[SciPy-Dev] Enhancement Request: SuperLU_dist/SuperLU_mt replace current scipy.sparse.superLU

[Ralf Gommers]

On Tue, Jun 1, 2021 at 6:40 AM Neil Godber <njgodber at gmail.com> wrote:

> Hi Dev-List,
>
> Regarding Replace superLU sequential with superLU dist · Issue #14096 ·
> scipy/scipy (github.com) <https://github.com/scipy/scipy/issues/14096>,
> would it be preferable to retain the sequential version a,d simply adding
> the mt version as an  option or would should simply swap out sequential for
> mt?
>

Typically we'd want to use the `workers=None` API pattern (see, e.g.
`scipy.fft.fft`) to avoid auto-parallelization by default. Reason: that
messes with multiprocessing.

I'd hope that we would be able to replace the sequential superLU code with
the MT version, rather than carry duplicate code around. This assumes that
asking for 1 thread from the MT version gives identical results and
performance as the sequential version. That would need checking.



> On Sun, 30 May 2021 at 09:40, Neil Godber <njgodber at gmail.com> wrote:
>
>> Hi Ralf,
>>
>> Saw your comment on the issue. Is there anything else I can do to help?
>> Unfortunately my C/C++ skills are lacking so I'm not sure how much help I
>> on the actual integration itself.
>>
>
Not sure - someone needs to volunteer to dig into the C code, without that
not much is going to happen. After initial conversion is done, extra
testing and writing more tests will be useful contributions.

Cheers,
Ralf
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scipy-dev/attachments/20210609/80c49127/attachment.html>