1
0
mirror of https://github.com/golang/go synced 2024-11-18 03:24:42 -07:00
go/test/codegen/arithmetic.go

578 lines
14 KiB
Go
Raw Normal View History

// 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.
cmd/compile/internal/ssa: optimize 386's subtraction The SUBL instruction can take a memory operand, and this CL implements this optimization. The go1 benchmark shows a little improvement. name old time/op new time/op delta BinaryTree17-4 3.27s ± 2% 3.29s ± 3% ~ (p=0.322 n=37+40) Fannkuch11-4 3.49s ± 0% 3.53s ± 1% +1.21% (p=0.000 n=31+40) FmtFprintfEmpty-4 46.2ns ± 3% 46.3ns ± 2% ~ (p=0.351 n=40+28) FmtFprintfString-4 82.0ns ± 3% 81.5ns ± 2% -0.69% (p=0.002 n=40+30) FmtFprintfInt-4 94.6ns ± 3% 94.6ns ± 6% ~ (p=0.913 n=39+37) FmtFprintfIntInt-4 147ns ± 3% 150ns ± 2% +1.72% (p=0.000 n=40+25) FmtFprintfPrefixedInt-4 186ns ± 3% 186ns ± 0% -0.33% (p=0.006 n=40+25) FmtFprintfFloat-4 388ns ± 4% 388ns ± 4% ~ (p=0.162 n=40+40) FmtManyArgs-4 612ns ± 3% 616ns ± 4% ~ (p=0.223 n=40+40) GobDecode-4 7.35ms ± 5% 7.42ms ± 5% ~ (p=0.095 n=40+40) GobEncode-4 7.21ms ± 8% 7.23ms ± 4% ~ (p=0.294 n=40+40) Gzip-4 360ms ± 4% 359ms ± 4% ~ (p=0.097 n=40+40) Gunzip-4 46.1ms ± 3% 45.6ms ± 3% -1.20% (p=0.000 n=40+40) HTTPClientServer-4 64.0µs ± 2% 64.1µs ± 2% ~ (p=0.648 n=39+40) JSONEncode-4 21.9ms ± 4% 22.1ms ± 5% ~ (p=0.086 n=40+40) JSONDecode-4 67.9ms ± 4% 66.7ms ± 4% -1.63% (p=0.000 n=40+40) Mandelbrot200-4 5.19ms ± 3% 5.17ms ± 3% ~ (p=0.881 n=40+40) GoParse-4 3.34ms ± 3% 3.28ms ± 2% -1.78% (p=0.000 n=40+40) RegexpMatchEasy0_32-4 101ns ± 5% 99ns ± 3% -2.40% (p=0.000 n=40+40) RegexpMatchEasy0_1K-4 851ns ± 1% 848ns ± 3% -0.36% (p=0.004 n=33+40) RegexpMatchEasy1_32-4 109ns ± 5% 105ns ± 3% -3.53% (p=0.000 n=39+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 3% ~ (p=0.638 n=40+38) RegexpMatchMedium_32-4 131ns ± 5% 127ns ± 4% -3.36% (p=0.000 n=38+40) RegexpMatchMedium_1K-4 43.4µs ± 4% 43.2µs ± 3% -0.46% (p=0.008 n=40+40) RegexpMatchHard_32-4 2.21µs ± 4% 2.23µs ± 1% +0.77% (p=0.014 n=40+28) RegexpMatchHard_1K-4 67.6µs ± 4% 67.7µs ± 3% +0.11% (p=0.016 n=40+40) Revcomp-4 1.86s ± 3% 1.77s ± 2% -4.81% (p=0.000 n=40+40) Template-4 71.7ms ± 3% 71.6ms ± 4% ~ (p=0.200 n=40+40) TimeParse-4 436ns ± 4% 433ns ± 3% ~ (p=0.358 n=40+40) TimeFormat-4 413ns ± 4% 412ns ± 3% ~ (p=0.415 n=40+40) [Geo mean] 63.9µs 63.6µs -0.49% name old speed new speed delta GobDecode-4 105MB/s ± 5% 104MB/s ± 5% ~ (p=0.096 n=40+40) GobEncode-4 106MB/s ± 7% 106MB/s ± 3% ~ (p=0.385 n=39+40) Gzip-4 54.0MB/s ± 4% 54.0MB/s ± 4% ~ (p=0.100 n=40+40) Gunzip-4 421MB/s ± 3% 426MB/s ± 3% +1.21% (p=0.000 n=40+40) JSONEncode-4 88.5MB/s ± 5% 88.0MB/s ± 5% ~ (p=0.083 n=40+40) JSONDecode-4 28.6MB/s ± 4% 29.1MB/s ± 4% +1.65% (p=0.000 n=40+40) GoParse-4 17.3MB/s ± 3% 17.7MB/s ± 2% +1.82% (p=0.000 n=40+40) RegexpMatchEasy0_32-4 316MB/s ± 5% 323MB/s ± 4% +2.44% (p=0.000 n=40+40) RegexpMatchEasy0_1K-4 1.20GB/s ± 1% 1.21GB/s ± 3% +0.40% (p=0.004 n=33+40) RegexpMatchEasy1_32-4 291MB/s ± 7% 302MB/s ± 4% +3.82% (p=0.000 n=40+40) RegexpMatchEasy1_1K-4 993MB/s ± 4% 990MB/s ± 3% ~ (p=0.623 n=40+38) RegexpMatchMedium_32-4 7.61MB/s ± 5% 7.87MB/s ± 4% +3.36% (p=0.000 n=38+40) RegexpMatchMedium_1K-4 23.6MB/s ± 4% 23.7MB/s ± 4% +0.46% (p=0.007 n=40+40) RegexpMatchHard_32-4 14.5MB/s ± 4% 14.3MB/s ± 1% -0.79% (p=0.017 n=40+28) RegexpMatchHard_1K-4 15.1MB/s ± 4% 15.1MB/s ± 3% -0.11% (p=0.015 n=40+40) Revcomp-4 137MB/s ± 3% 144MB/s ± 3% +5.06% (p=0.000 n=40+40) Template-4 27.1MB/s ± 3% 27.1MB/s ± 4% ~ (p=0.211 n=40+40) [Geo mean] 78.9MB/s 79.7MB/s +1.01% Change-Id: I638fa4fef85833e8605919d693f9570cc3cf7334 Reviewed-on: https://go-review.googlesource.com/107275 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-04-15 03:31:39 -06:00
// ----------------- //
// Subtraction //
// ----------------- //
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>
2018-10-06 07:13:48 -06:00
var ef int
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>
2018-10-06 07:13:48 -06:00
func SubMem(arr []int, b, c, d int) int {
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>
2018-04-29 04:42:14 -06:00
// 386:`SUBL\s[A-Z]+,\s8\([A-Z]+\)`
cmd/compile: introduce more read-modify-write operations for amd64 Add suport of read-modify-write for AND/SUB/AND/OR/XOR on amd64. 1. The total size of pkg/linux_amd64 decreases about 4KB, excluding cmd/compile. 2. The go1 benchmark shows a little improvement, excluding noise. name old time/op new time/op delta BinaryTree17-4 2.63s ± 3% 2.65s ± 4% +1.01% (p=0.037 n=35+35) Fannkuch11-4 2.33s ± 2% 2.39s ± 2% +2.49% (p=0.000 n=35+35) FmtFprintfEmpty-4 45.4ns ± 5% 40.8ns ± 6% -10.09% (p=0.000 n=35+35) FmtFprintfString-4 73.3ns ± 4% 70.9ns ± 3% -3.23% (p=0.000 n=30+35) FmtFprintfInt-4 79.9ns ± 4% 79.5ns ± 3% ~ (p=0.736 n=34+35) FmtFprintfIntInt-4 126ns ± 4% 125ns ± 4% ~ (p=0.083 n=35+35) FmtFprintfPrefixedInt-4 152ns ± 6% 152ns ± 3% ~ (p=0.855 n=34+35) FmtFprintfFloat-4 215ns ± 4% 213ns ± 4% ~ (p=0.066 n=35+35) FmtManyArgs-4 522ns ± 3% 506ns ± 3% -3.15% (p=0.000 n=35+35) GobDecode-4 6.45ms ± 8% 6.51ms ± 7% +0.96% (p=0.026 n=35+35) GobEncode-4 6.10ms ± 6% 6.02ms ± 8% ~ (p=0.160 n=35+35) Gzip-4 228ms ± 3% 221ms ± 3% -2.92% (p=0.000 n=35+35) Gunzip-4 37.5ms ± 4% 37.2ms ± 3% -0.78% (p=0.036 n=35+35) HTTPClientServer-4 58.7µs ± 2% 59.2µs ± 1% +0.80% (p=0.000 n=33+33) JSONEncode-4 12.0ms ± 3% 12.2ms ± 3% +1.84% (p=0.008 n=35+35) JSONDecode-4 57.0ms ± 4% 56.6ms ± 3% ~ (p=0.320 n=35+35) Mandelbrot200-4 3.82ms ± 3% 3.79ms ± 3% ~ (p=0.074 n=35+35) GoParse-4 3.21ms ± 5% 3.24ms ± 4% ~ (p=0.119 n=35+35) RegexpMatchEasy0_32-4 76.3ns ± 4% 75.4ns ± 4% -1.14% (p=0.014 n=34+33) RegexpMatchEasy0_1K-4 251ns ± 4% 254ns ± 3% +1.28% (p=0.016 n=35+35) RegexpMatchEasy1_32-4 69.6ns ± 3% 70.1ns ± 3% +0.82% (p=0.005 n=35+35) RegexpMatchEasy1_1K-4 367ns ± 4% 376ns ± 4% +2.47% (p=0.000 n=35+35) RegexpMatchMedium_32-4 108ns ± 5% 104ns ± 4% -3.18% (p=0.000 n=35+35) RegexpMatchMedium_1K-4 33.8µs ± 3% 32.7µs ± 3% -3.27% (p=0.000 n=35+35) RegexpMatchHard_32-4 1.55µs ± 3% 1.52µs ± 3% -1.64% (p=0.000 n=35+35) RegexpMatchHard_1K-4 46.6µs ± 3% 46.6µs ± 4% ~ (p=0.149 n=35+35) Revcomp-4 416ms ± 7% 412ms ± 6% -0.95% (p=0.033 n=33+35) Template-4 64.3ms ± 3% 62.4ms ± 7% -2.94% (p=0.000 n=35+35) TimeParse-4 320ns ± 2% 322ns ± 3% ~ (p=0.589 n=35+35) TimeFormat-4 300ns ± 3% 300ns ± 3% ~ (p=0.597 n=35+35) [Geo mean] 47.4µs 47.0µs -0.86% name old speed new speed delta GobDecode-4 119MB/s ± 7% 118MB/s ± 7% -0.96% (p=0.027 n=35+35) GobEncode-4 126MB/s ± 7% 127MB/s ± 6% ~ (p=0.157 n=34+34) Gzip-4 85.3MB/s ± 3% 87.9MB/s ± 3% +3.02% (p=0.000 n=35+35) Gunzip-4 518MB/s ± 4% 522MB/s ± 3% +0.79% (p=0.037 n=35+35) JSONEncode-4 162MB/s ± 3% 159MB/s ± 3% -1.81% (p=0.009 n=35+35) JSONDecode-4 34.1MB/s ± 4% 34.3MB/s ± 3% ~ (p=0.318 n=35+35) GoParse-4 18.0MB/s ± 5% 17.9MB/s ± 4% ~ (p=0.117 n=35+35) RegexpMatchEasy0_32-4 419MB/s ± 3% 425MB/s ± 4% +1.46% (p=0.003 n=32+33) RegexpMatchEasy0_1K-4 4.07GB/s ± 4% 4.02GB/s ± 3% -1.28% (p=0.014 n=35+35) RegexpMatchEasy1_32-4 460MB/s ± 3% 456MB/s ± 4% -0.82% (p=0.004 n=35+35) RegexpMatchEasy1_1K-4 2.79GB/s ± 4% 2.72GB/s ± 4% -2.39% (p=0.000 n=35+35) RegexpMatchMedium_32-4 9.23MB/s ± 4% 9.53MB/s ± 4% +3.16% (p=0.000 n=35+35) RegexpMatchMedium_1K-4 30.3MB/s ± 3% 31.3MB/s ± 3% +3.38% (p=0.000 n=35+35) RegexpMatchHard_32-4 20.7MB/s ± 3% 21.0MB/s ± 3% +1.67% (p=0.000 n=35+35) RegexpMatchHard_1K-4 22.0MB/s ± 3% 21.9MB/s ± 4% ~ (p=0.277 n=35+33) Revcomp-4 612MB/s ± 7% 618MB/s ± 6% +0.96% (p=0.034 n=33+35) Template-4 30.2MB/s ± 3% 31.1MB/s ± 6% +3.05% (p=0.000 n=35+35) [Geo mean] 123MB/s 124MB/s +0.64% Change-Id: Ia025da272e07d0069413824bfff3471b106d6280 Reviewed-on: https://go-review.googlesource.com/121535 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com> Reviewed-by: Keith Randall <khr@golang.org>
2018-06-28 20:11:53 -06:00
// amd64:`SUBQ\s[A-Z]+,\s16\([A-Z]+\)`
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>
2018-04-29 04:42:14 -06:00
arr[2] -= b
// 386:`SUBL\s[A-Z]+,\s12\([A-Z]+\)`
cmd/compile: introduce more read-modify-write operations for amd64 Add suport of read-modify-write for AND/SUB/AND/OR/XOR on amd64. 1. The total size of pkg/linux_amd64 decreases about 4KB, excluding cmd/compile. 2. The go1 benchmark shows a little improvement, excluding noise. name old time/op new time/op delta BinaryTree17-4 2.63s ± 3% 2.65s ± 4% +1.01% (p=0.037 n=35+35) Fannkuch11-4 2.33s ± 2% 2.39s ± 2% +2.49% (p=0.000 n=35+35) FmtFprintfEmpty-4 45.4ns ± 5% 40.8ns ± 6% -10.09% (p=0.000 n=35+35) FmtFprintfString-4 73.3ns ± 4% 70.9ns ± 3% -3.23% (p=0.000 n=30+35) FmtFprintfInt-4 79.9ns ± 4% 79.5ns ± 3% ~ (p=0.736 n=34+35) FmtFprintfIntInt-4 126ns ± 4% 125ns ± 4% ~ (p=0.083 n=35+35) FmtFprintfPrefixedInt-4 152ns ± 6% 152ns ± 3% ~ (p=0.855 n=34+35) FmtFprintfFloat-4 215ns ± 4% 213ns ± 4% ~ (p=0.066 n=35+35) FmtManyArgs-4 522ns ± 3% 506ns ± 3% -3.15% (p=0.000 n=35+35) GobDecode-4 6.45ms ± 8% 6.51ms ± 7% +0.96% (p=0.026 n=35+35) GobEncode-4 6.10ms ± 6% 6.02ms ± 8% ~ (p=0.160 n=35+35) Gzip-4 228ms ± 3% 221ms ± 3% -2.92% (p=0.000 n=35+35) Gunzip-4 37.5ms ± 4% 37.2ms ± 3% -0.78% (p=0.036 n=35+35) HTTPClientServer-4 58.7µs ± 2% 59.2µs ± 1% +0.80% (p=0.000 n=33+33) JSONEncode-4 12.0ms ± 3% 12.2ms ± 3% +1.84% (p=0.008 n=35+35) JSONDecode-4 57.0ms ± 4% 56.6ms ± 3% ~ (p=0.320 n=35+35) Mandelbrot200-4 3.82ms ± 3% 3.79ms ± 3% ~ (p=0.074 n=35+35) GoParse-4 3.21ms ± 5% 3.24ms ± 4% ~ (p=0.119 n=35+35) RegexpMatchEasy0_32-4 76.3ns ± 4% 75.4ns ± 4% -1.14% (p=0.014 n=34+33) RegexpMatchEasy0_1K-4 251ns ± 4% 254ns ± 3% +1.28% (p=0.016 n=35+35) RegexpMatchEasy1_32-4 69.6ns ± 3% 70.1ns ± 3% +0.82% (p=0.005 n=35+35) RegexpMatchEasy1_1K-4 367ns ± 4% 376ns ± 4% +2.47% (p=0.000 n=35+35) RegexpMatchMedium_32-4 108ns ± 5% 104ns ± 4% -3.18% (p=0.000 n=35+35) RegexpMatchMedium_1K-4 33.8µs ± 3% 32.7µs ± 3% -3.27% (p=0.000 n=35+35) RegexpMatchHard_32-4 1.55µs ± 3% 1.52µs ± 3% -1.64% (p=0.000 n=35+35) RegexpMatchHard_1K-4 46.6µs ± 3% 46.6µs ± 4% ~ (p=0.149 n=35+35) Revcomp-4 416ms ± 7% 412ms ± 6% -0.95% (p=0.033 n=33+35) Template-4 64.3ms ± 3% 62.4ms ± 7% -2.94% (p=0.000 n=35+35) TimeParse-4 320ns ± 2% 322ns ± 3% ~ (p=0.589 n=35+35) TimeFormat-4 300ns ± 3% 300ns ± 3% ~ (p=0.597 n=35+35) [Geo mean] 47.4µs 47.0µs -0.86% name old speed new speed delta GobDecode-4 119MB/s ± 7% 118MB/s ± 7% -0.96% (p=0.027 n=35+35) GobEncode-4 126MB/s ± 7% 127MB/s ± 6% ~ (p=0.157 n=34+34) Gzip-4 85.3MB/s ± 3% 87.9MB/s ± 3% +3.02% (p=0.000 n=35+35) Gunzip-4 518MB/s ± 4% 522MB/s ± 3% +0.79% (p=0.037 n=35+35) JSONEncode-4 162MB/s ± 3% 159MB/s ± 3% -1.81% (p=0.009 n=35+35) JSONDecode-4 34.1MB/s ± 4% 34.3MB/s ± 3% ~ (p=0.318 n=35+35) GoParse-4 18.0MB/s ± 5% 17.9MB/s ± 4% ~ (p=0.117 n=35+35) RegexpMatchEasy0_32-4 419MB/s ± 3% 425MB/s ± 4% +1.46% (p=0.003 n=32+33) RegexpMatchEasy0_1K-4 4.07GB/s ± 4% 4.02GB/s ± 3% -1.28% (p=0.014 n=35+35) RegexpMatchEasy1_32-4 460MB/s ± 3% 456MB/s ± 4% -0.82% (p=0.004 n=35+35) RegexpMatchEasy1_1K-4 2.79GB/s ± 4% 2.72GB/s ± 4% -2.39% (p=0.000 n=35+35) RegexpMatchMedium_32-4 9.23MB/s ± 4% 9.53MB/s ± 4% +3.16% (p=0.000 n=35+35) RegexpMatchMedium_1K-4 30.3MB/s ± 3% 31.3MB/s ± 3% +3.38% (p=0.000 n=35+35) RegexpMatchHard_32-4 20.7MB/s ± 3% 21.0MB/s ± 3% +1.67% (p=0.000 n=35+35) RegexpMatchHard_1K-4 22.0MB/s ± 3% 21.9MB/s ± 4% ~ (p=0.277 n=35+33) Revcomp-4 612MB/s ± 7% 618MB/s ± 6% +0.96% (p=0.034 n=33+35) Template-4 30.2MB/s ± 3% 31.1MB/s ± 6% +3.05% (p=0.000 n=35+35) [Geo mean] 123MB/s 124MB/s +0.64% Change-Id: Ia025da272e07d0069413824bfff3471b106d6280 Reviewed-on: https://go-review.googlesource.com/121535 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com> Reviewed-by: Keith Randall <khr@golang.org>
