cmd/compile: optimize len([]rune(string))

Adds a new runtime function to count runes in a string.
Modifies the compiler to detect the pattern len([]rune(string))
and replaces it with the new rune counting runtime function.

RuneCount/lenruneslice/ASCII                  27.8ns ± 2%  14.5ns ± 3%  -47.70%  (p=0.000 n=10+10)
RuneCount/lenruneslice/Japanese                126ns ± 2%    60ns ± 2%  -52.03%  (p=0.000 n=10+10)
RuneCount/lenruneslice/MixedLength             104ns ± 2%    50ns ± 1%  -51.71%  (p=0.000 n=10+9)

Fixes #24923

Change-Id: Ie9c7e7391a4e2cca675c5cdcc1e5ce7d523948b9
Reviewed-on: https://go-review.googlesource.com/108985
Run-TryBot: Martin Möhrmann <moehrmann@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>

1 files changed, 38 insertions, 0 deletions

diff --git a/src/runtime/string_test.go b/src/runtime/string_test.go
index c6e925d2e0..678ff00363 100644
--- a/src/runtime/string_test.go
+++ b/src/runtime/string_test.go
@@ -9,6 +9,7 @@ import (
 	"strconv"
 	"strings"
 	"testing"
+	"unicode/utf8"
 )
 
 // Strings and slices that don't escape and fit into tmpBuf are stack allocated,
@@ -110,6 +111,43 @@ var stringdata = []struct{ name, data string }{
 	{"MixedLength", "$Ѐࠀက퀀𐀀\U00040000\U0010FFFF"},
 }
 
+var sinkInt int
+
+func BenchmarkRuneCount(b *testing.B) {
+	// Each sub-benchmark counts the runes in a string in a different way.
+	b.Run("lenruneslice", func(b *testing.B) {
+		for _, sd := range stringdata {
+			b.Run(sd.name, func(b *testing.B) {
+				for i := 0; i < b.N; i++ {
+					sinkInt += len([]rune(sd.data))
+				}
+			})
+		}
+	})
+	b.Run("rangeloop", func(b *testing.B) {
+		for _, sd := range stringdata {
+			b.Run(sd.name, func(b *testing.B) {
+				for i := 0; i < b.N; i++ {
+					n := 0
+					for range sd.data {
+						n++
+					}
+					sinkInt += n
+				}
+			})
+		}
+	})
+	b.Run("utf8.RuneCountInString", func(b *testing.B) {
+		for _, sd := range stringdata {
+			b.Run(sd.name, func(b *testing.B) {
+				for i := 0; i < b.N; i++ {
+					sinkInt += utf8.RuneCountInString(sd.data)
+				}
+			})
+		}
+	})
+}
+
 func BenchmarkRuneIterate(b *testing.B) {
 	b.Run("range", func(b *testing.B) {
 		for _, sd := range stringdata {