[mpich-discuss] valgrind warning in MPIR_Process_status

[VandeVondele Joost]

I can confirm that Daniel's patch also fixes the issue I was seeing.

Thanks for the quick resolution.


________________________________
________________________________
From: Jeff Hammond [jeff.science at gmail.com]
Sent: Monday, January 11, 2016 6:51 AM
To: discuss at mpich.org
Subject: Re: [mpich-discuss] valgrind warning in MPIR_Process_status

To be explicit, the other thread is http://lists.mpich.org/pipermail/devel/2016-January/000677.html and it is indeed the same issue.

I pushed dibanez-helper_fns-valgrind to mpich-review just now.  https://trac.mpich.org/projects/mpich/ticket/2328 was created for tracking purposes.

Jeff

On Sun, Jan 10, 2016 at 5:04 PM, Jeff Hammond <jeff.science at gmail.com<mailto:jeff.science at gmail.com>> wrote:
I think this is the same issue reported on the devel list yesterday. If it is, Daniel Ibanez provided a patch that I've merged into my (completely unofficial fork on github) and will push to the official MPICH review repo tonight.

If you want to try and/or verify Daniel's patch, see github/jeffhammond/mpich. The branch you want should be obvious from the name (I can't remember what it is off hand).

Best,

Jeff


On Sunday, January 10, 2016, VandeVondele Joost <joost.vandevondele at mat.ethz.ch<mailto:joost.vandevondele at mat.ethz.ch>> wrote:
Hi,

we upgraded from mpich 3.1.2 to 3.2 and our nightly builds under valgrind show a new valgrind warning, which I suppose originates from the mpi library, rather than our code (given the stack trace below and the fact that they are absent with 3.1):

There are two slightly distinct traces (alltoall and alltoallv):

==30165== Conditional jump or move depends on uninitialised value(s)
==30165==    at 0x6E00056: MPIR_Process_status (mpiimpl.h:4394)
==30165==    by 0x6E00056: MPIC_Waitall (helper_fns.c:774)
==30165==    by 0x6D5A853: MPIR_Alltoall_intra (alltoall.c:369)
==30165==    by 0x6D5B63C: MPIR_Alltoall (alltoall.c:564)
==30165==    by 0x6D5B6EF: MPIR_Alltoall_impl (alltoall.c:599)
==30165==    by 0x6D5BF07: PMPI_Alltoall (alltoall.c:722)
==30165==    by 0x6AFF0DC: PMPI_ALLTOALL (alltoallf.c:276)
==30165==    by 0x1D04699: __message_passing_MOD_mp_alltoall_i22

==30201== Conditional jump or move depends on uninitialised value(s)
==30201==    at 0x6E00056: MPIR_Process_status (mpiimpl.h:4394)
==30201==    by 0x6E00056: MPIC_Waitall (helper_fns.c:774)
==30201==    by 0x6D5C4EA: MPIR_Alltoallv_intra (alltoallv.c:194)
==30201==    by 0x6D5CEC9: MPIR_Alltoallv (alltoallv.c:339)
==30201==    by 0x6D5CFAA: MPIR_Alltoallv_impl (alltoallv.c:376)
==30201==    by 0x6D5D8CA: PMPI_Alltoallv (alltoallv.c:527)
==30201==    by 0x6AFF13E: PMPI_ALLTOALLV (alltoallvf.c:276)
==30201==    by 0x1CCE180: __message_passing_MOD_mp_alltoall_z22v (message_passing_z.f90:223)

Is this issue already known/fixed ?

I saw there was a somewhat related change (which is part of 3.2):

https://trac.mpich.org/projects/mpich/changeset/be7c17b3177ccb0ede49761b44a438952360b061

but maybe that change was not fully complete ?

Best regards,

Joost VandeVondele

________________________________
Prof. Dr. Joost VandeVondele
Nanoscale Simulations

ETH Zurich
HIT G 41.4
Wolfgang-Pauli-Strasse 27
8093 Zurich, Switzerland

Joost.VandeVondele at mat.ethz.ch
http://www.nanosim.mat.ethz.ch/
Tel.: +41 (0)44 6338451
________________________________


--
Jeff Hammond
jeff.science at gmail.com<mailto:jeff.science at gmail.com>
http://jeffhammond.github.io/



--
Jeff Hammond
jeff.science at gmail.com<mailto:jeff.science at gmail.com>
http://jeffhammond.github.io/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20160111/21a91450/attachment.html>
-------------- next part --------------
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss