Here’s a breakdown of particular particulars for the ten total quickest supercomputer methods on the TOP500 record for Could 2024:
#1: Frontier
This HPE Cray EX system is the primary U.S. system with a efficiency exceeding one Exaflop/s. It’s put in on the ORNL in Tenn., the place it’s operated for the Division of Power (DOE).
- Cores: 8,699,904
- Rmax (PFLOPS): 1,206.00
- Rpeak (PFLOPS): 1,714.81
- Energy (kW): 22,786
#2: Aurora
The Aurora system is put in on the Argonne Management Computing Facility, Illinois, USA, the place it’s also operated for the DOE and holds a preliminary HPL rating of 1.012 Exaflop/s.
- Cores: 9,264,128
- Rmax (PFLOPS): 1,012.00
- Rpeak (PFLOPS): 1,980.01
- Energy (kW): 38,698
#3: Eagle
The No. 3 system is put in by Microsoft in its Azure cloud. This Microsoft NDv5 system relies on Xeon Platinum 8480C processors and Nvidia H100 accelerators and achieved an HPL rating of 561 Pflop/s.
- Cores: 2,073,600
- Rmax (PFLOPS): 561.20
- Rpeak (PFLOPS): 846.84
#4: Supercomputer Fugaku
This method is put in on the RIKEN Middle for Computational Science (R-CCS) in Kobe, Japan. It has 7,630,848 cores which allowed it to realize an HPL benchmark rating of 442 Pflop/s.
- Cores: 7,630,848
- Rmax (PFLOPS): 442.01
- Rpeak (PFLOPS): 537.21
- Energy (kW): 29,899
#5: LUMI
Positioned in CSC’s knowledge middle in Kajaani, Finland, the European Excessive-Efficiency Computing Joint Enterprise (EuroHPC JU) is pooling European assets to develop top-of-the-range Exascale supercomputers for processing huge knowledge.
