1
0
mirror of https://github.com/golang/go synced 2024-11-17 10:24:48 -07:00
go/test/codegen/arithmetic.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

221 lines
4.6 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\([A-Z]+\)`
// amd64:`SUBQ\s[A-Z]+,\s16\([A-Z]+\)`
arr[2] -= b
// 386:`SUBL\s[A-Z]+,\s12\([A-Z]+\)`
// amd64:`SUBQ\s[A-Z]+,\s24\([A-Z]+\)`
arr[3] -= b
// 386:`DECL\s16\([A-Z]+\)`
arr[4]--
// 386:`ADDL\s[$]-20,\s20\([A-Z]+\)`
arr[5] -= 20
// 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[$]6",-"MUL"
// arm64:`NEG\sR[0-9]+<<6,\sR[0-9]+`,-`LSL`,-`MUL`
b := -64 * n2
return a, b
}
func Mul_96(n int) int {
// amd64:`SHLQ\t[$]5`,`LEAQ\t\(.*\)\(.*\*2\),`
return n * 96
}
func MulMemSrc(a []uint32, b []float32) {
// 386:`IMULL\s4\([A-Z]+\),\s[A-Z]+`
a[0] *= a[1]
// 386/sse2:`MULSS\s4\([A-Z]+\),\sX[0-9]+`
b[0] *= b[1]
}
// 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 DivMemSrc(a []float64) {
// 386/sse2:`DIVSD\s8\([A-Z]+\),\sX[0-9]+`
a[0] /= a[1]
}
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 FloatDivs(a []float32) float32 {
// amd64:`DIVSS\s8\([A-Z]+\),\sX[0-9]+`
return a[1] / a[2]
}
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
}
func MULA(a, b, c uint32) (uint32, uint32, uint32) {
// arm:`MULA`,-`MUL\s`
// arm64:`MADDW`,-`MULW`
r0 := a*b + c
// arm:`MULA`-`MUL\s`
// arm64:`MADDW`,-`MULW`
r1 := c*79 + a
// arm:`ADD`,-`MULA`-`MUL\s`
// arm64:`ADD`,-`MADD`,-`MULW`
r2 := b*64 + c
return r0, r1, r2
}