Hacker News new | ask | show | jobs
by zX41ZdbW 13 days ago
It is slower than LZ4 on AArch64.
2 comments
nonadhocproblem 13 days ago
Could you tell me what your test setup and corpus was?

For reference, to test ARM64, I tested v0.1.0 on an M3 mac with this fork of lzbench: https://github.com/welcome-to-the-sunny-side/lzbench/tree/ad...

Here, lz4's decompression speed was far slower than misa77 and zxc. Results are here: https://github.com/welcome-to-the-sunny-side/misa77/blob/mai...

link
noname120 13 days ago
Source?
link
zX41ZdbW 13 days ago
Just tested a few minutes ago on the ClickBench dataset. Overall quite good, but, depending on particular columns, most of the time slower - e.g., ~2.0 vs ~2.8 GB/sec on Graviton 4 machine in AWS.
link
zX41ZdbW 13 days ago
https://pastila.nl/?cafebabe/5763fb6ec6db85bf0f20fbd710a8c83...
link
croemer 13 days ago
You probably meant MB/sec not GB.
link
wmf 13 days ago
No? Decompression is rated in GB/s per core now.
link
croemer 13 days ago
Parent fixed the error I pointed out since making my post by dividing by a thousand instead of changing the units so now my comment looks wrong.

It used to say 2800 GB/s which is obviously bonkers.

link
zX41ZdbW 12 days ago
Yes, it was a typo. Thank you!
link