AMD) today announced multiple new high-performance computing wins for AMD EPYC processors, including that the seventh fastest supercomputer in the world and four of the 50 highest-performance systems on the bi-annual TOP500 list are now powered by AMD. Momentum for AMD EPYC™ processors in advanced science and health research continues to grow with new installations at Indiana University, Purdue University and CERN as well as high-performance computing (HPC) cloud instances from Amazon Web Services, Google, and Oracle Cloud.
“The leading HPC institutions are increasingly leveraging the power of 2nd Gen AMD EPYC processors to enable cutting-edge research that addresses the world’s greatest challenges,” said Forrest Norrod, senior vice president and general manager, data center and embedded systems group, AMD. “Our AMD EPYC CPUs, Radeon Instinct accelerators and open software programming environment are helping to advance the industry towards exascale-class computing, and we are proud to strengthen the global HPC ecosystem through our support of the top supercomputing clusters and cloud computing environments.”
From powering the upcoming world’s fastest exascale supercomputers, Frontier and El Capitan, to supporting workloads in the cloud, and driving new advancements in health research, the high core count and extensive memory bandwidth of AMD EPYC processors are helping meet the growing demand from HPC providers for improved performance, scalability, efficiency, and total cost of ownership.
AMD Continues Expanding Share of TOP500 Supercomputers
Four AMD EPYC powered supercomputers are now among the 50 highest-performance systems in the world and there are now ten AMD EPYC-powered supercomputers on the TOP500:
- Selene (No.7) an AMD EPYC 7742-based system in a DGX A100 SuperPOD platform from Nvidia,
- Belenos (No.30), one of the two BullSequana XH2000 supercomputers at Météo-France, the French national meteorological service powered by 2nd Gen AMD EPYC processors,
- Joliot-Curie (No.34), moved up the list based on a new submission for the BullSequana XH2000 system using 2nd Gen AMD EPYC™ processors at GENCI, the French national high-performance computing organization,
- Mahti (No. 48), a 2nd Gen AMD EPYC processor powered BullSequana XH2000 supercomputer at Finland’s Center for Science Information Technology,
“Atos is proud to provide to its customers with cutting edge technology, integrating 2nd Gen AMD EPYC processors as soon as released, and demonstrating increased performance on HPC applications in production environments,” said Agnès Boudot, group senior vice president, Head of HPC and Quantum at Atos.
AMD Powered Supercomputing Systems Drive Research of the Future
Two universities announced new research supercomputing systems powered by AMD EPYC processors in Dell EMC PowerEdge servers.
Indiana University will deploy Jetstream 2, an eight-petaflop distributed cloud computing system powered by upcoming 3rd Gen AMD EPYC processors. This system will be used by researchers in a variety of fields such as AI, social sciences, and COVID-19 research. AMD EPYC processors already power Big Red 200 at the Indiana University campus.
“Jetstream 2 bundles computation, software and access to storage for individuals and teams of researchers across an array of areas of research,” said David Hancock, Director in Research Technologies, affiliated with the Pervasive Technology Institute at Indiana University. “With the next generation AMD EPYC processor, Jetstream 2 will provide 8 petaflops of cloud computing power, giving more access to high-end technologies to enable deep learning and artificial intelligence techniques.”
Purdue University will deploy Anvil, a supercomputer powered by next generation AMD EPYC processors, which will provide advanced computing capabilities to support a wide range of computational and data-intensive research. AMD EPYC will also power Purdue’s latest community cluster “Bell”, scheduled for deployment early this fall.
In addition, CERN, the largest particle physics laboratory in the world, recently selected 2nd Gen AMD EPYC processors in Gigabyte servers to harness the massive amounts of data from their latest Large Hadron Collider (LHC) experiment to rapidly detect subatomic particles known as beauty quarks. A new case study details how combining the increased bandwidth of PCIe® 4.0, DDR4 memory speed, and the 64 core AMD EPYC™ 7742 processor allows researchers to collect the raw data streams generated by 40 terabytes of collision data occurring every second in the LHC.
High Performance Computing in the Cloud with AMD EPYC
As the HPC industry evolves to support new workload demands, cloud providers continue to adopt 2nd Gen AMD EPYC processors to provide leadership performance and flexible solutions. With recent cloud wins among technology partners like Amazon Web Services, Google Cloud and Oracle Cloud, AMD is helping industry leaders push the boundaries in the new era of HPC and cloud computing.
AMD and Microsoft Azure have continued to build upon their cloud partnership with the recently announced HBv2-Series VMs for high-performance computing workloads. The 2nd Gen AMD EPYC processors provide Microsoft Azure customers with impressive core scaling, access to massive memory bandwidth and are the first x86 server processors that support PCIe® 4.0, enabling some of the best high-performance computing experiences in the industry. Together, AMD and Microsoft Azure will support real-world HPC workloads, such as CFD, explicit finite element analysis, seismic processing, reservoir modeling, rendering, and weather simulation.
AMD Updates ROCm™ For Heterogenous Software Support
Community support continues to grow for AMD Radeon Open eCosystem (ROCm™), AMD’s open source foundation for heterogenous compute. Major development milestones in the latest update include:
- The HIP-Clang compiler is now up-streamed and reviewed by the LLVM™ community, providing a better open source experience for the developer,
- A new rocprofiler start/stop API to enable/disable GPU kernel HSA dispatch callbacks, increasing developer productivity and shortening the profiling run times,
- AMD RCCL compatibility with NVIDIA Communications Collective Library (NCCL) v2.6.4m,
- MIOpen provides an optional pre-compiled kernel package to reduce startup latency,
- A new CPU Affinity API is introduced for aiding applications to select the appropriate memory node for a given accelerator (GPU) and a given CPU,
- The new Radeon Performance Primitives library is a comprehensive high-performance computer vision library for AMD (CPU and GPU) with the HIP and OpenCL backend.
Join AMD CTO and executive vice president, Mark Papermaster, for a webinar on July 15th to discuss the full range of AMD solutions and upcoming innovations in HPC. Click the link for the time most convenient for you to register: 9 AM EDT, 12 PM EDT or 9 PM EDT.
Supporting Resources
- Tour the HLRS “Hawk” supercomputing system
- Learn more about the AMD 2nd Gen EPYCTM Processor
- Learn more about AMD Radeon Instinct™ Accelerators
- Become a fanof AMDonFacebook
- FollowAMD on Twitter
About AMD
For 50 years AMD has driven innovation in high-performance computing, graphics, and visualization technologies ― the building blocks for gaming, immersive platforms and the datacenter. Hundreds of millions of consumers, leading Fortune 500 businesses and cutting-edge scientific research facilities around the world rely on AMD technology daily to improve how they live, work and play. AMD employees around the world are focused on building great products that push the boundaries of what is possible. For more information about how AMD is enabling today and inspiring tomorrow, visit the AMD (NASDAQ: AMD) website, blog, Facebook and Twitter pages.
AMD, the AMD logo, EPYC, Radeon Instinct, ROCm, and combinations thereof are trademarks of Advanced Micro Devices, Inc. Amazon Web Services (AWS) is a trademark of Amazon.com, Inc. or its affiliates in the United States and/or other countries, Google Cloud Platform is a trademark of Google LLC., LLVM is a trademark of LLVM Foundation, OpenCL is a trademark of Apple Inc. used by permission by Khronos Group, Inc., Oracle is a registered mark of Oracle and/or its affiliates. PCIe is a registered trademark of PCI-SIG Corporation. Other product names used in this publication are for identification purposes only and may be trademarks of their respective companies. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
