[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Investigating a reproducibility failure
From: |
Ludovic Courtès |
Subject: |
Re: Investigating a reproducibility failure |
Date: |
Sat, 05 Feb 2022 15:12:28 +0100 |
User-agent: |
Gnus/5.13 (Gnus v5.13) Emacs/27.2 (gnu/linux) |
Konrad Hinsen <konrad.hinsen@fastmail.net> skribis:
> There is obviously a trade-off between reproducibility and performance
> here.
I tried hard to dispel that belief: you do not have to trade one for the other.
Yes, in some cases scientific software might lack the engineering work
that allows for portable performance; but in those cases, there’s
‘--tune’.
https://hpc.guix.info/blog/2022/01/tuning-packages-for-a-cpu-micro-architecture/
We should keep repeating that message: reproducibility and performance
are not antithetic. And I really mean it, otherwise fellow HPC
practitioners will keep producing unverifiable results on the grounds
that they cannot possibly compromise on performance!
Thanks,
Ludo’.
- Re: Investigating a reproducibility failure, (continued)
- Re: Investigating a reproducibility failure, Ludovic Courtès, 2022/02/05
- Re: Investigating a reproducibility failure, zimoun, 2022/02/02
- Re: Investigating a reproducibility failure, zimoun, 2022/02/02
- Re: Investigating a reproducibility failure, zimoun, 2022/02/03
- Re: Investigating a reproducibility failure,
Ludovic Courtès <=
- Re: Investigating a reproducibility failure, Bengt Richter, 2022/02/15
- Re: Investigating a reproducibility failure, zimoun, 2022/02/16
- Re: Investigating a reproducibility failure, Konrad Hinsen, 2022/02/16
- Re: Investigating a reproducibility failure, zimoun, 2022/02/17
- Re: Investigating a reproducibility failure, Konrad Hinsen, 2022/02/17