aboutsummaryrefslogtreecommitdiff
path: root/src/compress
diff options
context:
space:
mode:
authorNao YONASHIRO <owan.orisano@gmail.com>2019-07-28 06:04:27 +0900
committerDaniel Martí <mvdan@mvdan.cc>2019-08-28 12:48:37 +0000
commitbc92fe8b340c302db970fe8a42c8fcf6ccf7141a (patch)
tree7108f1517de20077b18ccfb78bfaa23a5ee69cab /src/compress
parent64cfe9fe22113cd6bc05a2c5d0cbe872b1b57860 (diff)
downloadgo-bc92fe8b340c302db970fe8a42c8fcf6ccf7141a.tar.gz
go-bc92fe8b340c302db970fe8a42c8fcf6ccf7141a.zip
compress/flate: improve deflate performance by register allocating the index
Use local index variable to help the go compiler use a register to for the hash index instead of continuous memory read and write operations. compress/flate: Encode/Digits/Huffman/1e4-4 35.3µs ± 1% 32.7µs ± 0% -7.48% (p=0.000 n=17+19) Encode/Digits/Huffman/1e5-4 330µs ± 0% 312µs ± 0% -5.55% (p=0.000 n=17+18) Encode/Digits/Huffman/1e6-4 3.30ms ± 0% 3.12ms ± 0% -5.64% (p=0.000 n=18+19) Encode/Digits/Speed/1e4-4 157µs ± 0% 156µs ± 0% -0.41% (p=0.000 n=17+19) Encode/Digits/Speed/1e5-4 1.46ms ± 0% 1.46ms ± 1% ~ (p=0.478 n=20+19) Encode/Digits/Speed/1e6-4 14.4ms ± 0% 14.4ms ± 0% ~ (p=0.835 n=19+20) Encode/Digits/Default/1e4-4 309µs ± 0% 310µs ± 0% +0.23% (p=0.000 n=19+17) Encode/Digits/Default/1e5-4 4.76ms ± 0% 4.76ms ± 0% ~ (p=0.297 n=19+19) Encode/Digits/Default/1e6-4 51.0ms ± 0% 51.0ms ± 1% ~ (p=0.233 n=18+19) Encode/Digits/Compression/1e4-4 309µs ± 0% 310µs ± 0% +0.21% (p=0.000 n=17+20) Encode/Digits/Compression/1e5-4 4.76ms ± 0% 4.76ms ± 0% ~ (p=0.749 n=20+19) Encode/Digits/Compression/1e6-4 50.9ms ± 0% 50.9ms ± 0% ~ (p=0.499 n=18+19) Encode/Newton/Huffman/1e4-4 51.9µs ± 0% 48.0µs ± 0% -7.61% (p=0.000 n=19+19) Encode/Newton/Huffman/1e5-4 396µs ± 0% 377µs ± 0% -4.79% (p=0.000 n=18+19) Encode/Newton/Huffman/1e6-4 3.95ms ± 0% 3.74ms ± 0% -5.21% (p=0.000 n=20+17) Encode/Newton/Speed/1e4-4 155µs ± 0% 154µs ± 0% -0.67% (p=0.000 n=17+18) Encode/Newton/Speed/1e5-4 1.17ms ± 0% 1.16ms ± 0% -0.64% (p=0.000 n=20+16) Encode/Newton/Speed/1e6-4 11.6ms ± 0% 11.5ms ± 0% -0.63% (p=0.000 n=19+20) Encode/Newton/Default/1e4-4 347µs ± 0% 347µs ± 0% ~ (p=0.744 n=20+19) Encode/Newton/Default/1e5-4 5.06ms ± 0% 5.02ms ± 0% -0.77% (p=0.000 n=20+19) Encode/Newton/Default/1e6-4 53.3ms ± 1% 52.8ms ± 0% -0.91% (p=0.000 n=18+16) Encode/Newton/Compression/1e4-4 351µs ± 0% 351µs ± 0% ~ (p=0.277 n=20+20) Encode/Newton/Compression/1e5-4 6.90ms ± 0% 6.85ms ± 0% -0.61% (p=0.000 n=19+18) Encode/Newton/Compression/1e6-4 73.2ms ± 0% 72.8ms ± 0% -0.52% (p=0.000 n=18+18) name old speed new speed delta Encode/Digits/Huffman/1e4-4 283MB/s ± 1% 306MB/s ± 0% +8.09% (p=0.000 n=17+19) Encode/Digits/Huffman/1e5-4 303MB/s ± 0% 321MB/s ± 0% +5.87% (p=0.000 n=18+18) Encode/Digits/Huffman/1e6-4 303MB/s ± 0% 321MB/s ± 0% +5.98% (p=0.000 n=18+19) Encode/Digits/Speed/1e4-4 63.9MB/s ± 0% 64.2MB/s ± 0% +0.41% (p=0.000 n=17+19) Encode/Digits/Speed/1e5-4 68.5MB/s ± 0% 68.4MB/s ± 1% ~ (p=0.481 n=20+19) Encode/Digits/Speed/1e6-4 69.4MB/s ± 0% 69.3MB/s ± 0% ~ (p=0.712 n=19+20) Encode/Digits/Default/1e4-4 32.3MB/s ± 0% 32.3MB/s ± 0% -0.23% (p=0.000 n=19+17) Encode/Digits/Default/1e5-4 21.0MB/s ± 0% 21.0MB/s ± 0% ~ (p=0.460 n=19+19) Encode/Digits/Default/1e6-4 19.6MB/s ± 0% 19.6MB/s ± 1% ~ (p=0.180 n=18+19) Encode/Digits/Compression/1e4-4 32.3MB/s ± 0% 32.3MB/s ± 0% -0.21% (p=0.000 n=17+20) Encode/Digits/Compression/1e5-4 21.0MB/s ± 0% 21.0MB/s ± 0% ~ (p=0.700 