2018-03-03 11:17:20 -07:00
|
|
|
// 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"
|
|
|
|
|
|
|
|
var sink64 [8]float64
|
|
|
|
|
|
|
|
func approx(x float64) {
|
|
|
|
// s390x:"FIDBR\t[$]6"
|
|
|
|
// arm64:"FRINTPD"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FRIP"
|
2018-03-02 12:47:54 -07:00
|
|
|
// ppc64le:"FRIP"
|
2019-03-04 17:56:17 -07:00
|
|
|
// wasm:"F64Ceil"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[0] = math.Ceil(x)
|
|
|
|
|
|
|
|
// s390x:"FIDBR\t[$]7"
|
|
|
|
// arm64:"FRINTMD"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FRIM"
|
2018-03-02 12:47:54 -07:00
|
|
|
// ppc64le:"FRIM"
|
2019-03-04 17:56:17 -07:00
|
|
|
// wasm:"F64Floor"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[1] = math.Floor(x)
|
|
|
|
|
|
|
|
// s390x:"FIDBR\t[$]1"
|
|
|
|
// arm64:"FRINTAD"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FRIN"
|
2018-03-02 12:47:54 -07:00
|
|
|
// ppc64le:"FRIN"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[2] = math.Round(x)
|
|
|
|
|
|
|
|
// s390x:"FIDBR\t[$]5"
|
|
|
|
// arm64:"FRINTZD"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FRIZ"
|
2018-03-02 12:47:54 -07:00
|
|
|
// ppc64le:"FRIZ"
|
2019-03-04 17:56:17 -07:00
|
|
|
// wasm:"F64Trunc"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[3] = math.Trunc(x)
|
|
|
|
|
|
|
|
// s390x:"FIDBR\t[$]4"
|
2018-05-22 00:58:32 -06:00
|
|
|
// arm64:"FRINTND"
|
2019-03-04 17:56:17 -07:00
|
|
|
// wasm:"F64Nearest"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[4] = math.RoundToEven(x)
|
|
|
|
}
|
|
|
|
|
|
|
|
func sqrt(x float64) float64 {
|
|
|
|
// amd64:"SQRTSD"
|
2018-04-15 11:00:27 -06:00
|
|
|
// 386/387:"FSQRT" 386/sse2:"SQRTSD"
|
2018-03-03 11:17:20 -07:00
|
|
|
// arm64:"FSQRTD"
|
2018-04-15 11:00:27 -06:00
|
|
|
// arm/7:"SQRTD"
|
2018-04-26 07:37:27 -06:00
|
|
|
// mips/hardfloat:"SQRTD" mips/softfloat:-"SQRTD"
|
|
|
|
// mips64/hardfloat:"SQRTD" mips64/softfloat:-"SQRTD"
|
2019-03-04 17:56:17 -07:00
|
|
|
// wasm:"F64Sqrt"
|
2018-03-03 11:17:20 -07:00
|
|
|
return math.Sqrt(x)
|
|
|
|
}
|
|
|
|
|
|
|
|
// Check that it's using integer registers
|
|
|
|
func abs(x, y float64) {
|
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:"BTRQ\t[$]63"
|
2018-05-22 00:58:32 -06:00
|
|
|
// arm64:"FABSD\t"
|
2018-03-03 11:17:20 -07:00
|
|
|
// s390x:"LPDFR\t",-"MOVD\t" (no integer load/store)
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FABS\t"
|
2018-03-03 11:17:20 -07:00
|
|
|
// ppc64le:"FABS\t"
|
2019-03-04 17:56:17 -07:00
|
|
|
// wasm:"F64Abs"
|
2019-08-01 20:41:59 -06:00
|
|
|
// arm/6:"ABSD\t"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[0] = math.Abs(x)
|
|
|
|
|
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:"BTRQ\t[$]63","PXOR" (TODO: this should be BTSQ)
|
2018-03-03 11:17:20 -07:00
|
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FNABS\t"
|
2018-03-03 11:17:20 -07:00
|
|
|
// ppc64le:"FNABS\t"
|
|
|
|
sink64[1] = -math.Abs(y)
|
|
|
|
}
|
|
|
|
|
|
|
|
// Check that it's using integer registers
|
|
|
|
func abs32(x float32) float32 {
|
|
|
|
// s390x:"LPDFR",-"LDEBR",-"LEDBR" (no float64 conversion)
|
|
|
|
return float32(math.Abs(float64(x)))
|
|
|
|
}
|
|
|
|
|
|
|
|
// Check that it's using integer registers
|
|
|
|
func copysign(a, b, c float64) {
|
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:"BTRQ\t[$]63","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
|
2018-03-03 11:17:20 -07:00
|
|
|
// s390x:"CPSDR",-"MOVD" (no integer load/store)
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FCPSGN"
|
2018-03-03 11:17:20 -07:00
|
|
|
// ppc64le:"FCPSGN"
|
2019-03-04 17:56:17 -07:00
|
|
|
// wasm:"F64Copysign"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[0] = math.Copysign(a, b)
|
|
|
|
|
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:"BTSQ\t[$]63"
|
2018-03-03 11:17:20 -07:00
|
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FCPSGN"
|
2018-03-03 11:17:20 -07:00
|
|
|
// ppc64le:"FCPSGN"
|
2018-09-11 19:43:09 -06:00
|
|
|
// arm64:"ORR", -"AND"
|
2018-03-03 11:17:20 -07:00
|
|
|
sink64[1] = math.Copysign(c, -1)
|
|
|
|
|
|
|
|
// Like math.Copysign(c, -1), but with integer operations. Useful
|
|
|
|
// for platforms that have a copysign opcode to see if it's detected.
|
|
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
|
|
|
sink64[2] = math.Float64frombits(math.Float64bits(a) | 1<<63)
|
|
|
|
|
|
|
|
// amd64:-"SHLQ\t[$]1",-"SHRQ\t[$]1","SHRQ\t[$]63","SHLQ\t[$]63","ORQ"
|
|
|
|
// s390x:"CPSDR\t",-"MOVD\t" (no integer load/store)
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FCPSGN"
|
2018-03-03 11:17:20 -07:00
|
|
|
// ppc64le:"FCPSGN"
|
|
|
|
sink64[3] = math.Copysign(-1, c)
|
|
|
|
}
|
|
|
|
|
|
|
|
func fromFloat64(f64 float64) uint64 {
|
|
|
|
// amd64:"MOVQ\tX.*, [^X].*"
|
2018-07-15 22:45:25 -06:00
|
|
|
// arm64:"FMOVD\tF.*, R.*"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"MFVSRD"
|
|
|
|
// ppc64le:"MFVSRD"
|
2018-03-03 11:17:20 -07:00
|
|
|
return math.Float64bits(f64+1) + 1
|
|
|
|
}
|
|
|
|
|
|
|
|
func fromFloat32(f32 float32) uint32 {
|
|
|
|
// amd64:"MOVL\tX.*, [^X].*"
|
2018-07-15 22:45:25 -06:00
|
|
|
// arm64:"FMOVS\tF.*, R.*"
|
2018-03-03 11:17:20 -07:00
|
|
|
return math.Float32bits(f32+1) + 1
|
|
|
|
}
|
|
|
|
|
|
|
|
func toFloat64(u64 uint64) float64 {
|
|
|
|
// amd64:"MOVQ\t[^X].*, X.*"
|
2018-07-15 22:45:25 -06:00
|
|
|
// arm64:"FMOVD\tR.*, F.*"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"MTVSRD"
|
|
|
|
// ppc64le:"MTVSRD"
|
2018-03-03 11:17:20 -07:00
|
|
|
return math.Float64frombits(u64+1) + 1
|
|
|
|
}
|
|
|
|
|
|
|
|
func toFloat32(u32 uint32) float32 {
|
|
|
|
// amd64:"MOVL\t[^X].*, X.*"
|
2018-07-15 22:45:25 -06:00
|
|
|
// arm64:"FMOVS\tR.*, F.*"
|
2018-03-03 11:17:20 -07:00
|
|
|
return math.Float32frombits(u32+1) + 1
|
|
|
|
}
|
|
|
|
|
|
|
|
// Test that comparisons with constants converted to float
|
|
|
|
// are evaluated at compile-time
|
|
|
|
|
|
|
|
func constantCheck64() bool {
|
|
|
|
// amd64:"MOVB\t[$]0",-"FCMP",-"MOVB\t[$]1"
|
|
|
|
// s390x:"MOV(B|BZ|D)\t[$]0,",-"FCMPU",-"MOV(B|BZ|D)\t[$]1,"
|
|
|
|
return 0.5 == float64(uint32(1)) || 1.5 > float64(uint64(1<<63)) || math.NaN() == math.NaN()
|
|
|
|
}
|
|
|
|
|
|
|
|
func constantCheck32() bool {
|
|
|
|
// amd64:"MOVB\t[$]1",-"FCMP",-"MOVB\t[$]0"
|
|
|
|
// s390x:"MOV(B|BZ|D)\t[$]1,",-"FCMPU",-"MOV(B|BZ|D)\t[$]0,"
|
|
|
|
return float32(0.5) <= float32(int64(1)) && float32(1.5) >= float32(int32(-1<<31)) && float32(math.NaN()) != float32(math.NaN())
|
|
|
|
}
|
|
|
|
|
|
|
|
// Test that integer constants are converted to floating point constants
|
|
|
|
// at compile-time
|
|
|
|
|
|
|
|
func constantConvert32(x float32) float32 {
|
|
|
|
// amd64:"MOVSS\t[$]f32.3f800000\\(SB\\)"
|
|
|
|
// s390x:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
2018-03-03 11:17:20 -07:00
|
|
|
// ppc64le:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
2018-07-15 22:45:25 -06:00
|
|
|
// arm64:"FMOVS\t[$]\\(1.0\\)"
|
2018-03-03 11:17:20 -07:00
|
|
|
if x > math.Float32frombits(0x3f800000) {
|
|
|
|
return -x
|
|
|
|
}
|
|
|
|
return x
|
|
|
|
}
|
|
|
|
|
|
|
|
func constantConvertInt32(x uint32) uint32 {
|
|
|
|
// amd64:-"MOVSS"
|
|
|
|
// s390x:-"FMOVS"
|
2018-10-15 10:53:07 -06:00
|
|
|
// ppc64:-"FMOVS"
|
2018-03-03 11:17:20 -07:00
|
|
|
// ppc64le:-"FMOVS"
|
2018-07-15 22:45:25 -06:00
|
|
|
// arm64:-"FMOVS"
|
2018-03-03 11:17:20 -07:00
|
|
|
if x > math.Float32bits(1) {
|
|
|
|
return -x
|
|
|
|
}
|
|
|
|
return x
|
|
|
|
}
|