Hello Andreas, Thank you for the quick and helpful reply!
None of the existing scikit-cuda routines does what I need, but there is a stub for cuSPARSE within scikit-cuda, which is promising. I’ve posted to an old issue about cuSPARSE and wrapping what I need, so hopefully I’ll get rolling soon: https://github.com/lebedov/scikit-cuda/issues/44 . Best, Ryan > On Apr 8, 2020, at 1:20 PM, Andreas Kloeckner <li...@informa.tiker.net> wrote: > > "Gutenkunst, Ryan N - (rgutenk)" <rgut...@arizona.edu> writes: > >> Hello, >> >> I need to access the tridiagonal solving routines gtsv2StridedBatch >> and gtsvInterleavedBatch from the cuSPARSE library in a Python/C >> program. Is there a way to access/link to the cuSPARSE library using >> PyCUDA? >> >> For background, I’m hoping to port a Python (with inner loops in C) >> application to leverage GPU computing. The most intensive part of the >> computation is solving tridiagonal systems, so I was excited to see >> that the standard cuSPARSE library includes routines for this. But I’m >> struggling to see how to access cuSPARSE using any of the existing >> Python to CUDA interfaces. For PyCUDA, I couldn’t find a similar >> example in the documentation. Pyculib has bindings for an older >> version of cuSPARSE, but it’s not maintained and I couldn’t get it >> installed easily: >> https://pyculib.readthedocs.io/en/latest/cusparse.html. CuPy seems to >> support only a very small fraction of cuSPARSE: >> https://docs-cupy.chainer.org/en/stable/reference/sparse.html . > > There's scikit.cuda, which offers access to cuSOLVER, which bills itself > as "the CUDA sparse matix library." > > https://scikit-cuda.readthedocs.io/en/latest/ > > There's also discussion going on about adapting PyCUDA to Nvidia's > "primary context" notion for easier interoperability with the runtime API. > > Hope that helps, > Andreas > > External Email > > _______________________________________________ > PyCUDA mailing list -- pycuda@tiker.net > To unsubscribe send an email to pycuda-le...@tiker.net -- Ryan Gutenkunst Associate Professor and Associate Department Head Department of Molecular and Cellular Biology, University of Arizona phone: (520) 626-0569, office: LSS 325, web: http://gutengroup.mcb.arizona.edu _______________________________________________ PyCUDA mailing list -- pycuda@tiker.net To unsubscribe send an email to pycuda-le...@tiker.net
