1
0
mirror of https://github.com/golang/go synced 2024-11-15 04:30:32 -07:00
go/test/codegen/comparisons.go

828 lines
15 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 (
"cmp"
"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\(.*\), [$]`
cmd/compile: add late lower pass for last rules to run Usually optimization rules have corresponding priorities, some need to be run first, some run next, and some run last, which produces the best code. But currently our optimization rules have no priority, this CL adds a late lower pass that runs those rules that need to be run at last, such as split unreasonable constant folding. This pass can be seen as the second round of the lower pass. For example: func foo(a, b uint64) uint64 { d := a+0x1234568 d1 := b+0x1234568 return d&d1 } The code generated by the master branch: 0x0004 00004 ADD $19088744, R0, R2 // movz+movk+add 0x0010 00016 ADD $19088744, R1, R1 // movz+movk+add 0x001c 00028 AND R1, R2, R0 This is because the current constant folding optimization rules do not take into account the range of constants, causing the constant to be loaded repeatedly. This CL splits these unreasonable constants folding in the late lower pass. With this CL the generated code: 0x0004 00004 MOVD $19088744, R2 // movz+movk 0x000c 00012 ADD R0, R2, R3 0x0010 00016 ADD R1, R2, R1 0x0014 00020 AND R1, R3, R0 This CL also adds constant folding optimization for ADDS instruction. In addition, in order not to introduce the codegen regression, an optimization rule is added to change the addition of a negative number into a subtraction of a positive number. go1 benchmarks: name old time/op new time/op delta BinaryTree17-8 1.22s ± 1% 1.24s ± 0% +1.56% (p=0.008 n=5+5) Fannkuch11-8 1.54s ± 0% 1.53s ± 0% -0.69% (p=0.016 n=4+5) FmtFprintfEmpty-8 14.1ns ± 0% 14.1ns ± 0% ~ (p=0.079 n=4+5) FmtFprintfString-8 26.0ns ± 0% 26.1ns ± 0% +0.23% (p=0.008 n=5+5) FmtFprintfInt-8 32.3ns ± 0% 32.9ns ± 1% +1.72% (p=0.008 n=5+5) FmtFprintfIntInt-8 54.5ns ± 0% 55.5ns ± 0% +1.83% (p=0.008 n=5+5) FmtFprintfPrefixedInt-8 61.5ns ± 0% 62.0ns ± 0% +0.93% (p=0.008 n=5+5) FmtFprintfFloat-8 72.0ns ± 0% 73.6ns ± 0% +2.24% (p=0.008 n=5+5) FmtManyArgs-8 221ns ± 0% 224ns ± 0% +1.22% (p=0.008 n=5+5) GobDecode-8 1.91ms ± 0% 1.93ms ± 0% +0.98% (p=0.008 n=5+5) GobEncode-8 1.40ms ± 1% 1.39ms ± 0% -0.79% (p=0.032 n=5+5) Gzip-8 115ms ± 0% 117ms ± 1% +1.17% (p=0.008 n=5+5) Gunzip-8 19.4ms ± 1% 19.3ms ± 0% -0.71% (p=0.016 n=5+4) HTTPClientServer-8 27.0µs ± 0% 27.3µs ± 0% +0.80% (p=0.008 n=5+5) JSONEncode-8 3.36ms ± 1% 3.33ms ± 0% ~ (p=0.056 n=5+5) JSONDecode-8 17.5ms ± 2% 17.8ms ± 0% +1.71% (p=0.016 n=5+4) Mandelbrot200-8 2.29ms ± 0% 2.29ms ± 0% ~ (p=0.151 n=5+5) GoParse-8 1.35ms ± 1% 1.36ms ± 1% ~ (p=0.056 n=5+5) RegexpMatchEasy0_32-8 24.5ns ± 0% 24.5ns ± 0% ~ (p=0.444 n=4+5) RegexpMatchEasy0_1K-8 131ns ±11% 118ns ± 6% ~ (p=0.056 n=5+5) RegexpMatchEasy1_32-8 22.9ns ± 0% 22.9ns ± 0% ~ (p=0.905 n=4+5) RegexpMatchEasy1_1K-8 126ns ± 0% 127ns ± 0% ~ (p=0.063 n=4+5) RegexpMatchMedium_32-8 486ns ± 5% 483ns ± 0% ~ (p=0.381 n=5+4) RegexpMatchMedium_1K-8 15.4µs ± 1% 15.5µs ± 0% ~ (p=0.151 n=5+5) RegexpMatchHard_32-8 687ns ± 0% 686ns ± 0% ~ (p=0.103 n=5+5) RegexpMatchHard_1K-8 20.7µs ± 0% 20.7µs ± 1% ~ (p=0.151 n=5+5) Revcomp-8 175ms ± 2% 176ms ± 3% ~ (p=1.000 n=5+5) Template-8 20.4ms ± 6% 20.1ms ± 2% ~ (p=0.151 n=5+5) TimeParse-8 112ns ± 0% 113ns ± 0% +0.97% (p=0.016 n=5+4) TimeFormat-8 156ns ± 0% 145ns ± 0% -7.14% (p=0.029 n=4+4) Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da Reviewed-on: https://go-review.googlesource.com/c/go/+/425134 Reviewed-by: Keith Randall <khr@google.com> Reviewed-by: Cherry Mui <cherryyz@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Eric Fang <eric.fang@arm.com>
2022-08-17 04:01:17 -06:00
// arm64:`MOVHU\t\(.*\), [R]`,`MOVD\t[$]`,`CMPW\tR`
// 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`
// ppc64x:-`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 {
