1
0
mirror of https://github.com/golang/go synced 2024-11-17 10:24:48 -07:00
go/test/codegen/comparisons.go
Ben Shi 5aeecc4530 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>
2018-09-28 15:05:17 +00:00

212 lines
4.3 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
// arm64:`TST\sR[0-9]+<<3,\sR[0-9]+`
c7 := e&(f<<3) < 0
// arm64:`CMN\sR[0-9]+<<3,\sR[0-9]+`
c8 := e+(f<<3) < 0
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 if c7 {
return 7
} else if c8 {
return 8
} else {
return 0
}
}