encoding/gob: parallelize Encode/Decode benchmarks

Results remain comparable with the non-parallel version with -cpu=1:

benchmark                              old ns/op     new ns/op     delta
BenchmarkEndToEndPipe                  6200          6171          -0.47%
BenchmarkEndToEndPipe-6                1073          1024          -4.57%
BenchmarkEndToEndByteBuffer            2925          2664          -8.92%
BenchmarkEndToEndByteBuffer-6          516           560           +8.53%
BenchmarkEndToEndSliceByteBuffer       231683        237450        +2.49%
BenchmarkEndToEndSliceByteBuffer-6     59080         59452         +0.63%
BenchmarkEncodeComplex128Slice         67541         66003         -2.28%
BenchmarkEncodeComplex128Slice-6       72740         11316         -84.44%
BenchmarkEncodeFloat64Slice            25769         27899         +8.27%
BenchmarkEncodeFloat64Slice-6          26655         4557          -82.90%
BenchmarkEncodeInt32Slice              18685         18845         +0.86%
BenchmarkEncodeInt32Slice-6            18389         3462          -81.17%
BenchmarkEncodeStringSlice             19089         19354         +1.39%
BenchmarkEncodeStringSlice-6           20155         3237          -83.94%
BenchmarkEncodeInterfaceSlice          659601        677129        +2.66%
BenchmarkEncodeInterfaceSlice-6        640974        251621        -60.74%
BenchmarkDecodeComplex128Slice         117130        129955        +10.95%
BenchmarkDecodeComplex128Slice-6       155447        24924         -83.97%
BenchmarkDecodeFloat64Slice            67695         68776         +1.60%
BenchmarkDecodeFloat64Slice-6          82966         15225         -81.65%
BenchmarkDecodeInt32Slice              63102         62733         -0.58%
BenchmarkDecodeInt32Slice-6            77857         13003         -83.30%
BenchmarkDecodeStringSlice             130240        129562        -0.52%
BenchmarkDecodeStringSlice-6           165500        31507         -80.96%
BenchmarkDecodeInterfaceSlice          937637        1060835       +13.14%
BenchmarkDecodeInterfaceSlice-6        973495        270613        -72.20%

updates #18177

Change-Id: Ib3579010faa70827d5cbd02a826dbbb66ca13eb7
Reviewed-on: https://go-review.googlesource.com/36722
Run-TryBot: Bryan Mills <bcmills@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>

src/encoding/gob/timing_test.go

@@ -8,6 +8,7 @@ import (
 	"bytes"
 	"io"
 	"os"
+	"reflect"
 	"runtime"
 	"testing"
 )
@@ -132,89 +133,60 @@ func TestCountDecodeMallocs(t *testing.T) {
 	}
 }
 
+func benchmarkEncodeSlice(b *testing.B, a interface{}) {
+	b.ResetTimer()
+	b.RunParallel(func(pb *testing.PB) {
+		var buf bytes.Buffer
+		enc := NewEncoder(&buf)
+
+		for pb.Next() {
+			buf.Reset()
+			err := enc.Encode(a)
+			if err != nil {
+				b.Fatal(err)
+			}
+		}
+	})
+}
+
 func BenchmarkEncodeComplex128Slice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]complex128, 1000)
 	for i := range a {
 		a[i] = 1.2 + 3.4i
 	}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		buf.Reset()
-		err := enc.Encode(a)
-		if err != nil {
-			b.Fatal(err)
-		}
-	}
+	benchmarkEncodeSlice(b, a)
 }
 
 func BenchmarkEncodeFloat64Slice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]float64, 1000)
 	for i := range a {
 		a[i] = 1.23e4
 	}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		buf.Reset()
-		err := enc.Encode(a)
-		if err != nil {
-			b.Fatal(err)
-		}
-	}
+	benchmarkEncodeSlice(b, a)
 }
 
 func BenchmarkEncodeInt32Slice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]int32, 1000)
 	for i := range a {
 		a[i] = int32(i * 100)
 	}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		buf.Reset()
-		err := enc.Encode(a)
-		if err != nil {
-			b.Fatal(err)
-		}
-	}
+	benchmarkEncodeSlice(b, a)
 }
 
 func BenchmarkEncodeStringSlice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]string, 1000)
 	for i := range a {
 		a[i] = "now is the time"
 	}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		buf.Reset()
-		err := enc.Encode(a)
-		if err != nil {
-			b.Fatal(err)
-		}
-	}
+	benchmarkEncodeSlice(b, a)
 }
 
 func BenchmarkEncodeInterfaceSlice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]interface{}, 1000)
 	for i := range a {
 		a[i] = "now is the time"
 	}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		buf.Reset()
-		err := enc.Encode(a)
-		if err != nil {
-			b.Fatal(err)
-		}
-	}
+	benchmarkEncodeSlice(b, a)
 }
 
