[gmx-developers] Replica exchange deadlock

Roland Schulz roland at utk.edu
Tue Feb 3 23:50:42 CET 2009


Hi,

I think the function replica_exchange is using the wrong MPI communicator. I
think it should be changed according to this diff:

--- repl_ex.c   16 Jan 2009 13:05:34 -0000      1.22.2.1
+++ repl_ex.c   3 Feb 2009 22:28:09 -0000
@@ -567,7 +567,7 @@
   if (PAR(cr)) {
 #ifdef GMX_MPI
     MPI_Bcast(&bExchanged,sizeof(bool),MPI_BYTE,MASTERRANK(cr),
-             cr->mpi_comm_mysim);
+             cr->mpi_comm_mygroup);
 #endif
   }

For me this remove a deadlock I have with certain number of PME nodes.

I haven't commited it directly because I'm not quite sure, whether this
fixes it in all cases and doesn't brake it in others.

BTW: Totalview callgraph feature was great to find this.


Roland



-- 
ORNL/UT Center for Molecular Biophysics cmb.ornl.gov
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://maillist.sys.kth.se/pipermail/gromacs.org_gmx-developers/attachments/20090203/45cec26b/attachment.html>


More information about the gromacs.org_gmx-developers mailing list