2014-07-29 01:01:02 -06:00
|
|
|
// Copyright 2014 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 runtime_test
|
|
|
|
|
|
|
|
import (
|
|
|
|
"bytes"
|
|
|
|
"runtime"
|
|
|
|
"testing"
|
|
|
|
)
|
|
|
|
|
|
|
|
// TestGCInfo tests that various objects in heap, data and bss receive correct GC pointer type info.
|
|
|
|
func TestGCInfo(t *testing.T) {
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
verifyGCInfo(t, "bss ScalarPtr", &bssScalarPtr, infoScalarPtr)
|
|
|
|
verifyGCInfo(t, "bss PtrScalar", &bssPtrScalar, infoPtrScalar)
|
|
|
|
verifyGCInfo(t, "bss BigStruct", &bssBigStruct, infoBigStruct())
|
|
|
|
verifyGCInfo(t, "bss string", &bssString, infoString)
|
|
|
|
verifyGCInfo(t, "bss slice", &bssSlice, infoSlice)
|
|
|
|
verifyGCInfo(t, "bss eface", &bssEface, infoEface)
|
|
|
|
verifyGCInfo(t, "bss iface", &bssIface, infoIface)
|
|
|
|
|
|
|
|
verifyGCInfo(t, "data ScalarPtr", &dataScalarPtr, infoScalarPtr)
|
|
|
|
verifyGCInfo(t, "data PtrScalar", &dataPtrScalar, infoPtrScalar)
|
|
|
|
verifyGCInfo(t, "data BigStruct", &dataBigStruct, infoBigStruct())
|
|
|
|
verifyGCInfo(t, "data string", &dataString, infoString)
|
|
|
|
verifyGCInfo(t, "data slice", &dataSlice, infoSlice)
|
|
|
|
verifyGCInfo(t, "data eface", &dataEface, infoEface)
|
|
|
|
verifyGCInfo(t, "data iface", &dataIface, infoIface)
|
2014-08-15 12:36:12 -06:00
|
|
|
|
2015-04-27 22:28:47 -06:00
|
|
|
verifyGCInfo(t, "stack ScalarPtr", new(ScalarPtr), nonStackInfo(infoScalarPtr))
|
|
|
|
verifyGCInfo(t, "stack PtrScalar", new(PtrScalar), nonStackInfo(infoPtrScalar))
|
|
|
|
verifyGCInfo(t, "stack BigStruct", new(BigStruct), nonStackInfo(infoBigStruct()))
|
|
|
|
verifyGCInfo(t, "stack string", new(string), nonStackInfo(infoString))
|
|
|
|
verifyGCInfo(t, "stack slice", new([]string), nonStackInfo(infoSlice))
|
|
|
|
verifyGCInfo(t, "stack eface", new(interface{}), nonStackInfo(infoEface))
|
|
|
|
verifyGCInfo(t, "stack iface", new(Iface), nonStackInfo(infoIface))
|
2014-07-29 01:01:02 -06:00
|
|
|
|
2014-08-18 12:21:55 -06:00
|
|
|
for i := 0; i < 10; i++ {
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
verifyGCInfo(t, "heap ScalarPtr", escape(new(ScalarPtr)), infoScalarPtr)
|
|
|
|
verifyGCInfo(t, "heap PtrScalar", escape(new(PtrScalar)), infoPtrScalar)
|
|
|
|
verifyGCInfo(t, "heap BigStruct", escape(new(BigStruct)), infoBigStruct())
|
|
|
|
verifyGCInfo(t, "heap string", escape(new(string)), infoString)
|
|
|
|
verifyGCInfo(t, "heap eface", escape(new(interface{})), infoEface)
|
|
|
|
verifyGCInfo(t, "heap iface", escape(new(Iface)), infoIface)
|
2014-07-29 01:01:02 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
func verifyGCInfo(t *testing.T, name string, p interface{}, mask0 []byte) {
|
|
|
|
mask := runtime.GCMask(p)
|
|
|
|
if len(mask) > len(mask0) {
|
2015-01-16 12:43:38 -07:00
|
|
|
mask0 = append(mask0, typeDead)
|
2014-07-29 01:01:02 -06:00
|
|
|
mask = mask[:len(mask0)]
|
|
|
|
}
|
|
|
|
if bytes.Compare(mask, mask0) != 0 {
|
|
|
|
t.Errorf("bad GC program for %v:\nwant %+v\ngot %+v", name, mask0, mask)
|
|
|
|
return
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-08-15 12:36:12 -06:00
|
|
|
func nonStackInfo(mask []byte) []byte {
|
2015-01-16 12:43:38 -07:00
|
|
|
// typeDead is replaced with typeScalar everywhere except stacks.
