1
0
mirror of https://github.com/golang/go synced 2024-11-14 08:00:22 -07:00
go/test/codegen/arithmetic.go
Ben Shi 098ca846c7 cmd/compile: emit more compact 386 instructions
ADDL/SUBL/ANDL/ORL/XORL can have a memory operand as destination,
and this CL optimize the compiler to emit such instructions on
386 for more compact binary.

Here is test report:
1. The total size of pkg/linux_386/ and pkg/tool/linux_386/ decreases
about 14KB.
(pkg/linux_386/cmd/compile/ and pkg/tool/linux_386/compile are excluded)

2. The go1 benchmark shows little change, excluding ±2% noise.
name                     old time/op    new time/op    delta
BinaryTree17-4              3.34s ± 2%     3.38s ± 2%  +1.27%  (p=0.000 n=40+39)
Fannkuch11-4                3.55s ± 1%     3.51s ± 1%  -1.33%  (p=0.000 n=40+40)
FmtFprintfEmpty-4          46.3ns ± 3%    46.9ns ± 4%  +1.41%  (p=0.002 n=40+40)
FmtFprintfString-4         80.8ns ± 3%    80.4ns ± 6%  -0.54%  (p=0.044 n=40+40)
FmtFprintfInt-4            93.0ns ± 3%    92.2ns ± 4%  -0.88%  (p=0.007 n=39+40)
FmtFprintfIntInt-4          144ns ± 5%     145ns ± 2%  +0.78%  (p=0.015 n=40+40)
FmtFprintfPrefixedInt-4     184ns ± 2%     182ns ± 2%  -1.06%  (p=0.004 n=40+40)
FmtFprintfFloat-4           415ns ± 4%     419ns ± 4%    ~     (p=0.434 n=40+40)
FmtManyArgs-4               615ns ± 3%     619ns ± 3%    ~     (p=0.100 n=40+40)
GobDecode-4                7.30ms ± 6%    7.36ms ± 6%    ~     (p=0.074 n=40+40)
GobEncode-4                7.10ms ± 6%    7.21ms ± 5%    ~     (p=0.082 n=40+39)
Gzip-4                      364ms ± 3%     362ms ± 6%  -0.71%  (p=0.020 n=40+40)
Gunzip-4                   42.4ms ± 3%    42.2ms ± 3%    ~     (p=0.303 n=40+40)
HTTPClientServer-4         62.9µs ± 1%    62.9µs ± 1%    ~     (p=0.768 n=38+39)
JSONEncode-4               21.4ms ± 4%    21.5ms ± 5%    ~     (p=0.210 n=40+40)
JSONDecode-4               67.7ms ± 3%    67.9ms ± 4%    ~     (p=0.713 n=40+40)
Mandelbrot200-4            5.18ms ± 3%    5.21ms ± 3%  +0.59%  (p=0.021 n=40+40)
GoParse-4                  3.35ms ± 3%    3.34ms ± 2%    ~     (p=0.996 n=40+40)
RegexpMatchEasy0_32-4      98.5ns ± 5%    96.3ns ± 4%  -2.15%  (p=0.001 n=40+40)
RegexpMatchEasy0_1K-4       851ns ± 4%     850ns ± 5%    ~     (p=0.700 n=40+40)
RegexpMatchEasy1_32-4       105ns ± 7%     107ns ± 4%  +1.50%  (p=0.017 n=40+40)
RegexpMatchEasy1_1K-4      1.03µs ± 5%    1.03µs ± 4%    ~     (p=0.992 n=40+40)
RegexpMatchMedium_32-4      130ns ± 6%     128ns ± 4%  -1.66%  (p=0.012 n=40+40)
RegexpMatchMedium_1K-4     44.0µs ± 5%    43.6µs ± 3%    ~     (p=0.704 n=40+40)
RegexpMatchHard_32-4       2.29µs ± 3%    2.23µs ± 4%  -2.38%  (p=0.000 n=40+40)
RegexpMatchHard_1K-4       69.0µs ± 3%    68.1µs ± 3%  -1.28%  (p=0.003 n=40+40)
Revcomp-4                   1.85s ± 2%     1.87s ± 3%  +1.11%  (p=0.000 n=40+40)
Template-4                 69.8ms ± 3%    69.6ms ± 3%    ~     (p=0.125 n=40+40)
TimeParse-4                 442ns ± 5%     440ns ± 3%    ~     (p=0.585 n=40+40)
TimeFormat-4                419ns ± 3%     420ns ± 3%    ~     (p=0.824 n=40+40)
[Geo mean]                 67.3µs         67.2µs       -0.11%

name                     old speed      new speed      delta
GobDecode-4               105MB/s ± 6%   104MB/s ± 6%    ~     (p=0.074 n=40+40)
GobEncode-4               108MB/s ± 7%   107MB/s ± 5%    ~     (p=0.080 n=40+39)
Gzip-4                   53.3MB/s ± 3%  53.7MB/s ± 6%  +0.73%  (p=0.021 n=40+40)
Gunzip-4                  458MB/s ± 3%   460MB/s ± 3%    ~     (p=0.301 n=40+40)
JSONEncode-4             90.8MB/s ± 4%  90.3MB/s ± 4%    ~     (p=0.213 n=40+40)
JSONDecode-4             28.7MB/s ± 3%  28.6MB/s ± 4%    ~     (p=0.679 n=40+40)
GoParse-4                17.3MB/s ± 3%  17.3MB/s ± 2%    ~     (p=1.000 n=40+40)
RegexpMatchEasy0_32-4     325MB/s ± 5%   333MB/s ± 4%  +2.44%  (p=0.000 n=40+38)
RegexpMatchEasy0_1K-4    1.20GB/s ± 4%  1.21GB/s ± 5%    ~     (p=0.684 n=40+40)
RegexpMatchEasy1_32-4     303MB/s ± 7%   298MB/s ± 4%  -1.52%  (p=0.022 n=40+40)
RegexpMatchEasy1_1K-4     995MB/s ± 5%   996MB/s ± 4%    ~     (p=0.996 n=40+40)
RegexpMatchMedium_32-4   7.67MB/s ± 6%  7.80MB/s ± 4%  +1.68%  (p=0.011 n=40+40)
RegexpMatchMedium_1K-4   23.3MB/s ± 5%  23.5MB/s ± 3%    ~     (p=0.697 n=40+40)
RegexpMatchHard_32-4     14.0MB/s ± 3%  14.3MB/s ± 4%  +2.43%  (p=0.000 n=40+40)
RegexpMatchHard_1K-4     14.8MB/s ± 3%  15.0MB/s ± 3%  +1.30%  (p=0.003 n=40+40)
Revcomp-4                 137MB/s ± 2%   136MB/s ± 3%  -1.10%  (p=0.000 n=40+40)
Template-4               27.8MB/s ± 3%  27.9MB/s ± 3%    ~     (p=0.128 n=40+40)
[Geo mean]               79.6MB/s       79.9MB/s       +0.28%

Change-Id: I02a3efc125dc81e18fc8495eb2bf1bba59ab8733
Reviewed-on: https://go-review.googlesource.com/110157
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
2018-05-08 06:44:54 +00:00

