/PLDM

A serial, parallel and vectorised version of PLDM dynamics has been implemented. The serial version uses numba to get speedup of a compiled language. The parallel version uses mpi4py to utilise the multiprocessing capability of HPC clusters. The vectorised version uses a wide variety of GPU libraries (cuda, cupy, pytorch) to highly vectorise PLDM.

Primary LanguagePython

Watchers