1
0
mirror of https://github.com/golang/go synced 2024-11-19 16:04:48 -07:00
go/src/runtime/iface_test.go
Josh Bleecher Snyder 504bc3ed24 cmd/compile, runtime: specialize convT2x, don't alloc for zero vals
Prior to this CL, all runtime conversions
from a concrete value to an interface went
through one of two runtime calls: convT2E or convT2I.
However, in practice, basic types are very common.
Specializing convT2x for those basic types allows
for a more efficient implementation for those types.
For basic scalars and strings, allocation and copying
can use the same methods as normal code.
For pointer-free types, allocation can occur without
zeroing, and copying can take place without GC calls.
For slices, copying is cheaper and simpler.

This CL adds twelve runtime routines:

convT2E16, convT2I16
convT2E32, convT2I32
convT2E64, convT2I64
convT2Estring, convT2Istring
convT2Eslice, convT2Islice
convT2Enoptr, convT2Inoptr

While compiling make.bash, 93% of all convT2x calls
are now to one of these specialized convT2x call.

Within specialized convT2x routines, it is cheap to check
for a zero value, in a way that it is not in general.
When we detect a zero value there, we return a pointer
to zeroVal, rather than allocating.

name                         old time/op  new time/op  delta
ConvT2Ezero/zero/16-8        17.9ns ± 2%   3.0ns ± 3%  -83.20%  (p=0.000 n=56+56)
ConvT2Ezero/zero/32-8        17.8ns ± 2%   3.0ns ± 3%  -83.15%  (p=0.000 n=59+60)
ConvT2Ezero/zero/64-8        20.1ns ± 1%   3.0ns ± 2%  -84.98%  (p=0.000 n=57+57)
ConvT2Ezero/zero/str-8       32.6ns ± 1%   3.0ns ± 4%  -90.70%  (p=0.000 n=59+60)
ConvT2Ezero/zero/slice-8     36.7ns ± 2%   3.0ns ± 2%  -91.78%  (p=0.000 n=59+59)
ConvT2Ezero/zero/big-8       91.9ns ± 2%  85.9ns ± 2%   -6.52%  (p=0.000 n=57+57)
ConvT2Ezero/nonzero/16-8     17.7ns ± 2%  12.7ns ± 3%  -28.38%  (p=0.000 n=55+60)
ConvT2Ezero/nonzero/32-8     17.8ns ± 1%  12.7ns ± 1%  -28.44%  (p=0.000 n=54+57)
ConvT2Ezero/nonzero/64-8     20.0ns ± 1%  15.0ns ± 1%  -24.90%  (p=0.000 n=56+58)
ConvT2Ezero/nonzero/str-8    32.6ns ± 1%  25.7ns ± 1%  -21.17%  (p=0.000 n=58+55)
ConvT2Ezero/nonzero/slice-8  36.8ns ± 2%  30.4ns ± 1%  -17.32%  (p=0.000 n=60+52)
ConvT2Ezero/nonzero/big-8    92.1ns ± 2%  85.9ns ± 2%   -6.70%  (p=0.000 n=57+59)

Benchmarks on a real program (the compiler):

name       old time/op      new time/op      delta
Template        227ms ± 5%       221ms ± 2%  -2.48%  (p=0.000 n=30+26)
Unicode         102ms ± 5%       100ms ± 3%  -1.30%  (p=0.009 n=30+26)
GoTypes         656ms ± 5%       659ms ± 4%    ~     (p=0.208 n=30+30)
Compiler        2.82s ± 2%       2.82s ± 1%    ~     (p=0.614 n=29+27)
Flate           128ms ± 2%       128ms ± 5%    ~     (p=0.783 n=27+28)
GoParser        158ms ± 3%       158ms ± 3%    ~     (p=0.261 n=28+30)
Reflect         408ms ± 7%       401ms ± 3%    ~     (p=0.075 n=30+30)
Tar             123ms ± 6%       121ms ± 8%    ~     (p=0.287 n=29+30)
XML             220ms ± 2%       220ms ± 4%    ~     (p=0.805 n=29+29)

