1
0
mirror of https://github.com/golang/go synced 2024-11-05 16:26:11 -07:00
go/test/codegen/fuse.go
Michael Munday e37cc29863 cmd/compile: optimize integer-in-range checks
This CL incorporates code from CL 201206 by Josh Bleecher Snyder
(thanks Josh).

This CL restores the integer-in-range optimizations in the SSA
backend. The fuse pass is enhanced to detect inequalities that
could be merged and fuse their associated blocks while the generic
rules optimize them into a single unsigned comparison.

For example, the inequality `x >= 0 && x < 10` will now be optimized
to `unsigned(x) < 10`.

Overall has a fairly positive impact on binary sizes.

name                      old time/op       new time/op       delta
Template                        192ms ± 1%        192ms ± 1%    ~     (p=0.757 n=17+18)
Unicode                        76.6ms ± 2%       76.5ms ± 2%    ~     (p=0.603 n=19+19)
GoTypes                         694ms ± 1%        693ms ± 1%    ~     (p=0.569 n=19+20)
Compiler                        3.26s ± 0%        3.27s ± 0%  +0.25%  (p=0.000 n=20+20)
SSA                             7.41s ± 0%        7.49s ± 0%  +1.10%  (p=0.000 n=17+19)
Flate                           120ms ± 1%        120ms ± 1%  +0.38%  (p=0.003 n=19+19)
GoParser                        152ms ± 1%        152ms ± 1%    ~     (p=0.061 n=17+19)
Reflect                         422ms ± 1%        425ms ± 2%  +0.76%  (p=0.001 n=18+20)
Tar                             167ms ± 1%        167ms ± 0%    ~     (p=0.730 n=18+19)
XML                             233ms ± 4%        231ms ± 1%    ~     (p=0.752 n=20+17)
LinkCompiler                    927ms ± 8%        928ms ± 8%    ~     (p=0.857 n=19+20)
ExternalLinkCompiler            1.81s ± 2%        1.81s ± 2%    ~     (p=0.513 n=19+20)
LinkWithoutDebugCompiler        556ms ±10%        583ms ±13%  +4.95%  (p=0.007 n=20+20)
[Geo mean]                      478ms             481ms       +0.52%

name                      old user-time/op  new user-time/op  delta
Template                        270ms ± 5%        269ms ± 7%    ~     (p=0.925 n=20+20)
Unicode                         134ms ± 7%        131ms ±14%    ~     (p=0.593 n=18+20)
GoTypes                         981ms ± 3%        987ms ± 2%  +0.63%  (p=0.049 n=19+18)
Compiler                        4.50s ± 2%        4.50s ± 1%    ~     (p=0.588 n=19+20)
SSA                             10.6s ± 2%        10.6s ± 1%    ~     (p=0.141 n=20+19)
Flate                           164ms ± 8%        165ms ±10%    ~     (p=0.738 n=20+20)
GoParser                        202ms ± 5%        203ms ± 6%    ~     (p=0.820 n=20+20)
Reflect                         587ms ± 6%        597ms ± 3%    ~     (p=0.087 n=20+18)
Tar                             230ms ± 6%        228ms ± 8%    ~     (p=0.569 n=19+20)
XML                             311ms ± 6%        314ms ± 5%    ~     (p=0.369 n=20+20)
LinkCompiler                    878ms ± 8%        887ms ± 7%    ~     (p=0.289 n=20+20)
ExternalLinkCompiler            1.60s ± 7%        1.60s ± 7%    ~     (p=0.820 n=20+20)
LinkWithoutDebugCompiler        498ms ±12%        489ms ±11%    ~     (p=0.398 n=20+20)
[Geo mean]                      611ms             611ms       +0.05%

