MPI Collectives for Multi-core Clusters: Optimized Performance of the Hybrid MPI+ MPI Parallel Codes. Proceedings of the 48th International Conference on Parallel Processing: Workshops, 18:1-18:10, ACM, New York, NY, USA, 2019. [PUMA: MPI collective communication hybrid memory model myown programming shared] URL
Collectives in hybrid MPI+ MPI code: Design, practice and performance. Parallel Computing, 102669, Elsevier, 2020. [PUMA: MPI collective communications hybrid myown programming] URL
Topology aware Cartesian grid mapping with MPI. September 2018. [PUMA: Cartesian MPI grid hlrs network parallel programming spmt topology] URL