2018-06-28 20:11:53 -06:00
// amd64:`SUBQ\s[A-Z]+,\s24\([A-Z]+\)`
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>
2018-04-29 04:42:14 -06:00
arr[3] -= b
cmd/compile: implement "OPC $imm, (mem)" for 386 New read-modify-write operations are introduced in this CL for 386. 1. The total size of pkg/linux_386 decreases about 10KB (excluding cmd/compile). 2. The go1 benchmark shows little regression. name old time/op new time/op delta BinaryTree17-4 3.32s ± 4% 3.29s ± 2% ~ (p=0.059 n=30+30) Fannkuch11-4 3.49s ± 1% 3.46s ± 1% -0.92% (p=0.001 n=30+30) FmtFprintfEmpty-4 47.7ns ± 2% 46.8ns ± 5% -1.93% (p=0.011 n=25+30) FmtFprintfString-4 79.5ns ± 7% 80.2ns ± 3% +0.89% (p=0.001 n=28+29) FmtFprintfInt-4 90.5ns ± 2% 92.1ns ± 2% +1.82% (p=0.014 n=22+30) FmtFprintfIntInt-4 141ns ± 1% 144ns ± 3% +2.23% (p=0.013 n=22+30) FmtFprintfPrefixedInt-4 183ns ± 2% 184ns ± 3% ~ (p=0.080 n=21+30) FmtFprintfFloat-4 409ns ± 3% 412ns ± 3% +0.83% (p=0.040 n=30+30) FmtManyArgs-4 597ns ± 6% 607ns ± 4% +1.71% (p=0.006 n=30+30) GobDecode-4 7.21ms ± 5% 7.18ms ± 6% ~ (p=0.665 n=30+30) GobEncode-4 7.17ms ± 6% 7.09ms ± 7% ~ (p=0.117 n=29+30) Gzip-4 413ms ± 4% 399ms ± 4% -3.48% (p=0.000 n=30+30) Gunzip-4 41.3ms ± 4% 41.7ms ± 3% +1.05% (p=0.011 n=30+30) HTTPClientServer-4 63.5µs ± 3% 62.9µs ± 2% -0.97% (p=0.017 n=30+27) JSONEncode-4 20.3ms ± 5% 20.1ms ± 5% -1.16% (p=0.004 n=30+30) JSONDecode-4 66.2ms ± 4% 67.7ms ± 4% +2.21% (p=0.000 n=30+30) Mandelbrot200-4 5.16ms ± 3% 5.18ms ± 3% ~ (p=0.123 n=30+30) GoParse-4 3.23ms ± 2% 3.27ms ± 2% +1.08% (p=0.006 n=30+30) RegexpMatchEasy0_32-4 98.9ns ± 5% 97.1ns ± 4% -1.83% (p=0.006 n=30+30) RegexpMatchEasy0_1K-4 842ns ± 3% 842ns ± 3% ~ (p=0.550 n=30+30) RegexpMatchEasy1_32-4 107ns ± 4% 105ns ± 4% -1.93% (p=0.012 n=30+30) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.04µs ± 4% ~ (p=0.304 n=30+30) RegexpMatchMedium_32-4 132ns ± 2% 129ns ± 4% -2.02% (p=0.000 n=21+30) RegexpMatchMedium_1K-4 44.1µs ± 4% 43.8µs ± 3% ~ (p=0.641 n=30+30) RegexpMatchHard_32-4 2.26µs ± 4% 2.23µs ± 4% -1.28% (p=0.023 n=30+30) RegexpMatchHard_1K-4 68.1µs ± 3% 68.6µs ± 4% ~ (p=0.089 n=30+30) Revcomp-4 1.85s ± 2% 1.84s ± 2% ~ (p=0.072 n=30+30) Template-4 69.2ms ± 3% 68.5ms ± 3% -1.04% (p=0.012 n=30+30) TimeParse-4 441ns ± 3% 446ns ± 4% +1.21% (p=0.001 n=30+30) TimeFormat-4 415ns ± 3% 415ns ± 3% ~ (p=0.436 n=30+30) [Geo mean] 67.0µs 66.9µs -0.17% name old speed new speed delta GobDecode-4 107MB/s ± 5% 107MB/s ± 6% ~ (p=0.663 n=30+30) GobEncode-4 107MB/s ± 6% 108MB/s ± 7% ~ (p=0.117 n=29+30) Gzip-4 47.0MB/s ± 4% 48.7MB/s ± 4% +3.61% (p=0.000 n=30+30) Gunzip-4 470MB/s ± 4% 466MB/s ± 4% -1.05% (p=0.011 n=30+30) JSONEncode-4 95.6MB/s ± 5% 96.7MB/s ± 5% +1.16% (p=0.005 n=30+30) JSONDecode-4 29.3MB/s ± 4% 28.7MB/s ± 4% -2.17% (p=0.000 n=30+30) GoParse-4 17.9MB/s ± 2% 17.7MB/s ± 2% -1.06% (p=0.007 n=30+30) RegexpMatchEasy0_32-4 323MB/s ± 5% 329MB/s ± 4% +1.93% (p=0.006 n=30+30) RegexpMatchEasy0_1K-4 1.22GB/s ± 3% 1.22GB/s ± 3% ~ (p=0.496 n=30+30) RegexpMatchEasy1_32-4 298MB/s ± 4% 303MB/s ± 4% +1.84% (p=0.017 n=30+30) RegexpMatchEasy1_1K-4 995MB/s ± 4% 989MB/s ± 4% ~ (p=0.307 n=30+30) RegexpMatchMedium_32-4 7.56MB/s ± 4% 7.74MB/s ± 4% +2.46% (p=0.000 n=22+30) RegexpMatchMedium_1K-4 23.2MB/s ± 4% 23.4MB/s ± 3% ~ (p=0.651 n=30+30) RegexpMatchHard_32-4 14.2MB/s ± 4% 14.3MB/s ± 4% +1.29% (p=0.021 n=30+30) RegexpMatchHard_1K-4 15.0MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.069 n=30+29) Revcomp-4 138MB/s ± 2% 138MB/s ± 2% ~ (p=0.072 n=30+30) Template-4 28.1MB/s ± 3% 28.4MB/s ± 3% +1.05% (p=0.012 n=30+30) [Geo mean] 79.7MB/s 80.2MB/s +0.60% Change-Id: I44a1dfc942c9a385904553c4fe1fa8e509c8aa31 Reviewed-on: https://go-review.googlesource.com/120916 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-06-25 20:58:54 -06:00
// 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]+`
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>
2018-10-06 07:13:48 -06:00
ef -= arr[b]
// 386:`SUBL\s[A-Z]+,\s\([A-Z]+\)\([A-Z]+\*4\)`
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>
2018-10-06 07:13:48 -06:00
arr[c] -= b
// 386:`ADDL\s[$]-15,\s\([A-Z]+\)\([A-Z]+\*4\)`
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>
2018-10-06 07:13:48 -06:00
arr[d] -= 15
// 386:`DECL\s\([A-Z]+\)\([A-Z]+\*4\)`
cmd/compile: optimize 386's ADDLconstmodifyidx4 This CL optimize ADDLconstmodifyidx4 to INCL/DECL, when the constant is +1/-1. 1. The total size of pkg/linux_386/ decreases 28 bytes, excluding cmd/compile. 2. There is no regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 2% 3.23s ± 3% -0.70% (p=0.040 n=30+30) Fannkuch11-4 3.50s ± 1% 3.47s ± 1% -0.68% (p=0.000 n=30+30) FmtFprintfEmpty-4 44.6ns ± 3% 44.8ns ± 3% +0.46% (p=0.029 n=30+30) FmtFprintfString-4 79.0ns ± 3% 78.7ns ± 3% ~ (p=0.053 n=30+30) FmtFprintfInt-4 89.2ns ± 2% 89.4ns ± 3% ~ (p=0.665 n=30+29) FmtFprintfIntInt-4 142ns ± 3% 142ns ± 3% ~ (p=0.435 n=30+30) FmtFprintfPrefixedInt-4 182ns ± 2% 182ns ± 2% ~ (p=0.964 n=30+30) FmtFprintfFloat-4 407ns ± 3% 411ns ± 4% ~ (p=0.080 n=30+30) FmtManyArgs-4 597ns ± 3% 593ns ± 4% ~ (p=0.222 n=30+30) GobDecode-4 7.09ms ± 6% 7.07ms ± 7% ~ (p=0.633 n=30+30) GobEncode-4 6.81ms ± 9% 6.81ms ± 8% ~ (p=0.982 n=30+30) Gzip-4 398ms ± 4% 400ms ± 6% ~ (p=0.177 n=30+30) Gunzip-4 41.3ms ± 3% 40.6ms ± 4% -1.71% (p=0.005 n=30+30) HTTPClientServer-4 63.4µs ± 3% 63.4µs ± 4% ~ (p=0.646 n=30+28) JSONEncode-4 16.0ms ± 3% 16.1ms ± 3% ~ (p=0.057 n=30+30) JSONDecode-4 63.3ms ± 8% 63.1ms ± 7% ~ (p=0.786 n=30+30) Mandelbrot200-4 5.17ms ± 3% 5.15ms ± 8% ~ (p=0.654 n=30+30) GoParse-4 3.24ms ± 3% 3.23ms ± 2% ~ (p=0.091 n=30+30) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.575 n=30+30) RegexpMatchEasy0_1K-4 823ns ± 2% 821ns ± 3% ~ (p=0.827 n=30+30) RegexpMatchEasy1_32-4 113ns ± 3% 112ns ± 3% ~ (p=0.076 n=30+30) RegexpMatchEasy1_1K-4 1.02µs ± 4% 1.01µs ± 5% ~ (p=0.087 n=30+30) RegexpMatchMedium_32-4 129ns ± 3% 127ns ± 4% -1.55% (p=0.009 n=30+30) RegexpMatchMedium_1K-4 39.3µs ± 4% 39.7µs ± 3% ~ (p=0.054 n=30+30) RegexpMatchHard_32-4 2.15µs ± 4% 2.15µs ± 4% ~ (p=0.712 n=30+30) RegexpMatchHard_1K-4 66.0µs ± 3% 65.1µs ± 3% -1.32% (p=0.002 n=30+30) Revcomp-4 1.85s ± 2% 1.85s ± 3% ~ (p=0.168 n=30+30) Template-4 69.5ms ± 7% 68.9ms ± 6% ~ (p=0.250 n=28+28) TimeParse-4 434ns ± 3% 432ns ± 4% ~ (p=0.629 n=30+30) TimeFormat-4 403ns ± 4% 408ns ± 3% +1.23% (p=0.019 n=30+29) [Geo mean] 65.5µs 65.3µs -0.20% name old speed new speed delta GobDecode-4 108MB/s ± 6% 109MB/s ± 6% ~ (p=0.636 n=30+30) GobEncode-4 113MB/s ±10% 113MB/s ± 9% ~ (p=0.982 n=30+30) Gzip-4 48.8MB/s ± 4% 48.6MB/s ± 5% ~ (p=0.178 n=30+30) Gunzip-4 470MB/s ± 3% 479MB/s ± 4% +1.72% (p=0.006 n=30+30) JSONEncode-4 121MB/s ± 3% 120MB/s ± 3% ~ (p=0.057 n=30+30) JSONDecode-4 30.7MB/s ± 8% 30.8MB/s ± 8% ~ (p=0.784 n=30+30) GoParse-4 17.9MB/s ± 3% 17.9MB/s ± 2% ~ (p=0.090 n=30+30) RegexpMatchEasy0_32-4 309MB/s ± 4% 309MB/s ± 3% ~ (p=0.530 n=30+30) RegexpMatchEasy0_1K-4 1.24GB/s ± 2% 1.25GB/s ± 3% ~ (p=0.976 n=30+30) RegexpMatchEasy1_32-4 282MB/s ± 3% 284MB/s ± 3% +0.81% (p=0.041 n=30+30) RegexpMatchEasy1_1K-4 1.00GB/s ± 3% 1.01GB/s ± 4% ~ (p=0.091 n=30+30) RegexpMatchMedium_32-4 7.71MB/s ± 3% 7.84MB/s ± 4% +1.71% (p=0.000 n=30+30) RegexpMatchMedium_1K-4 26.1MB/s ± 4% 25.8MB/s ± 3% ~ (p=0.051 n=30+30) RegexpMatchHard_32-4 14.9MB/s ± 4% 14.9MB/s ± 4% ~ (p=0.712 n=30+30) RegexpMatchHard_1K-4 15.5MB/s ± 3% 15.7MB/s ± 3% +1.34% (p=0.003 n=30+30) Revcomp-4 138MB/s ± 2% 137MB/s ± 3% ~ (p=0.174 n=30+30) Template-4 28.0MB/s ± 6% 28.2MB/s ± 6% ~ (p=0.251 n=28+28) [Geo mean] 82.3MB/s 82.6MB/s +0.36% Change-Id: I389829699ffe9500a013fcf31be58a97e98043e1 Reviewed-on: https://go-review.googlesource.com/c/140701 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-09 05:01:34 -06:00
arr[b]--
cmd/compile: optimize amd64's ADDQconstmodify/ADDLconstmodify This CL optimize amd64's code: "ADDQ $-1, MEM_OP" -> "DECQ MEM_OP" "ADDL $-1, MEM_OP" -> "DECL MEM_OP" 1. The total size of pkg/linux_amd64 (excluding cmd/compile) decreases about 0.1KB. 2. The go1 benchmark shows little regression, excluding noise. name old time/op new time/op delta BinaryTree17-4 2.60s ± 5% 2.64s ± 3% +1.53% (p=0.000 n=38+39) Fannkuch11-4 2.37s ± 2% 2.38s ± 2% ~ (p=0.950 n=40+40) FmtFprintfEmpty-4 40.4ns ± 5% 40.5ns ± 5% ~ (p=0.711 n=40+40) FmtFprintfString-4 72.4ns ± 5% 72.3ns ± 3% ~ (p=0.485 n=40+40) FmtFprintfInt-4 79.7ns ± 3% 80.1ns ± 3% ~ (p=0.124 n=40+40) FmtFprintfIntInt-4 126ns ± 3% 127ns ± 3% +0.71% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 153ns ± 4% 153ns ± 2% ~ (p=0.604 n=40+40) FmtFprintfFloat-4 206ns ± 5% 210ns ± 5% +1.79% (p=0.002 n=40+40) FmtManyArgs-4 498ns ± 3% 496ns ± 3% ~ (p=0.099 n=40+40) GobDecode-4 6.48ms ± 6% 6.47ms ± 7% ~ (p=0.686 n=39+40) GobEncode-4 5.95ms ± 7% 5.96ms ± 6% ~ (p=0.670 n=40+34) Gzip-4 224ms ± 6% 223ms ± 5% ~ (p=0.143 n=40+40) Gunzip-4 36.5ms ± 4% 36.5ms ± 4% ~ (p=0.556 n=40+40) HTTPClientServer-4 60.7µs ± 2% 59.9µs ± 3% -1.20% (p=0.000 n=39+39) JSONEncode-4 9.03ms ± 4% 9.04ms ± 4% ~ (p=0.589 n=40+40) JSONDecode-4 49.4ms ± 4% 49.2ms ± 4% ~ (p=0.276 n=40+40) Mandelbrot200-4 3.80ms ± 4% 3.79ms ± 4% ~ (p=0.837 n=40+40) GoParse-4 3.15ms ± 5% 3.13ms ± 5% ~ (p=0.240 n=40+40) RegexpMatchEasy0_32-4 72.9ns ± 3% 72.0ns ± 8% -1.25% (p=0.003 n=40+40) RegexpMatchEasy0_1K-4 229ns ± 5% 230ns ± 4% ~ (p=0.318 n=40+40) RegexpMatchEasy1_32-4 66.9ns ± 3% 67.3ns ± 7% ~ (p=0.817 n=40+40) RegexpMatchEasy1_1K-4 371ns ± 5% 370ns ± 4% ~ (p=0.275 n=40+40) RegexpMatchMedium_32-4 106ns ± 4% 104ns ± 7% -2.28% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 32.0µs ± 2% 31.4µs ± 3% -2.08% (p=0.000 n=40+40) RegexpMatchHard_32-4 1.54µs ± 7% 1.52µs ± 3% -1.80% (p=0.007 n=39+40) RegexpMatchHard_1K-4 45.8µs ± 4% 45.5µs ± 3% ~ (p=0.707 n=40+40) Revcomp-4 401ms ± 5% 401ms ± 6% ~ (p=0.935 n=40+40) Template-4 62.4ms ± 4% 61.2ms ± 3% -1.85% (p=0.000 n=40+40) TimeParse-4 315ns ± 2% 318ns ± 3% +1.10% (p=0.002 n=40+40) TimeFormat-4 297ns ± 3% 298ns ± 3% ~ (p=0.238 n=40+40) [Geo mean] 45.8µs 45.7µs -0.22% name old speed new speed delta GobDecode-4 119MB/s ± 6% 119MB/s ± 7% ~ (p=0.684 n=39+40) GobEncode-4 129MB/s ± 7% 128MB/s ± 6% ~ (p=0.413 n=40+34) Gzip-4 86.6MB/s ± 6% 87.0MB/s ± 6% ~ (p=0.145 n=40+40) Gunzip-4 532MB/s ± 4% 532MB/s ± 4% ~ (p=0.556 n=40+40) JSONEncode-4 215MB/s ± 4% 215MB/s ± 4% ~ (p=0.583 n=40+40) JSONDecode-4 39.3MB/s ± 4% 39.5MB/s ± 4% ~ (p=0.277 n=40+40) GoParse-4 18.4MB/s ± 5% 18.5MB/s ± 5% ~ (p=0.229 n=40+40) RegexpMatchEasy0_32-4 439MB/s ± 3% 445MB/s ± 8% +1.28% (p=0.003 n=40+40) RegexpMatchEasy0_1K-4 4.46GB/s ± 4% 4.45GB/s ± 4% ~ (p=0.343 n=40+40) RegexpMatchEasy1_32-4 479MB/s ± 3% 476MB/s ± 7% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 2.76GB/s ± 5% 2.77GB/s ± 4% ~ (p=0.250 n=40+40) RegexpMatchMedium_32-4 9.36MB/s ± 4% 9.58MB/s ± 6% +2.31% (p=0.001 n=40+40) RegexpMatchMedium_1K-4 32.0MB/s ± 2% 32.7MB/s ± 3% +2.12% (p=0.000 n=40+40) RegexpMatchHard_32-4 20.7MB/s ± 7% 21.1MB/s ± 3% +1.95% (p=0.005 n=40+40) RegexpMatchHard_1K-4 22.4MB/s ± 4% 22.5MB/s ± 3% ~ (p=0.689 n=40+40) Revcomp-4 634MB/s ± 5% 634MB/s ± 6% ~ (p=0.935 n=40+40) Template-4 31.1MB/s ± 3% 31.7MB/s ± 3% +1.88% (p=0.000 n=40+40) [Geo mean] 129MB/s 130MB/s +0.62% Change-Id: I9d61ee810d900920c572cbe89e2f1626bfed12b7 Reviewed-on: https://go-review.googlesource.com/c/145209 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-29 02:34:42 -06:00
