compress/flate: use math/bits.Reverse8/16 instead of local implementation

No measurable impact on performance (specifically, no degradation).
Reverse is used in Huffman en/de-coding. For completeness, here are
all the speed-related benchmark results:

name                             old time/op    new time/op    delta
Decode/Digits/Huffman/1e4-8         181µs ± 0%     178µs ± 1%   ~             (p=0.100 n=3+3)
Decode/Digits/Huffman/1e5-8        1.60ms ± 3%    1.56ms ± 3%   ~             (p=0.400 n=3+3)
Decode/Digits/Huffman/1e6-8        15.7ms ± 1%    15.3ms ± 3%   ~             (p=0.700 n=3+3)
Decode/Digits/Speed/1e4-8           179µs ± 0%     180µs ± 0%   ~             (p=0.200 n=3+3)
Decode/Digits/Speed/1e5-8          1.68ms ± 0%    1.66ms ± 3%   ~             (p=0.700 n=3+3)
Decode/Digits/Speed/1e6-8          16.6ms ± 2%    16.6ms ± 5%   ~             (p=0.700 n=3+3)
Decode/Digits/Default/1e4-8         179µs ± 1%     178µs ± 1%   ~             (p=0.700 n=3+3)
Decode/Digits/Default/1e5-8        1.62ms ± 3%    1.62ms ± 4%   ~             (p=1.000 n=3+3)
Decode/Digits/Default/1e6-8        16.0ms ± 2%    16.0ms ± 3%   ~             (p=1.000 n=3+3)
Decode/Digits/Compression/1e4-8     179µs ± 1%     179µs ± 0%   ~             (p=0.200 n=3+3)
Decode/Digits/Compression/1e5-8    1.62ms ± 2%    1.62ms ± 3%   ~             (p=1.000 n=3+3)
Decode/Digits/Compression/1e6-8    16.1ms ± 3%    16.0ms ± 3%   ~             (p=1.000 n=3+3)
Decode/Twain/Huffman/1e4-8          205µs ± 2%     207µs ± 1%   ~             (p=1.000 n=3+3)
Decode/Twain/Huffman/1e5-8         1.77ms ± 2%    1.77ms ± 4%   ~             (p=0.700 n=3+3)
Decode/Twain/Huffman/1e6-8         17.4ms ± 2%    17.4ms ± 3%   ~             (p=1.000 n=3+3)
Decode/Twain/Speed/1e4-8            186µs ± 1%     186µs ± 1%   ~             (p=0.400 n=3+3)
Decode/Twain/Speed/1e5-8           1.53ms ± 2%    1.52ms ± 0%   ~             (p=0.700 n=3+3)
Decode/Twain/Speed/1e6-8           14.9ms ± 1%    14.8ms ± 1%   ~             (p=1.000 n=3+3)
Decode/Twain/Default/1e4-8          176µs ± 1%     174µs ± 0%   ~             (p=0.200 n=3+3)
Decode/Twain/Default/1e5-8         1.30ms ± 2%    1.31ms ± 1%   ~             (p=0.700 n=3+3)
Decode/Twain/Default/1e6-8         12.6ms ± 3%    12.5ms ± 0%   ~             (p=0.700 n=3+3)
Decode/Twain/Compression/1e4-8      177µs ± 0%     174µs ± 1%   ~             (p=0.100 n=3+3)
Decode/Twain/Compression/1e5-8     1.30ms ± 1%    1.31ms ± 0%   ~             (p=0.700 n=3+3)
Decode/Twain/Compression/1e6-8     12.5ms ± 1%    12.5ms ± 1%   ~             (p=1.000 n=3+3)
Encode/Digits/Huffman/1e4-8        47.4µs ± 1%    46.5µs ± 0%   ~             (p=0.100 n=3+3)
Encode/Digits/Huffman/1e5-8         453µs ± 2%     446µs ± 1%   ~             (p=0.700 n=3+3)
Encode/Digits/Huffman/1e6-8        4.44ms ± 3%    4.39ms ± 0%   ~             (p=1.000 n=3+3)
Encode/Digits/Speed/1e4-8           190µs ± 4%     185µs ± 0%   ~             (p=0.100 n=3+3)
Encode/Digits/Speed/1e5-8          1.78ms ± 5%    1.75ms ± 1%   ~             (p=1.000 n=3+3)
Encode/Digits/Speed/1e6-8          17.9ms ± 7%    17.3ms ± 1%   ~             (p=0.400 n=3+3)
Encode/Digits/Default/1e4-8         366µs ± 1%     361µs ± 0%   ~             (p=0.200 n=3+3)
Encode/Digits/Default/1e5-8        5.58ms ± 5%    5.44ms ± 1%   ~             (p=0.400 n=3+3)
Encode/Digits/Default/1e6-8        59.0ms ± 3%    58.2ms ± 1%   ~             (p=0.700 n=3+3)
Encode/Digits/Compression/1e4-8     369µs ± 3%     362µs ± 0%   ~             (p=0.100 n=3+3)
Encode/Digits/Compression/1e5-8    5.50ms ± 2%    5.47ms ± 1%   ~             (p=1.000 n=3+3)
Encode/Digits/Compression/1e6-8    59.4ms ± 2%    58.5ms ± 1%   ~             (p=0.400 n=3+3)
Encode/Twain/Huffman/1e4-8         64.4µs ± 3%    64.7µs ± 1%   ~             (p=0.700 n=3+3)
Encode/Twain/Huffman/1e5-8          526µs ± 1%     526µs ± 2%   ~             (p=1.000 n=3+3)
Encode/Twain/Huffman/1e6-8         5.18ms ± 2%    5.17ms ± 1%   ~             (p=0.700 n=3+3)
Encode/Twain/Speed/1e4-8            206µs ± 1%     204µs ± 0%   ~             (p=0.100 n=3+3)
Encode/Twain/Speed/1e5-8           1.73ms ± 2%    1.70ms ± 0%   ~             (p=0.100 n=3+3)
Encode/Twain/Speed/1e6-8           16.7ms ± 0%    16.7ms ± 1%   ~             (p=1.000 n=3+3)
Encode/Twain/Default/1e4-8          423µs ± 3%     418µs ± 1%   ~             (p=1.000 n=3+3)
Encode/Twain/Default/1e5-8         6.34ms ± 4%    6.23ms ± 0%   ~             (p=1.000 n=3+3)
Encode/Twain/Default/1e6-8         68.0ms ± 3%    67.5ms ± 0%   ~             (p=0.700 n=3+3)
Encode/Twain/Compression/1e4-8      435µs ± 3%     424µs ± 0%   ~             (p=0.700 n=3+3)
Encode/Twain/Compression/1e5-8     7.01ms ± 1%    6.92ms ± 0%   ~             (p=0.100 n=3+3)
Encode/Twain/Compression/1e6-8     77.1ms ± 4%    75.5ms ± 1%   ~             (p=0.400 n=3+3)

