I've built Sage on the LittleFe teaching cluster, made of six Intel Atoms in a case I can carry from class to class (littlefe.net, if you're interested).
Sage works just fine on the head node, but won't detect the other nodes. I ran "import sage.parallel.ncpus" and "sage.parallel.ncpus.ncpus()", and just get 2 [just the head node], not the expected 12 [the entire cluster]. I tried putting "-machinefile ~/machines" into the argument of sage.parallel.ncpus.ncpus(), which is what I do with mpirun, but just got errors. Does Sage support distributed memory parallelism (like MPI), or just shared memory parallelism (like OpenMP)? Even if Sage supports distributed memory parallelism, I have a very minimal cluster where only the head node has a hard drive; the other nodes PXE boot off of it. Does that raise other issues for Sage? I teach mathematics at Louisiana's state magnet high school. I'm hoping to set up the cluster to be easy enough to use that the instructors in our Python, C++, Data Structures, Linear Algebra, DiffEq, and Numerical Methods classes will want to use it, at least to introduce students to the idea of parallelism. Being able to use Sage in parallel would be a big step towards "user friendly." Suggestions? Thanks, Brad -- To post to this group, send an email to [email protected] To unsubscribe from this group, send an email to [email protected] For more options, visit this group at http://groups.google.com/group/sage-devel URL: http://www.sagemath.org
