Gadgets Now Bureau May 26, 2023 7:47 am IST
The 61st edition of the world’s most powerful supercomputers is out. As the name suggests, the Top500 list names the 500 most popular supercomputers in the world. The list shows that AMD, Intel and IBM processors are the preferred choice for supercomputing systems. Of the TOP10, four systems use AMD processors, two Intel processors and two IBM processors. Similar to the previous lists, China and the United States have the most entries in the overall TOP500 list. The United States increased its lead from 126 machines on the last list (December 2022) to 150 on the current list, while China fell from 162 systems to 134. Based on the entire continent, a total of 192 machines were on the list in Asia. North America added 160 systems and Europe offered 133 systems. Here are the 10 most powerful supercomputers in the list.
Subscribe to Gadgets Now notifications for the latest tech news, reviews and more
Frontier installed at Oak Ridge National Lab in Tennessee, USA
Frontier is the #1 system in the TOP500. This HPE Cray EX system is the first US system to exceed 1 exaflop/s performance. It is installed and operated for the Department of Energy (DOE) at Oak Ridge National Laboratory (ORNL) in Tennessee, USA. Currently, 1.194 exaflop/s has been achieved with 8,699,904 cores. HPE Cray EX architecture combines 3rd Gen AMD EPYC CPUs optimized for HPC and AI with AMD Instinct 250X accelerators and Slingshot 11 interconnect.
Image courtesy: Wikipedia
Fugaku installed at the RIKEN Center for Computational Science in Kobe, Japan
Fugaku, the #2 system, is installed at the RIKEN Center for Computational Science (R-CCS) in Kobe, Japan. It has 7,630,848 cores, which enabled it to achieve an HPL benchmark score of 442 pflop/s.
Image courtesy: Japan Times
LUMI system installed at CSC data center in Kajaani, Finland
The LUMI system, another HPE Cray EX system installed at the EuroHPC center at CSC in Finland, is #3 with a performance of 309.1 Pflop/s. The European High-Performance Computing Joint Undertaking ( EuroHPC JU) pools European resources to develop high-end exascale supercomputers for processing large amounts of data. One of the pan-European pre-exascale supercomputers, LUMI, resides at CSC’s data center in Kajaani, Finland.
Leonardo will be installed at the EuroHPC site in CINECA, Italy
The #4 Leonardo system is installed at another EuroHPC site in CINECA, Italy. It is an Atos BullSequana. It achieved a linpack performance of 238.7 pflop/s.
Expand
Summit installed at Oak Ridge National Lab in Tennessee, USA
Summit, an IBM-built system at Oak Ridge National Laboratory (ORNL) in Tennessee, USA, is again ranked #5 worldwide with a performance of 148.8 Pflop/s on the HPL benchmark used for ranking TOP500- List. Summit has 4,356 nodes, each housing two POWER9 CPUs, each with 22 cores, and six NVIDIA Tesla V100 GPUs, each with 80 streaming multiprocessors (SM). The nodes are interconnected via a Mellanox Dual Rail EDR InfiniBand network.
Image courtesy: Wikipedia
Sierra installed at Lawrence Livermore National Laboratory, CA, USA
Sierra, a system at Lawrence Livermore National Laboratory, CA, USA, ranks sixth. Its architecture is very similar to the Summit of system #5. It consists of 4,320 nodes with two POWER9 CPUs and four NVIDIA Tesla V100 GPUs. Sierra reached 94.6 pflop/s.
Image courtesy: Wikipedia
Sunway TaihuLight installed at National Supercomputing Center in Wuxi, China
Sunway TaihuLight, a system developed by China’s National Research Center of Parallel Computer Engineering & Technology (NRCPC) and installed at the National Supercomputing Center in Wuxi, China’s Jiangsu Province, ranked 7th with 93 pflop/s.
Mother of pearl installed at Berkeley Lab, USA
Perlmutter at number 8 is based on the HPE Cray “Shasta” platform and a heterogeneous system with AMD EPYC-based nodes and 1,536 accelerated NVIDIA A100 nodes. Perlmutter reached 64.6 pflop/s
Selene installed in the US
Selene, now ranked 9th, is an NVIDIA DGX A100 SuperPOD installed in-house at NVIDIA in the US. The system is based on an AMD EPYC processor with NVIDIA A100 for acceleration and a Mellanox HDR InfiniBand for networking and achieves 63.4 pflop/s.
Tianhe-2A installed at the National Supercomputer Center in Guangzhou, China
Tianhe-2A (Milky Way-2A), a system developed by China’s National University of Defense Technology (NUDT) and deployed at the National Supercomputer Center in Guangzhou, China, is now operating at 61.4 pflop/s as the No 10 listed.
Image courtesy: Wikipedia
Indian supercomputer in the list
The first Indian entry is the AI supercomputer “AIRAWAT”, which is ranked 75th. The AI supercomputer “AIRAWAT” is installed at C-DAC, Pune. Others included on the list are the supercomputer PARAM Siddhi-AI at number 131; Pratyush supercomputer at #169; and Mihir supercomputer #316.
