CRII: CI: Scalable Multigrid Algorithms for Solving Elliptic PDEs on Power-Efficient Clusters

CRII：CI：用于求解节能集群上椭圆偏微分方程的可扩展多重网格算法

基本信息

批准号：
1464244
负责人：
Hari Sundar
金额：
$ 17.5万
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：
2015
资助国家：
美国
起止时间：
2015-07-01 至 2018-06-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1464244&HistoricalAwards=false
关键词：
CRII CI Scalable Multigrid Algorithms

项目摘要

While emerging extreme-scale computing systems could provide unprecedented resources for scientific discovery, two major challenges are the cost and the energy required to run and cool these systems. The system-on-a-chip (SoC) components widely used in the mobile device market are substantially cheaper and more energy efficient compared to desktop or server processors, and represent a promising option for future systems. This project addresses three challenges for emerging extreme-scale computing systems: the potential move to mobile processors, the increasing levels of concurrency, and the need for energy efficiency. Shared infrastructure is developed to accelerate interdisciplinary and collaborative research. This is a first step in the development of mathematical and computational methods for solving scientific computing problems on low-energy systems that can reduce the overall cost of scientific discoveries and promote the progress of science. The project develops a scalable and power efficient parallel multigrid solver for elliptic partial differential equations (PDEs) that targets emerging extreme scale computing systems. Elliptic PDEs are ubiquitous in natural, engineered and societal systems, and the efficient multigrid solvers being developed as part of this project are beneficial to research across several disciplines. The project also develops a power-performance model to aid in application-controlled power-performance management, at the per-node level. Motivated by the slower interconnections common on low-power clusters, the project develops a new class of parallel algorithms that lower the power utilization of computations to overlap with the communication. This is the reverse of what has conventionally been done, where communication costs are hidden by overlapping with computation. Additionally, the algorithms utilize compute nodes that are not computationally active at all times -- a radically different approach that creates a new class of energy-efficient scalable parallel algorithms. The research will be evaluated initially using a 16 node Tegra/ARM-based cluster and ultimately, the CloudLab cluster at the University of Utah. The developed software will be disseminated using an open source license. The scalability experiments will be run on the NSF-supported CloudLab cluster, hosted at the University of Utah, allowing other users to re-create both the hardware and software stack used for the experiments. The resulting system will be among the first large scale low-energy clusters available anywhere.

虽然新兴的超大规模计算系统可以为科学发现提供前所未有的资源，但两个主要挑战是运行和冷却这些系统所需的成本和能源。与台式机或服务器处理器相比，移动设备市场广泛使用的片上系统 (SoC) 组件更便宜、更节能，是未来系统的一个有前途的选择。该项目解决了新兴超大规模计算系统的三大挑战：向移动处理器的潜在转变、并发水平的提高以及对能源效率的需求。开发共享基础设施是为了加速跨学科和协作研究。这是发展解决低能系统科学计算问题的数学和计算方法的第一步，可以降低科学发现的总体成本，促进科学进步。该项目开发了一种可扩展且节能的并行多重网格求解器，适用于椭圆偏微分方程 (PDE)，其目标是新兴的超大规模计算系统。椭圆偏微分方程在自然、工程和社会系统中普遍存在，作为该项目一部分开发的高效多重网格求解器有利于跨多个学科的研究。该项目还开发了一个功耗性能模型，以帮助在每个节点级别进行应用程序控制的功耗性能管理。受低功耗集群中常见的较慢互连速度的推动，该项目开发了一种新型并行算法，可降低与通信重叠的计算的功耗。这与传统做法相反，传统做法是通过与计算重叠来隐藏通信成本。此外，这些算法利用的计算节点并非始终处于计算活动状态，这是一种完全不同的方法，创建了一类新的节能可扩展并行算法。该研究最初将使用基于 Tegra/ARM 的 16 节点集群进行评估，最终使用犹他大学的 CloudLab 集群进行评估。开发的软件将使用开源许可证进行传播。可扩展性实验将在犹他大学托管的 NSF 支持的 CloudLab 集群上运行，允许其他用户重新创建用于实验的硬件和软件堆栈。由此产生的系统将成为第一批随处可用的大规模低能量集群之一。

项目成果

期刊论文数量（4）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

A Scalable Hierarchical Semi-Separable Library for Heterogeneous Clusters

异构集群的可扩展分层半分离库

DOI：
10.1109/icpp.2017.60
发表时间：
2017-08
期刊：
46th International Conference on Parallel Processing (ICPP
影响因子：
0
作者：
Fernando, Isuru Dilanka;Jayasena, Sanath;Fernando, Milinda;Sundar, Hari
通讯作者：
Sundar, Hari

Improving Performance and Scalability of Algebraic Multigrid through a Specialized MATVEC

通过专门的 MATVEC 提高代数多重网格的性能和可扩展性

DOI：
发表时间：
2018-09
期刊：
IEEE High Performance Extreme Computing Conference
影响因子：
0
作者：
Majid Rasouli; Vidhi Zala
通讯作者：
Vidhi Zala

Towards Triangle Counting on GPU using Stable Radix Binning

使用稳定基数合并在 GPU 上进行三角形计数

DOI：
发表时间：
2018-09
期刊：
IEEE High Performance Extreme Computing Conference
影响因子：
0
作者：
Tirpankar, Nishith;Sundar, Hari
通讯作者：
Sundar, Hari

Machine and Application Aware Partitioning for Adaptive Mesh Refinement Applications

自适应网格细化应用程序的机器和应用程序感知分区

DOI：
10.1145/3078597.3078610
发表时间：
2017-06
期刊：
Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing
影响因子：
0
作者：
Fernando, Milinda;Duplyakin, Dmitry;Sundar, Hari
通讯作者：
Sundar, Hari