THE “CPU+GPU+MIC” HYBRID SUPERCOMPUTER π
DOI:
https://doi.org/10.32010/26166127.2018.1.1.126.128Keywords:
Supercomputer π, CPU, GPU, MIC, Hybrid SupercomputerAbstract
The supercomputer π at Center for HPC (CHPC) of Shanghai Jiao Tong University (SJTU) was the fastest supercomputer among all the universities in China during 2013 to 2015. With a highly hybrid architecture, it is the first “CPU+GPU+MIC” supercomputer in China. It was also the largest Kepler GPU cluster in China when deployed in 2013. In addition, it firstly utilized the “FDR+DDN” combination in China. In this paper, we will introduce the design of supercomputer π.
Downloads
References
[1]. Schulte, M. J. (2015) Achieving exascale capabilities through heterogeneous computing. IEEE Micro 35(4), 26-36.
[2]. Mittal, S., Jeffrey S. V. (2015) A survey of CPU-GPU heterogeneous computing techniques. ACM Computing Surveys (CSUR) 47(4), 69.
[3]. Jin, G., Lin, J., Endo, T. (2014) Efficient utilization of memory hierarchy to enable the computation on bigger domains for stencil computation in CPU-GPU based systems. Proceedings of the International Conference on High Performance Computing and Applications.
[4]. Sîrbu, A., Babaoglu, O. (2016) Power consumption modeling and prediction in a hybrid CPU-GPU-MIC supercomputer. European Conference on Parallel Processing.
[5]. Bientinesi, P. (2015) Parallel computing on graphics processing units and heterogeneous platforms. Concurrency and Computation: Practice and Experience 27(6), 1525-1527.
[6]. Sawadsitang, S. (2015) Understanding Performance Portability of OpenACC for Supercomputers. IEEE International Parallel and Distributed Processing Symposium Workshop.
[7]. Fu, H. (2017) Solving global shallow water equations on heterogeneous supercomputers. PloS one 12(3).
