Revcomp-4 37.5ms ± 1% 37.5ms ± 1% ~ (p=0.279 n=29+29) Template-4 519ms ± 2% 519ms ± 2% ~ (p=0.652 n=28+29) TimeParse-4 2.83µs ± 0% 2.78µs ± 0% -1.90% (p=0.000 n=27+28) TimeFormat-4 5.79µs ± 0% 5.60µs ± 0% -3.23% (p=0.000 n=29+29) [Geo mean] 331µs 330µs -0.16% name old speed new speed delta GobDecode-4 20.1MB/s ± 1% 20.3MB/s ± 1% +0.61% (p=0.000 n=29+29) GobEncode-4 21.7MB/s ± 2% 21.8MB/s ± 1% ~ (p=0.294 n=30+30) Gzip-4 8.23MB/s ± 1% 8.20MB/s ± 2% ~ (p=0.099 n=26+28) Gunzip-4 73.5MB/s ± 1% 73.4MB/s ± 1% ~ (p=0.107 n=28+30) JSONEncode-4 24.7MB/s ± 1% 24.4MB/s ± 1% -1.32% (p=0.000 n=27+28) JSONDecode-4 5.13MB/s ± 4% 5.52MB/s ± 5% +7.65% (p=0.000 n=29+30) GoParse-4 2.65MB/s ± 1% 2.63MB/s ± 1% -0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 50.7MB/s ± 0% 49.9MB/s ± 0% -1.58% (p=0.000 n=29+29) RegexpMatchEasy0_1K-4 249MB/s ± 0% 249MB/s ± 0% ~ (p=0.342 n=30+28) RegexpMatchEasy1_32-4 47.7MB/s ± 0% 47.1MB/s ± 0% -1.39% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 193MB/s ± 0% 195MB/s ± 0% +1.04% (p=0.000 n=25+28) RegexpMatchMedium_32-4 1.10MB/s ± 0% 1.10MB/s ± 0% -0.42% (p=0.000 n=30+26) RegexpMatchMedium_1K-4 5.33MB/s ± 0% 5.36MB/s ± 0% +0.43% (p=0.000 n=29+29) RegexpMatchHard_32-4 2.72MB/s ± 0% 2.73MB/s ± 0% +0.37% (p=0.000 n=29+30) RegexpMatchHard_1K-4 2.95MB/s ± 0% 2.95MB/s ± 0% ~ (all equal) Revcomp-4 67.8MB/s ± 1% 67.7MB/s ± 1% ~ (p=0.273 n=29+29) Template-4 3.74MB/s ± 2% 3.74MB/s ± 2% ~ (p=0.665 n=28+29) [Geo mean] 15.2MB/s 15.2MB/s +0.21% Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a Reviewed-on: https://go-review.googlesource.com/132115 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-29 19:19:58 -06:00
// 386:`TESTL`,-`ANDL`
// amd64:`TESTL`,-`ANDL`
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
c0 := a&b < 0
// arm:`CMN`,-`ADD`
// arm64:`CMNW`,-`ADD`
c1 := a+b < 0
// arm:`TEQ`,-`XOR`
c2 := a^b < 0
// arm64:`TST`,-`AND`
cmd/compile: optimize ARM's comparision Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits when the result of the addition is no longer used, otherwise there might be even performance drop. And this CL fixes that issue for CMP/CMN/TST/TEQ. There is little regression in the go1 benchmark (excluding noise), and the test case JSONDecode-4 even gets improvement. name old time/op new time/op delta BinaryTree17-4 21.6s ± 1% 21.6s ± 0% -0.22% (p=0.013 n=30+30) Fannkuch11-4 11.1s ± 0% 11.1s ± 0% +0.11% (p=0.000 n=30+29) FmtFprintfEmpty-4 297ns ± 0% 297ns ± 0% +0.08% (p=0.007 n=26+28) FmtFprintfString-4 589ns ± 1% 589ns ± 0% ~ (p=0.659 n=30+25) FmtFprintfInt-4 644ns ± 1% 650ns ± 0% +0.88% (p=0.000 n=30+24) FmtFprintfIntInt-4 964ns ± 0% 977ns ± 0% +1.33% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.06µs ± 0% 1.07µs ± 0% +1.31% (p=0.000 n=29+27) FmtFprintfFloat-4 1.89µs ± 0% 1.92µs ± 0% +1.25% (p=0.000 n=29+29) FmtManyArgs-4 3.63µs ± 0% 3.67µs ± 0% +1.33% (p=0.000 n=29+27) GobDecode-4 38.1ms ± 1% 37.9ms ± 1% -0.60% (p=0.000 n=29+29) GobEncode-4 35.3ms ± 2% 35.2ms ± 1% ~ (p=0.286 n=30+30) Gzip-4 2.36s ± 0% 2.37s ± 2% ~ (p=0.277 n=24+28) Gunzip-4 264ms ± 1% 264ms ± 1% ~ (p=0.104 n=28+30) HTTPClientServer-4 1.04ms ± 4% 1.02ms ± 4% -1.65% (p=0.000 n=28+28) JSONEncode-4 78.5ms ± 1% 79.6ms ± 1% +1.34% (p=0.000 n=27+28) JSONDecode-4 379ms ± 4% 352ms ± 5% -7.09% (p=0.000 n=29+30) Mandelbrot200-4 17.6ms ± 0% 17.6ms ± 0% ~ (p=0.206 n=28+29) GoParse-4 21.9ms ± 1% 22.1ms ± 1% +0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 631ns ± 0% 641ns ± 0% +1.63% (p=0.000 n=29+30) RegexpMatchEasy0_1K-4 4.11µs ± 0% 4.11µs ± 0% ~ (p=0.700 n=30+30) RegexpMatchEasy1_32-4 670ns ± 0% 679ns ± 0% +1.37% (p=0.000 n=21+30) RegexpMatchEasy1_1K-4 5.31µs ± 0% 5.26µs ± 0% -1.03% (p=0.000 n=25+28) RegexpMatchMedium_32-4 905ns ± 0% 906ns ± 0% +0.14% (p=0.001 n=30+30) RegexpMatchMedium_1K-4 192µs ± 0% 191µs ± 0% -0.45% (p=0.000 n=29+27) RegexpMatchHard_32-4 11.8µs ± 0% 11.7µs ± 0% -0.39% (p=0.000 n=29+28) RegexpMatchHard_1K-4 347µs ± 0% 347µs ± 0% ~ (p=0.084 n=29+30) Revcomp-4 37.5ms ± 1% 37.5ms ± 1% ~ (p=0.279 n=29+29) Template-4 519ms ± 2% 519ms ± 2% ~ (p=0.652 n=28+29) TimeParse-4 2.83µs ± 0% 2.78µs ± 0% -1.90% (p=0.000 n=27+28) TimeFormat-4 5.79µs ± 0% 5.60µs ± 0% -3.23% (p=0.000 n=29+29) [Geo mean] 331µs 330µs -0.16% name old speed new speed delta GobDecode-4 20.1MB/s ± 1% 20.3MB/s ± 1% +0.61% (p=0.000 n=29+29) GobEncode-4 21.7MB/s ± 2% 21.8MB/s ± 1% ~ (p=0.294 n=30+30) Gzip-4 8.23MB/s ± 1% 8.20MB/s ± 2% ~ (p=0.099 n=26+28) Gunzip-4 73.5MB/s ± 1% 73.4MB/s ± 1% ~ (p=0.107 n=28+30) JSONEncode-4 24.7MB/s ± 1% 24.4MB/s ± 1% -1.32% (p=0.000 n=27+28) JSONDecode-4 5.13MB/s ± 4% 5.52MB/s ± 5% +7.65% (p=0.000 n=29+30) GoParse-4 2.65MB/s ± 1% 2.63MB/s ± 1% -0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 50.7MB/s ± 0% 49.9MB/s ± 0% -1.58% (p=0.000 n=29+29) RegexpMatchEasy0_1K-4 249MB/s ± 0% 249MB/s ± 0% ~ (p=0.342 n=30+28) RegexpMatchEasy1_32-4 47.7MB/s ± 0% 47.1MB/s ± 0% -1.39% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 193MB/s ± 0% 195MB/s ± 0% +1.04% (p=0.000 n=25+28) RegexpMatchMedium_32-4 1.10MB/s ± 0% 1.10MB/s ± 0% -0.42% (p=0.000 n=30+26) RegexpMatchMedium_1K-4 5.33MB/s ± 0% 5.36MB/s ± 0% +0.43% (p=0.000 n=29+29) RegexpMatchHard_32-4 2.72MB/s ± 0% 2.73MB/s ± 0% +0.37% (p=0.000 n=29+30) RegexpMatchHard_1K-4 2.95MB/s ± 0% 2.95MB/s ± 0% ~ (all equal) Revcomp-4 67.8MB/s ± 1% 67.7MB/s ± 1% ~ (p=0.273 n=29+29) Template-4 3.74MB/s ± 2% 3.74MB/s ± 2% ~ (p=0.665 n=28+29) [Geo mean] 15.2MB/s 15.2MB/s +0.21% Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a Reviewed-on: https://go-review.googlesource.com/132115 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-29 19:19:58 -06:00
// amd64:`TESTQ`,-`ANDQ`
c3 := e&f < 0
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
// arm64:`CMN`,-`ADD`
cmd/compile: optimize ARM's comparision Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits when the result of the addition is no longer used, otherwise there might be even performance drop. And this CL fixes that issue for CMP/CMN/TST/TEQ. There is little regression in the go1 benchmark (excluding noise), and the test case JSONDecode-4 even gets improvement. name old time/op new time/op delta BinaryTree17-4 21.6s ± 1% 21.6s ± 0% -0.22% (p=0.013 n=30+30) Fannkuch11-4 11.1s ± 0% 11.1s ± 0% +0.11% (p=0.000 n=30+29) FmtFprintfEmpty-4 297ns ± 0% 297ns ± 0% +0.08% (p=0.007 n=26+28) FmtFprintfString-4 589ns ± 1% 589ns ± 0% ~ (p=0.659 n=30+25) FmtFprintfInt-4 644ns ± 1% 650ns ± 0% +0.88% (p=0.000 n=30+24) FmtFprintfIntInt-4 964ns ± 0% 977ns ± 0% +1.33% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.06µs ± 0% 1.07µs ± 0% +1.31% (p=0.000 n=29+27) FmtFprintfFloat-4 1.89µs ± 0% 1.92µs ± 0% +1.25% (p=0.000 n=29+29) FmtManyArgs-4 3.63µs ± 0% 3.67µs ± 0% +1.33% (p=0.000 n=29+27) GobDecode-4 38.1ms ± 1% 37.9ms ± 1% -0.60% (p=0.000 n=29+29) GobEncode-4 35.3ms ± 2% 35.2ms ± 1% ~ (p=0.286 n=30+30) Gzip-4 2.36s ± 0% 2.37s ± 2% ~ (p=0.277 n=24+28) Gunzip-4 264ms ± 1% 264ms ± 1% ~ (p=0.104 n=28+30) HTTPClientServer-4 1.04ms ± 4% 1.02ms ± 4% -1.65% (p=0.000 