1
0
mirror of https://github.com/golang/go synced 2024-11-24 00:30:15 -07:00
go/test/codegen/bits.go

377 lines
6.2 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
import "math/bits"
cmd/compile: add patterns for bit set/clear/complement on amd64 This patch completes implementation of BT(Q|L), and adds support for BT(S|R|C)(Q|L). Example of code changes from time.(*Time).addSec: if t.wall&hasMonotonic != 0 { 0x1073465 488b08 MOVQ 0(AX), CX 0x1073468 4889ca MOVQ CX, DX 0x107346b 48c1e93f SHRQ $0x3f, CX 0x107346f 48c1e13f SHLQ $0x3f, CX 0x1073473 48f7c1ffffffff TESTQ $-0x1, CX 0x107347a 746b JE 0x10734e7 if t.wall&hasMonotonic != 0 { 0x1073435 488b08 MOVQ 0(AX), CX 0x1073438 480fbae13f BTQ $0x3f, CX 0x107343d 7363 JAE 0x10734a2 Another example: t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x10734c8 4881e1ffffff3f ANDQ $0x3fffffff, CX 0x10734cf 48c1e61e SHLQ $0x1e, SI 0x10734d3 4809ce ORQ CX, SI 0x10734d6 48b90000000000000080 MOVQ $0x8000000000000000, CX 0x10734e0 4809f1 ORQ SI, CX 0x10734e3 488908 MOVQ CX, 0(AX) t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x107348b 4881e2ffffff3f ANDQ $0x3fffffff, DX 0x1073492 48c1e61e SHLQ $0x1e, SI 0x1073496 4809f2 ORQ SI, DX 0x1073499 480fbaea3f BTSQ $0x3f, DX 0x107349e 488910 MOVQ DX, 0(AX) Go1 benchmarks seem unaffected, and I would be surprised otherwise: name old time/op new time/op delta BinaryTree17-4 2.64s ± 4% 2.56s ± 9% -2.92% (p=0.008 n=9+9) Fannkuch11-4 2.90s ± 1% 2.95s ± 3% +1.76% (p=0.010 n=10+9) FmtFprintfEmpty-4 35.3ns ± 1% 34.5ns ± 2% -2.34% (p=0.004 n=9+8) FmtFprintfString-4 57.0ns ± 1% 58.4ns ± 5% +2.52% (p=0.029 n=9+10) FmtFprintfInt-4 59.8ns ± 3% 59.8ns ± 6% ~ (p=0.565 n=10+10) FmtFprintfIntInt-4 93.9ns ± 3% 91.2ns ± 5% -2.94% (p=0.014 n=10+9) FmtFprintfPrefixedInt-4 107ns ± 6% 104ns ± 6% ~ (p=0.099 n=10+10) FmtFprintfFloat-4 187ns ± 3% 188ns ± 3% ~ (p=0.505 n=10+9) FmtManyArgs-4 410ns ± 1% 415ns ± 6% ~ (p=0.649 n=8+10) GobDecode-4 5.30ms ± 3% 5.27ms ± 3% ~ (p=0.436 n=10+10) GobEncode-4 4.62ms ± 5% 4.47ms ± 2% -3.24% (p=0.001 n=9+10) Gzip-4 197ms ± 4% 193ms ± 3% ~ (p=0.123 n=10+10) Gunzip-4 30.4ms ± 3% 30.1ms ± 3% ~ (p=0.481 n=10+10) HTTPClientServer-4 76.3µs ± 1% 76.0µs ± 1% ~ (p=0.236 n=8+9) JSONEncode-4 10.5ms ± 9% 10.3ms ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 42.3ms ±10% 41.3ms ± 2% ~ (p=0.053 n=9+10) Mandelbrot200-4 3.80ms ± 2% 3.72ms ± 2% -2.15% (p=0.001 n=9+10) GoParse-4 2.88ms ±10% 2.81ms ± 2% ~ (p=0.247 n=10+10) RegexpMatchEasy0_32-4 69.5ns ± 4% 68.6ns ± 2% ~ (p=0.171 n=10+10) RegexpMatchEasy0_1K-4 165ns ± 3% 162ns ± 3% ~ (p=0.137 n=10+10) RegexpMatchEasy1_32-4 65.7ns ± 6% 64.4ns ± 2% -2.02% (p=0.037 n=10+10) RegexpMatchEasy1_1K-4 278ns ± 2% 279ns ± 3% ~ (p=0.991 n=8+9) RegexpMatchMedium_32-4 99.3ns ± 3% 98.5ns ± 4% ~ (p=0.457 n=10+9) RegexpMatchMedium_1K-4 30.1µs ± 1% 30.4µs ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 1.40µs ± 2% 1.41µs ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 42.5µs ± 1% 41.5µs ± 3% -2.13% (p=0.002 n=8+9) Revcomp-4 332ms ± 4% 328ms ± 5% ~ (p=0.720 n=9+10) Template-4 48.3ms ± 2% 49.6ms ± 3% +2.56% (p=0.002 n=8+10) TimeParse-4 252ns ± 2% 249ns ± 3% ~ (p=0.116 n=9+10) TimeFormat-4 262ns ± 4% 252ns ± 3% -4.01% (p=0.000 n=9+10) name old speed new speed delta GobDecode-4 145MB/s ± 3% 146MB/s ± 3% ~ (p=0.436 n=10+10) GobEncode-4 166MB/s ± 5% 172MB/s ± 2% +3.28% (p=0.001 n=9+10) Gzip-4 98.6MB/s ± 4% 100.4MB/s ± 3% ~ (p=0.123 n=10+10) Gunzip-4 639MB/s ± 3% 645MB/s ± 3% ~ (p=0.481 n=10+10) JSONEncode-4 185MB/s ± 8% 189MB/s ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 46.0MB/s ± 9% 47.0MB/s ± 2% +2.21% (p=0.046 n=9+10) GoParse-4 20.1MB/s ± 9% 20.6MB/s ± 2% ~ (p=0.239 n=10+10) RegexpMatchEasy0_32-4 460MB/s ± 4% 467MB/s ± 2% ~ (p=0.165 n=10+10) RegexpMatchEasy0_1K-4 6.19GB/s ± 3% 6.28GB/s ± 3% ~ (p=0.165 n=10+10) RegexpMatchEasy1_32-4 487MB/s ± 5% 497MB/s ± 2% +2.00% (p=0.043 n=10+10) RegexpMatchEasy1_1K-4 3.67GB/s ± 2% 3.67GB/s ± 3% ~ (p=0.963 n=8+9) RegexpMatchMedium_32-4 10.1MB/s ± 3% 10.1MB/s ± 4% ~ (p=0.435 n=10+9) RegexpMatchMedium_1K-4 34.0MB/s ± 1% 33.7MB/s ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 22.9MB/s ± 2% 22.7MB/s ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 24.0MB/s ± 3% 24.7MB/s ± 3% +2.64% (p=0.001 n=9+9) Revcomp-4 766MB/s ± 4% 775MB/s ± 5% ~ (p=0.720 n=9+10) Template-4 40.2MB/s ± 2% 39.2MB/s ± 3% -2.47% (p=0.002 n=8+10) The rules match ~1800 times during all.bash. Fixes #18943 Change-Id: I64be1ada34e89c486dfd935bf429b35652117ed4 Reviewed-on: https://go-review.googlesource.com/94766 Run-TryBot: Giovanni Bajo <rasky@develer.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-02-17 05:54:03 -07:00
/************************************
* 64-bit instructions
************************************/
func bitcheck64_constleft(a uint64) (n int) {
// amd64:"BTQ\t[$]63"
if a&(1<<63) != 0 {
return 1
}
// amd64:"BTQ\t[$]60"
if a&(1<<60) != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&(1<<0) != 0 {
return 1
}
return 0
}
func bitcheck64_constright(a [8]uint64) (n int) {
// amd64:"BTQ\t[$]63"
if (a[0]>>63)&1 != 0 {
return 1
}
// amd64:"BTQ\t[$]63"
if a[1]>>63 != 0 {
return 1
}
// amd64:"BTQ\t[$]63"
if a[2]>>63 == 0 {
return 1
}
// amd64:"BTQ\t[$]60"
if (a[3]>>60)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]1"
if (a[4]>>1)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]0"
if (a[5]>>0)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]7"
if (a[6]>>5)&4 == 0 {
return 1
}
return 0
}
func bitcheck64_var(a, b uint64) (n int) {
// amd64:"BTQ"
if a&(1<<(b&63)) != 0 {
return 1
}
// amd64:"BTQ",-"BT.\t[$]0"
if (b>>(a&63))&1 != 0 {
return 1
}
return 0
}
func bitcheck64_mask(a uint64) (n int) {
// amd64:"BTQ\t[$]63"
if a&0x8000000000000000 != 0 {
return 1
}
// amd64:"BTQ\t[$]59"
if a&0x800000000000000 != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&0x1 != 0 {
return 1
}
return 0
}
func biton64(a, b uint64) (n uint64) {
// amd64:"BTSQ"
n += b | (1 << (a & 63))
// amd64:"BTSQ\t[$]63"
n += a | (1 << 63)
// amd64:"BTSQ\t[$]60"
n += a | (1 << 60)
// amd64:"ORQ\t[$]1"
n += a | (1 << 0)
return n
}
func bitoff64(a, b uint64) (n uint64) {
// amd64:"BTRQ"
n += b &^ (1 << (a & 63))
// amd64:"BTRQ\t[$]63"
n += a &^ (1 << 63)
// amd64:"BTRQ\t[$]60"
n += a &^ (1 << 60)
// amd64:"ANDQ\t[$]-2"
n += a &^ (1 << 0)
return n
}
func bitcompl64(a, b uint64) (n uint64) {
// amd64:"BTCQ"
n += b ^ (1 << (a & 63))
// amd64:"BTCQ\t[$]63"
n += a ^ (1 << 63)
// amd64:"BTCQ\t[$]60"
n += a ^ (1 << 60)
// amd64:"XORQ\t[$]1"
n += a ^ (1 << 0)
return n
}
/************************************
* 32-bit instructions
************************************/
func bitcheck32_constleft(a uint32) (n int) {
// amd64:"BTL\t[$]31"
if a&(1<<31) != 0 {
return 1
}
// amd64:"BTL\t[$]28"
if a&(1<<28) != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&(1<<0) != 0 {
return 1
}
return 0
}
func bitcheck32_constright(a [8]uint32) (n int) {
// amd64:"BTL\t[$]31"
if (a[0]>>31)&1 != 0 {
return 1
}
// amd64:"BTL\t[$]31"
if a[1]>>31 != 0 {
return 1
}
// amd64:"BTL\t[$]31"
if a[2]>>31 == 0 {
return 1
}
// amd64:"BTL\t[$]28"
if (a[3]>>28)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]1"
if (a[4]>>1)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]0"
