November 2021

The system to claim the No. 1 spot for the Green500 was MN-3 from Preferred Networks in Japan. Relying on the MN-Core chip and an accelerator optimized for matrix arithmetic, this machine was able to achieve an incredible 39.38 gigaflops/watt power-efficiency. This machine provided a performance 29.7- gigaflops/watt on the last list, clearly showcasing some impressive improvement. It also enhanced its standing on the TOP500 list, moving from No. 337 to No. 302. 

The new SSC-21 Scalable Module an HPE Apollo 6500 system installed at Samsung Electronics in South Korea achieved an impressive 33.98 gigaflops/watt. They did so by submitting an power optimized run of the HPL benchmark. It is listed at  position 292 in the TOP500.

NVIDIA installed a new liquid cooled DGX A100 prototype system called Tethys. With a power optimized HPL run Tethys achieved 31.5 gigaflops/watt and garne red the No. 3 spot on the Green500. It is listed at position 296 in the TOP500.

The Wilkes-3 system improved its results but was still pushed down to the No.4 spot on the Green500.  Wilkes-3, which is housed at the University of Cambridge in the U.K., had a power-efficiency of 30.8 gigaflops/watt. However, it was pushed from No. 100 to No. 281 on the TOP500 list.

The University of Florida in the USA with its HiPerGator AI system was pushed from the No. 2 spot to the No. 5 spot. This machine held steady at 29.52 gigaflops/watt. This NVIDIA system has 138,880 cores and relies on an AMD EPYC 7742 processor. Despite this impressive performance, HiPerGator AI was pushed from No. 22 to No. 31 on the TOP500.

Rmax and Rpeak values are in PFlop/s. For more details about other fields, check the TOP500 description.

Rpeak values are calculated using the advertised clock rate of the CPU. For the efficiency of the systems you should take into account the Turbo CPU clock rate where it applies.

Green500 Data

Rank TOP500 Rank System Cores Rmax (PFlop/s) Power (kW) Energy Efficiency (GFlops/watts)
1 301 MN-3 - MN-Core Server, Xeon Platinum 8260M 24C 2.4GHz, Preferred Networks MN-Core, MN-Core DirectConnect, Preferred Networks
Preferred Networks
Japan
1,664 2.18 55 39.379
2 291 SSC-21 Scalable Module - Apollo 6500 Gen10 plus, AMD EPYC 7543 32C 2.8GHz, NVIDIA A100 80GB​, Infiniband HDR200, HPE
Samsung Electronics
South Korea
16,704 2.27 103 33.983
3 295 Tethys - NVIDIA DGX A100 Liquid Cooled Prototype, AMD EPYC 7742 64C 2.25GHz, NVIDIA A100 80GB​, Infiniband HDR, Nvidia
NVIDIA Corporation
United States
19,840 2.25 72 31.538
4 280 Wilkes-3 - PowerEdge XE8545, AMD EPYC 7763 64C 2.45GHz, NVIDIA A100 80GB​, Infiniband HDR200 dual rail, DELL EMC
University of Cambridge
United Kingdom
26,880 2.29 74 30.797
5 30 HiPerGator AI - NVIDIA DGX A100, AMD EPYC 7742 64C 2.25GHz, NVIDIA A100, Infiniband HDR, Nvidia
University of Florida
United States
138,880 17.20 583 29.521
6 403 Snellius Phase 1 GPU - ThinkSystem SD650-N V2, Xeon Platinum 8360Y 36C 2.4GHz, NVIDIA A100 SXM4 40 GB, Infiniband HDR, Lenovo
SURF
Netherlands
6,480 1.82 63 29.046
7 5 Perlmutter - HPE Cray EX235n, AMD EPYC 7763 64C 2.45GHz, NVIDIA A100 SXM4 40 GB, Slingshot-10, HPE
DOE/SC/LBNL/NERSC
United States
761,856 70.87 2,589 27.374
8 71 Karolina, GPU partition - Apollo 6500, AMD EPYC 7763 64C 2.45GHz, NVIDIA A100 SXM4 40 GB, Infiniband HDR200, HPE
IT4Innovations National Supercomputing Center, VSB-Technical University of Ostrava
Czechia
71,424 6.75 311 27.213
9 45 MeluXina - Accelerator Module - BullSequana XH2000, AMD EPYC 7452 32C 2.35GHz, NVIDIA A100 40GB, Mellanox HDR InfiniBand/ParTec ParaStation ClusterSuite, EVIDEN
LuxProvide
Luxembourg
99,200 10.52 390 26.957
10 262 NVIDIA DGX SuperPOD - NVIDIA DGX A100, AMD EPYC 7742 64C 2.25GHz, NVIDIA A100, Mellanox HDR Infiniband, Nvidia
NVIDIA Corporation
United States
19,840 2.36 90 26.195