The distributed virtual shared-memory system based on the InfiniBand architecture |
| |
| Affiliation: | 1. Dept. of Computer Engineering, Sharif University of Technology and IPM School of Computer Science, Tehran, Iran;2. Dept. of Computer Science, University of Glasgow, Glasgow G12 8RZ, United Kingdom;3. School of Information Technologies, Sydney NSW 2006, University of Sydney, Australia;1. School of Chemistry, The University of Melbourne, Victoria 3010, Australia;2. CSIRO Manufacturing, Clayton South, Victoria 3168, Australia;1. National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University, China;2. Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education, China;3. Liaoning Engineering Laboratory of Operations Analytics and Optimization for Smart Industry, Northeastern University, China;4. BMW-Brilliance Automobile Industry, Shenyang, China;5. Liaoning Key Laboratory of Manufacturing System and Logistics Optimization, Northeastern University, China;1. Dpto. de Lenguajes y Ciencias de la Computación, Univ. de Málaga, E.T.S. Ingeniería Informática, Campus de Teatinos, 29071 Málaga, Spain;2. Faculty of Science, Assiut University, 71515 Assiut, Egypt |
| |
| Abstract: | Even though there have been strong research activities about distributed virtual shared-memory (DVSM) systems, their architectures have been not widely used in current high-performance computing markets. The reason is that the previously introduced DVSM systems use conventional interconnection technologies like Ethernet, which incurs high execution overhead due to process interruption at data communication for memory consistency. In this paper, we present the DVSM architecture based on the next generation of an interconnection technique, the InfiniBand Architecture (IBA). Because the IBA supports shared-memory programming semantics by means of remote direct-memory access (RDMA) and atomic operations in hardware, we can minimize the communication overhead for memory consistency on the DVSM system. For characterizing multithreaded applications on our IBA-based DVSM system, we examined two different shared-memory programming models, i.e. SPMD and OpenMP benchmarks. We show that our DVSM to use full features of the IBA can improve the performance significantly over the IPoIB-based DVSM system in all benchmarks, and also comparable to the bus-based shared-memory multiprocessor system in some benchmarks. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