if (a[5]>>0)&1 == 0 {
return 1
}
cmd/compile: add patterns for bit set/clear/complement on amd64 This patch completes implementation of BT(Q|L), and adds support for BT(S|R|C)(Q|L). Example of code changes from time.(*Time).addSec: if t.wall&hasMonotonic != 0 { 0x1073465 488b08 MOVQ 0(AX), CX 0x1073468 4889ca MOVQ CX, DX 0x107346b 48c1e93f SHRQ $0x3f, CX 0x107346f 48c1e13f SHLQ $0x3f, CX 0x1073473 48f7c1ffffffff TESTQ $-0x1, CX 0x107347a 746b JE 0x10734e7 if t.wall&hasMonotonic != 0 { 0x1073435 488b08 MOVQ 0(AX), CX 0x1073438 480fbae13f BTQ $0x3f, CX 0x107343d 7363 JAE 0x10734a2 Another example: t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x10734c8 4881e1ffffff3f ANDQ $0x3fffffff, CX 0x10734cf 48c1e61e SHLQ $0x1e, SI 0x10734d3 4809ce ORQ CX, SI 0x10734d6 48b90000000000000080 MOVQ $0x8000000000000000, CX 0x10734e0 4809f1 ORQ SI, CX 0x10734e3 488908 MOVQ CX, 0(AX) t.wall = t.wall&nsecMask | uint64(dsec)<<nsecShift | hasMonotonic 0x107348b 4881e2ffffff3f ANDQ $0x3fffffff, DX 0x1073492 48c1e61e SHLQ $0x1e, SI 0x1073496 4809f2 ORQ SI, DX 0x1073499 480fbaea3f BTSQ $0x3f, DX 0x107349e 488910 MOVQ DX, 0(AX) Go1 benchmarks seem unaffected, and I would be surprised otherwise: name old time/op new time/op delta BinaryTree17-4 2.64s ± 4% 2.56s ± 9% -2.92% (p=0.008 n=9+9) Fannkuch11-4 2.90s ± 1% 2.95s ± 3% +1.76% (p=0.010 n=10+9) FmtFprintfEmpty-4 35.3ns ± 1% 34.5ns ± 2% -2.34% (p=0.004 n=9+8) FmtFprintfString-4 57.0ns ± 1% 58.4ns ± 5% +2.52% (p=0.029 n=9+10) FmtFprintfInt-4 59.8ns ± 3% 59.8ns ± 6% ~ (p=0.565 n=10+10) FmtFprintfIntInt-4 93.9ns ± 3% 91.2ns ± 5% -2.94% (p=0.014 n=10+9) FmtFprintfPrefixedInt-4 107ns ± 6% 104ns ± 6% ~ (p=0.099 n=10+10) FmtFprintfFloat-4 187ns ± 3% 188ns ± 3% ~ (p=0.505 n=10+9) FmtManyArgs-4 410ns ± 1% 415ns ± 6% ~ (p=0.649 n=8+10) GobDecode-4 5.30ms ± 3% 5.27ms ± 3% ~ (p=0.436 n=10+10) GobEncode-4 4.62ms ± 5% 4.47ms ± 2% -3.24% (p=0.001 n=9+10) Gzip-4 197ms ± 4% 193ms ± 3% ~ (p=0.123 n=10+10) Gunzip-4 30.4ms ± 3% 30.1ms ± 3% ~ (p=0.481 n=10+10) HTTPClientServer-4 76.3µs ± 1% 76.0µs ± 1% ~ (p=0.236 n=8+9) JSONEncode-4 10.5ms ± 9% 10.3ms ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 42.3ms ±10% 41.3ms ± 2% ~ (p=0.053 n=9+10) Mandelbrot200-4 3.80ms ± 2% 3.72ms ± 2% -2.15% (p=0.001 n=9+10) GoParse-4 2.88ms ±10% 2.81ms ± 2% ~ (p=0.247 n=10+10) RegexpMatchEasy0_32-4 69.5ns ± 4% 68.6ns ± 2% ~ (p=0.171 n=10+10) RegexpMatchEasy0_1K-4 165ns ± 3% 162ns ± 3% ~ (p=0.137 n=10+10) RegexpMatchEasy1_32-4 65.7ns ± 6% 64.4ns ± 2% -2.02% (p=0.037 n=10+10) RegexpMatchEasy1_1K-4 278ns ± 2% 279ns ± 3% ~ (p=0.991 n=8+9) RegexpMatchMedium_32-4 99.3ns ± 3% 98.5ns ± 4% ~ (p=0.457 n=10+9) RegexpMatchMedium_1K-4 30.1µs ± 1% 30.4µs ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 1.40µs ± 2% 1.41µs ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 42.5µs ± 1% 41.5µs ± 3% -2.13% (p=0.002 n=8+9) Revcomp-4 332ms ± 4% 328ms ± 5% ~ (p=0.720 n=9+10) Template-4 48.3ms ± 2% 49.6ms ± 3% +2.56% (p=0.002 n=8+10) TimeParse-4 252ns ± 2% 249ns ± 3% ~ (p=0.116 n=9+10) TimeFormat-4 262ns ± 4% 252ns ± 3% -4.01% (p=0.000 n=9+10) name old speed new speed delta GobDecode-4 145MB/s ± 3% 146MB/s ± 3% ~ (p=0.436 n=10+10) GobEncode-4 166MB/s ± 5% 172MB/s ± 2% +3.28% (p=0.001 n=9+10) Gzip-4 98.6MB/s ± 4% 100.4MB/s ± 3% ~ (p=0.123 n=10+10) Gunzip-4 639MB/s ± 3% 645MB/s ± 3% ~ (p=0.481 n=10+10) JSONEncode-4 185MB/s ± 8% 189MB/s ± 3% ~ (p=0.280 n=10+10) JSONDecode-4 46.0MB/s ± 9% 47.0MB/s ± 2% +2.21% (p=0.046 n=9+10) GoParse-4 20.1MB/s ± 9% 20.6MB/s ± 2% ~ (p=0.239 n=10+10) RegexpMatchEasy0_32-4 460MB/s ± 4% 467MB/s ± 2% ~ (p=0.165 n=10+10) RegexpMatchEasy0_1K-4 6.19GB/s ± 3% 6.28GB/s ± 3% ~ (p=0.165 n=10+10) RegexpMatchEasy1_32-4 487MB/s ± 5% 497MB/s ± 2% +2.00% (p=0.043 n=10+10) RegexpMatchEasy1_1K-4 3.67GB/s ± 2% 3.67GB/s ± 3% ~ (p=0.963 n=8+9) RegexpMatchMedium_32-4 10.1MB/s ± 3% 10.1MB/s ± 4% ~ (p=0.435 n=10+9) RegexpMatchMedium_1K-4 34.0MB/s ± 1% 33.7MB/s ± 2% ~ (p=0.173 n=8+10) RegexpMatchHard_32-4 22.9MB/s ± 2% 22.7MB/s ± 4% ~ (p=0.565 n=10+10) RegexpMatchHard_1K-4 24.0MB/s ± 3% 24.7MB/s ± 3% +2.64% (p=0.001 n=9+9) Revcomp-4 766MB/s ± 4% 775MB/s ± 5% ~ (p=0.720 n=9+10) Template-4 40.2MB/s ± 2% 39.2MB/s ± 3% -2.47% (p=0.002 n=8+10) The rules match ~1800 times during all.bash. Fixes #18943 Change-Id: I64be1ada34e89c486dfd935bf429b35652117ed4 Reviewed-on: https://go-review.googlesource.com/94766 Run-TryBot: Giovanni Bajo <rasky@develer.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-02-17 05:54:03 -07:00
// amd64:"BTL\t[$]7"
if (a[6]>>5)&4 == 0 {
return 1
}
return 0
}
func bitcheck32_var(a, b uint32) (n int) {
// amd64:"BTL"
if a&(1<<(b&31)) != 0 {
return 1
}
// amd64:"BTL",-"BT.\t[$]0"
if (b>>(a&31))&1 != 0 {
return 1
}
return 0
}
func bitcheck32_mask(a uint32) (n int) {
// amd64:"BTL\t[$]31"
if a&0x80000000 != 0 {
return 1
}
// amd64:"BTL\t[$]27"
if a&0x8000000 != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&0x1 != 0 {
return 1
}
return 0
}
func biton32(a, b uint32) (n uint32) {
// amd64:"BTSL"
n += b | (1 << (a & 31))
// amd64:"BTSL\t[$]31"
n += a | (1 << 31)
// amd64:"BTSL\t[$]28"
n += a | (1 << 28)
// amd64:"ORL\t[$]1"
n += a | (1 << 0)
return n
}
func bitoff32(a, b uint32) (n uint32) {
// amd64:"BTRL"
n += b &^ (1 << (a & 31))
// amd64:"BTRL\t[$]31"
n += a &^ (1 << 31)
// amd64:"BTRL\t[$]28"
n += a &^ (1 << 28)
// amd64:"ANDL\t[$]-2"
n += a &^ (1 << 0)
return n
}
func bitcompl32(a, b uint32) (n uint32) {
// amd64:"BTCL"
n += b ^ (1 << (a & 31))
// amd64:"BTCL\t[$]31"
n += a ^ (1 << 31)
// amd64:"BTCL\t[$]28"
n += a ^ (1 << 28)
// amd64:"XORL\t[$]1"
n += a ^ (1 << 0)
return n
}
cmd/compile: fix long RMW bit operations on AMD64 Under certain circumstances, the existing rules for bit operations can produce code that writes beyond its intended bounds. For example, consider the following code: func repro(b []byte, addr, bit int32) { _ = b[3] v := uint32(b[0]) | uint32(b[1])<<8 | uint32(b[2])<<16 | uint32(b[3])<<24 | 1<<(bit&31) b[0] = byte(v) b[1] = byte(v >> 8) b[2] = byte(v >> 16) b[3] = byte(v >> 24) } Roughly speaking: 1. The expression `1 << (bit & 31)` is rewritten into `(SHLL 1 bit)` 2. The expression `uint32(b[0]) | uint32(b[1])<<8 | uint32(b[2])<<16 | uint32(b[3])<<24` is rewritten into `(MOVLload &b[0])` 3. The statements `b[0] = byte(v) ... b[3] = byte(v >> 24)` are rewritten into `(MOVLstore &b[0], v)` 4. `(ORL (SHLL 1, bit) (MOVLload &b[0]))` is rewritten into `(BTSL (MOVLload &b[0]) bit)`. This is a valid transformation because the destination is a register: in this case, the bit offset is masked by the number of bits in the destination register. This is identical to the masking performed by `SHL`. 5. `(MOVLstore &b[0] (BTSL (MOVLload &b[0]) bit))` is rewritten into `(BTSLmodify &b[0] bit)`. This is an invalid transformation because the destination is memory: in this case, the bit offset is not masked, and the chosen instruction may write outside its intended 32-bit location. These changes fix the invalid rewrite performed in step (5) by explicitly maksing the bit offset operand to `BT(S|R|C)(L|Q)modify`. In the example above, the adjusted rules produce `(BTSLmodify &b[0] (ANDLconst [31] bit))` in step (5). These changes also add several new rules to rewrite bit sets, toggles, and clears that are rooted at `(OR|XOR|AND)(L|Q)modify` operators into appropriate `BT(S|R|C)(L|Q)modify` operators. These rules catch cases where `MOV(L|Q)store ((OR|XOR|AND)(L|Q) ...)