name                             old speed      new speed      delta
Decode/Digits/Huffman/1e4-8      55.2MB/s ± 0%  56.2MB/s ± 1%   ~             (p=0.100 n=3+3)
Decode/Digits/Huffman/1e5-8      62.4MB/s ± 3%  64.1MB/s ± 3%   ~             (p=0.400 n=3+3)
Decode/Digits/Huffman/1e6-8      63.8MB/s ± 1%  65.3MB/s ± 3%   ~             (p=0.700 n=3+3)
Decode/Digits/Speed/1e4-8        55.8MB/s ± 0%  55.4MB/s ± 0%   ~             (p=0.200 n=3+3)
Decode/Digits/Speed/1e5-8        59.6MB/s ± 0%  60.3MB/s ± 3%   ~             (p=0.700 n=3+3)
Decode/Digits/Speed/1e6-8        60.1MB/s ± 2%  60.3MB/s ± 4%   ~             (p=0.700 n=3+3)
Decode/Digits/Default/1e4-8      55.8MB/s ± 1%  56.1MB/s ± 1%   ~             (p=0.700 n=3+3)
Decode/Digits/Default/1e5-8      61.8MB/s ± 3%  61.7MB/s ± 4%   ~             (p=1.000 n=3+3)
Decode/Digits/Default/1e6-8      62.4MB/s ± 2%  62.4MB/s ± 3%   ~             (p=1.000 n=3+3)
Decode/Digits/Compression/1e4-8  55.7MB/s ± 1%  56.0MB/s ± 0%   ~             (p=0.300 n=3+3)
Decode/Digits/Compression/1e5-8  61.7MB/s ± 2%  61.9MB/s ± 3%   ~             (p=1.000 n=3+3)
Decode/Digits/Compression/1e6-8  62.2MB/s ± 3%  62.6MB/s ± 3%   ~             (p=1.000 n=3+3)
Decode/Twain/Huffman/1e4-8       48.8MB/s ± 2%  48.4MB/s ± 1%   ~             (p=1.000 n=3+3)
Decode/Twain/Huffman/1e5-8       56.4MB/s ± 2%  56.6MB/s ± 4%   ~             (p=0.700 n=3+3)
Decode/Twain/Huffman/1e6-8       57.6MB/s ± 2%  57.5MB/s ± 3%   ~             (p=1.000 n=3+3)
Decode/Twain/Speed/1e4-8         53.7MB/s ± 1%  53.9MB/s ± 1%   ~             (p=0.400 n=3+3)
Decode/Twain/Speed/1e5-8         65.5MB/s ± 2%  65.6MB/s ± 0%   ~             (p=0.700 n=3+3)
Decode/Twain/Speed/1e6-8         66.9MB/s ± 1%  67.4MB/s ± 1%   ~             (p=1.000 n=3+3)
Decode/Twain/Default/1e4-8       56.9MB/s ± 1%  57.3MB/s ± 0%   ~             (p=0.200 n=3+3)
Decode/Twain/Default/1e5-8       77.2MB/s ± 2%  76.6MB/s ± 1%   ~             (p=0.700 n=3+3)
Decode/Twain/Default/1e6-8       79.3MB/s ± 3%  80.0MB/s ± 0%   ~             (p=0.700 n=3+3)
Decode/Twain/Compression/1e4-8   56.4MB/s ± 0%  57.5MB/s ± 1%   ~             (p=0.100 n=3+3)
Decode/Twain/Compression/1e5-8   76.8MB/s ± 1%  76.5MB/s ± 0%   ~             (p=0.700 n=3+3)
Decode/Twain/Compression/1e6-8   80.1MB/s ± 1%  79.8MB/s ± 1%   ~             (p=1.000 n=3+3)
