OAC Core: Small: Architecture and Network-aware Partitioning Algorithms for Scalable PDE Solvers

OAC 核心：小型：可扩展 PDE 求解器的架构和网络感知分区算法

• 批准号: 2008772
• 负责人: Hari Sundar
• 金额: $ 49.93万
• 依托单位: University of Utah
• 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: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2008772&HistoricalAwards=false
• 关键词: OAC; Core; Small; Architecture; Network

Solving large-scale partial differential equations (PDE) is common in science and engineering, from studying gravitational waves to designing aerodynamic cars. Given the scale of these problems, solving such PDEs requires supercomputing resources. The latest supercomputing architectures are different from the previous generation of leadership class architectures and and are characterized by high levels of diversity within and across machines. Such diversity and heterogeneity makes it extremely difficult to effectively distribute work, i.e., partition the data or tasks, across disparate computing resources. Since the primary objective of building leadership class machines is to further scientific discovery and national prosperity, it is essential that applications, old and new, are able to scale and utilize these machines to their full potential. This project develops novel data and task partitioning algorithms that factor in the architectural characteristics of modern supercomputers to enable efficient and scalable utilization of current and future computing architectures.Existing data and task partitioning schemes do not explicitly consider the underlying architectural topology while partitioning or is done indirectly during the design of the algorithm and codes. Ignoring topology leads to loss of scalability and performance, while shifting the burden to algorithm/code design increases the development costs and complexity, and decreases portability. While data and task partitioning for parallelization, along with mapping the partitions to processes, have been studied for a long time, they have not been considered as a combined problem. To a large extent this was due to the simple structures and symmetry that existed in cluster computing architectures. Inefficiencies that did not significantly impact performance and scalability ten years ago are starting to inhibit scalability and thereby scientific discovery. This project is a first step in ensuring that scientific discovery is not hampered as a result of the difficulty in porting codes to new architectures. This project develops new graph and space-filling-curve-based partitioning algorithms that are aware of the architectural topology and are able to automatically generate data/task partitions and mappings to address problems with current schemes. The algorithms and software developed as part of this proposal will have wide-ranging impact, by improving the performance and scalability of legacy applications and reducing the development cost and improving the portability of new applications, to run efficiently on systems ranging from simple shared memory architectures to the largest heterogeneous clusters.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.

求解大规模偏微分方程（PDE）在科学和工程中很常见，从研究引力波到设计气动汽车。考虑到这些问题的规模，解决这样的偏微分方程需要超级计算资源。最新的超级计算架构不同于上一代的领导级架构，其特点是机器内部和机器之间的高度多样性。这种多样性和异构性使得在不同的计算资源之间有效地分配工作（即对数据或任务进行分区）变得极其困难。由于建造领导级机器的主要目标是促进科学发现和国家繁荣，因此，无论新旧，应用程序都能够扩展并充分利用这些机器的潜力，这一点至关重要。该项目开发了新颖的数据和任务划分算法，这些算法考虑了现代超级计算机的体系结构特征，从而能够有效和可扩展地利用当前和未来的计算体系结构。现有的数据和任务分区方案在分区时没有明确地考虑底层的体系结构拓扑，或者在算法和代码的设计过程中间接地进行。忽略拓扑会导致可伸缩性和性能的损失，而将负担转移到算法/代码设计上则会增加开发成本和复杂性，并降低可移植性。虽然用于并行化的数据和任务分区以及将分区映射到进程已经研究了很长时间，但它们并没有被视为一个综合问题。在很大程度上，这是由于集群计算体系结构中存在的简单结构和对称性。十年前对性能和可伸缩性没有显著影响的低效率开始抑制可伸缩性，从而抑制科学发现。这个项目是确保科学发现不会因为将代码移植到新架构的困难而受到阻碍的第一步。该项目开发了新的基于图形和空间填充曲线的分区算法，这些算法能够意识到架构拓扑，并能够自动生成数据/任务分区和映射，以解决当前方案中的问题。作为该提案一部分的算法和软件开发将产生广泛的影响，通过提高遗留应用程序的性能和可扩展性，降低开发成本和提高新应用程序的可移植性，在从简单的共享内存架构到最大的异构集群的系统上高效运行。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Multi-discretization domain specific language and code generation for differential equations

微分方程的多离散化域特定语言和代码生成

• 发表时间: 2023
• 期刊: Journal of computational science
• 影响因子: 3.3
• 作者: Heisler, Eric;Deshmukh, Aadesh;Mazumder, Sandip;Sadayappan, Ponnuswamy;Sundar, Hari
• 通讯作者: Sundar, Hari

Scalable Adaptive PDE Solvers in Arbitrary Domains

• DOI: 10.1145/3458817.3476220
• 发表时间: 2021-08
• 期刊: SC21: International Conference for High Performance Computing, Networking, Storage and Analysis
• 作者: K. Saurabh;Masado Ishii;Milinda Fernando;Boshun Gao;Kendrick Tan;M. Hsu;A. Krishnamurthy;H. Sundar;B. Ganapathysubramanian

Finch: Domain Specific Language and Code Generation for Finite Element and Finite Volume in Julia

Finch：Julia 中有限元和有限体积的领域特定语言和代码生成

• DOI: 10.1007/978-3-031-08751-6_9
• 发表时间: 2022
• 期刊: Journal of Geodesy
• 影响因子: 4.4
• 作者: E. Heisler;Aadesh Deshmukh;H. Sundar
• 通讯作者: H. Sundar

A Domain Specific Language Applied to Phonon Boltzmann Transport for Heat Conduction

应用于热传导声子玻尔兹曼输运的领域特定语言

• DOI: 10.1115/imece2022-95034
• 发表时间: 2022
• 期刊: ASME International Mechanical Engineering Congress and Exposition
• 作者: Heisler, Eric;Saurav, Siddharth;Deshmukh, Aadesh;Mazumder, Sandip;Sadayappan, Ponnuswamy;Sundar, Hari
• 通讯作者: Sundar, Hari