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.

得克萨斯州高级计算中心（TACC）已资助以获取和部署一个名为Frontera的系统，该系统是一种强大的科学和工程学高级计算工具（S＆E）研究。该系统的名称受到范内瓦尔·布什（Vannevar Bush）的论文“无尽边界”的启发，该纸在1950年建立了国家科学基金会。布什认为科学是人类的最后边境，导致了无尽的创新和发现流，这将改善人类状况。如今，计算是最重要的工具之一，可以更深入地进入无尽的边界。 Frontera在NSF高级计算组合中提供了一个前所未有的规模系统，该系统将在第一天产生生产科学，同时还为社区做好准备，以使转变向更有能力的未来系统。部署后，该系统将提供当前NSF领导力类计算资源的性能的三倍以上，并在广泛的领域中启用S＆E发现，否则不可能。该项目在系统生产生活期间通过运营和维护计划支持Frontera的收购计划。Frontera运营和维护计划由经验丰富的合作伙伴和供应商团队锚定，并具有社区领先的绩效记录。该项目将通过全面的项目计划来支持系统，包括一流的用户支持和培训，教育，外展，文档，数据管理，可视化，分析驱动的应用程序支持和研究合作。该计划还设有一个专门的基于广泛的科学团队，以确保S＆E应用程序有效地在此规模的资源上运行。 Frontera将通过专门的领导级计算科学团队，协作支持团队的深度计算科学参与以及容器的创新使用来支持所有S＆E学科的大科学。 此外，Frontera系统将支持广泛的软件服务，包括应用程序程序员界面（API），以支持不断发展的用户群，该用户群将更广泛地使用科学网关，自动化工作流和Web服务。 该项目将开发新的专业知识和技术，用于领导级计算和数据驱动的应用程序，以通过出版物，培训和咨询来使未来用户受益。 此外，Frontera项目将在2024年及以后的未来系统中为S＆E社区提供桥梁。 该项目将利用团队的独特教育，外展和培训活动的独特方法，为领导级计算的新用户和现有用户做好准备，并鼓励，教育和发展下一代计算研究人员。 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.

项目成果

OMB-Py: Python Micro-Benchmarks for Evaluating Performance of MPI Libraries on HPC Systems

OMB-Py：用于评估 HPC 系统上 MPI 库性能的 Python 微基准

• DOI: 10.1109/ipdpsw55747.2022.00143
• 发表时间: 2022
• 期刊: 23rd Parallel and Distributed Scientific and Engineering Computing Workshop (PDSEC
• 作者: Alnaasan, Nawras;Jain, Arpan;Shafi, Aamir;Subramoni, Hari;Panda, Dhabaleswar K
• 通讯作者: Panda, Dhabaleswar K

Designing Hierarchical Multi-HCA Aware Allgather in MPI

• DOI: 10.1145/3547276.3548524
• 发表时间: 2022-08
• 期刊: Workshop Proceedings of the 51st International Conference on Parallel Processing
• 作者: Tu Tran;Benjamin Michalowicz;B. Ramesh;H. Subramoni;A. Shafi;D. Panda

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
• 期刊: Heterogeneity in Computing Workshop
• 作者: Chen, Chen-Chun;Khorassani, Kawthar Shafie;Anthony, Quentin G.;Shafi, Aamir;Subramoni, Hari;Panda, Dhabaleswar K.
• 通讯作者: Panda, Dhabaleswar K.

Hy-Fi: Hybrid Five-Dimensional Parallel DNN Training on High-Performance GPU Clusters

Hy-Fi：高性能 GPU 集群上的混合五维并行 DNN 训练

• DOI: 10.1007/978-3-031-07312-0_6
• 发表时间: 2022
• 期刊: Proceedings International Conference on High Performance Computing
• 作者: Jain, A;Shafi, A.;Anthony, Q.;Kousha, P.;Subramoni, H.;Panda, DK.
• 通讯作者: Panda, DK.

Arm meets Cloud: A Case Study of MPI Library Performance on AWS Arm-based HPC Cloud with Elastic Fabric Adapter

Arm 与云的结合：基于 AWS Arm 的 HPC 云（具有 Elastic Fabric Adapter）的 MPI 库性能案例研究

• DOI: 10.1109/ipdpsw55747.2022.00083
• 发表时间: 2022
• 期刊: IEEE International Parallel and Distributed Processing Symposium Workshops
• 作者: Xu, Shulei;Shafi, Aamir;Subramoni, Hari;Panda, Dhabaleswar K.
• 通讯作者: Panda, Dhabaleswar K.