|
2014-08-15 12:36:12 -06:00
|
|
|
mask1 := make([]byte, len(mask))
|
|
|
|
for i, v := range mask {
|
2015-01-16 12:43:38 -07:00
|
|
|
if v == typeDead {
|
|
|
|
v = typeScalar
|
2014-08-15 12:36:12 -06:00
|
|
|
}
|
|
|
|
mask1[i] = v
|
|
|
|
}
|
|
|
|
return mask1
|
|
|
|
}
|
|
|
|
|
2014-07-29 01:01:02 -06:00
|
|
|
var gcinfoSink interface{}
|
|
|
|
|
|
|
|
func escape(p interface{}) interface{} {
|
|
|
|
gcinfoSink = p
|
|
|
|
return p
|
|
|
|
}
|
|
|
|
|
|
|
|
const (
|
2015-01-16 12:43:38 -07:00
|
|
|
typeDead = iota
|
|
|
|
typeScalar
|
|
|
|
typePointer
|
2014-07-29 01:01:02 -06:00
|
|
|
)
|
|
|
|
|
|
|
|
const (
|
2014-08-25 12:38:19 -06:00
|
|
|
BitsString = iota // unused
|
|
|
|
BitsSlice // unused
|
2014-07-29 01:01:02 -06:00
|
|
|
BitsIface
|
|
|
|
BitsEface
|
|
|
|
)
|
|
|
|
|
|
|
|
type ScalarPtr struct {
|
|
|
|
q int
|
|
|
|
w *int
|
|
|
|
e int
|
|
|
|
r *int
|
|
|
|
t int
|
|
|
|
y *int
|
|
|
|
}
|
|
|
|
|
2015-01-16 12:43:38 -07:00
|
|
|
var infoScalarPtr = []byte{typeScalar, typePointer, typeScalar, typePointer, typeScalar, typePointer}
|
2014-07-29 01:01:02 -06:00
|
|
|
|
|
|
|
type PtrScalar struct {
|
|
|
|
q *int
|
|
|
|
w int
|
|
|
|
e *int
|
|
|
|
r int
|
|
|
|
t *int
|
|
|
|
y int
|
|
|
|
}
|
|
|
|
|
2015-01-16 12:43:38 -07:00
|
|
|
var infoPtrScalar = []byte{typePointer, typeScalar, typePointer, typeScalar, typePointer, typeScalar}
|
2014-07-29 01:01:02 -06:00
|
|
|
|
2014-08-25 12:38:19 -06:00
|
|
|
type BigStruct struct {
|
2014-07-29 01:01:02 -06:00
|
|
|
q *int
|
|
|
|
w byte
|
|
|
|
e [17]byte
|
|
|
|
r []byte
|
|
|
|
t int
|
|
|
|
y uint16
|
|
|
|
u uint64
|
|
|
|
i string
|
|
|
|
}
|
|
|
|
|
2014-08-25 12:38:19 -06:00
|
|
|
func infoBigStruct() []byte {
|
2014-07-29 01:01:02 -06:00
|
|
|
switch runtime.GOARCH {
|
|
|
|
case "386", "arm":
|
|
|
|
return []byte{
|
2015-01-16 12:43:38 -07:00
|
|
|
typePointer, // q *int
|
|
|
|
typeScalar, typeScalar, typeScalar, typeScalar, typeScalar, // w byte; e [17]byte
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
typePointer, typeScalar, typeScalar, // r []byte
|
2015-01-16 12:43:38 -07:00
|
|
|
typeScalar, typeScalar, typeScalar, typeScalar, // t int; y uint16; u uint64
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
typePointer, typeScalar, // i string
|
2014-07-29 01:01:02 -06:00
|
|
|
}
|
2015-03-08 07:20:20 -06:00
|
|
|
case "arm64", "amd64", "ppc64", "ppc64le":
|
2014-07-29 01:01:02 -06:00
