1
0
mirror of https://github.com/golang/go synced 2024-11-08 18:46:16 -07:00
go/test/codegen/bits.go

355 lines
5.7 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
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: 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
// check direct operation on memory with constant source
func bitOpOnMem(a []uint32) {
// amd64:`ANDL\s[$]200,\s\([A-Z]+\)`
a[0] &= 200
// amd64:`ORL\s[$]220,\s4\([A-Z]+\)`
a[1] |= 220
// amd64:`XORL\s[$]240,\s8\([A-Z]+\)`
a[2] ^= 240
cmd/compile: optimize AMD64's bit wise operation Currently "arr[idx] |= 0x80" is compiled to MOVLload->BTSL->MOVLstore. And this CL optimizes it to a single BTSLconstmodify. Other bit wise operations with a direct memory operand are also implemented. 1. The size of the executable bin/go decreases about 4KB, and the total size of pkg/linux_amd64 (excluding cmd/compile) decreases about 0.6KB. 2. There a little improvement in the go1 benchmark test (excluding noise). name old time/op new time/op delta BinaryTree17-4 2.66s ± 4% 2.66s ± 3% ~ (p=0.596 n=49+49) Fannkuch11-4 2.38s ± 2% 2.32s ± 2% -2.69% (p=0.000 n=50+50) FmtFprintfEmpty-4 42.7ns ± 4% 43.2ns ± 7% +1.31% (p=0.009 n=50+50) FmtFprintfString-4 71.0ns ± 5% 72.0ns ± 3% +1.33% (p=0.000 n=50+50) FmtFprintfInt-4 80.7ns ± 4% 80.6ns ± 3% ~ (p=0.931 n=50+50) FmtFprintfIntInt-4 125ns ± 3% 126ns ± 4% ~ (p=0.051 n=50+50) FmtFprintfPrefixedInt-4 158ns ± 1% 142ns ± 3% -9.84% (p=0.000 n=36+50) FmtFprintfFloat-4 215ns ± 4% 212ns ± 4% -1.23% (p=0.002 n=50+50) FmtManyArgs-4 519ns ± 3% 510ns ± 3% -1.77% (p=0.000 n=50+50) GobDecode-4 6.49ms ± 6% 6.52ms ± 5% ~ (p=0.866 n=50+50) GobEncode-4 5.93ms ± 8% 6.01ms ± 7% ~ (p=0.076 n=50+50) Gzip-4 222ms ± 4% 224ms ± 8% +0.80% (p=0.001 n=50+50) Gunzip-4 36.6ms ± 5% 36.4ms ± 4% ~ (p=0.093 n=50+50) HTTPClientServer-4 59.1µs ± 1% 58.9µs ± 2% -0.24% (p=0.039 n=49+48) JSONEncode-4 9.23ms ± 4% 9.21ms ± 5% ~ (p=0.244 n=50+50) JSONDecode-4 48.8ms ± 4% 48.7ms ± 4% ~ (p=0.653 n=50+50) Mandelbrot200-4 3.81ms ± 4% 3.80ms ± 3% ~ (p=0.834 n=50+50) GoParse-4 3.20ms ± 5% 3.19ms ± 5% ~ (p=0.494 n=50+50) RegexpMatchEasy0_32-4 78.1ns ± 2% 77.4ns ± 3% -0.86% (p=0.005 n=50+50) RegexpMatchEasy0_1K-4 233ns ± 3% 233ns ± 3% ~ (p=0.074 n=50+50) RegexpMatchEasy1_32-4 74.2ns ± 3% 73.4ns ± 3% -1.06% (p=0.000 n=50+50) RegexpMatchEasy1_1K-4 