go/test/codegen/arithmetic.go
Ben Shi 705f3c74e6 cmd/compile: optimize AMD64 with DIVSSload and DIVSDload
DIVSSload & DIVSDload directly operate on a memory operand. And
binary size can be reduced by them, while the performance is
not affected.

The total size of pkg/linux_amd64 (excluding cmd/compile) decreases
about 6KB.

There is little regression in the go1 benchmark test (excluding noise).
name                     old time/op    new time/op    delta
BinaryTree17-4              2.63s ± 4%     2.62s ± 4%    ~     (p=0.809 n=30+30)
Fannkuch11-4                2.40s ± 2%     2.40s ± 2%    ~     (p=0.109 n=30+30)
FmtFprintfEmpty-4          43.1ns ± 4%    43.2ns ± 9%    ~     (p=0.168 n=30+30)
FmtFprintfString-4         73.6ns ± 4%    74.1ns ± 4%    ~     (p=0.069 n=30+30)
FmtFprintfInt-4            81.0ns ± 3%    81.4ns ± 5%    ~     (p=0.350 n=30+30)
FmtFprintfIntInt-4          127ns ± 4%     129ns ± 4%  +0.99%  (p=0.021 n=30+30)
FmtFprintfPrefixedInt-4     156ns ± 4%     155ns ± 4%    ~     (p=0.415 n=30+30)
FmtFprintfFloat-4           219ns ± 4%     218ns ± 4%    ~     (p=0.071 n=30+30)
FmtManyArgs-4               522ns ± 3%     518ns ± 3%  -0.68%  (p=0.034 n=30+30)
GobDecode-4                6.49ms ± 6%    6.52ms ± 6%    ~     (p=0.832 n=30+30)
GobEncode-4                6.10ms ± 9%    6.14ms ± 7%    ~     (p=0.485 n=30+30)
Gzip-4                      227ms ± 1%     224ms ± 4%    ~     (p=0.484 n=24+30)
Gunzip-4                   37.2ms ± 3%    36.8ms ± 4%    ~     (p=0.889 n=30+30)
HTTPClientServer-4         58.9µs ± 1%    58.7µs ± 2%  -0.42%  (p=0.003 n=28+28)
JSONEncode-4               12.0ms ± 3%    12.0ms ± 4%    ~     (p=0.523 n=30+30)
JSONDecode-4               54.6ms ± 4%    54.5ms ± 4%    ~     (p=0.708 n=30+30)
Mandelbrot200-4            3.78ms ± 4%    3.81ms ± 3%  +0.99%  (p=0.016 n=30+30)
GoParse-4                  3.20ms ± 4%    3.20ms ± 5%    ~     (p=0.994 n=30+30)
RegexpMatchEasy0_32-4      77.0ns ± 4%    75.9ns ± 3%  -1.39%  (p=0.006 n=29+30)
RegexpMatchEasy0_1K-4       255ns ± 4%     253ns ± 4%    ~     (p=0.091 n=30+30)
RegexpMatchEasy1_32-4      69.7ns ± 3%    70.3ns ± 4%    ~     (p=0.120 n=30+30)
RegexpMatchEasy1_1K-4       373ns ± 2%     378ns ± 3%  +1.43%  (p=0.000 n=21+26)
RegexpMatchMedium_32-4      107ns ± 2%     108ns ± 4%  +1.50%  (p=0.012 n=22+30)
RegexpMatchMedium_1K-4     34.0µs ± 1%    34.3µs ± 3%  +1.08%  (p=0.008 n=24+30)
RegexpMatchHard_32-4       1.53µs ± 3%    1.54µs ± 3%    ~     (p=0.234 n=30+30)
RegexpMatchHard_1K-4       46.7µs ± 4%    47.0µs ± 4%    ~     (p=0.420 n=30+30)
Revcomp-4                   411ms ± 7%     415ms ± 6%    ~     (p=0.059 n=30+30)
Template-4                 65.5ms ± 5%    66.9ms ± 4%  +2.21%  (p=0.001 n=30+30)
TimeParse-4                 317ns ± 3%     311ns ± 3%  -1.97%  (p=0.000 n=30+30)
TimeFormat-4                293ns ± 3%     294ns ± 3%    ~     (p=0.243 n=30+30)
[Geo mean]                 47.4µs         47.5µs       +0.17%

name                     old speed      new speed      delta
GobDecode-4               118MB/s ± 5%   118MB/s ± 6%    ~     (p=0.832 n=30+30)
GobEncode-4               125MB/s ± 7%   125MB/s ± 7%    ~     (p=0.625 n=29+30)
Gzip-4                   85.3MB/s ± 1%  86.6MB/s ± 4%    ~     (p=0.486 n=24+30)
Gunzip-4                  522MB/s ± 3%   527MB/s ± 4%    ~     (p=0.889 n=30+30)
JSONEncode-4              162MB/s ± 3%   162MB/s ± 4%    ~     (p=0.520 n=30+30)
JSONDecode-4             35.5MB/s ± 4%  35.6MB/s ± 4%    ~     (p=0.701 n=30+30)
GoParse-4                18.1MB/s ± 4%  18.1MB/s ± 4%    ~     (p=0.891 n=29+30)
RegexpMatchEasy0_32-4     416MB/s ± 4%   422MB/s ± 3%  +1.43%  (p=0.005 n=29+30)
RegexpMatchEasy0_1K-4    4.01GB/s ± 4%  4.04GB/s ± 4%    ~     (p=0.091 n=30+30)
RegexpMatchEasy1_32-4     460MB/s ± 3%   456MB/s ± 5%    ~     (p=0.123 n=30+30)
RegexpMatchEasy1_1K-4    2.74GB/s ± 2%  2.70GB/s ± 3%  -1.33%  (p=0.000 n=22+26)
RegexpMatchMedium_32-4   9.39MB/s ± 3%  9.19MB/s ± 4%  -2.06%  (p=0.001 n=28+30)
RegexpMatchMedium_1K-4   30.1MB/s ± 1%  29.8MB/s ± 3%  -1.04%  (p=0.008 n=24+30)
RegexpMatchHard_32-4     20.9MB/s ± 3%  20.8MB/s ± 3%    ~     (p=0.234 n=30+30)
RegexpMatchHard_1K-4     21.9MB/s ± 4%  21.8MB/s ± 4%    ~     (p=0.420 n=30+30)
Revcomp-4                 619MB/s ± 7%   612MB/s ± 7%    ~     (p=0.059 n=30+30)
Template-4               29.6MB/s ± 4%  29.0MB/s ± 4%  -2.16%  (p=0.002 n=30+30)
[Geo mean]                123MB/s        123MB/s       -0.33%

Change-Id: Ia59e077feae4f2824df79059daea4d0f678e3e4c
Reviewed-on: https://go-review.googlesource.com/120275
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
2018-08-22 02:47:49 +00:00

190 lines
3.9 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 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
}