The primary true exascale supercomputer, Frontier, is now the quickest on the earth, toppling Fugaku, which held the title for the previous two years, based on the most recent TOPP500 checklist of the perfect performing supercomputers.
An exascale laptop is one that may carry out 1018 (one quintillion) floating level operations per second (1 exaFLOPS), and Frontier, put in at Oak Ridge Nationwide Laboratory in Tennessee, weighed in at 1.12 exaFLOPS.
Frontier additionally captured the title of most power environment friendly supercomputer, producing 62.68 GFLOP per watt.
Frontier’s velocity bumps down Fugaku on the RIKEN Middle for Computational Science (R-CCS) in Kobe, Japan, from number one on the TOPP500 checklist final fall to quantity 2 now. Fugaku scored 442 peta FLOPS (PFLOPS) on the  Excessive Efficiency Linpack (HPL) benchmark, which measures how effectively programs remedy a dense system of linear equations.
TOPP500 notes that the theoretical higher peak of Fugaku is greater than 1exaFLOP, but it surely didn’t show that velocity within the HPL benchmark.
That is Frontier’s first itemizing within the prime 10, and two different supercomputers, each in Europe additionally broke into the checklist. The LUMI system at EUROHPC/CSC in Finland weighed in at quantity 3, and the Adastra system at GENCI-CINES in France got here in at quantity 10.
Right here is the highest 10 checklist.
#1—Frontier
An HPE Cray EX system run by the US Division of Power, Frontier incorporates third Gen AMD EPYCâ„¢ CPUs representing 8,730,112 cores which were optimized for high-performance computing (HPC) and AI with AMD Intuitionâ„¢ 250X accelerators and Slingshot-11Â interconnects.
#2—Fugaku
Fugaku has 7,630,848 cores and was constructed by Fujitsu.
#3—LUMI
LUMI is an HPE Cray EX system on the EuroHPC middle at CSC in Kajaani, Finland with a efficiency of 151.9 PFLOPS.
#4—Summit
An IBM system at Oak Ridge Nationwide Laboaratory in Tennessee, Summit scored 148.8 PFLOPS on the HPL benchmark. It has  4,356 nodes, every with two Power9 CPUs with 22 cores and 6 NVIDIA Tesla V100 GPUs, every with 80 streaming multiprocessors (SM). The nodes are linked by a Mellanox dual-rail EDR InfiniBand community.
#5—Sierra
Related in structure to Summit, Sierra reached 94.6 PFLOPS. It has 4,320 nodes with two Power9 CPUs and 4 NVIDIA Tesla V100 GPUs and is housed on the Lawrence Livermore Nationwide Laboratory, in California. CA, USA
#6—Sunway TaihuLight
Sunway TaihuLight is a machine developed by Nationwide Analysis Middle of Parallel Pc Engineering & Know-how (NRCPC) in China and is put in within the metropolis of Wuxi. It reached 93PFLOPS on the HPL benchmark.
#7—Perlmutter
The perlmutter system is predicated on the HPE Cray Shasta platform, and is a heterogeneous system with each AMD EPYC-based nodes and 1536 Nvidia A100-accelerated nodes. It achieved 64.6 Pflop/s.
#8—Selene
Selene is an Nvidia DGX A100 SuperPOD primarily based on an AMD EPYC processor with Nvidia A100 for acceleration and a Mellanox HDR InfiniBand as a community. It achieved 63.4 Pflop/s and is put in in-house at Nvidia amenities within the US.
#9—Tianhe-2A (Milky Method-2A)
Powered by Intel Xeon CPUs and NUDT’s Matrix-2000 DSP accelerators, it has 4,981,760 cores within the system to realize 61.4 Pflop/s. It was developed by China’s Nationwide College of Protection Know-how (NUDT) and is deployed on the Nationwide Supercomputer Middle in Guangzhou, China.
#10—Adastra
Adestra, put in at GENCI-CINES, is new one other HPE Cray EX system and the second quickest system in Europe. It achieved 46.1 Pflop/s.
Copyright © 2022 IDG Communications, Inc.