n=28+28) JSONEncode-4 78.5ms ± 1% 79.6ms ± 1% +1.34% (p=0.000 n=27+28) JSONDecode-4 379ms ± 4% 352ms ± 5% -7.09% (p=0.000 n=29+30) Mandelbrot200-4 17.6ms ± 0% 17.6ms ± 0% ~ (p=0.206 n=28+29) GoParse-4 21.9ms ± 1% 22.1ms ± 1% +0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 631ns ± 0% 641ns ± 0% +1.63% (p=0.000 n=29+30) RegexpMatchEasy0_1K-4 4.11µs ± 0% 4.11µs ± 0% ~ (p=0.700 n=30+30) RegexpMatchEasy1_32-4 670ns ± 0% 679ns ± 0% +1.37% (p=0.000 n=21+30) RegexpMatchEasy1_1K-4 5.31µs ± 0% 5.26µs ± 0% -1.03% (p=0.000 n=25+28) RegexpMatchMedium_32-4 905ns ± 0% 906ns ± 0% +0.14% (p=0.001 n=30+30) RegexpMatchMedium_1K-4 192µs ± 0% 191µs ± 0% -0.45% (p=0.000 n=29+27) RegexpMatchHard_32-4 11.8µs ± 0% 11.7µs ± 0% -0.39% (p=0.000 n=29+28) RegexpMatchHard_1K-4 347µs ± 0% 347µs ± 0% ~ (p=0.084 n=29+30) Revcomp-4 37.5ms ± 1% 37.5ms ± 1% ~ (p=0.279 n=29+29) Template-4 519ms ± 2% 519ms ± 2% ~ (p=0.652 n=28+29) TimeParse-4 2.83µs ± 0% 2.78µs ± 0% -1.90% (p=0.000 n=27+28) TimeFormat-4 5.79µs ± 0% 5.60µs ± 0% -3.23% (p=0.000 n=29+29) [Geo mean] 331µs 330µs -0.16% name old speed new speed delta GobDecode-4 20.1MB/s ± 1% 20.3MB/s ± 1% +0.61% (p=0.000 n=29+29) GobEncode-4 21.7MB/s ± 2% 21.8MB/s ± 1% ~ (p=0.294 n=30+30) Gzip-4 8.23MB/s ± 1% 8.20MB/s ± 2% ~ (p=0.099 n=26+28) Gunzip-4 73.5MB/s ± 1% 73.4MB/s ± 1% ~ (p=0.107 n=28+30) JSONEncode-4 24.7MB/s ± 1% 24.4MB/s ± 1% -1.32% (p=0.000 n=27+28) JSONDecode-4 5.13MB/s ± 4% 5.52MB/s ± 5% +7.65% (p=0.000 n=29+30) GoParse-4 2.65MB/s ± 1% 2.63MB/s ± 1% -0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 50.7MB/s ± 0% 49.9MB/s ± 0% -1.58% (p=0.000 n=29+29) RegexpMatchEasy0_1K-4 249MB/s ± 0% 249MB/s ± 0% ~ (p=0.342 n=30+28) RegexpMatchEasy1_32-4 47.7MB/s ± 0% 47.1MB/s ± 0% -1.39% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 193MB/s ± 0% 195MB/s ± 0% +1.04% (p=0.000 n=25+28) RegexpMatchMedium_32-4 1.10MB/s ± 0% 1.10MB/s ± 0% -0.42% (p=0.000 n=30+26) RegexpMatchMedium_1K-4 5.33MB/s ± 0% 5.36MB/s ± 0% +0.43% (p=0.000 n=29+29) RegexpMatchHard_32-4 2.72MB/s ± 0% 2.73MB/s ± 0% +0.37% (p=0.000 n=29+30) RegexpMatchHard_1K-4 2.95MB/s ± 0% 2.95MB/s ± 0% ~ (all equal) Revcomp-4 67.8MB/s ± 1% 67.7MB/s ± 1% ~ (p=0.273 n=29+29) Template-4 3.74MB/s ± 2% 3.74MB/s ± 2% ~ (p=0.665 n=28+29) [Geo mean] 15.2MB/s 15.2MB/s +0.21% Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a Reviewed-on: https://go-review.googlesource.com/132115 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-29 19:19:58 -06:00
c4 := e+f < 0
// not optimized to single CMNW/CMN due to further use of b+d
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
// arm64:`ADD`,-`CMNW`
cmd/compile: optimize ARM's comparision Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits when the result of the addition is no longer used, otherwise there might be even performance drop. And this CL fixes that issue for CMP/CMN/TST/TEQ. There is little regression in the go1 benchmark (excluding noise), and the test case JSONDecode-4 even gets improvement. name old time/op new time/op delta BinaryTree17-4 21.6s ± 1% 21.6s ± 0% -0.22% (p=0.013 n=30+30) Fannkuch11-4 11.1s ± 0% 11.1s ± 0% +0.11% (p=0.000 n=30+29) FmtFprintfEmpty-4 297ns ± 0% 297ns ± 0% +0.08% (p=0.007 n=26+28) FmtFprintfString-4 589ns ± 1% 589ns ± 0% ~ (p=0.659 n=30+25) FmtFprintfInt-4 644ns ± 1% 650ns ± 0% +0.88% (p=0.000 n=30+24) FmtFprintfIntInt-4 964ns ± 0% 977ns ± 0% +1.33% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.06µs ± 0% 1.07µs ± 0% +1.31% (p=0.000 n=29+27) FmtFprintfFloat-4 1.89µs ± 0% 1.92µs ± 0% +1.25% (p=0.000 n=29+29) FmtManyArgs-4 3.63µs ± 0% 3.67µs ± 0% +1.33% (p=0.000 n=29+27) GobDecode-4 38.1ms ± 1% 37.9ms ± 1% -0.60% (p=0.000 n=29+29) GobEncode-4 35.3ms ± 2% 35.2ms ± 1% ~ (p=0.286 n=30+30) Gzip-4 2.36s ± 0% 2.37s ± 2% ~ (p=0.277 n=24+28) Gunzip-4 264ms ± 1% 264ms ± 1% ~ (p=0.104 n=28+30) HTTPClientServer-4 1.04ms ± 4% 1.02ms ± 4% -1.65% (p=0.000 n=28+28) JSONEncode-4 78.5ms ± 1% 79.6ms ± 1% +1.34% (p=0.000 n=27+28) JSONDecode-4 379ms ± 4% 352ms ± 5% -7.09% (p=0.000 n=29+30) Mandelbrot200-4 17.6ms ± 0% 17.6ms ± 0% ~ (p=0.206 n=28+29) GoParse-4 21.9ms ± 1% 22.1ms ± 1% +0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 631ns ± 0% 641ns ± 0% +1.63% (p=0.000 n=29+30) RegexpMatchEasy0_1K-4 4.11µs ± 0% 4.11µs ± 0% ~ (p=0.700 n=30+30) RegexpMatchEasy1_32-4 670ns ± 0% 679ns ± 0% +1.37% (p=0.000 n=21+30) RegexpMatchEasy1_1K-4 5.31µs ± 0% 5.26µs ± 0% -1.03% (p=0.000 n=25+28) RegexpMatchMedium_32-4 905ns ± 0% 906ns ± 0% +0.14% (p=0.001 n=30+30) RegexpMatchMedium_1K-4 192µs ± 0% 191µs ± 0% -0.45% (p=0.000 n=29+27) RegexpMatchHard_32-4 11.8µs ± 0% 11.7µs ± 0% -0.39% (p=0.000 n=29+28) RegexpMatchHard_1K-4 347µs ± 0% 347µs ± 0% ~ (p=0.084 n=29+30) Revcomp-4 37.5ms ± 1% 37.5ms ± 1% ~ (p=0.279 n=29+29) Template-4 519ms ± 2% 519ms ± 2% ~ (p=0.652 n=28+29) TimeParse-4 2.83µs ± 0% 2.78µs ± 0% -1.90% (p=0.000 n=27+28) TimeFormat-4 5.79µs ± 0% 5.60µs ± 0% -3.23% (p=0.000 n=29+29) [Geo mean] 331µs 330µs -0.16% name old speed new speed delta GobDecode-4 20.1MB/s ± 1% 20.3MB/s ± 1% +0.61% (p=0.000 n=29+29) GobEncode-4 21.7MB/s ± 2% 21.8MB/s ± 1% ~ (p=0.294 n=30+30) Gzip-4 8.23MB/s ± 1% 8.20MB/s ± 2% ~ (p=0.099 n=26+28) Gunzip-4 73.5MB/s ± 1% 73.4MB/s ± 1% ~ (p=0.107 n=28+30) JSONEncode-4 24.7MB/s ± 1% 24.4MB/s ± 1% -1.32% (p=0.000 n=27+28) JSONDecode-4 5.13MB/s ± 4% 5.52MB/s ± 5% +7.65% (p=0.000 n=29+30) GoParse-4 2.65MB/s ± 1% 2.63MB/s ± 1% -0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 50.7MB/s ± 0% 49.9MB/s ± 0% -1.58% (p=0.000 n=29+29) RegexpMatchEasy0_1K-4 249MB/s ± 0% 249MB/s ± 0% ~ (p=0.342 n=30+28) RegexpMatchEasy1_32-4 47.7MB/s ± 0% 47.1MB/s ± 0% -1.39% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 193MB/s ± 0% 195MB/s ± 0% +1.04% (p=0.000 n=25+28) RegexpMatchMedium_32-4 1.10MB/s ± 0% 1.10MB/s ± 0% -0.42% (p=0.000 n=30+26) RegexpMatchMedium_1K-4 5.33MB/s ± 0% 5.36MB/s ± 0% +0.43% (p=0.000 n=29+29) RegexpMatchHard_32-4 2.72MB/s ± 0% 2.73MB/s ± 0% +0.37% (p=0.000 n=29+30) RegexpMatchHard_1K-4 2.95MB/s ± 0% 2.95MB/s ± 0% ~ (all equal) Revcomp-4 67.8MB/s ± 1% 67.7MB/s ± 1% ~ (p=0.273 n=29+29) Template-4 3.74MB/s ± 2% 3.74MB/s ± 2% ~ (p=0.665 n=28+29) [Geo mean] 15.2MB/s 15.2MB/s +0.21% Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a Reviewed-on: https://go-review.googlesource.com/132115 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-29 19:19:58 -06:00
// arm:`ADD`,-`CMN`
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
c5 := b+d == 0
