[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Guix-HPC activity report
From: |
Ludovic Courtès |
Subject: |
Re: Guix-HPC activity report |
Date: |
Fri, 15 Feb 2019 18:09:35 +0100 |
User-agent: |
Gnus/5.13 (Gnus v5.13) Emacs/26.1 (gnu/linux) |
Hi Simon,
zimoun <address@hidden> skribis:
> In the Guix FFTW package definition, there is a comment about AVX.
>
> Well, is it still accurate ?
> Is Guix binary still slower than other ?
The comment links to
<http://fftw.org/fftw3_doc/Installation-on-Unix.html>, which reads:
Enable various SIMD instruction sets. […] FFTW will try to detect at
runtime whether the CPU supports these extensions. That is, you can
compile with --enable-avx and the code will still run on a CPU without
AVX support.
So I believe the numbers one gets with the ‘fftw’ package in Guix are
the best one can get because FFTW does the right thing of using the
right version of its hot functions at run time. (That said, you can
redo the benchs, and if this is not the case, it’s a bug! :-))
See also this article, which addresses this topic:
https://guix-hpc.bordeaux.inria.fr/blog/2018/01/pre-built-binaries-vs-performance/
Thanks,
Ludo’.