TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Kraken: 3x faster decompression than zlib

147 pointsby dahjelleabout 9 years ago

13 comments

rb2k_about 9 years ago
Another interesting compression project is &quot;Zstandard&quot;<p>Open source, high performance, decent compression and a &quot;dictionary mode&quot; that&#x27;s especially fun when it comes to compressing a lot of small data.<p><a href="http:&#x2F;&#x2F;www.zstd.net" rel="nofollow">http:&#x2F;&#x2F;www.zstd.net</a><p>Previous discussion over at <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=8941955" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=8941955</a>
评论 #11587708 未加载
评论 #11587107 未加载
Johnieabout 9 years ago
There&#x27;s too many projects named Kraken:<p>* <a href="http:&#x2F;&#x2F;krakenjs.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;krakenjs.com&#x2F;</a> - Javascript framework<p>* <a href="https:&#x2F;&#x2F;www.kraken.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.kraken.com&#x2F;</a> - BTC exchange<p>* <a href="https:&#x2F;&#x2F;kraken.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;kraken.io&#x2F;</a> - Image Optimizer
评论 #11586548 未加载
评论 #11584980 未加载
评论 #11585071 未加载
评论 #11587794 未加载
评论 #11587460 未加载
userbinatorabout 9 years ago
I guess it&#x27;s yet another optimised LZ variant, and it&#x27;s no surprise that LZ-based&#x2F;inspired algorithms are fast, because their main loop is very simple and does not involve the intense bit manipulation of Huffman&#x2F;Arithmetic algorithms. That&#x27;s how very carefully optimised LZ can end up being <i>faster than memcpy()</i> in some cases:<p><a href="http:&#x2F;&#x2F;www.oldskool.org&#x2F;pc&#x2F;lz4_8088" rel="nofollow">http:&#x2F;&#x2F;www.oldskool.org&#x2F;pc&#x2F;lz4_8088</a>
mmozeikoabout 9 years ago
Few benchmarks from @rygorous:<p><a href="https:&#x2F;&#x2F;gist.github.com&#x2F;rygorous&#x2F;67c78fde615e078117ea187047291913" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;rygorous&#x2F;67c78fde615e078117ea1870472...</a> (on PC)<p><a href="https:&#x2F;&#x2F;gist.github.com&#x2F;rygorous&#x2F;9563760e24463a37984c117b5728638d" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;rygorous&#x2F;9563760e24463a37984c117b572...</a> (on PS4)
评论 #11586683 未加载
EvgeniyZhabout 9 years ago
How is it compared to Zstandard <a href="https:&#x2F;&#x2F;github.com&#x2F;Cyan4973&#x2F;zstd" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Cyan4973&#x2F;zstd</a> ?
评论 #11585412 未加载
muizelaarabout 9 years ago
Unfortunately not open source.
评论 #11584700 未加载
kazinatorabout 9 years ago
Is this 3x faster than zlib at decompressing on zlib-compressed data, or 3x faster on samples compressed with its own format versus the same samples compressed with zlib?
评论 #11585283 未加载
Jerry2about 9 years ago
Does anyone know how Apple&#x27;s lzfse [0] compares to some of these other compression algos?<p>&gt;Beginning with iOS 9 and OSX 10.11 El Capitan, we provide Apple’s proprietary compression algorithm, LZFSE. LZFSE is a new algorithm, matching the compression ratio of ZLIB level 5, but with much higher energy efficiency and speed (between 2x and 3x) for both encode and decode operations.<p>I&#x27;m interested because of the low energy characteristics...<p>[0] : <a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;library&#x2F;tvos&#x2F;documentation&#x2F;Performance&#x2F;Reference&#x2F;Compression&#x2F;" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;library&#x2F;tvos&#x2F;documentation&#x2F;Perfo...</a>
MichaelGGabout 9 years ago
What about LZHAM; I thought that was the top &quot;slow compress, good ratio, fast decompress&quot; contender for games and such?
评论 #11586351 未加载
iso-8859-1about 9 years ago
It is no secret that vanilla zlib is slow. Would have been interesting if they compared with <a href="https:&#x2F;&#x2F;github.com&#x2F;Dead2&#x2F;zlib-ng" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Dead2&#x2F;zlib-ng</a>
noir_lordabout 9 years ago
Is the speed difference algorithmic, implementation optimization or a mix of both?
评论 #11585515 未加载
stellar2about 9 years ago
Looking at the figures, it seems to have roughly the same performance as Zstandard in high compression mode.
Gratsbyabout 9 years ago
But what is it&#x27;s Weissman score?
评论 #11585145 未加载