[petsc-dev] Backend independent VecGetArray for GPUs

[Ashwin Srinath]

Matthew, I think this fixes the scalar issue:

https://github.com/ashwinsrnth/petsc-pycuda/commit/145b5f138ecbdddf3c8a2ab4caa86e132ece347f

On Sun, Oct 26, 2014 at 9:05 PM, Matthew Knepley <knepley at gmail.com> wrote:

> 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/20141026/399fd7a3/attachment.html>