[petsc-dev] Backend independent VecGetArray for GPUs

[Matthew Knepley]

On Sun, Oct 26, 2014 at 7:20 PM, Ashwin Srinath <ashwinsrnth at gmail.com>
wrote:

> Hi,
>
> I re-wrote the code to include the code from this branch - it's made
> everything a lot simpler:
> https://github.com/ashwinsrnth/petsc-pycuda/blob/master/GPUArray.pyx
>

Some notes:

  1) You can check the return type of the PETSc calls for errors

  2) Lisandro, do you have an automatic converter from PetscScalar to a
numpy dtype? Using np.dtype.float64 is dicey.

  Thanks,

    Matt


>
> If I can help with adding the functionality to `petsc4py`, I'd be glad to
> :)
>
> Thanks,
> Ashwin
>
> On Fri, Oct 24, 2014 at 2:43 PM, Lisandro Dalcin <dalcinl at gmail.com>
> wrote:
>
>> On 24 October 2014 03:56, Karl Rupp <rupp at iue.tuwien.ac.at> wrote:
>> >
>> > Both 1) and 2) are now pushed to the feature branch. Any feedback
>> > appreciated :-)
>> >
>>
>> Thanks! Looks good. Ashwin, could you please re-write your code to
>> test this branch? Once you confirm everything's working, we can follow
>> discussing how to better support this in petsc4py.
>>
>>
>> --
>> Lisandro Dalcin
>> ============
>> Research Scientist
>> Computer, Electrical and Mathematical Sciences & Engineering (CEMSE)
>> Numerical Porous Media Center (NumPor)
>> King Abdullah University of Science and Technology (KAUST)
>> http://numpor.kaust.edu.sa/
>>
>> 4700 King Abdullah University of Science and Technology
>> al-Khawarizmi Bldg (Bldg 1), Office # 4332
>> Thuwal 23955-6900, Kingdom of Saudi Arabia
>> http://www.kaust.edu.sa
>>
>> Office Phone: +966 12 808-0459
>>
>
>


-- 
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments lead.
-- Norbert Wiener
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20141026/e757efe1/attachment.html>