` is rewritten to `(OR|XOR|AND)(L|Q)modify` before the `(OR|XOR|AND)(L|Q) ...` can be rewritten to `BT(S|R|C)(L|Q) ...`. Overall, compilecmp reports small improvements in code size on darwin/amd64 when the changes to the compiler itself are exlcuded: file before after Δ % runtime.s 536464 536412 -52 -0.010% bytes.s 32629 32593 -36 -0.110% strings.s 44565 44529 -36 -0.081% os/signal.s 7967 7959 -8 -0.100% cmd/vendor/golang.org/x/sys/unix.s 81686 81678 -8 -0.010% math/big.s 188235 188253 +18 +0.010% cmd/link/internal/loader.s 89295 89056 -239 -0.268% cmd/link/internal/ld.s 633551 633232 -319 -0.050% cmd/link/internal/arm.s 18934 18928 -6 -0.032% cmd/link/internal/arm64.s 31814 31801 -13 -0.041% cmd/link/internal/riscv64.s 7347 7345 -2 -0.027% cmd/compile/internal/ssa.s 4029173 4033066 +3893 +0.097% total 21298280 21301472 +3192 +0.015% Change-Id: I2e560548b515865129e1724e150e30540e9d29ce GitHub-Last-Rev: 9a42bd29a55b3917651aecab6932074df96535ae GitHub-Pull-Request: golang/go#45242 Reviewed-on: https://go-review.googlesource.com/c/go/+/304869 Reviewed-by: Keith Randall <khr@golang.org> Trust: Josh Bleecher Snyder <josharian@gmail.com>
2021-03-26 11:48:42 -06:00
// check direct operation on memory with constant and shifted constant sources
func bitOpOnMem(a []uint32, b, c, d uint32) {
// amd64:`ANDL\s[$]200,\s\([A-Z][A-Z0-9]+\)`
cmd/compile: optimize AMD64 with more read-modify-write operations 6 more operations which do read-modify-write with a constant source operand are added. 1. The total size of pkg/linux_amd64 decreases about 3KB, excluding cmd/compile. 2. The go1 benckmark shows a slight improvement. name old time/op new time/op delta BinaryTree17-4 2.61s ± 4% 2.67s ± 2% +2.26% (p=0.000 n=30+29) Fannkuch11-4 2.39s ± 2% 2.32s ± 2% -2.67% (p=0.000 n=30+30) FmtFprintfEmpty-4 44.0ns ± 4% 41.7ns ± 4% -5.15% (p=0.000 n=30+30) FmtFprintfString-4 74.2ns ± 4% 72.3ns ± 4% -2.59% (p=0.000 n=30+30) FmtFprintfInt-4 81.7ns ± 3% 78.8ns ± 4% -3.54% (p=0.000 n=27+30) FmtFprintfIntInt-4 130ns ± 4% 124ns ± 5% -4.60% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 154ns ± 3% 152ns ± 3% -1.13% (p=0.012 n=30+30) FmtFprintfFloat-4 215ns ± 4% 212ns ± 5% -1.56% (p=0.002 n=30+30) FmtManyArgs-4 522ns ± 3% 512ns ± 3% -1.84% (p=0.001 n=30+30) GobDecode-4 6.42ms ± 5% 6.49ms ± 7% ~ (p=0.070 n=30+30) GobEncode-4 6.07ms ± 8% 5.98ms ± 8% ~ (p=0.150 n=30+30) Gzip-4 236ms ± 4% 223ms ± 4% -5.57% (p=0.000 n=30+30) Gunzip-4 37.4ms ± 3% 36.7ms ± 4% -2.03% (p=0.000 n=30+30) HTTPClientServer-4 58.7µs ± 1% 58.5µs ± 2% -0.37% (p=0.018 n=30+29) JSONEncode-4 12.0ms ± 4% 12.1ms ± 3% ~ (p=0.112 n=30+30) JSONDecode-4 54.5ms ± 3% 55.5ms ± 4% +1.80% (p=0.006 n=30+30) Mandelbrot200-4 3.78ms ± 4% 3.78ms ± 4% ~ (p=0.173 n=30+30) GoParse-4 3.16ms ± 5% 3.22ms ± 5% +1.75% (p=0.010 n=30+30) RegexpMatchEasy0_32-4 76.6ns ± 1% 75.9ns ± 3% ~ (p=0.672 n=25+30) RegexpMatchEasy0_1K-4 252ns ± 3% 253ns ± 3% +0.57% (p=0.027 n=30+30) RegexpMatchEasy1_32-4 69.8ns ± 4% 70.2ns ± 6% ~ (p=0.539 n=30+30) RegexpMatchEasy1_1K-4 374ns ± 3% 373ns ± 5% ~ (p=0.263 n=30+30) RegexpMatchMedium_32-4 107ns ± 4% 109ns ± 3% ~ (p=0.067 n=30+30) RegexpMatchMedium_1K-4 33.9µs ± 5% 34.1µs ± 4% ~ (p=0.297 n=30+30) RegexpMatchHard_32-4 1.54µs ± 3% 1.56µs ± 4% +1.43% (p=0.002 n=30+30) RegexpMatchHard_1K-4 46.6µs ± 3% 47.0µs ± 3% ~ (p=0.055 n=30+30) Revcomp-4 411ms ± 6% 407ms ± 6% ~ (p=0.219 n=30+30) Template-4 66.8ms ± 3% 64.8ms ± 5% -3.01% (p=0.000 n=30+30) TimeParse-4 312ns ± 2% 319ns ± 3% +2.50% (p=0.000 n=30+30) TimeFormat-4 296ns ± 5% 299ns ± 3% +0.93% (p=0.005 n=30+30) [Geo mean] 47.5µs 47.1µs -0.75% name old speed new speed delta GobDecode-4 120MB/s ± 5% 118MB/s ± 6% ~ (p=0.072 n=30+30) GobEncode-4 127MB/s ± 8% 129MB/s ± 8% ~ (p=0.150 n=30+30) Gzip-4 82.1MB/s ± 4% 87.0MB/s ± 4% +5.90% (p=0.000 n=30+30) Gunzip-4 519MB/s ± 4% 529MB/s ± 4% +2.07% (p=0.001 n=30+30) JSONEncode-4 162MB/s ± 4% 161MB/s ± 3% ~ (p=0.110 n=30+30) JSONDecode-4 35.6MB/s ± 3% 35.0MB/s ± 4% -1.77% (p=0.007 n=30+30) GoParse-4 18.3MB/s ± 4% 18.0MB/s ± 4% -1.72% (p=0.009 n=30+30) RegexpMatchEasy0_32-4 418MB/s ± 1% 422MB/s ± 3% ~ (p=0.645 n=25+30) RegexpMatchEasy0_1K-4 4.06GB/s ± 3% 4.04GB/s ± 3% -0.57% (p=0.033 n=30+30) RegexpMatchEasy1_32-4 459MB/s ± 4% 456MB/s ± 6% ~ (p=0.530 n=30+30) RegexpMatchEasy1_1K-4 2.73GB/s ± 3% 2.75GB/s ± 5% ~ (p=0.279 n=30+30) RegexpMatchMedium_32-4 9.28MB/s ± 5% 9.18MB/s ± 4% ~ (p=0.086 n=30+30) RegexpMatchMedium_1K-4 30.2MB/s ± 4% 30.0MB/s ± 4% ~ (p=0.300 n=30+30) RegexpMatchHard_32-4 20.8MB/s ± 3% 20.5MB/s ± 4% -1.41% (p=0.002 n=30+30) RegexpMatchHard_1K-4 22.0MB/s ± 3% 21.8MB/s ± 3% ~ (p=0.051 n=30+30) Revcomp-4 619MB/s ± 7% 625MB/s ± 7% ~ (p=0.219 n=30+30) Template-4 29.0MB/s ± 3% 29.9MB/s ± 4% +3.11% (p=0.000 n=30+30) [Geo mean] 123MB/s 123MB/s +0.28% Change-Id: I850652cfd53329c1af804b7f57f4393d8097bb0d Reviewed-on: https://go-review.googlesource.com/121135 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
2018-06-26 20:46:17 -06:00
a[0] &= 200
// amd64:`ORL\s[$]220,\s4\([A-Z][A-Z0-9]+\)`
cmd/compile: optimize AMD64 with more read-modify-write operations 6 more operations which do read-modify-write with a constant source operand are added. 1. The total size of pkg/linux_amd64 decreases about 3KB, excluding cmd/compile. 2. The go1 benckmark shows a slight improvement. name old time/op new time/op delta BinaryTree17-4 2.61s ± 4% 2.67s ± 2% +2.26% (p=0.000 n=30+29) Fannkuch11-4 2.39s ± 2% 2.32s ± 2% -2.67% (p=0.000 n=30+30) FmtFprintfEmpty-4 44.0ns ± 4% 41.7ns ± 4% -5.15% (p=0.000 n=30+30) FmtFprintfString-4 74.2ns ± 4% 72.3ns ± 4% -2.59% (p=0.000 n=30+30) FmtFprintfInt-4 81.7ns ± 3% 78.8ns ± 4% -3.54% (p=0.000 n=27+30) FmtFprintfIntInt-4 130ns ± 4% 124ns ± 5% -4.60% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 154ns ± 3% 152ns ± 3% -1.13% (p=0.012 n=30+30) FmtFprintfFloat-4 215ns ± 4% 212ns ± 5% -1.56% (p=0.002 n=30+30) FmtManyArgs-4 522ns ± 3% 512ns ± 3% -1.84% (p=0.001 n=30+30) GobDecode-4 6.42ms ± 5% 6.49ms ± 7% ~ (p=0.070 n=30+30) GobEncode-4 6.07ms ± 8% 5.98ms ± 8% ~ (p=0.150 n=30+30) Gzip-4 236ms ± 4% 223ms ± 4% -5.57% (p=0.000 n=30+30) Gunzip-4 37.4ms ± 3% 36.7ms ± 4% -2.03% (p=0.000 n=30+30) HTTPClientServer-4 58.7µs ± 1% 58.5µs ± 2% -0.37% (p=0.018 n=30+29) JSONEncode-4 12.0ms ± 4% 12.1ms ± 3% ~ (p=0.112 n=30+30) JSONDecode-4 54.5ms ± 3% 55.5ms ± 4% +1.80% (p=0.006 n=30+30) Mandelbrot200-4 3.78ms ± 4% 3.78ms ± 4% ~ (p=0.173 n=30+30) GoParse-4 3.16ms ± 5% 3.22ms ± 5% +1.75% (p=0.010 n=30+30) RegexpMatchEasy0_32-4 76.6ns ± 1% 75.9ns ± 3% ~ (p=0.672 n=25+30) RegexpMatchEasy0_1K-4 252ns ± 3% 253ns ± 3% +0.57% (p=0.027 n=30+30) RegexpMatchEasy1_32-4 69.8ns ± 4% 70.2ns ± 6% ~ (p=0.539 n=30+30) RegexpMatchEasy1_1K-4 374ns ± 3% 373ns ± 5% ~ (p=0.263 n=30+30) RegexpMatchMedium_32-4 107ns ± 4% 109ns ± 3% ~ (p=0.067 n=30+30) RegexpMatchMedium_1K-4 33.9µs ± 5% 34.1µs ± 4% ~ (p=0.297 n=30+30) RegexpMatchHard_32-4 1.54µs ± 3% 1.56µs ± 4% +1.43% (p=0.002 n=30+30) RegexpMatchHard_1K-4 46.6µs ± 3% 47.0µs ± 3% ~ (p=0.055 n=30+30) Revcomp-4 411ms ± 6% 407ms ± 6% ~ (p=0.219 n=30+30) Template-4 66.8ms ± 3% 64.8ms ± 5% -3.01% (p=0.000 n=30+30) TimeParse-4 312ns ± 2% 319ns ± 3% +2.50% (p=0.000 n=30+30) TimeFormat-4 296ns ± 5% 299ns ± 3% +0.93% (p=0.005 n=30+30) [Geo mean] 47.5µs 47.1µs -0.75% name old speed new speed delta GobDecode-4 120MB/s ± 5% 118MB/s ± 6% ~ (p=0.072 n=30+30) GobEncode-4 127MB/s ± 8% 129MB/s ± 8% ~ (p=0.150 n=30+30) Gzip-4 82.1MB/s ± 4% 87.0MB/s ± 4% +5.90% (p=0.000 n=30+30) Gunzip-4 519MB/s ± 4% 529MB/s ± 4% +2.07% (p=0.001 n=30+30) JSONEncode-4 162MB/s ± 4% 161MB/s ± 3% ~ (p=0.110 n=30+30) JSONDecode-4 35.6MB/s ± 3% 35.0MB/s ± 4% -1.77% (p=0.007 n=30+30) GoParse-4 18.3MB/s ± 4% 18.0MB/s ± 4% -1.72% (p=0.009 n=30+30) RegexpMatchEasy0_32-4 418MB/s ± 1% 422MB/s ± 3% ~ (p=0.645 n=25+30) RegexpMatchEasy0_1K-4 4.06GB/s ± 3% 4.04GB/s ± 3% -0.57% (p=0.033 n=30+30) RegexpMatchEasy1_32-4 459MB/s ± 4% 456MB/s ± 6% ~ (p=0.530 n=30+30) RegexpMatchEasy1_1K-4 2.73GB/s ± 3% 2.75GB/s ± 5% ~ (p=0.279 n=30+30) RegexpMatchMedium_32-4 9.28MB/s ± 5% 9.18MB/s ± 4% ~ (p=0.086 n=30+30) RegexpMatchMedium_1K-4 30.2MB/s ± 4% 30.0MB/s ± 4% ~ (p=0.300 n=30+30) RegexpMatchHard_32-4 20.8MB/s ± 3% 20.5MB/s ± 4% -1.41% (p=0.002 n=30+30) RegexpMatchHard_1K-4 22.0MB/s ± 3% 21.8MB/s ± 3% ~ (p=0.051 n=30+30) Revcomp-4 619MB/s ± 7% 625MB/s ± 7% ~ (p=0.219 n=30+30) Template-4 29.0MB/s ± 3% 29.9MB/s ± 4% +3.11% (p=0.000 n=30+30) [Geo mean] 123MB/s 123MB/s +0.28% Change-Id: I850652cfd53329c1af804b7f57f4393d8097bb0d Reviewed-on: https://go-review.googlesource.com/121135 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
2018-06-26 20:46:17 -06:00
a[1] |= 220
// amd64:`XORL\s[$]240,\s8\([A-Z][A-Z0-9]+\)`
cmd/compile: optimize AMD64 with more read-modify-write operations 6 more operations which do read-modify-write with a constant source operand are added. 1. The total size of pkg/linux_amd64 decreases about 3KB, excluding cmd/compile. 2. The go1 benckmark shows a slight improvement. name old time/op new time/op delta BinaryTree17-4 2.61s ± 4% 2.67s ± 2% +2.26% (p=0.000 n=30+29) Fannkuch11-4 2.39s ± 2% 2.32s ± 2% -2.67% (p=0.000 n=30+30) FmtFprintfEmpty-4 44.0ns ± 4% 41.7ns ± 4% -5.15% (p=0.000 n=30+30) FmtFprintfString-4 74.2ns ± 4% 72.3ns ± 4% -2.59% (p=0.000 n=30+30) FmtFprintfInt-4 81.7ns ± 3% 78.8ns ± 4% -3.54% (p=0.000 n=27+30) FmtFprintfIntInt-4 130ns ± 4% 124ns ± 5% -4.60% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 154ns ± 3% 152ns ± 3% -1.13% (p=0.012 n=30+30) FmtFprintfFloat-4 215ns ± 4% 212ns ± 5% -1.56% (p=0.002 n=30+30) FmtManyArgs-4 522ns ± 3% 512ns ± 3% -1.84% (p=0.001 n=30+30) GobDecode-4 6.42ms ± 5% 6.49ms ± 7% ~ (p=0.070 n=30+30) GobEncode-4 6.07ms ± 8% 5.98ms ± 8% ~ (p=0.150 n=30+30) Gzip-4 236ms ± 4% 223ms ± 4% -5.57% (p=0.000 n=30+30) Gunzip-4 37.4ms ± 3% 36.7ms ± 4% -2.03% (p=0.000 n=30+30) HTTPClientServer-4 58.7µs ± 1% 58.5µs ± 2% -0.37% (p=0.018 n=30+29) JSONEncode-4 12.0ms ± 4% 12.1ms ± 3% ~ (p=0.112 n=30+30) JSONDecode-4 54.5ms ± 3% 55.5ms ± 4% +1.80% (p=0.006 n=30+30) Mandelbrot200-4 3.78ms ± 4% 3.78ms ± 4% ~ (p=0.173 n=30+30) GoParse-4 3.16ms ± 5% 3.22ms ± 5% +1.75% (p=0.010 n=30+30) RegexpMatchEasy0_32-4 76.6ns ± 1% 75.9ns ± 3% ~ (p=0.672 n=25+30) RegexpMatchEasy0_1K-4 252ns ± 3% 253ns ± 3% +0.57% (p=0.027 n=30+30) RegexpMatchEasy1_32-4 69.8ns ± 4% 70.2ns ± 6% ~ (p=0.539 n=30+30) RegexpMatchEasy1_1K-4 374ns ± 3% 373ns ± 5% ~ (p=0.263 n=30+30) RegexpMatchMedium_32-4 107ns ± 4% 109ns ± 3% ~ (p=0.067 n=30+30) RegexpMatchMedium_1K-4 33.9µs ± 5% 34.1µs ± 4% ~ (p=0.297 n=30+30) RegexpMatchHard_32-4 1.54µs ± 3% 1.56µs ± 4% +1.43% (p=0.002 n=30+30) RegexpMatchHard_1K-4 46.6µs ± 3% 47.0µs ± 3% ~ (p=0.055 n=30+30) Revcomp-4 411ms ± 6% 407ms ± 6% ~ (p=0.219 n=30+30) Template-4 66.8ms ± 3% 64.8ms ± 5% -3.01% (p=0.000 n=30+30) TimeParse-4 312ns ± 2% 319ns ± 3% +2.50% (p=0.000 n=30+30) TimeFormat-4 296ns ± 5% 299ns ± 3% +0.93% (p=0.005 n=30+30) [Geo mean] 47.5µs 47.1µs -0.75% name old speed new speed delta GobDecode-4 120MB/s ± 5% 118MB/s ± 6% ~ (p=0.072 n=30+30) GobEncode-4 127MB/s ± 8% 129MB/s ± 8% ~ (p=0.150 n=30+30) Gzip-4 82.1MB/s ± 4% 87.0MB/s ± 4% +5.90% (p=0.000 n=30+30) Gunzip-4 519MB/s ± 4% 529MB/s ± 4% +2.07% (p=0.001 n=30+30) JSONEncode-4 162MB/s ± 4% 161MB/s ± 3% ~ (p=0.110 n=30+30) JSONDecode-4 35.6MB/s ± 3% 35.0MB/s ± 4% -1.77% (p=0.007 n=30+30) GoParse-4 18.3MB/s ± 4% 18.0MB/s ± 4% -1.72% (p=0.009 n=30+30) RegexpMatchEasy0_32-4 418MB/s ± 1% 422MB/s ± 3% ~ (p=0.645 n=25+30) RegexpMatchEasy0_1K-4 4.06GB/s ± 3% 4.04GB/s ± 3% -0.57% (p=0.033 n=30+30) RegexpMatchEasy1_32-4 459MB/s ± 4% 456MB/s ± 6% ~ (p=0.530 n=30+30) RegexpMatchEasy1_1K-4 2.73GB/s ± 3% 2.75GB/s ± 5% ~ (p=0.279 n=30+30) RegexpMatchMedium_32-4 9.28MB/s ± 5% 9.18MB/s ± 4% ~ (p=0.086 n=30+30) RegexpMatchMedium_1K-4 30.2MB/s ± 4% 30.0MB/s ± 4% ~ (p=0.300 n=30+30) RegexpMatchHard_32-4 20.8MB/s ± 3% 20.5MB/s ± 4% -1.41% (p=0.002 n=30+30) RegexpMatchHard_1K-4 22.0MB/s ± 3% 21.8MB/s ± 3% ~ (p=0.051 n=30+30) Revcomp-4 619MB/s ± 7% 625MB/s ± 7% ~ (p=0.219 n=30+30) Template-4 29.0MB/s ± 3% 29.9MB/s ± 4% +3.11% (p=0.000 n=30+30) [Geo mean] 123MB/s 123MB/s +0.28% Change-Id: I850652cfd53329c1af804b7f57f4393d8097bb0d Reviewed-on: https://go-review.googlesource.com/121135 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
2018-06-26 20:46:17 -06:00
a[2] ^= 240
}
func bitcheckMostNegative(b uint8) bool {
// amd64:"TESTB"
return b&0x80 == 0x80
}
// Check AND masking on arm64 (Issue #19857)
func and_mask_1(a uint64) uint64 {
// arm64:`AND\t`
return a & ((1 << 63) - 1)
}
func and_mask_2(a uint64) uint64 {
// arm64:`AND\t`
return a & (1 << 63)
}
cmd/compile: optimize arm's bit operation BFC (Bit Field Clear) was introduced in ARMv7, which can simplify ANDconst and BICconst. And this CL implements that optimization. 1. The total size of pkg/android_arm decreases about 3KB, excluding cmd/compile/. 2. There is no regression in the go1 benchmark result, and some cases (FmtFprintfEmpty-4 and RegexpMatchMedium_32-4) even get slight improvement. name old time/op new time/op delta BinaryTree17-4 25.3s ± 1% 25.2s ± 1% ~ (p=0.072 n=30+29) Fannkuch11-4 13.3s ± 0% 13.3s ± 0% +0.13% (p=0.000 n=30+26) FmtFprintfEmpty-4 407ns ± 0% 394ns ± 0% -3.19% (p=0.000 n=26+28) FmtFprintfString-4 664ns ± 0% 662ns ± 0% -0.22% (p=0.000 n=30+30) FmtFprintfInt-4 712ns ± 0% 706ns ± 0% -0.79% (p=0.000 n=30+30) FmtFprintfIntInt-4 1.06µs ± 0% 1.05µs ± 0% -0.38% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.16µs ± 0% 1.16µs ± 0% -0.13% (p=0.000 n=30+29) FmtFprintfFloat-4 2.24µs ± 0% 2.23µs ± 0% -0.51% (p=0.000 n=29+21) FmtManyArgs-4 4.09µs ± 0% 4.06µs ± 0% -0.83% (p=0.000 n=28+30) GobDecode-4 55.0ms ± 5% 55.4ms ± 5% ~ (p=0.307 n=30+30) GobEncode-4 51.2ms ± 1% 51.9ms ± 1% +1.23% (p=0.000 n=29+30) Gzip-4 2.64s ± 0% 2.60s ± 0% -1.35% (p=0.000 n=30+29) Gunzip-4 309ms ± 0% 308ms ± 0% -0.27% (p=0.000 n=30+30) HTTPClientServer-4 1.03ms ± 5% 1.02ms ± 4% ~ (p=0.117 n=30+29) JSONEncode-4 101ms ± 2% 101ms ± 2% ~ (p=0.338 n=29+29) JSONDecode-4 383ms ± 2% 382ms ± 2% ~ (p=0.751 n=26+30) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% -0.10% (p=0.000 n=29+29) GoParse-4 22.6ms ± 0% 22.5ms ± 0% -0.39% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 761ns ± 0% 750ns ± 0% -1.47% (p=0.000 