cmd/compile: set LocalPkg.Path to -p flag Since CL 391014, cmd/compile now requires the -p flag to be set the build system. This CL changes it to initialize LocalPkg.Path to the provided path, rather than relying on writing out `"".` into object files and expecting cmd/link to substitute them. However, this actually involved a rather long tail of fixes. Many have already been submitted, but a few notable ones that have to land simultaneously with changing LocalPkg: 1. When compiling package runtime, there are really two "runtime" packages: types.LocalPkg (the source package itself) and ir.Pkgs.Runtime (the compiler's internal representation, for synthetic references). Previously, these ended up creating separate link symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both end up as `runtime.xxx`, which causes lsym collisions (notably inittask and funcsyms). 2. test/codegen tests need to be updated to expect symbols to be named `command-line-arguments.xxx` rather than `"".foo`. 3. The issue20014 test case is sensitive to the sort order of field tracking symbols. In particular, the local package now sorts to its natural place in the list, rather than to the front. Thanks to David Chase for helping track down all of the fixes needed for this CL. Updates #51734. Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565 Reviewed-on: https://go-review.googlesource.com/c/go/+/393715 Reviewed-by: David Chase <drchase@google.com> Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
2022-03-17 14:27:40 -06:00
// amd64:`CMPW\tcommand-line-arguments[.+_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 {
cmd/compile: set LocalPkg.Path to -p flag Since CL 391014, cmd/compile now requires the -p flag to be set the build system. This CL changes it to initialize LocalPkg.Path to the provided path, rather than relying on writing out `"".` into object files and expecting cmd/link to substitute them. However, this actually involved a rather long tail of fixes. Many have already been submitted, but a few notable ones that have to land simultaneously with changing LocalPkg: 1. When compiling package runtime, there are really two "runtime" packages: types.LocalPkg (the source package itself) and ir.Pkgs.Runtime (the compiler's internal representation, for synthetic references). Previously, these ended up creating separate link symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both end up as `runtime.xxx`, which causes lsym collisions (notably inittask and funcsyms). 2. test/codegen tests need to be updated to expect symbols to be named `command-line-arguments.xxx` rather than `"".foo`. 3. The issue20014 test case is sensitive to the sort order of field tracking symbols. In particular, the local package now sorts to its natural place in the list, rather than to the front. Thanks to David Chase for helping track down all of the fixes needed for this CL. Updates #51734. Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565 Reviewed-on: https://go-review.googlesource.com/c/go/+/393715 Reviewed-by: David Chase <drchase@google.com> Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
2022-03-17 14:27:40 -06:00
// amd64:`CMPL\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPW\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray3(a, b [3]int16) bool {
cmd/compile: set LocalPkg.Path to -p flag Since CL 391014, cmd/compile now requires the -p flag to be set the build system. This CL changes it to initialize LocalPkg.Path to the provided path, rather than relying on writing out `"".` into object files and expecting cmd/link to substitute them. However, this actually involved a rather long tail of fixes. Many have already been submitted, but a few notable ones that have to land simultaneously with changing LocalPkg: 1. When compiling package runtime, there are really two "runtime" packages: types.LocalPkg (the source package itself) and ir.Pkgs.Runtime (the compiler's internal representation, for synthetic references). Previously, these ended up creating separate link symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both end up as `runtime.xxx`, which causes lsym collisions (notably inittask and funcsyms). 2. test/codegen tests need to be updated to expect symbols to be named `command-line-arguments.xxx` rather than `"".foo`. 3. The issue20014 test case is sensitive to the sort order of field tracking symbols. In particular, the local package now sorts to its natural place in the list, rather than to the front. Thanks to David Chase for helping track down all of the fixes needed for this CL. Updates #51734. Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565 Reviewed-on: https://go-review.googlesource.com/c/go/+/393715 Reviewed-by: David Chase <drchase@google.com> Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
