- \n
- \nIntel\u2019s broad portfolio of HPC and AI products provides competitive performance, with Intel\u00ae<\/sup> Data Center GPU Max Series 1550 showing an average speedup of 30% over Nvidia H100 on a wide range of scientific workloads.1<\/sup><\/li>\n
- \nProduct roadmap updates highlight Granite Rapids, a next-generation CPU to address memory bandwidth demands, and Falcon Shores GPU to meet an expanding, diverse set of workloads for HPC and AI.<\/p>\n<\/li>\n
- \nArgonne National Laboratory and Intel announce full Aurora specifications, system momentum and international initiative with Hewlett Packard Enterprise (HPE) and partners to bring the power of generative AI and large language models (LLM) to science and society.<\/p>\n<\/li>\n
- \nEnhanced oneAPI and AI tools help developers speed up HPC and AI workloads and enhance code portability across multiple architectures.<\/p>\n<\/li>\n<\/ul>\n
HAMBURG, Germany–(BUSINESS WIRE<\/a>)–
\nAt the ISC High Performance Conference, Intel showcased leadership performance for high performance computing (HPC) and artificial intelligence (AI) workloads; shared its portfolio of future HPC and AI products, unified by the oneAPI open programming model; and announced an ambitious international effort to use the Aurora supercomputer to develop generative AI models for science and society.<\/p>\nThis press release features multimedia. View the full release here: https:\/\/www.businesswire.com\/news\/home\/20230522005289\/en\/<\/a><\/p>\n
![\"Intel](\"https:\/\/mms.businesswire.com\/media\/20230522005289\/en\/1799212\/4\/Supercomputer_newsroom_1920w.jpg\")
<\/p>\nIntel is committed to serving the high performance computing (HPC) and artificial intelligence (AI) communities with products that help customers and end-users make breakthrough discoveries faster. Intel\u2019s product portfolio \u2013 spanning Intel\u00ae Xeon\u00ae CPU Max Series, Intel\u00ae Data Center GPU Max Series, 4th Gen Intel\u00ae Xeon\u00ae Scalable processors and Habana\u00ae Gaudi\u00ae2 processors \u2013 meets the needs of the HPC community. At the same time, oneAPI and AI tools help developers speed up HPC and AI workloads and enhance code portability across multiple architectures. (Credit: Intel Corporation)<\/p>\n<\/div>\n
More:<\/b>International Supercomputing Conference 2023<\/a> (Quote Sheet)<\/p>\n
\n\u201cIntel is committed to serving the HPC and AI community with products that help customers and end-users make breakthrough discoveries faster,\u201d said Jeff McVeigh, Intel corporate vice president and general manager of the Super Compute Group. \u201cOur product portfolio spanning Intel\u00ae<\/sup> Xeon\u00ae<\/sup> CPU Max Series, Intel\u00ae<\/sup> Data Center GPU Max Series, 4th Generation Intel\u00ae<\/sup> Xeon\u00ae<\/sup> Scalable Processors and Habana\u00ae<\/sup> Gaudi\u00ae<\/sup>2 are outperforming the competition on a variety of workloads, offering energy and total cost of ownership advantages, democratizing AI and providing choice, openness and flexibility.\u201d<\/p>\n
Hardware Performance at Scale<\/b><\/p>\n
\nAt the Intel special presentation, McVeigh highlighted the latest competitive performance results across the full breadth of hardware and shared strong momentum with customers.<\/p>\n
- \n
- \nThe Intel\u00ae<\/sup> Data Center GPU Max Series outperforms Nvidia H100 PCIe card by an average of 30% on diverse workloads1<\/sup>, while independent software vendor Ansys shows a 50% speedup for the Max Series GPU over H100 on AI-accelerated HPC applications.2<\/sup><\/li>\n
- \nThe Xeon Max Series CPU, the only x86 processor with high bandwidth memory, exhibits a 65% improvement over AMD\u2019s Genoa processor on the High Performance Conjugate Gradients (HPCG) benchmark1<\/sup>, using less power. High memory bandwidth has been noted as among the most desired features for HPC customers.3<\/sup><\/li>\n
