go/test/codegen/arithmetic.go
Ben Shi 90f2fa0037 cmd/compile: optimize 386 code with MULLload/DIVSSload/DIVSDload
IMULL/DIVSS/DIVSD all can take the source operand from memory
directly. And this CL implement that optimization.

1. The total size of pkg/linux_386 decreases about 84KB (excluding
cmd/compile).

2. The go1 benchmark shows little regression in total (excluding noise).
name                     old time/op    new time/op    delta
BinaryTree17-4              3.29s ± 2%     3.27s ± 4%    ~     (p=0.192 n=30+30)
Fannkuch11-4                3.49s ± 2%     3.54s ± 1%  +1.48%  (p=0.000 n=30+30)
FmtFprintfEmpty-4          45.9ns ± 3%    46.3ns ± 4%  +0.89%  (p=0.037 n=30+30)
FmtFprintfString-4         78.8ns ± 3%    78.7ns ± 4%    ~     (p=0.209 n=30+27)
FmtFprintfInt-4            91.0ns ± 2%    90.3ns ± 2%  -0.82%  (p=0.031 n=30+27)
FmtFprintfIntInt-4          142ns ± 4%     143ns ± 4%    ~     (p=0.136 n=30+30)
FmtFprintfPrefixedInt-4     181ns ± 3%     183ns ± 4%  +1.40%  (p=0.005 n=30+30)
FmtFprintfFloat-4           404ns ± 4%     408ns ± 3%    ~     (p=0.397 n=30+30)
FmtManyArgs-4               601ns ± 3%     609ns ± 5%    ~     (p=0.059 n=30+30)
GobDecode-4                7.21ms ± 5%    7.24ms ± 5%    ~     (p=0.612 n=30+30)
GobEncode-4                6.91ms ± 6%    6.91ms ± 6%    ~     (p=0.797 n=30+30)
Gzip-4                      398ms ± 6%     399ms ± 4%    ~     (p=0.173 n=30+30)
Gunzip-4                   41.7ms ± 3%    41.8ms ± 3%    ~     (p=0.423 n=30+30)
HTTPClientServer-4         62.3µs ± 2%    62.7µs ± 3%    ~     (p=0.085 n=29+30)
JSONEncode-4               21.0ms ± 4%    20.7ms ± 5%  -1.39%  (p=0.014 n=30+30)
JSONDecode-4               66.3ms ± 3%    67.4ms ± 1%  +1.71%  (p=0.003 n=30+24)
Mandelbrot200-4            5.15ms ± 3%    5.16ms ± 3%    ~     (p=0.697 n=30+30)
GoParse-4                  3.24ms ± 3%    3.27ms ± 4%  +0.91%  (p=0.032 n=30+30)
RegexpMatchEasy0_32-4       101ns ± 5%      99ns ± 4%  -1.82%  (p=0.008 n=29+30)
RegexpMatchEasy0_1K-4       848ns ± 4%     841ns ± 2%  -0.77%  (p=0.043 n=30+30)
RegexpMatchEasy1_32-4       106ns ± 6%     106ns ± 3%    ~     (p=0.939 n=29+30)
RegexpMatchEasy1_1K-4      1.02µs ± 3%    1.03µs ± 4%    ~     (p=0.297 n=28+30)
RegexpMatchMedium_32-4      129ns ± 4%     127ns ± 4%    ~     (p=0.073 n=30+30)
RegexpMatchMedium_1K-4     43.9µs ± 3%    43.8µs ± 3%    ~     (p=0.186 n=30+30)
RegexpMatchHard_32-4       2.24µs ± 4%    2.22µs ± 4%    ~     (p=0.332 n=30+29)
RegexpMatchHard_1K-4       68.0µs ± 4%    67.5µs ± 3%    ~     (p=0.290 n=30+30)
Revcomp-4                   1.85s ± 3%     1.85s ± 3%    ~     (p=0.358 n=30+30)
Template-4                 69.6ms ± 3%    70.0ms ± 4%    ~     (p=0.273 n=30+30)
TimeParse-4                 445ns ± 3%     441ns ± 3%    ~     (p=0.494 n=30+30)
TimeFormat-4                412ns ± 3%     412ns ± 6%    ~     (p=0.841 n=30+30)
[Geo mean]                 66.7µs         66.8µs       +0.13%

name                     old speed      new speed      delta
GobDecode-4               107MB/s ± 5%   106MB/s ± 5%    ~     (p=0.615 n=30+30)
GobEncode-4               111MB/s ± 6%   111MB/s ± 6%    ~     (p=0.790 n=30+30)
Gzip-4                   48.8MB/s ± 6%  48.7MB/s ± 4%    ~     (p=0.167 n=30+30)
Gunzip-4                  465MB/s ± 3%   465MB/s ± 3%    ~     (p=0.420 n=30+30)
JSONEncode-4             92.4MB/s ± 4%  93.7MB/s ± 5%  +1.42%  (p=0.015 n=30+30)
JSONDecode-4             29.3MB/s ± 3%  28.8MB/s ± 1%  -1.72%  (p=0.003 n=30+24)
GoParse-4                17.9MB/s ± 3%  17.7MB/s ± 4%  -0.89%  (p=0.037 n=30+30)
RegexpMatchEasy0_32-4     317MB/s ± 8%   324MB/s ± 4%  +2.14%  (p=0.006 n=30+30)
RegexpMatchEasy0_1K-4    1.21GB/s ± 4%  1.22GB/s ± 2%  +0.77%  (p=0.036 n=30+30)
RegexpMatchEasy1_32-4     298MB/s ± 7%   299MB/s ± 4%    ~     (p=0.511 n=30+30)
RegexpMatchEasy1_1K-4    1.00GB/s ± 3%  1.00GB/s ± 4%    ~     (p=0.304 n=28+30)
RegexpMatchMedium_32-4   7.75MB/s ± 4%  7.82MB/s ± 4%    ~     (p=0.089 n=30+30)
RegexpMatchMedium_1K-4   23.3MB/s ± 3%  23.4MB/s ± 3%    ~     (p=0.181 n=30+30)
RegexpMatchHard_32-4     14.3MB/s ± 4%  14.4MB/s ± 4%    ~     (p=0.320 n=30+29)
RegexpMatchHard_1K-4     15.1MB/s ± 4%  15.2MB/s ± 3%    ~     (p=0.273 n=30+30)
Revcomp-4                 137MB/s ± 3%   137MB/s ± 3%    ~     (p=0.352 n=30+30)
Template-4               27.9MB/s ± 3%  27.7MB/s ± 4%    ~     (p=0.277 n=30+30)
[Geo mean]               79.9MB/s       80.1MB/s       +0.15%

Change-Id: I97333cd8ddabb3c7c88ca5aa9e14a005b74d306d
Reviewed-on: https://go-review.googlesource.com/120695
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
2018-08-22 03:38:38 +00:00

202 lines
4.2 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
}
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
}