- Registered on: 12/21/2018
- Last connection: 07/05/2019
- 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.
- 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...
- 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- Ensure modernized naming in all new kernels - renaming of all the outdated/abbreviated variable names.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.
- 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...
- 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...
- 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
- 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...
- 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,...
Also available in: Atom