n=26+29) RegexpMatchEasy0_1K-4 4.33µs ± 0% 4.34µs ± 0% +0.27% (p=0.000 n=25+28) RegexpMatchEasy1_32-4 809ns ± 0% 795ns ± 0% -1.74% (p=0.000 n=27+25) RegexpMatchEasy1_1K-4 5.54µs ± 0% 5.53µs ± 0% -0.18% (p=0.000 n=29+29) RegexpMatchMedium_32-4 1.11µs ± 0% 1.08µs ± 0% -2.78% (p=0.000 n=27+29) RegexpMatchMedium_1K-4 255µs ± 0% 255µs ± 0% -0.02% (p=0.029 n=30+30) RegexpMatchHard_32-4 14.7µs ± 0% 14.7µs ± 0% -0.28% (p=0.000 n=30+29) RegexpMatchHard_1K-4 439µs ± 0% 439µs ± 0% ~ (p=0.907 n=23+27) Revcomp-4 41.9ms ± 1% 41.9ms ± 1% ~ (p=0.230 n=28+30) Template-4 522ms ± 1% 528ms ± 1% +1.25% (p=0.000 n=30+30) TimeParse-4 3.34µs ± 0% 3.35µs ± 0% +0.23% (p=0.000 n=30+27) TimeFormat-4 6.06µs ± 0% 6.13µs ± 0% +1.08% (p=0.000 n=29+29) [Geo mean] 384µs 382µs -0.37% name old speed new speed delta GobDecode-4 14.0MB/s ± 5% 13.9MB/s ± 5% ~ (p=0.308 n=30+30) GobEncode-4 15.0MB/s ± 1% 14.8MB/s ± 1% -1.22% (p=0.000 n=29+30) Gzip-4 7.36MB/s ± 0% 7.46MB/s ± 0% +1.35% (p=0.000 n=30+30) Gunzip-4 62.8MB/s ± 0% 63.0MB/s ± 0% +0.27% (p=0.000 n=30+30) JSONEncode-4 19.2MB/s ± 2% 19.2MB/s ± 2% ~ (p=0.312 n=29+29) JSONDecode-4 5.05MB/s ± 3% 5.08MB/s ± 2% ~ (p=0.356 n=29+30) GoParse-4 2.56MB/s ± 0% 2.57MB/s ± 0% +0.39% (p=0.000 n=23+27) RegexpMatchEasy0_32-4 42.0MB/s ± 0% 42.6MB/s ± 0% +1.50% (p=0.000 n=26+28) RegexpMatchEasy0_1K-4 236MB/s ± 0% 236MB/s ± 0% -0.27% (p=0.000 n=25+28) RegexpMatchEasy1_32-4 39.6MB/s ± 0% 40.2MB/s ± 0% +1.73% (p=0.000 n=27+27) RegexpMatchEasy1_1K-4 185MB/s ± 0% 185MB/s ± 0% +0.18% (p=0.000 n=29+29) RegexpMatchMedium_32-4 900kB/s ± 0% 920kB/s ± 0% +2.22% (p=0.000 n=29+29) RegexpMatchMedium_1K-4 4.02MB/s ± 0% 4.02MB/s ± 0% +0.07% (p=0.004 n=30+27) RegexpMatchHard_32-4 2.17MB/s ± 0% 2.18MB/s ± 0% +0.46% (p=0.000 n=30+26) RegexpMatchHard_1K-4 2.33MB/s ± 0% 2.33MB/s ± 0% ~ (all equal) Revcomp-4 60.6MB/s ± 1% 60.7MB/s ± 1% ~ (p=0.207 n=28+30) Template-4 3.72MB/s ± 1% 3.67MB/s ± 1% -1.23% (p=0.000 n=30+30) [Geo mean] 12.9MB/s 12.9MB/s +0.29% Change-Id: I07f497f8bb476c950dc555491d00c9066fb64a4e Reviewed-on: https://go-review.googlesource.com/134232 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-09-10 02:29:52 -06:00
func and_mask_3(a, b uint32) (uint32, uint32) {
cmd/compile: optimize ARMv7 code "AND $0xffff0000, Rx" will be encoded to 12 bytes. 1. MOVWload from the constant pool to Rtmp 2. AND Rtmp, Rx 3. a 4-byte item in the constant pool It can be simplified to 8 bytes on ARMv7, since ARMv7 has "MOVW $imm-16, Rx". 1. MOVW $0xffff, Rtmp 2. BIC Rtmp, Rx The above optimization also applies to BICconst, ADDconst and SUBconst. 1. The total size of pkg/android_arm (excluding cmd/compile) decreases about 2KB. 2. The go1 benchmark shows no regression, exlcuding noise. name old time/op new time/op delta BinaryTree17-4 25.5s ± 1% 25.2s ± 1% -0.85% (p=0.000 n=30+30) Fannkuch11-4 13.3s ± 0% 13.3s ± 0% +0.16% (p=0.000 n=24+25) FmtFprintfEmpty-4 397ns ± 0% 394ns ± 0% -0.64% (p=0.000 n=30+30) FmtFprintfString-4 679ns ± 0% 678ns ± 0% ~ (p=0.093 n=30+29) FmtFprintfInt-4 708ns ± 0% 707ns ± 0% -0.19% (p=0.000 n=27+28) FmtFprintfIntInt-4 1.05µs ± 0% 1.05µs ± 0% -0.07% (p=0.001 n=18+30) FmtFprintfPrefixedInt-4 1.16µs ± 0% 1.15µs ± 0% -0.41% (p=0.000 n=29+30) FmtFprintfFloat-4 2.26µs ± 0% 2.23µs ± 1% -1.40% (p=0.000 n=30+30) FmtManyArgs-4 3.96µs ± 0% 3.95µs ± 0% -0.29% (p=0.000 n=29+30) GobDecode-4 52.9ms ± 2% 53.4ms ± 2% +0.92% (p=0.004 n=28+30) GobEncode-4 49.7ms ± 2% 49.8ms ± 2% ~ (p=0.890 n=30+26) Gzip-4 2.61s ± 0% 2.60s ± 0% -0.36% (p=0.000 n=29+29) Gunzip-4 312ms ± 0% 311ms ± 0% -0.13% (p=0.000 n=30+28) HTTPClientServer-4 1.02ms ± 8% 1.00ms ± 7% ~ (p=0.224 n=29+26) JSONEncode-4 125ms ± 1% 124ms ± 3% -1.05% (p=0.000 n=25+30) JSONDecode-4 432ms ± 1% 436ms ± 2% ~ (p=0.277 n=26+30) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% +0.02% (p=0.001 n=28+25) GoParse-4 22.4ms ± 1% 22.3ms ± 1% -0.41% (p=0.000 n=28+28) RegexpMatchEasy0_32-4 697ns ± 0% 706ns ± 0% +1.23% (p=0.000 n=19+30) RegexpMatchEasy0_1K-4 4.27µs ± 0% 4.26µs ± 0% -0.06% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 741ns ± 0% 735ns ± 0% -0.86% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 5.49µs ± 0% 5.49µs ± 0% -0.03% (p=0.023 n=25+30) RegexpMatchMedium_32-4 1.05µs ± 2% 1.04µs ± 2% ~ (p=0.893 n=30+30) RegexpMatchMedium_1K-4 261µs ± 0% 261µs ± 0% -0.11% (p=0.000 n=29+30) RegexpMatchHard_32-4 14.9µs ± 0% 14.9µs ± 0% -0.36% (p=0.000 n=23+29) RegexpMatchHard_1K-4 446µs ± 0% 445µs ± 0% -0.17% (p=0.000 n=30+29) Revcomp-4 41.6ms ± 1% 41.7ms ± 1% +0.27% (p=0.040 n=28+30) Template-4 531ms ± 0% 532ms ± 1% ~ (p=0.059 n=30+30) TimeParse-4 3.40µs ± 0% 3.33µs ± 0% -2.02% (p=0.000 n=30+30) TimeFormat-4 6.14µs ± 0% 6.11µs ± 0% -0.45% (p=0.000 n=27+29) [Geo mean] 384µs 383µs -0.27% name old speed new speed delta GobDecode-4 14.5MB/s ± 2% 14.4MB/s ± 2% -0.90% (p=0.005 n=28+30) GobEncode-4 15.4MB/s ± 2% 15.4MB/s ± 2% ~ (p=0.741 n=30+25) Gzip-4 7.44MB/s ± 0% 7.47MB/s ± 1% +0.37% (p=0.000 n=25+30) Gunzip-4 62.3MB/s ± 0% 62.4MB/s ± 0% +0.13% (p=0.000 n=30+28) JSONEncode-4 15.5MB/s ± 1% 15.6MB/s ± 3% +1.07% (p=0.000 n=25+30) JSONDecode-4 4.48MB/s ± 0% 4.46MB/s ± 2% ~ (p=0.655 n=23+30) GoParse-4 2.58MB/s ± 1% 2.59MB/s ± 1% +0.42% (p=0.000 n=28+29) RegexpMatchEasy0_32-4 45.9MB/s ± 0% 45.3MB/s ± 0% -1.23% (p=0.000 n=28+30) RegexpMatchEasy0_1K-4 240MB/s ± 0% 240MB/s ± 0% +0.07% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 43.2MB/s ± 0% 43.5MB/s ± 0% +0.85% (p=0.000 n=30+28) RegexpMatchEasy1_1K-4 186MB/s ± 0% 186MB/s ± 0% +0.03% (p=0.026 n=25+30) RegexpMatchMedium_32-4 955kB/s ± 2% 960kB/s ± 2% ~ (p=0.084 n=30+30) RegexpMatchMedium_1K-4 3.92MB/s ± 0% 3.93MB/s ± 0% +0.14% (p=0.000 n=29+30) RegexpMatchHard_32-4 2.14MB/s ± 0% 2.15MB/s ± 0% +0.31% (p=0.000 n=30+26) RegexpMatchHard_1K-4 2.30MB/s ± 0% 2.30MB/s ± 0% ~ (all equal) Revcomp-4 61.1MB/s ± 1% 60.9MB/s ± 1% -0.27% (p=0.039 n=28+30) Template-4 3.66MB/s ± 0% 3.65MB/s ± 1% -0.14% (p=0.045 n=30+30) [Geo mean] 12.8MB/s 12.8MB/s +0.04% Change-Id: I02370e2584b4c041fddd324c97628fd6f0c12183 Reviewed-on: https://go-review.googlesource.com/123179 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-10 19:30:32 -06:00
// arm/7:`BIC`,-`AND`
