Benchmarking of high performance computing clusters with heterogeneous CPU/GPU architecture

The most modern supercomputers are clusters of computing nodes with a heterogeneous architecture; in such a node we can see both classical CPUs and specialized computing coprocessors (GPU-or MIC-based). Modern benchmark tests are oriented either for CPU or for specific coprocessor calculations — but not in a whole thing. This article is dedicated to describe an approach to build a unified performance test for a heterogeneous HPC cluster with CPU/GPU computing nodes.

[1]  Massimiliano Fatica,et al.  Performance analysis of the high-performance conjugate gradient benchmark on GPUs , 2016, Int. J. High Perform. Comput. Appl..

[2]  Haihang You,et al.  HPC Benchmark Assessment with Statistical Analysis , 2014, ICCS.

[3]  Jack J. Dongarra,et al.  The LINPACK Benchmark: past, present and future , 2003, Concurr. Comput. Pract. Exp..

[4]  Claudio Pica,et al.  BSMBench: A flexible and scalable HPC benchmark from beyond the standard model physics , 2014, International Symposium on High Performance Computing Systems and Applications.

[5]  Erich Strohmaier,et al.  The TOP500 List and Progress in High-Performance Computing , 2015, Computer.

[6]  Claudio Pica,et al.  BSMBench: a flexible and scalable supercomputer benchmark from computational particle physics , 2014, ArXiv.

[7]  A. Rawat,et al.  Analysis of process distribution in HPC cluster using HPL , 2012, 2012 2nd IEEE International Conference on Parallel, Distributed and Grid Computing.

[8]  Shubham Gupta,et al.  Generating Performance Analysis of GPU compared to Single-core and Multi-core CPU for Natural Language Applications , 2011 .

[9]  David A. Wood,et al.  A comparative analysis of microarchitecture effects on CPU and GPU memory system behavior , 2014, 2014 IEEE International Symposium on Workload Characterization (IISWC).

[10]  I. V. Chugunkov,et al.  Three-dimensional data stochastic transformation algorithms for hybrid supercomputer implementation , 2014, MELECON 2014 - 2014 17th IEEE Mediterranean Electrotechnical Conference.