Performance analysis of a hybrid MPI/OpenMP application on multi-core clusters |
| |
| Authors: | Martin J Chorley David W Walker |
| |
| Institution: | 1. Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovi?a 6, 21000 Novi Sad, Serbia;2. Scientific Computing Laboratory, Institute of Physics Belgrade, University of Belgrade, Pregrevica 118, 11080 Belgrade, Serbia;3. School of Physics, Bharathidasan University, Palkalaiperur Campus, Tiruchirappalli–620024, Tamil Nadu, India;4. Instituto de Física Teórica, UNESP–Universidade Estadual Paulista, 01.140-70 São Paulo, São Paulo, Brazil;1. DIBRIS, University of Genoa, Via Opera Pia 13, I-16145, Genoa, Italy;2. DITEN, University of Genoa, Via Opera Pia 11A, I-16145, Genoa, Italy;1. Department of Computer Systems Engineering and Telematics, University of Extremadura, Avd. Universidad s/n, 10003 Cáceres, Spain;2. Department of Computer and Communications Technology, University of Extremadura, Avd. Universidad s/n, 10003 Cáceres, Spain |
| |
| Abstract: | The mixing of shared memory and message passing programming models within a single application has often been suggested as a method for improving scientific application performance on clusters of shared memory or multi-core systems. DL_POLY, a large scale molecular dynamics application programmed using message passing programming has been modified to add a layer of shared memory threading and the performance analysed on two multi-core clusters. At lower processor numbers, the extra overheads from shared memory threading in the hybrid code outweigh performance benefits gained over the pure MPI code. On larger core counts the hybrid model performs better than pure MPI, with reduced communication time decreasing the overall runtime. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
