HPCG benchmark

The HPCG (high performance conjugate gradient) benchmark is a supercomputing benchmark test proposed by Michael Heroux from Sandia National Laboratories, and Jack Dongarra and Piotr Luszczek from the University of Tennessee.[1][2] It is intended to model the data access patterns of real-world applications such as sparse matrix calculations, thus testing the effect of limitations of the memory subsystem and internal interconnect of the supercomputer on its computing performance.[3] Because it is internally I/O bound, HPCG testing generally achieves only a tiny fraction of the peak FLOPS of the computer.[4]

HPCG is intended to complement benchmarks such as the LINPACK benchmarks that put relatively little stress on the internal interconnect.[5] The source of the HPCG benchmark is available on GitHub.[6]

As of June 2018, the Summit supercomputer held the top spot in the HPCG performance rankings, followed by the Sierra and the K computer.[7]

See also

References
  1. Hemsoth, Nicole (June 26, 2014). "New HPC Benchmark Delivers Promising Results". HPCWire. Retrieved 2014-09-08.
  2. Dongarra, Jack; Heroux, Michael (June 2013). "Toward a New Metric for Ranking High Performance Computing Systems" (PDF). Sandia National Laboratory. Retrieved 2016-07-04.
  3. Trader, Tiffany (2015-07-16). "LINPACK's 'Companion Metric' Gains Traction". HPCwire. Retrieved 2016-07-04.
  4. Jackson, Adrian (30 July 2015). "HPCG: benchmarking supercomputers". www.epcc.ed.ac.uk. EPCC at the University of Edinburgh. Retrieved 2016-07-04.
  5. Brueckner, Rich (2015-07-13). "Latest HPCG Performance List Complements TOP500". Inside HPC. Retrieved 2016-07-04.
  6. "HPC-G source code". Github. Retrieved 6 February 2019.
  7. "US Regains TOP500 Crown with Summit Supercomputer, Sierra Grabs Number Three Spot". Top500. Top500.org. Retrieved 28 June 2018.



This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.