compare two style of copy golang slice performance

golangcopylistbench.go

package gotrial

import (
	"strings"
	"testing"
)

func copyListV1(in []string) []string {
	var out []string

	for _, s := range in {
		out = append(out, s)
	}

	return out
}

func copyListV2(in []string) []string {
	out := make([]string, len(in))

	for i, s := range in {
		out[i] = s
	}

	return out
}

var input = strings.Fields(`Making code faster is exciting, and benchmarks in Go make that easy to do! Not really. 
Optimizing a program can be complex and require careful consideration to do properly. 
Daniel demonstrates techniques and tools which are a must for any performance aficionado.`)

func BenchmarkCopyList(b *testing.B) {
	b.ReportAllocs()

	for i := 0; i < b.N; i++ {
		copyListV2(input)
	}
}

➜  gotrial export http_proxy=http://127.0.0.1:9999; export https_proxy=http://127.0.0.1:9999;
➜  gotrial go get golang.org/x/tools/cmd/benchcmp
go: finding golang.org/x/tools/cmd/benchcmp latest
go: finding golang.org/x/tools/cmd latest
go: finding golang.org/x/tools latest
go: downloading golang.org/x/tools v0.0.0-20190509153222-73554e0f7805
go: extracting golang.org/x/tools v0.0.0-20190509153222-73554e0f7805
➜  gotrial go test -bench=BenchmarkCopyList > v1.txt
➜  gotrial go test -bench=BenchmarkCopyList > v2.txt
➜  gotrial benchcmp v1.txt v2.txt
benchmark                old ns/op     new ns/op     delta
BenchmarkCopyList-12     703           190           -72.97%
benchmark                old allocs     new allocs     delta
BenchmarkCopyList-12     7              1              -85.71%
benchmark                old bytes     new bytes     delta
BenchmarkCopyList-12     2032          704           -65.35%
➜  gotrial go test -bench=. -cpuprofile=cpu.out
goos: darwin
goarch: amd64
pkg: gotrial
BenchmarkCopyList-12    	 2000000	       729 ns/op	    2032 B/op	       7 allocs/op
PASS
ok  	gotrial	2.372s
➜  gotrial
➜  gotrial go tool pprof cpu.out
Type: cpu
Time: May 10, 2019 at 10:53am (CST)
Duration: 2.36s, Total samples = 2.72s (115.09%)
Entering interactive mode (type "help" for commands, "o" for options)
(pprof) list gotrial.copyListV1
Total: 2.72s
ROUTINE ======================== gotrial.copyListV1 in /Users/bingoobjca/github/gotrial/cp_test.go
      10ms       80ms (flat, cum)  2.94% of Total
         .          .      6:)
         .          .      7:
         .          .      8:func copyListV1(in []string) []string {
         .          .      9:	var out []string
         .          .     10:
      10ms       10ms     11:	for _, s := range in {
         .       70ms     12:		out = append(out, s)
         .          .     13:	}
         .          .     14:
         .          .     15:	return out
         .          .     16:}
         .          .     17:
(pprof) %
➜  gotrial go test -bench=. -cpuprofile=cpu.out
goos: darwin
goarch: amd64
pkg: gotrial
BenchmarkCopyList-12    	10000000	       201 ns/op	     704 B/op	       1 allocs/op
PASS
ok  	gotrial	2.393s
➜  gotrial go tool pprof cpu.out
Type: cpu
Time: May 10, 2019 at 10:55am (CST)
Duration: 2.38s, Total samples = 2.88s (120.77%)
Entering interactive mode (type "help" for commands, "o" for options)
(pprof) list gotrial.copyListV2
Total: 2.88s
ROUTINE ======================== gotrial.copyListV2 in /Users/bingoobjca/github/gotrial/cp_test.go
      40ms       80ms (flat, cum)  2.78% of Total
         .          .     14:
         .          .     15:	return out
         .          .     16:}
         .          .     17:
         .          .     18:func copyListV2(in []string) []string {
         .       40ms     19:	out := make([]string, len(in))
         .          .     20:
         .          .     21:	for i, s := range in {
      40ms       40ms     22:		out[i] = s
         .          .     23:	}
         .          .     24:
         .          .     25:	return out
         .          .     26:}
         .          .     27:
(pprof) %

from Optimizing Go code without a blindfold Daniel Martí at dotGo 2019

➜  gotrial go get golang.org/x/perf/cmd/benchstat
➜  gotrial benchstat v1.txt v2.txt
name         old time/op    new time/op    delta
CopyList-12     703ns ± 0%     190ns ± 0%   ~     (p=1.000 n=1+1)

name         old alloc/op   new alloc/op   delta
CopyList-12    2.03kB ± 0%    0.70kB ± 0%   ~     (p=1.000 n=1+1)

name         old allocs/op  new allocs/op  delta
CopyList-12      7.00 ± 0%      1.00 ± 0%   ~     (p=1.000 n=1+1)