[mpich-discuss] mpich2 acts strange.

Eugene N neverov.biks.07.1 at gmail.com
Wed Jan 12 13:28:26 CST 2011


thanks a lot to you and Pavan,

you are very helpful

2011/1/12 Darius Buntinas <buntinas at mcs.anl.gov>

>
> Normally you shouldn't need to use buffered sends.  E.g., just using
> MPI_Send() and MPI_Recv() is enough to ensure that the server will receive a
> message from each client.
>
> -d
>
> On Jan 12, 2011, at 12:47 PM, Eugene N wrote:
>
> > Hello, dear community neighbours
> >
> > Can I ask you some questions that are bothering me?
> >
> > if several nodes report in "safe" mode to server node, and data arrives
> simultaneously (competing messages), will only one message survive, and
> others will be lost?
> >
> > Is this why a buffer is needed? Do we have to use buffer attach on the
> client or on the server (or both)??
> >
> > Thanks
> >
> > Eugene
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> > _______________________________________________
> > mpich-discuss mailing list
> > mpich-discuss at mcs.anl.gov
> > https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss
>
> _______________________________________________
> mpich-discuss mailing list
> mpich-discuss at mcs.anl.gov
> https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20110112/71a25e0f/attachment.htm>


More information about the mpich-discuss mailing list