name       old user-ns/op   new user-ns/op   delta
Template   281user-ms ± 4%  279user-ms ± 3%  -0.87%  (p=0.044 n=28+28)
Unicode    142user-ms ± 4%  141user-ms ± 3%  -1.04%  (p=0.015 n=30+27)
GoTypes    884user-ms ± 3%  886user-ms ± 2%    ~     (p=0.532 n=30+30)
Compiler   3.94user-s ± 3%  3.92user-s ± 1%    ~     (p=0.185 n=30+28)
Flate      165user-ms ± 2%  165user-ms ± 4%    ~     (p=0.780 n=27+29)
GoParser   209user-ms ± 2%  208user-ms ± 3%    ~     (p=0.453 n=28+30)
Reflect    533user-ms ± 6%  526user-ms ± 3%    ~     (p=0.057 n=30+30)
Tar        156user-ms ± 6%  154user-ms ± 6%    ~     (p=0.133 n=29+30)
XML        288user-ms ± 4%  288user-ms ± 4%    ~     (p=0.633 n=30+30)

name       old alloc/op     new alloc/op     delta
Template       41.0MB ± 0%      40.9MB ± 0%  -0.11%  (p=0.000 n=29+29)
Unicode        32.6MB ± 0%      32.6MB ± 0%    ~     (p=0.572 n=29+30)
GoTypes         122MB ± 0%       122MB ± 0%  -0.10%  (p=0.000 n=30+30)
Compiler        482MB ± 0%       481MB ± 0%  -0.07%  (p=0.000 n=30+29)
Flate          26.6MB ± 0%      26.6MB ± 0%    ~     (p=0.096 n=30+30)
GoParser       32.7MB ± 0%      32.6MB ± 0%  -0.06%  (p=0.011 n=28+28)
Reflect        84.2MB ± 0%      84.1MB ± 0%  -0.17%  (p=0.000 n=29+30)
Tar            27.7MB ± 0%      27.7MB ± 0%  -0.05%  (p=0.032 n=27+28)
XML            44.7MB ± 0%      44.7MB ± 0%    ~     (p=0.131 n=28+30)

name       old allocs/op    new allocs/op    delta
Template         373k ± 1%        370k ± 1%  -0.76%  (p=0.000 n=30+30)
Unicode          325k ± 1%        325k ± 1%    ~     (p=0.383 n=29+30)
GoTypes         1.16M ± 0%       1.15M ± 0%  -0.75%  (p=0.000 n=29+30)
Compiler        4.15M ± 0%       4.13M ± 0%  -0.59%  (p=0.000 n=30+29)
Flate            238k ± 1%        237k ± 1%  -0.62%  (p=0.000 n=30+30)
GoParser         304k ± 1%        302k ± 1%  -0.64%  (p=0.000 n=30+28)
Reflect         1.00M ± 0%       0.99M ± 0%  -1.10%  (p=0.000 n=29+30)
Tar              245k ± 1%        244k ± 1%  -0.59%  (p=0.000 n=27+29)
XML              391k ± 1%        389k ± 1%  -0.59%  (p=0.000 n=29+30)

Change-Id: Id7f456d690567c2b0a96b0d6d64de8784b6e305f
Reviewed-on: https://go-review.googlesource.com/36476
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
2017-02-28 19:23:33 +00:00