name                      old alloc/op      new alloc/op      delta
Template                       36.1MB ± 0%       36.0MB ± 0%  -0.32%  (p=0.000 n=20+20)
Unicode                        28.3MB ± 0%       28.3MB ± 0%  -0.03%  (p=0.000 n=19+20)
GoTypes                         121MB ± 0%        121MB ± 0%    ~     (p=0.226 n=16+20)
Compiler                        563MB ± 0%        563MB ± 0%    ~     (p=0.166 n=20+19)
SSA                            1.32GB ± 0%       1.33GB ± 0%  +0.88%  (p=0.000 n=20+19)
Flate                          22.7MB ± 0%       22.7MB ± 0%  -0.02%  (p=0.033 n=19+20)
GoParser                       27.9MB ± 0%       27.9MB ± 0%  -0.02%  (p=0.001 n=20+20)
Reflect                        78.3MB ± 0%       78.2MB ± 0%  -0.01%  (p=0.019 n=20+20)
Tar                            34.0MB ± 0%       34.0MB ± 0%  -0.04%  (p=0.000 n=20+20)
XML                            43.9MB ± 0%       43.9MB ± 0%  -0.07%  (p=0.000 n=20+19)
LinkCompiler                    205MB ± 0%        205MB ± 0%  +0.44%  (p=0.000 n=20+18)
ExternalLinkCompiler            223MB ± 0%        223MB ± 0%  +0.03%  (p=0.000 n=20+20)
LinkWithoutDebugCompiler        139MB ± 0%        142MB ± 0%  +1.75%  (p=0.000 n=20+20)
[Geo mean]                     93.7MB            93.9MB       +0.20%

name                      old allocs/op     new allocs/op     delta
Template                         363k ± 0%         361k ± 0%  -0.58%  (p=0.000 n=20+19)
Unicode                          329k ± 0%         329k ± 0%  -0.06%  (p=0.000 n=19+20)
GoTypes                         1.28M ± 0%        1.28M ± 0%  -0.01%  (p=0.000 n=20+20)
Compiler                        5.40M ± 0%        5.40M ± 0%  -0.01%  (p=0.000 n=20+20)
SSA                             12.7M ± 0%        12.8M ± 0%  +0.80%  (p=0.000 n=20+20)
Flate                            228k ± 0%         228k ± 0%    ~     (p=0.194 n=20+20)
GoParser                         295k ± 0%         295k ± 0%  -0.04%  (p=0.000 n=20+20)
Reflect                          949k ± 0%         949k ± 0%  -0.01%  (p=0.000 n=20+20)
Tar                              337k ± 0%         337k ± 0%  -0.06%  (p=0.000 n=20+20)
XML                              418k ± 0%         417k ± 0%  -0.17%  (p=0.000 n=20+20)
LinkCompiler                     553k ± 0%         554k ± 0%  +0.22%  (p=0.000 n=20+19)
ExternalLinkCompiler            1.52M ± 0%        1.52M ± 0%  +0.27%  (p=0.000 n=20+20)
LinkWithoutDebugCompiler         186k ± 0%         186k ± 0%  +0.06%  (p=0.000 n=20+20)
[Geo mean]                       723k              723k       +0.03%

name                      old text-bytes    new text-bytes    delta
HelloSize                       828kB ± 0%        828kB ± 0%  -0.01%  (p=0.000 n=20+20)

name                      old data-bytes    new data-bytes    delta
HelloSize                      13.4kB ± 0%       13.4kB ± 0%    ~     (all equal)

name                      old bss-bytes     new bss-bytes     delta
HelloSize                       180kB ± 0%        180kB ± 0%    ~     (all equal)

name                      old exe-bytes     new exe-bytes     delta
HelloSize                      1.23MB ± 0%       1.23MB ± 0%  -0.33%  (p=0.000 n=20+20)

file      before    after     Δ       %
addr2line 4320075   4311883   -8192   -0.190%
asm       5191932   5187836   -4096   -0.079%
buildid   2835338   2831242   -4096   -0.144%
compile   20531717  20569099  +37382  +0.182%
cover     5322511   5318415   -4096   -0.077%
dist      3723749   3719653   -4096   -0.110%
doc       4743515   4739419   -4096   -0.086%
fix       3413960   3409864   -4096   -0.120%
link      6690119   6686023   -4096   -0.061%
nm        4269616   4265520   -4096   -0.096%
pprof     14942189  14929901  -12288  -0.082%
trace     11807164  11790780  -16384  -0.139%
vet       8384104   8388200   +4096   +0.049%
go        15339076  15334980  -4096   -0.027%
total     132258257 132226007 -32250  -0.024%

Fixes #30645.

