1
0
mirror of https://github.com/golang/go synced 2024-09-29 01:34:32 -06:00
go/test/codegen/comparisons.go
Ben Shi 067dfce21f 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>
2018-09-05 14:54:08 +00:00

203 lines
4.1 KiB
Go

// asmcheck
// Copyright 2018 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package codegen
import "unsafe"
// This file contains code generation tests related to the comparison
// operators.
// -------------- //
// Equality //
// -------------- //
// Check that compare to constant string use 2/4/8 byte compares
func CompareString1(s string) bool {
// amd64:`CMPW\t\(.*\), [$]`
// arm64:`MOVHU\t\(.*\), [R]`,`CMPW\t[$]`
// ppc64le:`MOVHZ\t\(.*\), [R]`,`CMPW\t.*, [$]`
// s390x:`MOVHBR\t\(.*\), [R]`,`CMPW\t.*, [$]`
return s == "xx"
}
func CompareString2(s string) bool {
// amd64:`CMPL\t\(.*\), [$]`
// arm64:`MOVWU\t\(.*\), [R]`,`CMPW\t.*, [R]`
// ppc64le:`MOVWZ\t\(.*\), [R]`,`CMPW\t.*, [R]`
// s390x:`MOVWBR\t\(.*\), [R]`,`CMPW\t.*, [$]`
return s == "xxxx"
}
func CompareString3(s string) bool {
// amd64:`CMPQ\t\(.*\), [A-Z]`
// arm64:-`CMPW\t`
// ppc64le:-`CMPW\t`
// s390x:-`CMPW\t`
return s == "xxxxxxxx"
}
// Check that arrays compare use 2/4/8 byte compares
func CompareArray1(a, b [2]byte) bool {
// amd64:`CMPW\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// arm64:-`MOVBU\t`
// ppc64le:-`MOVBZ\t`
// s390x:-`MOVBZ\t`
return a == b
}
func CompareArray2(a, b [3]uint16) bool {
// amd64:`CMPL\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPW\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray3(a, b [3]int16) bool {
// amd64:`CMPL\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPW\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray4(a, b [12]int8) bool {
// amd64:`CMPQ\t""[.+_a-z0-9]+\(SP\), [A-Z]`
// amd64:`CMPL\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
func CompareArray5(a, b [15]byte) bool {
// amd64:`CMPQ\t""[.+_a-z0-9]+\(SP\), [A-Z]`
return a == b
}
// This was a TODO in mapaccess1_faststr
func CompareArray6(a, b unsafe.Pointer) bool {
// amd64:`CMPL\t\(.*\), [A-Z]`
// arm64:`MOVWU\t\(.*\), [R]`,`CMPW\t.*, [R]`
// ppc64le:`MOVWZ\t\(.*\), [R]`,`CMPW\t.*, [R]`
// s390x:`MOVWBR\t\(.*\), [R]`,`CMPW\t.*, [R]`
return *((*[4]byte)(a)) != *((*[4]byte)(b))
}
// -------------- //
// Ordering //
// -------------- //
// Test that LEAQ/ADDQconst are folded into SETx ops
func CmpFold(x uint32) bool {
// amd64:`SETHI\t.*\(SP\)`
return x > 4
}
// Test that direct comparisons with memory are generated when
// possible
func CmpMem1(p int, q *int) bool {
// amd64:`CMPQ\t\(.*\), [A-Z]`
return p < *q
}
func CmpMem2(p *int, q int) bool {
// amd64:`CMPQ\t\(.*\), [A-Z]`
return *p < q
}
func CmpMem3(p *int) bool {
// amd64:`CMPQ\t\(.*\), [$]7`
return *p < 7
}
func CmpMem4(p *int) bool {
// amd64:`CMPQ\t\(.*\), [$]7`
return 7 < *p
}
func CmpMem5(p **int) {
// amd64:`CMPL\truntime.writeBarrier\(SB\), [$]0`
*p = nil
}
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
}
}
func CmpToZero(a, b, d int32, e, f int64) int32 {
// arm:`TST`,-`AND`
// arm64:`TSTW`,-`AND`
// 386:`TESTL`,-`ANDL`
// amd64:`TESTL`,-`ANDL`
c0 := a&b < 0
// arm:`CMN`,-`ADD`
// arm64:`CMNW`,-`ADD`
c1 := a+b < 0
// arm:`TEQ`,-`XOR`
c2 := a^b < 0
// arm64:`TST`,-`AND`
// amd64:`TESTQ`,-`ANDQ`
c3 := e&f < 0
// arm64:`CMN`,-`ADD`
c4 := e+f < 0
// not optimized to single CMNW/CMN due to further use of b+d
// arm64:`ADD`,-`CMNW`
// arm:`ADD`,-`CMN`
c5 := b+d == 0
// not optimized to single TSTW/TST due to further use of a&d
// arm64:`AND`,-`TSTW`
// arm:`AND`,-`TST`
c6 := a&d >= 0
if c0 {
return 1
} else if c1 {
return 2
} else if c2 {
return 3
} else if c3 {
return 4
} else if c4 {
return 5
} else if c5 {
return b + d
} else if c6 {
return a & d
} else {
return 0
}
}