encoding/base32: improve performance in common case

Unroll loop to improve perfromance back to 1.8 level.
name              old time/op    new time/op    delta
EncodeToString-6    63.0µs ± 3%    51.7µs ± 2%  -17.94%  (p=0.000 n=10+10)

name              old speed      new speed      delta
EncodeToString-6   130MB/s ± 3%   159MB/s ± 2%  +21.83%  (p=0.000 n=10+10)

Vs 1.8:
EncodeToString-6    54.9µs ± 2%    51.7µs ± 2%   -5.95%  (p=0.000 n=10+10)

name              old speed      new speed      delta
EncodeToString-6   149MB/s ± 2%   159MB/s ± 2%   +6.32%  (p=0.000 n=10+10)

Fixes #21262

Change-Id: I41bf7e1f61041781386d16d573bffe1a7173c0c3
Reviewed-on: https://go-review.googlesource.com/52510
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

src/encoding/base32/base32.go

@@ -130,8 +130,19 @@ func (enc *Encoding) Encode(dst, src []byte) {
 		}
 
 		// Encode 5-bit blocks using the base32 alphabet
-		for i := 0; i < 8; i++ {
-			if len(dst) > i {
+		size := len(dst)
+		if size >= 8 {
+			// Common case, unrolled for extra performance
+			dst[0] = enc.encode[b[0]]
+			dst[1] = enc.encode[b[1]]
+			dst[2] = enc.encode[b[2]]
+			dst[3] = enc.encode[b[3]]
+			dst[4] = enc.encode[b[4]]
+			dst[5] = enc.encode[b[5]]
+			dst[6] = enc.encode[b[6]]
+			dst[7] = enc.encode[b[7]]
+		} else {
+			for i := 0; i < size; i++ {
 				dst[i] = enc.encode[b[i]]
 			}
 		}