The problem is that the error, (which shows up as a random NaN, or a sudden jump in the residual, which does not s only occurs while running in parallel on fairly large systems, after a few timesteps. Running a debug case will be painfully slow. I’ve a couple of questions. 1. Will using a devel build help? 2. Can there be problem with having systems defined over various subdomains which have the same name (I am guessing not), Thanks, Subramanya. On Dec 1, 2013, at 3:02 PM, Roy Stogner <[email protected]> wrote:
> > On Sat, 30 Nov 2013, Subramanya Sadasiva wrote: > >> Do you guys know of any free tools that help debug memory errors in >> parallel code? Essentially a free version of total-view? > > If you can replicate the errors on a small problem, valgrind is usable > in parallel. > --- > Roy ------------------------------------------------------------------------------ Rapidly troubleshoot problems before they affect your business. Most IT organizations don't have a clear picture of how application performance affects their revenue. With AppDynamics, you get 100% visibility into your Java,.NET, & PHP application. Start your 15-day FREE TRIAL of AppDynamics Pro! http://pubads.g.doubleclick.net/gampad/clk?id=84349351&iu=/4140/ostg.clktrk _______________________________________________ Libmesh-users mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/libmesh-users
