[petsc-users] Offloading linear solves in time stepper to GPU

[Jed Brown]

Harshad Sahasrabudhe <hsahasra at purdue.edu> writes:

>>
>> Is your intent to solve a problem that matters in a way that makes sense
>> for a scientist or engineer
>
>
> I want to see if we can speed up the time stepper for a large system using
> GPUs. For large systems with sparse matrix of size 420,000^2, each time
> step takes 341 sec on a single process and 180 seconds on 16 processes. So
> the scaling isn't that good. 

 Surely you're familiar with this.

http://www.mcs.anl.gov/petsc/documentation/faq.html#computers

Is the poor scaling due to increased iteration count?  What method are
you using?

> We also run out of memory with more number of processes.

This sounds like a problem with your code (non-scalable data structure).

Also, the GPU doesn't have more memory than the CPU.

How long does it take to solve that system stand-alone using MAGMA,
including the data transfers?
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 818 bytes
Desc: not available
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20150531/cae5fb7c/attachment.pgp>