2022-03-17 14:27:40 -06:00
// amd64:`CMPL\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPW\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray4(a, b [12]int8) bool {
cmd/compile: set LocalPkg.Path to -p flag Since CL 391014, cmd/compile now requires the -p flag to be set the build system. This CL changes it to initialize LocalPkg.Path to the provided path, rather than relying on writing out `"".` into object files and expecting cmd/link to substitute them. However, this actually involved a rather long tail of fixes. Many have already been submitted, but a few notable ones that have to land simultaneously with changing LocalPkg: 1. When compiling package runtime, there are really two "runtime" packages: types.LocalPkg (the source package itself) and ir.Pkgs.Runtime (the compiler's internal representation, for synthetic references). Previously, these ended up creating separate link symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both end up as `runtime.xxx`, which causes lsym collisions (notably inittask and funcsyms). 2. test/codegen tests need to be updated to expect symbols to be named `command-line-arguments.xxx` rather than `"".foo`. 3. The issue20014 test case is sensitive to the sort order of field tracking symbols. In particular, the local package now sorts to its natural place in the list, rather than to the front. Thanks to David Chase for helping track down all of the fixes needed for this CL. Updates #51734. Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565 Reviewed-on: https://go-review.googlesource.com/c/go/+/393715 Reviewed-by: David Chase <drchase@google.com> Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
2022-03-17 14:27:40 -06:00
// amd64:`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPL\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray5(a, b [15]byte) bool {
cmd/compile: set LocalPkg.Path to -p flag Since CL 391014, cmd/compile now requires the -p flag to be set the build system. This CL changes it to initialize LocalPkg.Path to the provided path, rather than relying on writing out `"".` into object files and expecting cmd/link to substitute them. However, this actually involved a rather long tail of fixes. Many have already been submitted, but a few notable ones that have to land simultaneously with changing LocalPkg: 1. When compiling package runtime, there are really two "runtime" packages: types.LocalPkg (the source package itself) and ir.Pkgs.Runtime (the compiler's internal representation, for synthetic references). Previously, these ended up creating separate link symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both end up as `runtime.xxx`, which causes lsym collisions (notably inittask and funcsyms). 2. test/codegen tests need to be updated to expect symbols to be named `command-line-arguments.xxx` rather than `"".foo`. 3. The issue20014 test case is sensitive to the sort order of field tracking symbols. In particular, the local package now sorts to its natural place in the list, rather than to the front. Thanks to David Chase for helping track down all of the fixes needed for this CL. Updates #51734. Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565 Reviewed-on: https://go-review.googlesource.com/c/go/+/393715 Reviewed-by: David Chase <drchase@google.com> Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
2022-03-17 14:27:40 -06:00
// amd64:`CMPQ\tcommand-line-arguments[.+_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))
}
// Check that some structs generate 2/4/8 byte compares.
type T1 struct {
a [8]byte
}
func CompareStruct1(s1, s2 T1) bool {
// amd64:`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:-`CALL`
return s1 == s2
}
type T2 struct {
a [16]byte
}
func CompareStruct2(s1, s2 T2) bool {
// amd64:`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:-`CALL`
return s1 == s2
}
// Assert that a memequal call is still generated when
// inlining would increase binary size too much.