Encode/Digits/Huffman/1e4-8       211MB/s ± 1%   215MB/s ± 0%   ~             (p=0.100 n=3+3)
Encode/Digits/Huffman/1e5-8       221MB/s ± 2%   224MB/s ± 1%   ~             (p=0.700 n=3+3)
Encode/Digits/Huffman/1e6-8       225MB/s ± 3%   228MB/s ± 0%   ~             (p=1.000 n=3+3)
Encode/Digits/Speed/1e4-8        52.8MB/s ± 4%  54.1MB/s ± 0%   ~             (p=0.100 n=3+3)
Encode/Digits/Speed/1e5-8        56.2MB/s ± 5%  57.0MB/s ± 1%   ~             (p=1.000 n=3+3)
Encode/Digits/Speed/1e6-8        56.0MB/s ± 6%  57.7MB/s ± 1%   ~             (p=0.400 n=3+3)
Encode/Digits/Default/1e4-8      27.3MB/s ± 1%  27.7MB/s ± 0%   ~             (p=0.200 n=3+3)
Encode/Digits/Default/1e5-8      17.9MB/s ± 4%  18.4MB/s ± 1%   ~             (p=0.400 n=3+3)
Encode/Digits/Default/1e6-8      17.0MB/s ± 3%  17.2MB/s ± 1%   ~             (p=0.500 n=3+3)
Encode/Digits/Compression/1e4-8  27.1MB/s ± 3%  27.6MB/s ± 0%   ~             (p=0.100 n=3+3)
Encode/Digits/Compression/1e5-8  18.2MB/s ± 2%  18.3MB/s ± 1%   ~             (p=1.000 n=3+3)
Encode/Digits/Compression/1e6-8  16.9MB/s ± 2%  17.1MB/s ± 1%   ~             (p=0.400 n=3+3)
Encode/Twain/Huffman/1e4-8        155MB/s ± 3%   155MB/s ± 1%   ~             (p=0.700 n=3+3)
Encode/Twain/Huffman/1e5-8        190MB/s ± 1%   190MB/s ± 2%   ~             (p=1.000 n=3+3)
Encode/Twain/Huffman/1e6-8        193MB/s ± 2%   193MB/s ± 1%   ~             (p=0.700 n=3+3)
Encode/Twain/Speed/1e4-8         48.5MB/s ± 1%  49.1MB/s ± 0%   ~             (p=0.100 n=3+3)
Encode/Twain/Speed/1e5-8         57.7MB/s ± 2%  59.0MB/s ± 0%   ~             (p=0.100 n=3+3)
Encode/Twain/Speed/1e6-8         59.7MB/s ± 0%  59.7MB/s ± 1%   ~             (p=1.000 n=3+3)
Encode/Twain/Default/1e4-8       23.6MB/s ± 3%  23.9MB/s ± 1%   ~             (p=1.000 n=3+3)
Encode/Twain/Default/1e5-8       15.8MB/s ± 4%  16.1MB/s ± 0%   ~             (p=1.000 n=3+3)
Encode/Twain/Default/1e6-8       14.7MB/s ± 3%  14.8MB/s ± 0%   ~             (p=0.700 n=3+3)
Encode/Twain/Compression/1e4-8   23.0MB/s ± 3%  23.6MB/s ± 0%   ~             (p=0.700 n=3+3)
Encode/Twain/Compression/1e5-8   14.3MB/s ± 1%  14.5MB/s ± 0%   ~             (p=0.100 n=3+3)
Encode/Twain/Compression/1e6-8   13.0MB/s ± 4%  13.2MB/s ± 1%   ~             (p=0.400 n=3+3)

