Atos Launches First Supercomputer Equipped with NVIDIA A100 GPU

New Atos accelerator blade enables JUWELS BullSequana technique to come to be the most strong

New Atos accelerator blade enables JUWELS BullSequana technique to come to be the most strong supercomputer in Europe

Paris, France, May fourteen 2020

Atos, a worldwide leader in electronic transformation, nowadays announces its new BullSequana X2415, the initially supercomputer in Europe to combine NVIDIA’s Ampere future-generation graphics processing unit architecture, the NVIDIA® A100 Tensor Main GPU. This new supercomputer blade will supply unprecedented computing ability to raise software performance for HPC and AI workloads, tackling the difficulties of the exascale era. The BullSequana X2415 blade will maximize computing ability by more than two* and enhance vitality consumption many thanks to Atos’ one hundred% remarkably productive h2o-cooled patented DLC (Immediate Liquid Cooling) remedy, which utilizes heat h2o to awesome the machine.

Forschungszentrum Julich Ralf-Uwe Limbach

Forschungszentrum Jülich will combine this new blade into its booster module, extending its current JUWELS BullSequana supercomputer, generating it the initially technique worldwide the use this new engineering. The JUWELS Booster will provide scientists across Europe with significantly amplified computational means. Some of the projects it will gas are the European Commission’s  Human Mind Project  and the Jülich Laboratories of  “Climate Science” and “Molecular Systems”. Once thoroughly deployed this summer the upgraded supercomputing technique, operated under ParTec’s computer software ParaStation Modulo, is expected to provide a computational peak performance of more than 70 Petaflops/s generating it the most strong supercomputer in Europe and a showcase for European exascale architecture.

“By integrating the most effective systems out there, such as this most recent blade from Atos which includes NVIDIA’s strong A100 GPU into our supercomputer, we are equipped to raise our supercomputing ability. This is an essential milestone on our path to achieve our top goal of furnishing exascale abilities to science and marketplace” reported Prof. Thomas Lippert, Director of the Jülich Supercomputing Centre (JSC).

“We’re happy to be a single of the initially supercomputer manufacturers worldwide to involve NVIDIA’s A100 GPU and to be equipped to provide scientists worldwide the greatest software performance for their HPC and AI workloads reported Agnès Boudot, Senior Vice President, Head of HPC & Quantum at Atos.  “We’re truly thrilled to be working with Jülich to raise its computing ability and to permit its JUWELS technique to come to be the most strong supercomputer in Europe.”

“Atos is a single of the leading players environment-extensive in the substantial stop of the server industry. It is the foremost European-dependent vendor of HPC methods, largely because of to the performance and ability of its BullSequana methods, its potent technological abilities and innovation and its ability to effectively handle significant-scale projects globally. It has doubled its presence in the TOP500 position over the past 5 years and its server industry share worldwide continues to expand. We see Atos as a single of the crucial supercomputing manufacturers that will most likely reward over the future couple years as need for exascale methods results in being more considerable.” said Steve Conway, Senior Advisor at Hyperion Exploration.

The new blade functions an NVIDIA HGX-A100 base-board outfitted with four NVIDIA A100 GPUs connected via third-generation NVIDIA NVLink™ engineering, along with two AMD EPYC CPUs and up to four NVIDIA Mellanox InfiniBand ports connected via a Dragonfly+ configuration. The NVIDIA Ampere architecture is a groundbreaking engineering achievement that provides a massive performance advancement over the past generation for AI coaching and inference. The NVIDIA A100 Tensor Main GPU functions the world’s most significant 7-nanometer processor, with more than 54 billion transistors. This staff of systems, together with the NVIDIA industry-foremost ecosystem of over 700 GPU-accelerated HPC apps and assist from NGC, will allow scientists to hit the floor operating with containerized computer software optimized for the improvement and deployment of GPU-accelerated HPC and AI projects.

The BullSequana X2415 will be out there in Q2 of 2020.



* in comparison to Atos’ current GPU blade


X2415 requirements

 1U kind component blade with one acceleration node.

Immediate Liquid Cooling.

For each node:

one x CPU Board with

  • two x AMD EPYC/Milan CPUs
  • 16 x DDR4 32GB @3200MTs minimum amount

one x GPU board “HGX-A100” with 4 x NVIDIA A100 GPUs

two x Interconnect Mezzanine boards (BXI or HDR200)

Optional one x M.two SATA SSD up to one.92TB or one x M.two NVMe SSD 960GB


About Atos

Atos is a worldwide leader in electronic transformation with a hundred and ten,000 workforce in seventy three countries and once-a-year revenue of € twelve billion. European range a single in Cloud, Cybersecurity and Substantial-Performance Computing, the Group presents stop-to-stop Orchestrated Hybrid Cloud, Huge Information, Organization Purposes and Electronic Office answers. The Group is the Around the globe Information and facts Technologies Companion for the Olympic & Paralympic Game titles and operates under the brands Atos, Atos|Syntel, and Unify. Atos is a SE (Societas Europaea), shown on the CAC40 Paris stock index.

The goal of Atos is to help design the long term of the information and facts place. Its abilities and expert services assist the improvement of know-how, education and investigate in a multicultural tactic and contribute to the improvement of scientific and technological excellence. Across the environment, the Group enables its customers and workforce, and associates of societies at significant to are living, work and create sustainably, in a safe and safe information and facts place.

Push call:

Laura Fau | [email protected] | +33 six seventy three sixty four 04 eighteen | @laurajanefau