404 lines
6.8 KiB
Go

// Copyright 2012 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 (
"runtime"
"testing"
)
type I1 interface {
Method1()
}
type I2 interface {
Method1()
Method2()
}
type TS uint16
type TM uintptr
type TL [2]uintptr
func (TS) Method1() {}
func (TS) Method2() {}
func (TM) Method1() {}
func (TM) Method2() {}
func (TL) Method1() {}
func (TL) Method2() {}
type T8 uint8
type T16 uint16
type T32 uint32
type T64 uint64
type Tstr string
type Tslice []byte
func (T8) Method1() {}
func (T16) Method1() {}
func (T32) Method1() {}
func (T64) Method1() {}
func (Tstr) Method1() {}
func (Tslice) Method1() {}
var (
e interface{}
e_ interface{}
i1 I1
i2 I2
ts TS
tm TM
tl TL
ok bool
)
// Issue 9370
func TestCmpIfaceConcreteAlloc(t *testing.T) {
if runtime.Compiler != "gc" {
t.Skip("skipping on non-gc compiler")
}
n := testing.AllocsPerRun(1, func() {
_ = e == ts
_ = i1 == ts
_ = e == 1
})
if n > 0 {
t.Fatalf("iface cmp allocs=%v; want 0", n)
}
}
func BenchmarkEqEfaceConcrete(b *testing.B) {
for i := 0; i < b.N; i++ {
_ = e == ts
}
}
func BenchmarkEqIfaceConcrete(b *testing.B) {
for i := 0; i < b.N; i++ {
_ = i1 == ts
}
}
func BenchmarkNeEfaceConcrete(b *testing.B) {
for i := 0; i < b.N; i++ {
_ = e != ts
}
}
func BenchmarkNeIfaceConcrete(b *testing.B) {
for i := 0; i < b.N; i++ {
_ = i1 != ts
}
}
func BenchmarkConvT2ESmall(b *testing.B) {
for i := 0; i < b.N; i++ {
e = ts
}
}
func BenchmarkConvT2EUintptr(b *testing.B) {
for i := 0; i < b.N; i++ {
e = tm
}
}
func BenchmarkConvT2ELarge(b *testing.B) {
for i := 0; i < b.N; i++ {
e = tl
}
}
func BenchmarkConvT2ISmall(b *testing.B) {
for i := 0; i < b.N; i++ {
i1 = ts
}
}
func BenchmarkConvT2IUintptr(b *testing.B) {
for i := 0; i < b.N; i++ {
i1 = tm
}
}
func BenchmarkConvT2ILarge(b *testing.B) {
for i := 0; i < b.N; i++ {
i1 = tl
}
}
func BenchmarkConvI2E(b *testing.B) {
i2 = tm
for i := 0; i < b.N; i++ {
e = i2
}
}
func BenchmarkConvI2I(b *testing.B) {
i2 = tm
for i := 0; i < b.N; i++ {
i1 = i2
}
}
func BenchmarkAssertE2T(b *testing.B) {
e = tm
for i := 0; i < b.N; i++ {
tm = e.(TM)
}
}
func BenchmarkAssertE2TLarge(b *testing.B) {
e = tl
for i := 0; i < b.N; i++ {
tl = e.(TL)
}
}
func BenchmarkAssertE2I(b *testing.B) {
e = tm
for i := 0; i < b.N; i++ {
i1 = e.(I1)
}
}
func BenchmarkAssertI2T(b *testing.B) {
i1 = tm
for i := 0; i < b.N; i++ {
tm = i1.(TM)
}
}
func BenchmarkAssertI2I(b *testing.B) {
i1 = tm
for i := 0; i < b.N; i++ {
i2 = i1.(I2)
}
}
func BenchmarkAssertI2E(b *testing.B) {
i1 = tm
for i := 0; i < b.N; i++ {
e = i1.(interface{})
}
}
func BenchmarkAssertE2E(b *testing.B) {
e = tm
for i := 0; i < b.N; i++ {
e_ = e
}
}
func BenchmarkAssertE2T2(b *testing.B) {
e = tm
for i := 0; i < b.N; i++ {
tm, ok = e.(TM)
}
}
func BenchmarkAssertE2T2Blank(b *testing.B) {
e = tm
for i := 0; i < b.N; i++ {
_, ok = e.(TM)
}
}
func BenchmarkAssertI2E2(b *testing.B) {
i1 = tm
for i := 0; i < b.N; i++ {
e, ok = i1.(interface{})
}
}
func BenchmarkAssertI2E2Blank(b *testing.B) {
i1 = tm
for i := 0; i < b.N; i++ {
_, ok = i1.(interface{})
}
}
func BenchmarkAssertE2E2(b *testing.B) {
e = tm
for i := 0; i < b.N; i++ {
e_, ok = e.(interface{})
}
}
func BenchmarkAssertE2E2Blank(b *testing.B) {
