unicode/utf8: added benchmarks

Cover some functions that weren't benched before and add InString
variants if the underlying implementation is different.

Note: compare (Valid|RuneCount)InString* to their (Valid|RuneCount)*
counterparts. It shows, somewhat unexpectedly, that ranging over
a string is *much* slower than using calls to DecodeRune.

Results:
In order to avoid a discrepancy in measuring the performance
of core we could leave the names of the string-based measurements
unchanged and suffix the added alternatives with Bytes.

Compared to old:
BenchmarkRuneCountTenASCIIChars-8        44.3          12.4          -72.01%
BenchmarkRuneCountTenJapaneseChars-8     167           67.1          -59.82%
BenchmarkEncodeASCIIRune-8               3.37          3.44          +2.08%
BenchmarkEncodeJapaneseRune-8            7.19          7.24          +0.70%
BenchmarkDecodeASCIIRune-8               5.41          5.53          +2.22%
BenchmarkDecodeJapaneseRune-8            8.17          8.41          +2.94%

All benchmarks:
BenchmarkRuneCountTenASCIIChars-8           	100000000	        12.4 ns/op
BenchmarkRuneCountTenJapaneseChars-8        	20000000	        67.1 ns/op
BenchmarkRuneCountInStringTenASCIIChars-8   	30000000	        44.5 ns/op
BenchmarkRuneCountInStringTenJapaneseChars-8	10000000	       165 ns/op
BenchmarkValidTenASCIIChars-8               	100000000	        12.5 ns/op
BenchmarkValidTenJapaneseChars-8            	20000000	        71.1 ns/op
BenchmarkValidStringTenASCIIChars-8         	30000000	        50.0 ns/op
BenchmarkValidStringTenJapaneseChars-8      	10000000	       161 ns/op
BenchmarkEncodeASCIIRune-8                  	500000000	         3.44 ns/op
BenchmarkEncodeJapaneseRune-8               	200000000	         7.24 ns/op
BenchmarkDecodeASCIIRune-8                  	300000000	         5.53 ns/op
BenchmarkDecodeJapaneseRune-8               	200000000	         8.41 ns/op
BenchmarkFullASCIIRune-8                    	500000000	         3.91 ns/op
BenchmarkFullJapaneseRune-8                 	300000000	         4.22 ns/op

Change-Id: I674d2ee4917b975a37717bbfa1082cc84dcd275e
Reviewed-on: https://go-review.googlesource.com/14431Reviewed-by: Russ Cox <rsc@golang.org>

src/unicode/utf8/utf8_test.go

@@ -404,17 +404,57 @@ func TestValidRune(t *testing.T) {
 }
 
 func BenchmarkRuneCountTenASCIIChars(b *testing.B) {
+	s := []byte("0123456789")
 	for i := 0; i < b.N; i++ {
-		RuneCountInString("0123456789")
+		RuneCount(s)
 	}
 }
 
 func BenchmarkRuneCountTenJapaneseChars(b *testing.B) {
+	s := []byte("日本語日本語日本語日")
+	for i := 0; i < b.N; i++ {
+		RuneCount(s)
+	}
+}
+
+func BenchmarkRuneCountInStringTenASCIIChars(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		RuneCountInString("0123456789")
+	}
+}
+
+func BenchmarkRuneCountInStringTenJapaneseChars(b *testing.B) {
 	for i := 0; i < b.N; i++ {
 		RuneCountInString("日本語日本語日本語日")
 	}
 }
 
+func BenchmarkValidTenASCIIChars(b *testing.B) {
+	s := []byte("0123456789")
+	for i := 0; i < b.N; i++ {
+		Valid(s)
+	}
+}
+
+func BenchmarkValidTenJapaneseChars(b *testing.B) {
+	s := []byte("日本語日本語日本語日")
+	for i := 0; i < b.N; i++ {
+		Valid(s)
+	}
+}
+
+func BenchmarkValidStringTenASCIIChars(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		ValidString("0123456789")
+	}
+}
+
+func BenchmarkValidStringTenJapaneseChars(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		ValidString("日本語日本語日本語日")
+	}
+}
+
 func BenchmarkEncodeASCIIRune(b *testing.B) {
 	buf := make([]byte, UTFMax)
 	for i := 0; i < b.N; i++ {
@@ -442,3 +482,17 @@ func BenchmarkDecodeJapaneseRune(b *testing.B) {
 		DecodeRune(nihon)
 	}
 }
+
+func BenchmarkFullASCIIRune(b *testing.B) {
+	a := []byte{'a'}
+	for i := 0; i < b.N; i++ {
+		FullRune(a)
+	}
+}
+
+func BenchmarkFullJapaneseRune(b *testing.B) {
+	nihon := []byte("本")
+	for i := 0; i < b.N; i++ {
+		FullRune(nihon)
+	}
+}