mirror of
https://github.com/golang/go
synced 2024-09-29 05:24:32 -06:00
79112707bb
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>
218 lines
4.1 KiB
Go
218 lines
4.1 KiB
Go
// asmcheck
|
|
|
|
// Copyright 2018 The Go Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style
|
|
// license that can be found in the LICENSE file.
|
|
|
|
package codegen
|
|
|
|
import "math/bits"
|
|
|
|
// ----------------------- //
|
|
// bits.LeadingZeros //
|
|
// ----------------------- //
|
|
|
|
func LeadingZeros(n uint) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.LeadingZeros(n)
|
|
}
|
|
|
|
func LeadingZeros64(n uint64) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.LeadingZeros64(n)
|
|
}
|
|
|
|
func LeadingZeros32(n uint32) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.LeadingZeros32(n)
|
|
}
|
|
|
|
func LeadingZeros16(n uint16) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.LeadingZeros16(n)
|
|
}
|
|
|
|
func LeadingZeros8(n uint8) int {
|
|
// amd64 LeadingZeros8 not intrinsified (see ssa.go)
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.LeadingZeros8(n)
|
|
}
|
|
|
|
// --------------- //
|
|
// bits.Len* //
|
|
// --------------- //
|
|
|
|
func Len(n uint) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.Len(n)
|
|
}
|
|
|
|
func Len64(n uint64) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.Len64(n)
|
|
}
|
|
|
|
func Len32(n uint32) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.Len32(n)
|
|
}
|
|
|
|
func Len16(n uint16) int {
|
|
// amd64:"BSRQ"
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.Len16(n)
|
|
}
|
|
|
|
func Len8(n uint8) int {
|
|
// amd64 Len8 not intrisified (see ssa.go)
|
|
// s390x:"FLOGR"
|
|
// arm:"CLZ" arm64:"CLZ"
|
|
// mips:"CLZ"
|
|
return bits.Len8(n)
|
|
}
|
|
|
|
// -------------------- //
|
|
// bits.OnesCount //
|
|
// -------------------- //
|
|
|
|
func OnesCount(n uint) int {
|
|
// amd64:"POPCNTQ",".*support_popcnt"
|
|
// arm64:"VCNT","VUADDLV"
|
|
return bits.OnesCount(n)
|
|
}
|
|
|
|
func OnesCount64(n uint64) int {
|
|
// amd64:"POPCNTQ",".*support_popcnt"
|
|
// arm64:"VCNT","VUADDLV"
|
|
return bits.OnesCount64(n)
|
|
}
|
|
|
|
func OnesCount32(n uint32) int {
|
|
// amd64:"POPCNTL",".*support_popcnt"
|
|
// arm64:"VCNT","VUADDLV"
|
|
return bits.OnesCount32(n)
|
|
}
|
|
|
|
func OnesCount16(n uint16) int {
|
|
// amd64:"POPCNTL",".*support_popcnt"
|
|
// arm64:"VCNT","VUADDLV"
|
|
return bits.OnesCount16(n)
|
|
}
|
|
|
|
// ----------------------- //
|
|
// bits.ReverseBytes //
|
|
// ----------------------- //
|
|
|
|
func ReverseBytes(n uint) uint {
|
|
// amd64:"BSWAPQ"
|
|
// s390x:"MOVDBR"
|
|
// arm64:"REV"
|
|
return bits.ReverseBytes(n)
|
|
}
|
|
|
|
func ReverseBytes64(n uint64) uint64 {
|
|
// amd64:"BSWAPQ"
|
|
// s390x:"MOVDBR"
|
|
// arm64:"REV"
|
|
return bits.ReverseBytes64(n)
|
|
}
|
|
|
|
func ReverseBytes32(n uint32) uint32 {
|
|
// amd64:"BSWAPL"
|
|
// s390x:"MOVWBR"
|
|
// arm64:"REVW"
|
|
return bits.ReverseBytes32(n)
|
|
}
|
|
|
|
func ReverseBytes16(n uint16) uint16 {
|
|
// amd64:"ROLW"
|
|
return bits.ReverseBytes16(n)
|
|
}
|
|
|
|
// --------------------- //
|
|
// bits.RotateLeft //
|
|
// --------------------- //
|
|
|
|
func RotateLeft64(n uint64) uint64 {
|
|
// amd64:"ROLQ"
|
|
// arm64:"ROR"
|
|
// ppc64:"ROTL"
|
|
return bits.RotateLeft64(n, 37)
|
|
}
|
|
|
|
func RotateLeft32(n uint32) uint32 {
|
|
// amd64:"ROLL" 386:"ROLL"
|
|
// arm64:"RORW"
|
|
// ppc64:"ROTLW"
|
|
return bits.RotateLeft32(n, 9)
|
|
}
|
|
|
|
func RotateLeft16(n uint16) uint16 {
|
|
// amd64:"ROLW" 386:"ROLW"
|
|
return bits.RotateLeft16(n, 5)
|
|
}
|
|
|
|
func RotateLeft8(n uint8) uint8 {
|
|
// amd64:"ROLB" 386:"ROLB"
|
|
return bits.RotateLeft8(n, 5)
|
|
}
|
|
|
|
// ------------------------ //
|
|
// bits.TrailingZeros //
|
|
// ------------------------ //
|
|
|
|
func TrailingZeros(n uint) int {
|
|
// amd64:"BSFQ","MOVL\t\\$64","CMOVQEQ"
|
|
// s390x:"FLOGR"
|
|
return bits.TrailingZeros(n)
|
|
}
|
|
|
|
func TrailingZeros64(n uint64) int {
|
|
// amd64:"BSFQ","MOVL\t\\$64","CMOVQEQ"
|
|
// s390x:"FLOGR"
|
|
return bits.TrailingZeros64(n)
|
|
}
|
|
|
|
func TrailingZeros32(n uint32) int {
|
|
// amd64:"BTSQ\\t\\$32","BSFQ"
|
|
// s390x:"FLOGR","MOVWZ"
|
|
return bits.TrailingZeros32(n)
|
|
}
|
|
|
|
func TrailingZeros16(n uint16) int {
|
|
// amd64:"BSFQ","BTSQ\\t\\$16"
|
|
// s390x:"FLOGR","OR\t\\$65536"
|
|
return bits.TrailingZeros16(n)
|
|
}
|
|
|
|
func TrailingZeros8(n uint8) int {
|
|
// amd64:"BSFQ","BTSQ\\t\\$8"
|
|
// s390x:"FLOGR","OR\t\\$256"
|
|
return bits.TrailingZeros8(n)
|
|
}
|