Dear Damian,
On 14/01/2019 10:59, Alvarez, Damian wrote:
Hi Kenneth,
Wouldn't compiling OpenMPI 4.0 with --enable-mpi1-compatibility be an option?
(See https://www.open-mpi.org/faq/?category=mpi-removed)
Maybe, but I would like to avoid i) using a new major release, ii) using
a non-default configuration in a common toolchain like foss/2019a.
regards,
Kenneth
Best,
Damian
On 12.01.19, 19:15, "[email protected] on behalf of Kenneth Hoste"
<[email protected] on behalf of [email protected]> wrote:
Dear EasyBuilders,
Based on the problems that several people are seeing with Intel MPI 2019
update 1 (see also notes of the last EasyBuild conf call [1]), we
concluded that it's better to stick with Intel MPI 2018 update 4 for the
intel/2019a toolchain.
I will change the pull request accordingly soon.
For the Intel compilers and Intel MKL, we'll use the latest release
(2019 update 1).
As for foss/2019a: OpenMPI 4.0 dropped some old/'obscure' parts of MPI,
which seems to affect several libraries/tools, incl. ScaLAPACK, so we'll
stick to the latest OpenMPI 3.x release for the time being.
regards,
Kenneth
[1]
https://github.com/easybuilders/easybuild/wiki/Conference-call-notes-20190109#2019a-update-of-common-toolchains
On 08/01/2019 07:12, pramod kumbhar wrote:
> Same experience on our systems : we encountered multiple issues,
> specifically with libfabric (which is default with Intel MPI 2019).
>
> -Pramod
>
> On Mon, Jan 7, 2019 at 4:45 PM Alvarez, Damian <[email protected]
> <mailto:[email protected]>> wrote:
>
> A word of caution regarding Intel MPI 2019: They changed a lot of
> things under the hood, and we have seen lots of issues in our
> systems on relatively large jobs (1.5K+ MPI processes). Basically
> most collective algorithms don't make it through. We have seen that
> on 2 different InfiniBand systems, I am unsure about OmniPath, or
> about the underlying cause (maybe libfabric issues?), but with Intel
> MPI 2018 we haven't seen them.
>
> Best,
> Damian
>
> On 07.01.19, 16:37, "[email protected]
> <mailto:[email protected]> on behalf of Kenneth
> Hoste" <[email protected]
> <mailto:[email protected]> on behalf of
> [email protected] <mailto:[email protected]>> wrote:
>
> Dear EasyBuilders,
>
> By tradition at the start of the year, I have started looking at
> updating the 'foss' and 'intel' common toolchains, currently
> for the
> 2019a update.
> The plan is to include these in the upcoming EasyBuild v3.8.1
> release,
> which I hope to release in a couple of weeks.
>
> Current proposals are:
>
> * foss/2019a:
> (see
> https://github.com/easybuilders/easybuild-easyconfigs/pull/7371)
>
> - GCC 8.2.0 + binutils 2.31.1 [LATEST for both]
>
> - OpenMPI 3.1.3 (latest 3.x)
>
> - OpenBLAS 0.3.5 [LATEST]
> + ScaLAPACK 2.0.2 [LATEST]
>
> - FFTW 3.3.8 [LATEST]
>
> => There also is OpenMPI 4.0.0, but we generally stay away
> from new
> major version of a toolchain component for the common
toolchains.
>
> Does anyone have a detailed view on how OpenMPI v4.0.0
> compares
> to v3.1.3, and whether or not we should consider v4.0.0?
>
>
> * intel/2019a
> (see
> https://github.com/easybuilders/easybuild-easyconfigs/pull/7372)
>
> - Intel C/C++/Fortran compilers 2019.1.144 [LATEST]
> (a.k.a. 2019 update 1, a.k.a. 19.0.1.144 according to "icc
> -V")
> on top of GCC 8.2.0 + binutils 2.31.1
>
> - Intel MPI 2019.1.144 (a.k.a. 2019 update 1) [LATEST]
>
> - Intel MKL 2019.1.144 (a.k.a. 2019 update 1) [LATEST]
>
> => Any positive/negative experiences with the latest version
> of the
> Intel tools, or any remarks that may be relevant to the version
> we pick
> for intel/2019a?
>
>
> I'm currently testing these foss/2019a and intel/2019a
> proposals with a
> bunch of existing easyconfigs using the */2018b equivalent.
>
> A couple of minor compilation problems popped up when compiling
> with GCC
> 8.2.0 (for HDF5, NASM, ...), but they were resolved trivially
> by simply
> updating to the latest version of these dependencies.
>
>
> The 2019a toolchain definitions will also be discussed during
the
> EasyBuild conf call this Wednesday (Jan 9th).
>
>
>
> regards,
>
> Kenneth
>
>
>
>
>
------------------------------------------------------------------------------------------------
>
------------------------------------------------------------------------------------------------
> Forschungszentrum Juelich GmbH
> 52425 Juelich
> Sitz der Gesellschaft: Juelich
> Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498
> Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher
> Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender),
> Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt,
> Prof. Dr. Sebastian M. Schmidt
>
------------------------------------------------------------------------------------------------
>
------------------------------------------------------------------------------------------------
>