- \n4th Gen Intel Xeon Scalable processors \u2013 the most widely used in HPC \u2013 deliver a 50% average speedup over AMD\u2019s Milan4<\/sup>, and energy company BP\u2019s newest 4th Gen Xeon HPC cluster provides an 8x increase in performance over its previous-generation processors with improved energy efficiency.2<\/sup><\/li>\n
- \nThe Gaudi2 deep learning accelerator performs competitively on deep learning training and inference, with up to 2.4x faster performance than Nvidia A100.1<\/sup><\/li>\n<\/ul>\n
\nCustomers have recently announced new installations with Intel 4th Gen Xeon and Max Series processors:<\/p>\n
- \n
- \nKyoto University is deploying 4th Gen Xeon for Laurel 3 and Cinnamon 3, and Xeon Max Series processors for Camphor 3.<\/p>\n<\/li>\n
- \nCineca deployed Leonardo with 4th Gen Intel Xeon processors.<\/p>\n<\/li>\n
- \nUniversity of Rochester – Laboratory for Laser Energetics is deploying a cluster with 4th<\/sup> Gen Xeon processors.<\/p>\n<\/li>\n
- \nServicio Meteorol\u00f3gico Nacional de Argentina will deploy a system with both Max Series CPUs and GPUs.<\/p>\n<\/li>\n<\/ul>\n
\nAdditionally, the Cambridge Open Zettascale Lab at the University of Cambridge has deployed the first Max GPU testbed in the United Kingdom and is seeing positive early results on molecular dynamics and biological imaging applications. Also, RIKEN announced a memorandum of understanding (MoU) with Intel aimed at accelerating joint research and development in the field of advanced computing technologies, such as artificial intelligence, high performance computing and quantum computing. As part of the MoU, RIKEN will also engage with Intel Foundry Services to create prototypes of these new solutions.<\/p>\n
Competitive Processors for Every Workload<\/b><\/p>\n
\nDynamic, emerging HPC and AI workloads require a full portfolio of hardware and software solutions. McVeigh provided an overview of Intel\u2019s data center offerings that deliver many choices and solutions for the HPC community, helping to democratize AI.<\/p>\n
\nIn his presentation, McVeigh introduced Intel\u2019s next-generation CPUs to meet high memory bandwidth demands. Intel led the ecosystem to develop a new type of DIMM \u2013 Multiplexer Combined Ranks (MCR) \u2013 for Granite Rapids. MCR achieves speeds of 8,800 megatransfers per second based on DDR5 and greater than 1.5 terabytes\/second (TB\/s) of memory bandwidth capability in a two-socket system. This boost in memory bandwidth is critical for feeding the fast-growing core counts of modern CPUs and enabling efficiency and flexibility.<\/p>\n
\nIntel also disclosed a new, AI-optimized x8 Max Series GPU-based subsystem from Supermicro, designed to accelerate deep learning training. In addition to access via Intel\u00ae<\/sup> Developer Cloud beta5<\/sup> later this year, multiple OEMs will offer solutions with Max Series GPUs x4 and x8 OAM subsystems and PCIe cards, which will be available in the summer.<\/p>\n
\nIntel\u2019s next-generation Max Series GPU, Falcon Shores, will give customers the flexibility to implement system-level CPU and discrete GPU combinations for the new and fast-changing workloads of the future. Falcon Shores is based on a modular, tile-based architecture and will:<\/p>\n
- \n
- \nSupport HPC and AI data types, from FP64 to BF16 to FP8.<\/p>\n<\/li>\n
- \nEnable up to 288GB of HBM3 memory with up to 9.8TB\/s total bandwidth and vastly improved high-speed I\/O.<\/p>\n<\/li>\n
- \nEmpower the CXL programming model.<\/p>\n<\/li>\n
- \nPresent a unified GPU programming interface through oneAPI.<\/p>\n<\/li>\n<\/ul>\n
Generative AI for Science<\/b><\/p>\n
