Prometheus
Computing cluster
operating system: Linux CentOS 7
configuration: HP Apollo 8000, HPE ProLiant DL360 Gen10
processors: Intel Xeon (Haswell / Skylake)
computing cores: 53604
GPGPU: 144 (Nvidia Tesla K40 XL), 32 (NVidia Tesla V100)
RAM: 282 TB
storage: 10 PB
computing power: 2403 TFlops
current TOP500 rank: 475 (June 2022)
The architecture of the Prometheus supercomputer responds to the diverse needs of scientists by providing resources organized in partitions:
• classic computing servers with high-performance Intel Xeon Haswell and Intel Xeon Gold processors,
• a set of servers with NVIDIA K40 XL graphics processors,
• an acceleration partition with NVIDIA K80 GPGPU cards and Intel Xeon Phi and Nallatech FPGA accelerators,
• a partition dedicated to computing related to artificial intelligence, equipped with 32 GPGPU NVIDIA Tesla V100 graphics accelerators.
Latest article on Prometheus and other supercomputers hosted at ACC Cyfronet AGH can be found: here
More information on the KDM web site (in Polish).