[5-16]On the Road to Exascale and Beyond, Intelligent Restarted Linear Algebra Methods

文章來源： | 發布時間：2016-05-13 | 【打印】【關閉】

報告題目：On the Road to Exascale and Beyond, Intelligent Restarted Linear Algebra Methods

　　報告人：Prof. Serge G. Petition

　　時間：2016年5月16日 10:00

　　地點：5號樓A507室

　　報告摘要:

　　Exascale hypercomputers are expected to have highly hierarchical architectures with nodes composed by lot-of-core processors and accelerators. The different programming levels (from clusters of processors loosely connected to tightly connected lot-of-core processors and/or accelerators) will generate new difficult algorithm issues. New methods should be defined and evaluated with respect to modern state-of-the-art of applied mathematics and scientific methods.

　　Krylov linear methods such as GMRES and ERAM are now heavily used with success in various domains and industries despite their complexity. Their convergence and speed greatly depends on the hardware used and on the choice of the Krylov subspace size and other parameters which are difficult to determine efficiently in advance. Moreover, hybrid Krylov Methods would allow reducing the communications along all the cores, limiting the reduction only through subsets of these cores. Added to their numerical behaviours and their fault tolerance properties, these methods are interesting candidates for exascale/extreme matrix computing. Avoiding communication strategies may also be developed for each of the instance of these methods, generating complex methods but with high potential efficiencies. These methods have a lot of correlated parameter which may be optimized using auto/smart-tuning strategies to accelerate convergence, minimize storage space, data movements, and energy consumption.

In this talk, we first will present some basic matrix operations utilized on Krylov methods on clusters of accelerators, with respect to a few chosen sparse compressed formats. We will discuss some recent experiments on a cluster of accelerators concerning comparison between orthogonal, incompletely orthogonal and non-orthogonal Krylov Basis computing. Then, we will discuss some results obtained on a cluster of accelerators to compute eigenvalues using the MERAM method with respect to the restarting strategies. We will survey some auto/smart-tunning strategies we proposed and evaluated for some of the Krylov method parameters. As a conclusion, we will introduce the concept of intelligent linear algebra for future hybrid methods on post-petascale computers, on the road to exascale hybrid methods.

　　報告人簡介:

　　Prof. Serge G. Petiton received the M.S. in Applied Mathematics, the Ph.D. degree in computer science, and the “Habilitation a? diriger des recherches”, from Pierre and Marie Curie University, Univ. PARIS 6. He was post-doc student, registered at the graduate school, and junior researcher scientist at the YALE University, 1989-1990. He has been researcher at the “Site Experimental en Hyperparallelisme” (supported by CNRS, CEA, and French DoD) from 1991 to 1994. He also was affiliate research scientist at YALE and visiting research fellow in several US laboratories, especially in NASA-ICASE and the AHPCRC during the period 1991-1994. Since then, Serge G. Petiton is Professor at the University of Lille, Sciences and Technologies. Serge G. Petiton was, and is, P.I. of several international projects with Japan, Venezuela and Germany. Since 2012, Serge G. Petiton has a half time CNRS senior position at the “Maison de la Simulation” in Saclay.

　　Serge G. Petiton has been scientific director of more than 22 Ph.D.s and has authored more than 100 articles on international journals and conferences. His main current research interests are in “Parallel and Distributed Computing”, “Post-Petascale Auto/smart-tuned Dense and Sparse Linear Algebra”, and “Language and Programming Paradigm for Extreme Modern Scientific Computing”; targeting especially geoscience and big data applications.

　　Serge G. Petiton is a member of SIAM, ACM, IEEE, the YALE club of France and the Ivy Plus European leaders club.