Skip to content

Replace direct calls to CUDA memory management API with wrappers in NBNXM

Artem Zhmurov requested to merge devicebuffer_ReplaceDirectCUDACallsNBNXM into master

Replace cudaMalloc(...) and cudaMemset(...) with the respective wrappers in CUDA implementation of NBNXM.

Refs #3318 (closed) Refs #3311 (closed)

From: https://gerrit.gromacs.org/#/c/gromacs/+/16541/

Compare with the parent: https://gitlab.com/gromacs/gromacs/-/compare/devicebuffer_RemoveDuplicatingCopyWrappersInCUDA...devicebuffer_ReplaceDirectCUDACallsNBNXM

Edited by Artem Zhmurov

Merge request reports