cmd/compile: optimize arm's bit operation BFC (Bit Field Clear) was introduced in ARMv7, which can simplify ANDconst and BICconst. And this CL implements that optimization. 1. The total size of pkg/android_arm decreases about 3KB, excluding cmd/compile/. 2. There is no regression in the go1 benchmark result, and some cases (FmtFprintfEmpty-4 and RegexpMatchMedium_32-4) even get slight improvement. name old time/op new time/op delta BinaryTree17-4 25.3s ± 1% 25.2s ± 1% ~ (p=0.072 n=30+29) Fannkuch11-4 13.3s ± 0% 13.3s ± 0% +0.13% (p=0.000 n=30+26) FmtFprintfEmpty-4 407ns ± 0% 394ns ± 0% -3.19% (p=0.000 n=26+28) FmtFprintfString-4 664ns ± 0% 662ns ± 0% -0.22% (p=0.000 n=30+30) FmtFprintfInt-4 712ns ± 0% 706ns ± 0% -0.79% (p=0.000 n=30+30) FmtFprintfIntInt-4 1.06µs ± 0% 1.05µs ± 0% -0.38% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 1.16µs ± 0% 1.16µs ± 0% -0.13% (p=0.000 n=30+29) FmtFprintfFloat-4 2.24µs ± 0% 2.23µs ± 0% -0.51% (p=0.000 n=29+21) FmtManyArgs-4 4.09µs ± 0% 4.06µs ± 0% -0.83% (p=0.000 n=28+30) GobDecode-4 55.0ms ± 5% 55.4ms ± 5% ~ (p=0.307 n=30+30) GobEncode-4 51.2ms ± 1% 51.9ms ± 1% +1.23% (p=0.000 n=29+30) Gzip-4 2.64s ± 0% 2.60s ± 0% -1.35% (p=0.000 n=30+29) Gunzip-4 309ms ± 0% 308ms ± 0% -0.27% (p=0.000 n=30+30) HTTPClientServer-4 1.03ms ± 5% 1.02ms ± 4% ~ (p=0.117 n=30+29) JSONEncode-4 101ms ± 2% 101ms ± 2% ~ (p=0.338 n=29+29) JSONDecode-4 383ms ± 2% 382ms ± 2% ~ (p=0.751 n=26+30) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% -0.10% (p=0.000 n=29+29) GoParse-4 22.6ms ± 0% 22.5ms ± 0% -0.39% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 761ns ± 0% 750ns ± 0% -1.47% (p=0.000 n=26+29) RegexpMatchEasy0_1K-4 4.33µs ± 0% 4.34µs ± 0% +0.27% (p=0.000 n=25+28) RegexpMatchEasy1_32-4 809ns ± 0% 795ns ± 0% -1.74% (p=0.000 n=27+25) RegexpMatchEasy1_1K-4 5.54µs ± 0% 5.53µs ± 0% -0.18% (p=0.000 n=29+29) RegexpMatchMedium_32-4 1.11µs ± 0% 1.08µs ± 0% -2.78% (p=0.000 n=27+29) RegexpMatchMedium_1K-4 255µs ± 0% 255µs ± 0% -0.02% (p=0.029 n=30+30) RegexpMatchHard_32-4 14.7µs ± 0% 14.7µs ± 0% -0.28% (p=0.000 n=30+29) RegexpMatchHard_1K-4 439µs ± 0% 439µs ± 0% ~ (p=0.907 n=23+27) Revcomp-4 41.9ms ± 1% 41.9ms ± 1% ~ (p=0.230 n=28+30) Template-4 522ms ± 1% 528ms ± 1% +1.25% (p=0.000 n=30+30) TimeParse-4 3.34µs ± 0% 3.35µs ± 0% +0.23% (p=0.000 n=30+27) TimeFormat-4 6.06µs ± 0% 6.13µs ± 0% +1.08% (p=0.000 n=29+29) [Geo mean] 384µs 382µs -0.37% name old speed new speed delta GobDecode-4 14.0MB/s ± 5% 13.9MB/s ± 5% ~ (p=0.308 n=30+30) GobEncode-4 15.0MB/s ± 1% 14.8MB/s ± 1% -1.22% (p=0.000 n=29+30) Gzip-4 7.36MB/s ± 0% 7.46MB/s ± 0% +1.35% (p=0.000 n=30+30) Gunzip-4 62.8MB/s ± 0% 63.0MB/s ± 0% +0.27% (p=0.000 n=30+30) JSONEncode-4 19.2MB/s ± 2% 19.2MB/s ± 2% ~ (p=0.312 n=29+29) JSONDecode-4 5.05MB/s ± 3% 5.08MB/s ± 2% ~ (p=0.356 n=29+30) GoParse-4 2.56MB/s ± 0% 2.57MB/s ± 0% +0.39% (p=0.000 n=23+27) RegexpMatchEasy0_32-4 42.0MB/s ± 0% 42.6MB/s ± 0% +1.50% (p=0.000 n=26+28) RegexpMatchEasy0_1K-4 236MB/s ± 0% 236MB/s ± 0% -0.27% (p=0.000 n=25+28) RegexpMatchEasy1_32-4 39.6MB/s ± 0% 40.2MB/s ± 0% +1.73% (p=0.000 n=27+27) RegexpMatchEasy1_1K-4 185MB/s ± 0% 185MB/s ± 0% +0.18% (p=0.000 n=29+29) RegexpMatchMedium_32-4 900kB/s ± 0% 920kB/s ± 0% +2.22% (p=0.000 n=29+29) RegexpMatchMedium_1K-4 4.02MB/s ± 0% 4.02MB/s ± 0% +0.07% (p=0.004 n=30+27) RegexpMatchHard_32-4 2.17MB/s ± 0% 2.18MB/s ± 0% +0.46% (p=0.000 n=30+26) RegexpMatchHard_1K-4 2.33MB/s ± 0% 2.33MB/s ± 0% ~ (all equal) Revcomp-4 60.6MB/s ± 1% 60.7MB/s ± 1% ~ (p=0.207 n=28+30) Template-4 3.72MB/s ± 1% 3.67MB/s ± 1% -1.23% (p=0.000 n=30+30) [Geo mean] 12.9MB/s 12.9MB/s +0.29% Change-Id: I07f497f8bb476c950dc555491d00c9066fb64a4e Reviewed-on: https://go-review.googlesource.com/134232 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-09-10 02:29:52 -06:00
a &= 0xffffaaaa
// arm/7:`BFC`,-`AND`,-`BIC`
b &= 0xffc003ff
return a, b
cmd/compile: optimize ARMv7 code "AND $0xffff0000, Rx" will be encoded to 12 bytes. 1. MOVWload from the constant pool to Rtmp 2. AND Rtmp, Rx 3. a 4-byte item in the constant pool It can be simplified to 8 bytes on ARMv7, since ARMv7 has "MOVW $imm-16, Rx". 1. MOVW $0xffff, Rtmp 2. BIC Rtmp, Rx The above optimization also applies to BICconst, ADDconst and SUBconst. 1. The total size of pkg/android_arm (excluding cmd/compile) decreases about 2KB. 2. The go1 benchmark shows no regression, exlcuding noise. name old time/op new time/op delta BinaryTree17-4 25.5s ± 1% 25.2s ± 1% -0.85% (p=0.000 n=30+30) Fannkuch11-4 13.3s ± 0% 13.3s ± 0% +0.16% (p=0.000 n=24+25) FmtFprintfEmpty-4 397ns ± 0% 394ns ± 0% -0.64% (p=0.000 n=30+30) FmtFprintfString-4 679ns ± 0% 678ns ± 0% ~ (p=0.093 n=30+29) FmtFprintfInt-4 708ns ± 0% 707ns ± 0% -0.19% (p=0.000 n=27+28) FmtFprintfIntInt-4 1.05µs ± 0% 1.05µs ± 0% -0.07% (p=0.001 n=18+30) FmtFprintfPrefixedInt-4 1.16µs ± 0% 1.15µs ± 0% -0.41% (p=0.000 n=29+30) FmtFprintfFloat-4 2.26µs ± 0% 2.23µs ± 1% -1.40% (p=0.000 n=30+30) FmtManyArgs-4 3.96µs ± 0% 3.95µs ± 0% -0.29% (p=0.000 n=29+30) GobDecode-4 52.9ms ± 2% 53.4ms ± 2% +0.92% (p=0.004 n=28+30) GobEncode-4 49.7ms ± 2% 49.8ms ± 2% ~ (p=0.890 n=30+26) Gzip-4 2.61s ± 0% 2.60s ± 0% -0.36% (p=0.000 n=29+29) Gunzip-4 312ms ± 0% 311ms ± 0% -0.13% (p=0.000 n=30+28) HTTPClientServer-4 1.02ms ± 8% 1.00ms ± 7% ~ (p=0.224 n=29+26) JSONEncode-4 125ms ± 1% 124ms ± 3% -1.05% (p=0.000 n=25+30) JSONDecode-4 432ms ± 1% 436ms ± 2% ~ (p=0.277 n=26+30) Mandelbrot200-4 18.4ms ± 0% 18.4ms ± 0% +0.02% (p=0.001 n=28+25) GoParse-4 22.4ms ± 1% 22.3ms ± 1% -0.41% (p=0.000 n=28+28) RegexpMatchEasy0_32-4 697ns ± 0% 706ns ± 0% +1.23% (p=0.000 n=19+30) RegexpMatchEasy0_1K-4 4.27µs ± 0% 4.26µs ± 0% -0.06% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 741ns ± 0% 735ns ± 0% -0.86% (p=0.000 n=26+30) RegexpMatchEasy1_1K-4 5.49µs ± 0% 5.49µs ± 0% -0.03% (p=0.023 n=25+30) RegexpMatchMedium_32-4 1.05µs ± 2% 1.04µs ± 2% ~ (p=0.893 n=30+30) RegexpMatchMedium_1K-4 261µs ± 0% 261µs ± 0% -0.11% (p=0.000 n=29+30) RegexpMatchHard_32-4 14.9µs ± 0% 14.9µs ± 0% -0.36% (p=0.000 n=23+29) RegexpMatchHard_1K-4 446µs ± 0% 445µs ± 0% -0.17% (p=0.000 n=30+29) Revcomp-4 41.6ms ± 1% 41.7ms ± 1% +0.27% (p=0.040 n=28+30) Template-4 531ms ± 0% 532ms ± 1% ~ (p=0.059 n=30+30) TimeParse-4 3.40µs ± 0% 3.33µs ± 0% -2.02% (p=0.000 n=30+30) TimeFormat-4 6.14µs ± 0% 6.11µs ± 0% -0.45% (p=0.000 n=27+29) [Geo mean] 384µs 383µs -0.27% name old speed new speed delta GobDecode-4 14.5MB/s ± 2% 14.4MB/s ± 2% -0.90% (p=0.005 n=28+30) GobEncode-4 15.4MB/s ± 2% 15.4MB/s ± 2% ~ (p=0.741 n=30+25) Gzip-4 7.44MB/s ± 0% 7.47MB/s ± 1% +0.37% (p=0.000 n=25+30) Gunzip-4 62.3MB/s ± 0% 62.4MB/s ± 0% +0.13% (p=0.000 n=30+28) JSONEncode-4 15.5MB/s ± 1% 15.6MB/s ± 3% +1.07% (p=0.000 n=25+30) JSONDecode-4 4.48MB/s ± 0% 4.46MB/s ± 2% ~ (p=0.655 n=23+30) GoParse-4 2.58MB/s ± 1% 2.59MB/s ± 1% +0.42% (p=0.000 n=28+29) RegexpMatchEasy0_32-4 45.9MB/s ± 0% 45.3MB/s ± 0% -1.23% (p=0.000 n=28+30) RegexpMatchEasy0_1K-4 240MB/s ± 0% 240MB/s ± 0% +0.07% (p=0.000 n=30+30) RegexpMatchEasy1_32-4 43.2MB/s ± 0% 43.5MB/s ± 0% +0.85% (p=0.000 n=30+28) RegexpMatchEasy1_1K-4 186MB/s ± 0% 186MB/s ± 0% +0.03% (p=0.026 n=25+30) RegexpMatchMedium_32-4 955kB/s ± 2% 960kB/s ± 2% ~ (p=0.084 n=30+30) RegexpMatchMedium_1K-4 3.92MB/s ± 0% 3.93MB/s ± 0% +0.14% (p=0.000 n=29+30) RegexpMatchHard_32-4 2.14MB/s ± 0% 2.15MB/s ± 0% +0.31% (p=0.000 n=30+26) RegexpMatchHard_1K-4 2.30MB/s ± 0% 2.30MB/s ± 0% ~ (all equal) Revcomp-4 61.1MB/s ± 1% 60.9MB/s ± 1% -0.27% (p=0.039 n=28+30) Template-4 3.66MB/s ± 0% 3.65MB/s ± 1% -0.14% (p=0.045 n=30+30) [Geo mean] 12.8MB/s 12.8MB/s +0.04% Change-Id: I02370e2584b4c041fddd324c97628fd6f0c12183 Reviewed-on: https://go-review.googlesource.com/123179 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-07-10 19:30:32 -06:00
}
// Check generation of arm64 BIC/EON/ORN instructions
func op_bic(x, y uint32) uint32 {
// arm64:`BIC\t`,-`AND`
return x &^ y
}
func op_eon(x, y, z uint32, a []uint32, n, m uint64) uint64 {
// arm64:`EON\t`,-`EOR`,-`MVN`
a[0] = x ^ (y ^ 0xffffffff)
// arm64:`EON\t`,-`EOR`,-`MVN`
a[1] = ^(y ^ z)
// arm64:`EON\t`,-`XOR`
a[2] = x ^ ^z
// arm64:`EON\t`,-`EOR`,-`MVN`
return n ^ (m ^ 0xffffffffffffffff)
}
func op_orn(x, y uint32) uint32 {
// arm64:`ORN\t`,-`ORR`
return x | ^y
}
// check bitsets
func bitSetPowerOf2Test(x int) bool {
// amd64:"BTL\t[$]3"
