Our supercomputers

Helios, a new light for innovation in Polish science and economy

Helios has 36 PFLOPS of theoretical computing power, more than 108 thousand computing cores, 460 TB of RAM, and 18 PB of disk system capacity, which together offer performance of almost 2 TB/s.

The supercomputer was built according to Cyfronet's design by Hewlett-Packard Enterprise based on the HPE Cray EX4000 platform. It consists of three computing partitions:

• CPU equipped with 82 944 AMD Zen4 computing cores and 220 TB of DDR5 RAM,
• GPU equipped with 440 NVIDIA Grace Hopper GH200 superchips,
• INT for interactive work, equipped with 24 NVIDIA H100 accelerators and fast local NVMe memory.

The Helios disk subsystem consists of two types of Lustre file systems: scratch with a capacity of 1.5 PB and a speed of over 1.8 TB/s and project with a capacity of 16 PB and a speed of almost 200 GB/s. All supercomputer components are connected via the Slingshot network with a speed of 200 Gb/s. The HPE Cray EX4000 platform, based on which Helios was built, is also used in constructing the fastest supercomputers in the world (El Capitan, Frontier) and Europe (LUMI). Thanks to direct liquid cooling of the CPU and GPU partitions, it is possible to achieve a very low PUE (Power Usage Effectiveness) for the system, increasing its energy efficiency and reducing operating costs. Additionally, thanks to the recovery of waste heat produced by Helios, it is possible to use it for heating.

Helios' computing power for AI computing is 1.8 ExaFlops.

Helios carries out many research projects for scientists from all over Poland, including in chemistry, physics, materials engineering, energy, medicine, biology and artificial intelligence. Helios was built as part of a project under the Intelligent Development Operational Program, so its computing power can also be used commercially by the economy.

Learn how to get Access to the Helios supercomputer.

Check out the Helios supercomputer documentation.

See the rankings Helios has achieved on the TOP500 and Green500 lists.

Photo gallery

• 
• 
• 
• 
• 

Athena - in 2022 and 2023 the fastest supercomputer in Poland

Athena achieves a theoretical computing power of over 7.7 PFlops. Until the installation of Helios, it was the fastest supercomputer in Poland.

Athena provides the Polish scientific community and economy with computing resources based on processors and GPGPU accelerators, along with the necessary data storage subsystem based on very fast flash memory. Athena's configuration includes: 48 servers with AMD EPYC processors and 1 TB of RAM (a total of 6144 CPU computing cores) and 384 NVIDIA A100 GPGPU cards.

An essential element enabling the effective use of such significant computing power is the provision of a high-performance internal network of the supercomputer (Infiniband HDR with a bandwidth of 4 x 200 Gb/s per server) and a very fast disk subsystem. It is built on open Lustre software, also used in the disk systems of the Prometheus and Ares supercomputers, and dedicated disk servers equipped with NVMe standard flash memory.

Athena's architecture meets the needs of Cyfronet supercomputer users, who use the computing infrastructure for both standard high-performance scientific simulations (HPC) and for applying artificial intelligence (AI) and machine learning (ML) methods in research in medicine, pharmacology, biology, chemistry, physics, and many other fields of science.

Athena's computing power for AI calculations is nearly 240 PFlops.

Find out how to get Access to the Athena supercomputer.

Check out the Athena supercomputer documentation.

See the rankings Athena has achieved on the TOP500 and Green500 lists.

Photo gallery

• 
• 
• 
• 
• 

Ares - powerful support for Cyfronet resources

The Ares supercomputer offers a total computing power of over 4 PFlops (the theoretical performance of the CPU part is over 3.5 PFlops, and the GPU part is over 0.5 PFlops). Ares' power is obtained from computing servers with Intel Xeon Platinum and Xeon Gold processors (37,824 computing cores) and 72 NVIDIA Tesla V100 computing cards.

Ares' computing servers can be divided into three groups:

• 532 servers, each equipped with 192 GB of RAM,
• 256 servers, each with 384 GB of RAM,
• 9 servers, each with 8 NVIDIA Tesla V100 cards.

Ares is also supported by a disk system with a capacity of over 11 PB. InfiniBand EDR network is used for data transmission. The supercomputer is equipped with a liquid cooling system.

Find out how to get Access to the Ares supercomputer.

Check out the Ares supercomputer documentation.

See the rankings Ares has achieved on the TOP500 and Green500 lists.

Photo gallery

• 
• 
• 

Prometheus - listed 15 times on the TOP500

Prometheus, operating at ACK Cyfronet AGH, has been listed 15 times in a row on the TOP500 list of the world's fastest supercomputers since its launch in 2015, with the highest position at 38. Its high placement on the TOP500 list was ensured by its computing power of 2.65 PFlops (PetaFlops), which was achieved primarily by using high-performance servers of the HP Apollo 8000 platform and connecting them with a 56 Gbps superfast InfiniBand network.

The supercomputer has 53,748 computing cores (energy-efficient and high-performance Intel Haswell and Intel Skylake processors) and 283.5 TB of DDR4 technology operating memory. The Prometheus supercomputer has two file systems with a total capacity of 10 PB and an access speed of 180 GB/s. It also features NVIDIA Tesla cards with GPGPUs. Prometheus was built by Hewlett-Packard according to the assumptions developed by Cyfronet experts.

The Prometheus architecture responds to the diverse needs of researchers by providing computing resources organised in partitions:

• classical cluster of computing servers with highly efficient CPU nodes equipped with Intel Xeon Haswell and Intel Xeon Gold processors,
• cluster of servers equipped with graphic accelerators GPGPU NVIDIA Tesla K40 XL,
• acceleration partition including GPGPU NVIDIA K80 cards as well as Intel Xeon Phi 7120P and Nallatech FPGA accelerators,
• partition dedicated to calculations related to artificial intelligence, equipped with GPGPU NVIDIA Tesla V100 graphics accelerators. It is worth mentioning that this partition is a system with computing power over 4 PFlops for tensor operations and 256 TFlops for standard calculations performed on double precision numbers, which made it the fastest dedicated solution for artificial intelligence available for the needs of scientists in Poland at the time.

Prometheus was distinguished by an innovative liquid cooling system. Thanks to the technology used, in its first years of use it was one of the most energy-efficient supercomputers of its class in the world.

To receive additional information about the Prometheus supercomputer, please send a request to: helpdesk (at) plgrid.pl

We also kindly ask you to read the Rules for using computational resources.

Photo gallery

• 
• 
• 
• 
• 
• 

The future technology cluster Faeton, with a theoretical computing power of 288 TFlops, is built from 64 computing servers, each equipped with two Intel Xeon Platinum 8352s processors - supporting application memory encryption, 1 TB of RAM, and 100 Gb/s low-latency Ethernet network adapters. Additionally, 4 computing servers are equipped with 8 TB of Intel Optane SCM memory.

Faeton also includes service servers and 12 storage servers, offering over 1 PB of NVMe disk storage and 12 TB of SCM memory.

This configuration provides an excellent environment for the development of innovative software, particularly in the field of data science and for running applications in a high-performance and highly secure cloud environment.

Faeton will be used to verify the possibilities of applying new technologies, particularly SCM (Storage Class Memory) in computational applications. The installation of such a system will enable work on the application of future technologies in the applications of Polish scientists and enterprises, giving them a competitive advantage by providing a platform that utilizes solutions at an early stage of development, with great potential for innovation.

To gain access to the Faeton supercomputer, please send your request to: helpdesk (at) plgrid.pl

We also kindly ask you to get familiar with the Rules for using computational resources.

Photo gallery

• 
• 
•