[gmx-developers] Use of SVE in GROMACS
pall.szilard at gmail.com
Wed Oct 7 13:58:25 CEST 2020
Initial SVE support has just been merged a few days ago and will be
included in the 2021 release:
This is initial support with a fixed implementation with some
optimizations for A64fx.
Your contributions are welcome! For the 2021 release, which will have
a beta release very soon, we can only accept minor improvements and
tweaks. After the release-2021 branch is forked, further development
should target the master branch.
See further replies below.
> 3) Is this routine responsible only of the non-bonded forces? Does the “nb” prefix indicate “non-bonded”?
> 4) Is this same effect (“do_nb_verlet” the most expensive) measured for others benchmarks?
Yes. There are two possible exceptions:
- strong scaling where communication and other less algorithms that
scales less well than the nonbonded pair-interactions starts to
- uncommon rare simulation types where other very high cost algorithms are used.
The former should become clear when you scale out to a few hundred
atoms/core. The latter I'd suggest to not worry about.
> 5) Are there others ready-to-use and small benchmarks like the “ion_channel.tpr” available (<150K atoms)? Test Case B from UEABS (3.3 M atoms) is not suitable for my hardware resources.
You can use the "rnase" benchamrk systems 19k/24k atoms (see here
You might also find useful the nonbonded-benchmark tool, see:
Let us know if you have further questions.
> Thanks a lot, Guido.
> Gromacs Developers mailing list
> * Please search the archive at http://www.gromacs.org/Support/Mailing_Lists/GMX-developers_List before posting!
> * Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
> * For (un)subscribe requests visit
> https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-developers or send a mail to gmx-developers-request at gromacs.org.
More information about the gromacs.org_gmx-developers