return x&8 == 8
}
func bitSetTest(x int) bool {
cmd/compile: use ANDL for small immediates We can rewrite ANDQ with an immediate fitting in 32bit with an ANDL, which is shorter to encode. Looking at Go binary itself, before the change there was: ANDL: 2337 ANDQ: 4476 After the change: ANDL: 3790 ANDQ: 3024 So we got rid of 1452 ANDQs This makes the Linux x86_64 binary 0.03% smaller. There seems to be an impact on performance. Intel Cascade Lake benchmarks (with perflock): name old time/op new time/op delta BinaryTree17-8 1.91s ± 1% 1.89s ± 1% -1.22% (p=0.000 n=21+18) Fannkuch11-8 2.34s ± 0% 2.34s ± 0% ~ (p=0.052 n=20+20) FmtFprintfEmpty-8 27.7ns ± 1% 27.4ns ± 3% ~ (p=0.497 n=21+21) FmtFprintfString-8 53.2ns ± 0% 51.5ns ± 0% -3.21% (p=0.000 n=20+19) FmtFprintfInt-8 57.3ns ± 0% 55.7ns ± 0% -2.89% (p=0.000 n=19+19) FmtFprintfIntInt-8 92.3ns ± 0% 88.4ns ± 1% -4.23% (p=0.000 n=20+21) FmtFprintfPrefixedInt-8 103ns ± 0% 103ns ± 0% +0.23% (p=0.000 n=20+21) FmtFprintfFloat-8 147ns ± 0% 148ns ± 0% +0.75% (p=0.000 n=20+21) FmtManyArgs-8 384ns ± 0% 381ns ± 0% -0.63% (p=0.000 n=21+21) GobDecode-8 3.86ms ± 1% 3.88ms ± 1% +0.52% (p=0.000 n=20+21) GobEncode-8 2.77ms ± 1% 2.77ms ± 0% ~ (p=0.078 n=21+21) Gzip-8 168ms ± 1% 168ms ± 0% +0.24% (p=0.000 n=20+20) Gunzip-8 25.1ms ± 0% 24.3ms ± 0% -3.03% (p=0.000 n=21+21) HTTPClientServer-8 61.4µs ± 8% 59.1µs ±10% ~ (p=0.088 n=20+21) JSONEncode-8 6.86ms ± 0% 6.70ms ± 0% -2.29% (p=0.000 n=20+19) JSONDecode-8 30.8ms ± 1% 30.6ms ± 1% -0.82% (p=0.000 n=20+20) Mandelbrot200-8 3.85ms ± 0% 3.85ms ± 0% ~ (p=0.191 n=16+17) GoParse-8 2.61ms ± 2% 2.60ms ± 1% ~ (p=0.561 n=21+20) RegexpMatchEasy0_32-8 48.5ns ± 2% 45.9ns ± 3% -5.26% (p=0.000 n=20+21) RegexpMatchEasy0_1K-8 139ns ± 0% 139ns ± 0% +0.27% (p=0.000 n=18+20) RegexpMatchEasy1_32-8 41.3ns ± 0% 42.1ns ± 4% +1.95% (p=0.000 n=17+21) RegexpMatchEasy1_1K-8 216ns ± 2% 216ns ± 0% +0.17% (p=0.020 n=21+19) RegexpMatchMedium_32-8 790ns ± 7% 803ns ± 8% ~ (p=0.178 n=21+21) RegexpMatchMedium_1K-8 23.5µs ± 5% 23.7µs ± 5% ~ (p=0.421 n=21+21) RegexpMatchHard_32-8 1.09µs ± 1% 1.09µs ± 1% -0.53% (p=0.000 n=19+18) RegexpMatchHard_1K-8 33.0µs ± 0% 33.0µs ± 0% ~ (p=0.610 n=21+20) Revcomp-8 348ms ± 0% 353ms ± 0% +1.38% (p=0.000 n=17+18) Template-8 42.0ms ± 1% 41.9ms ± 1% -0.30% (p=0.049 n=20+20) TimeParse-8 185ns ± 0% 185ns ± 0% ~ (p=0.387 n=20+18) TimeFormat-8 237ns ± 1% 241ns ± 1% +1.57% (p=0.000 n=21+21) [Geo mean] 35.4µs 35.2µs -0.66% name old speed new speed delta GobDecode-8 199MB/s ± 1% 198MB/s ± 1% -0.52% (p=0.000 n=20+21) GobEncode-8 277MB/s ± 1% 277MB/s ± 0% ~ (p=0.075 n=21+21) Gzip-8 116MB/s ± 1% 115MB/s ± 0% -0.25% (p=0.000 n=20+20) Gunzip-8 773MB/s ± 0% 797MB/s ± 0% +3.12% (p=0.000 n=21+21) JSONEncode-8 283MB/s ± 0% 290MB/s ± 0% +2.35% (p=0.000 n=20+19) JSONDecode-8 63.0MB/s ± 1% 63.5MB/s ± 1% +0.82% (p=0.000 n=20+20) GoParse-8 22.2MB/s ± 2% 22.3MB/s ± 1% ~ (p=0.539 n=21+20) RegexpMatchEasy0_32-8 660MB/s ± 2% 697MB/s ± 3% +5.57% (p=0.000 n=20+21) RegexpMatchEasy0_1K-8 7.36GB/s ± 0% 7.34GB/s ± 0% -0.26% (p=0.000 n=18+20) RegexpMatchEasy1_32-8 775MB/s ± 0% 761MB/s ± 4% -1.88% (p=0.000 n=17+21) RegexpMatchEasy1_1K-8 4.74GB/s ± 2% 4.74GB/s ± 0% -0.18% (p=0.020 n=21+19) RegexpMatchMedium_32-8 40.6MB/s ± 7% 39.9MB/s ± 9% ~ (p=0.191 n=21+21) RegexpMatchMedium_1K-8 43.7MB/s ± 5% 43.2MB/s ± 5% ~ (p=0.435 n=21+21) RegexpMatchHard_32-8 29.3MB/s ± 1% 29.4MB/s ± 1% +0.53% (p=0.000 n=19+18) RegexpMatchHard_1K-8 31.0MB/s ± 0% 31.0MB/s ± 0% ~ (p=0.572 n=21+20) Revcomp-8 730MB/s ± 0% 720MB/s ± 0% -1.36% (p=0.000 n=17+18) Template-8 46.2MB/s ± 1% 46.3MB/s ± 1% +0.30% (p=0.041 n=20+20) [Geo mean] 204MB/s 205MB/s +0.30% Change-Id: Iac75d0ec184a515ce0e65e19559d5fe2e9840514 Reviewed-on: https://go-review.googlesource.com/c/go/+/354970 Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com> Trust: Josh Bleecher Snyder <josharian@gmail.com> Trust: Keith Randall <khr@golang.org> Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Go Bot <gobot@golang.org>
2021-10-10 09:56:16 -06:00
// amd64:"ANDL\t[$]9, AX"
// amd64:"CMPQ\tAX, [$]9"
return x&9 == 9
}
cmd/compile: optimize shift pairs and masks on s390x Optimize combinations of left and right shifts by a constant value into a 'rotate then insert selected bits [into zero]' instruction. Use the same instruction for contiguous masks since it has some benefits over 'and immediate' (not restricted to 32-bits, does not overwrite source register). To keep the complexity of this change under control I've only implemented 64 bit operations for now. There are a lot more optimizations that can be done with this instruction family. However, since their function overlaps with other instructions we need to be somewhat careful not to break existing optimization rules by creating optimization dead ends. This is particularly true of the load/store merging rules which contain lots of zero extensions and shifts. This CL does interfere with the store merging rules when an operand is shifted left before it is stored: binary.BigEndian.PutUint64(b, x << 1) This is unfortunate but it's not critical and somewhat complex so I plan to fix that in a follow up CL. file before after Δ % addr2line 4117446 4117282 -164 -0.004% api 4945184 4942752 -2432 -0.049% asm 4998079 4991891 -6188 -0.124% buildid 2685158 2684074 -1084 -0.040% cgo 4553732 4553394 -338 -0.007% compile 19294446 19245070 -49376 -0.256% cover 4897105 4891319 -5786 -0.118% dist 3544389 3542785 -1604 -0.045% doc 3926795 3927617 +822 +0.021% fix 3302958 3293868 -9090 -0.275% link 6546274 6543456 -2818 -0.043% nm 4102021 4100825 -1196 -0.029% objdump 4542431 4548483 +6052 +0.133% pack 2482465 2416389 -66076 -2.662% pprof 13366541 13363915 -2626 -0.020% test2json 2829007 2761515 -67492 -2.386% trace 10216164 10219684 +3520 +0.034% vet 6773956 6773572 -384 -0.006% total 107124151 106917891 -206260 -0.193% Change-Id: I7591cce41e06867ba10a745daae9333513062746 Reviewed-on: https://go-review.googlesource.com/c/go/+/233317 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Trust: Michael Munday <mike.munday@ibm.com>
2020-05-11 10:44:48 -06:00
// mask contiguous one bits
func cont1Mask64U(x uint64) uint64 {
// s390x:"RISBGZ\t[$]16, [$]47, [$]0,"
return x & 0x0000ffffffff0000
cmd/compile: optimize shift pairs and masks on s390x Optimize combinations of left and right shifts by a constant value into a 'rotate then insert selected bits [into zero]' instruction. Use the same instruction for contiguous masks since it has some benefits over 'and immediate' (not restricted to 32-bits, does not overwrite source register). To keep the complexity of this change under control I've only implemented 64 bit operations for now. There are a lot more optimizations that can be done with this instruction family. However, since their function overlaps with other instructions we need to be somewhat careful not to break existing optimization rules by creating optimization dead ends. This is particularly true of the load/store merging rules which contain lots of zero extensions and shifts. This CL does interfere with the store merging rules when an operand is shifted left before it is stored: binary.BigEndian.PutUint64(b, x << 1) This is unfortunate but it's not critical and somewhat complex so I plan to fix that in a follow up CL. file before after Δ % addr2line 4117446 4117282 -164 -0.004% api 4945184 4942752 -2432 -0.049% asm 4998079 4991891 -6188 -0.124% buildid 2685158 2684074 -1084 -0.040% cgo 4553732 4553394 -338 -0.007% compile 19294446 19245070 -49376 -0.256% cover 4897105 4891319 -5786 -0.118% dist 3544389 3542785 -1604 -0.045% doc 3926795 3927617 +822 +0.021% fix 3302958 3293868 -9090 -0.275% link 6546274 6543456 -2818 -0.043% nm 4102021 4100825 -1196 -0.029% objdump 4542431 4548483 +6052 +0.133% pack 2482465 2416389 -66076 -2.662% pprof 13366541 13363915 -2626 -0.020% test2json 2829007 2761515 -67492 -2.386% trace 10216164 10219684 +3520 +0.034% vet 6773956 6773572 -384 -0.006% total 107124151 106917891 -206260 -0.193% Change-Id: I7591cce41e06867ba10a745daae9333513062746 Reviewed-on: https://go-review.googlesource.com/c/go/+/233317 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Trust: Michael Munday <mike.munday@ibm.com>
