On Tue, 20 Aug 2013, John Peterson wrote:

> It's not clear to me why running this example serially would
> segfault while running it with mpirun would not.

I've seen MPI stacks which actually *required* the mpirun/mpiexec
environment, to the point that "mpirun -np 1" was the only way to
execute an MPI-compiled program on a single processor.

I think even that case was nice enough to give an error message rather
than a segfault, though.  You're right that the latter is suspicious.
---
Roy

------------------------------------------------------------------------------
Introducing Performance Central, a new site from SourceForge and 
AppDynamics. Performance Central is your source for news, insights, 
analysis and resources for efficient Application Performance Management. 
Visit us today!
http://pubads.g.doubleclick.net/gampad/clk?id=48897511&iu=/4140/ostg.clktrk
_______________________________________________
Libmesh-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/libmesh-users

Reply via email to