e = tm
for i := 0; i < b.N; i++ {
_, ok = e.(interface{})
}
}
func TestNonEscapingConvT2E(t *testing.T) {
m := make(map[interface{}]bool)
m[42] = true
if !m[42] {
t.Fatalf("42 is not present in the map")
}
if m[0] {
t.Fatalf("0 is present in the map")
}
n := testing.AllocsPerRun(1000, func() {
if m[0] {
t.Fatalf("0 is present in the map")
}
})
if n != 0 {
t.Fatalf("want 0 allocs, got %v", n)
}
}
func TestNonEscapingConvT2I(t *testing.T) {
m := make(map[I1]bool)
m[TM(42)] = true
if !m[TM(42)] {
t.Fatalf("42 is not present in the map")
}
if m[TM(0)] {
t.Fatalf("0 is present in the map")
}
n := testing.AllocsPerRun(1000, func() {
if m[TM(0)] {
t.Fatalf("0 is present in the map")
}
})
if n != 0 {
t.Fatalf("want 0 allocs, got %v", n)
}
}
func TestZeroConvT2x(t *testing.T) {
tests := []struct {
name string
fn func()
}{
{name: "E8", fn: func() { e = eight8 }}, // any byte-sized value does not allocate
{name: "E16", fn: func() { e = zero16 }}, // zero values do not allocate
{name: "E32", fn: func() { e = zero32 }},
{name: "E64", fn: func() { e = zero64 }},
{name: "Estr", fn: func() { e = zerostr }},
{name: "Eslice", fn: func() { e = zeroslice }},
{name: "Econstflt", fn: func() { e = 99.0 }}, // constants do not allocate
{name: "Econststr", fn: func() { e = "change" }},
{name: "I8", fn: func() { i1 = eight8I }},
{name: "I16", fn: func() { i1 = zero16I }},
{name: "I32", fn: func() { i1 = zero32I }},
{name: "I64", fn: func() { i1 = zero64I }},
{name: "Istr", fn: func() { i1 = zerostrI }},
{name: "Islice", fn: func() { i1 = zerosliceI }},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
n := testing.AllocsPerRun(1000, test.fn)
if n != 0 {
t.Errorf("want zero allocs, got %v", n)
}
})
}
}
var (
eight8 uint8 = 8
eight8I T8 = 8
zero16 uint16 = 0
zero16I T16 = 0
one16 uint16 = 1
zero32 uint32 = 0
zero32I T32 = 0
one32 uint32 = 1
zero64 uint64 = 0
zero64I T64 = 0
one64 uint64 = 1
zerostr string = ""
zerostrI Tstr = ""
nzstr string = "abc"
zeroslice []byte = nil
zerosliceI Tslice = nil
nzslice []byte = []byte("abc")
zerobig [512]byte
nzbig [512]byte = [512]byte{511: 1}
)
func BenchmarkConvT2Ezero(b *testing.B) {
b.Run("zero", func(b *testing.B) {
b.Run("16", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = zero16
}
})
b.Run("32", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = zero32
}
})
b.Run("64", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = zero64
}
})
b.Run("str", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = zerostr
}
})
b.Run("slice", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = zeroslice
}
})
b.Run("big", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = zerobig
}
})
})
b.Run("nonzero", func(b *testing.B) {
b.Run("16", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = one16
}
})
b.Run("32", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = one32
}
})
b.Run("64", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = one64
}
})
b.Run("str", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = nzstr
}
})
b.Run("slice", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = nzslice
}
})
b.Run("big", func(b *testing.B) {
for i := 0; i < b.N; i++ {
e = nzbig
}
})
})
}