misa77 - Ultra-fast decompression codec outperforming LZ4
Show HN: misa77 - a codec that decodes 2x faster than LZ4 (at better ratios)
misa77 is a high-performance LZ-based codec designed for the write-once, read-many niche, delivering decompression speeds 1.5 to 3 times faster than LZ4 on both x86 and ARM architectures. While it trades compression speed for extreme decompression throughput, it achieves modest compression ratios with constant, low memory usage. Ideal for scenarios requiring rapid data retrieval, misa77 leverages experimental modes to optimize streams for modern CPU microarchitectures, sitting on the Pareto frontier for decode speed versus ratio.
misa77 lies on the pareto frontier for decompression throughput vs compression ratio on most shapes of data, frequently decoding faster even when competitors have a significantly worse ratio.
- danlark1
It's a somewhat known tradeoff, you can streamline and make the format friendlier to do memcpy which this library targets, the more memcpys you do, the faster it is overall to decode. On highly compressible data lz4, snappy become faster. Snappy on level 2 has faster decompression speed
But you have to pay the price that you need a slower encoding, because finding matches, putting restrictions on match lengths, putting things in different streams have costs you need to pay upfront.
Anyway good work, there is probably a need for that.
// Currently own Google's snappy and do compression at Google
P.S. if you want better snappy's results, compile with clang.
P.S.S you can optimize aarch64 speed by movemasks from shrn instruction. https://developer.arm.com/community/arm-community-blogs/b/se...
- purple-leafy
Compression is so tricky.
I got really into compression experimenting while I was developing my browser game.
I was trying to compress entire human gameplay matches into a QR code, for upto 60 minutes of gameplay both single player and multiplayer.
My game is a fast paced, grid based, snake x scrabble word game.
My first compression attempt was to do run length encoding and cardinal directions, encoded into 1 byte. This was really compressible data.
The best approach was to use relative direction changes instead of cardinal directions. Compressed even better as the raw data was more consistent (for the most part you are moving forward etc).
Some other attempts were: zone based encoding, double movement pattern encoding (much smaller raw data but less compressible), triple movement pattern encoding, interrupt encoding.
I am at a point where I can fit all 30 minute single player games into a QR code, some 60 minute games, and with a special encoding scheme I can fit 15 minute N player multiplayer matches in a QR code
For reference qr code max size is about ~3000 bytes
- wolf550e
From status in readme in github:
- misa77's format may change unexpectedly as it's still v0.x.y.
- The decoder assumes that the input is a valid misa77 stream. Invalid input is UB and I offer no guarantees for whatever misa77 does in this case.
- It's been through some local fuzzing but is not hardened, so treat it as experimental.
- mijoharas
So, I couldn't see it in the readme, apologies if I missed it but why?
It's a very significant speedup in decompression speed (albeit with a compression speed slowdown as a trade-off), but what's the insight that makes it faster? What was the idea or approach behind it?
- Sesse__
Interesting, but if you are not robust to corrupted/malicious data, it is really in a different class of algorithm and it is hard to compare speeds directly.
From memory, 2505 MB/sec also sounds on the low side for LZ4 on a modern CPU?