369ns ± 2% 364ns ± 4% -1.41% (p=0.000 n=36+50) RegexpMatchMedium_32-4 109ns ± 4% 107ns ± 3% -2.06% (p=0.001 n=50+50) RegexpMatchMedium_1K-4 31.5µs ± 3% 30.8µs ± 3% -2.20% (p=0.000 n=50+50) RegexpMatchHard_32-4 1.57µs ± 3% 1.56µs ± 2% -0.57% (p=0.016 n=50+50) RegexpMatchHard_1K-4 47.4µs ± 4% 47.0µs ± 3% -0.82% (p=0.008 n=50+50) Revcomp-4 414ms ± 7% 412ms ± 7% ~ (p=0.285 n=50+50) Template-4 64.3ms ± 4% 62.7ms ± 3% -2.44% (p=0.000 n=50+50) TimeParse-4 316ns ± 3% 313ns ± 3% ~ (p=0.122 n=50+50) TimeFormat-4 291ns ± 3% 293ns ± 3% +0.80% (p=0.001 n=50+50) [Geo mean] 46.5µs 46.2µs -0.81% name old speed new speed delta GobDecode-4 118MB/s ± 6% 118MB/s ± 5% ~ (p=0.863 n=50+50) GobEncode-4 130MB/s ± 9% 128MB/s ± 8% ~ (p=0.076 n=50+50) Gzip-4 87.4MB/s ± 4% 86.8MB/s ± 7% -0.78% (p=0.002 n=50+50) Gunzip-4 531MB/s ± 5% 533MB/s ± 4% ~ (p=0.093 n=50+50) JSONEncode-4 210MB/s ± 4% 211MB/s ± 5% ~ (p=0.247 n=50+50) JSONDecode-4 39.8MB/s ± 4% 39.9MB/s ± 4% ~ (p=0.654 n=50+50) GoParse-4 18.1MB/s ± 5% 18.2MB/s ± 5% ~ (p=0.493 n=50+50) RegexpMatchEasy0_32-4 410MB/s ± 2% 413MB/s ± 3% +0.86% (p=0.004 n=50+50) RegexpMatchEasy0_1K-4 4.39GB/s ± 3% 4.38GB/s ± 3% ~ (p=0.063 n=50+50) RegexpMatchEasy1_32-4 432MB/s ± 3% 436MB/s ± 3% +1.07% (p=0.000 n=50+50) RegexpMatchEasy1_1K-4 2.77GB/s ± 2% 2.81GB/s ± 4% +1.46% (p=0.000 n=36+50) RegexpMatchMedium_32-4 9.16MB/s ± 3% 9.35MB/s ± 4% +2.09% (p=0.001 n=50+50) RegexpMatchMedium_1K-4 32.5MB/s ± 3% 33.2MB/s ± 3% +2.25% (p=0.000 n=50+50) RegexpMatchHard_32-4 20.4MB/s ± 3% 20.5MB/s ± 2% +0.56% (p=0.017 n=50+50) RegexpMatchHard_1K-4 21.6MB/s ± 4% 21.8MB/s ± 3% +0.83% (p=0.008 n=50+50) Revcomp-4 613MB/s ± 4% 618MB/s ± 7% ~ (p=0.152 n=48+50) Template-4 30.2MB/s ± 4% 30.9MB/s ± 3% +2.49% (p=0.000 n=50+50) [Geo mean] 127MB/s 128MB/s +0.64% Change-Id: If405198283855d75697f66cf894b2bef458f620e Reviewed-on: https://go-review.googlesource.com/135422 Reviewed-by: Keith Randall <khr@golang.org>
2018-09-16 20:05:22 -06:00
// amd64:`BTRL\s[$]15,\s12\([A-Z]+\)`,-`ANDL`
a[3] &= 0xffff7fff
// amd64:`BTSL\s[$]14,\s16\([A-Z]+\)`,-`ORL`
a[4] |= 0x4000
// amd64:`BTCL\s[$]13,\s20\([A-Z]+\)`,-`XORL`
a[5] ^= 0x2000
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
}
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 {
// amd64:"ANDQ\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
}