Events: 13th HPCG Performance List
HPCG Performance List announced at a ISC 2020
HPCG Performance List announced at a ISC 2020

The new HPCG Performance List was announced at the ISC 2020 conference in Frankfurt am Main in Germany. The session entitled TOP500, Green500 & HPCG Awards took place on Monday, June 22, 2020.

The HPCG results are now integrated into the TOP500 list. The main HPCG list of results contains the complete list of submissions some of which might have not made the TOP500 list.

The bi-annual High Performance Conjugate Gradients (HPCG) Benchmark list was announced on June 22, 2019 at the ISC 2020 conference.

This is the thirteenth list produced for the benchmark designed to complement the traditional High Performance LINPACK (HPL) benchmark used as the official metric for ranking the TOP500 systems. The first HPCG list was announced at ISC 2014 over six years ago, containing only 15 entries. Since then, HPCG list was released bi-annually and the number of entries has steadily increased as the new results became available. The current list contains nearly 170 entries as HPCG continues to gain traction in the HPC community.

It is now customary that the new list contains entries from many of the TOP500's highest ranked, mainly top-50 systems — 71 system cross-list in total. The current list is no exception. However, the HPCG ranking continues to provide a significantly different ordering of the machines when compared with the TOP500 ranking. A major change in TOP500 ranking is now reflected in the HPCG results. Fugaku system from Japan leads the list with over 13 Pflop/s achieved performance. Summit and Sierra supercomputers no longer lead the HPCG list with their score breaking the 1 Pflop/s barrier and almost approaching 3 Pflop/s for the number 2 system.

Summary highlights from the 13th HPCG list include:

  • The new #1 entry, Fugaku housed at RIKEN, is more than 4.5x faster than the previous top-ranked Summit hosted at ORNL.
  • Fugaku is nearly as fast as all the other entries on the list combined which indicates large performance skew at the top of the list.
  • Entering the top-10 part of the list now requires performance close to 400 Tflop/s.
  • With addition of Selene supercomputer, HPCG list now features 5 generations of GPU accelerators from NVIDIA: Fermi, Kepler, Pascal, Volta, and Ampere.
  • New type of accelerator appeared on the list based on NEC SX-Aurora TSUBASA vector processor.

Jul 13 2020 Contact: Admin Login