// amd64:`DECQ\s64\([A-Z]+\)`
arr[8]--
cmd/compile/internal/ssa: optimize 386's subtraction The SUBL instruction can take a memory operand, and this CL implements this optimization. The go1 benchmark shows a little improvement. name old time/op new time/op delta BinaryTree17-4 3.27s ± 2% 3.29s ± 3% ~ (p=0.322 n=37+40) Fannkuch11-4 3.49s ± 0% 3.53s ± 1% +1.21% (p=0.000 n=31+40) FmtFprintfEmpty-4 46.2ns ± 3% 46.3ns ± 2% ~ (p=0.351 n=40+28) FmtFprintfString-4 82.0ns ± 3% 81.5ns ± 2% -0.69% (p=0.002 n=40+30) FmtFprintfInt-4 94.6ns ± 3% 94.6ns ± 6% ~ (p=0.913 n=39+37) FmtFprintfIntInt-4 147ns ± 3% 150ns ± 2% +1.72% (p=0.000 n=40+25) FmtFprintfPrefixedInt-4 186ns ± 3% 186ns ± 0% -0.33% (p=0.006 n=40+25) FmtFprintfFloat-4 388ns ± 4% 388ns ± 4% ~ (p=0.162 n=40+40) FmtManyArgs-4 612ns ± 3% 616ns ± 4% ~ (p=0.223 n=40+40) GobDecode-4 7.35ms ± 5% 7.42ms ± 5% ~ (p=0.095 n=40+40) GobEncode-4 7.21ms ± 8% 7.23ms ± 4% ~ (p=0.294 n=40+40) Gzip-4 360ms ± 4% 359ms ± 4% ~ (p=0.097 n=40+40) Gunzip-4 46.1ms ± 3% 45.6ms ± 3% -1.20% (p=0.000 n=40+40) HTTPClientServer-4 64.0µs ± 2% 64.1µs ± 2% ~ (p=0.648 n=39+40) JSONEncode-4 21.9ms ± 4% 22.1ms ± 5% ~ (p=0.086 n=40+40) JSONDecode-4 67.9ms ± 4% 66.7ms ± 4% -1.63% (p=0.000 n=40+40) Mandelbrot200-4 5.19ms ± 3% 5.17ms ± 3% ~ (p=0.881 n=40+40) GoParse-4 3.34ms ± 3% 3.28ms ± 2% -1.78% (p=0.000 n=40+40) RegexpMatchEasy0_32-4 101ns ± 5% 99ns ± 3% -2.40% (p=0.000 n=40+40) RegexpMatchEasy0_1K-4 851ns ± 1% 848ns ± 3% -0.36% (p=0.004 n=33+40) RegexpMatchEasy1_32-4 109ns ± 5% 105ns ± 3% -3.53% (p=0.000 n=39+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 3% ~ (p=0.638 n=40+38) RegexpMatchMedium_32-4 131ns ± 5% 127ns ± 4% -3.36% (p=0.000 n=38+40) RegexpMatchMedium_1K-4 43.4µs ± 4% 43.2µs ± 3% -0.46% (p=0.008 n=40+40) RegexpMatchHard_32-4 2.21µs ± 4% 2.23µs ± 1% +0.77% (p=0.014 n=40+28) RegexpMatchHard_1K-4 67.6µs ± 4% 67.7µs ± 3% +0.11% (p=0.016 n=40+40) Revcomp-4 1.86s ± 3% 1.77s ± 2% -4.81% (p=0.000 n=40+40) Template-4 71.7ms ± 3% 71.6ms ± 4% ~ (p=0.200 n=40+40) TimeParse-4 436ns ± 4% 433ns ± 3% ~ (p=0.358 n=40+40) TimeFormat-4 413ns ± 4% 412ns ± 3% ~ (p=0.415 n=40+40) [Geo mean] 63.9µs 63.6µs -0.49% name old speed new speed delta GobDecode-4 105MB/s ± 5% 104MB/s ± 5% ~ (p=0.096 n=40+40) GobEncode-4 106MB/s ± 7% 106MB/s ± 3% ~ (p=0.385 n=39+40) Gzip-4 54.0MB/s ± 4% 54.0MB/s ± 4% ~ (p=0.100 n=40+40) Gunzip-4 421MB/s ± 3% 426MB/s ± 3% +1.21% (p=0.000 n=40+40) JSONEncode-4 88.5MB/s ± 5% 88.0MB/s ± 5% ~ (p=0.083 n=40+40) JSONDecode-4 28.6MB/s ± 4% 29.1MB/s ± 4% +1.65% (p=0.000 n=40+40) GoParse-4 17.3MB/s ± 3% 17.7MB/s ± 2% +1.82% (p=0.000 n=40+40) RegexpMatchEasy0_32-4 316MB/s ± 5% 323MB/s ± 4% +2.44% (p=0.000 n=40+40) RegexpMatchEasy0_1K-4 1.20GB/s ± 1% 1.21GB/s ± 3% +0.40% (p=0.004 n=33+40) RegexpMatchEasy1_32-4 291MB/s ± 7% 302MB/s ± 4% +3.82% (p=0.000 n=40+40) RegexpMatchEasy1_1K-4 993MB/s ± 4% 990MB/s ± 3% ~ (p=0.623 n=40+38) RegexpMatchMedium_32-4 7.61MB/s ± 5% 7.87MB/s ± 4% +3.36% (p=0.000 n=38+40) RegexpMatchMedium_1K-4 23.6MB/s ± 4% 23.7MB/s ± 4% +0.46% (p=0.007 n=40+40) RegexpMatchHard_32-4 14.5MB/s ± 4% 14.3MB/s ± 1% -0.79% (p=0.017 n=40+28) RegexpMatchHard_1K-4 15.1MB/s ± 4% 15.1MB/s ± 3% -0.11% (p=0.015 n=40+40) Revcomp-4 137MB/s ± 3% 144MB/s ± 3% +5.06% (p=0.000 n=40+40) Template-4 27.1MB/s ± 3% 27.1MB/s ± 4% ~ (p=0.211 n=40+40) [Geo mean] 78.9MB/s 79.7MB/s +1.01% Change-Id: I638fa4fef85833e8605919d693f9570cc3cf7334 Reviewed-on: https://go-review.googlesource.com/107275 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-04-15 03:31:39 -06:00
// 386:"SUBL\t4"
// amd64:"SUBQ\t8"
return arr[0] - arr[1]
}
func SubFromConst(a int) int {
// ppc64le: `SUBC\tR[0-9]+,\s[$]40,\sR`
// ppc64: `SUBC\tR[0-9]+,\s[$]40,\sR`
b := 40 - a
return b
}
func SubFromConstNeg(a int) int {
// ppc64le: `ADD\t[$]40,\sR[0-9]+,\sR`
// ppc64: `ADD\t[$]40,\sR[0-9]+,\sR`
c := 40 - (-a)
return c
}
func SubSubFromConst(a int) int {
// ppc64le: `ADD\t[$]20,\sR[0-9]+,\sR`
// ppc64: `ADD\t[$]20,\sR[0-9]+,\sR`
c := 40 - (20 - a)
return c
}
func AddSubFromConst(a int) int {
// ppc64le: `SUBC\tR[0-9]+,\s[$]60,\sR`
// ppc64: `SUBC\tR[0-9]+,\s[$]60,\sR`
c := 40 + (20 - a)
return c
}
func NegSubFromConst(a int) int {
// ppc64le: `ADD\t[$]-20,\sR[0-9]+,\sR`
// ppc64: `ADD\t[$]-20,\sR[0-9]+,\sR`
c := -(20 - a)
return c
}
func NegAddFromConstNeg(a int) int {
// ppc64le: `SUBC\tR[0-9]+,\s[$]40,\sR`
// ppc64: `SUBC\tR[0-9]+,\s[$]40,\sR`
c := -(-40 + a)
return c
}
cmd/compile: generic SSA rules for simplifying 2 and 3 operand integer arithmetic expressions This applies the following generic integer addition/subtraction transformations: x - (x + y) = -y (x - y) - x = -y y + (x - y) = x y + (z + (x - y) = x + z There's over 40 unique functions matching in Go. Hits 2 funcs in the runtime itself: runtime.stackfree() runtime.runqdrain() Go binary size reduced by 0.05% on Linux x86_64. StackCopy bench (perflocked Cascade Lake x86): name old time/op new time/op delta StackCopyPtr-8 87.3ms ± 1% 86.9ms ± 0% -0.45% (p=0.000 n=20+20) StackCopy-8 77.6ms ± 1% 77.0ms ± 0% -0.76% (p=0.000 n=20+20) StackCopyNoCache-8 2.28ms ± 2% 2.26ms ± 2% -0.93% (p=0.008 n=19+20) test/bench/go1 benchmarks (perflocked Cascade Lake x86): name old time/op new time/op delta BinaryTree17-8 1.88s ± 1% 1.88s ± 0% ~ (p=0.373 n=15+12) Fannkuch11-8 2.31s ± 0% 2.35s ± 0% +1.52% (p=0.000 n=15+14) FmtFprintfEmpty-8 26.6ns ± 0% 26.6ns ± 0% ~ (p=0.081 n=14+13) FmtFprintfString-8 48.6ns ± 0% 50.0ns ± 0% +2.86% (p=0.000 n=15+14) FmtFprintfInt-8 56.9ns ± 0% 54.8ns ± 0% -3.70% (p=0.000 n=15+15) FmtFprintfIntInt-8 90.4ns ± 0% 88.8ns ± 0% -1.78% (p=0.000 n=15+15) FmtFprintfPrefixedInt-8 104ns ± 0% 104ns ± 0% ~ (p=0.905 n=14+13) FmtFprintfFloat-8 148ns ± 0% 144ns ± 0% -2.19% (p=0.000 n=14+15) FmtManyArgs-8 389ns ± 0% 390ns ± 0% +0.35% (p=0.000 n=12+15) GobDecode-8 3.90ms ± 1% 3.88ms ± 0% -0.49% (p=0.000 n=15+14) GobEncode-8 2.73ms ± 0% 2.73ms ± 0% ~ (p=0.425 n=15+14) Gzip-8 169ms ± 0% 168ms ± 0% -0.52% (p=0.000 n=13+13) Gunzip-8 24.7ms ± 0% 24.8ms ± 0% +0.61% (p=0.000 n=15+15) HTTPClientServer-8 60.5µs ± 6% 60.4µs ± 7% ~ (p=0.595 n=15+15) JSONEncode-8 6.97ms ± 1% 6.93ms ± 0% -0.69% (p=0.000 n=14+14) JSONDecode-8 31.2ms ± 1% 30.8ms ± 1% -1.27% (p=0.000 n=14+14) Mandelbrot200-8 3.87ms ± 0% 3.87ms ± 0% ~ (p=0.652 n=15+14) GoParse-8 2.65ms ± 2% 2.64ms ± 1% ~ (p=0.202 n=15+15) RegexpMatchEasy0_32-8 45.1ns ± 0% 45.9ns ± 0% +1.68% (p=0.000 n=14+15) RegexpMatchEasy0_1K-8 140ns ± 0% 139ns ± 0% -0.44% (p=0.000 n=15+14) RegexpMatchEasy1_32-8 40.9ns ± 3% 40.5ns ± 0% -0.88% (p=0.000 n=15+13) RegexpMatchEasy1_1K-8 215ns ± 1% 220ns ± 1% +2.27% (p=0.000 n=15+15) RegexpMatchMedium_32-8 783ns ± 7% 738ns ± 0% ~ (p=0.361 n=15+15) RegexpMatchMedium_1K-8 24.1µs ± 6% 23.4µs ± 6% -2.94% (p=0.004 n=15+15) RegexpMatchHard_32-8 1.10µs ± 1% 1.09µs ± 1% -0.40% (p=0.006 n=15+14) RegexpMatchHard_1K-8 33.0µs ± 0% 33.0µs ± 0% ~ (p=0.535 n=12+14) Revcomp-8 354ms ± 0% 353ms ± 0% -0.23% (p=0.002 n=15+13) Template-8 42.0ms ± 1% 41.8ms ± 2% -0.37% (p=0.023 n=14+15) TimeParse-8 181ns ± 0% 180ns ± 1% -0.18% (p=0.014 n=12+13) TimeFormat-8 240ns ± 0% 242ns ± 1% +0.69% (p=0.000 n=12+15) [Geo mean] 35.2µs 35.1µs -0.43% name old speed new speed delta GobDecode-8 197MB/s ± 1% 198MB/s ± 0% +0.49% (p=0.000 n=15+14) GobEncode-8 281MB/s ± 0% 281MB/s ± 0% ~ (p=0.419 n=15+14) Gzip-8 115MB/s ± 0% 115MB/s ± 0% +0.52% (p=0.000 n=13+13) Gunzip-8 786MB/s ± 0% 781MB/s ± 0% -0.60% (p=0.000 n=15+15) JSONEncode-8 278MB/s ± 1% 280MB/s ± 0% +0.69% (p=0.000 n=14+14) JSONDecode-8 62.3MB/s ± 1% 63.1MB/s ± 1% +1.29% (p=0.000 n=14+14) GoParse-8 21.9MB/s ± 2% 22.0MB/s ± 1% ~ (p=0.205 n=15+15) RegexpMatchEasy0_32-8 709MB/s ± 0% 697MB/s ± 0% -1.65% (p=0.000 n=14+15) RegexpMatchEasy0_1K-8 7.34GB/s ± 0% 7.37GB/s ± 0% +0.43% (p=0.000 n=15+15) RegexpMatchEasy1_32-8 783MB/s ± 2% 790MB/s ± 0% +0.88% (p=0.000 n=15+13) RegexpMatchEasy1_1K-8 4.77GB/s ± 1% 4.66GB/s ± 1% -2.23% (p=0.000 n=15+15) RegexpMatchMedium_32-8 41.0MB/s ± 7% 43.3MB/s ± 0% ~ (p=0.360 n=15+15) RegexpMatchMedium_1K-8 42.5MB/s ± 6% 43.8MB/s ± 6% +3.07% (p=0.004 n=15+15) RegexpMatchHard_32-8 29.2MB/s ± 1% 29.3MB/s ± 1% +0.41% (p=0.006 n=15+14) RegexpMatchHard_1K-8 31.1MB/s ± 0% 31.1MB/s ± 0% ~ (p=0.495 n=12+14) Revcomp-8 718MB/s ± 0% 720MB/s ± 0% +0.23% (p=0.002 n=15+13) Template-8 46.3MB/s ± 1% 46.4MB/s ± 2% +0.38% (p=0.021 n=14+15) [Geo mean] 205MB/s 206MB/s +0.57% Change-Id: Ibd1afdf8b6c0b08087dcc3acd8f943637eb95ac0 Reviewed-on: https://go-review.googlesource.com/c/go/+/344930 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Trust: Josh Bleecher Snyder <josharian@gmail.com>
2021-08-25 04:36:17 -06:00
func SubSubNegSimplify(a, b int) int {
// amd64:"NEGQ"
r := (a - b) - a
return r
}
func SubAddSimplify(a, b int) int {
// amd64:-"SUBQ",-"ADDQ"
r := a + (b - a)
return r
}
func SubAddNegSimplify(a, b int) int {
// amd64:"NEGQ",-"ADDQ",-"SUBQ"
r := a - (b + a)
return r
}
func AddAddSubSimplify(a, b, c int) int {
// amd64:-"SUBQ"
r := a + (b + (c - a))
return r
}
// -------------------- //
// 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"
// ppc64:"SLD\t[$]5",-"MUL"
// ppc64le:"SLD\t[$]5",-"MUL"
a := n1 * 32
// amd64:"SHLQ\t[$]6",-"IMULQ"
// 386:"SHLL\t[$]6",-"IMULL"
// arm:"SLL\t[$]6",-"MUL"
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>
2018-09-27 00:21:14 -06:00
// arm64:`NEG\sR[0-9]+<<6,\sR[0-9]+`,-`LSL`,-`MUL`
// ppc64:"SLD\t[$]6","NEG\\sR[0-9]+,\\sR[0-9]+",-"MUL"
// ppc64le:"SLD\t[$]6","NEG\\sR[0-9]+,\\sR[0-9]+",-"MUL"
b := -64 * n2
return a, b
}
func Mul_96(n int) int {
// amd64:`SHLQ\t[$]5`,`LEAQ\t\(.*\)\(.*\*2\),`,-`IMULQ`
// 386:`SHLL\t[$]5`,`LEAL\t\(.*\)\(.*\*2\),`,-`IMULL`
// arm64:`LSL\t[$]5`,`ADD\sR[0-9]+<<1,\sR[0-9]+`,-`MUL`
// arm:`SLL\t[$]5`,`ADD\sR[0-9]+<<1,\sR[0-9]+`,-`MUL`
// s390x:`SLD\t[$]5`,`SLD\t[$]6`,-`MULLD`
return n * 96
}
func Mul_n120(n int) int {
// s390x:`SLD\t[$]3`,`SLD\t[$]7`,-`MULLD`
return n * -120
}
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>
2018-06-24 01:04:21 -06:00
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]+`
// amd64:`MULSS\s4\([A-Z]+\),\sX[0-9]+`
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>
2018-06-24 01:04:21 -06:00
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)|(LEAQ\t29)"
// 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 //
// -------------- //
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>
2018-06-24 01:04:21 -06:00
func DivMemSrc(a []float64) {
// 386/sse2:`DIVSD\s8\([A-Z]+\),\sX[0-9]+`
// amd64:`DIVSD\s8\([A-Z]+\),\sX[0-9]+`
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>
2018-06-24 01:04:21 -06:00
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"
// ppc64:"SRD"
// ppc64le:"SRD"
a := n1 / 32 // unsigned
// amd64:"SARQ\t[$]6",-"IDIVQ"
// 386:"SARL\t[$]6",-"IDIVL"
// arm:"SRA\t[$]6",-".*udiv"
// arm64:"ASR\t[$]6",-"SDIV"
// ppc64:"SRAD"
// ppc64le:"SRAD"
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[$]-1085102592571150095","MULQ",-"DIVQ"
// 386:"MOVL\t[$]-252645135","MULL",-"DIVL"
// arm64:`MOVD`,`UMULH`,-`DIV`
// arm:`MOVW`,`MUL`,-`.*udiv`
a := n1 / 17 // unsigned
// amd64:"MOVQ\t[$]-1085102592571150095","IMULQ",-"IDIVQ"
// 386:"MOVL\t[$]-252645135","IMULL",-"IDIVL"
// arm64:`SMULH`,-`DIV`
// arm:`MOVW`,`MUL`,-`.*udiv`
b := n2 / 17 // signed
return a, b
}
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>
2018-06-21 04:14:18 -06:00
func FloatDivs(a []float32) float32 {