Change-Id: If551ac5996097f3685870d083151b5843170aab0
Reviewed-on: https://go-review.googlesource.com/c/go/+/165998
Run-TryBot: Michael Munday <mike.munday@ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
2020-03-03 14:30:26 +00:00

198 lines
4.8 KiB
Go

// asmcheck
// Copyright 2019 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
// Notes:
// - these examples use channels to provide a source of
// unknown values that cannot be optimized away
// - these examples use for loops to force branches
// backward (predicted taken)
// ---------------------------------- //
// signed integer range (conjunction) //
// ---------------------------------- //
func si1c(c <-chan int64) {
// amd64:"CMPQ\t.+, [$]256"
// s390x:"CLGIJ\t[$]12, R[0-9]+, [$]255"
for x := <-c; x >= 0 && x < 256; x = <-c {
}
}
func si2c(c <-chan int32) {
// amd64:"CMPL\t.+, [$]256"
// s390x:"CLIJ\t[$]12, R[0-9]+, [$]255"
for x := <-c; x >= 0 && x < 256; x = <-c {
}
}
func si3c(c <-chan int16) {
// amd64:"CMPW\t.+, [$]256"
// s390x:"CLIJ\t[$]12, R[0-9]+, [$]255"
for x := <-c; x >= 0 && x < 256; x = <-c {
}
}
func si4c(c <-chan int8) {
// amd64:"CMPB\t.+, [$]10"
// s390x:"CLIJ\t[$]4, R[0-9]+, [$]10"
for x := <-c; x >= 0 && x < 10; x = <-c {
}
}
func si5c(c <-chan int64) {
// amd64:"CMPQ\t.+, [$]251","ADDQ\t[$]-5,"
// s390x:"CLGIJ\t[$]4, R[0-9]+, [$]251","ADD\t[$]-5,"
for x := <-c; x < 256 && x > 4; x = <-c {
}
}
func si6c(c <-chan int32) {
// amd64:"CMPL\t.+, [$]255","DECL\t"
// s390x:"CLIJ\t[$]12, R[0-9]+, [$]255","ADDW\t[$]-1,"
for x := <-c; x > 0 && x <= 256; x = <-c {
}
}
func si7c(c <-chan int16) {
// amd64:"CMPW\t.+, [$]60","ADDL\t[$]10,"
// s390x:"CLIJ\t[$]12, R[0-9]+, [$]60","ADDW\t[$]10,"
for x := <-c; x >= -10 && x <= 50; x = <-c {
}
}
func si8c(c <-chan int8) {
// amd64:"CMPB\t.+, [$]126","ADDL\t[$]126,"
// s390x:"CLIJ\t[$]4, R[0-9]+, [$]126","ADDW\t[$]126,"
for x := <-c; x >= -126 && x < 0; x = <-c {
}
}
// ---------------------------------- //
// signed integer range (disjunction) //
// ---------------------------------- //
func si1d(c <-chan int64) {
// amd64:"CMPQ\t.+, [$]256"
// s390x:"CLGIJ\t[$]2, R[0-9]+, [$]255"
for x := <-c; x < 0 || x >= 256; x = <-c {
}
}
func si2d(c <-chan int32) {
// amd64:"CMPL\t.+, [$]256"
// s390x:"CLIJ\t[$]2, R[0-9]+, [$]255"
for x := <-c; x < 0 || x >= 256; x = <-c {
}
}
func si3d(c <-chan int16) {
// amd64:"CMPW\t.+, [$]256"
// s390x:"CLIJ\t[$]2, R[0-9]+, [$]255"
for x := <-c; x < 0 || x >= 256; x = <-c {
}
}