type T3 struct {
a [24]byte
}
func CompareStruct3(s1, s2 T3) bool {
// amd64:-`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CALL`
return s1 == s2
}
type T4 struct {
a [32]byte
}
func CompareStruct4(s1, s2 T4) bool {
// amd64:-`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CALL`
return s1 == s2
}
// -------------- //
// Ordering //
// -------------- //
// Test that LEAQ/ADDQconst are folded into SETx ops
var r bool
func CmpFold(x uint32) {
// amd64:`SETHI\t.*\(SB\)`
r = 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
func CmpToZero(a, b, d int32, e, f int64, deOptC0, deOptC1 bool) 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
// For arm64, could be TST+BGE or AND+TBZ
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
c7 := e&(f<<3) < 0
// For arm64, could be CMN+BPL or ADD+TBZ
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
c8 := e+(f<<3) < 0
// arm64:`TST\sR[0-9],\sR[0-9]+`
c9 := e&(-19) < 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 6
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 c6 {
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
return 7
} else if c7 {
return 9
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 c8 {
return 10
} else if c9 {
return 11
} else if deOptC0 {
return b + d
} else if deOptC1 {
return a & d
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, f, g uint64) uint64 {
// ppc64x:"ANDCC",-"CMPW"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if a&63 == 0 {
return 1
}
// ppc64x:"ANDCC",-"CMP"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if d&255 == 0 {
return 1
}
// ppc64x:"ANDCC",-"CMP"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if d&e == 0 {
return 1
}
// ppc64x:"ORCC",-"CMP"
// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64"
if f|g == 0 {
return 1
}
// ppc64x:"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: add late lower pass for last rules to run Usually optimization rules have corresponding priorities, some need to be run first, some run next, and some run last, which produces the best code. But currently our optimization rules have no priority, this CL adds a late lower pass that runs those rules that need to be run at last, such as split unreasonable constant folding. This pass can be seen as the second round of the lower pass. For example: func foo(a, b uint64) uint64 { d := a+0x1234568 d1 := b+0x1234568 return d&d1 } The code generated by the master branch: 0x0004 00004 ADD $19088744, R0, R2 // movz+movk+add 0x0010 00016 ADD $19088744, R1, R1 // movz+movk+add 0x001c 00028 AND R1, R2, R0 This is because the current constant folding optimization rules do not take into account the range of constants, causing the constant to be loaded repeatedly. This CL splits these unreasonable constants folding in the late lower pass. With this CL the generated code: 0x0004 00004 MOVD $19088744, R2 // movz+movk 0x000c 00012 ADD R0, R2, R3 0x0010 00016 ADD R1, R2, R1 0x0014 00020 AND R1, R3, R0 This CL also adds constant folding optimization for ADDS instruction. In addition, in order not to introduce the codegen regression, an optimization rule is added to change the addition of a negative number into a subtraction of a positive number. go1 benchmarks: name old time/op new time/op delta BinaryTree17-8 1.22s ± 1% 1.24s ± 0% +1.56% (p=0.008 n=5+5) Fannkuch11-8 1.54s ± 0% 1.53s ± 0% -0.69% (p=0.016 n=4+5) FmtFprintfEmpty-8 14.1ns ± 0% 14.1ns ± 0% ~ (p=0.079 n=4+5) FmtFprintfString-8 26.0ns ± 0% 26.1ns ± 0% +0.23% (p=0.008 n=5+5) FmtFprintfInt-8 32.3ns ± 0% 32.9ns ± 1% +1.72% (p=0.008 n=5+5) FmtFprintfIntInt-8 54.5ns ± 0% 55.5ns ± 0% +1.83% (p=0.008 n=5+5) FmtFprintfPrefixedInt-8 61.5ns ± 0% 62.0ns ± 0% +0.93% (p=0.008 n=5+5) FmtFprintfFloat-8 72.0ns ± 0% 73.6ns ± 0% +2.24% (p=0.008 n=5+5) FmtManyArgs-8 221ns ± 0% 224ns ± 0% +1.22% (p=0.008 n=5+5) GobDecode-8 1.91ms ± 0% 1.93ms ± 0% +0.98% (p=0.008 n=5+5) GobEncode-8 1.40ms ± 1% 1.39ms ± 0% -0.79% (p=0.032 n=5+5) Gzip-8 115ms ± 0% 117ms ± 1% +1.17% (p=0.008 n=5+5) Gunzip-8 19.4ms ± 1% 19.3ms ± 0% -0.71% (p=0.016 n=5+4) HTTPClientServer-8 27.0µs ± 0% 27.3µs ± 0% +0.80% (p=0.008 n=5+5) JSONEncode-8 3.36ms ± 1% 3.33ms ± 0% ~ (p=0.056 n=5+5) JSONDecode-8 17.5ms ± 2% 17.8ms ± 0% +1.71% (p=0.016 n=5+4) Mandelbrot200-8 2.29ms ± 0% 2.29ms ± 0% ~ (p=0.151 n=5+5) GoParse-8 1.35ms ± 1% 1.36ms ± 1% ~ (p=0.056 n=5+5) RegexpMatchEasy0_32-8 24.5ns ± 0% 24.5ns ± 0% ~ (p=0.444 n=4+5) RegexpMatchEasy0_1K-8 131ns ±11% 118ns ± 6% ~ (p=0.056 n=5+5) RegexpMatchEasy1_32-8 22.9ns ± 0% 22.9ns ± 0% ~ (p=0.905 n=4+5) RegexpMatchEasy1_1K-8 126ns ± 0% 127ns ± 0% ~ (p=0.063 n=4+5) RegexpMatchMedium_32-8 486ns ± 5% 483ns ± 0% ~ (p=0.381 n=5+4) RegexpMatchMedium_1K-8 15.4µs ± 1% 15.5µs ± 0% ~ (p=0.151 n=5+5) RegexpMatchHard_32-8 687ns ± 0% 686ns ± 0% ~ (p=0.103 n=5+5) RegexpMatchHard_1K-8 20.7µs ± 0% 20.7µs ± 1% ~ (p=0.151 n=5+5) Revcomp-8 175ms ± 2% 176ms ± 3% ~ (p=1.000 n=5+5) Template-8 20.4ms ± 6% 20.1ms ± 2% ~ (p=0.151 n=5+5) TimeParse-8 112ns ± 0% 113ns ± 0% +0.97% (p=0.016 n=5+4) TimeFormat-8 156ns ± 0% 145ns ± 0% -7.14% (p=0.029 n=4+4) Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da Reviewed-on: https://go-review.googlesource.com/c/go/+/425134 Reviewed-by: Keith Randall <khr@google.com> Reviewed-by: Cherry Mui <cherryyz@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Eric Fang <eric.fang@arm.com>
2022-08-17 04:01:17 -06:00
// arm64:`SUB`,`TBZ`
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: add late lower pass for last rules to run Usually optimization rules have corresponding priorities, some need to be run first, some run next, and some run last, which produces the best code. But currently our optimization rules have no priority, this CL adds a late lower pass that runs those rules that need to be run at last, such as split unreasonable constant folding. This pass can be seen as the second round of the lower pass. For example: func foo(a, b uint64) uint64 { d := a+0x1234568 d1 := b+0x1234568 return d&d1 } The code generated by the master branch: 0x0004 00004 ADD $19088744, R0, R2 // movz+movk+add 0x0010 00016 ADD $19088744, R1, R1 // movz+movk+add 0x001c 00028 AND R1, R2, R0 This is because the current constant folding optimization rules do not take into account the range of constants, causing the constant to be loaded repeatedly. This CL splits these unreasonable constants folding in the late lower pass. With this CL the generated code: 0x0004 00004 MOVD $19088744, R2 // movz+movk 0x000c 00012 ADD R0, R2, R3 0x0010 00016 ADD R1, R2, R1 0x0014 00020 AND R1, R3, R0 This CL also adds constant folding optimization for ADDS instruction. In addition, in order not to introduce the codegen regression, an optimization rule is added to change the addition of a negative number into a subtraction of a positive number. go1 benchmarks: name old time/op