\nArgonne National Laboratory, in collaboration with Intel and HPE, announced plans to create a series of generative AI models for the scientific research community.<\/p>\n
\n\u201cThe project aims to leverage the full potential of the Aurora supercomputer to produce a resource that can be used for downstream science at the Department of Energy labs and in collaboration with others,\u201d said Rick Stevens, Argonne associate laboratory director.<\/p>\n
\nThese generative AI models for science will be trained on general text, code, scientific texts and structured scientific data from biology, chemistry, materials science, physics, medicine and other sources.<\/p>\n
\nThe resulting models (with as many as 1 trillion parameters) will be used in a variety of scientific applications, from the design of molecules and materials to the synthesis of knowledge across millions of sources to suggest new and interesting experiments in systems biology, polymer chemistry and energy materials, climate science and cosmology. The model will also be used to accelerate the identification of biological processes related to cancer and other diseases and suggest targets for drug design.<\/p>\n
\nArgonne is spearheading an international collaboration to advance the project, including Intel; HPE; Department of Energy laboratories; U.S. and international universities; nonprofits; and international partners, such as RIKEN.<\/p>\n
\nAdditionally, Intel and Argonne National Laboratory highlighted installation progress, system specs and early performance results for Aurora:<\/p>\n
- \n
- \nIntel has completed the physical delivery of more than 10,000 blades for the Aurora supercomputer.<\/p>\n<\/li>\n
- \nAurora\u2019s full system, built using HPE Cray EX supercomputers, will have 63,744 GPUs and 21,248 CPUs and 1,024 DAOS storage nodes. And it will utilize the HPE Slingshot high-performance Ethernet network.<\/p>\n<\/li>\n
- \nEarly results show leading performance on real-world science and engineering workloads, with up to 2x performance over AMD MI250 GPUs, 20% improvement over H100 on the QMCPACK quantum mechanical application, and near linear scaling up to hundreds of nodes.2<\/sup><\/li>\n<\/ul>\n
\nAurora is expected to offer more than 2 exaflops of peak double-precision compute performance when launched this year.<\/p>\n
Productive, Open Accelerated Computing Through oneAPI<\/b><\/p>\n
\nWorldwide, about 90% of all developers benefit from or use software developed for or optimized by Intel.6<\/sup> Since the oneAPI programming model launched in 2020, developers have demonstrated oneAPI on diverse CPU, GPU, FPGA and AI silicon from multiple hardware providers, addressing the challenges of single-vendor accelerated programming models. The latest Intel oneAPI tools deliver speedups for HPC applications with OpenMP GPU offload, extend support for OpenMP and Fortran, and accelerate AI and deep learning through optimized frameworks, including TensorFlow and PyTorch, and AI tools, enabling orders of magnitude performance improvements.<\/p>\n
\noneAPI makes multiarchitecture programming easier for programmers through oneAPI\u2019s SYCL implementation, oneAPI plug-ins for Nvidia and AMD processors developed by Codeplay, and the Intel\u00ae<\/sup> DPC++ Compatibility Tool (based on open source SYCLomatic) that migrates code from CUDA to SYCL and C++ where 90-95% of code typically migrates automatically.7<\/sup> The resulting SYCL code shows comparable performance with the same code running on Nvidia- and AMD-native systems languages. Data shows SYCL code for the DPEcho astrophysics application running on the Max Series GPU outperforms the same CUDA code on Nvidia H100 by 48%.1<\/sup><\/p>\n