cmd/compile: optimize ARM's comparision Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits when the result of the addition is no longer used, otherwise there might be even performance drop. And this CL fixes that issue for CMP/CMN/TST/TEQ. There is little regression in the go1 benchmark (excluding noise), and the test case JSONDecode-4 even gets improvement. name old time/op new time/op delta BinaryTree17-4 21.6s ± 1% 21.6s ± 0% -0.22% (p=0.013 n=30+30) Fannkuch11-4 11.1s ± 0% 11.1s ± 0% +0.11% (p=0.000 n=30+29) FmtFprintfEmpty-4 297ns ± 0% 297ns ± 0% +0.08% (p=0.007 n=26+28) FmtFprintfString-4 589ns ± 1% 589ns ± 0% ~ (p=0.659 n=30+25) FmtFprintfInt-4 644ns ± 1% 650ns ± 0% +0.88% (p=0.000 n=30+24) FmtFprintfIntInt-4 964ns ± 0% 977ns ± 0% +1.33% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.06µs ± 0% 1.07µs ± 0% +1.31% (p=0.000 n=29+27) FmtFprintfFloat-4 1.89µs ± 0% 1.92µs ± 0% +1.25% (p=0.000 n=29+29) FmtManyArgs-4 3.63µs ± 0% 3.67µs ± 0% +1.33% (p=0.000 n=29+27) GobDecode-4 38.1ms ± 1% 37.9ms ± 1% -0.60% (p=0.000 n=29+29) GobEncode-4 35.3ms ± 2% 35.2ms ± 1% ~ (p=0.286 n=30+30) Gzip-4 2.36s ± 0% 2.37s ± 2% ~ (p=0.277 n=24+28) Gunzip-4 264ms ± 1% 264ms ± 1% ~ (p=0.104 n=28+30) HTTPClientServer-4 1.04ms ± 4% 1.02ms ± 4% -1.65% (p=0.000 n=28+28) JSONEncode-4 78.5ms ± 1% 79.6ms ± 1% +1.34% (p=0.000 n=27+28) JSONDecode-4 379ms ± 4% 352ms ± 5% -7.09% (p=0.000 n=29+30) Mandelbrot200-4 17.6ms ± 0% 17.6ms ± 0% ~ (p=0.206 n=28+29) GoParse-4 21.9ms ± 1% 22.1ms ± 1% +0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 631ns ± 0% 641ns ± 0% +1.63% (p=0.000 n=29+30) RegexpMatchEasy0_1K-4 4.11µs ± 0% 4.11µs ± 0% ~ (p=0.700 n=30+30) RegexpMatchEasy1_32-4 670ns ± 0% 679ns ± 0% +1.37% (p=0.000 n=21+30) RegexpMatchEasy1_1K-4 5.31µs ± 0% 5.26µs ± 0% -1.03% (p=0.000 n=25+28) RegexpMatchMedium_32-4 905ns ± 0% 906ns ± 0% +0.14% (p=0.001 n=30+30) RegexpMatchMedium_1K-4 192µs ± 0% 191µs ± 0% -0.45% (p=0.000 n=29+27) RegexpMatchHard_32-4 11.8µs ± 0% 11.7µs ± 0% -0.39% (p=0.000 n=29+28) RegexpMatchHard_1K-4 347µs ± 0% 347µs ± 0% ~ (p=0.084 n=29+30) Revcomp-4 37.5ms ± 1% 37.5ms ± 1% ~ (p=0.279 n=29+29) Template-4 519ms ± 2% 519ms ± 2% ~ (p=0.652 n=28+29) TimeParse-4 2.83µs ± 0% 2.78µs ± 0% -1.90% (p=0.000 n=27+28) TimeFormat-4 5.79µs ± 0% 5.60µs ± 0% -3.23% (p=0.000 n=29+29) [Geo mean] 331µs 330µs -0.16% name old speed new speed delta GobDecode-4 20.1MB/s ± 1% 20.3MB/s ± 1% +0.61% (p=0.000 n=29+29) GobEncode-4 21.7MB/s ± 2% 21.8MB/s ± 1% ~ (p=0.294 n=30+30) Gzip-4 8.23MB/s ± 1% 8.20MB/s ± 2% ~ (p=0.099 n=26+28) Gunzip-4 73.5MB/s ± 1% 73.4MB/s ± 1% ~ (p=0.107 n=28+30) JSONEncode-4 24.7MB/s ± 1% 24.4MB/s ± 1% -1.32% (p=0.000 n=27+28) JSONDecode-4 5.13MB/s ± 4% 5.52MB/s ± 5% +7.65% (p=0.000 n=29+30) GoParse-4 2.65MB/s ± 1% 2.63MB/s ± 1% -0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 50.7MB/s ± 0% 49.9MB/s ± 0% -1.58% (p=0.000 n=29+29) RegexpMatchEasy0_1K-4 249MB/s ± 0% 249MB/s ± 0% ~ (p=0.342 n=30+28) RegexpMatchEasy1_32-4 47.7MB/s ± 0% 47.1MB/s ± 0% -1.39% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 193MB/s ± 0% 195MB/s ± 0% +1.04% (p=0.000 n=25+28) RegexpMatchMedium_32-4 1.10MB/s ± 0% 1.10MB/s ± 0% -0.42% (p=0.000 n=30+26) RegexpMatchMedium_1K-4 5.33MB/s ± 0% 5.36MB/s ± 0% +0.43% (p=0.000 n=29+29) RegexpMatchHard_32-4 2.72MB/s ± 0% 2.73MB/s ± 0% +0.37% (p=0.000 n=29+30) RegexpMatchHard_1K-4 2.95MB/s ± 0% 2.95MB/s ± 0% ~ (all equal) Revcomp-4 67.8MB/s ± 1% 67.7MB/s ± 1% ~ (p=0.273 n=29+29) Template-4 3.74MB/s ± 2% 3.74MB/s ± 2% ~ (p=0.665 n=28+29) [Geo mean] 15.2MB/s 15.2MB/s +0.21% Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a Reviewed-on: https://go-review.googlesource.com/132115 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-29 19:19:58 -06:00
// not optimized to single TSTW/TST due to further use of a&d
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
// arm64:`AND`,-`TSTW`
cmd/compile: optimize ARM's comparision Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits when the result of the addition is no longer used, otherwise there might be even performance drop. And this CL fixes that issue for CMP/CMN/TST/TEQ. There is little regression in the go1 benchmark (excluding noise), and the test case JSONDecode-4 even gets improvement. name old time/op new time/op delta BinaryTree17-4 21.6s ± 1% 21.6s ± 0% -0.22% (p=0.013 n=30+30) Fannkuch11-4 11.1s ± 0% 11.1s ± 0% +0.11% (p=0.000 n=30+29) FmtFprintfEmpty-4 297ns ± 0% 297ns ± 0% +0.08% (p=0.007 n=26+28) FmtFprintfString-4 589ns ± 1% 589ns ± 0% ~ (p=0.659 n=30+25) FmtFprintfInt-4 644ns ± 1% 650ns ± 0% +0.88% (p=0.000 n=30+24) FmtFprintfIntInt-4 964ns ± 0% 977ns ± 0% +1.33% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.06µs ± 0% 1.07µs ± 0% +1.31% (p=0.000 n=29+27) FmtFprintfFloat-4 1.89µs ± 0% 1.92µs ± 0% +1.25% (p=0.000 n=29+29) FmtManyArgs-4 3.63µs ± 0% 3.67µs ± 0% +1.33% (p=0.000 n=29+27) GobDecode-4 38.1ms ± 1% 37.9ms ± 1% -0.60% (p=0.000 n=29+29) GobEncode-4 35.3ms ± 2% 35.2ms ± 1% ~ (p=0.286 n=30+30) Gzip-4 2.36s ± 0% 2.37s ± 2% ~ (p=0.277 n=24+28) Gunzip-4 264ms ± 1% 264ms ± 1% ~ (p=0.104 n=28+30) HTTPClientServer-4 1.04ms ± 4% 1.02ms ± 4% -1.65% (p=0.000 n=28+28) JSONEncode-4 78.5ms ± 1% 79.6ms ± 1% +1.34% (p=0.000 n=27+28) JSONDecode-4 379ms ± 4% 352ms ± 5% -7.09% (p=0.000 n=29+30) Mandelbrot200-4 17.6ms ± 0% 17.6ms ± 0% ~ (p=0.206 n=28+29) GoParse-4 21.9ms ± 1% 22.1ms ± 1% +0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 631ns ± 0% 641ns ± 0% +1.63% (p=0.000 n=29+30) RegexpMatchEasy0_1K-4 4.11µs ± 0% 4.11µs ± 0% ~ (p=0.700 n=30+30) RegexpMatchEasy1_32-4 670ns ± 0% 679ns ± 0% +1.37% (p=0.000 n=21+30) RegexpMatchEasy1_1K-4 5.31µs ± 0% 5.26µs ± 0% -1.03% (p=0.000 n=25+28) RegexpMatchMedium_32-4 905ns ± 0% 906ns ± 0% +0.14% (p=0.001 n=30+30) RegexpMatchMedium_1K-4 192µs ± 0% 191µs ± 0% -0.45% (p=0.000 n=29+27) RegexpMatchHard_32-4 11.8µs ± 0% 11.7µs ± 0% -0.39% (p=0.000 n=29+28) RegexpMatchHard_1K-4 347µs ± 0% 347µs ± 0% ~ (p=0.084 n=29+30) Revcomp-4 37.5ms ± 1% 37.5ms ± 1% ~ (p=0.279 n=29+29) Template-4 519ms ± 2% 519ms ± 2% ~ (p=0.652 n=28+29) TimeParse-4 2.83µs ± 0% 2.78µs ± 0% -1.90% (p=0.000 n=27+28) TimeFormat-4 5.79µs ± 0% 5.60µs ± 0% -3.23% (p=0.000 n=29+29) [Geo mean] 331µs 330µs -0.16% name old speed new speed delta GobDecode-4 20.1MB/s ± 1% 20.3MB/s ± 1% +0.61% (p=0.000 n=29+29) GobEncode-4 21.7MB/s ± 2% 21.8MB/s ± 1% ~ (p=0.294 n=30+30) Gzip-4 8.23MB/s ± 1% 8.20MB/s ± 2% ~ (p=0.099 n=26+28) Gunzip-4 73.5MB/s ± 1% 73.4MB/s ± 1% ~ (p=0.107 n=28+30) JSONEncode-4 24.7MB/s ± 1% 24.4MB/s ± 1% -1.32% (p=0.000 n=27+28) JSONDecode-4 5.13MB/s ± 4% 5.52MB/s ± 5% +7.65% (p=0.000 n=29+30) GoParse-4 2.65MB/s ± 1% 2.63MB/s ± 1% -0.87% (p=0.000 n=28+26) RegexpMatchEasy0_32-4 50.7MB/s ± 0% 49.9MB/s ± 0% -1.58% (p=0.000 n=29+29) RegexpMatchEasy0_1K-4 249MB/s ± 0% 249MB/s ± 0% ~ (p=0.342 n=30+28) RegexpMatchEasy1_32-4 47.7MB/s ± 0% 47.1MB/s ± 0% -1.39% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 193MB/s ± 0% 195MB/s ± 0% +1.04% (p=0.000 n=25+28) RegexpMatchMedium_32-4 1.10MB/s ± 0% 1.10MB/s ± 0% -0.42% (p=0.000 n=30+26) RegexpMatchMedium_1K-4 5.33MB/s ± 0% 5.36MB/s ± 0% +0.43% (p=0.000 n=29+29) RegexpMatchHard_32-4 2.72MB/s ± 0% 2.73MB/s ± 0% +0.37% (p=0.000 n=29+30) RegexpMatchHard_1K-4 2.95MB/s ± 0% 2.95MB/s ± 0% ~ (all equal) Revcomp-4 67.8MB/s ± 1% 67.7MB/s ± 1% ~ (p=0.273 n=29+29) Template-4 3.74MB/s ± 2% 3.74MB/s ± 2% ~ (p=0.665 n=28+29) [Geo mean] 15.2MB/s 15.2MB/s +0.21% Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a Reviewed-on: https://go-review.googlesource.com/132115 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-29 19:19:58 -06:00
