[Beowulf] mpich vs hp mpi performance

[Linus Harling]

Alan Louis Scheinine skrev:
> It depends very much on hardware and on the specific program.
> My experience with MPICH on Ethernet and MVAPICH, MVAPICH2,
> OpenMPI on Infiniband is that different programs find one
> or the other better, no clear winner.  Also, small changes
> in some options that one learns about from other sites or
> from Google can make big differences in performance.

Thank you for the input! The system is a Dell T605 2x4core Opteron 2354
 with 32GB RAM. With a second one like it being added (probably using
ethernet) if need arises. Which means most/all of the communication will
be by shared memory to begin with.

The app is LS-DYNA, a FEM-suite from LSTC: http://www.ls-dyna.com/

I'm just a sysadmin tasked with installing the machine, and have limited
knowledge in math, but my guess is that the code is quite
communication-heavy considering the specs of the machine and an
assumption that FEM is essentially SIMD. Am I correct in my assumptions
and does anyone have any experience of different mpi-implementations on
such codes?

/Linus H

> I regret that I have no organized documentation or performance
> tables that could provide a more precise answer.
> Alan Scheinine