\nThe broader ecosystem is embracing SYCL, as well. Eviden, an Atos business, announced CEPP one+ with Intel, an HPC\/AI Code modernization service based on Eviden\u2019s Center of Excellence in Performance Programming (CEPP). CEPP one+ will focus on the adoption of SYCL and OpenMP, preparing the community for a heterogeneous computing landscape while providing freedom of choice in hardware through open standards.<\/p>\n
About Intel<\/b><\/p>\n
\nIntel (Nasdaq: INTC) is an industry leader, creating world-changing technology that enables global progress and enriches lives. Inspired by Moore\u2019s Law, we continuously work to advance the design and manufacturing of semiconductors to help address our customers\u2019 greatest challenges. By embedding intelligence in the cloud, network, edge and every kind of computing device, we unleash the potential of data to transform business and society for the better. To learn more about Intel\u2019s innovations, go to newsroom.intel.com<\/a> and intel.com<\/a>.<\/p>\n
Disclaimers and configuration:<\/b><\/p>\n
1<\/sup> Visit the International Supercomputing Conference (ISC\u201923) page on intel.com\/performanceindex<\/a> for workloads and configurations. Results may vary.<\/p>\n
2<\/sup> Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy.<\/p>\n
3<\/sup>Hyperion Research HPC Market Update<\/a>, Nov. 2022.<\/p>\n
4<\/sup> Intel\u00ae<\/sup> Xeon\u00ae<\/sup> 8480+ has 1.5x higher geomean HPC performance across 27 benchmarks and applications than AMD EPYC 7763. Results may vary.<\/p>\n
5<\/sup> The Intel Developer Cloud beta is currently available to select prequalified customers.<\/p>\n
6<\/sup> According to Intel estimates.<\/p>\n
7<\/sup> Intel estimates as of March 2023. Based on measurements on a set of 85 HPC benchmarks and samples, with examples like Rodinia, SHOC, PENNANT. Results may vary.<\/p>\n
\nPerformance varies by use, configuration and other factors. Performance results are based on testing as of dates shown in configurations and may not reflect all publicly available updates. No product or component can be absolutely secure.<\/p>\n
\nYour costs and results may vary.<\/p>\n
\nIntel technologies may require enabled hardware, software or service activation.<\/p>\n
\nStatements in this document that refer to future plans or expectations are forward-looking statements. These statements are based on current expectations and involve many risks and uncertainties that could cause actual results to differ materially from those expressed or implied in such statements. For more information on the factors that could cause actual results to differ materially, see our most recent earnings release and SEC filings at www.intc.com<\/a>.<\/p>\n
\n\u00a9 Intel Corporation. Intel, the Intel logo and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.<\/p>\n
<\/p>\n
View source version on businesswire.com: <\/span>https:\/\/www.businesswire.com\/news\/home\/20230522005289\/en\/<\/a><\/span><\/p>\n
\nBats Jafferji
\n
1-603-809-5145
\n
bats.jafferji@intel.com<\/a><\/p>\nKEYWORDS:<\/b> California Germany Europe United States North America<\/p>\n
INDUSTRY KEYWORDS:<\/b> Apps\/Applications Technology Software Networks Artificial Intelligence Internet Hardware<\/p>\n
- \nServicio Meteorol\u00f3gico Nacional de Argentina will deploy a system with both Max Series CPUs and GPUs.<\/p>\n<\/li>\n<\/ul>\n
- \nThe Xeon Max Series CPU, the only x86 processor with high bandwidth memory, exhibits a 65% improvement over AMD\u2019s Genoa processor on the High Performance Conjugate Gradients (HPCG) benchmark1<\/sup>, using less power. High memory bandwidth has been noted as among the most desired features for HPC customers.3<\/sup><\/li>\n
![\"Logo\"](\"https:\/\/mms.businesswire.com\/media\/20230522005289\/en\/817781\/3\/intel_logo.jpg\"){kind=logo}
<\/td>\n<\/tr>\n![\"Photo\"](\"https:\/\/mms.businesswire.com\/media\/20230522005289\/en\/1799212\/3\/Supercomputer_newsroom_1920w.jpg\")
<\/td>\n<\/tr>\n