Foad Sojoodi Farimani wrote:
>
> On Tue, Jul 17, 2018 at 11:29 PM Waldek Hebisch <[email protected]>
> wrote:
>
> > Foad S Farimani wrote:
> > >
> > > I was wondering if there are any plans/attempts to get GPU acceleration
> > for
> > > numerical calculations on FriCAS? OpenCL would be the best API as it is
> > > cross platform and vendor natural.
> >
> > There were some speculations but AFAIK no serious plans or attempts.
> > Note that GPU acceleration is most useful for special "computational
> > kernels". Notable example is linear algebra
>
> True
>
> > -- for linear algebra
> > the simplest way to get GPU acceleration is probably to call
> > extermal library using GPU acceleration. The similar thing
> > is likely for other numeric kernels.
> >
> Which implementations of BLAS and LAPACK FriCAS already uses?
ATM FriCAS does not use BLAS and LAPACK. There are experimental
interfaces to BLAS and LAPACK, but one of main to do items to
make them standard is to find out which versions of BLAS and LAPACK
are available and how exactly to call them.
--
Waldek Hebisch
--
You received this message because you are subscribed to the Google Groups
"FriCAS - computer algebra system" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/fricas-devel.
For more options, visit https://groups.google.com/d/optout.
