This site may earn affiliate commissions from the links on this folio. Terms of use.

Today brings a new TOP500 list of the 500 fastest supercomputers in the world. And China still sits on top, with the number one and number two systems: Sunway TaihuLight, at a Linpack rating of 93 petaflops, and Tianhe-2, at 34 petaflops.

That said, two new systems are in the top x, both of which run Intel Knights Landing Xeon Phi 7250 68-core processors: Cori, a new Cray XC40 at Berkeley Lab'due south National Energy Research Scientific Computing Center (NERSC), lands at number five with a rating of 14 petaflops. Oakforest-PACS, a Fujitsu Primergy CX1640 M1 cluster, scored 13.half dozen petaflops; it resides in Japan'due south Joint Center for Advanced High Performance Computing.

"In improver to matching each other in system count in the latest rankings, People's republic of china and the US are running neck and neck in aggregate Linpack performance," the TOP500 team said in a argument. The grouping said the US holds the narrowest of leads, with 33.ix pct of the total, and that China is 2d with 33.3 pct. The full operation of all 500 computers on the list adds upward to 672 petaflops, sixty percentage higher than it was a year ago; in June, it was 566 petaflops.

Other cardinal data: Of the 500 systems now in the listing, Intel chips power 462 of them. IBM Ability chips account for 22, and AMD has simply seven. Manycore accelerators are nowadays in 96 of the systems, with 60 using Nvidia GPUs, 21 using Xeon Phi, one using AMD FirePro, one with PEZY, and three employing a combo of Nvidia and Intel Xeon Phi GPUs. Gigabit Ethernet interconnect is nowadays in 206 systems, while InfiniBand technology accounts for 187. Intel's relatively new Omni-Path went up from eight systems to 28 this time around.

Here'southward the electric current list of the 10 fastest supercomputers in the world:

1. TaihuLight: Sunway MPP, SW26010; National Supercomputing Center in Wuxi, China; ten.6 million cores (93.01 petaflop/due south).

2. Tianhe-2: Thursday-IVB-FEP Cluster; National Super Computer Center in Guangzhou, China; three.12 million cores (33.86 petaflop/due south).

three. Titan: A Cray XK7 system at the Department of Energy's Oak Ridge National Laboratory (17.59 petaflop/south).

iv. Sequoia: An IBM BlueGene/Q organization located at the Department of Free energy'southward Lawrence Livermore National Lab in California, with 1.57 1000000 cores.

five. Cori: A Cray XC40 at Berkeley Lab'southward National Energy Enquiry Scientific Computing Heart (NERSC) (14 petaflop/s).

6.Oakforest-PACS: A Fujitsu Primergy CX1640 M1 cluster located at Japan'due south Joint Middle for Advanced High Performance Computing (thirteen.half-dozen petaflop/s).

7. One thousand Computer: A SPARC64 organization with 705k cores at RIKEN Avant-garde Institute for Computational Science in Japan (10.v petaflop/s).

8. Piz Daint: Cray XC30 with 116k Xeon and Nvidia cores; located at the Swiss National Computing Centre in Switzerland; new Nvidia P100 GPUs boosted this i by 3.five petaflops, and then it'south notwithstanding at number eight (9.8 petaflop/due south).

nine. Mira: IBM BlueGene/Q; DOE/SC/Argonne National Laboratory, Usa; inside are 786k custom IBM cores (8.half-dozen petaflop/s).

10.Trinity: A Cray XC40 at DOE/NNSA/LANL/SNL in the US; it contains 301,056 Xeon E5-2698v3 cores (8.ane petaflop/s).

Height epitome credit: Jack Dongarra, Study on the Sunway TaihuLight Organisation, June 2022