new time/op delta BinaryTree17-8 1.22s ± 1% 1.24s ± 0% +1.56% (p=0.008 n=5+5) Fannkuch11-8 1.54s ± 0% 1.53s ± 0% -0.69% (p=0.016 n=4+5) FmtFprintfEmpty-8 14.1ns ± 0% 14.1ns ± 0% ~ (p=0.079 n=4+5) FmtFprintfString-8 26.0ns ± 0% 26.1ns ± 0% +0.23% (p=0.008 n=5+5) FmtFprintfInt-8 32.3ns ± 0% 32.9ns ± 1% +1.72% (p=0.008 n=5+5) FmtFprintfIntInt-8 54.5ns ± 0% 55.5ns ± 0% +1.83% (p=0.008 n=5+5) FmtFprintfPrefixedInt-8 61.5ns ± 0% 62.0ns ± 0% +0.93% (p=0.008 n=5+5) FmtFprintfFloat-8 72.0ns ± 0% 73.6ns ± 0% +2.24% (p=0.008 n=5+5) FmtManyArgs-8 221ns ± 0% 224ns ± 0% +1.22% (p=0.008 n=5+5) GobDecode-8 1.91ms ± 0% 1.93ms ± 0% +0.98% (p=0.008 n=5+5) GobEncode-8 1.40ms ± 1% 1.39ms ± 0% -0.79% (p=0.032 n=5+5) Gzip-8 115ms ± 0% 117ms ± 1% +1.17% (p=0.008 n=5+5) Gunzip-8 19.4ms ± 1% 19.3ms ± 0% -0.71% (p=0.016 n=5+4) HTTPClientServer-8 27.0µs ± 0% 27.3µs ± 0% +0.80% (p=0.008 n=5+5) JSONEncode-8 3.36ms ± 1% 3.33ms ± 0% ~ (p=0.056 n=5+5) JSONDecode-8 17.5ms ± 2% 17.8ms ± 0% +1.71% (p=0.016 n=5+4) Mandelbrot200-8 2.29ms ± 0% 2.29ms ± 0% ~ (p=0.151 n=5+5) GoParse-8 1.35ms ± 1% 1.36ms ± 1% ~ (p=0.056 n=5+5) RegexpMatchEasy0_32-8 24.5ns ± 0% 24.5ns ± 0% ~ (p=0.444 n=4+5) RegexpMatchEasy0_1K-8 131ns ±11% 118ns ± 6% ~ (p=0.056 n=5+5) RegexpMatchEasy1_32-8 22.9ns ± 0% 22.9ns ± 0% ~ (p=0.905 n=4+5) RegexpMatchEasy1_1K-8 126ns ± 0% 127ns ± 0% ~ (p=0.063 n=4+5) RegexpMatchMedium_32-8 486ns ± 5% 483ns ± 0% ~ (p=0.381 n=5+4) RegexpMatchMedium_1K-8 15.4µs ± 1% 15.5µs ± 0% ~ (p=0.151 n=5+5) RegexpMatchHard_32-8 687ns ± 0% 686ns ± 0% ~ (p=0.103 n=5+5) RegexpMatchHard_1K-8 20.7µs ± 0% 20.7µs ± 1% ~ (p=0.151 n=5+5) Revcomp-8 175ms ± 2% 176ms ± 3% ~ (p=1.000 n=5+5) Template-8 20.4ms ± 6% 20.1ms ± 2% ~ (p=0.151 n=5+5) TimeParse-8 112ns ± 0% 113ns ± 0% +0.97% (p=0.016 n=5+4) TimeFormat-8 156ns ± 0% 145ns ± 0% -7.14% (p=0.029 n=4+4) Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da Reviewed-on: https://go-review.googlesource.com/c/go/+/425134 Reviewed-by: Keith Randall <khr@google.com> Reviewed-by: Cherry Mui <cherryyz@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Eric Fang <eric.fang@arm.com>
2022-08-17 04:01:17 -06:00
// arm64:`SUB`,`CMP`,`BGT`
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: add late lower pass for last rules to run Usually optimization rules have corresponding priorities, some need to be run first, some run next, and some run last, which produces the best code. But currently our optimization rules have no priority, this CL adds a late lower pass that runs those rules that need to be run at last, such as split unreasonable constant folding. This pass can be seen as the second round of the lower pass. For example: func foo(a, b uint64) uint64 { d := a+0x1234568 d1 := b+0x1234568 return d&d1 } The code generated by the master branch: 0x0004 00004 ADD $19088744, R0, R2 // movz+movk+add 0x0010 00016 ADD $19088744, R1, R1 // movz+movk+add 0x001c 00028 AND R1, R2, R0 This is because the current constant folding optimization rules do not take into account the range of constants, causing the constant to be loaded repeatedly. This CL splits these unreasonable constants folding in the late lower pass. With this CL the generated code: 0x0004 00004 MOVD $19088744, R2 // movz+movk 0x000c 00012 ADD R0, R2, R3 0x0010 00016 ADD R1, R2, R1 0x0014 00020 AND R1, R3, R0 This CL also adds constant folding optimization for ADDS instruction. In addition, in order not to