185 lines
3.8 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
// This file contains codegen tests related to arithmetic
// simplifications and optimizations on integer types.
// For codegen tests on float types, see floats.go.
// ----------------- //
// Subtraction //
// ----------------- //
func SubMem(arr []int, b int) int {
// 386:`SUBL\s[A-Z]+,\s8\([A-Z]+\)`
arr[2] -= b
// 386:`SUBL\s[A-Z]+,\s12\([A-Z]+\)`
arr[3] -= b
// 386:"SUBL\t4"
// amd64:"SUBQ\t8"
return arr[0] - arr[1]
}
// -------------------- //
// Multiplication //
// -------------------- //
func Pow2Muls(n1, n2 int) (int, int) {
// amd64:"SHLQ\t[$]5",-"IMULQ"
// 386:"SHLL\t[$]5",-"IMULL"
// arm:"SLL\t[$]5",-"MUL"
// arm64:"LSL\t[$]5",-"MUL"
a := n1 * 32
// amd64:"SHLQ\t[$]6",-"IMULQ"
// 386:"SHLL\t[$]6",-"IMULL"
// arm:"SLL\t[$]6",-"MUL"
// arm64:"LSL\t[$]6",-"MUL"
b := -64 * n2
return a, b
}
func Mul_96(n int) int {
// amd64:`SHLQ\t[$]5`,`LEAQ\t\(.*\)\(.*\*2\),`
return n * 96
}
// Multiplications merging tests
func MergeMuls1(n int) int {
// amd64:"IMUL3Q\t[$]46"
// 386:"IMUL3L\t[$]46"
return 15*n + 31*n // 46n
}
func MergeMuls2(n int) int {
// amd64:"IMUL3Q\t[$]23","ADDQ\t[$]29"
// 386:"IMUL3L\t[$]23","ADDL\t[$]29"
return 5*n + 7*(n+1) + 11*(n+2) // 23n + 29
}
func MergeMuls3(a, n int) int {
// amd64:"ADDQ\t[$]19",-"IMULQ\t[$]19"
// 386:"ADDL\t[$]19",-"IMULL\t[$]19"
return a*n + 19*n // (a+19)n
}
func MergeMuls4(n int) int {
// amd64:"IMUL3Q\t[$]14"
// 386:"IMUL3L\t[$]14"
return 23*n - 9*n // 14n
}
func MergeMuls5(a, n int) int {
// amd64:"ADDQ\t[$]-19",-"IMULQ\t[$]19"
// 386:"ADDL\t[$]-19",-"IMULL\t[$]19"
return a*n - 19*n // (a-19)n
}
// -------------- //
// Division //
// -------------- //
func Pow2Divs(n1 uint, n2 int) (uint, int) {
// 386:"SHRL\t[$]5",-"DIVL"
// amd64:"SHRQ\t[$]5",-"DIVQ"
// arm:"SRL\t[$]5",-".*udiv"
// arm64:"LSR\t[$]5",-"UDIV"
a := n1 / 32 // unsigned
// amd64:"SARQ\t[$]6",-"IDIVQ"
// 386:"SARL\t[$]6",-"IDIVL"
// arm:"SRA\t[$]6",-".*udiv"
// arm64:"ASR\t[$]6",-"SDIV"
b := n2 / 64 // signed
return a, b
}
// Check that constant divisions get turned into MULs
func ConstDivs(n1 uint, n2 int) (uint, int) {
// amd64:"MOVQ\t[$]-1085102592571150095","MULQ",-"DIVQ"
a := n1 / 17 // unsigned
// amd64:"MOVQ\t[$]-1085102592571150095","IMULQ",-"IDIVQ"
b := n2 / 17 // signed
return a, b
}
func Pow2Mods(n1 uint, n2 int) (uint, int) {
// 386:"ANDL\t[$]31",-"DIVL"
// amd64:"ANDQ\t[$]31",-"DIVQ"
// arm:"AND\t[$]31",-".*udiv"
// arm64:"AND\t[$]31",-"UDIV"
a := n1 % 32 // unsigned
// 386:-"IDIVL"
// amd64:-"IDIVQ"
// arm:-".*udiv"
// arm64:-"REM"
b := n2 % 64 // signed
return a, b
}
// Check that constant modulo divs get turned into MULs
func ConstMods(n1 uint, n2 int) (uint, int) {
// amd64:"MOVQ\t[$]-1085102592571150095","MULQ",-"DIVQ"
a := n1 % 17 // unsigned
// amd64:"MOVQ\t[$]-1085102592571150095","IMULQ",-"IDIVQ"
b := n2 % 17 // signed
return a, b
}
// Check that len() and cap() calls divided by powers of two are
// optimized into shifts and ands
func LenDiv1(a []int) int {
// 386:"SHRL\t[$]10"
// amd64:"SHRQ\t[$]10"
return len(a) / 1024
}
func LenDiv2(s string) int {
// 386:"SHRL\t[$]11"
// amd64:"SHRQ\t[$]11"
return len(s) / (4097 >> 1)
}
func LenMod1(a []int) int {
// 386:"ANDL\t[$]1023"
// amd64:"ANDQ\t[$]1023"
return len(a) % 1024
}
func LenMod2(s string) int {
// 386:"ANDL\t[$]2047"
// amd64:"ANDQ\t[$]2047"
return len(s) % (4097 >> 1)
}
func CapDiv(a []int) int {
// 386:"SHRL\t[$]12"
// amd64:"SHRQ\t[$]12"
return cap(a) / ((1 << 11) + 2048)
}
func CapMod(a []int) int {
// 386:"ANDL\t[$]4095"
// amd64:"ANDQ\t[$]4095"
return cap(a) % ((1 << 11) + 2048)
}
func AddMul(x int) int {
// amd64:"LEAQ\t1"
return 2*x + 1
}