[mvapich-discuss] truly one-sided communication
Thiago Ize
thiago at sci.utah.edu
Thu Jan 20 04:10:57 EST 2011
Hi Sreeram,
Scattering some iprobes in my code roughly doubled my programs
performance in certain situations. Unfortunately, since my code is kind
of random with the communication, occasionally there will already be too
many MPI calls taking place such that performance is impacted and then
the additional iprobes don't help at all. I guess 1.7 will solve most
of these issues, but until then this will have to do.
Thanks for the help!
Thiago
sreeram potluri wrote:
> Dear Thiago,
>
> I you can spare a thread, making it call MPI_iProbe on a dummy tag
> will help progress in the background. From your description, we think
> that process 0 is the source and is computation intensive. In this
> case having an extra thread at this process should not have a negative
> impact. However, you will have to initialize MPI with MPI_THREAD_MULTIPLE.
>
> MV2 uses process binding by default but in multi-threaded
> environments, it is suggested to disable binding and let OS take care
> of it. Please see this section of our user guide:
>
> http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.6rc2.html#x1-530006.12
>
> Please let us know if this works and if you have any other questions.
>
> Sreeram Potluri
>
More information about the mvapich-discuss
mailing list