// amd64:`DIVSS\s8\([A-Z]+\),\sX[0-9]+`
// 386/sse2:`DIVSS\s8\([A-Z]+\),\sX[0-9]+`
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>
2018-06-21 04:14:18 -06:00
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"
// ppc64:"ANDCC\t[$]31"
// ppc64le:"ANDCC\t[$]31"
a := n1 % 32 // unsigned
cmd/compile: add signed divisibility by power of 2 rules For powers of two (c=1<<k), the divisibility check x%c == 0 can be made just by checking the trailing zeroes via a mask x&(c-1) == 0 even for signed integers. This avoids division fix-ups when just divisibility check is needed. To apply this rule, we match on the fixed-up version of the division. This is neccessary because the mod and division rewrite rules are already applied during the initial opt pass. The speed up on amd64 due to elimination of unneccessary fix-up code is ~55%: name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.09ns ± 1% ~ (p=0.730 n=5+5) DivisiblePow2constI64-4 1.78ns ± 1% 0.81ns ± 1% -54.66% (p=0.008 n=5+5) DivconstU64-4 2.08ns ± 0% 2.08ns ± 0% ~ (p=0.683 n=5+5) DivconstI32-4 1.53ns ± 0% 1.53ns ± 1% ~ (p=0.968 n=4+5) DivisiblePow2constI32-4 1.79ns ± 1% 0.81ns ± 1% -54.97% (p=0.008 n=5+5) DivconstU32-4 1.78ns ± 1% 1.80ns ± 2% ~ (p=0.206 n=5+5) DivconstI16-4 1.54ns ± 2% 1.54ns ± 0% ~ (p=0.238 n=5+4) DivisiblePow2constI16-4 1.78ns ± 0% 0.81ns ± 1% -54.72% (p=0.000 n=4+5) DivconstU16-4 1.00ns ± 5% 1.01ns ± 1% ~ (p=0.119 n=5+5) DivconstI8-4 1.54ns ± 0% 1.54ns ± 2% ~ (p=0.571 n=4+5) DivisiblePow2constI8-4 1.78ns ± 0% 0.82ns ± 8% -53.71% (p=0.008 n=5+5) DivconstU8-4 0.93ns ± 1% 0.93ns ± 1% ~ (p=0.643 n=5+5) A follow-up CL will address the general case of x%c == 0 for signed integers. Updates #15806 Change-Id: Iabadbbe369b6e0998c8ce85d038ebc236142e42a Reviewed-on: https://go-review.googlesource.com/c/go/+/173557 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-23 22:04:38 -06:00
// 386:"SHRL",-"IDIVL"
// amd64:"SHRQ",-"IDIVQ"
// arm:"SRA",-".*udiv"
// arm64:"ASR",-"REM"
// ppc64:"SRAD"
// ppc64le:"SRAD"
b := n2 % 64 // signed
return a, b
}
cmd/compile: add signed divisibility by power of 2 rules For powers of two (c=1<<k), the divisibility check x%c == 0 can be made just by checking the trailing zeroes via a mask x&(c-1) == 0 even for signed integers. This avoids division fix-ups when just divisibility check is needed. To apply this rule, we match on the fixed-up version of the division. This is neccessary because the mod and division rewrite rules are already applied during the initial opt pass. The speed up on amd64 due to elimination of unneccessary fix-up code is ~55%: name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.09ns ± 1% ~ (p=0.730 n=5+5) DivisiblePow2constI64-4 1.78ns ± 1% 0.81ns ± 1% -54.66% (p=0.008 n=5+5) DivconstU64-4 2.08ns ± 0% 2.08ns ± 0% ~ (p=0.683 n=5+5) DivconstI32-4 1.53ns ± 0% 1.53ns ± 1% ~ (p=0.968 n=4+5) DivisiblePow2constI32-4 1.79ns ± 1% 0.81ns ± 1% -54.97% (p=0.008 n=5+5) DivconstU32-4 1.78ns ± 1% 1.80ns ± 2% ~ (p=0.206 n=5+5) DivconstI16-4 1.54ns ± 2% 1.54ns ± 0% ~ (p=0.238 n=5+4) DivisiblePow2constI16-4 1.78ns ± 0% 0.81ns ± 1% -54.72% (p=0.000 n=4+5) DivconstU16-4 1.00ns ± 5% 1.01ns ± 1% ~ (p=0.119 n=5+5) DivconstI8-4 1.54ns ± 0% 1.54ns ± 2% ~ (p=0.571 n=4+5) DivisiblePow2constI8-4 1.78ns ± 0% 0.82ns ± 8% -53.71% (p=0.008 n=5+5) DivconstU8-4 0.93ns ± 1% 0.93ns ± 1% ~ (p=0.643 n=5+5) A follow-up CL will address the general case of x%c == 0 for signed integers. Updates #15806 Change-Id: Iabadbbe369b6e0998c8ce85d038ebc236142e42a Reviewed-on: https://go-review.googlesource.com/c/go/+/173557 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-23 22:04:38 -06:00
// Check that signed divisibility checks get converted to AND on low bits
func Pow2DivisibleSigned(n1, n2 int) (bool, bool) {
cmd/compile: add signed divisibility by power of 2 rules For powers of two (c=1<<k), the divisibility check x%c == 0 can be made just by checking the trailing zeroes via a mask x&(c-1) == 0 even for signed integers. This avoids division fix-ups when just divisibility check is needed. To apply this rule, we match on the fixed-up version of the division. This is neccessary because the mod and division rewrite rules are already applied during the initial opt pass. The speed up on amd64 due to elimination of unneccessary fix-up code is ~55%: name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.09ns ± 1% ~ (p=0.730 n=5+5) DivisiblePow2constI64-4 1.78ns ± 1% 0.81ns ± 1% -54.66% (p=0.008 n=5+5) DivconstU64-4 2.08ns ± 0% 2.08ns ± 0% ~ (p=0.683 n=5+5) DivconstI32-4 1.53ns ± 0% 1.53ns ± 1% ~ (p=0.968 n=4+5) DivisiblePow2constI32-4 1.79ns ± 1% 0.81ns ± 1% -54.97% (p=0.008 n=5+5) DivconstU32-4 1.78ns ± 1% 1.80ns ± 2% ~ (p=0.206 n=5+5) DivconstI16-4 1.54ns ± 2% 1.54ns ± 0% ~ (p=0.238 n=5+4) DivisiblePow2constI16-4 1.78ns ± 0% 0.81ns ± 1% -54.72% (p=0.000 n=4+5) DivconstU16-4 1.00ns ± 5% 1.01ns ± 1% ~ (p=0.119 n=5+5) DivconstI8-4 1.54ns ± 0% 1.54ns ± 2% ~ (p=0.571 n=4+5) DivisiblePow2constI8-4 1.78ns ± 0% 0.82ns ± 8% -53.71% (p=0.008 n=5+5) DivconstU8-4 0.93ns ± 1% 0.93ns ± 1% ~ (p=0.643 n=5+5) A follow-up CL will address the general case of x%c == 0 for signed integers. Updates #15806 Change-Id: Iabadbbe369b6e0998c8ce85d038ebc236142e42a Reviewed-on: https://go-review.googlesource.com/c/go/+/173557 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-23 22:04:38 -06:00
// 386:"TESTL\t[$]63",-"DIVL",-"SHRL"
// amd64:"TESTQ\t[$]63",-"DIVQ",-"SHRQ"
// arm:"AND\t[$]63",-".*udiv",-"SRA"
// arm64:"AND\t[$]63",-"UDIV",-"ASR"
// ppc64:"ANDCC\t[$]63",-"SRAD"
// ppc64le:"ANDCC\t[$]63",-"SRAD"
a := n1%64 == 0 // signed divisible
// 386:"TESTL\t[$]63",-"DIVL",-"SHRL"
// amd64:"TESTQ\t[$]63",-"DIVQ",-"SHRQ"
// arm:"AND\t[$]63",-".*udiv",-"SRA"
// arm64:"AND\t[$]63",-"UDIV",-"ASR"
// ppc64:"ANDCC\t[$]63",-"SRAD"
// ppc64le:"ANDCC\t[$]63",-"SRAD"
b := n2%64 != 0 // signed indivisible
return a, b
cmd/compile: add signed divisibility by power of 2 rules For powers of two (c=1<<k), the divisibility check x%c == 0 can be made just by checking the trailing zeroes via a mask x&(c-1) == 0 even for signed integers. This avoids division fix-ups when just divisibility check is needed. To apply this rule, we match on the fixed-up version of the division. This is neccessary because the mod and division rewrite rules are already applied during the initial opt pass. The speed up on amd64 due to elimination of unneccessary fix-up code is ~55%: name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.09ns ± 1% ~ (p=0.730 n=5+5) DivisiblePow2constI64-4 1.78ns ± 1% 0.81ns ± 1% -54.66% (p=0.008 n=5+5) DivconstU64-4 2.08ns ± 0% 2.08ns ± 0% ~ (p=0.683 n=5+5) DivconstI32-4 1.53ns ± 0% 1.53ns ± 1% ~ (p=0.968 n=4+5) DivisiblePow2constI32-4 1.79ns ± 1% 0.81ns ± 1% -54.97% (p=0.008 n=5+5) DivconstU32-4 1.78ns ± 1% 1.80ns ± 2% ~ (p=0.206 n=5+5) DivconstI16-4 1.54ns ± 2% 1.54ns ± 0% ~ (p=0.238 n=5+4) DivisiblePow2constI16-4 1.78ns ± 0% 0.81ns ± 1% -54.72% (p=0.000 n=4+5) DivconstU16-4 1.00ns ± 5% 1.01ns ± 1% ~ (p=0.119 n=5+5) DivconstI8-4 1.54ns ± 0% 1.54ns ± 2% ~ (p=0.571 n=4+5) DivisiblePow2constI8-4 1.78ns ± 0% 0.82ns ± 8% -53.71% (p=0.008 n=5+5) DivconstU8-4 0.93ns ± 1% 0.93ns ± 1% ~ (p=0.643 n=5+5) A follow-up CL will address the general case of x%c == 0 for signed integers. Updates #15806 Change-Id: Iabadbbe369b6e0998c8ce85d038ebc236142e42a Reviewed-on: https://go-review.googlesource.com/c/go/+/173557 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-23 22:04:38 -06:00
}
// Check that constant modulo divs get turned into MULs
func ConstMods(n1 uint, n2 int) (uint, int) {
// amd64:"MOVQ\t[$]-1085102592571150095","MULQ",-"DIVQ"
// 386:"MOVL\t[$]-252645135","MULL",-"DIVL"
// arm64:`MOVD`,`UMULH`,-`DIV`
// arm:`MOVW`,`MUL`,-`.*udiv`
a := n1 % 17 // unsigned
// amd64:"MOVQ\t[$]-1085102592571150095","IMULQ",-"IDIVQ"
// 386:"MOVL\t[$]-252645135","IMULL",-"IDIVL"
// arm64:`SMULH`,-`DIV`
// arm:`MOVW`,`MUL`,-`.*udiv`
b := n2 % 17 // signed
return a, b
}
cmd/compile: add unsigned divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also available. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. Additional rules to lower the generic RotateLeft* ops were also applied. On amd64, the divisibility check is 25-50% faster. name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.08ns ± 1% ~ (p=0.881 n=5+5) DivisibleconstI64-4 2.67ns ± 0% 2.67ns ± 1% ~ (p=1.000 n=5+5) DivisibleWDivconstI64-4 2.67ns ± 0% 2.67ns ± 0% ~ (p=0.683 n=5+5) DivconstU64-4 2.08ns ± 1% 2.08ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstU64-4 2.77ns ± 1% 1.55ns ± 2% -43.90% (p=0.008 n=5+5) DivisibleWDivconstU64-4 2.99ns ± 1% 2.99ns ± 1% ~ (p=1.000 n=5+5) DivconstI32-4 1.53ns ± 2% 1.53ns ± 0% ~ (p=1.000 n=5+5) DivisibleconstI32-4 2.23ns ± 0% 2.25ns ± 3% ~ (p=0.167 n=5+5) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.429 n=5+5) DivconstU32-4 1.78ns ± 0% 1.78ns ± 1% ~ (p=1.000 n=4+5) DivisibleconstU32-4 2.52ns ± 2% 1.26ns ± 0% -49.96% (p=0.000 n=5+4) DivisibleWDivconstU32-4 2.63ns ± 0% 2.85ns ±10% +8.29% (p=0.016 n=4+5) DivconstI16-4 1.54ns ± 0% 1.54ns ± 0% ~ (p=0.333 n=4+5) DivisibleconstI16-4 2.10ns ± 0% 2.10ns ± 1% ~ (p=0.571 n=4+5) DivisibleWDivconstI16-4 2.22ns ± 0% 2.23ns ± 1% ~ (p=0.556 n=4+5) DivconstU16-4 1.09ns ± 0% 1.01ns ± 1% -7.74% (p=0.000 n=4+5) DivisibleconstU16-4 1.83ns ± 0% 1.26ns ± 0% -31.52% (p=0.008 n=5+5) DivisibleWDivconstU16-4 1.88ns ± 0% 1.89ns ± 1% ~ (p=0.365 n=5+5) DivconstI8-4 1.54ns ± 1% 1.54ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstI8-4 2.10ns ± 0% 2.11ns ± 0% ~ (p=0.238 n=5+4) DivisibleWDivconstI8-4 2.22ns ± 0% 2.23ns ± 2% ~ (p=0.762 n=5+5) DivconstU8-4 0.92ns ± 1% 0.94ns ± 1% +2.65% (p=0.008 n=5+5) DivisibleconstU8-4 1.66ns ± 0% 1.26ns ± 1% -24.28% (p=0.008 n=5+5) DivisibleWDivconstU8-4 1.79ns ± 0% 1.80ns ± 1% ~ (p=0.079 n=4+5) A follow-up change will address the signed division case. Updates #30282 Change-Id: I7e995f167179aa5c76bb10fbcbeb49c520943403 Reviewed-on: https://go-review.googlesource.com/c/go/+/168037 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-03-09 21:58:16 -07:00
// Check that divisibility checks x%c==0 are converted to MULs and rotates
cmd/compile: add signed divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication, and add and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also needed. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. On amd64, the divisibility check is 30-45% faster. name old time/op new time/op delta` DivisiblePow2constI64-4 0.83ns ± 1% 0.82ns ± 0% ~ (p=0.079 n=5+4) DivisibleconstI64-4 2.68ns ± 1% 1.87ns ± 0% -30.33% (p=0.000 n=5+4) DivisibleWDivconstI64-4 2.69ns ± 1% 2.71ns ± 3% ~ (p=1.000 n=5+5) DivisiblePow2constI32-4 1.15ns ± 1% 1.15ns ± 0% ~ (p=0.238 n=5+4) DivisibleconstI32-4 2.24ns ± 1% 1.20ns ± 0% -46.48% (p=0.016 n=5+4) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.683 n=5+5) DivisiblePow2constI16-4 0.81ns ± 1% 0.82ns ± 1% ~ (p=0.135 n=5+5) DivisibleconstI16-4 2.11ns ± 2% 1.20ns ± 1% -42.99% (p=0.008 n=5+5) DivisibleWDivconstI16-4 2.23ns ± 0% 2.27ns ± 2% +1.79% (p=0.029 n=4+4) DivisiblePow2constI8-4 0.81ns ± 1% 0.81ns ± 1% ~ (p=0.286 n=5+5) DivisibleconstI8-4 2.13ns ± 3% 1.19ns ± 1% -43.84% (p=0.008 n=5+5) DivisibleWDivconstI8-4 2.23ns ± 1% 2.25ns ± 1% ~ (p=0.183 n=5+5) Fixes #30282 Fixes #15806 Change-Id: Id20d78263a4fdfe0509229ae4dfa2fede83fc1d0 Reviewed-on: https://go-review.googlesource.com/c/go/+/173998 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-05 14:05:07 -06:00