// arm:`AND`,-`TST`
cmd/compile: optimize 386's comparison Optimization of "(CMPconst [0] (ANDL x y)) -> (TESTL x y)" only get benefits if there is no further use of the result of x&y. A condition of uses==1 will have slight improvements. 1. The code size of pkg/linux_386 decreases about 300 bytes, excluding cmd/compile/. 2. The go1 benchmark shows no regression, and even a slight improvement in test case FmtFprintfEmpty-4, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.34s ± 3% 3.32s ± 2% ~ (p=0.197 n=30+30) Fannkuch11-4 3.48s ± 2% 3.47s ± 1% -0.33% (p=0.015 n=30+30) FmtFprintfEmpty-4 46.3ns ± 4% 44.8ns ± 4% -3.33% (p=0.000 n=30+30) FmtFprintfString-4 78.8ns ± 7% 77.3ns ± 5% ~ (p=0.098 n=30+26) FmtFprintfInt-4 90.2ns ± 1% 90.0ns ± 7% -0.23% (p=0.027 n=18+30) FmtFprintfIntInt-4 144ns ± 4% 143ns ± 5% ~ (p=0.945 n=30+29) FmtFprintfPrefixedInt-4 180ns ± 4% 180ns ± 5% ~ (p=0.858 n=30+30) FmtFprintfFloat-4 409ns ± 4% 406ns ± 3% -0.87% (p=0.028 n=30+30) FmtManyArgs-4 611ns ± 5% 608ns ± 4% ~ (p=0.812 n=30+30) GobDecode-4 7.30ms ± 5% 7.26ms ± 5% ~ (p=0.522 n=30+29) GobEncode-4 6.90ms ± 7% 6.82ms ± 4% ~ (p=0.086 n=29+28) Gzip-4 396ms ± 4% 400ms ± 4% +0.99% (p=0.026 n=30+30) Gunzip-4 41.1ms ± 3% 41.2ms ± 3% ~ (p=0.495 n=30+30) HTTPClientServer-4 63.7µs ± 3% 63.3µs ± 2% ~ (p=0.113 n=29+29) JSONEncode-4 16.1ms ± 2% 16.1ms ± 2% -0.30% (p=0.041 n=30+30) JSONDecode-4 60.9ms ± 3% 61.2ms ± 6% ~ (p=0.187 n=30+30) Mandelbrot200-4 5.17ms ± 2% 5.19ms ± 3% ~ (p=0.676 n=30+30) GoParse-4 3.28ms ± 3% 3.25ms ± 2% -0.97% (p=0.002 n=30+30) RegexpMatchEasy0_32-4 103ns ± 4% 104ns ± 4% ~ (p=0.352 n=30+30) RegexpMatchEasy0_1K-4 849ns ± 2% 845ns ± 2% ~ (p=0.381 n=30+30) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.795 n=30+30) RegexpMatchEasy1_1K-4 1.03µs ± 3% 1.03µs ± 4% ~ (p=0.275 n=25+30) RegexpMatchMedium_32-4 132ns ± 3% 132ns ± 3% ~ (p=0.970 n=30+30) RegexpMatchMedium_1K-4 41.4µs ± 3% 41.4µs ± 3% ~ (p=0.212 n=30+30) RegexpMatchHard_32-4 2.22µs ± 4% 2.22µs ± 4% ~ (p=0.399 n=30+30) RegexpMatchHard_1K-4 67.2µs ± 3% 67.6µs ± 4% ~ (p=0.359 n=30+30) Revcomp-4 1.84s ± 2% 1.83s ± 2% ~ (p=0.532 n=30+30) Template-4 69.1ms ± 4% 68.8ms ± 3% ~ (p=0.146 n=30+30) TimeParse-4 441ns ± 3% 442ns ± 3% ~ (p=0.154 n=30+30) TimeFormat-4 413ns ± 3% 414ns ± 3% ~ (p=0.275 n=30+30) [Geo mean] 66.2µs 66.0µs -0.28% name old speed new speed delta GobDecode-4 105MB/s ± 5% 106MB/s ± 5% ~ (p=0.514 n=30+29) GobEncode-4 111MB/s ± 5% 113MB/s ± 4% +1.37% (p=0.046 n=28+28) Gzip-4 49.1MB/s ± 4% 48.6MB/s ± 4% -0.98% (p=0.028 n=30+30) Gunzip-4 472MB/s ± 4% 472MB/s ± 3% ~ (p=0.496 n=30+30) JSONEncode-4 120MB/s ± 2% 121MB/s ± 2% +0.29% (p=0.042 n=30+30) JSONDecode-4 31.9MB/s ± 3% 31.7MB/s ± 6% ~ (p=0.186 n=30+30) GoParse-4 17.6MB/s ± 3% 17.8MB/s ± 2% +0.98% (p=0.002 n=30+30) RegexpMatchEasy0_32-4 309MB/s ± 4% 307MB/s ± 4% ~ (p=0.501 n=30+30) RegexpMatchEasy0_1K-4 1.21GB/s ± 2% 1.21GB/s ± 2% ~ (p=0.301 n=30+30) RegexpMatchEasy1_32-4 283MB/s ± 4% 282MB/s ± 3% ~ (p=0.877 n=30+30) RegexpMatchEasy1_1K-4 1.00GB/s ± 3% 0.99GB/s ± 4% ~ (p=0.276 n=25+30) RegexpMatchMedium_32-4 7.54MB/s ± 3% 7.55MB/s ± 3% ~ (p=0.528 n=30+30) RegexpMatchMedium_1K-4 24.7MB/s ± 3% 24.7MB/s ± 3% ~ (p=0.203 n=30+30) RegexpMatchHard_32-4 14.4MB/s ± 4% 14.4MB/s ± 4% ~ (p=0.407 n=30+30) RegexpMatchHard_1K-4 15.3MB/s ± 3% 15.1MB/s ± 4% ~ (p=0.306 n=30+30) Revcomp-4 138MB/s ± 2% 139MB/s ± 2% ~ (p=0.520 n=30+30) Template-4 28.1MB/s ± 4% 28.2MB/s ± 3% ~ (p=0.149 n=30+30) [Geo mean] 81.5MB/s 81.5MB/s +0.06% Change-Id: I7f75425f79eec93cdd8fdd94db13ad4f61b6a2f5 Reviewed-on: https://go-review.googlesource.com/133657 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-09-05 19:13:14 -06:00
// 386:`ANDL`
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
c6 := a&d >= 0
cmd/compile: optimize arm64's code with more shifted operations This CL optimizes arm64's NEG/MVN/TST/CMN with a shifted operand. 1. The total size of pkg/android_arm64 decreases about 0.2KB, excluding cmd/compile/ . 2. The go1 benchmark shows no regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 16.4s ± 1% 16.4s ± 1% ~ (p=0.914 n=29+29) Fannkuch11-4 8.72s ± 0% 8.72s ± 0% ~ (p=0.274 n=30+29) FmtFprintfEmpty-4 174ns ± 0% 174ns ± 0% ~ (all equal) FmtFprintfString-4 370ns ± 0% 370ns ± 0% ~ (all equal) FmtFprintfInt-4 419ns ± 0% 419ns ± 0% ~ (all equal) FmtFprintfIntInt-4 672ns ± 1% 675ns ± 2% ~ (p=0.217 n=28+30) FmtFprintfPrefixedInt-4 806ns ± 0% 806ns ± 0% ~ (p=0.402 n=30+28) FmtFprintfFloat-4 1.09µs ± 0% 1.09µs ± 0% +0.02% (p=0.011 n=22+27) FmtManyArgs-4 2.67µs ± 0% 2.68µs ± 0% ~ (p=0.279 n=29+30) GobDecode-4 33.1ms ± 1% 33.1ms ± 0% ~ (p=0.052 n=28+29) GobEncode-4 29.6ms ± 0% 29.6ms ± 0% +0.08% (p=0.013 n=28+29) Gzip-4 1.38s ± 2% 1.39s ± 2% ~ (p=0.071 n=29+29) Gunzip-4 139ms ± 0% 139ms ± 0% ~ (p=0.265 n=29+29) HTTPClientServer-4 789µs ± 4% 785µs ± 4% ~ (p=0.206 n=29+28) JSONEncode-4 49.7ms ± 0% 49.6ms ± 0% -0.24% (p=0.000 n=30+30) JSONDecode-4 266ms ± 1% 267ms ± 1% +0.34% (p=0.000 n=30+30) Mandelbrot200-4 16.6ms ± 0% 16.6ms ± 0% ~ (p=0.835 n=28+30) GoParse-4 15.9ms ± 0% 15.8ms ± 0% -0.29% (p=0.000 n=27+30) RegexpMatchEasy0_32-4 380ns ± 0% 381ns ± 0% +0.18% (p=0.000 n=30+30) RegexpMatchEasy0_1K-4 1.18µs ± 0% 1.19µs ± 0% +0.23% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 357ns ± 0% 358ns ± 0% +0.28% (p=0.000 n=29+29) RegexpMatchEasy1_1K-4 2.04µs ± 0% 2.04µs ± 0% +0.06% (p=0.006 n=30+30) RegexpMatchMedium_32-4 589ns ± 0% 590ns ± 0% +0.24% (p=0.000 n=28+30) RegexpMatchMedium_1K-4 162µs ± 0% 162µs ± 0% -0.01% (p=0.027 n=26+29) RegexpMatchHard_32-4 9.58µs ± 0% 9.58µs ± 0% ~ (p=0.935 n=30+30) RegexpMatchHard_1K-4 287µs ± 0% 287µs ± 0% ~ (p=0.387 n=29+30) Revcomp-4 2.50s ± 0% 2.50s ± 0% -0.10% (p=0.020 n=28+28) Template-4 310ms ± 0% 310ms ± 1% ~ (p=0.406 n=30+30) TimeParse-4 1.68µs ± 0% 1.68µs ± 0% +0.03% (p=0.014 n=30+17) TimeFormat-4 1.65µs ± 0% 1.66µs ± 0% +0.32% (p=0.000 n=27+29) [Geo mean] 247µs 247µs +0.05% name old speed new speed delta GobDecode-4 23.2MB/s ± 0% 23.2MB/s ± 0% -0.08% (p=0.032 n=27+29) GobEncode-4 26.0MB/s ± 0% 25.9MB/s ± 0% -0.10% (p=0.011 n=29+29) Gzip-4 14.1MB/s ± 2% 14.0MB/s ± 2% ~ (p=0.081 n=29+29) Gunzip-4 139MB/s ± 0% 139MB/s ± 0% ~ (p=0.290 n=29+29) JSONEncode-4 39.0MB/s ± 0% 39.1MB/s ± 0% +0.25% (p=0.000 n=29+30) JSONDecode-4 7.30MB/s ± 1% 7.28MB/s ± 1% -0.33% (p=0.000 n=30+30) GoParse-4 3.65MB/s ± 0% 3.66MB/s ± 0% +0.29% (p=0.000 n=27+30) RegexpMatchEasy0_32-4 84.1MB/s ± 0% 84.0MB/s ± 0% -0.17% (p=0.000 n=30+28) RegexpMatchEasy0_1K-4 864MB/s ± 0% 862MB/s ± 0% -0.24% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 89.5MB/s ± 0% 89.3MB/s ± 0% -0.18% (p=0.000 n=28+24) RegexpMatchEasy1_1K-4 502MB/s ± 0% 502MB/s ± 0% -0.05% (p=0.008 n=30+29) RegexpMatchMedium_32-4 1.70MB/s ± 0% 1.69MB/s ± 0% -0.59% (p=0.000 n=29+30) RegexpMatchMedium_1K-4 6.31MB/s ± 0% 6.31MB/s ± 0% +0.05% (p=0.005 n=30+26) RegexpMatchHard_32-4 3.34MB/s ± 0% 3.34MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 3.57MB/s ± 0% 3.57MB/s ± 0% ~ (all equal) Revcomp-4 102MB/s ± 0% 102MB/s ± 0% +0.10% (p=0.022 n=28+28) Template-4 6.26MB/s ± 0% 6.26MB/s ± 1% ~ (p=0.768 n=30+30) [Geo mean] 24.2MB/s 24.1MB/s -0.08% Change-Id: I494f9db7f8a568a00e9c74ae25086a58b2221683 Reviewed-on: https://go-review.googlesource.com/137976 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-09-27 00:21:14 -06:00
