Title :
A Decoupled Execution Paradigm for Data-Intensive High-End Computing
Author :
Chen, Yong ; Chen, Chao ; Sun, Xian-He ; Gropp, William D. ; Thakur, Rajeev
Author_Institution :
Dept. of Comput. Sci., Texas Tech Univ., Lubbock, TX, USA
Abstract :
High-end computing (HEC) applications in critical areas of science and technology tend to be more and more data intensive. I/O has become a vital performance bottleneck of modern HEC practice. Conventional HEC execution paradigms, however, are computing-centric for computation intensive applications. They are designed to utilize memory and CPU performance and have inherent limitations in addressing the critical I/O bottleneck issues of HEC. In this study, we propose a decoupled execution paradigm (DEP) to address the challenging I/O bottleneck issues. DEP is the first paradigm enabling users to identify and handle data-intensive operations separately. It can significantly reduce costly data movement and is better than the existing execution paradigms for data-intensive applications. The initial experimental tests have confirmed its promising potential. Its data-centric architecture could have an impact in future HEC systems, programming models, and algorithms design and development.
Keywords :
parallel machines; performance evaluation; CPU performance; DEP; HEC execution paradigms; IO bottleneck issues; computation intensive applications; data movement; data-centric architecture; data-intensive high-end computing; decoupled execution paradigm; high-end computing applications; performance bottleneck; Computational modeling; Computer architecture; Data models; Data processing; Libraries; Programming; Runtime; data-intensive computing; decoupled execution paradigm; high-end computing; storage;
Conference_Titel :
Cluster Computing (CLUSTER), 2012 IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4673-2422-9
DOI :
10.1109/CLUSTER.2012.80