Charm++ parallel programming system

["Totoni, Ehsan" <totoni2 AT illinois.edu>]

Hi Dominik,

I'm not aware of anyone who has tried PETSc on AMPI, but I don't think 
compiling with AMPI is a problem. 

AMPI implements all of MPI 1.1 standard as far as I know. Have you 
encountered any function that isn't implemented in AMPI?

A potential problem is that PETSc might not be thread-safe (it might have 
global variables). Multithreaded execution is required for getting most of 
the benefits of AMPI (e.g. load balancing).

Bests,
-Ehsan

________________________________________
From: 
ppl-bounces AT cs.uiuc.edu
 
[ppl-bounces AT cs.uiuc.edu]
 on behalf of Dominik Heller 
[dominik.heller1 AT gmail.com]
Sent: Friday, January 30, 2015 11:20 AM
To: 
charm AT cs.uiuc.edu
Subject: [ppl] [charm] Building PETSc on top of Charm++'s AMPI

Hi,

I'm trying to get PETSc to build on top of Charm++'s Adaptive MPI.
So far I've had no success trying a variety of parameters for the PETSc
configuration script.
Will this be possible at all, with AMPI only being a subset of MPI1.1
and bringing its own suite of compile scripts as well as charmrun?

Thanks,
Dominik
_______________________________________________
charm mailing list
charm AT cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/charm
_______________________________________________
ppl mailing list
ppl AT cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/ppl