introduce the codegen regression, an optimization rule is added to change the addition of a negative number into a subtraction of a positive number. go1 benchmarks: name old time/op new time/op delta BinaryTree17-8 1.22s ± 1% 1.24s ± 0% +1.56% (p=0.008 n=5+5) Fannkuch11-8 1.54s ± 0% 1.53s ± 0% -0.69% (p=0.016 n=4+5) FmtFprintfEmpty-8 14.1ns ± 0% 14.1ns ± 0% ~ (p=0.079 n=4+5) FmtFprintfString-8 26.0ns ± 0% 26.1ns ± 0% +0.23% (p=0.008 n=5+5) FmtFprintfInt-8 32.3ns ± 0% 32.9ns ± 1% +1.72% (p=0.008 n=5+5) FmtFprintfIntInt-8 54.5ns ± 0% 55.5ns ± 0% +1.83% (p=0.008 n=5+5) FmtFprintfPrefixedInt-8 61.5ns ± 0% 62.0ns ± 0% +0.93% (p=0.008 n=5+5) FmtFprintfFloat-8 72.0ns ± 0% 73.6ns ± 0% +2.24% (p=0.008 n=5+5) FmtManyArgs-8 221ns ± 0% 224ns ± 0% +1.22% (p=0.008 n=5+5) GobDecode-8 1.91ms ± 0% 1.93ms ± 0% +0.98% (p=0.008 n=5+5) GobEncode-8 1.40ms ± 1% 1.39ms ± 0% -0.79% (p=0.032 n=5+5) Gzip-8 115ms ± 0% 117ms ± 1% +1.17% (p=0.008 n=5+5) Gunzip-8 19.4ms ± 1% 19.3ms ± 0% -0.71% (p=0.016 n=5+4) HTTPClientServer-8 27.0µs ± 0% 27.3µs ± 0% +0.80% (p=0.008 n=5+5) JSONEncode-8 3.36ms ± 1% 3.33ms ± 0% ~ (p=0.056 n=5+5) JSONDecode-8 17.5ms ± 2% 17.8ms ± 0% +1.71% (p=0.016 n=5+4) Mandelbrot200-8 2.29ms ± 0% 2.29ms ± 0% ~ (p=0.151 n=5+5) GoParse-8 1.35ms ± 1% 1.36ms ± 1% ~ (p=0.056 n=5+5) RegexpMatchEasy0_32-8 24.5ns ± 0% 24.5ns ± 0% ~ (p=0.444 n=4+5) RegexpMatchEasy0_1K-8 131ns ±11% 118ns ± 6% ~ (p=0.056 n=5+5) RegexpMatchEasy1_32-8 22.9ns ± 0% 22.9ns ± 0% ~ (p=0.905 n=4+5) RegexpMatchEasy1_1K-8 126ns ± 0% 127ns ± 0% ~ (p=0.063 n=4+5) RegexpMatchMedium_32-8 486ns ± 5% 483ns ± 0% ~ (p=0.381 n=5+4) RegexpMatchMedium_1K-8 15.4µs ± 1% 15.5µs ± 0% ~ (p=0.151 n=5+5) RegexpMatchHard_32-8 687ns ± 0% 686ns ± 0% ~ (p=0.103 n=5+5) RegexpMatchHard_1K-8 20.7µs ± 0% 20.7µs ± 1% ~ (p=0.151 n=5+5) Revcomp-8 175ms ± 2% 176ms ± 3% ~ (p=1.000 n=5+5) Template-8 20.4ms ± 6% 20.1ms ± 2% ~ (p=0.151 n=5+5) TimeParse-8 112ns ± 0% 113ns ± 0% +0.97% (p=0.016 n=5+4) TimeFormat-8 156ns ± 0% 145ns ± 0% -7.14% (p=0.029 n=4+4) Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da Reviewed-on: https://go-review.googlesource.com/c/go/+/425134 Reviewed-by: Keith Randall <khr@google.com> Reviewed-by: Cherry Mui <cherryyz@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Eric Fang <eric.fang@arm.com>
2022-08-17 04:01:17 -06:00
// arm64:`SUB`,`TBNZ`
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:`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 {
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(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 {
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(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 {
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(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 {
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(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
}
// Check that small memequals are replaced with eq instructions
func equalConstString1() bool {
a := string("A")
b := string("Z")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a == b
}
func equalVarString1(a string) bool {
b := string("Z")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a[:1] == b
}
func equalConstString2() bool {
a := string("AA")
b := string("ZZ")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a == b
}
func equalVarString2(a string) bool {
b := string("ZZ")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a[:2] == b
