Skip to content

PERUN Supercomputer

Overview

The PERUN Supercomputer, operated at the Technical University of Košice, represents a technological pillar of Slovakia's national research infrastructure. It is designed to deliver top-tier computational performance for projects in artificial intelligence, modeling, simulations, big data processing, and next-generation scientific research. PERUN features 12,800 CPU cores and an accelerated computing segment equipped with 208 NVIDIA H200 GPU units, among the most powerful AI accelerators in the world. The system provides 29.3 TB GPU memory and 115.2 TB system memory, enabling the processing of exceptionally large and complex computational tasks. High throughput and efficient cooperation among computing nodes are ensured by a 400 Gbit InfiniBand network infrastructure. The total installed performance of the PERUN supercomputer reaches 10.7 PFlops (Rmax), placing it among the most advanced HPC systems in the European Union. The infrastructure also includes the Qaptiva 808 quantum simulator, the first installed quantum simulator in Slovakia, expanding opportunities in quantum algorithm development and testing. By integrating classical high-performance and quantum computing, the Supercomputing Center at TUKE provides a unique environment supporting research, innovation, and technological progress aligned with global trends. PERUN Supercomputer

PERUN Architecture

Universal Computing Partition (PERUN Universal)

This partition is designed for a wide range of HPC workloads — from parallel scientific simulations to data-intensive applications.

  • Number of nodes: 32 × HPE Cray XD2000 (XD225v)
  • Processor: 2 × AMD EPYC 9745 (256 cores per node)
  • Memory (RAM): 1,536 GB DDR5 ECC
  • Networking:
  • 2 × 100 Gb/s Ethernet
  • 1 × 200 Gb/s NDR200 InfiniBand

This partition delivers high computational performance for traditional HPC applications, optimized parallel algorithms, and workloads with demanding memory requirements.

Accelerated GPU Partition (PERUN AI)

This partition is dedicated to the most demanding computations in artificial intelligence, machine learning, numerical simulations, and data-intensive workloads utilizing GPU acceleration.

  • Number of nodes: 26 × HPE ProLiant Compute XD685
  • Processor (CPU): 2 × AMD EPYC 9535 (128 cores per node)
  • GPU Accelerator: 8 × NVIDIA H200 (141 GB HBM3e each)
  • Memory (RAM): 2,304 GB DDR5 ECC
  • Networking:
  • 2 × 100 Gb/s Ethernet
  • 4 × 400 Gb/s NDR InfiniBand
  • GPU-to-GPU bandwidth: 900 GB/s
  • GPU-to-CPU bandwidth: 128 GB/s
  • Internal GPU Network: NVIDIA NVLink

Thanks to the NVIDIA Hopper architecture and its high-throughput interconnects, this partition provides exceptional performance for massively parallel workloads, neural-network training, and large-scale data modeling.

Performance and Flexibility

By combining the universal CPU partition and the accelerated GPU partition, the PERUN system enables optimal allocation of computing resources for diverse scientific and industrial tasks.

Its architecture ensures high performance, stability, and scalability to support research, education, and innovative technological projects.

  • Total Performance: 10.7 PFlops (Rmax)

The PERUN Supercomputer is connected to a high-speed InfiniBand network and the HPC PERUN data storage system, enabling efficient data processing and full utilization of available computational power.