// arm64:`TST\sR[0-9]+<<3,\sR[0-9]+`
c7 := e&(f<<3) < 0
// arm64:`CMN\sR[0-9]+<<3,\sR[0-9]+`
c8 := e+(f<<3) < 0
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
if c0 {
cmd/compile: optimize arm's comparison The CMP/CMN/TST/TEQ perform similar to SUB/ADD/AND/XOR except the result is abondoned, and only NZCV flags are affected. This CL implements further optimization with them. 1. A micro benchmark test gets more than 9% improvment. TSTTEQ-4 6.99ms ± 0% 6.35ms ± 0% -9.15% (p=0.000 n=33+36) (https://github.com/benshi001/ugo1/blob/master/tstteq2_test.go) 2. The go1 benckmark shows no regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 25.7s ± 1% 25.7s ± 1% ~ (p=0.830 n=40+40) Fannkuch11-4 13.3s ± 0% 13.2s ± 0% -0.65% (p=0.000 n=40+34) FmtFprintfEmpty-4 394ns ± 0% 394ns ± 0% ~ (p=0.819 n=40+40) FmtFprintfString-4 677ns ± 0% 677ns ± 0% +0.06% (p=0.039 n=39+40) FmtFprintfInt-4 707ns ± 0% 706ns ± 0% -0.14% (p=0.000 n=40+39) FmtFprintfIntInt-4 1.04µs ± 0% 1.04µs ± 0% +0.10% (p=0.000 n=29+31) FmtFprintfPrefixedInt-4 1.10µs ± 0% 1.11µs ± 0% +0.65% (p=0.000 n=39+37) FmtFprintfFloat-4 2.27µs ± 0% 2.26µs ± 0% -0.53% (p=0.000 n=39+40) FmtManyArgs-4 3.96µs ± 0% 3.96µs ± 0% +0.10% (p=0.000 n=39+40) GobDecode-4 53.4ms ± 1% 52.8ms ± 2% -1.10% (p=0.000 n=39+39) GobEncode-4 50.3ms ± 3% 50.4ms ± 2% ~ (p=0.089 n=40+39) Gzip-4 2.62s ± 0% 2.64s ± 0% +0.60% (p=0.000 n=40+39) Gunzip-4 312ms ± 0% 312ms ± 0% +0.02% (p=0.030 n=40+39) HTTPClientServer-4 1.01ms ± 7% 0.98ms ± 7% -2.37% (p=0.000 n=40+39) JSONEncode-4 126ms ± 1% 126ms ± 1% -0.38% (p=0.004 n=39+39) JSONDecode-4 423ms ± 0% 426ms ± 2% +0.72% (p=0.001 n=39+40) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% +0.04% (p=0.000 n=38+40) GoParse-4 22.8ms ± 0% 22.6ms ± 0% -0.68% (p=0.000 n=35+40) RegexpMatchEasy0_32-4 699ns ± 0% 704ns ± 0% +0.73% (p=0.000 n=27+40) RegexpMatchEasy0_1K-4 4.27µs ± 0% 4.26µs ± 0% -0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 741ns ± 0% 735ns ± 0% -0.85% (p=0.000 n=40+35) RegexpMatchEasy1_1K-4 5.53µs ± 0% 5.49µs ± 0% -0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 1.07µs ± 0% 1.04µs ± 2% -2.34% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 261µs ± 0% 261µs ± 0% -0.16% (p=0.000 n=40+39) RegexpMatchHard_32-4 14.9µs ± 0% 14.9µs ± 0% -0.18% (p=0.000 n=39+40) RegexpMatchHard_1K-4 445µs ± 0% 446µs ± 0% +0.09% (p=0.000 n=36+34) Revcomp-4 41.8ms ± 1% 41.8ms ± 1% ~ (p=0.595 n=39+38) Template-4 530ms ± 1% 528ms ± 1% -0.49% (p=0.000 n=40+40) TimeParse-4 3.39µs ± 0% 3.42µs ± 0% +0.98% (p=0.000 n=36+38) TimeFormat-4 6.12µs ± 0% 6.07µs ± 0% -0.81% (p=0.000 n=34+38) [Geo mean] 384µs 383µs -0.24% name old speed new speed delta GobDecode-4 14.4MB/s ± 1% 14.5MB/s ± 2% +1.11% (p=0.000 n=39+39) GobEncode-4 15.3MB/s ± 3% 15.2MB/s ± 2% ~ (p=0.104 n=40+39) Gzip-4 7.40MB/s ± 1% 7.36MB/s ± 0% -0.60% (p=0.000 n=40+39) Gunzip-4 62.2MB/s ± 0% 62.1MB/s ± 0% -0.02% (p=0.047 n=40+39) JSONEncode-4 15.4MB/s ± 1% 15.4MB/s ± 2% +0.39% (p=0.002 n=39+39) JSONDecode-4 4.59MB/s ± 0% 4.56MB/s ± 2% -0.71% (p=0.000 n=39+40) GoParse-4 2.54MB/s ± 0% 2.56MB/s ± 0% +0.72% (p=0.000 n=26+40) RegexpMatchEasy0_32-4 45.8MB/s ± 0% 45.4MB/s ± 0% -0.75% (p=0.000 n=38+40) RegexpMatchEasy0_1K-4 240MB/s ± 0% 240MB/s ± 0% +0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 43.1MB/s ± 0% 43.5MB/s ± 0% +0.84% (p=0.000 n=40+39) RegexpMatchEasy1_1K-4 185MB/s ± 0% 186MB/s ± 0% +0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 936kB/s ± 1% 959kB/s ± 2% +2.38% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 3.92MB/s ± 0% 3.93MB/s ± 0% +0.18% (p=0.000 n=39+40) RegexpMatchHard_32-4 2.15MB/s ± 0% 2.15MB/s ± 0% +0.19% (p=0.000 n=40+40) RegexpMatchHard_1K-4 2.30MB/s ± 0% 2.30MB/s ± 0% ~ (all equal) Revcomp-4 60.8MB/s ± 1% 60.8MB/s ± 1% ~ (p=0.600 n=39+38) Template-4 3.66MB/s ± 1% 3.68MB/s ± 1% +0.46% (p=0.000 n=40+40) [Geo mean] 12.8MB/s 12.8MB/s +0.27% Change-Id: I849161169ecf0876a04b7c1d3990fa8d1435215e Reviewed-on: https://go-review.googlesource.com/122855 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-09 19:48:55 -06:00
return 1
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
} else if c1 {
cmd/compile: optimize arm's comparison The CMP/CMN/TST/TEQ perform similar to SUB/ADD/AND/XOR except the result is abondoned, and only NZCV flags are affected. This CL implements further optimization with them. 1. A micro benchmark test gets more than 9% improvment. TSTTEQ-4 6.99ms ± 0% 6.35ms ± 0% -9.15% (p=0.000 n=33+36) (https://github.com/benshi001/ugo1/blob/master/tstteq2_test.go) 2. The go1 benckmark shows no regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 25.7s ± 1% 25.7s ± 1% ~ (p=0.830 n=40+40) Fannkuch11-4 13.3s ± 0% 13.2s ± 0% -0.65% (p=0.000 n=40+34) FmtFprintfEmpty-4 394ns ± 0% 394ns ± 0% ~ (p=0.819 n=40+40) FmtFprintfString-4 677ns ± 0% 677ns ± 0% +0.06% (p=0.039 n=39+40) FmtFprintfInt-4 707ns ± 0% 706ns ± 0% -0.14% (p=0.000 n=40+39) FmtFprintfIntInt-4 1.04µs ± 0% 1.04µs ± 0% +0.10% (p=0.000 n=29+31) FmtFprintfPrefixedInt-4 1.10µs ± 0% 1.11µs ± 0% +0.65% (p=0.000 n=39+37) FmtFprintfFloat-4 2.27µs ± 0% 2.26µs ± 0% -0.53% (p=0.000 n=39+40) FmtManyArgs-4 3.96µs ± 0% 3.96µs ± 0% +0.10% (p=0.000 n=39+40) GobDecode-4 53.4ms ± 1% 52.8ms ± 2% -1.10% (p=0.000 n=39+39) GobEncode-4 50.3ms ± 3% 50.4ms ± 2% ~ (p=0.089 n=40+39) Gzip-4 2.62s ± 0% 2.64s ± 0% +0.60% (p=0.000 n=40+39) Gunzip-4 312ms ± 0% 312ms ± 0% +0.02% (p=0.030 n=40+39) HTTPClientServer-4 1.01ms ± 7% 0.98ms ± 7% -2.37% (p=0.000 n=40+39) JSONEncode-4 126ms ± 1% 126ms ± 1% -0.38% (p=0.004 n=39+39) JSONDecode-4 423ms ± 0% 426ms ± 2% +0.72% (p=0.001 n=39+40) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% +0.04% (p=0.000 n=38+40) GoParse-4 22.8ms ± 0% 22.6ms ± 0% -0.68% (p=0.000 n=35+40) RegexpMatchEasy0_32-4 699ns ± 0% 704ns ± 0% +0.73% (p=0.000 n=27+40) RegexpMatchEasy0_1K-4 4.27µs ± 0% 4.26µs ± 0% -0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 741ns ± 0% 735ns ± 0% -0.85% (p=0.000 n=40+35) RegexpMatchEasy1_1K-4 5.53µs ± 0% 5.49µs ± 0% -0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 1.07µs ± 0% 1.04µs ± 2% -2.34% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 261µs ± 0% 261µs ± 0% -0.16% (p=0.000 n=40+39) RegexpMatchHard_32-4 14.9µs ± 0% 14.9µs ± 0% -0.18% (p=0.000 n=39+40) RegexpMatchHard_1K-4 445µs ± 0% 446µs ± 0% +0.09% (p=0.000 n=36+34) Revcomp-4 41.8ms ± 1% 41.8ms ± 1% ~ (p=0.595 n=39+38) Template-4 530ms ± 1% 528ms ± 1% -0.49% (p=0.000 n=40+40) TimeParse-4 3.39µs ± 0% 3.42µs ± 0% +0.98% (p=0.000 n=36+38) TimeFormat-4 6.12µs ± 0% 6.07µs ± 0% -0.81% (p=0.000 n=34+38) [Geo mean] 384µs 383µs -0.24% name old speed new speed delta GobDecode-4 14.4MB/s ± 1% 14.5MB/s ± 2% +1.11% (p=0.000 n=39+39) GobEncode-4 15.3MB/s ± 3% 15.2MB/s ± 2% ~ (p=0.104 n=40+39) Gzip-4 