}
func equalConstString4() bool {
a := string("AAAA")
b := string("ZZZZ")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a == b
}
func equalVarString4(a string) bool {
b := string("ZZZZ")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a[:4] == b
}
func equalConstString8() bool {
a := string("AAAAAAAA")
b := string("ZZZZZZZZ")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a == b
}
func equalVarString8(a string) bool {
b := string("ZZZZZZZZ")
// amd64:-".*memequal"
// arm64:-".*memequal"
// ppc64x:-".*memequal"
return a[:8] == b
}
func cmpToCmn(a, b, c, d int) int {
var c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 int
// arm64:`CMN`,-`CMP`
if a < -8 {
c1 = 1
}
// arm64:`CMN`,-`CMP`
if a+1 == 0 {
c2 = 1
}
// arm64:`CMN`,-`CMP`
if a+3 != 0 {
c3 = 1
}
// arm64:`CMN`,-`CMP`
if a+b == 0 {
c4 = 1
}
// arm64:`CMN`,-`CMP`
if b+c != 0 {
c5 = 1
}
// arm64:`CMN`,-`CMP`
if a == -c {
c6 = 1
}
// arm64:`CMN`,-`CMP`
if b != -d {
c7 = 1
}
// arm64:`CMN`,-`CMP`
if a*b+c == 0 {
c8 = 1
}
// arm64:`CMN`,-`CMP`
if a*c+b != 0 {
c9 = 1
}
// arm64:`CMP`,-`CMN`
if b*c-a == 0 {
c10 = 1
}
// arm64:`CMP`,-`CMN`
if a*d-b != 0 {
c11 = 1
}
return c1 + c2 + c3 + c4 + c5 + c6 + c7 + c8 + c9 + c10 + c11
}
func cmpToCmnLessThan(a, b, c, d int) int {
var c1, c2, c3, c4 int
// arm64:`CMN`,`CSET\tMI`,-`CMP`
if a+1 < 0 {
c1 = 1
}
// arm64:`CMN`,`CSET\tMI`,-`CMP`
if a+b < 0 {
c2 = 1
}
// arm64:`CMN`,`CSET\tMI`,-`CMP`
if a*b+c < 0 {
c3 = 1
}
// arm64:`CMP`,`CSET\tMI`,-`CMN`
if a-b*c < 0 {
c4 = 1
}
return c1 + c2 + c3 + c4
}
func cmpToCmnGreaterThanEqual(a, b, c, d int) int {
var c1, c2, c3, c4 int
// arm64:`CMN`,`CSET\tPL`,-`CMP`
if a+1 >= 0 {
c1 = 1
}
// arm64:`CMN`,`CSET\tPL`,-`CMP`
if a+b >= 0 {
c2 = 1
}
// arm64:`CMN`,`CSET\tPL`,-`CMP`
if a*b+c >= 0 {
c3 = 1
}
// arm64:`CMP`,`CSET\tPL`,-`CMN`
if a-b*c >= 0 {
c4 = 1
}
return c1 + c2 + c3 + c4
}
func cmp1(val string) bool {
var z string
// amd64:-".*memequal"
return z == val
}
func cmp2(val string) bool {
var z string
// amd64:-".*memequal"
return val == z
}
func cmp3(val string) bool {
z := "food"
// amd64:-".*memequal"
return z == val
}
func cmp4(val string) bool {
z := "food"
// amd64:-".*memequal"
return val == z
}
func cmp5[T comparable](val T) bool {
var z T
// amd64:-".*memequal"
return z == val
}
func cmp6[T comparable](val T) bool {
var z T
// amd64:-".*memequal"
return val == z
}
func cmp7() {
cmp5[string]("") // force instantiation
cmp6[string]("") // force instantiation
}
type Point struct {
X, Y int
}
// invertLessThanNoov checks (LessThanNoov (InvertFlags x)) is lowered as
// CMP, CSET, CSEL instruction sequence. InvertFlags are only generated under
// certain conditions, see canonLessThan, so if the code below does not
// generate an InvertFlags OP, this check may fail.
func invertLessThanNoov(p1, p2, p3 Point) bool {
// arm64:`CMP`,`CSET`,`CSEL`
return (p1.X-p3.X)*(p2.Y-p3.Y)-(p2.X-p3.X)*(p1.Y-p3.Y) < 0
}
func cmpstring1(x, y string) int {
// amd64:".*cmpstring"
if x < y {
return -1
}
// amd64:-".*cmpstring"
if x > y {
return +1
}
return 0
}
func cmpstring2(x, y string) int {
// We want to fail if there are two calls to cmpstring.
// They will both have the same line number, so a test
// like in cmpstring1 will not work. Instead, we
// look for spill/restore instructions, which only
// need to exist if there are 2 calls.
//amd64:-`MOVQ\t.*\(SP\)`
return cmp.Compare(x, y)
}