2020-05-11 10:44:48 -06:00
}
// mask contiguous zero bits
func cont0Mask64U(x uint64) uint64 {
// s390x:"RISBGZ\t[$]48, [$]15, [$]0,"
return x & 0xffff00000000ffff
cmd/compile: optimize shift pairs and masks on s390x Optimize combinations of left and right shifts by a constant value into a 'rotate then insert selected bits [into zero]' instruction. Use the same instruction for contiguous masks since it has some benefits over 'and immediate' (not restricted to 32-bits, does not overwrite source register). To keep the complexity of this change under control I've only implemented 64 bit operations for now. There are a lot more optimizations that can be done with this instruction family. However, since their function overlaps with other instructions we need to be somewhat careful not to break existing optimization rules by creating optimization dead ends. This is particularly true of the load/store merging rules which contain lots of zero extensions and shifts. This CL does interfere with the store merging rules when an operand is shifted left before it is stored: binary.BigEndian.PutUint64(b, x << 1) This is unfortunate but it's not critical and somewhat complex so I plan to fix that in a follow up CL. file before after Δ % addr2line 4117446 4117282 -164 -0.004% api 4945184 4942752 -2432 -0.049% asm 4998079 4991891 -6188 -0.124% buildid 2685158 2684074 -1084 -0.040% cgo 4553732 4553394 -338 -0.007% compile 19294446 19245070 -49376 -0.256% cover 4897105 4891319 -5786 -0.118% dist 3544389 3542785 -1604 -0.045% doc 3926795 3927617 +822 +0.021% fix 3302958 3293868 -9090 -0.275% link 6546274 6543456 -2818 -0.043% nm 4102021 4100825 -1196 -0.029% objdump 4542431 4548483 +6052 +0.133% pack 2482465 2416389 -66076 -2.662% pprof 13366541 13363915 -2626 -0.020% test2json 2829007 2761515 -67492 -2.386% trace 10216164 10219684 +3520 +0.034% vet 6773956 6773572 -384 -0.006% total 107124151 106917891 -206260 -0.193% Change-Id: I7591cce41e06867ba10a745daae9333513062746 Reviewed-on: https://go-review.googlesource.com/c/go/+/233317 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Trust: Michael Munday <mike.munday@ibm.com>
2020-05-11 10:44:48 -06:00
}
func issue44228a(a []int64, i int) bool {
// amd64: "BTQ", -"SHL"
return a[i>>6]&(1<<(i&63)) != 0
}
func issue44228b(a []int32, i int) bool {
// amd64: "BTL", -"SHL"
return a[i>>5]&(1<<(i&31)) != 0
}
func issue48467(x, y uint64) uint64 {
// arm64: -"NEG"
d, borrow := bits.Sub64(x, y, 0)
return x - d&(-borrow)
}
cmd/compile: add late lower pass for last rules to run Usually optimization rules have corresponding priorities, some need to be run first, some run next, and some run last, which produces the best code. But currently our optimization rules have no priority, this CL adds a late lower pass that runs those rules that need to be run at last, such as split unreasonable constant folding. This pass can be seen as the second round of the lower pass. For example: func foo(a, b uint64) uint64 { d := a+0x1234568 d1 := b+0x1234568 return d&d1 } The code generated by the master branch: 0x0004 00004 ADD $19088744, R0, R2 // movz+movk+add 0x0010 00016 ADD $19088744, R1, R1 // movz+movk+add 0x001c 00028 AND R1, R2, R0 This is because the current constant folding optimization rules do not take into account the range of constants, causing the constant to be loaded repeatedly. This CL splits these unreasonable constants folding in the late lower pass. With this CL the generated code: 0x0004 00004 MOVD $19088744, R2 // movz+movk 0x000c 00012 ADD R0, R2, R3 0x0010 00016 ADD R1, R2, R1 0x0014 00020 AND R1, R3, R0 This CL also adds constant folding optimization for ADDS instruction. In addition, in order not to introduce the codegen regression, an optimization rule is added to change the addition of a negative number into a subtraction of a positive number. go1 benchmarks: name old time/op new time/op delta BinaryTree17-8 1.22s ± 1% 1.24s ± 0% +1.56% (p=0.008 n=5+5) Fannkuch11-8 1.54s ± 0% 1.53s ± 0% -0.69% (p=0.016 n=4+5) FmtFprintfEmpty-8 14.1ns ± 0% 14.1ns ± 0% ~ (p=0.079 n=4+5) FmtFprintfString-8 26.0ns ± 0% 26.1ns ± 0% +0.23% (p=0.008 n=5+5) FmtFprintfInt-8 32.3ns ± 0% 32.9ns ± 1% +1.72% (p=0.008 n=5+5) FmtFprintfIntInt-8 54.5ns ± 0% 55.5ns ± 0% +1.83% (p=0.008 n=5+5) FmtFprintfPrefixedInt-8 61.5ns ± 0% 62.0ns ± 0% +0.93% (p=0.008 n=5+5) FmtFprintfFloat-8 72.0ns ± 0% 73.6ns ± 0% +2.24% (p=0.008 n=5+5) FmtManyArgs-8 221ns ± 0% 224ns ± 0% +1.22% (p=0.008 n=5+5) GobDecode-8 1.91ms ± 0% 1.93ms ± 0% +0.98% (p=0.008 n=5+5) GobEncode-8 1.40ms ± 1% 1.39ms ± 0% -0.79% (p=0.032 n=5+5) Gzip-8 115ms ± 0% 117ms ± 1% +1.17% (p=0.008 n=5+5) Gunzip-8 19.4ms ± 1% 19.3ms ± 0% -0.71% (p=0.016 n=5+4) HTTPClientServer-8 27.0µs ± 0% 27.3µs ± 0% +0.80% (p=0.008 n=5+5) JSONEncode-8 3.36ms ± 1% 3.33ms ± 0% ~ (p=0.056 n=5+5) JSONDecode-8 17.5ms ± 2% 17.8ms ± 0% +1.71% (p=0.016 n=5+4) Mandelbrot200-8 2.29ms ± 0% 2.29ms ± 0% ~ (p=0.151 n=5+5) GoParse-8 1.35ms ± 1% 1.36ms ± 1% ~ (p=0.056 n=5+5) RegexpMatchEasy0_32-8 24.5ns ± 0% 24.5ns ± 0% ~ (p=0.444 n=4+5) RegexpMatchEasy0_1K-8 131ns ±11% 118ns ± 6% ~ (p=0.056 n=5+5) RegexpMatchEasy1_32-8 22.9ns ± 0% 22.9ns ± 0% ~ (p=0.905 n=4+5) RegexpMatchEasy1_1K-8 126ns ± 0% 127ns ± 0% ~ (p=0.063 n=4+5) RegexpMatchMedium_32-8 486ns ± 5% 483ns ± 0% ~ (p=0.381 n=5+4) RegexpMatchMedium_1K-8 15.4µs ± 1% 15.5µs ± 0% ~ (p=0.151 n=5+5) RegexpMatchHard_32-8 687ns ± 0% 686ns ± 0% ~ (p=0.103 n=5+5) RegexpMatchHard_1K-8 20.7µs ± 0% 20.7µs ± 1% ~ (p=0.151 n=5+5) Revcomp-8 175ms ± 2% 176ms ± 3% ~ (p=1.000 n=5+5) Template-8 20.4ms ± 6% 20.1ms ± 2% ~ (p=0.151 n=5+5) TimeParse-8 112ns ± 0% 113ns ± 0% +0.97% (p=0.016 n=5+4) TimeFormat-8 156ns ± 0% 145ns ± 0% -7.14% (p=0.029 n=4+4) Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da Reviewed-on: https://go-review.googlesource.com/c/go/+/425134 Reviewed-by: Keith Randall <khr@google.com> Reviewed-by: Cherry Mui <cherryyz@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Eric Fang <eric.fang@arm.com>
2022-08-17 04:01:17 -06:00
func foldConst(x, y uint64) uint64 {
// arm64: "ADDS\t[$]7",-"MOVD\t[$]7"
d, b := bits.Add64(x, 7, 0)
return b & d
}
func foldConstOutOfRange(a uint64) uint64 {
// arm64: "MOVD\t[$]19088744",-"ADD\t[$]19088744"
return a + 0x1234568
}