|
|
|
return []byte{
|
2015-01-16 12:43:38 -07:00
|
|
|
typePointer, // q *int
|
|
|
|
typeScalar, typeScalar, typeScalar, // w byte; e [17]byte
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
typePointer, typeScalar, typeScalar, // r []byte
|
2015-01-16 12:43:38 -07:00
|
|
|
typeScalar, typeScalar, typeScalar, // t int; y uint16; u uint64
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
typePointer, typeScalar, // i string
|
2014-07-29 01:01:02 -06:00
|
|
|
}
|
|
|
|
case "amd64p32":
|
|
|
|
return []byte{
|
2015-01-16 12:43:38 -07:00
|
|
|
typePointer, // q *int
|
|
|
|
typeScalar, typeScalar, typeScalar, typeScalar, typeScalar, // w byte; e [17]byte
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
typePointer, typeScalar, typeScalar, // r []byte
|
|
|
|
typeScalar, typeScalar, typeScalar, typeScalar, typeScalar, // t int; y uint16; u uint64
|
|
|
|
typePointer, typeScalar, // i string
|
2014-07-29 01:01:02 -06:00
|
|
|
}
|
|
|
|
default:
|
|
|
|
panic("unknown arch")
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-08-18 12:21:55 -06:00
|
|
|
type Iface interface {
|
|
|
|
f()
|
|
|
|
}
|
|
|
|
|
|
|
|
type IfaceImpl int
|
|
|
|
|
|
|
|
func (IfaceImpl) f() {
|
|
|
|
}
|
|
|
|
|
2014-07-29 01:01:02 -06:00
|
|
|
var (
|
|
|
|
// BSS
|
|
|
|
bssScalarPtr ScalarPtr
|
|
|
|
bssPtrScalar PtrScalar
|
2014-08-25 12:38:19 -06:00
|
|
|
bssBigStruct BigStruct
|
2014-07-29 01:01:02 -06:00
|
|
|
bssString string
|
2014-08-18 12:21:55 -06:00
|
|
|
bssSlice []string
|
2014-07-29 01:01:02 -06:00
|
|
|
bssEface interface{}
|
2014-08-18 12:21:55 -06:00
|
|
|
bssIface Iface
|
2014-07-29 01:01:02 -06:00
|
|
|
|
|
|
|
// DATA
|
|
|
|
dataScalarPtr = ScalarPtr{q: 1}
|
|
|
|
dataPtrScalar = PtrScalar{w: 1}
|
2014-08-25 12:38:19 -06:00
|
|
|
dataBigStruct = BigStruct{w: 1}
|
2014-07-29 01:01:02 -06:00
|
|
|
dataString = "foo"
|
2014-08-18 12:21:55 -06:00
|
|
|
dataSlice = []string{"foo"}
|
2014-07-29 01:01:02 -06:00
|
|
|
dataEface interface{} = 42
|
2014-08-18 12:21:55 -06:00
|
|
|
dataIface Iface = IfaceImpl(42)
|
2014-07-29 01:01:02 -06:00
|
|
|
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
infoString = []byte{typePointer, typeScalar}
|
|
|
|
infoSlice = []byte{typePointer, typeScalar, typeScalar}
|
2015-01-16 12:43:38 -07:00
|
|
|
infoEface = []byte{typePointer, typePointer}
|
|
|
|
infoIface = []byte{typePointer, typePointer}
|
2014-07-29 01:01:02 -06:00
|
|
|
)
|