func Divisible(n1 uint, n2 int) (bool, bool, bool, bool) {
cmd/compile: add unsigned divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also available. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. Additional rules to lower the generic RotateLeft* ops were also applied. On amd64, the divisibility check is 25-50% faster. name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.08ns ± 1% ~ (p=0.881 n=5+5) DivisibleconstI64-4 2.67ns ± 0% 2.67ns ± 1% ~ (p=1.000 n=5+5) DivisibleWDivconstI64-4 2.67ns ± 0% 2.67ns ± 0% ~ (p=0.683 n=5+5) DivconstU64-4 2.08ns ± 1% 2.08ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstU64-4 2.77ns ± 1% 1.55ns ± 2% -43.90% (p=0.008 n=5+5) DivisibleWDivconstU64-4 2.99ns ± 1% 2.99ns ± 1% ~ (p=1.000 n=5+5) DivconstI32-4 1.53ns ± 2% 1.53ns ± 0% ~ (p=1.000 n=5+5) DivisibleconstI32-4 2.23ns ± 0% 2.25ns ± 3% ~ (p=0.167 n=5+5) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.429 n=5+5) DivconstU32-4 1.78ns ± 0% 1.78ns ± 1% ~ (p=1.000 n=4+5) DivisibleconstU32-4 2.52ns ± 2% 1.26ns ± 0% -49.96% (p=0.000 n=5+4) DivisibleWDivconstU32-4 2.63ns ± 0% 2.85ns ±10% +8.29% (p=0.016 n=4+5) DivconstI16-4 1.54ns ± 0% 1.54ns ± 0% ~ (p=0.333 n=4+5) DivisibleconstI16-4 2.10ns ± 0% 2.10ns ± 1% ~ (p=0.571 n=4+5) DivisibleWDivconstI16-4 2.22ns ± 0% 2.23ns ± 1% ~ (p=0.556 n=4+5) DivconstU16-4 1.09ns ± 0% 1.01ns ± 1% -7.74% (p=0.000 n=4+5) DivisibleconstU16-4 1.83ns ± 0% 1.26ns ± 0% -31.52% (p=0.008 n=5+5) DivisibleWDivconstU16-4 1.88ns ± 0% 1.89ns ± 1% ~ (p=0.365 n=5+5) DivconstI8-4 1.54ns ± 1% 1.54ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstI8-4 2.10ns ± 0% 2.11ns ± 0% ~ (p=0.238 n=5+4) DivisibleWDivconstI8-4 2.22ns ± 0% 2.23ns ± 2% ~ (p=0.762 n=5+5) DivconstU8-4 0.92ns ± 1% 0.94ns ± 1% +2.65% (p=0.008 n=5+5) DivisibleconstU8-4 1.66ns ± 0% 1.26ns ± 1% -24.28% (p=0.008 n=5+5) DivisibleWDivconstU8-4 1.79ns ± 0% 1.80ns ± 1% ~ (p=0.079 n=4+5) A follow-up change will address the signed division case. Updates #30282 Change-Id: I7e995f167179aa5c76bb10fbcbeb49c520943403 Reviewed-on: https://go-review.googlesource.com/c/go/+/168037 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-03-09 21:58:16 -07:00
// amd64:"MOVQ\t[$]-6148914691236517205","IMULQ","ROLQ\t[$]63",-"DIVQ"
// 386:"IMUL3L\t[$]-1431655765","ROLL\t[$]31",-"DIVQ"
// arm64:"MOVD\t[$]-6148914691236517205","MUL","ROR",-"DIV"
// arm:"MUL","CMP\t[$]715827882",-".*udiv"
// ppc64:"MULLD","ROTL\t[$]63"
// ppc64le:"MULLD","ROTL\t[$]63"
cmd/compile: add signed divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication, and add and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also needed. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. On amd64, the divisibility check is 30-45% faster. name old time/op new time/op delta` DivisiblePow2constI64-4 0.83ns ± 1% 0.82ns ± 0% ~ (p=0.079 n=5+4) DivisibleconstI64-4 2.68ns ± 1% 1.87ns ± 0% -30.33% (p=0.000 n=5+4) DivisibleWDivconstI64-4 2.69ns ± 1% 2.71ns ± 3% ~ (p=1.000 n=5+5) DivisiblePow2constI32-4 1.15ns ± 1% 1.15ns ± 0% ~ (p=0.238 n=5+4) DivisibleconstI32-4 2.24ns ± 1% 1.20ns ± 0% -46.48% (p=0.016 n=5+4) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.683 n=5+5) DivisiblePow2constI16-4 0.81ns ± 1% 0.82ns ± 1% ~ (p=0.135 n=5+5) DivisibleconstI16-4 2.11ns ± 2% 1.20ns ± 1% -42.99% (p=0.008 n=5+5) DivisibleWDivconstI16-4 2.23ns ± 0% 2.27ns ± 2% +1.79% (p=0.029 n=4+4) DivisiblePow2constI8-4 0.81ns ± 1% 0.81ns ± 1% ~ (p=0.286 n=5+5) DivisibleconstI8-4 2.13ns ± 3% 1.19ns ± 1% -43.84% (p=0.008 n=5+5) DivisibleWDivconstI8-4 2.23ns ± 1% 2.25ns ± 1% ~ (p=0.183 n=5+5) Fixes #30282 Fixes #15806 Change-Id: Id20d78263a4fdfe0509229ae4dfa2fede83fc1d0 Reviewed-on: https://go-review.googlesource.com/c/go/+/173998 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-05 14:05:07 -06:00
evenU := n1%6 == 0
cmd/compile: add unsigned divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also available. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. Additional rules to lower the generic RotateLeft* ops were also applied. On amd64, the divisibility check is 25-50% faster. name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.08ns ± 1% ~ (p=0.881 n=5+5) DivisibleconstI64-4 2.67ns ± 0% 2.67ns ± 1% ~ (p=1.000 n=5+5) DivisibleWDivconstI64-4 2.67ns ± 0% 2.67ns ± 0% ~ (p=0.683 n=5+5) DivconstU64-4 2.08ns ± 1% 2.08ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstU64-4 2.77ns ± 1% 1.55ns ± 2% -43.90% (p=0.008 n=5+5) DivisibleWDivconstU64-4 2.99ns ± 1% 2.99ns ± 1% ~ (p=1.000 n=5+5) DivconstI32-4 1.53ns ± 2% 1.53ns ± 0% ~ (p=1.000 n=5+5) DivisibleconstI32-4 2.23ns ± 0% 2.25ns ± 3% ~ (p=0.167 n=5+5) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.429 n=5+5) DivconstU32-4 1.78ns ± 0% 1.78ns ± 1% ~ (p=1.000 n=4+5) DivisibleconstU32-4 2.52ns ± 2% 1.26ns ± 0% -49.96% (p=0.000 n=5+4) DivisibleWDivconstU32-4 2.63ns ± 0% 2.85ns ±10% +8.29% (p=0.016 n=4+5) DivconstI16-4 1.54ns ± 0% 1.54ns ± 0% ~ (p=0.333 n=4+5) DivisibleconstI16-4 2.10ns ± 0% 2.10ns ± 1% ~ (p=0.571 n=4+5) DivisibleWDivconstI16-4 2.22ns ± 0% 2.23ns ± 1% ~ (p=0.556 n=4+5) DivconstU16-4 1.09ns ± 0% 1.01ns ± 1% -7.74% (p=0.000 n=4+5) DivisibleconstU16-4 1.83ns ± 0% 1.26ns ± 0% -31.52% (p=0.008 n=5+5) DivisibleWDivconstU16-4 1.88ns ± 0% 1.89ns ± 1% ~ (p=0.365 n=5+5) DivconstI8-4 1.54ns ± 1% 1.54ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstI8-4 2.10ns ± 0% 2.11ns ± 0% ~ (p=0.238 n=5+4) DivisibleWDivconstI8-4 2.22ns ± 0% 2.23ns ± 2% ~ (p=0.762 n=5+5) DivconstU8-4 0.92ns ± 1% 0.94ns ± 1% +2.65% (p=0.008 n=5+5) DivisibleconstU8-4 1.66ns ± 0% 1.26ns ± 1% -24.28% (p=0.008 n=5+5) DivisibleWDivconstU8-4 1.79ns ± 0% 1.80ns ± 1% ~ (p=0.079 n=4+5) A follow-up change will address the signed division case. Updates #30282 Change-Id: I7e995f167179aa5c76bb10fbcbeb49c520943403 Reviewed-on: https://go-review.googlesource.com/c/go/+/168037 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-03-09 21:58:16 -07:00
// amd64:"MOVQ\t[$]-8737931403336103397","IMULQ",-"ROLQ",-"DIVQ"
// 386:"IMUL3L\t[$]678152731",-"ROLL",-"DIVQ"
// arm64:"MOVD\t[$]-8737931403336103397","MUL",-"ROR",-"DIV"
// arm:"MUL","CMP\t[$]226050910",-".*udiv"
// ppc64:"MULLD",-"ROTL"
// ppc64le:"MULLD",-"ROTL"
cmd/compile: add signed divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication, and add and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also needed. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. On amd64, the divisibility check is 30-45% faster. name old time/op new time/op delta` DivisiblePow2constI64-4 0.83ns ± 1% 0.82ns ± 0% ~ (p=0.079 n=5+4) DivisibleconstI64-4 2.68ns ± 1% 1.87ns ± 0% -30.33% (p=0.000 n=5+4) DivisibleWDivconstI64-4 2.69ns ± 1% 2.71ns ± 3% ~ (p=1.000 n=5+5) DivisiblePow2constI32-4 1.15ns ± 1% 1.15ns ± 0% ~ (p=0.238 n=5+4) DivisibleconstI32-4 2.24ns ± 1% 1.20ns ± 0% -46.48% (p=0.016 n=5+4) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.683 n=5+5) DivisiblePow2constI16-4 0.81ns ± 1% 0.82ns ± 1% ~ (p=0.135 n=5+5) DivisibleconstI16-4 2.11ns ± 2% 1.20ns ± 1% -42.99% (p=0.008 n=5+5) DivisibleWDivconstI16-4 2.23ns ± 0% 2.27ns ± 2% +1.79% (p=0.029 n=4+4) DivisiblePow2constI8-4 0.81ns ± 1% 0.81ns ± 1% ~ (p=0.286 n=5+5) DivisibleconstI8-4 2.13ns ± 3% 1.19ns ± 1% -43.84% (p=0.008 n=5+5) DivisibleWDivconstI8-4 2.23ns ± 1% 2.25ns ± 1% ~ (p=0.183 n=5+5) Fixes #30282 Fixes #15806 Change-Id: Id20d78263a4fdfe0509229ae4dfa2fede83fc1d0 Reviewed-on: https://go-review.googlesource.com/c/go/+/173998 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-05 14:05:07 -06:00
oddU := n1%19 == 0
// amd64:"IMULQ","ADD","ROLQ\t[$]63",-"DIVQ"
// 386:"IMUL3L\t[$]-1431655765","ADDL\t[$]715827882","ROLL\t[$]31",-"DIVQ"
// arm64:"MUL","ADD\t[$]3074457345618258602","ROR",-"DIV"
// arm:"MUL","ADD\t[$]715827882",-".*udiv"
// ppc64/power8:"MULLD","ADD","ROTL\t[$]63"
// ppc64le/power8:"MULLD","ADD","ROTL\t[$]63"
// ppc64/power9:"MADDLD","ROTL\t[$]63"
// ppc64le/power9:"MADDLD","ROTL\t[$]63"
cmd/compile: add signed divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication, and add and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also needed. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. On amd64, the divisibility check is 30-45% faster. name old time/op new time/op delta` DivisiblePow2constI64-4 0.83ns ± 1% 0.82ns ± 0% ~ (p=0.079 n=5+4) DivisibleconstI64-4 2.68ns ± 1% 1.87ns ± 0% -30.33% (p=0.000 n=5+4) DivisibleWDivconstI64-4 2.69ns ± 1% 2.71ns ± 3% ~ (p=1.000 n=5+5) DivisiblePow2constI32-4 1.15ns ± 1% 1.15ns ± 0% ~ (p=0.238 n=5+4) DivisibleconstI32-4 2.24ns ± 1% 1.20ns ± 0% -46.48% (p=0.016 n=5+4) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.683 n=5+5) DivisiblePow2constI16-4 0.81ns ± 1% 0.82ns ± 1% ~ (p=0.135 n=5+5) DivisibleconstI16-4 2.11ns ± 2% 1.20ns ± 1% -42.99% (p=0.008 n=5+5) DivisibleWDivconstI16-4 2.23ns ± 0% 2.27ns ± 2% +1.79% (p=0.029 n=4+4) DivisiblePow2constI8-4 0.81ns ± 1% 0.81ns ± 1% ~ (p=0.286 n=5+5) DivisibleconstI8-4 2.13ns ± 3% 1.19ns ± 1% -43.84% (p=0.008 n=5+5) DivisibleWDivconstI8-4 2.23ns ± 1% 2.25ns ± 1% ~ (p=0.183 n=5+5) Fixes #30282 Fixes #15806 Change-Id: Id20d78263a4fdfe0509229ae4dfa2fede83fc1d0 Reviewed-on: https://go-review.googlesource.com/c/go/+/173998 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-05 14:05:07 -06:00
evenS := n2%6 == 0
// amd64:"IMULQ","ADD",-"ROLQ",-"DIVQ"
// 386:"IMUL3L\t[$]678152731","ADDL\t[$]113025455",-"ROLL",-"DIVQ"
// arm64:"MUL","ADD\t[$]485440633518672410",-"ROR",-"DIV"
// arm:"MUL","ADD\t[$]113025455",-".*udiv"
// ppc64/power8:"MULLD","ADD",-"ROTL"
// ppc64/power9:"MADDLD",-"ROTL"
// ppc64le/power8:"MULLD","ADD",-"ROTL"
// ppc64le/power9:"MADDLD",-"ROTL"
cmd/compile: add signed divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication, and add and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also needed. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. On amd64, the divisibility check is 30-45% faster. name old time/op new time/op delta` DivisiblePow2constI64-4 0.83ns ± 1% 0.82ns ± 0% ~ (p=0.079 n=5+4) DivisibleconstI64-4 2.68ns ± 1% 1.87ns ± 0% -30.33% (p=0.000 n=5+4) DivisibleWDivconstI64-4 2.69ns ± 1% 2.71ns ± 3% ~ (p=1.000 n=5+5) DivisiblePow2constI32-4 1.15ns ± 1% 1.15ns ± 0% ~ (p=0.238 n=5+4) DivisibleconstI32-4 2.24ns ± 1% 1.20ns ± 0% -46.48% (p=0.016 n=5+4) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.683 n=5+5) DivisiblePow2constI16-4 0.81ns ± 1% 0.82ns ± 1% ~ (p=0.135 n=5+5) DivisibleconstI16-4 2.11ns ± 2% 1.20ns ± 1% -42.99% (p=0.008 n=5+5) DivisibleWDivconstI16-4 2.23ns ± 0% 2.27ns ± 2% +1.79% (p=0.029 n=4+4) DivisiblePow2constI8-4 0.81ns ± 1% 0.81ns ± 1% ~ (p=0.286 n=5+5) DivisibleconstI8-4 2.13ns ± 3% 1.19ns ± 1% -43.84% (p=0.008 n=5+5) DivisibleWDivconstI8-4 2.23ns ± 1% 2.25ns ± 1% ~ (p=0.183 n=5+5) Fixes #30282 Fixes #15806 Change-Id: Id20d78263a4fdfe0509229ae4dfa2fede83fc1d0 Reviewed-on: https://go-review.googlesource.com/c/go/+/173998 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-04-05 14:05:07 -06:00
oddS := n2%19 == 0
return evenU, oddU, evenS, oddS