n=20+19) Encode/Digits/Compression/1e6-4 19.6MB/s ± 0% 19.6MB/s ± 0% ~ (p=0.486 n=18+19) Encode/Newton/Huffman/1e4-4 193MB/s ± 0% 208MB/s ± 0% +8.23% (p=0.000 n=19+19) Encode/Newton/Huffman/1e5-4 252MB/s ± 0% 265MB/s ± 0% +5.04% (p=0.000 n=18+19) Encode/Newton/Huffman/1e6-4 253MB/s ± 0% 267MB/s ± 0% +5.49% (p=0.000 n=20+17) Encode/Newton/Speed/1e4-4 64.5MB/s ± 0% 65.0MB/s ± 0% +0.67% (p=0.000 n=17+18) Encode/Newton/Speed/1e5-4 85.7MB/s ± 0% 86.3MB/s ± 0% +0.65% (p=0.000 n=20+16) Encode/Newton/Speed/1e6-4 86.2MB/s ± 0% 86.7MB/s ± 0% +0.63% (p=0.000 n=19+20) Encode/Newton/Default/1e4-4 28.9MB/s ± 0% 28.9MB/s ± 0% ~ (p=0.840 n=20+19) Encode/Newton/Default/1e5-4 19.8MB/s ± 0% 19.9MB/s ± 0% +0.78% (p=0.000 n=20+19) Encode/Newton/Default/1e6-4 18.8MB/s ± 1% 18.9MB/s ± 0% +0.93% (p=0.000 n=18+16) Encode/Newton/Compression/1e4-4 28.5MB/s ± 0% 28.5MB/s ± 0% ~ (p=0.244 n=20+20) Encode/Newton/Compression/1e5-4 14.5MB/s ± 0% 14.6MB/s ± 0% +0.61% (p=0.000 n=19+18) Encode/Newton/Compression/1e6-4 13.7MB/s ± 0% 13.7MB/s ± 0% +0.53% (p=0.000 n=18+18) image/png: name old time/op new time/op delta EncodeGray-4 2.16ms ± 1% 1.85ms ± 1% -14.17% (p=0.000 n=86+91) EncodeGrayWithBufferPool-4 1.99ms ± 0% 1.69ms ± 0% -15.09% (p=0.000 n=97+94) EncodeNRGBOpaque-4 6.51ms ± 1% 5.62ms ± 1% -13.66% (p=0.000 n=90+92) EncodeNRGBA-4 7.33ms ± 1% 6.12ms ± 1% -16.49% (p=0.000 n=89+90) EncodePaletted-4 5.10ms ± 1% 4.96ms ± 1% -2.76% (p=0.000 n=90+87) EncodeRGBOpaque-4 6.51ms ± 1% 5.63ms ± 1% -13.49% (p=0.000 n=94+87) EncodeRGBA-4 24.3ms ± 2% 23.0ms ± 0% -5.23% (p=0.000 n=91+89) name old speed new speed delta EncodeGray-4 142MB/s ± 1% 166MB/s ± 1% +16.50% (p=0.000 n=86+91) EncodeGrayWithBufferPool-4 154MB/s ± 0% 182MB/s ± 0% +17.78% (p=0.000 n=97+94) EncodeNRGBOpaque-4 189MB/s ± 1% 219MB/s ± 1% +15.82% (p=0.000 n=90+93) EncodeNRGBA-4 168MB/s ± 1% 201MB/s ± 1% +19.75% (p=0.000 n=89+90) EncodePaletted-4 60.3MB/s ± 1% 62.0MB/s ± 1% +2.84% (p=0.000 n=90+87) EncodeRGBOpaque-4 189MB/s ± 1% 218MB/s ± 1% +15.60% (p=0.000 n=94+87) EncodeRGBA-4 50.6MB/s ± 2% 53.4MB/s ± 0% +5.51% (p=0.000 n=91+89) Change-Id: Ifed4486a7ba19a26abe5cbf2142f15cc7464e84f Reviewed-on: https://go-review.googlesource.com/c/go/+/187837 Run-TryBot: Daniel Martí <mvdan@mvdan.cc> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Joe Tsai <thebrokentoaster@gmail.com>
Diffstat (limited to 'src/compress')
-rw-r--r--src/compress/flate/deflate.go13
1 files changed, 8 insertions, 5 deletions
diff --git a/src/compress/flate/deflate.go b/src/compress/flate/deflate.go
index 8b92f1586d..550032176d 100644
--- a/src/compress/flate/deflate.go
+++ b/src/compress/flate/deflate.go
@@ -465,17 +465,20 @@ Loop:
} else {
newIndex = d.index + prevLength - 1
}
- for d.index++; d.index < newIndex; d.index++ {
- if d.index < d.maxInsertIndex {
- d.hash = hash4(d.window[d.index : d.index+minMatchLength])
+ index := d.index
+ for index++; index < newIndex; index++ {
+ if index < d.maxInsertIndex {
+ d.hash = hash4(d.window[index : index+minMatchLength])
// Get previous value with the same hash.
// Our chain should point to the previous value.
hh := &d.hashHead[d.hash&hashMask]
- d.hashPrev[d.index&windowMask] = *hh
+ d.hashPrev[index&windowMask] = *hh
// Set the head of the hash chain to us.
- *hh = uint32(d.index + d.hashOffset)
+ *hh = uint32(index + d.hashOffset)
}
}
+ d.index = index
+
if d.fastSkipHashing == skipNever {
d.byteAvailable = false
d.length = minMatchLength - 1