GROMACS development

Today

05:14 PM GROMACS Task #3143 (New): move the non-force accumulation/accounting tasks out of the GPU wait functions

Current code works, but it is too error-prone due to the complex buffer ops/reduction code-path. We would benefit fro...

04:56 PM GROMACS Feature #3142: centralize and clarify GPU force buffer clearing

Note: this is high priority, but we can consider bumping it to beta3 *except* the last item and its impact on the buf...

04:53 PM GROMACS Feature #3142 (New): centralize and clarify GPU force buffer clearing

The responsibility of (rvec) force buffer clearing should be moved into StatePropagatorDataGpu and arranged for such ...

10/13/2019

11:37 PM GROMACS Bug #3125: OpenCL on Volta and Turing borken

Szilárd Páll wrote:
> Here's the relevant clinfo code that we should adopt:
> https://github.com/Oblomov/clinfo/blo...

01:27 PM GROMACS Revision 8a0d4d97: Enable StatePropagatorGpuData for force transfers

Force transfers have been switched to use StatePropagatorGpuData already
before. This change updates the synchronizat...

01:10 PM GROMACS Revision 78956ab8: Move buffer ops / PME F reduction flags into StepWorkload

Also moved overrides conditions for when buffer ops can not be offloaded
into the DevelopmentFeatureFlags data struct...

10/12/2019

08:47 PM GROMACS Bug #3125: OpenCL on Volta and Turing borken

Here's the relevant clinfo code that we should adopt:
https://github.com/Oblomov/clinfo/blob/master/src/clinfo.c#L15...

08:45 PM GROMACS Bug #3125: OpenCL on Volta and Turing borken

Berk Hess wrote:
> > Perhaps we should give the issue a more descriptive title and keep a record of it. It would be ...

10/11/2019

05:57 PM GROMACS Feature #2890: GPU Halo Exchange

@Alan, can you please update the status of the outstanding TODOs and subtasks, in particular #3093 and #3082 and lik...

05:53 PM GROMACS Task #3093: rework GPU direct halo-exchange related force reduction complexities

what is the