Measured on a "quiet" (no browser running) 2.3 GHz Intel Core i7, running macOS 10.12.3.

See also #19279.

Change-Id: Ice759eb34eb37442b543957447c264e0aadc1fa9
Reviewed-on: https://go-review.googlesource.com/37460
Run-TryBot: Robert Griesemer <gri@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>

3 files changed, 9 insertions, 51 deletions

diff --git a/src/compress/flate/huffman_code.go b/src/compress/flate/huffman_code.go
index bdcbd823b0..891537ed5e 100644
--- a/src/compress/flate/huffman_code.go
+++ b/src/compress/flate/huffman_code.go
@@ -6,6 +6,7 @@ package flate
 
 import (
 	"math"
+	"math/bits"
 	"sort"
 )
 
@@ -342,3 +343,7 @@ func (s byFreq) Less(i, j int) bool {
 }
 
 func (s byFreq) Swap(i, j int) { s[i], s[j] = s[j], s[i] }
+
+func reverseBits(number uint16, bitLength byte) uint16 {
+	return bits.Reverse16(number << (16 - bitLength))
+}
diff --git a/src/compress/flate/inflate.go b/src/compress/flate/inflate.go
index 9a8c4fc455..faa33cc6e9 100644
--- a/src/compress/flate/inflate.go
+++ b/src/compress/flate/inflate.go
@@ -10,6 +10,7 @@ package flate
 import (
 	"bufio"
 	"io"
+	mathbits "math/bits"
 	"strconv"
 	"sync"
 )
@@ -176,7 +177,7 @@ func (h *huffmanDecoder) init(bits []int) bool {
 		link := nextcode[huffmanChunkBits+1] >> 1
 		h.links = make([][]uint32, huffmanNumChunks-link)
 		for j := uint(link); j < huffmanNumChunks; j++ {
-			reverse := int(reverseByte[j>>8]) | int(reverseByte[j&0xff])<<8
+			reverse := int(mathbits.Reverse16(uint16(j)))
 			reverse >>= uint(16 - huffmanChunkBits)
 			off := j - uint(link)
 			if sanity && h.chunks[reverse] != 0 {
@@ -194,7 +195,7 @@ func (h *huffmanDecoder) init(bits []int) bool {
 		code := nextcode[n]
 		nextcode[n]++
 		chunk := uint32(i<<huffmanValueShift | n)
-		reverse := int(reverseByte[code>>8]) | int(reverseByte[code&0xff])<<8
+		reverse := int(mathbits.Reverse16(uint16(code)))
 		reverse >>= uint(16 - n)
 		if n <= huffmanChunkBits {
 			for off := reverse; off < len(h.chunks); off += 1 << uint(n) {
@@ -556,7 +557,7 @@ readLiteral:
 					return
 				}
 			}
-			dist = int(reverseByte[(f.b&0x1F)<<3])
+			dist = int(mathbits.Reverse8(uint8(f.b & 0x1F << 3)))
 			f.b >>= 5
 			f.nb -= 5
 		} else {