7.40MB/s ± 1% 7.36MB/s ± 0% -0.60% (p=0.000 n=40+39) Gunzip-4 62.2MB/s ± 0% 62.1MB/s ± 0% -0.02% (p=0.047 n=40+39) JSONEncode-4 15.4MB/s ± 1% 15.4MB/s ± 2% +0.39% (p=0.002 n=39+39) JSONDecode-4 4.59MB/s ± 0% 4.56MB/s ± 2% -0.71% (p=0.000 n=39+40) GoParse-4 2.54MB/s ± 0% 2.56MB/s ± 0% +0.72% (p=0.000 n=26+40) RegexpMatchEasy0_32-4 45.8MB/s ± 0% 45.4MB/s ± 0% -0.75% (p=0.000 n=38+40) RegexpMatchEasy0_1K-4 240MB/s ± 0% 240MB/s ± 0% +0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 43.1MB/s ± 0% 43.5MB/s ± 0% +0.84% (p=0.000 n=40+39) RegexpMatchEasy1_1K-4 185MB/s ± 0% 186MB/s ± 0% +0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 936kB/s ± 1% 959kB/s ± 2% +2.38% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 3.92MB/s ± 0% 3.93MB/s ± 0% +0.18% (p=0.000 n=39+40) RegexpMatchHard_32-4 2.15MB/s ± 0% 2.15MB/s ± 0% +0.19% (p=0.000 n=40+40) RegexpMatchHard_1K-4 2.30MB/s ± 0% 2.30MB/s ± 0% ~ (all equal) Revcomp-4 60.8MB/s ± 1% 60.8MB/s ± 1% ~ (p=0.600 n=39+38) Template-4 3.66MB/s ± 1% 3.68MB/s ± 1% +0.46% (p=0.000 n=40+40) [Geo mean] 12.8MB/s 12.8MB/s +0.27% Change-Id: I849161169ecf0876a04b7c1d3990fa8d1435215e Reviewed-on: https://go-review.googlesource.com/122855 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-09 19:48:55 -06:00
return 2
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
} else if c2 {
cmd/compile: optimize arm's comparison The CMP/CMN/TST/TEQ perform similar to SUB/ADD/AND/XOR except the result is abondoned, and only NZCV flags are affected. This CL implements further optimization with them. 1. A micro benchmark test gets more than 9% improvment. TSTTEQ-4 6.99ms ± 0% 6.35ms ± 0% -9.15% (p=0.000 n=33+36) (https://github.com/benshi001/ugo1/blob/master/tstteq2_test.go) 2. The go1 benckmark shows no regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 25.7s ± 1% 25.7s ± 1% ~ (p=0.830 n=40+40) Fannkuch11-4 13.3s ± 0% 13.2s ± 0% -0.65% (p=0.000 n=40+34) FmtFprintfEmpty-4 394ns ± 0% 394ns ± 0% ~ (p=0.819 n=40+40) FmtFprintfString-4 677ns ± 0% 677ns ± 0% +0.06% (p=0.039 n=39+40) FmtFprintfInt-4 707ns ± 0% 706ns ± 0% -0.14% (p=0.000 n=40+39) FmtFprintfIntInt-4 1.04µs ± 0% 1.04µs ± 0% +0.10% (p=0.000 n=29+31) FmtFprintfPrefixedInt-4 1.10µs ± 0% 1.11µs ± 0% +0.65% (p=0.000 n=39+37) FmtFprintfFloat-4 2.27µs ± 0% 2.26µs ± 0% -0.53% (p=0.000 n=39+40) FmtManyArgs-4 3.96µs ± 0% 3.96µs ± 0% +0.10% (p=0.000 n=39+40) GobDecode-4 53.4ms ± 1% 52.8ms ± 2% -1.10% (p=0.000 n=39+39) GobEncode-4 50.3ms ± 3% 50.4ms ± 2% ~ (p=0.089 n=40+39) Gzip-4 2.62s ± 0% 2.64s ± 0% +0.60% (p=0.000 n=40+39) Gunzip-4 312ms ± 0% 312ms ± 0% +0.02% (p=0.030 n=40+39) HTTPClientServer-4 1.01ms ± 7% 0.98ms ± 7% -2.37% (p=0.000 n=40+39) JSONEncode-4 126ms ± 1% 126ms ± 1% -0.38% (p=0.004 n=39+39) JSONDecode-4 423ms ± 0% 426ms ± 2% +0.72% (p=0.001 n=39+40) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% +0.04% (p=0.000 n=38+40) GoParse-4 22.8ms ± 0% 22.6ms ± 0% -0.68% (p=0.000 n=35+40) RegexpMatchEasy0_32-4 699ns ± 0% 704ns ± 0% +0.73% (p=0.000 n=27+40) RegexpMatchEasy0_1K-4 4.27µs ± 0% 4.26µs ± 0% -0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 741ns ± 0% 735ns ± 0% -0.85% (p=0.000 n=40+35) RegexpMatchEasy1_1K-4 5.53µs ± 0% 5.49µs ± 0% -0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 1.07µs ± 0% 1.04µs ± 2% -2.34% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 261µs ± 0% 261µs ± 0% -0.16% (p=0.000 n=40+39) RegexpMatchHard_32-4 14.9µs ± 0% 14.9µs ± 0% -0.18% (p=0.000 n=39+40) RegexpMatchHard_1K-4 445µs ± 0% 446µs ± 0% +0.09% (p=0.000 n=36+34) Revcomp-4 41.8ms ± 1% 41.8ms ± 1% ~ (p=0.595 n=39+38) Template-4 530ms ± 1% 528ms ± 1% -0.49% (p=0.000 n=40+40) TimeParse-4 3.39µs ± 0% 3.42µs ± 0% +0.98% (p=0.000 n=36+38) TimeFormat-4 6.12µs ± 0% 6.07µs ± 0% -0.81% (p=0.000 n=34+38) [Geo mean] 384µs 383µs -0.24% name old speed new speed delta GobDecode-4 14.4MB/s ± 1% 14.5MB/s ± 2% +1.11% (p=0.000 n=39+39) GobEncode-4 15.3MB/s ± 3% 15.2MB/s ± 2% ~ (p=0.104 n=40+39) Gzip-4 7.40MB/s ± 1% 7.36MB/s ± 0% -0.60% (p=0.000 n=40+39) Gunzip-4 62.2MB/s ± 0% 62.1MB/s ± 0% -0.02% (p=0.047 n=40+39) JSONEncode-4 15.4MB/s ± 1% 15.4MB/s ± 2% +0.39% (p=0.002 n=39+39) JSONDecode-4 4.59MB/s ± 0% 4.56MB/s ± 2% -0.71% (p=0.000 n=39+40) GoParse-4 2.54MB/s ± 0% 2.56MB/s ± 0% +0.72% (p=0.000 n=26+40) RegexpMatchEasy0_32-4 45.8MB/s ± 0% 45.4MB/s ± 0% -0.75% (p=0.000 n=38+40) RegexpMatchEasy0_1K-4 240MB/s ± 0% 240MB/s ± 0% +0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 43.1MB/s ± 0% 43.5MB/s ± 0% +0.84% (p=0.000 n=40+39) RegexpMatchEasy1_1K-4 185MB/s ± 0% 186MB/s ± 0% +0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 936kB/s ± 1% 959kB/s ± 2% +2.38% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 3.92MB/s ± 0% 3.93MB/s ± 0% +0.18% (p=0.000 n=39+40) RegexpMatchHard_32-4 2.15MB/s ± 0% 2.15MB/s ± 0% +0.19% (p=0.000 n=40+40) RegexpMatchHard_1K-4 2.30MB/s ± 0% 2.30MB/s ± 0% ~ (all equal) Revcomp-4 60.8MB/s ± 1% 60.8MB/s ± 1% ~ (p=0.600 n=39+38) Template-4 3.66MB/s ± 1% 3.68MB/s ± 1% +0.46% (p=0.000 n=40+40) [Geo mean] 12.8MB/s 12.8MB/s +0.27% Change-Id: I849161169ecf0876a04b7c1d3990fa8d1435215e Reviewed-on: https://go-review.googlesource.com/122855 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-09 19:48:55 -06:00
return 3
cmd/compile: optimize arm64's comparison Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-19 02:09:13 -06:00
} else if c3 {
return 4
} else if c4 {
return 5
} else if c5 {
return b + d
} else if c6 {
return a & d
cmd/compile: optimize arm64's code with more shifted operations This CL optimizes arm64's NEG/MVN/TST/CMN with a shifted operand. 1. The total size of pkg/android_arm64 decreases about 0.2KB, excluding cmd/compile/ . 2. The go1 benchmark shows no regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 16.4s ± 1% 16.4s ± 1% ~ (p=0.914 n=29+29) Fannkuch11-4 8.72s ± 0% 8.72s ± 0% ~ (p=0.274 n=30+29) FmtFprintfEmpty-4 174ns ± 0% 174ns ± 0% ~ (all equal) FmtFprintfString-4 370ns ± 0% 370ns ± 0% ~ (all equal) FmtFprintfInt-4 419ns ± 0% 419ns ± 0% ~ (all equal) FmtFprintfIntInt-4 672ns ± 1% 675ns ± 2% ~ (p=0.217 n=28+30) FmtFprintfPrefixedInt-4 806ns ± 0% 806ns ± 0% ~ (p=0.402 n=30+28) FmtFprintfFloat-4 1.09µs ± 0% 1.09µs ± 0% +0.02% (p=0.011 n=22+27) FmtManyArgs-4 2.67µs ± 0% 2.68µs ± 0% ~ (p=0.279 n=29+30) GobDecode-4 33.1ms ± 1% 33.1ms ± 0% ~ (p=0.052 n=28+29) GobEncode-4 29.6ms ± 0% 29.6ms ± 0% +0.08% (p=0.013 n=28+29) Gzip-4 1.38s ± 2% 1.39s ± 2% ~ (p=0.071 n=29+29) Gunzip-4 139ms ± 0% 139ms ± 0% ~ (p=0.265 n=29+29) HTTPClientServer-4 789µs ± 4% 785µs ± 4% ~ (p=0.206 n=29+28) JSONEncode-4 49.7ms ± 0% 49.6ms ± 0% -0.24% (p=0.000 n=30+30) JSONDecode-4 266ms ± 1% 267ms ± 1% +0.34% (p=0.000 n=30+30) Mandelbrot200-4 16.6ms ± 0% 16.6ms ± 0% ~ (p=0.835 n=28+30) GoParse-4 15.9ms ± 0% 15.8ms ± 0% -0.29% (p=0.000 n=27+30) RegexpMatchEasy0_32-4 380ns ± 0% 381ns ± 0% +0.18% (p=0.000 n=30+30) RegexpMatchEasy0_1K-4 1.18µs ± 0% 1.19µs ± 0% +0.23% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 357ns ± 0% 358ns ± 0% +0.28% (p=0.000 n=29+29) RegexpMatchEasy1_1K-4 