TY - GEN
T1 - A comprehensive study of in-memory computing on large HPC systems
AU - Huang, Dan
AU - Qin, Zhenlu
AU - Liu, Qing
AU - Podhorszki, Norbert
AU - Klasky, Scott
N1 - Funding Information:
The authors wish to acknowledge the support from the US NSF under Grant No. CCF-1718297, CCF-1812861, and NJIT research startup fund. This research used resources of the Oak Ridge Leadership Computing Facility and National Energy Research Scientific Computing Center, which are supported by the Office of Science of the U.S. Department of Energy.
Publisher Copyright:
©2020 IEEE
PY - 2020/11
Y1 - 2020/11
N2 - —With the increasing fidelity and resolution enabled by high-performance computing systems, simulation-based scientific discovery is able to model and understand microscopic physical phenomena at a level that was not possible in the past. A grand challenge that the HPC community is faced with is how to handle the large amounts of analysis data generated from simulations. In-memory computing, among others, is recognized to be a viable path forward and has experienced tremendous success in the past decade. Nevertheless, there has been a lack of a complete study and understanding of in-memory computing as a whole on HPC systems. This paper presents a comprehensive study, which goes well beyond the typical performance metrics. In particular, we assess the in-memory computing with regard to its usability, portability, robustness and internal design trade-offs, which are the key factors that of interest to domain scientists. We use two realistic scientific workflows, LAMMPS and Laplace, to conduct comprehensive studies on state-of-the-art in-memory computing libraries, including DataSpaces, DIMES, Flexpath and Decaf. We conduct cross-platform experiments at scale on two leading supercomputers, Titan at ORNL and Cori at NERSC, and summarize our key findings in this critical area.
AB - —With the increasing fidelity and resolution enabled by high-performance computing systems, simulation-based scientific discovery is able to model and understand microscopic physical phenomena at a level that was not possible in the past. A grand challenge that the HPC community is faced with is how to handle the large amounts of analysis data generated from simulations. In-memory computing, among others, is recognized to be a viable path forward and has experienced tremendous success in the past decade. Nevertheless, there has been a lack of a complete study and understanding of in-memory computing as a whole on HPC systems. This paper presents a comprehensive study, which goes well beyond the typical performance metrics. In particular, we assess the in-memory computing with regard to its usability, portability, robustness and internal design trade-offs, which are the key factors that of interest to domain scientists. We use two realistic scientific workflows, LAMMPS and Laplace, to conduct comprehensive studies on state-of-the-art in-memory computing libraries, including DataSpaces, DIMES, Flexpath and Decaf. We conduct cross-platform experiments at scale on two leading supercomputers, Titan at ORNL and Cori at NERSC, and summarize our key findings in this critical area.
KW - Data analytics
KW - High-performance computing
KW - In-memory computing
KW - Workflow
UR - http://www.scopus.com/inward/record.url?scp=85102014416&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102014416&partnerID=8YFLogxK
U2 - 10.1109/ICDCS47774.2020.00045
DO - 10.1109/ICDCS47774.2020.00045
M3 - Conference contribution
AN - SCOPUS:85102014416
T3 - Proceedings - International Conference on Distributed Computing Systems
SP - 987
EP - 997
BT - Proceedings - 2020 IEEE 40th International Conference on Distributed Computing Systems, ICDCS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 40th IEEE International Conference on Distributed Computing Systems, ICDCS 2020
Y2 - 29 November 2020 through 1 December 2020
ER -