Operations & Maintenance for the Endless Frontier

运营

• 批准号: 1854828
• 负责人: Daniel Stanzione
• 金额: $ 6000万
• 依托单位: University of Texas at Austin
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1854828&HistoricalAwards=false
• 关键词: Operations; & Maintenance; Endless; Frontier

The Texas Advanced Computing Center (TACC) has been funded to acquire and deploy a system called Frontera, a powerful new advanced computational instrument for Science and Engineering (S&E) research. The name of the system is inspired by Vannevar Bush's paper "The Endless Frontier", which led to the establishment of the National Science Foundation in 1950. Bush argued that science was humanity's last frontier, leading to an endless stream of innovation and discovery that would improve the human condition. Today, computation is one of the most critical tools to advance more deeply into the Endless Frontier. Frontera provides a system of unprecedented scale in the NSF advanced computational portfolio that will yield productive science on day one, while also preparing the community for the shift to even more capable future systems. When deployed, the system will provide more than three times the performance of the current NSF leadership-class computing resource and enable S&E discoveries across a broad range of domains that were not possible otherwise. This project supports the Frontera acquisition plan with the operations and maintenance plan during the production life of the system.The plan for Frontera operations and maintenance is anchored by an experienced team of partners and vendors with a community-leading track record of performance. The project will support the system through a comprehensive project plan, including first-class user support and training, education, outreach, documentation, data management, visualization, analytics-driven application support, and research collaboration. The plan also features a dedicated, broad-based science team, selected to ensure that S&E applications run effectively on a resource of this scale. Frontera will support big science in virtually all S&E disciplines through a dedicated leadership-class computing science team, deep computational science engagements of the Collaborative Support team, and the innovative use of containers. Additionally, the Frontera system will support a broad range of software services, including Application Programmer Interfaces (APIs) to support an evolving user base that will make more extensive use of science gateways, automated workflows, and web services. The project will develop new expertise and techniques for leadership-class computing and data-driven applications that benefit future users worldwide through publications, training, and consulting. Furthermore, the Frontera project will serve as a bridge for the S&E community to future systems in 2024 and beyond. The project will leverage the team's unique approach to education, outreach, and training activities to prepare new and current users for leadership-class computing and to encourage, educate, and develop the next generation of computational researchers. The team includes leaders in campus bridging and minority-serving institution (MSI) outreach, and will use data technologies that will increase the number and diversity of people using leadership-class computing for traditional and data-driven applications.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.

德克萨斯州高级计算中心 (TACC) 已获得资助购买并部署名为 Frontera 的系统，这是一种用于科学与工程 (S&E) 研究的强大的新型高级计算仪器。该系统名称的灵感源自万尼瓦尔·布什 (Vannevar Bush) 的论文《无尽的前沿》(The Endless Frontier)，该论文促成了 1950 年国家科学基金会的成立。布什认为，科学是人类最后的前沿，带来源源不断的创新和发现，改善人类状况。如今，计算是更深入地探索无尽前沿的最关键工具之一。 Frontera 在 NSF 先进计算组合中提供了一个规模空前的系统，该系统将在第一天产生富有成效的科学成果，同时也为社区向更强大的未来系统的转变做好准备。部署后，该系统将提供比当前 NSF 领先级计算资源三倍以上的性能，并实现跨广泛领域的 S&E 发现，这是其他方式无法实现的。该项目通过系统生产生命周期内的运营和维护计划来支持 Frontera 采购计划。Frontera 运营和维护计划由经验丰富的合作伙伴和供应商团队负责，他们拥有社区领先的绩效记录。该项目将通过全面的项目计划支持该系统，包括一流的用户支持和培训、教育、推广、文档、数据管理、可视化、分析驱动的应用程序支持和研究协作。该计划还设有一个专门的、基础广泛的科学团队，其选择是为了确保科学与工程应用程序在如此规模的资源上有效运行。 Frontera 将通过专门的领导级计算科学团队、协作支持团队的深入计算科学参与以及容器的创新使用，支持几乎所有 S&E 学科的大科学。 此外，Frontera 系统将支持广泛的软件服务，包括应用程序编程接口 (API)，以支持不断发展的用户群，从而更广泛地使用科学网关、自动化工作流程和 Web 服务。 该项目将为领先级计算和数据驱动应用程序开发新的专业知识和技术，通过出版物、培训和咨询使全球未来用户受益。 此外，Frontera 项目将成为 S&E 社区与 2024 年及以后的未来系统的桥梁。 该项目将利用该团队独特的教育、推广和培训活动方法，为新用户和现有用户做好领导级计算的准备，并鼓励、教育和培养下一代计算研究人员。该团队包括校园桥接和少数族裔服务机构 (MSI) 外展方面的领导者，并将使用数据技术来增加将领导级计算用于传统和数据驱动应用程序的人员的数量和多样性。该奖项反映了 NSF 的法定使命通过使用基金会的智力优点和更广泛的影响审查标准进行评估，并被认为值得支持。

项目成果

Layout-aware Hardware-assisted Designs for Derived Data Types in MPI

MPI 中派生数据类型的布局感知硬件辅助设计

• DOI: 10.1109/hipc53243.2021.00044
• 发表时间: 2021-12
• 期刊: and Analytics (HiPC
• 作者: Suresh, Kaushik Kandadi;Ramesh, Bharath;Chen, Chen Chun;Ghazimirsaeed, Seyedeh Mahdieh;Bayatpour, Mohammadreza;Shafi, Aamir;Subramoni, Hari;Panda, Dhabaleswar K.
• 通讯作者: Panda, Dhabaleswar K.

“Hey CAI” - Conversational AI Enabled User Interface for HPC Tools

–Hey CAI – 适用于 HPC 工具的对话式 AI 用户界面

• DOI: 10.1007/978-3-031-07312-0_5
• 发表时间: 2022-05
• 期刊: Proceedings International Conference on High Performance Computing
• 作者: Kousha, P.;Jain, A.;Kolli, A.;Prasanna, S.;Miriyala, S.;Subramoni, H.;Shafi, A.;Panda, DK.
• 通讯作者: Panda, DK.

Towards Java-based HPC using the MVAPICH2 Library: Early Experiences

使用 MAPICH2 库实现基于 Java 的 HPC：早期经验

• DOI: 10.1109/ipdpsw55747.2022.00091
• 发表时间: 2022-05
• 期刊: 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (
• 作者: Al;Shafi, Aamir;Subramoni, Hari;Panda, Dhabaleswar K.
• 通讯作者: Panda, Dhabaleswar K.

Highly Efficient Alltoall and Alltoallv Communication Algorithms for GPU Systems

适用于 GPU 系统的高效 Alltoall 和 Alltoallv 通信算法

• DOI: 10.1109/ipdpsw55747.2022.00014
• 发表时间: 2022-05
• 期刊: Heterogeneity in Computing Workshop
• 作者: Chen, Chen;Khorassani, Kawthar Shafie;Anthony, Quentin G.;Shafi, Aamir;Subramoni, Hari;Panda, Dhabaleswar K.
• 通讯作者: Panda, Dhabaleswar K.

Network Assisted Non-Contiguous Transfers for GPU-Aware MPI Libraries

GPU 感知 MPI 库的网络辅助非连续传输

• 发表时间: 2022-01
• 期刊: Hot Interconnects
• 作者: Suresh, K.;Khorassani, K.;Chen, C.;Ramesh, B.;Abduljabbar, M.;Shafi, A.;Panda, DK.
• 通讯作者: Panda, DK.