2.04µs ± 0% 2.04µs ± 0% +0.06% (p=0.006 n=30+30) RegexpMatchMedium_32-4 589ns ± 0% 590ns ± 0% +0.24% (p=0.000 n=28+30) RegexpMatchMedium_1K-4 162µs ± 0% 162µs ± 0% -0.01% (p=0.027 n=26+29) RegexpMatchHard_32-4 9.58µs ± 0% 9.58µs ± 0% ~ (p=0.935 n=30+30) RegexpMatchHard_1K-4 287µs ± 0% 287µs ± 0% ~ (p=0.387 n=29+30) Revcomp-4 2.50s ± 0% 2.50s ± 0% -0.10% (p=0.020 n=28+28) Template-4 310ms ± 0% 310ms ± 1% ~ (p=0.406 n=30+30) TimeParse-4 1.68µs ± 0% 1.68µs ± 0% +0.03% (p=0.014 n=30+17) TimeFormat-4 1.65µs ± 0% 1.66µs ± 0% +0.32% (p=0.000 n=27+29) [Geo mean] 247µs 247µs +0.05% name old speed new speed delta GobDecode-4 23.2MB/s ± 0% 23.2MB/s ± 0% -0.08% (p=0.032 n=27+29) GobEncode-4 26.0MB/s ± 0% 25.9MB/s ± 0% -0.10% (p=0.011 n=29+29) Gzip-4 14.1MB/s ± 2% 14.0MB/s ± 2% ~ (p=0.081 n=29+29) Gunzip-4 139MB/s ± 0% 139MB/s ± 0% ~ (p=0.290 n=29+29) JSONEncode-4 39.0MB/s ± 0% 39.1MB/s ± 0% +0.25% (p=0.000 n=29+30) JSONDecode-4 7.30MB/s ± 1% 7.28MB/s ± 1% -0.33% (p=0.000 n=30+30) GoParse-4 3.65MB/s ± 0% 3.66MB/s ± 0% +0.29% (p=0.000 n=27+30) RegexpMatchEasy0_32-4 84.1MB/s ± 0% 84.0MB/s ± 0% -0.17% (p=0.000 n=30+28) RegexpMatchEasy0_1K-4 864MB/s ± 0% 862MB/s ± 0% -0.24% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 89.5MB/s ± 0% 89.3MB/s ± 0% -0.18% (p=0.000 n=28+24) RegexpMatchEasy1_1K-4 502MB/s ± 0% 502MB/s ± 0% -0.05% (p=0.008 n=30+29) RegexpMatchMedium_32-4 1.70MB/s ± 0% 1.69MB/s ± 0% -0.59% (p=0.000 n=29+30) RegexpMatchMedium_1K-4 6.31MB/s ± 0% 6.31MB/s ± 0% +0.05% (p=0.005 n=30+26) RegexpMatchHard_32-4 3.34MB/s ± 0% 3.34MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 3.57MB/s ± 0% 3.57MB/s ± 0% ~ (all equal) Revcomp-4 102MB/s ± 0% 102MB/s ± 0% +0.10% (p=0.022 n=28+28) Template-4 6.26MB/s ± 0% 6.26MB/s ± 1% ~ (p=0.768 n=30+30) [Geo mean] 24.2MB/s 24.1MB/s -0.08% Change-Id: I494f9db7f8a568a00e9c74ae25086a58b2221683 Reviewed-on: https://go-review.googlesource.com/137976 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-09-27 00:21:14 -06:00
} else if c7 {
return 7
} else if c8 {
return 8
cmd/compile: optimize arm's comparison The CMP/CMN/TST/TEQ perform similar to SUB/ADD/AND/XOR except the result is abondoned, and only NZCV flags are affected. This CL implements further optimization with them. 1. A micro benchmark test gets more than 9% improvment. TSTTEQ-4 6.99ms ± 0% 6.35ms ± 0% -9.15% (p=0.000 n=33+36) (https://github.com/benshi001/ugo1/blob/master/tstteq2_test.go) 2. The go1 benckmark shows no regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 25.7s ± 1% 25.7s ± 1% ~ (p=0.830 n=40+40) Fannkuch11-4 13.3s ± 0% 13.2s ± 0% -0.65% (p=0.000 n=40+34) FmtFprintfEmpty-4 394ns ± 0% 394ns ± 0% ~ (p=0.819 n=40+40) FmtFprintfString-4 677ns ± 0% 677ns ± 0% +0.06% (p=0.039 n=39+40) FmtFprintfInt-4 707ns ± 0% 706ns ± 0% -0.14% (p=0.000 n=40+39) FmtFprintfIntInt-4 1.04µs ± 0% 1.04µs ± 0% +0.10% (p=0.000 n=29+31) FmtFprintfPrefixedInt-4 1.10µs ± 0% 1.11µs ± 0% +0.65% (p=0.000 n=39+37) FmtFprintfFloat-4 2.27µs ± 0% 2.26µs ± 0% -0.53% (p=0.000 n=39+40) FmtManyArgs-4 3.96µs ± 0% 3.96µs ± 0% +0.10% (p=0.000 n=39+40) GobDecode-4 53.4ms ± 1% 52.8ms ± 2% -1.10% (p=0.000 n=39+39) GobEncode-4 50.3ms ± 3% 50.4ms ± 2% ~ (p=0.089 n=40+39) Gzip-4 2.62s ± 0% 2.64s ± 0% +0.60% (p=0.000 n=40+39) Gunzip-4 312ms ± 0% 312ms ± 0% +0.02% (p=0.030 n=40+39) HTTPClientServer-4 1.01ms ± 7% 0.98ms ± 7% -2.37% (p=0.000 n=40+39) JSONEncode-4 126ms ± 1% 126ms ± 1% -0.38% (p=0.004 n=39+39) JSONDecode-4 423ms ± 0% 426ms ± 2% +0.72% (p=0.001 n=39+40) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% +0.04% (p=0.000 n=38+40) GoParse-4 22.8ms ± 0% 22.6ms ± 0% -0.68% (p=0.000 n=35+40) RegexpMatchEasy0_32-4 699ns ± 0% 704ns ± 0% +0.73% (p=0.000 n=27+40) RegexpMatchEasy0_1K-4 4.27µs ± 0% 4.26µs ± 0% -0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 741ns ± 0% 735ns ± 0% -0.85% (p=0.000 n=40+35) RegexpMatchEasy1_1K-4 5.53µs ± 0% 5.49µs ± 0% -0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 1.07µs ± 0% 1.04µs ± 2% -2.34% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 261µs ± 0% 261µs ± 0% -0.16% (p=0.000 n=40+39) RegexpMatchHard_32-4 14.9µs ± 0% 14.9µs ± 0% -0.18% (p=0.000 n=39+40) RegexpMatchHard_1K-4 445µs ± 0% 446µs ± 0% +0.09% (p=0.000 n=36+34) Revcomp-4 41.8ms ± 1% 41.8ms ± 1% ~ (p=0.595 n=39+38) Template-4 530ms ± 1% 528ms ± 1% -0.49% (p=0.000 n=40+40) TimeParse-4 3.39µs ± 0% 3.42µs ± 0% +0.98% (p=0.000 n=36+38) TimeFormat-4 6.12µs ± 0% 6.07µs ± 0% -0.81% (p=0.000 n=34+38) [Geo mean] 384µs 383µs -0.24% name old speed new speed delta GobDecode-4 14.4MB/s ± 1% 14.5MB/s ± 2% +1.11% (p=0.000 n=39+39) GobEncode-4 15.3MB/s ± 3% 15.2MB/s ± 2% ~ (p=0.104 n=40+39) Gzip-4 7.40MB/s ± 1% 7.36MB/s ± 0% -0.60% (p=0.000 n=40+39) Gunzip-4 62.2MB/s ± 0% 62.1MB/s ± 0% -0.02% (p=0.047 n=40+39) JSONEncode-4 15.4MB/s ± 1% 15.4MB/s ± 2% +0.39% (p=0.002 n=39+39) JSONDecode-4 4.59MB/s ± 0% 4.56MB/s ± 2% -0.71% (p=0.000 n=39+40) GoParse-4 2.54MB/s ± 0% 2.56MB/s ± 0% +0.72% (p=0.000 n=26+40) RegexpMatchEasy0_32-4 45.8MB/s ± 0% 45.4MB/s ± 0% -0.75% (p=0.000 n=38+40) RegexpMatchEasy0_1K-4 240MB/s ± 0% 240MB/s ± 0% +0.09% (p=0.000 n=35+38) RegexpMatchEasy1_32-4 43.1MB/s ± 0% 43.5MB/s ± 0% +0.84% (p=0.000 n=40+39) RegexpMatchEasy1_1K-4 185MB/s ± 0% 186MB/s ± 0% +0.69% (p=0.000 n=39+40) RegexpMatchMedium_32-4 936kB/s ± 1% 959kB/s ± 2% +2.38% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 3.92MB/s ± 0% 3.93MB/s ± 0% +0.18% (p=0.000 n=39+40) RegexpMatchHard_32-4 2.15MB/s ± 0% 2.15MB/s ± 0% +0.19% (p=0.000 n=40+40) RegexpMatchHard_1K-4 2.30MB/s ± 0% 2.30MB/s ± 0% ~ (all equal) Revcomp-4 60.8MB/s ± 1% 60.8MB/s ± 1% ~ (p=0.600 n=39+38) Template-4 3.66MB/s ± 1% 3.68MB/s ± 1% +0.46% (p=0.000 n=40+40) [Geo mean] 12.8MB/s 12.8MB/s +0.27% Change-Id: I849161169ecf0876a04b7c1d3990fa8d1435215e Reviewed-on: https://go-review.googlesource.com/122855 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-09 19:48:55 -06:00
} else {
return 0
}
}
func CmpLogicalToZero(a, b, c uint32, d, e uint64) uint64 {
// ppc64:"ANDCC",-"CMPW"
// ppc64le:"ANDCC",-"CMPW"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if a&63 == 0 {
return 1
}
// ppc64:"ANDCC",-"CMP"
// ppc64le:"ANDCC",-"CMP"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if d&255 == 0 {
return 1
}
// ppc64:"ANDCC",-"CMP"
// ppc64le:"ANDCC",-"CMP"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if d&e == 0 {
return 1
}
// ppc64:"ORCC",-"CMP"
// ppc64le:"ORCC",-"CMP"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if d|e == 0 {
return 1
}
// ppc64:"XORCC",-"CMP"
// ppc64le:"XORCC",-"CMP"
// wasm:"I64Eqz","I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if e^d == 0 {
return 1
}
return 0
}
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
// The following CmpToZero_ex* check that cmp|cmn with bmi|bpl are generated for
// 'comparing to zero' expressions
// var + const
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// 'x-const' might be canonicalized to 'x+(-const)', so we check both
// CMN and CMP for subtraction expressions to make the pattern robust.
