We have a branch that adds cuda compilation support to the build system so you can drop in .cu files. Dina and I got distracted from the gnu work shortly after writing that though.


On Tue, Jan 7, 2014 at 1:02 PM, Yannick Spill <yannick@salilab.org> wrote:
I can confirm that. I get a 4-16x speedup on a single tesla card. Unfortunately parallelization across multiple gpus is very bad. For that, namd is still the best option.

Dina started to do something cuda-related for saxs.

On 7 janv. 2014, at 21:57, Barak Raveh <barak.raveh@gmail.com> wrote:

A bit of the work that was being done to tune AMBER for GPUs in collaboration with NVIDIA http://www.wmd-lab.org/, I head the performance is phenomenal even on a regular desktop machine. Perhaps we can draw some ideas and apply in IMP? There are now also designated GPU servers available from NVIDIA.

_______________________________________________
IMP-dev mailing list
IMP-dev@salilab.org
https://salilab.org/mailman/listinfo/imp-dev

_______________________________________________
IMP-dev mailing list
IMP-dev@salilab.org
https://salilab.org/mailman/listinfo/imp-dev