diff --git a/src/compress/flate/reverse_bits.go b/src/compress/flate/reverse_bits.go
deleted file mode 100644
index 6b222900c1..0000000000
--- a/src/compress/flate/reverse_bits.go
+++ /dev/null
@@ -1,48 +0,0 @@
-// Copyright 2009 The Go Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style
-// license that can be found in the LICENSE file.
-
-package flate
-
-var reverseByte = [256]byte{
-	0x00, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0,
-	0x10, 0x90, 0x50, 0xd0, 0x30, 0xb0, 0x70, 0xf0,
-	0x08, 0x88, 0x48, 0xc8, 0x28, 0xa8, 0x68, 0xe8,
-	0x18, 0x98, 0x58, 0xd8, 0x38, 0xb8, 0x78, 0xf8,
-	0x04, 0x84, 0x44, 0xc4, 0x24, 0xa4, 0x64, 0xe4,
-	0x14, 0x94, 0x54, 0xd4, 0x34, 0xb4, 0x74, 0xf4,
-	0x0c, 0x8c, 0x4c, 0xcc, 0x2c, 0xac, 0x6c, 0xec,
-	0x1c, 0x9c, 0x5c, 0xdc, 0x3c, 0xbc, 0x7c, 0xfc,
-	0x02, 0x82, 0x42, 0xc2, 0x22, 0xa2, 0x62, 0xe2,
-	0x12, 0x92, 0x52, 0xd2, 0x32, 0xb2, 0x72, 0xf2,
-	0x0a, 0x8a, 0x4a, 0xca, 0x2a, 0xaa, 0x6a, 0xea,
-	0x1a, 0x9a, 0x5a, 0xda, 0x3a, 0xba, 0x7a, 0xfa,
-	0x06, 0x86, 0x46, 0xc6, 0x26, 0xa6, 0x66, 0xe6,
-	0x16, 0x96, 0x56, 0xd6, 0x36, 0xb6, 0x76, 0xf6,
-	0x0e, 0x8e, 0x4e, 0xce, 0x2e, 0xae, 0x6e, 0xee,
-	0x1e, 0x9e, 0x5e, 0xde, 0x3e, 0xbe, 0x7e, 0xfe,
-	0x01, 0x81, 0x41, 0xc1, 0x21, 0xa1, 0x61, 0xe1,
-	0x11, 0x91, 0x51, 0xd1, 0x31, 0xb1, 0x71, 0xf1,
-	0x09, 0x89, 0x49, 0xc9, 0x29, 0xa9, 0x69, 0xe9,
-	0x19, 0x99, 0x59, 0xd9, 0x39, 0xb9, 0x79, 0xf9,
-	0x05, 0x85, 0x45, 0xc5, 0x25, 0xa5, 0x65, 0xe5,
-	0x15, 0x95, 0x55, 0xd5, 0x35, 0xb5, 0x75, 0xf5,
-	0x0d, 0x8d, 0x4d, 0xcd, 0x2d, 0xad, 0x6d, 0xed,
-	0x1d, 0x9d, 0x5d, 0xdd, 0x3d, 0xbd, 0x7d, 0xfd,
-	0x03, 0x83, 0x43, 0xc3, 0x23, 0xa3, 0x63, 0xe3,
-	0x13, 0x93, 0x53, 0xd3, 0x33, 0xb3, 0x73, 0xf3,
-	0x0b, 0x8b, 0x4b, 0xcb, 0x2b, 0xab, 0x6b, 0xeb,
-	0x1b, 0x9b, 0x5b, 0xdb, 0x3b, 0xbb, 0x7b, 0xfb,
-	0x07, 0x87, 0x47, 0xc7, 0x27, 0xa7, 0x67, 0xe7,
-	0x17, 0x97, 0x57, 0xd7, 0x37, 0xb7, 0x77, 0xf7,
-	0x0f, 0x8f, 0x4f, 0xcf, 0x2f, 0xaf, 0x6f, 0xef,
-	0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff,
-}
-
-func reverseUint16(v uint16) uint16 {
-	return uint16(reverseByte[v>>8]) | uint16(reverseByte[v&0xFF])<<8
-}
-
-func reverseBits(number uint16, bitLength byte) uint16 {
-	return reverseUint16(number << (16 - bitLength))
-}