课题基金 / 基金详情

MRI: Acquisition of a High-Performance Instrument for Interdisciplinary Computational Science and Engineering

MRI: Acquisition of a High-Performance Instrument for Interdisciplinary Computational Science and Engineering
MRI:为跨学科计算科学与工程购置高性能仪器
批准号:
0923256
负责人:
Tarek El-Ghazawi
金额:
$78.72万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2009
资助国家:
美国
项目状态:
已结题
起止时间:
2009-10-01 至 2014-09-30

项目摘要

项目成果

Tarek El-Ghazawi的其他基金

相似基金

相关文献

中文摘要
翻译
提案编号:MRI 09- 23256 PI:El-Ghazawi,Tarek A.;作者:William J. Lang,Roger H.; Lee,Frank X.; Mittal,Rajat机构:乔治华盛顿大学职位:MRI/采集:跨学科计算科学与工程的高性能仪器项目建议:该项目,获得Cray XT5和足够的存储,升级计算机集群的网络,并将这些整合为一个高性能计算(HPC)仪器,通过新的大规模并行应用和计算技术研究所(IMPACT)支持来自两个学校和七个部门的跨学科研究人员团队。新的编程模型和处理器技术在理解高性能计算系统的生产力,以及新技术对科学的影响将进行调查。编程模型包括UPC,Co-Array FORTRAN,X10和并行Matlab。应用需求将推动UPC-10工作和特定于应用的PGAS编译器优化。研究新的处理器技术将与NSF工业/大学合作CHREC中心联合进行。在计算流体动力学(CFD)中,该仪器将有助于设计受昆虫飞行动力学启发的微型飞行器(以前的工作假设为刚性机翼)。HPC仪器将有助于进行详细的建模,以了解昆虫翅膀?s变形。该仪器还将用于采用CFD技术,使用一种新颖的浸入边界法分析美国国家队的游泳动作。由于HPC资源的缺乏,目前的模拟在低雷诺数下进行。在核物理学中,该仪器将有助于解开由量子色动力学(QCD)控制的最深层次的物质结构。后者是非常困难的解决没有大规模并行计算的离散时空晶格与数百万自由度。该仪器将有助于加快将基本核反应中的实验和理论核物理研究联系起来,并解释介子和超子的光电产生方面的最新实验结果。它还将为遥感小组提供更精确的土壤、地表和植被模型,从而将传感器响应与地面生物物理变量联系起来。更广泛的影响:此次收购有助于培养新一代能够面对当前计算机技术变化的学生和博士后研究员。该仪器将允许分配现实的计算问题,可以整合研究和教学,促进通过发现学习。这些举措包括广泛的外联方案。计划举办开放日活动,将包括社区大学、高中和初中学生以及K-12教师,以提高他们对科学和技术的兴趣。制定了一项具体计划,让妇女和少数民族接受培训,使用该工具,并与教师进行研究合作。该计划侧重于该地区的HBCU机构,并向妇女和少数民族开放。调查将产生代码和数据,这些代码和数据将使用公共许可证(如GNU/GPL)与社区共享。该网站将提供论文、介绍和免费分发的相关软件;还将组织会议和讲习班。此外,将颁发跨学科HPC的研究生证书,并将聘请HPC领域的更多教师。
英文摘要
Proposal #: MRI 09-23256PI(s): El-Ghazawi, Tarek A.; Briscoe, William J.; Lang, Roger H.; Lee, Frank X.; Mittal, RajatInstitution: George Washington University Title: MRI/Acq.: High Performance Instrument for Interdisciplinary Computational Science and Engineering Project Proposed:This project, acquiring a Cray XT5 and adequate storage, upgrading the network of a computer cluster, and integrating these as one High Performance Computing (HPC) instrument, supports a team of interdisciplinary researchers from two schools and seven departments via the new Institute for Massively Parallel Applications and Computing Technologies (IMPACT). New programming models and processor technologies in understanding high-performance computing systems productivity, as well as the impact of new technologies on science will be investigated. Programming models include UPC, Co-Array FORTRAN, X10, and Parallel Matlab. Application requirements will drive the UPC-10 work and application specific PGAS compiler optimizations. Investigating new processor technologies will be pursued jointly with the NSF Industry/University Cooperative CHREC center. In computational fluid dynamics (CFD), the instrument will help in the design of micro-aerial vehicles inspired by the dynamics of insect flight (previous work assumed rigid wings). The HPC instrument will help carry out detailed modeling to understand insect wing?s deformation. The instrument will also be used in employing CFD techniques to analyze swimming strokes for U.S. national teams using a novel immersed boundary method. Current simulations are carried out at low Reynolds numbers due to lack of HPC resources. In nuclear physics, the instrument will help unravel the structure of matter at its deepest level as governed by Quantum Chromodynamics (QCD). The latter is very difficult to solve without massively parallel computations on a discrete space-time lattice with millions of degrees of freedom. The instrument will help expedite the linking of experimental and theoretical nuclear physics studies in fundamental nuclear reactions and account for the most recent experimental results in photo and electro-production of mesons and hyperons. Helping the remote sensing group, it will also contribute to provide more accurate models of the soil, ground surface and vegetation that can relate the sensor responses to the bio-physical variables on the ground.Broader Impacts: This acquisition enables producing a new generation of students and postdoctoral fellows who can face the current changes in computing technology. The instrument will allow assigning realistic computational problems that can integrate research and teaching promoting learning through discovery. Initiatives include an extensive outreach program. Open house events are planned and will include community colleges, high school and middle school students, and K-12 teachers to increase interest in science and technology. A concrete plan is devised to include women and minority to receive training, use the instrument, and engage in research collaboration with the faculty. The plan focuses on HBCU institutions in the area, and is open to women and minorities. Investigations will result in codes and data that will be shared with the community using a public license such as GNU/GPL. The website will provide access to papers, presentations, and freely distributed relevant software; conferences and workshops will also be organized. Furthermore, a graduate certificate in interdisciplinary HPC will be issued and more faculty in the HPC area will be hired.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
IDIEA-DC: An Infrastructure for Distributed Intelligence Experimentation and Architectures in the Digital Continuum: from IoTs to the Cloud
  • 批准号:
    2038682
  • 项目类别:
    Standard Grant
  • 资助金额:
    $29.99万
  • 财政年份:
    2020
  • 负责人:
    Tarek El-Ghazawi
  • 依托单位:
RAISE: The Reconfigurable Optical Computer (ROC)
  • 批准号:
    1748294
  • 项目类别:
    Continuing Grant
  • 资助金额:
    $90.0万
  • 财政年份:
    2017
  • 负责人:
    Tarek El-Ghazawi
  • 依托单位:
Architecture Support for Advancing PGAS (ASAP)
  • 批准号:
    1547980
  • 项目类别:
    Standard Grant
  • 资助金额:
    $23.0万
  • 财政年份:
    2015
  • 负责人:
    Tarek El-Ghazawi
  • 依托单位:
I/UCRC: FRP: Productive Scientific Computing on Heterogeneous Systems
  • 批准号:
    1230815
  • 项目类别:
    Standard Grant
  • 资助金额:
    $10.0万
  • 财政年份:
    2012
  • 负责人:
    Tarek El-Ghazawi
  • 依托单位:
海外基金