go/test/codegen/arithmetic.go
Ben Shi 3933302550 cmd/compile: add indexed form for several 386 instructions
This CL implements indexed memory operands for the following instructions.
(ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4
(ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4
(ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4

1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding
cmd/compile/ .

2. There is little regression in the go1 benchmark test, excluding noise.
name                     old time/op    new time/op    delta
BinaryTree17-4              3.25s ± 3%     3.25s ± 3%    ~     (p=0.218 n=40+40)
Fannkuch11-4                3.53s ± 1%     3.53s ± 1%    ~     (p=0.303 n=40+40)
FmtFprintfEmpty-4          44.9ns ± 3%    45.6ns ± 3%  +1.48%  (p=0.030 n=40+36)
FmtFprintfString-4         78.7ns ± 5%    80.1ns ± 7%    ~     (p=0.217 n=36+40)
FmtFprintfInt-4            90.2ns ± 6%    89.8ns ± 5%    ~     (p=0.659 n=40+38)
FmtFprintfIntInt-4          140ns ± 5%     141ns ± 5%  +1.00%  (p=0.027 n=40+40)
FmtFprintfPrefixedInt-4     185ns ± 3%     183ns ± 3%    ~     (p=0.104 n=40+40)
FmtFprintfFloat-4           411ns ± 4%     406ns ± 3%  -1.37%  (p=0.005 n=40+40)
FmtManyArgs-4               590ns ± 4%     598ns ± 4%  +1.35%  (p=0.008 n=40+40)
GobDecode-4                7.16ms ± 5%    7.10ms ± 5%    ~     (p=0.335 n=40+40)
GobEncode-4                6.85ms ± 7%    6.74ms ± 9%    ~     (p=0.058 n=38+40)
Gzip-4                      400ms ± 4%     399ms ± 2%  -0.34%  (p=0.003 n=40+33)
Gunzip-4                   41.4ms ± 3%    41.4ms ± 4%  -0.12%  (p=0.020 n=40+40)
HTTPClientServer-4         64.1µs ± 4%    63.5µs ± 2%  -1.07%  (p=0.000 n=39+37)
JSONEncode-4               15.9ms ± 2%    15.9ms ± 3%    ~     (p=0.103 n=40+40)
JSONDecode-4               62.2ms ± 4%    61.6ms ± 3%  -0.98%  (p=0.006 n=39+40)
Mandelbrot200-4            5.18ms ± 3%    5.14ms ± 4%    ~     (p=0.125 n=40+40)
GoParse-4                  3.29ms ± 2%    3.27ms ± 2%  -0.66%  (p=0.006 n=40+40)
RegexpMatchEasy0_32-4       103ns ± 4%     103ns ± 4%    ~     (p=0.632 n=40+40)
RegexpMatchEasy0_1K-4       830ns ± 3%     828ns ± 3%    ~     (p=0.563 n=40+40)
RegexpMatchEasy1_32-4       113ns ± 4%     113ns ± 4%    ~     (p=0.494 n=40+40)
RegexpMatchEasy1_1K-4      1.03µs ± 4%    1.03µs ± 4%    ~     (p=0.665 n=40+40)
RegexpMatchMedium_32-4      130ns ± 4%     129ns ± 3%    ~     (p=0.458 n=40+40)
RegexpMatchMedium_1K-4     39.4µs ± 3%    39.7µs ± 3%    ~     (p=0.825 n=40+40)
RegexpMatchHard_32-4       2.16µs ± 4%    2.15µs ± 4%    ~     (p=0.137 n=40+40)
RegexpMatchHard_1K-4       65.2µs ± 3%    65.4µs ± 4%    ~     (p=0.160 n=40+40)
Revcomp-4                   1.87s ± 2%     1.87s ± 1%  +0.17%  (p=0.019 n=33+33)
Template-4                 69.4ms ± 3%    69.8ms ± 3%  +0.60%  (p=0.009 n=40+40)
TimeParse-4                 437ns ± 4%     438ns ± 4%    ~     (p=0.234 n=40+40)
TimeFormat-4                408ns ± 3%     408ns ± 3%    ~     (p=0.904 n=40+40)
[Geo mean]                 65.7µs         65.6µs       -0.08%

name                     old speed      new speed      delta
GobDecode-4               107MB/s ± 5%   108MB/s ± 5%    ~     (p=0.336 n=40+40)
GobEncode-4               112MB/s ± 6%   114MB/s ± 9%  +1.95%  (p=0.036 n=37+40)
Gzip-4                   48.5MB/s ± 4%  48.6MB/s ± 2%  +0.28%  (p=0.003 n=40+33)
Gunzip-4                  469MB/s ± 4%   469MB/s ± 4%  +0.11%  (p=0.021 n=40+40)
JSONEncode-4              122MB/s ± 2%   122MB/s ± 3%    ~     (p=0.105 n=40+40)
JSONDecode-4             31.2MB/s ± 4%  31.5MB/s ± 4%  +0.99%  (p=0.007 n=39+40)
GoParse-4                17.6MB/s ± 2%  17.7MB/s ± 2%  +0.66%  (p=0.007 n=40+40)
RegexpMatchEasy0_32-4     310MB/s ± 4%   310MB/s ± 4%    ~     (p=0.384 n=40+40)
RegexpMatchEasy0_1K-4    1.23GB/s ± 3%  1.24GB/s ± 3%    ~     (p=0.186 n=40+40)
RegexpMatchEasy1_32-4     283MB/s ± 3%   281MB/s ± 4%    ~     (p=0.855 n=40+40)
RegexpMatchEasy1_1K-4    1.00GB/s ± 4%  1.00GB/s ± 4%    ~     (p=0.665 n=40+40)
RegexpMatchMedium_32-4   7.68MB/s ± 4%  7.73MB/s ± 3%    ~     (p=0.359 n=40+40)
RegexpMatchMedium_1K-4   26.0MB/s ± 3%  25.8MB/s ± 3%    ~     (p=0.825 n=40+40)
RegexpMatchHard_32-4     14.8MB/s ± 3%  14.9MB/s ± 4%    ~     (p=0.136 n=40+40)
RegexpMatchHard_1K-4     15.7MB/s ± 3%  15.7MB/s ± 4%    ~     (p=0.150 n=40+40)
Revcomp-4                 136MB/s ± 1%   136MB/s ± 1%  -0.09%  (p=0.028 n=32+33)
Template-4               28.0MB/s ± 3%  27.8MB/s ± 3%  -0.59%  (p=0.010 n=40+40)
[Geo mean]               82.1MB/s       82.3MB/s       +0.25%

Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0
Reviewed-on: https://go-review.googlesource.com/c/140303
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
2018-10-09 03:55:08 +00:00

228 lines
4.8 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 //
// ----------------- //
var ef int
func SubMem(arr []int, b, c, d 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\s\([A-Z]+\)\([A-Z]+\*4\),\s[A-Z]+`
ef -= arr[b]
// 386:`SUBL\s[A-Z]+,\s\([A-Z]+\)\([A-Z]+\*4\)`
arr[c] -= b
// 386:`ADDL\s[$]-15,\s\([A-Z]+\)\([A-Z]+\*4\)`
arr[d] -= 15
// 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
}