Cargando…
Communication-Aware Hardware-Assisted MPI Overlap Engine
Overlap of computation and communication is critical for good application-level performance. Modern high-performance networks offer Hardware-assisted tag matching and rendezvous offload to enable communication progress without involving the host CPU. However, hardware based offload cannot be used in...
Autores principales: | Bayatpour, Mohammadreza, Hashmi Maqbool, Jahanzeb, Chakraborty, Sourav, Kandadi Suresh, Kaushik, Ghazimirsaeed, Seyedeh Mahdieh, Ramesh, Bharath, Subramoni, Hari, Panda, Dhabaleswar K. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7295353/ http://dx.doi.org/10.1007/978-3-030-50743-5_26 |
Ejemplares similares
-
HyPar-Flow: Exploiting MPI and Keras for Scalable Hybrid-Parallel DNN Training with TensorFlow
por: Awan, Ammar Ahmad, et al.
Publicado: (2020) -
MPI Learn: Distributed learning over MPI
por: Guerra Magalhaes, Filipe Pedro
Publicado: (2018) -
MPI@LHC Talk.
por: Jiggins, Stephen
Publicado: (2016) -
CERN-MPI program
por: CERN. Geneva. Electronic Experiments Committee
Publicado: (1973) -
ATLAS Tunes for MPI
por: Wahrmund, S
Publicado: (2012)