Accelerate

[Ben Lever]

Hi Manuel,

I just pushed a patch with stencil support in the frontend and interpreter.  There are still three smaller items missing:

This is great! I've pulled the latest changes and have started using stencil in the algorithm we're currently porting.


* Add 'stencil2' — Ben, do you need this at the moment? (should be easy to add)

I don't think I'll need stencil2 for the current algorithm, so there's no rush for it. It may be simple enough for us to have a go at implementing.


* Add support for up to 9-tuples (currently, the maximum is 5-tuples) — trivial cut-copy-paste job

I will need 8-tuple support so I'll look at adding support for up to 9-tuples.


* Add support to reify the stencil shape for the CUDA backend — should maybe go into a new module D.A.A.Analysis.Stencil (main question is what the nicest representation of the reified form is, remember that stencil can be irregular)


I spoke with Trevor this morning about this and together we will work on the CUDA backed. Rami and I we be able to contribute the CUDA stencil skeleton and Trevor is going to take a look at what's required in the Haskell-portion of the backend.


Regards,

Ben Lever
Senior Researcher Engineer
National ICT Australia

NICTA l Locked Bag 9013 l Alexandria NSW 1435
T + 612 8306 0742 | F +612 9376 2027
www.nicta.com.au<http://www.nicta.com.au/> l ben.lever at nicta.com.au<mailto:ben.lever at nicta.com.au>