Highlights - November 2019

This is the 54th edition of the TOP500.

Since June 2019 only Petaflop systems have been able to make the list. The total aggregate performance of all 500 system has now risen to 1.65 Exaflops.

Two IBM build systems called Summit and Sierra and installed at DOE’s Oak Ridge National Laboratory (ORNL) in Tennessee and Lawrence Livermore National Laboratory in California kept the first two positions in the TOP500 in the USA.  

The share of installations in China continues to rise strongly. 45.6 % of all system are now listed as being installed in China. The share of system listed in the USA remains near it's all time low at 23.4 %. However, systems in the USA are on average larger, which allowed the USA (37.1%) to stay close to China (32.3%) in terms of installed performance.

There were no changes to the top of the list at all. The first new system shows up only at position 24! It is an IBM Power based system utilizing NVidia Volta GV100 which allowed it to capture the No 3 spot on the Green500 list.

Highlights from the Top 10

Highlights from the List

  • A total of 145 systems on the list are using accelerator/co-processor technology, up from 134 six months ago. 94 of these use NVIDIA Volta chips, 0 use NVIDIA Ampere, and there are now 30 systems with NVIDIA Pascal.

  • Intel continues to provide the processors for the largest share (94.80 percent) of TOP500 systems.

  • We have incorporated the HPCG benchmark results into the Top500 list to provide a more balanced look at performance.

  • The 2 top DOE systems Sierra and Summit also lead with respect to HPCG performance.

  • Japanese systems continue to take leading roles in the Green500. However, the top 2 DOE systems Sierra and Summit also make the top10 in the Green500 and demonstrate the progress in performance efficiency.

  • The entry level to the list moved up to the 1,142.0 Tflop/s mark on the Linpack benchmark.

  • The last system on the newest list was listed at position 399 in the previous TOP500.

  • Total combined performance of all 500 exceeded the Exaflop barrier with now 1.65 exaflop/s (Eflop/s) up from 1.56 exaflop/s (Eflop/s) 6 months ago.

  • The entry point for the TOP100 increased to 2.57 Pflop/s.

  • The average concurrency level in the TOP500 is 126,308 cores per system up from 118,213 six months ago.

General Trends

  • Installations by countries/regions:

  • TOP 10 HPC manufacturer:

  • TOP 10 Interconnect Technologies:

  • TOP 10 Processor Technologies:

Green500

HPCG Results

About the TOP500 List

The first version of what became today’s TOP500 list started as an exercise for a small conference in Germany in June 1993. Out of curiosity, the authors decided to revisit the list in November 1993 to see how things had changed. About that time they realized they might be onto something and decided to continue compiling the list, which is now a much-anticipated, much-watched and much-debated twice-yearly event.