On Thu, Oct 25, 2012 at 1:43 PM, Lorenzo Botti <bottilore...@gmail.com> wrote: > http://epubs.siam.org/doi/abs/10.1137/110830125 > I guess you already know this work...
Wow, the matrix multiplication results (Fig. 2) in this paper are pretty damning for "traditional" ETs (Blitz++ and UBLAS). That's something I was not aware of, so thanks for posting it! Otherwise it looks like a toss-up between Eigen3 and Blaze in most of the results, and we already have configure tests in place for Eigen, so that'd be my first choice for anyone wanting to work on this optimization. But let's keep in mind that matrix assembly involves essentially zero dense linear algebra. Anything with better memory alignment than vector<vector> would probably be enough to optimize assembly times... If I had to guess, the most expensive part of applying constraints would probably be the cholesky_solve() stuff, and the reduced basis code uses lu_solve(). Looks like Blaze may not have those features yet (at least as of August 2012) http://listengine.tuxfamily.org/lists.tuxfamily.org/eigen/2012/08/msg00041.html again making Eigen the more natural choice. -- John ------------------------------------------------------------------------------ Everyone hates slow websites. So do we. Make your web apps faster with AppDynamics Download AppDynamics Lite for free today: http://p.sf.net/sfu/appdyn_sfd2d_oct _______________________________________________ Libmesh-devel mailing list Libmesh-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/libmesh-devel
