POOMA vs PETSc on Beowulf Clusters
kaustuv at stanford.edu
Fri Feb 14 09:48:29 PST 2003
I am looking for a nice matrix library for parallel applications (mostly
solution of Partial Differential Equations on structured Grids over
cluster of linux boxes), and after a lot of web-searching I stumbled upon
these two...PETSc and POOMA. Having gone through the manuals of the two I
had following comparision chart:
+ Easy development of parallel applications & is in public domain.
+ Lot of Numerical libraries supported (Basic Backend is LAPACK)
+ Writen in C, so should give highly optimized code even with average
- You cannot extract an single indivisual element of array directly.
- No Stencils (like ones available in BLITZ++/POOMA) to make life easy.
- Not suited for Matrix Free methods for it assumes you finally have a
matrix (which might be costly to create even in compressed format)
+ Easy development of parallel applications & is in public Domain.
+ Stencils via expression templates. So coding is a simplified.
- Makes heavy use C++ expression templates which I believe mihgt hinder
compiler level optimization. In any case they lead to code bloat
- No support for numeric linear libraries (cf. PETSc)
Can some one please share theri experiences of their use with the two
libraies (advantages - disadvatages - suggestions - scalability)?
More information about the Beowulf