1
0
mirror of https://github.com/golang/go synced 2024-11-24 04:40:24 -07:00
go/test/codegen/comparisons.go
Ben Shi 031a35ec84 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>
2018-09-07 01:20:45 +00:00

204 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`
// 386:`ANDL`
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
}
}