GROMACS development

07/19/2019

02:03 PM GROMACS Revision 8e83edea: F buffer operations in CUDA

This patch performs GPU buffer ops for force buffers.
Enable with GMX_USE_GPU_BUFFER_OPS env variable.
Currently, t...

07/05/2019

12:15 PM GROMACS Task #3026 (New): add flags for GPU force buffer op / reduction activation

To activate the GPU path for force buffer ops, we should use two flags:
* one indicating whether the feature is en...

07/04/2019

10:48 AM GROMACS Feature #3022 (New): modernized naming for new GPU developments

Ensure modernized naming in all new kernels - renaming of all the outdated/abbreviated variable names.

10:45 AM GROMACS Feature #3021 (New): Completion of docs for GPU developments

Completion of full doxygen commenting for all new developments.

07/01/2019

11:44 PM GROMACS Revision 32b78914: Bug fix and simplification for CUDA X Buffer Ops

Fixes bug when there are more than two grids (ie they don't naively
map to local/nonlocal), by using a separate GPU m...

05/31/2019

03:11 PM GROMACS Task #2965 (New): Performance of GPU direct communications

This issue is to track testing / evaluating usability / performance of the CUDA-aware MPI and direct copy implementat...

05/22/2019

08:53 PM GROMACS Revision 6e14d4ac: Pin X buffer with DD and use proper abstraction in buffer ops

This patch fixes an issue that the coordinate buffer was not being
pinned with DD, and replaces a raw cudaMemcpy call...

02:29 PM GROMACS Revision f457e9a4: Code quality improvements for CUDA position buffer ops

* improved variable naming
* use of reallocateDeviceBuffer
Follow up to Gerrit change 9169
Implements part of #2934
...

05/10/2019

01:40 AM GROMACS Revision 42b343b9: Position buffer ops in CUDA

On all but search steps the buffer ops transform can now be done on a
CUDA GPU. If PME runs on the same GPU the alrea...

04/25/2019

05:02 PM GROMACS Feature #2934 (New): GPU X Buffer ops

Implement and improve the GPU version of position buffer operations. Gerrit change 9169 implements the functionality,...