1
0
mirror of https://github.com/golang/go synced 2024-11-14 08:10:22 -07:00
go/test/codegen/comparisons.go
Ben Shi 2b69ad0b3c 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>
2018-08-27 15:49:46 +00:00

172 lines
3.5 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 int32) int32 {
if a&b < 0 { // arm:`TST`,-`AND`
return 1
} else if a+b < 0 { // arm:`CMN`,-`ADD`
return 2
} else if a^b < 0 { // arm:`TEQ`,-`XOR`
return 3
} else {
return 0
}
}