MRI: Acquisition of FASTER - Fostering Accelerated Sciences Transformation Education and Research

MRI：收购 FASTER - 促进加速科学转型教育和研究

• 批准号: 2019129
• 负责人: Honggao Liu
• 金额: $ 309万
• 依托单位: Texas A&M University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2019129&HistoricalAwards=false
• 关键词: MRI; Acquisition; FASTER; Fostering; Accelerated

The project funds the acquisition of a composable high-performance data-analysis and computing instrument, named FASTER (Fostering Accelerated Scientific Transformations, Education, and Research). FASTER will enable transformative advances in scientific fields that rely on artificial intelligence and machine learning (AI/ML) techniques, big data practices, and high-performance computing (HPC) technologies. The FASTER platform removes significant bottlenecks in research computing by leveraging a technology that can dynamically allocate resources to support workflows. It will support researchers from across the Texas A&M University System and their collaborating institutions. Thirty percent of FASTER’s computing resources will also be allocated to researchers nationwide by the National Science Foundation (NSF) XSEDE (Extreme Science and Engineering Discovery Environment) program. FASTER’s composable interface allows it to simultaneously support both emerging and traditional workloads in research computing. Transformative research projects benefiting from FASTER will include the development of AI/ML models, cybersecurity, health population informatics, genomics, bioinformatics, computer-aided drug design, agricultural sciences, life sciences, oil and gas simulations, de novo materials design, climate modeling, multi-scale simulations, quantum computing architectures, biomedical imaging, geosciences, and quantum chemistry. In addition to supporting a wide-range of fields of research, the project contributes to code development, education, and the workforce development goals of several NSF Big Ideas.FASTER adopts the innovative Liqid composable software-hardware approach combined with cutting-edge technologies such as state of the art CPUs and GPUs, NVMe (Non-Volatile Memory Express) based storage, and thigh speed interconnect. Workflows on FASTER will be able to dynamically integrate disaggregated GPUs and NVMe to compose a single node, allowing them to scale beyond traditional hardware limits. The composable and configurable techniques will allow researchers to use resources efficiently, enabling more science. Best practices gathered from managing the resource will be shared with the community. FASTER will coordinate a three-pronged effort to effectively broaden participation in computing by focusing on training, education and outreach. FASTER will leverage existing efforts that promote STEM (Science, Technology, Engineering and Mathematics) and broaden participation in computing at the K-12, collegiate, and professional levels to have a transformative impact nationally. FASTER activities are designed to expand the participation of traditionally underrepresented groups in computing and STEM, particularly at minority-serving institutions.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目资助了一个可组合的高性能数据分析和计算工具的获取，该工具被称为更快（促进加速的科学转型，教育和研究）。更快的速度将在依赖人工智能和机器学习（AI/ML）技术，大数据实践和高性能计算（HPC）技术的科学领域中实现变革性进步。更快的平台通过利用可以动态分配资源来支持工作流程的技术来消除研究计算中的重要瓶颈。它将支持来自德克萨斯A＆M大学系统及其合作机构的研究人员。国家科学基金会（NSF）XSEDE（极端的科学与工程发现环境）计划，更快的计算资源的30％也将在全国范围内分配给全国研究人员。 FASTER’s composable interface allows it to Transformative research projects benefiting from FASTER will include the development of AI/ML models, cybersecurity, health population informatives, genomics, bioinformatics, computer-aided drug design, agricultural sciences, life sciences, oil and gas simulations, de novo materials design, climate modeling, multi-scale simulations, quantum computing architectures, biomedical imaging,地球科学和量子化学。除了支持广泛的研究领域外，该项目还为代码开发，教育以及几个NSF大思想的劳动力发展目标做出了贡献。Faster采用创新的液化液化式软件软件方法，结合了最先进的技术与ART CPU和GPUS和GPUS，NVME，NVME（NOR-VOLATILIE MEMORYE SESTICTER）等最先进的技术相结合。更快的工作流将能够动态整合分开的GPU和NVME以组成一个节点，从而使它们可以超越传统硬件限制。可组合和可配置的技术将使研究人员能够有效地使用资源，从而实现更多的科学。从管理资源中获得的最佳实践将与社区共享。更快的速度将通过专注于培训，教育和外展来协调三方面的努力，以有效地扩大计算的参与。更快的速度将利用促进STEM（科学，技术，工程和数学）的现有努力，并扩大了K-12，大学和专业水平的计算参与，以在全国范围内产生变革性的影响。更快的活动旨在扩大传统上代表性不足的团体参与计算和STEM的参与，尤其是在少数派服务机构中。该奖项反映了NSF的法定任务，并通过使用该基金会的知识分子的优点和更广泛的影响来审查标准，通过评估来评估。

项目成果

Regional Collaborations Supporting Cyberinfrastructure-Enabled Research During a Pandemic: The Structure and Support Plan of the SWEETER CyberTeam

大流行期间支持网络基础设施研究的区域合作：SWEETER Cyber​​Team 的结构和支持计划

• DOI: 10.1145/3491418.3535186
• 发表时间: 2022
• 期刊: PEARC '22: Practice and Experience in Advanced Research Computing
• 作者: Medina-Gurrola, Edmundo;Chakravorty, Dhruva K.;Dugas, Diana V.;Cockerill, Tim;Perez, Lisa M.;Hunt, Emily
• 通讯作者: Hunt, Emily

Benchmarking the Performance of Accelerators on National Cyberinfrastructure Resources for Artificial Intelligence / Machine Learning Workloads

• DOI: 10.1145/3491418.3530772
• 发表时间: 2022-07
• 期刊: Practice and Experience in Advanced Research Computing
• 作者: Abhinand Nasari;Hieu Hanh Le;Richard Lawrence;Zhenhua He;Xin Yang;Mario Krell;A. Tsyplikhin;M. Tatineni;Tim Cockerill;Lisa M. Perez;Dhruva K. Chakravorty;Honggao Liu

Expanding the Reach of Research Computing: A Landscape Study: Pathways Bringing Research Computing to Smaller Universities and Community Colleges

扩大研究计算的范围：景观研究：将研究计算引入小型大学和社区学院的途径

• DOI: 10.1145/3491418.3535169
• 发表时间: 2022
• 期刊: PEARC '22: Practice and Experience in Advanced Research Computing
• 作者: Chakravorty, Dhruva;Janes, Sarah;Howell, James;Perez, Lisa;Schultz, Amy;Goldie, Marie;Gamble, Austin;Malkan, Rajiv;Liu, Honggao;Mireles, Daniel
• 通讯作者: Mireles, Daniel