[mpiwg-ft] FTWG Call Topics?

Anthony Skjellum skjellum at auburn.edu
Wed Jun 21 12:29:56 CDT 2017


Hi all, I am OK if we cancel too, but at the next meeting we hold, I wanted to do an update about FA-MPI work and answer questions people have about our approach to it.
Since this came up a couple calls ago.  It would be fine to wait for next call slot to do this... We are actively extending FA-MPI at this time.
Tony


Anthony Skjellum, PhD
Professor of Computer Science and Software Engineering and
    Charles D. McCrary Eminent Scholar Endowed Chair
Director of the Charles D. McCrary Institute
Samuel Ginn College of Engineering
Auburn University
e-mail: skjellum at auburn.edu or skjellum at gmail.com
web sites: http://cyber.auburn.edu     http://mccrary.auburn.edu
cell: +1-205-807-4968 ; office: +1-334-844-6360

CONFIDENTIALITY: This e-mail and any attachments are confidential and
may be privileged. If you are not a named recipient, please notify the
sender immediately and do not disclose the contents to another person,
use it for any purpose or store or copy the information in any medium.

________________________________________
From: mpiwg-ft <mpiwg-ft-bounces at lists.mpi-forum.org> on behalf of Ignacio Laguna <lagunaperalt1 at llnl.gov>
Sent: Wednesday, June 21, 2017 12:17 PM
To: MPI WG Fault Tolerance and Dynamic Process Control working Group; Bland, Wesley
Subject: Re: [mpiwg-ft] FTWG Call Topics?

I'm okay if we cancel.

On a different note, I wanted to ask the group about the error handler
for MPI_Init. As I look into the problem of MPI re-initialization, I
came across some questions, which I'm not been able to answer myself by
reading the standard:

- Since one cannot set an error handler before MPI_Init, is is expected
that MPI_ERRORS_ARE_FATAL is enabled when MPI_Init is called? If that is
the case, one can assume that if an error occurs the first time MPI_Init
is called (let's assume in the future we can call MPI_Init several
times), MPI will abort?

- Is there any situation, in which MPI_Init could return an error code
if a failure occurs?

- Is there a way to set MPI_ERROR_RETURN in COMM_WORLD before calling
MPI_Init?

I realize this was discussed in 2010, but I'm not sure if the forum
found a solution:
https://lists.mpi-forum.org/pipermail/mpiwg-ft/2010-August/000500.html

Thanks!

--
Ignacio Laguna
Center for Applied Scientific Computing (CASC)
Lawrence Livermore National Laboratory
Phone: 925-422-7308, Fax: 925-422-6287

On 6/21/17 9:40 AM, Bland, Wesley wrote:
> I don't have any topics for today's FTWG con call. Does anyone have anything they want to discuss?
>
> Should we cancel?
> _______________________________________________
> mpiwg-ft mailing list
> mpiwg-ft at lists.mpi-forum.org
> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-ft
>
_______________________________________________
mpiwg-ft mailing list
mpiwg-ft at lists.mpi-forum.org
https://lists.mpi-forum.org/mailman/listinfo/mpiwg-ft


More information about the mpiwg-ft mailing list