Difficult to say as it depends upon so many things that you haven't described. What do you do to "test a hypothesis"? Is each test an MPI job? If so, how big? Do they all run at the same time? Do all the tests need to participate in this "aggregate function"?
Achieving subsecond response while running millions of tests seems a stretch unless those tests are rather trivial
On May 8, 2013, at 7:54 AM, Robobeans <robobeans_at_[hidden]> wrote:
> Any thoughts about this? Thanks for your time.
> On May 7, 2013, at 10:48 AM, RoboBeans <robobeans_at_[hidden]> wrote:
>> Are people in community using MPI libraries in their application for real time processing / analytics? I have access to a cluster with infiniband and want to test millions of hypotheses and depending upon which one passed would run an aggregate function over them. I would like to achieve a subsecond response for this and was wondering how one could take care of the network calls overhead? Thanks!
> users mailing list