IRES Track I: Algorithms and Software for SUpercomputers with emerging aRchitEctures (ASSURE)

IRES Track I：具有新兴架构的超级计算机的算法和软件（ASSURE）

基本信息

批准号：
1827093
负责人：
John Verboncoeur
金额：
$ 26.95万
依托单位：
Michigan State University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-01-01 至 2024-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1827093&HistoricalAwards=false
关键词：
IRES Track Algorithms Software SUpercomputers

项目摘要

Supercomputers enable researchers to push the boundaries of science and find innovative approaches to complex problems. From improving advanced manufacturing with modeling and simulation to understanding earth systems and weather with greater precision, harnessing the data revolution and applying data to understand life processes, supercomputers are essential to human advancement. HPC (High Performing Computer) systems of the future will likely be very different from those of today. Emerging architectures can have a tremendous impact on the development of software, methods and models that can take advantage of these new features resulting in speed up and improvement in the accuracy of calculations. Early adoption of these emerging technologies to take advantage of special features is key to remaining competitive in the global economy. The goal of this IRES site is to engage PhD. students in research learning experiences that increase their capacity to conduct research on supercomputing systems, (including those with classical and emerging architectures), and their exposure to international collaborative research.This IRES, called ASSURE, aims to enhance the capabilities of US graduate students to develop Algorithms and Software in key scientific disciplines that benefit from Supercomputers and emerging aRchitEctures (ASSURE). The program focuses on equipping students to conduct research on one of the fastest supercomputers in the world, Sunway Taihulight, housed in Wuxi China, which has a unique architecture. ASSURE achieves this goal by: (i) training students to utilize unique international large-scale systems; (ii) engaging students in high quality collaborative research in four key areas of computational and data science utilizing these systems; and (iii) exposing students to international large-scale research environments that prepare them with cultural and professional skills required to occupy international leadership roles. Specifically, IRES students at this site will conduct research at two locations in China: The National Supercomputing Center (NSCC) in Wuxi China and the University of Tsinghua and the East China Normal University.The ASSURE site is open to US Ph.D. students with an interest in computational and data science in the areas of earth systems, drug design, advanced manufacturing, big data and machine learning. Specifically, US citizens or permanent residents, including women and students from underrepresented populations in international STEM research, are invited to participate.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.

超级计算机使研究人员能够突破科学的界限，并找到解决复杂问题的创新方法。从建模和仿真改善先进的制造业到以更精确的方式了解地球系统和天气，利用数据革命并应用数据以了解生活过程，超级计算机对于人类的进步至关重要。未来的HPC（高性能计算机）系统可能与当今的系统大不相同。新兴体系结构可能会对软件，方法和模型的开发产生巨大影响，从而可以利用这些新功能，从而迅速提高和提高计算的准确性。这些新兴技术的早期采用以利用特殊功能是在全球经济中保持竞争力的关键。该IRES网站的目标是吸引博士学位。研究学习经验的学生增加了对超级计算系统进行研究的能力（包括具有经典和新兴体系结构的人），以及他们接触国际协作研究的能力。这一称为Assure的IRES旨在增强美国研究生的能力，以在关键科学领域中开发算法和软件的能力，从而受益于从超级科学领域中受益于超级群体和Emeregunting Architecter和Emergucting Arneging Arneging Arneging Arnedecruning（Assecruning Assunecrunge）（Assenging Assunecrune）（Assecrunge）（Assemenging Assunecuring）。该计划的重点是让学生对世界上最快的超级计算机之一进行研究，即在中国的Wuxi China中安置的Sunway Taihulight，该公司具有独特的建筑。通过以下方式确保实现这一目标，请培训学生利用独特的国际大型系统；（ii）在利用这些系统的计算和数据科学的四个关键领域，让学生参与高质量的协作研究；（iii）将学生暴露于国际大规模研究环境中，以使他们拥有占据国际领导角色所需的文化和专业技能。具体来说，该站点的IRES学生将在中国的两个地点进行研究：中国Wuxi的国家超级计算中心（NSCC）和Tsinghua大学和东中国师范大学。在地球系统，药物设计，高级制造，大数据和机器学习方面对计算和数据科学感兴趣的学生。具体来说，美国公民或永久居民，包括国际STEM研究中代表性不足人群的妇女和学生的学生参加。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子的评估来支持的，并具有更广泛的影响。