权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

SHF: Medium: Compute on Data Path: Combating Data Movement in High Performance Computing

SHF：中：数据路径上的计算：在高性能计算中对抗数据移动

基本信息

批准号：
1409946
负责人：
Yong Chen
金额：
$ 100万
依托单位：
Texas Tech University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2014
资助国家：
美国
起止时间：
2014-06-01 至 2021-05-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1409946&HistoricalAwards=false
关键词：
SHF Medium Compute Data Path

项目摘要

High performance computing enabled simulation has been widely considered a third pillar of science along with theory and experimentation, and is a strategic tool in many aspects of scientific discovery and innovation. High performance computing simulations, however, have become highly data intensive in recent years due to data acquisition and generation becoming much cheaper, newer high-resolution multi-model scientific discovery producing and requiring more data, and the insight that useful data can be mined out of large amounts of data being substantially increased. This project combats the increasingly critical data movement challenge in high performance computing. This project studies the feasibility of a new Compute on Data Path methodology that expects to improve the performance and energy efficiency for high performance computing. This new methodology models both computations and data as objects with a data model that encapsulates and binds them. It fuses data motion and computation leveraging programming model and compiler. It develops an object-based store and runtime to enable computations along data path pipeline. In recent years, a proliferation of advanced high performance computing architectures including multi- and many-core systems, co-processors and accelerators, and heterogeneous computing platforms have been observed. The software solution that addresses the critical data movement challenge, however, has significantly lagged behind. This project has the potential of advancing the understandings and the software solution and further unleashing the power of high performance computing enabled simulation.

高性能计算支持的模拟被广泛认为是继理论和实验之后的第三个科学支柱，并且是科学发现和创新许多方面的战略工具。然而，近年来，由于数据采集和生成变得更加便宜，更新的高分辨率多模型科学发现产生并需要更多数据，以及可以从大量数据中挖掘有用数据的洞察力大幅增加，高性能计算模拟已变得高度数据密集型。该项目应对高性能计算中日益严峻的数据移动挑战。该项目研究了一种新的数据路径计算方法的可行性，该方法有望提高高性能计算的性能和能源效率。这种新方法将计算和数据建模为对象，并使用封装和绑定它们的数据模型。它利用编程模型和编译器融合数据移动和计算。它开发了一个基于对象的存储和运行时，以实现沿数据路径管道的计算。近年来，先进的高性能计算架构（包括多核和众核系统、协处理器和加速器以及异构计算平台）不断涌现。然而，解决关键数据移动挑战的软件解决方案却明显落后。该项目有潜力推进理解和软件解决方案，并进一步释放高性能计算支持的模拟的力量。

项目成果

期刊论文数量（5）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Comparison of Threading Programming Models

DOI：
10.1109/ipdpsw.2017.141
发表时间：
2017-05
期刊：
2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
影响因子：
0
作者：
S. Salehian;Jiawen Liu;Yonghong Yan
通讯作者：
S. Salehian;Jiawen Liu;Yonghong Yan

Remote Atomic Extension (RAE) for Scalable High Performance Computing

用于可扩展高性能计算的远程原子扩展 (RAE)

DOI：
10.1109/dac18072.2020.9218589
发表时间：
2020
期刊：
Proceedings of The 57th Design Automation Conference (DAC'20
影响因子：
0
作者：
Wang, Xi;Williams, Brody;Leidel, John D.;Ehret, Alan;Kinsy, Michel;Chen, Yong
通讯作者：
Chen, Yong

HOMP: Automated Distribution of Parallel Loops and Data in Highly Parallel Accelerator-Based Systems

HOMP：基于高度并行加速器的系统中并行循环和数据的自动分配

DOI：
10.1109/ipdps.2017.99
发表时间：
2017
期刊：
2017 IEEE International
影响因子：
0
作者：
Yan, Yonghong;Liu, Jiawen;Cameron, Kirk W.;Umar, Mariam
通讯作者：
Umar, Mariam

I/O characteristic discovery for storage system optimizations

DOI：
10.1016/j.jpdc.2020.08.005
发表时间：
2021-02
期刊：
J. Parallel Distributed Comput.
影响因子：
0
作者：
Jiang Zhou;Yong Chen;Dong Dai;Zhuang Yu;Weiping Wang
通讯作者：
Jiang Zhou;Yong Chen;Dong Dai;Zhuang Yu;Weiping Wang

MIQS: metadata indexing and querying service for self-describing file formats

DOI：
10.1145/3295500.3356146
发表时间：
2019-11
期刊：
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
影响因子：
0
作者：
Wei Zhang;S. Byna;Houjun Tang;Brody Williams;Yong Chen
通讯作者：
Wei Zhang;S. Byna;Houjun Tang;Brody Williams;Yong Chen