cmd/compile: add unsigned divisibility rules "Division by invariant integers using multiplication" paper by Granlund and Montgomery contains a method for directly computing divisibility (x%c == 0 for c constant) by means of the modular inverse. The method is further elaborated in "Hacker's Delight" by Warren Section 10-17 This general rule can compute divisibilty by one multiplication and a compare for odd divisors and an additional rotate for even divisors. To apply the divisibility rule, we must take into account the rules to rewrite x%c = x-((x/c)*c) and (x/c) for c constant on the first optimization pass "opt". This complicates the matching as we want to match only in the cases where the result of (x/c) is not also available. So, we must match on the expanded form of (x/c) in the expression x == c*(x/c) in the "late opt" pass after common subexpresion elimination. Note, that if there is an intermediate opt pass introduced in the future we could simplify these rules by delaying the magic division rewrite to "late opt" and matching directly on (x/c) in the intermediate opt pass. Additional rules to lower the generic RotateLeft* ops were also applied. On amd64, the divisibility check is 25-50% faster. name old time/op new time/op delta DivconstI64-4 2.08ns ± 0% 2.08ns ± 1% ~ (p=0.881 n=5+5) DivisibleconstI64-4 2.67ns ± 0% 2.67ns ± 1% ~ (p=1.000 n=5+5) DivisibleWDivconstI64-4 2.67ns ± 0% 2.67ns ± 0% ~ (p=0.683 n=5+5) DivconstU64-4 2.08ns ± 1% 2.08ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstU64-4 2.77ns ± 1% 1.55ns ± 2% -43.90% (p=0.008 n=5+5) DivisibleWDivconstU64-4 2.99ns ± 1% 2.99ns ± 1% ~ (p=1.000 n=5+5) DivconstI32-4 1.53ns ± 2% 1.53ns ± 0% ~ (p=1.000 n=5+5) DivisibleconstI32-4 2.23ns ± 0% 2.25ns ± 3% ~ (p=0.167 n=5+5) DivisibleWDivconstI32-4 2.27ns ± 1% 2.27ns ± 1% ~ (p=0.429 n=5+5) DivconstU32-4 1.78ns ± 0% 1.78ns ± 1% ~ (p=1.000 n=4+5) DivisibleconstU32-4 2.52ns ± 2% 1.26ns ± 0% -49.96% (p=0.000 n=5+4) DivisibleWDivconstU32-4 2.63ns ± 0% 2.85ns ±10% +8.29% (p=0.016 n=4+5) DivconstI16-4 1.54ns ± 0% 1.54ns ± 0% ~ (p=0.333 n=4+5) DivisibleconstI16-4 2.10ns ± 0% 2.10ns ± 1% ~ (p=0.571 n=4+5) DivisibleWDivconstI16-4 2.22ns ± 0% 2.23ns ± 1% ~ (p=0.556 n=4+5) DivconstU16-4 1.09ns ± 0% 1.01ns ± 1% -7.74% (p=0.000 n=4+5) DivisibleconstU16-4 1.83ns ± 0% 1.26ns ± 0% -31.52% (p=0.008 n=5+5) DivisibleWDivconstU16-4 1.88ns ± 0% 1.89ns ± 1% ~ (p=0.365 n=5+5) DivconstI8-4 1.54ns ± 1% 1.54ns ± 1% ~ (p=1.000 n=5+5) DivisibleconstI8-4 2.10ns ± 0% 2.11ns ± 0% ~ (p=0.238 n=5+4) DivisibleWDivconstI8-4 2.22ns ± 0% 2.23ns ± 2% ~ (p=0.762 n=5+5) DivconstU8-4 0.92ns ± 1% 0.94ns ± 1% +2.65% (p=0.008 n=5+5) DivisibleconstU8-4 1.66ns ± 0% 1.26ns ± 1% -24.28% (p=0.008 n=5+5) DivisibleWDivconstU8-4 1.79ns ± 0% 1.80ns ± 1% ~ (p=0.079 n=4+5) A follow-up change will address the signed division case. Updates #30282 Change-Id: I7e995f167179aa5c76bb10fbcbeb49c520943403 Reviewed-on: https://go-review.googlesource.com/c/go/+/168037 Run-TryBot: Brian Kessler <brian.m.kessler@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2019-03-09 21:58:16 -07:00
}
// Check that fix-up code is not generated for divisions where it has been proven that
// that the divisor is not -1 or that the dividend is > MinIntNN.
func NoFix64A(divr int64) (int64, int64) {
var d int64 = 42
var e int64 = 84
if divr > 5 {
d /= divr // amd64:-"JMP"
e %= divr // amd64:-"JMP"
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
// The following statement is to avoid conflict between the above check
// and the normal JMP generated at the end of the block.
d += e
}
return d, e
}
func NoFix64B(divd int64) (int64, int64) {
var d int64
var e int64
var divr int64 = -1
if divd > -9223372036854775808 {
d = divd / divr // amd64:-"JMP"
e = divd % divr // amd64:-"JMP"
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
d += e
}
return d, e
}
func NoFix32A(divr int32) (int32, int32) {
var d int32 = 42
var e int32 = 84
if divr > 5 {
// amd64:-"JMP"
// 386:-"JMP"
d /= divr
// amd64:-"JMP"
// 386:-"JMP"
e %= divr
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
d += e
}
return d, e
}
func NoFix32B(divd int32) (int32, int32) {
var d int32
var e int32
var divr int32 = -1
if divd > -2147483648 {
// amd64:-"JMP"
// 386:-"JMP"
d = divd / divr
// amd64:-"JMP"
// 386:-"JMP"
e = divd % divr
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
d += e
}
return d, e
}
func NoFix16A(divr int16) (int16, int16) {
var d int16 = 42
var e int16 = 84
if divr > 5 {
// amd64:-"JMP"
// 386:-"JMP"
d /= divr
// amd64:-"JMP"
// 386:-"JMP"
e %= divr
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
d += e
}
return d, e
}
func NoFix16B(divd int16) (int16, int16) {
var d int16
var e int16
var divr int16 = -1
if divd > -32768 {
// amd64:-"JMP"
// 386:-"JMP"
d = divd / divr
// amd64:-"JMP"
// 386:-"JMP"
e = divd % divr
cmd/compile: use depth first topological sort algorithm for layout The current layout algorithm tries to put consecutive blocks together, so the priority of the successor block is higher than the priority of the zero indegree block. This algorithm is beneficial for subsequent register allocation, but will result in more branch instructions. The depth-first topological sorting algorithm is a well-known layout algorithm, which has applications in many languages, and it helps to reduce branch instructions. This CL applies it to the layout pass. The test results show that it helps to reduce the code size. This CL also includes the following changes: 1, Removed the primary predecessor mechanism. The new layout algorithm is not very friendly to register allocator in some cases, in order to adapt to the new layout algorithm, a new primary predecessor selection strategy is introduced. 2, Since the new layout implementation may place non-loop blocks between loop blocks, some adaptive modifications have also been made to looprotate pass. 3, The layout also affects the results of codegen, so this CL also adjusted several codegen tests accordingly. It is inevitable that this CL will cause the code size or performance of a few functions to decrease, but the number of cases it improves is much larger than the number of cases it drops. Statistical data from compilecmp on linux/amd64 is as follow: name old time/op new time/op delta Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50) Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50) GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48) Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50) SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50) Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49) GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50) Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49) Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48) XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48) LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49) ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48) LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50) [Geo mean] 615ms 613ms -0.37% name old alloc/op new alloc/op delta Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50) Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50) GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47) Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50) SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50) Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46) GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50) Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49) Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49) XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50) LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50) ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50) LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50) [Geo mean] 69.3MB 69.1MB -0.22% file before after Δ % addr2line 4104220 4043684 -60536 -1.475% api 5342502 5249678 -92824 -1.737% asm 4973785 4858257 -115528 -2.323% buildid 2667844 2625660 -42184 -1.581% cgo 4686849 4616313 -70536 -1.505% compile 23667431 23268406 -399025 -1.686% cover 4959676 4874108 -85568 -1.725% dist 3515934 3450422 -65512 -1.863% doc 3995581 3925469 -70112 -1.755% fix 3379202 3318522 -60680 -1.796% link 6743249 6629913 -113336 -1.681% nm 4047529 3991777 -55752 -1.377% objdump 4456151 4388151 -68000 -1.526% pack 2435040 2398072 -36968 -1.518% pprof 13804080 13565808 -238272 -1.726% test2json 2690043 2645987 -44056 -1.638% trace 10418492 10232716 -185776 -1.783% vet 7258259 7121259 -137000 -1.888% total 113145867 111204202 -1941665 -1.716% The situation on linux/arm64 is as follow: name old time/op new time/op delta Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48) Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50) GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50) Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50) SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50) Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49) GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48) Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49) Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50) XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49) LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47) ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50) LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50) [Geo mean] 485ms 488ms +0.49% name old alloc/op new alloc/op delta Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49) Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45) GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50) Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44) SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49) Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50) GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50) Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47) Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50) XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48) LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50) ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50) LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50) [Geo mean] 70.4MB 70.4MB +0.01% file before after Δ % addr2line 4021557 4002933 -18624 -0.463% api 5127847 5028503 -99344 -1.937% asm 5034716 4936836 -97880 -1.944% buildid 2608118 2594094 -14024 -0.538% cgo 4488592 4398320 -90272 -2.011% compile 22501129 22213592 -287537 -1.278% cover 4742301 4713573 -28728 -0.606% dist 3388071 3365311 -22760 -0.672% doc 3802250 3776082 -26168 -0.688% fix 3306147 3216939 -89208 -2.698% link 6404483 6363699 -40784 -0.637% nm 3941026 3921930 -19096 -0.485% objdump 4383330 4295122 -88208 -2.012% pack 2404547 2389515 -15032 -0.625% pprof 12996234 12856818 -139416 -1.073% test2json 2668500 2586788 -81712 -3.062% trace 9816276 9609580 -206696 -2.106% vet 6900682 6787338 -113344 -1.643% total 108535806 107056973 -1478833 -1.363% Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d Reviewed-on: https://go-review.googlesource.com/c/go/+/255239 Reviewed-by: eric fang <eric.fang@arm.com> Reviewed-by: Keith Randall <khr@golang.org> Trust: eric fang <eric.fang@arm.com>
2020-07-22 20:24:56 -06:00
d += e
}
return d, e
}
// 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"
// arm64:"LSR\t[$]10",-"SDIV"
// arm:"SRL\t[$]10",-".*udiv"
// ppc64:"SRD"\t[$]10"
// ppc64le:"SRD"\t[$]10"
return len(a) / 1024
}
func LenDiv2(s string) int {
// 386:"SHRL\t[$]11"
// amd64:"SHRQ\t[$]11"
// arm64:"LSR\t[$]11",-"SDIV"
// arm:"SRL\t[$]11",-".*udiv"
// ppc64:"SRD\t[$]11"
// ppc64le:"SRD\t[$]11"
return len(s) / (4097 >> 1)
}
func LenMod1(a []int) int {
// 386:"ANDL\t[$]1023"
// amd64:"ANDQ\t[$]1023"
// arm64:"AND\t[$]1023",-"SDIV"
// arm/6:"AND",-".*udiv"