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
func CmpToZero_ex1(a int64, e int32) int {
// arm64:`CMN`,-`ADD`,`(BMI|BPL)`
if a+3 < 0 {
return 1
}
// arm64:`CMN`,-`ADD`,`BEQ`,`(BMI|BPL)`
if a+5 <= 0 {
return 1
}
// arm64:`CMN`,-`ADD`,`(BMI|BPL)`
if a+13 >= 0 {
return 2
}
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm64:`CMP|CMN`,-`(ADD|SUB)`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if a-7 < 0 {
return 3
}
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm64:`CMP|CMN`,-`(ADD|SUB)`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if a-11 >= 0 {
return 4
}
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm64:`CMP|CMN`,-`(ADD|SUB)`,`BEQ`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if a-19 > 0 {
return 4
}
// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)`
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm:`CMN`,-`ADD`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if e+3 < 0 {
return 5
}
// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)`
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm:`CMN`,-`ADD`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if e+13 >= 0 {
return 6
}
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm64:`CMPW|CMNW`,`(BMI|BPL)`
// arm:`CMP|CMN`, -`(ADD|SUB)`, `(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if e-7 < 0 {
return 7
}
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm64:`CMPW|CMNW`,`(BMI|BPL)`
// arm:`CMP|CMN`, -`(ADD|SUB)`, `(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if e-11 >= 0 {
return 8
}
return 0
}
// var + var
// TODO: optimize 'var - var'
func CmpToZero_ex2(a, b, c int64, e, f, g int32) int {
// arm64:`CMN`,-`ADD`,`(BMI|BPL)`
if a+b < 0 {
return 1
}
// arm64:`CMN`,-`ADD`,`BEQ`,`(BMI|BPL)`
if a+c <= 0 {
return 1
}
// arm64:`CMN`,-`ADD`,`(BMI|BPL)`
if b+c >= 0 {
return 2
}
// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)`
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm:`CMN`,-`ADD`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if e+f < 0 {
return 5
}
// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)`
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm:`CMN`,-`ADD`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if f+g >= 0 {
return 6
}
return 0
}
// var + var*var
func CmpToZero_ex3(a, b, c, d int64, e, f, g, h int32) int {
// arm64:`CMN`,-`MADD`,`MUL`,`(BMI|BPL)`
if a+b*c < 0 {
return 1
}
// arm64:`CMN`,-`MADD`,`MUL`,`(BMI|BPL)`
if b+c*d >= 0 {
return 2
}
// arm64:`CMNW`,-`MADDW`,`MULW`,`BEQ`,`(BMI|BPL)`
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm:`CMN`,-`MULA`,`MUL`,`BEQ`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if e+f*g > 0 {
return 5
}
// arm64:`CMNW`,-`MADDW`,`MULW`,`BEQ`,`(BMI|BPL)`
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
// arm:`CMN`,-`MULA`,`MUL`,`BEQ`,`(BMI|BPL)`
cmd/compile: fix incorrect rewriting to if condition Some ARM64 rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag, in the following categories: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The backend generates two consecutive branch instructions for 'LEnoov' and 'GTnoov' to model their expected behavior. A slight change to 'gc' and amd64/386 backends is made to unify the code generation. Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules identified on arm64, more might be needed on other arches, like 32-bit arm. Add two benchmarks profiling the aforementioned category 1&2 and category 3&4 separetely, we expect the first two categories will show performance improvement and the second will not result in visible regression compared with the non-optimized version. This change also updates TestFormats to support using %#x. Examples exhibiting where does the issue come from: 1: 'if x + 3 < 0' might be converted to: before: CMN $3, R0 BGE <else branch> // wrong branch is taken if 'x+3' overflows after: CMN $3, R0 BPL <else branch> 2: 'if y - 3 > 0' might be converted to: before: CMP $3, R0 BLE <else branch> // wrong branch is taken if 'y-3' underflows after: CMP $3, R0 BMI <else branch> BEQ <else branch> Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized version (not the parent commit), generally the optimization version outperforms. S1: name old time/op new time/op delta CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10) CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10) S2: name old time/op new time/op delta CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10) CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10) S3: name old time/op new time/op delta CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10) CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9) S4: name old time/op new time/op delta CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10) CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10) S5: name old time/op new time/op delta CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10) CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9) Go1 perf. data: name old time/op new time/op delta BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5) Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5) FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5) FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5) FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5) FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5) FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5) FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5) FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5) GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5) GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5) Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5) Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5) HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4) JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5) JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5) Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5) GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5) RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal) RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5) RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4) RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5) RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal) RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5) RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5) RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5) Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5) Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5) TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5) TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5) Updates #38740 Change-Id: I06c604874acdc1e63e66452dadee5df053045222 Reviewed-on: https://go-review.googlesource.com/c/go/+/233097 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org>
2020-05-06 03:54:40 -06:00
if f+g*h <= 0 {
return 6
}
return 0
}
// var - var*var
func CmpToZero_ex4(a, b, c, d int64, e, f, g, h int32) int {
// arm64:`CMP`,-`MSUB`,`MUL`,`BEQ`,`(BMI|BPL)`
if a-b*c > 0 {
return 1
}
// arm64:`CMP`,-`MSUB`,`MUL`,`(BMI|BPL)`
if b-c*d >= 0 {
return 2
}
// arm64:`CMPW`,-`MSUBW`,`MULW`,`(BMI|BPL)`
if e-f*g < 0 {
return 5
}
// arm64:`CMPW`,-`MSUBW`,`MULW`,`(BMI|BPL)`
if f-g*h >= 0 {
return 6
}
return 0
}
cmd/compile: ARM comparisons with 0 incorrect on overflow Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-06-01 05:01:14 -06:00
func CmpToZero_ex5(e, f int32, u uint32) int {
// arm:`CMN`,-`ADD`,`BEQ`,`(BMI|BPL)`
if e+f<<1 > 0 {
return 1
}
// arm:`CMP`,-`SUB`,`(BMI|BPL)`
if f-int32(u>>2) >= 0 {
return 2
}
return 0
}
func UintLtZero(a uint8, b uint16, c uint32, d uint64) int {
// amd64: -`(TESTB|TESTW|TESTL|TESTQ|JCC|JCS)`
// arm64: -`(CMPW|CMP|BHS|BLO)`
if a < 0 || b < 0 || c < 0 || d < 0 {
return 1
}
return 0
}
func UintGeqZero(a uint8, b uint16, c uint32, d uint64) int {
// amd64: -`(TESTB|TESTW|TESTL|TESTQ|JCS|JCC)`
// arm64: -`(CMPW|CMP|BLO|BHS)`
if a >= 0 || b >= 0 || c >= 0 || d >= 0 {
return 1
}
return 0
}
func UintGtZero(a uint8, b uint16, c uint32, d uint64) int {
// arm64: `CBZW`, `CBNZW`, `CBNZ`, -`(CMPW|CMP|BLS|BHI)`
if a > 0 || b > 0 || c > 0 || d > 0 {
return 1
}
return 0
}
func UintLeqZero(a uint8, b uint16, c uint32, d uint64) int {
// arm64: `CBNZW`, `CBZW`, `CBZ`, -`(CMPW|CMP|BHI|BLS)`
if a <= 0 || b <= 0 || c <= 0 || d <= 0 {
return 1
}
return 0
}
func UintLtOne(a uint8, b uint16, c uint32, d uint64) int {
// arm64: `CBNZW`, `CBZW`, `CBZW`, `CBZ`, -`(CMPW|CMP|BHS|BLO)`
if a < 1 || b < 1 || c < 1 || d < 1 {
return 1
}
return 0
}
func UintGeqOne(a uint8, b uint16, c uint32, d uint64) int {
// arm64: `CBZW`, `CBNZW`, `CBNZ`, -`(CMPW|CMP|BLO|BHS)`
if a >= 1 || b >= 1 || c >= 1 || d >= 1 {
return 1
}
return 0
}
func CmpToZeroU_ex1(a uint8, b uint16, c uint32, d uint64) int {
// wasm:"I64Eqz"-"I64LtU"
if 0 < a {
return 1
}
// wasm:"I64Eqz"-"I64LtU"
if 0 < b {
return 1
}
// wasm:"I64Eqz"-"I64LtU"
if 0 < c {
return 1
}
// wasm:"I64Eqz"-"I64LtU"
if 0 < d {
return 1
}
return 0
}
func CmpToZeroU_ex2(a uint8, b uint16, c uint32, d uint64) int {
// wasm:"I64Eqz"-"I64LeU"
if a <= 0 {
return 1
}
// wasm:"I64Eqz"-"I64LeU"
if b <= 0 {
return 1
}
// wasm:"I64Eqz"-"I64LeU"
if c <= 0 {
return 1
}
// wasm:"I64Eqz"-"I64LeU"
if d <= 0 {
return 1
}
return 0
}
func CmpToOneU_ex1(a uint8, b uint16, c uint32, d uint64) int {
// wasm:"I64Eqz"-"I64LtU"
if a < 1 {
return 1
}
// wasm:"I64Eqz"-"I64LtU"
if b < 1 {
return 1
}
// wasm:"I64Eqz"-"I64LtU"
if c < 1 {
return 1
}
// wasm:"I64Eqz"-"I64LtU"
if d < 1 {
return 1
}
return 0
}
func CmpToOneU_ex2(a uint8, b uint16, c uint32, d uint64) int {
// wasm:"I64Eqz"-"I64LeU"
if 1 <= a {
return 1
}
// wasm:"I64Eqz"-"I64LeU"
if 1 <= b {
return 1
}
// wasm:"I64Eqz"-"I64LeU"
if 1 <= c {
return 1
}
// wasm:"I64Eqz"-"I64LeU"
if 1 <= d {
return 1
}
return 0
}