- Registered on: 12/21/2018
- Last connection: 02/21/2020
- 02:02 PM GROMACS Task #3370: Further improvements to GPU Buffer Ops and Comms
- OK, noted. I will update the existing patches in gerrit accordingly.
- 10:04 AM GROMACS Task #3370: Further improvements to GPU Buffer Ops and Comms
- The idea is to try and simplify the logic in do_force (and do_md) by unifying flags and ultimately code-paths, to imp...
- 09:34 AM GROMACS Feature #2817: GPU X/F buffer ops
- I had already moved the TODO into https://redmine.gromacs.org/issues/3370 ("Force buffer op and reduction cleanup/imp...
- 09:15 PM GROMACS Task #3106 (Closed): Implement multiple pulses with GPU communication
- Merged in https://gerrit.gromacs.org/c/gromacs/+/14723
- 12:48 PM GROMACS Feature #2915 (In Progress): GPU direct communications
- 12:47 PM GROMACS Feature #2816 (Closed): GPU offload / optimization for update&constraits, buffer ops and multi-gpu communication
- Closing this old parent task, superseded by new large tasks listed here: https://redmine.gromacs.org/projects/gromacs...
- 12:45 PM GROMACS Task #3180: Remove extra D2H and H2D copies of coordinates when the COM motion is compensated.
- Moving out of old parent task, so I can close it. Artem, does this best belong in one of your new umbrella tasks?
- 12:41 PM GROMACS Feature #2890 (In Progress): GPU Halo Exchange
- 12:40 PM GROMACS Feature #2891 (In Progress): PME/PP GPU communications
- 12:38 PM GROMACS Task #2965 (In Progress): Performance of GPU direct communications
Also available in: Atom