// arm/7:"BFC",-".*udiv",-"AND"
// ppc64:"ANDCC\t[$]1023"
// ppc64le:"ANDCC\t[$]1023"
return len(a) % 1024
}
func LenMod2(s string) int {
// 386:"ANDL\t[$]2047"
// amd64:"ANDQ\t[$]2047"
// arm64:"AND\t[$]2047",-"SDIV"
// arm/6:"AND",-".*udiv"
// arm/7:"BFC",-".*udiv",-"AND"
// ppc64:"ANDCC\t[$]2047"
// ppc64le:"ANDCC\t[$]2047"
return len(s) % (4097 >> 1)
}
func CapDiv(a []int) int {
// 386:"SHRL\t[$]12"
// amd64:"SHRQ\t[$]12"
// arm64:"LSR\t[$]12",-"SDIV"
// arm:"SRL\t[$]12",-".*udiv"
// ppc64:"SRD\t[$]12"
// ppc64le:"SRD\t[$]12"
return cap(a) / ((1 << 11) + 2048)
}
func CapMod(a []int) int {
// 386:"ANDL\t[$]4095"
// amd64:"ANDQ\t[$]4095"
// arm64:"AND\t[$]4095",-"SDIV"
// arm/6:"AND",-".*udiv"
// arm/7:"BFC",-".*udiv",-"AND"
// ppc64:"ANDCC\t[$]4095"
// ppc64le:"ANDCC\t[$]4095"
return cap(a) % ((1 << 11) + 2048)
}
func AddMul(x int) int {
// amd64:"LEAQ\t1"
return 2*x + 1
}
cmd/compile: optimize ARM64's code with MADD/MSUB MADD does MUL-ADD in a single instruction, and MSUB does the similiar simplification for MUL-SUB. The CL implements the optimization with MADD/MSUB. 1. The total size of pkg/android_arm64/ decreases about 20KB, excluding cmd/compile/. 2. The go1 benchmark shows a little improvement for RegexpMatchHard_32-4 and Template-4, excluding noise. name old time/op new time/op delta BinaryTree17-4 16.3s ± 1% 16.5s ± 1% +1.41% (p=0.000 n=26+28) Fannkuch11-4 8.79s ± 1% 8.76s ± 0% -0.36% (p=0.000 n=26+28) FmtFprintfEmpty-4 172ns ± 0% 172ns ± 0% ~ (all equal) FmtFprintfString-4 362ns ± 1% 364ns ± 0% +0.55% (p=0.000 n=30+30) FmtFprintfInt-4 416ns ± 0% 416ns ± 0% ~ (p=0.099 n=22+30) FmtFprintfIntInt-4 655ns ± 1% 660ns ± 1% +0.76% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 810ns ± 0% 809ns ± 0% -0.08% (p=0.009 n=29+29) FmtFprintfFloat-4 1.08µs ± 0% 1.09µs ± 0% +0.61% (p=0.000 n=30+29) FmtManyArgs-4 2.70µs ± 0% 2.69µs ± 0% -0.23% (p=0.000 n=29+28) GobDecode-4 32.2ms ± 1% 32.1ms ± 1% -0.39% (p=0.000 n=27+26) GobEncode-4 27.4ms ± 2% 27.4ms ± 1% ~ (p=0.864 n=28+28) Gzip-4 1.53s ± 1% 1.52s ± 1% -0.30% (p=0.031 n=29+29) Gunzip-4 146ms ± 0% 146ms ± 0% -0.14% (p=0.001 n=25+30) HTTPClientServer-4 1.00ms ± 4% 0.98ms ± 6% -1.65% (p=0.001 n=29+30) JSONEncode-4 67.3ms ± 1% 67.2ms ± 1% ~ (p=0.520 n=28+28) JSONDecode-4 329ms ± 5% 330ms ± 4% ~ (p=0.142 n=30+30) Mandelbrot200-4 17.3ms ± 0% 17.3ms ± 0% ~ (p=0.055 n=26+29) GoParse-4 16.9ms ± 1% 17.0ms ± 1% +0.82% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 382ns ± 0% 382ns ± 0% ~ (all equal) RegexpMatchEasy0_1K-4 1.33µs ± 0% 1.33µs ± 0% -0.25% (p=0.000 n=30+27) RegexpMatchEasy1_32-4 361ns ± 0% 361ns ± 0% -0.08% (p=0.002 n=30+28) RegexpMatchEasy1_1K-4 2.11µs ± 0% 2.09µs ± 0% -0.54% (p=0.000 n=30+29) RegexpMatchMedium_32-4 594ns ± 0% 592ns ± 0% -0.32% (p=0.000 n=30+30) RegexpMatchMedium_1K-4 173µs ± 0% 172µs ± 0% -0.77% (p=0.000 n=29+27) RegexpMatchHard_32-4 10.4µs ± 0% 10.1µs ± 0% -3.63% (p=0.000 n=28+27) RegexpMatchHard_1K-4 306µs ± 0% 301µs ± 0% -1.64% (p=0.000 n=29+30) Revcomp-4 2.51s ± 1% 2.52s ± 0% +0.18% (p=0.017 n=26+27) Template-4 394ms ± 3% 382ms ± 3% -3.22% (p=0.000 n=28+28) TimeParse-4 1.67µs ± 0% 1.67µs ± 0% +0.05% (p=0.030 n=27+30) TimeFormat-4 1.72µs ± 0% 1.70µs ± 0% -0.79% (p=0.000 n=28+26) [Geo mean] 259µs 259µs -0.33% name old speed new speed delta GobDecode-4 23.8MB/s ± 1% 23.9MB/s ± 1% +0.40% (p=0.001 n=27+26) GobEncode-4 28.0MB/s ± 2% 28.0MB/s ± 1% ~ (p=0.863 n=28+28) Gzip-4 12.7MB/s ± 1% 12.7MB/s ± 1% +0.32% (p=0.026 n=29+29) Gunzip-4 133MB/s ± 0% 133MB/s ± 0% +0.15% (p=0.001 n=24+30) JSONEncode-4 28.8MB/s ± 1% 28.9MB/s ± 1% ~ (p=0.475 n=28+28) JSONDecode-4 5.89MB/s ± 4% 5.87MB/s ± 5% ~ (p=0.174 n=29+30) GoParse-4 3.43MB/s ± 0% 3.40MB/s ± 1% -0.83% (p=0.000 n=28+30) RegexpMatchEasy0_32-4 83.6MB/s ± 0% 83.6MB/s ± 0% ~ (p=0.848 n=28+29) RegexpMatchEasy0_1K-4 768MB/s ± 0% 770MB/s ± 0% +0.25% (p=0.000 n=30+27) RegexpMatchEasy1_32-4 88.5MB/s ± 0% 88.5MB/s ± 0% ~ (p=0.086 n=29+29) RegexpMatchEasy1_1K-4 486MB/s ± 0% 489MB/s ± 0% +0.54% (p=0.000 n=30+29) RegexpMatchMedium_32-4 1.68MB/s ± 0% 1.69MB/s ± 0% +0.60% (p=0.000 n=30+23) RegexpMatchMedium_1K-4 5.90MB/s ± 0% 5.95MB/s ± 0% +0.85% (p=0.000 n=18+20) RegexpMatchHard_32-4 3.07MB/s ± 0% 3.18MB/s ± 0% +3.72% (p=0.000 n=29+26) RegexpMatchHard_1K-4 3.35MB/s ± 0% 3.40MB/s ± 0% +1.69% (p=0.000 n=30+30) Revcomp-4 101MB/s ± 0% 101MB/s ± 0% -0.18% (p=0.018 n=26+27) Template-4 4.92MB/s ± 4% 5.09MB/s ± 3% +3.31% (p=0.000 n=28+28) [Geo mean] 22.4MB/s 22.6MB/s +0.62% Change-Id: I8f304b272785739f57b3c8f736316f658f8c1b2a Reviewed-on: https://go-review.googlesource.com/129119 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-13 04:38:25 -06:00
cmd/compile: optimize arm64's MADD and MSUB This CL implements constant folding for MADD/MSUB on arm64. 1. The total size of pkg/android_arm64/ decreases about 4KB, excluding cmd/compile/ . 2. There is no regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 16.4s ± 1% 16.5s ± 1% +0.24% (p=0.008 n=29+29) Fannkuch11-4 8.73s ± 0% 8.71s ± 0% -0.15% (p=0.000 n=29+29) FmtFprintfEmpty-4 174ns ± 0% 174ns ± 0% ~ (all equal) FmtFprintfString-4 370ns ± 0% 372ns ± 2% +0.53% (p=0.007 n=24+30) FmtFprintfInt-4 419ns ± 0% 419ns ± 0% ~ (all equal) FmtFprintfIntInt-4 673ns ± 1% 661ns ± 1% -1.81% (p=0.000 n=30+27) FmtFprintfPrefixedInt-4 806ns ± 0% 805ns ± 0% ~ (p=0.957 n=28+27) FmtFprintfFloat-4 1.09µs ± 0% 1.09µs ± 0% -0.04% (p=0.001 n=22+30) FmtManyArgs-4 2.67µs ± 0% 2.68µs ± 0% +0.03% (p=0.045 n=29+28) GobDecode-4 33.2ms ± 1% 32.5ms ± 1% -2.11% (p=0.000 n=29+29) GobEncode-4 29.5ms ± 0% 29.2ms ± 0% -1.04% (p=0.000 n=28+28) Gzip-4 1.39s ± 2% 1.38s ± 1% -0.48% (p=0.023 n=30+30) Gunzip-4 139ms ± 0% 139ms ± 0% ~ (p=0.616 n=30+28) HTTPClientServer-4 766µs ± 4% 758µs ± 3% -1.03% (p=0.013 n=28+29) JSONEncode-4 49.7ms ± 0% 49.6ms ± 0% -0.24% (p=0.000 n=30+30) JSONDecode-4 266ms ± 0% 268ms ± 1% +1.07% (p=0.000 n=29+30) Mandelbrot200-4 16.6ms ± 0% 16.6ms ± 0% ~ (p=0.248 n=30+29) GoParse-4 15.9ms ± 0% 16.0ms ± 0% +0.76% (p=0.000 n=29+29) RegexpMatchEasy0_32-4 381ns ± 0% 380ns ± 0% -0.14% (p=0.000 n=30+30) RegexpMatchEasy0_1K-4 1.18µs ± 0% 1.19µs ± 1% +0.30% (p=0.000 n=29+30) RegexpMatchEasy1_32-4 357ns ± 0% 357ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.04µs ± 0% 2.05µs ± 0% +0.50% (p=0.000 n=26+28) RegexpMatchMedium_32-4 590ns ± 0% 589ns ± 0% -0.12% (p=0.000 n=30+23) RegexpMatchMedium_1K-4 162µs ± 0% 162µs ± 0% ~ (p=0.318 n=28+25) RegexpMatchHard_32-4 9.56µs ± 0% 9.56µs ± 0% ~ (p=0.072 n=30+29) RegexpMatchHard_1K-4 287µs ± 0% 287µs ± 0% -0.02% (p=0.005 n=28+28) Revcomp-4 2.50s ± 0% 2.51s ± 0% ~ (p=0.246 n=29+29) Template-4 312ms ± 1% 313ms ± 1% +0.46% (p=0.002 n=30+30) TimeParse-4 1.68µs ± 0% 1.67µs ± 0% -0.31% (p=0.000 n=27+29) TimeFormat-4 1.66µs ± 0% 1.64µs ± 0% -0.92% (p=0.000 n=29+26) [Geo mean] 247µs 246µs -0.15% name old speed new speed delta GobDecode-4 23.1MB/s ± 1% 23.6MB/s ± 0% +2.17% (p=0.000 n=29+28) GobEncode-4 26.0MB/s ± 0% 26.3MB/s ± 0% +1.05% (p=0.000 n=28+28) Gzip-4 14.0MB/s ± 2% 14.1MB/s ± 1% +0.47% (p=0.026 n=30+30) Gunzip-4 139MB/s ± 0% 139MB/s ± 0% ~ (p=0.624 n=30+28) JSONEncode-4 39.1MB/s ± 0% 39.2MB/s ± 0% +0.24% (p=0.000 n=30+30) JSONDecode-4 7.31MB/s ± 0% 7.23MB/s ± 1% -1.07% (p=0.000 n=28+30) GoParse-4 3.65MB/s ± 0% 3.62MB/s ± 0% -0.77% (p=0.000 n=29+29) RegexpMatchEasy0_32-4 84.0MB/s ± 0% 84.1MB/s ± 0% +0.18% (p=0.000 n=28+30) RegexpMatchEasy0_1K-4 864MB/s ± 0% 861MB/s ± 1% -0.29% (p=0.000 n=29+30) RegexpMatchEasy1_32-4 89.5MB/s ± 0% 89.5MB/s ± 0% ~ (p=0.841 n=28+28) RegexpMatchEasy1_1K-4 502MB/s ± 0% 500MB/s ± 0% -0.51% (p=0.000 n=29+29) RegexpMatchMedium_32-4 1.69MB/s ± 0% 1.70MB/s ± 0% +0.41% (p=0.000 n=26+30) RegexpMatchMedium_1K-4 6.31MB/s ± 0% 6.30MB/s ± 0% ~ (p=0.129 n=30+25) RegexpMatchHard_32-4 3.35MB/s ± 0% 3.35MB/s ± 0% ~ (p=0.657 n=30+29) RegexpMatchHard_1K-4 3.57MB/s ± 0% 3.57MB/s ± 0% ~ (all equal) Revcomp-4 102MB/s ± 0% 101MB/s ± 0% ~ (p=0.213 n=29+29) Template-4 6.22MB/s ± 1% 6.19MB/s ± 1% -0.42% (p=0.005 n=30+29) [Geo mean] 24.1MB/s 24.2MB/s +0.08% Change-Id: I6c02d3c9975f6bd8bc215cb1fc14d29602b45649 Reviewed-on: https://go-review.googlesource.com/138095 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-09-27 07:21:03 -06:00
func MULA(a, b, c uint32) (uint32, uint32, uint32) {
// arm:`MULA`,-`MUL\s`
// arm64:`MADDW`,-`MULW`
r0 := a*b + c
// arm:`MULA`,-`MUL\s`
cmd/compile: optimize arm64's MADD and MSUB This CL implements constant folding for MADD/MSUB on arm64. 1. The total size of pkg/android_arm64/ decreases about 4KB, excluding cmd/compile/ . 2. There is no regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 16.4s ± 1% 16.5s ± 1% +0.24% (p=0.008 n=29+29) Fannkuch11-4 8.73s ± 0% 8.71s ± 0% -0.15% (p=0.000 n=29+29) FmtFprintfEmpty-4 174ns ± 0% 174ns ± 0% ~ (all equal) FmtFprintfString-4 370ns ± 0% 372ns ± 2% +0.53% (p=0.007 n=24+30) FmtFprintfInt-4 419ns ± 0% 419ns ± 0% ~ (all equal) FmtFprintfIntInt-4 673ns ± 1% 661ns ± 1% -1.81% (p=0.000 n=30+27) FmtFprintfPrefixedInt-4 806ns ± 0% 805ns ± 0% ~ (p=0.957 n=28+27) FmtFprintfFloat-4 1.09µs ± 0% 1.09µs ± 0% -0.04% (p=0.001 n=22+30) FmtManyArgs-4 2.67µs ± 0% 2.68µs ± 0% +0.03% (p=0.045 n=29+28) GobDecode-4 33.2ms ± 1% 32.5ms ± 1% -2.11% (p=0.000 n=29+29) GobEncode-4 29.5ms ± 0% 29.2ms ± 0% -1.04% (p=0.000 n=28+28) Gzip-4 1.39s ± 2% 1.38s ± 1% -0.48% (p=0.023 n=30+30) Gunzip-4 139ms ± 0% 139ms ± 0% ~ (p=0.616 n=30+28) HTTPClientServer-4 766µs ± 4% 758µs ± 3% -1.03% (p=0.013 n=28+29) JSONEncode-4 49.7ms ± 0% 49.6ms ± 0% -0.24% (p=0.000 n=30+30) JSONDecode-4 266ms ± 0% 268ms ± 1% +1.07% (p=0.000 n=29+30) Mandelbrot200-4 16.6ms ± 0% 16.6ms ± 0% ~ (p=0.248 n=30+29) GoParse-4 15.9ms ± 0% 16.0ms ± 0% +0.76% (p=0.000 n=29+29) RegexpMatchEasy0_32-4 381ns ± 0% 380ns ± 0% -0.14% (p=0.000 n=30+30) RegexpMatchEasy0_1K-4 1.18µs ± 0% 1.19µs ± 1% +0.30% (p=0.000 n=29+30) RegexpMatchEasy1_32-4 357ns ± 0% 357ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.04µs ± 0% 2.05µs ± 0% +0.50% (p=0.000 n=26+28) RegexpMatchMedium_32-4 590ns ± 0% 589ns ± 0% -0.12% (p=0.000 n=30+23) RegexpMatchMedium_1K-4 162µs ± 0% 162µs ± 0% ~ (p=0.318 n=28+25) RegexpMatchHard_32-4 9.56µs ± 0% 9.56µs ± 0% ~ (p=0.072 n=30+29) RegexpMatchHard_1K-4 287µs ± 0% 287µs ± 0% -0.02% (p=0.005 n=28+28) Revcomp-4 2.50s ± 0% 2.51s ± 0% ~ (p=0.246 n=29+29) Template-4 312ms ± 1% 313ms ± 1% +0.46% (p=0.002 n=30+30) TimeParse-4 1.68µs ± 0% 1.67µs ± 0% -0.31% (p=0.000 n=27+29) TimeFormat-4 1.66µs ± 0% 1.64µs ± 0% -0.92% (p=0.000 n=29+26) [Geo mean] 247µs 246µs -0.15% name old speed new speed delta GobDecode-4 23.1MB/s ± 1% 23.6MB/s ± 0% +2.17% (p=0.000 n=29+28) GobEncode-4 26.0MB/s ± 0% 26.3MB/s ± 0% +1.05% (p=0.000 n=28+28) Gzip-4 14.0MB/s ± 2% 14.1MB/s ± 1% +0.47% (p=0.026 n=30+30) Gunzip-4 139MB/s ± 0% 139MB/s ± 0% ~ (p=0.624 n=30+28) JSONEncode-4 39.1MB/s ± 0% 39.2MB/s ± 0% +0.24% (p=0.000 n=30+30) JSONDecode-4 7.31MB/s ± 0% 7.23MB/s ± 1% -1.07% (p=0.000 n=28+30) GoParse-4 3.65MB/s ± 0% 3.62MB/s ± 0% -0.77% (p=0.000 n=29+29) RegexpMatchEasy0_32-4 84.0MB/s ± 0% 84.1MB/s ± 0% +0.18% (p=0.000 n=28+30) RegexpMatchEasy0_1K-4 864MB/s ± 0% 861MB/s ± 1% -0.29% (p=0.000 n=29+30) RegexpMatchEasy1_32-4 89.5MB/s ± 0% 89.5MB/s ± 0% ~ (p=0.841 n=28+28) RegexpMatchEasy1_1K-4 502MB/s ± 0% 500MB/s ± 0% -0.51% (p=0.000 n=29+29) RegexpMatchMedium_32-4 1.69MB/s ± 0% 1.70MB/s ± 0% +0.41% (p=0.000 n=26+30) RegexpMatchMedium_1K-4 6.31MB/s ± 0% 6.30MB/s ± 0% ~ (p=0.129 n=30+25) RegexpMatchHard_32-4 3.35MB/s ± 0% 3.35MB/s ± 0% ~ (p=0.657 n=30+29) RegexpMatchHard_1K-4 3.57MB/s ± 0% 3.57MB/s ± 0% ~ (all equal) Revcomp-4 102MB/s ± 0% 101MB/s ± 0% ~ (p=0.213 n=29+29) Template-4 6.22MB/s ± 1% 6.19MB/s ± 1% -0.42% (p=0.005 n=30+29) [Geo mean] 24.1MB/s 24.2MB/s +0.08% Change-Id: I6c02d3c9975f6bd8bc215cb1fc14d29602b45649 Reviewed-on: https://go-review.googlesource.com/138095 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-09-27 07:21:03 -06:00
