URL: https://doi.org/10.1109/TPDS.2022.3153113
Authors: Martinez-Ferrer, P. / Yzelman, A. / Beltran, V.
Publication: IEEE Transactions on Parallel and Distributed Systems
Volume / Number / Pagination: 33 / 12 / 3363-3374
Palabras clave: Parallel algorithms, shared memory, tensor computations, high bandwidth memory, NUMA