On 07/06/2011 10:42 AM, Constantinos Makassikis wrote:
> On Tue, Jul 5, 2011 at 9:48 PM, Robert Sacker <rsacker_at_[hidden]
> <mailto:rsacker_at_[hidden]>> wrote:
> Hi all,
> Hello !
> I need some help. I'm trying to run C++ code in Xcode on a Mac Pro
> Desktop (OS 10.6) and utilize all 8 cores . My ultimate goal is to
> be able to run the code on the cluster here on campus. I'm in the
> process of converting into C++ the number crunching part of the
> stuff I previously wrote in Matlab.
> Is there some documentation that explains how to get started?
> Thanks. Bob
> I am not sure whether this is the relevant mailing list for
> general parallelization questions ...
Well, general MPI questions not specific to OpenMPI are not uncommon here.
> In any case, before converting your Matlab code to C++ try using
> parallelization features that come with Matlab.
> Otherwise, after translating your Matlab code to C++, you should
> consider in the first place getting acquainted with OpenMP and
> use it to speed up your code on your 8-core machine.
> OpenMP can be rather straightforward to apply.
> Afterwards, if necessary, you may look into parallelizing over multiple
> machines with OpenMPI.
Why not just use MPI for every step? Open MPI can detect when
communication partners are on the same host and use shared memory for
improved performance. Not sure how this measures up to OpenMP for
intra-node communications, but I imagine it can make the programming
simpler, since only one syntax needs to be learned/used.
As I said, I don't know the performance difference between MPI and
OpenMP, so if someone can shed some light...