Parallel Programming in the Age of Ubiquitous Parallelism
撰稿：
摄影：
发布时间：2013年01月09日
时间：2013年1月10日（周四）上午9:00-10:30
地点：446会议室
摘要
Multicore and manycore processors are now ubiquitous, butparallel programming remains as difficult as it was 30-40 years ago. During this time, our community has exploredmany promising approaches including functional and dataflow languages, logic programming, and automatic parallelization using program analysis and restructuring, but none of theseapproaches has succeeded except in a few niche applicationareas.
In this talk, I will argue that these problems arise largelyfrom the computation-centric foundations and abstractions that we currently use to think about parallelism. In theirplace, I will propose a novel data-centric foundation forparallel programming called the operator formulation in whichalgorithms are described in terms of actions on data.The operator formulation shows that a generalized form ofdata-parallelism called amorphous data-parallelism is ubiquitouseven in complex, irregular graph applications such as mesh generation/refinement/partitioning and SAT solvers.Regular algorithms emerge as a special case of irregular ones, and many application-specific optimizationtechniques can be generalized to a broader context.The operator formulation also leads to a structural analysis of algorithms called TAO-analysis that provides implementation guidelines for exploiting parallelism efficiently. Finally, I will describe a system called Galois based on these ideasfor exploiting amorphous data-parallelism on multicores and GPUs.
主讲人简介
KeshavPingali is a Professor in the Department of Computer Scienceat the University of Texas at Austin, and he holds the W.A."Tex" Moncrief Chair of Computing in the Institute for Computational Engineering and Sciences (ICES) at UT Austin. He was on the faculty of the Department of Computer Science at Cornell University from 1986 to 2006, where he held the India Chair of Computer Science.
Pingali's research has focused on programminglanguages and compiler technology for program understanding, restructuring, and optimization. His group is known for its contributions to memory-hierarchy optimization; some of these have been patented and are in use in industry compilers. His current research is focused on programming languagesand tools for multicore processors.
Pingali is a Fellow of the ACM, IEEE and the American Association for the Advancement of Science. He was the co-Editor-in-chief of the ACM Transactions on Programming Languages and Systems, and currently serves on the editorial boards of the InternationalJournal of Parallel Programming and Distributed Computing. He also served on the NSF CISE Advisory Committee (2009-2012).
附件下载：
合作交流