HPCG benchmark

From Wikipedia, the free encyclopedia

The High Performance Conjugate Gradients 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 (the data for the benchmark resides in main memory as it is too large for processor caches), HPCG testing generally achieves only a tiny fraction of the peak FLOPS the computer could theoretically deliver.[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]

In June of 2020, Summit was superseded by Fugaku with a speed of 16.0 HPCG-petaflops (an increase of 540%). Summit is currently 4th,[8] LUMI 3rd and Frontier 2nd.

See also[edit]

References[edit]

  1. ^ Hemsoth, Nicole (June 26, 2014). "New HPC Benchmark Delivers Promising Results". HPCWire. Archived from the original on 2014-09-08. 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. Archived from the original (PDF) on August 20, 2013. Retrieved 2016-07-04.
  3. ^ Trader, Tiffany (2015-07-16). "LINPACK's 'Companion Metric' Gains Traction". HPCwire. Archived from the original on 2016-05-30. Retrieved 2016-07-04.
  4. ^ Jackson, Adrian (30 July 2015). "HPCG: benchmarking supercomputers". www.epcc.ed.ac.uk. EPCC at the University of Edinburgh. Archived from the original on 2016-08-20. Retrieved 2016-07-04.
  5. ^ Brueckner, Rich (2015-07-13). "Latest HPCG Performance List Complements TOP500". Inside HPC. Archived from the original on 2016-05-28. Retrieved 2016-07-04.
  6. ^ "HPC-G source code". Github. Archived from the original on 11 June 2018. Retrieved 6 February 2019.
  7. ^ "US Regains TOP500 Crown with Summit Supercomputer, Sierra Grabs Number Three Spot". Top500. Top500.org. Archived from the original on 25 March 2021. Retrieved 28 June 2018.
  8. ^ "HPCG - November 2022 | TOP500". www.top500.org. Archived from the original on 2023-01-20. Retrieved 2023-02-08.

External links[edit]