 // benchmarkBuf is a read buffer we can reset
@@ -245,124 +217,75 @@ func (b *benchmarkBuf) reset() {
 	b.offset = 0
 }
 
-func BenchmarkDecodeComplex128Slice(b *testing.B) {
+func benchmarkDecodeSlice(b *testing.B, a interface{}) {
 	var buf bytes.Buffer
 	enc := NewEncoder(&buf)
-	a := make([]complex128, 1000)
-	for i := range a {
-		a[i] = 1.2 + 3.4i
-	}
 	err := enc.Encode(a)
 	if err != nil {
 		b.Fatal(err)
 	}
-	x := make([]complex128, 1000)
-	bbuf := benchmarkBuf{data: buf.Bytes()}
+
+	ra := reflect.ValueOf(a)
+	rt := ra.Type()
 	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		bbuf.reset()
-		dec := NewDecoder(&bbuf)
-		err := dec.Decode(&x)
-		if err != nil {
-			b.Fatal(i, err)
+
+	b.RunParallel(func(pb *testing.PB) {
+		// TODO(#19025): Move per-thread allocation before ResetTimer.
+		rp := reflect.New(rt)
+		rp.Elem().Set(reflect.MakeSlice(rt, ra.Len(), ra.Cap()))
+		p := rp.Interface()
+
+		bbuf := benchmarkBuf{data: buf.Bytes()}
+
+		for pb.Next() {
+			bbuf.reset()
+			dec := NewDecoder(&bbuf)
+			err := dec.Decode(p)
+			if err != nil {
+				b.Fatal(err)
+			}
 		}
+	})
+}
+
+func BenchmarkDecodeComplex128Slice(b *testing.B) {
+	a := make([]complex128, 1000)
+	for i := range a {
+		a[i] = 1.2 + 3.4i
 	}
+	benchmarkDecodeSlice(b, a)
 }
 
 func BenchmarkDecodeFloat64Slice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]float64, 1000)
 	for i := range a {
 		a[i] = 1.23e4
 	}
-	err := enc.Encode(a)
-	if err != nil {
-		b.Fatal(err)
-	}
-	x := make([]float64, 1000)
-	bbuf := benchmarkBuf{data: buf.Bytes()}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		bbuf.reset()
-		dec := NewDecoder(&bbuf)
-		err := dec.Decode(&x)
-		if err != nil {
-			b.Fatal(i, err)
-		}
-	}
+	benchmarkDecodeSlice(b, a)
 }
 
 func BenchmarkDecodeInt32Slice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]int32, 1000)
 	for i := range a {
 		a[i] = 1234
 	}
-	err := enc.Encode(a)
-	if err != nil {
-		b.Fatal(err)
-	}
-	x := make([]int32, 1000)
-	bbuf := benchmarkBuf{data: buf.Bytes()}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		bbuf.reset()
-		dec := NewDecoder(&bbuf)
-		err := dec.Decode(&x)
-		if err != nil {
-			b.Fatal(i, err)
-		}
-	}
+	benchmarkDecodeSlice(b, a)
 }
 
 func BenchmarkDecodeStringSlice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]string, 1000)
 	for i := range a {
 		a[i] = "now is the time"
 	}
-	err := enc.Encode(a)
-	if err != nil {
-		b.Fatal(err)
-	}
-	x := make([]string, 1000)
-	bbuf := benchmarkBuf{data: buf.Bytes()}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		bbuf.reset()
-		dec := NewDecoder(&bbuf)
-		err := dec.Decode(&x)
-		if err != nil {
-			b.Fatal(i, err)
-		}
-	}
+	benchmarkDecodeSlice(b, a)
 }
 
 func BenchmarkDecodeInterfaceSlice(b *testing.B) {
-	var buf bytes.Buffer
-	enc := NewEncoder(&buf)
 	a := make([]interface{}, 1000)
 	for i := range a {
 		a[i] = "now is the time"
 	}
-	err := enc.Encode(a)
-	if err != nil {
-		b.Fatal(err)
-	}
-	x := make([]interface{}, 1000)
-	bbuf := benchmarkBuf{data: buf.Bytes()}
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		bbuf.reset()
-		dec := NewDecoder(&bbuf)
-		err := dec.Decode(&x)
-		if err != nil {
-			b.Fatal(i, err)
-		}
-	}
+	benchmarkDecodeSlice(b, a)
 }
 
 func BenchmarkDecodeMap(b *testing.B) {