LAPACK and ScaLAPACK Survey Results - ordered by question
ScaLAPACK Usage
Question #3. If using another package, which one(s)? | Response | Count | Percent |
|---|
| PLAPACK | 10 | 43% | | | LAPACK - SCALAPACK does not support SVD | 1 | 4% | | | SuperLU | 1 | 4% | | | PESSL (IBM) | 1 | 4% | | | LAPACK | 1 | 4% | | | LAPACK -- matrices are local to node | 1 | 4% | | | (we use coarse-gain parallelization above the numerical layer) | 1 | 4% | | | Matlab | 1 | 4% | | | MPIBNCpack | 1 | 4% | | | I usually write my own solvers. | 1 | 4% | | | PETSc | 1 | 4% | | | Typically, I use pESSL, but use ScaLAPACK or PLAPACK when users have the need (prefer PLAPACK, especially to build a custom solver/routine). | 1 | 4% | | | symmlq | 1 | 4% | | | self written | 1 | 4% | |
|