func si4d(c <-chan int8) {
// amd64:"CMPB\t.+, [$]10"
// s390x:"CLIJ\t[$]10, R[0-9]+, [$]10"
for x := <-c; x < 0 || x >= 10; x = <-c {
}
}
func si5d(c <-chan int64) {
// amd64:"CMPQ\t.+, [$]251","ADDQ\t[$]-5,"
// s390x:"CLGIJ\t[$]10, R[0-9]+, [$]251","ADD\t[$]-5,"
for x := <-c; x >= 256 || x <= 4; x = <-c {
}
}
func si6d(c <-chan int32) {
// amd64:"CMPL\t.+, [$]255","DECL\t"
// s390x:"CLIJ\t[$]2, R[0-9]+, [$]255","ADDW\t[$]-1,"
for x := <-c; x <= 0 || x > 256; x = <-c {
}
}
func si7d(c <-chan int16) {
// amd64:"CMPW\t.+, [$]60","ADDL\t[$]10,"
// s390x:"CLIJ\t[$]2, R[0-9]+, [$]60","ADDW\t[$]10,"
for x := <-c; x < -10 || x > 50; x = <-c {
}
}
func si8d(c <-chan int8) {
// amd64:"CMPB\t.+, [$]126","ADDL\t[$]126,"
// s390x:"CLIJ\t[$]10, R[0-9]+, [$]126","ADDW\t[$]126,"
for x := <-c; x < -126 || x >= 0; x = <-c {
}
}
// ------------------------------------ //
// unsigned integer range (conjunction) //
// ------------------------------------ //
func ui1c(c <-chan uint64) {
// amd64:"CMPQ\t.+, [$]251","ADDQ\t[$]-5,"
// s390x:"CLGIJ\t[$]4, R[0-9]+, [$]251","ADD\t[$]-5,"
for x := <-c; x < 256 && x > 4; x = <-c {
}
}
func ui2c(c <-chan uint32) {
// amd64:"CMPL\t.+, [$]255","DECL\t"
// s390x:"CLIJ\t[$]12, R[0-9]+, [$]255","ADDW\t[$]-1,"
for x := <-c; x > 0 && x <= 256; x = <-c {
}
}
func ui3c(c <-chan uint16) {
// amd64:"CMPW\t.+, [$]40","ADDL\t[$]-10,"
// s390x:"CLIJ\t[$]12, R[0-9]+, [$]40","ADDW\t[$]-10,"
for x := <-c; x >= 10 && x <= 50; x = <-c {
}
}
func ui4c(c <-chan uint8) {
// amd64:"CMPB\t.+, [$]2","ADDL\t[$]-126,"
// s390x:"CLIJ\t[$]4, R[0-9]+, [$]2","ADDW\t[$]-126,"
for x := <-c; x >= 126 && x < 128; x = <-c {
}
}
// ------------------------------------ //
// unsigned integer range (disjunction) //
// ------------------------------------ //
func ui1d(c <-chan uint64) {
// amd64:"CMPQ\t.+, [$]251","ADDQ\t[$]-5,"
// s390x:"CLGIJ\t[$]10, R[0-9]+, [$]251","ADD\t[$]-5,"
for x := <-c; x >= 256 || x <= 4; x = <-c {
}
}
func ui2d(c <-chan uint32) {
// amd64:"CMPL\t.+, [$]254","ADDL\t[$]-2,"
// s390x:"CLIJ\t[$]2, R[0-9]+, [$]254","ADDW\t[$]-2,"
for x := <-c; x <= 1 || x > 256; x = <-c {
}
}
func ui3d(c <-chan uint16) {
// amd64:"CMPW\t.+, [$]40","ADDL\t[$]-10,"
// s390x:"CLIJ\t[$]2, R[0-9]+, [$]40","ADDW\t[$]-10,"
for x := <-c; x < 10 || x > 50; x = <-c {
}
}
func ui4d(c <-chan uint8) {
// amd64:"CMPB\t.+, [$]2","ADDL\t[$]-126,"
// s390x:"CLIJ\t[$]10, R[0-9]+, [$]2","ADDW\t[$]-126,"
for x := <-c; x < 126 || x >= 128; x = <-c {
}
}