Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Questions related to benchmark results in README file #4130

Open
ksolana opened this issue Aug 24, 2024 · 1 comment
Open

Questions related to benchmark results in README file #4130

ksolana opened this issue Aug 24, 2024 · 1 comment
Assignees
Labels

Comments

@ksolana
Copy link

ksolana commented Aug 24, 2024

  1. Is v1.5.6 slower than v1.5.1?
    As per https://github.com/facebook/zstd/tree/dev?tab=readme-ov-file#benchmarks the results for v1.5.6 is worse than v1.5.1 https://github.com/facebook/zstd/blob/v1.5.1/README.md at --fast=3.
zstd 1.5.1 --fast=3 	2.239 	670 MB/s
zstd 1.5.6 --fast=3 	2.239 	650 MB/s

zstd 1.5.1 -1 	2.887 	530 MB/s
zstd 1.5.6 -1 	2.887 	510 MB/s

Is it just noise level?

  1. Why are the results collected using a very old version of gcc? The latest gcc-14 is 5 years ahead of the one used in benchmarking.
@Cyan4973 Cyan4973 self-assigned this Dec 9, 2024
@Cyan4973
Copy link
Contributor

Cyan4973 commented Dec 9, 2024

Is it just noise level?

Yes, most likely

Why are the results collected using a very old version of gcc?

The system used for this benchmark was running on Ubuntu 20.04, which default compiler is gcc-9.
This will be changed in the next update,
using most likely the default compiler of Ubuntu 24.04.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants