On Thu, 14 Jan 2010 13:48:35 +0100, Joa Ljungvall <[email protected]> wrote: > Hi all, > > I have a small question... In a program of mine I'm using libmesh to solve a > PDE. This by having turned example 14 into > a class that inherits from a base class I've written to interface different > FEM packges to my code > (I've solved the same problem using dealii). So I link to libmesh.so (or > dylib, I work on both mac and under linux). To get > this to run I had to compile libmesh without support for MPI. This is not a > big problem for me since the problem at hand not is > big enough to spend the time running it on clusters. However, some threading > would be nice... I tried to compile libmesh with > --enable-tbb and then running example 14, but no threads around? Any ideas?
It's probably worth getting MPI working because even if you integrate element matrices with threads, inserting the entries and solving the system will still be single threaded so the threaded integration will offer very limited benefit. Jed ------------------------------------------------------------------------------ Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev _______________________________________________ Libmesh-users mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/libmesh-users