// arm64:`MADDW`,-`MULW`
r1 := c*79 + a
// arm:`ADD`,-`MULA`,-`MUL\s`
cmd/compile: optimize arm64's MADD and MSUB This CL implements constant folding for MADD/MSUB on arm64. 1. The total size of pkg/android_arm64/ decreases about 4KB, excluding cmd/compile/ . 2. There is no regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 16.4s ± 1% 16.5s ± 1% +0.24% (p=0.008 n=29+29) Fannkuch11-4 8.73s ± 0% 8.71s ± 0% -0.15% (p=0.000 n=29+29) FmtFprintfEmpty-4 174ns ± 0% 174ns ± 0% ~ (all equal) FmtFprintfString-4 370ns ± 0% 372ns ± 2% +0.53% (p=0.007 n=24+30) FmtFprintfInt-4 419ns ± 0% 419ns ± 0% ~ (all equal) FmtFprintfIntInt-4 673ns ± 1% 661ns ± 1% -1.81% (p=0.000 n=30+27) FmtFprintfPrefixedInt-4 806ns ± 0% 805ns ± 0% ~ (p=0.957 n=28+27) FmtFprintfFloat-4 1.09µs ± 0% 1.09µs ± 0% -0.04% (p=0.001 n=22+30) FmtManyArgs-4 2.67µs ± 0% 2.68µs ± 0% +0.03% (p=0.045 n=29+28) GobDecode-4 33.2ms ± 1% 32.5ms ± 1% -2.11% (p=0.000 n=29+29) GobEncode-4 29.5ms ± 0% 29.2ms ± 0% -1.04% (p=0.000 n=28+28) Gzip-4 1.39s ± 2% 1.38s ± 1% -0.48% (p=0.023 n=30+30) Gunzip-4 139ms ± 0% 139ms ± 0% ~ (p=0.616 n=30+28) HTTPClientServer-4 766µs ± 4% 758µs ± 3% -1.03% (p=0.013 n=28+29) JSONEncode-4 49.7ms ± 0% 49.6ms ± 0% -0.24% (p=0.000 n=30+30) JSONDecode-4 266ms ± 0% 268ms ± 1% +1.07% (p=0.000 n=29+30) Mandelbrot200-4 16.6ms ± 0% 16.6ms ± 0% ~ (p=0.248 n=30+29) GoParse-4 15.9ms ± 0% 16.0ms ± 0% +0.76% (p=0.000 n=29+29) RegexpMatchEasy0_32-4 381ns ± 0% 380ns ± 0% -0.14% (p=0.000 n=30+30) RegexpMatchEasy0_1K-4 1.18µs ± 0% 1.19µs ± 1% +0.30% (p=0.000 n=29+30) RegexpMatchEasy1_32-4 357ns ± 0% 357ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.04µs ± 0% 2.05µs ± 0% +0.50% (p=0.000 n=26+28) RegexpMatchMedium_32-4 590ns ± 0% 589ns ± 0% -0.12% (p=0.000 n=30+23) RegexpMatchMedium_1K-4 162µs ± 0% 162µs ± 0% ~ (p=0.318 n=28+25) RegexpMatchHard_32-4 9.56µs ± 0% 9.56µs ± 0% ~ (p=0.072 n=30+29) RegexpMatchHard_1K-4 287µs ± 0% 287µs ± 0% -0.02% (p=0.005 n=28+28) Revcomp-4 2.50s ± 0% 2.51s ± 0% ~ (p=0.246 n=29+29) Template-4 312ms ± 1% 313ms ± 1% +0.46% (p=0.002 n=30+30) TimeParse-4 1.68µs ± 0% 1.67µs ± 0% -0.31% (p=0.000 n=27+29) TimeFormat-4 1.66µs ± 0% 1.64µs ± 0% -0.92% (p=0.000 n=29+26) [Geo mean] 247µs 246µs -0.15% name old speed new speed delta GobDecode-4 23.1MB/s ± 1% 23.6MB/s ± 0% +2.17% (p=0.000 n=29+28) GobEncode-4 26.0MB/s ± 0% 26.3MB/s ± 0% +1.05% (p=0.000 n=28+28) Gzip-4 14.0MB/s ± 2% 14.1MB/s ± 1% +0.47% (p=0.026 n=30+30) Gunzip-4 139MB/s ± 0% 139MB/s ± 0% ~ (p=0.624 n=30+28) JSONEncode-4 39.1MB/s ± 0% 39.2MB/s ± 0% +0.24% (p=0.000 n=30+30) JSONDecode-4 7.31MB/s ± 0% 7.23MB/s ± 1% -1.07% (p=0.000 n=28+30) GoParse-4 3.65MB/s ± 0% 3.62MB/s ± 0% -0.77% (p=0.000 n=29+29) RegexpMatchEasy0_32-4 84.0MB/s ± 0% 84.1MB/s ± 0% +0.18% (p=0.000 n=28+30) RegexpMatchEasy0_1K-4 864MB/s ± 0% 861MB/s ± 1% -0.29% (p=0.000 n=29+30) RegexpMatchEasy1_32-4 89.5MB/s ± 0% 89.5MB/s ± 0% ~ (p=0.841 n=28+28) RegexpMatchEasy1_1K-4 502MB/s ± 0% 500MB/s ± 0% -0.51% (p=0.000 n=29+29) RegexpMatchMedium_32-4 1.69MB/s ± 0% 1.70MB/s ± 0% +0.41% (p=0.000 n=26+30) RegexpMatchMedium_1K-4 6.31MB/s ± 0% 6.30MB/s ± 0% ~ (p=0.129 n=30+25) RegexpMatchHard_32-4 3.35MB/s ± 0% 3.35MB/s ± 0% ~ (p=0.657 n=30+29) RegexpMatchHard_1K-4 3.57MB/s ± 0% 3.57MB/s ± 0% ~ (all equal) Revcomp-4 102MB/s ± 0% 101MB/s ± 0% ~ (p=0.213 n=29+29) Template-4 6.22MB/s ± 1% 6.19MB/s ± 1% -0.42% (p=0.005 n=30+29) [Geo mean] 24.1MB/s 24.2MB/s +0.08% Change-Id: I6c02d3c9975f6bd8bc215cb1fc14d29602b45649 Reviewed-on: https://go-review.googlesource.com/138095 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-09-27 07:21:03 -06:00
// arm64:`ADD`,-`MADD`,-`MULW`
r2 := b*64 + c
return r0, r1, r2
cmd/compile: optimize ARM64's code with MADD/MSUB MADD does MUL-ADD in a single instruction, and MSUB does the similiar simplification for MUL-SUB. The CL implements the optimization with MADD/MSUB. 1. The total size of pkg/android_arm64/ decreases about 20KB, excluding cmd/compile/. 2. The go1 benchmark shows a little improvement for RegexpMatchHard_32-4 and Template-4, excluding noise. name old time/op new time/op delta BinaryTree17-4 16.3s ± 1% 16.5s ± 1% +1.41% (p=0.000 n=26+28) Fannkuch11-4 8.79s ± 1% 8.76s ± 0% -0.36% (p=0.000 n=26+28) FmtFprintfEmpty-4 172ns ± 0% 172ns ± 0% ~ (all equal) FmtFprintfString-4 362ns ± 1% 364ns ± 0% +0.55% (p=0.000 n=30+30) FmtFprintfInt-4 416ns ± 0% 416ns ± 0% ~ (p=0.099 n=22+30) FmtFprintfIntInt-4 655ns ± 1% 660ns ± 1% +0.76% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 810ns ± 0% 809ns ± 0% -0.08% (p=0.009 n=29+29) FmtFprintfFloat-4 1.08µs ± 0% 1.09µs ± 0% +0.61% (p=0.000 n=30+29) FmtManyArgs-4 2.70µs ± 0% 2.69µs ± 0% -0.23% (p=0.000 n=29+28) GobDecode-4 32.2ms ± 1% 32.1ms ± 1% -0.39% (p=0.000 n=27+26) GobEncode-4 27.4ms ± 2% 27.4ms ± 1% ~ (p=0.864 n=28+28) Gzip-4 1.53s ± 1% 1.52s ± 1% -0.30% (p=0.031 n=29+29) Gunzip-4 146ms ± 0% 146ms ± 0% -0.14% (p=0.001 n=25+30) HTTPClientServer-4 1.00ms ± 4% 0.98ms ± 6% -1.65% (p=0.001 n=29+30) JSONEncode-4 67.3ms ± 1% 67.2ms ± 1% ~ (p=0.520 n=28+28) JSONDecode-4 329ms ± 5% 330ms ± 4% ~ (p=0.142 n=30+30) Mandelbrot200-4 17.3ms ± 0% 17.3ms ± 0% ~ (p=0.055 n=26+29) GoParse-4 16.9ms ± 1% 17.0ms ± 1% +0.82% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 382ns ± 0% 382ns ± 0% ~ (all equal) RegexpMatchEasy0_1K-4 1.33µs ± 0% 1.33µs ± 0% -0.25% (p=0.000 n=30+27) RegexpMatchEasy1_32-4 361ns ± 0% 361ns ± 0% -0.08% (p=0.002 n=30+28) RegexpMatchEasy1_1K-4 2.11µs ± 0% 2.09µs ± 0% -0.54% (p=0.000 n=30+29) RegexpMatchMedium_32-4 594ns ± 0% 592ns ± 0% -0.32% (p=0.000 n=30+30) RegexpMatchMedium_1K-4 173µs ± 0% 172µs ± 0% -0.77% (p=0.000 n=29+27) RegexpMatchHard_32-4 10.4µs ± 0% 10.1µs ± 0% -3.63% (p=0.000 n=28+27) RegexpMatchHard_1K-4 306µs ± 0% 301µs ± 0% -1.64% (p=0.000 n=29+30) Revcomp-4 2.51s ± 1% 2.52s ± 0% +0.18% (p=0.017 n=26+27) Template-4 394ms ± 3% 382ms ± 3% -3.22% (p=0.000 n=28+28) TimeParse-4 1.67µs ± 0% 1.67µs ± 0% +0.05% (p=0.030 n=27+30) TimeFormat-4 1.72µs ± 0% 1.70µs ± 0% -0.79% (p=0.000 n=28+26) [Geo mean] 259µs 259µs -0.33% name old speed new speed delta GobDecode-4 23.8MB/s ± 1% 23.9MB/s ± 1% +0.40% (p=0.001 n=27+26) GobEncode-4 28.0MB/s ± 2% 28.0MB/s ± 1% ~ (p=0.863 n=28+28) Gzip-4 12.7MB/s ± 1% 12.7MB/s ± 1% +0.32% (p=0.026 n=29+29) Gunzip-4 133MB/s ± 0% 133MB/s ± 0% +0.15% (p=0.001 n=24+30) JSONEncode-4 28.8MB/s ± 1% 28.9MB/s ± 1% ~ (p=0.475 n=28+28) JSONDecode-4 5.89MB/s ± 4% 5.87MB/s ± 5% ~ (p=0.174 n=29+30) GoParse-4 3.43MB/s ± 0% 3.40MB/s ± 1% -0.83% (p=0.000 n=28+30) RegexpMatchEasy0_32-4 83.6MB/s ± 0% 83.6MB/s ± 0% ~ (p=0.848 n=28+29) RegexpMatchEasy0_1K-4 768MB/s ± 0% 770MB/s ± 0% +0.25% (p=0.000 n=30+27) RegexpMatchEasy1_32-4 88.5MB/s ± 0% 88.5MB/s ± 0% ~ (p=0.086 n=29+29) RegexpMatchEasy1_1K-4 486MB/s ± 0% 489MB/s ± 0% +0.54% (p=0.000 n=30+29) RegexpMatchMedium_32-4 1.68MB/s ± 0% 1.69MB/s ± 0% +0.60% (p=0.000 n=30+23) RegexpMatchMedium_1K-4 5.90MB/s ± 0% 5.95MB/s ± 0% +0.85% (p=0.000 n=18+20) RegexpMatchHard_32-4 3.07MB/s ± 0% 3.18MB/s ± 0% +3.72% (p=0.000 n=29+26) RegexpMatchHard_1K-4 3.35MB/s ± 0% 3.40MB/s ± 0% +1.69% (p=0.000 n=30+30) Revcomp-4 101MB/s ± 0% 101MB/s ± 0% -0.18% (p=0.018 n=26+27) Template-4 4.92MB/s ± 4% 5.09MB/s ± 3% +3.31% (p=0.000 n=28+28) [Geo mean] 22.4MB/s 22.6MB/s +0.62% Change-Id: I8f304b272785739f57b3c8f736316f658f8c1b2a Reviewed-on: https://go-review.googlesource.com/129119 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-08-13 04:38:25 -06:00
}
func MULS(a, b, c uint32) (uint32, uint32, uint32) {
// arm/7:`MULS`,-`MUL\s`
// arm/6:`SUB`,`MUL\s`,-`MULS`
// arm64:`MSUBW`,-`MULW`
r0 := c - a*b
// arm/7:`MULS`,-`MUL\s`
// arm/6:`SUB`,`MUL\s`,-`MULS`
// arm64:`MSUBW`,-`MULW`
r1 := a - c*79
// arm/7:`SUB`,-`MULS`,-`MUL\s`
// arm64:`SUB`,-`MSUBW`,-`MULW`
r2 := c - b*64
return r0, r1, r2
}
func addSpecial(a, b, c uint32) (uint32, uint32, uint32) {
// amd64:`INCL`
a++
// amd64:`DECL`
b--
// amd64:`SUBL.*-128`
c += 128
return a, b, c
}
cmd/compile: in prove, zero right shifts of positive int by #bits - 1 Taking over Zach's CL 212277. Just cleaned up and added a test. For a positive, signed integer, an arithmetic right shift of count (bit-width - 1) equals zero. e.g. int64(22) >> 63 -> 0. This CL makes prove replace these right shifts with a zero-valued constant. These shifts may arise in source code explicitly, but can also be created by the generic rewrite of signed division by a power of 2. // Signed divide by power of 2. // n / c = n >> log(c) if n >= 0 // = (n+c-1) >> log(c) if n < 0 // We conditionally add c-1 by adding n>>63>>(64-log(c)) (first shift signed, second shift unsigned). (Div64 <t> n (Const64 [c])) && isPowerOfTwo(c) -> (Rsh64x64 (Add64 <t> n (Rsh64Ux64 <t> (Rsh64x64 <t> n (Const64 <typ.UInt64> [63])) (Const64 <typ.UInt64> [64-log2(c)]))) (Const64 <typ.UInt64> [log2(c)])) If n is known to be positive, this rewrite includes an extra Add and 2 extra Rsh. This CL will allow prove to replace one of the extra Rsh with a 0. That replacement then allows lateopt to remove all the unneccesary fixups from the generic rewrite. There is a rewrite rule to handle this case directly: (Div64 n (Const64 [c])) && isNonNegative(n) && isPowerOfTwo(c) -> (Rsh64Ux64 n (Const64 <typ.UInt64> [log2(c)])) But this implementation of isNonNegative really only handles constants and a few special operations like len/cap. The division could be handled if the factsTable version of isNonNegative were available. Unfortunately, the first opt pass happens before prove even has a chance to deduce the numerator is non-negative, so the generic rewrite has already fired and created the extra Ops discussed above. Fixes #36159 By Printf count, this zeroes 137 right shifts when building std and cmd. Change-Id: Iab486910ac9d7cfb86ace2835456002732b384a2 Reviewed-on: https://go-review.googlesource.com/c/go/+/232857 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-05-07 14:44:51 -06:00
// Divide -> shift rules usually require fixup for negative inputs.
// If the input is non-negative, make sure the fixup is eliminated.
func divInt(v int64) int64 {
if v < 0 {
return 0
}
// amd64:-`.*SARQ.*63,`, -".*SHRQ", ".*SARQ.*[$]9,"
return v / 512
}
// The reassociate rules "x - (z + C) -> (x - z) - C" and
// "(z + C) -x -> C + (z - x)" can optimize the following cases.
func constantFold1(i0, j0, i1, j1, i2, j2, i3, j3 int) (int, int, int, int) {
// arm64:"SUB","ADD\t[$]2"
r0 := (i0 + 3) - (j0 + 1)
// arm64:"SUB","SUB\t[$]4"
r1 := (i1 - 3) - (j1 + 1)
// arm64:"SUB","ADD\t[$]4"
r2 := (i2 + 3) - (j2 - 1)
// arm64:"SUB","SUB\t[$]2"
r3 := (i3 - 3) - (j3 - 1)
return r0, r1, r2, r3
}
// The reassociate rules "x - (z + C) -> (x - z) - C" and
// "(C - z) - x -> C - (z + x)" can optimize the following cases.
func constantFold2(i0, j0, i1, j1 int) (int, int) {
// arm64:"ADD","MOVD\t[$]2","SUB"
r0 := (3 - i0) - (j0 + 1)
// arm64:"ADD","MOVD\t[$]4","SUB"
r1 := (3 - i1) - (j1 - 1)
return r0, r1
}
func constantFold3(i, j int) int {
// arm64: "MOVD\t[$]30","MUL",-"ADD",-"LSL"
r := (5 * i) * (6 * j)
return r
}