SC Conference - Activity Details

Parallel Computing Landscape: A View from Berkeley

David Patterson  (University of California, Berkeley)
Invited Speakers Session
Wednesday,  09:15AM - 10:00AM
Room Ballroom D
In December 2006 we published a broad survey of the issues for the whole field concerning the multicore/manycore sea change (see view.eecs.berkeley.edu). We view the ultimate goal as being able to productively create efficient, correct, and portable software that smoothly scales when the number of cores per chip doubles biennially. This talk covers the specific research agenda that a large group of us at Berkeley are going to follow (see parlab.eecs.berkeley.edu) as part of a center funded for five years by Intel and Microsoft. To take a fresh approach to the longstanding parallel computing problem, our research agenda will be driven by compelling applications developed by domain experts in personal health, image retrieval, music, speech understanding, and browsers. The development of parallel software is divided into two layers: an efficiency layer that aims at low overhead for 10 percent of the best programmers, and a productivity layer for the rest of the programming community--including domain experts--that reuses the parallel software developed at the efficiency layer. Key to this approach is a layer of libraries and programming frameworks centered around the 13 design patterns that we identified in the Berkeley View report. We rely on autotuning to map the software efficiently to a particular parallel computer. The role of the operating systems and the architecture in this project is to support software and applications in achieving the ultimate goal. Examples include primitives like thin hypervisors and libraries for the operating system and hardware support for partitioning and fast barrier synchronization. We will prototype the hardware of the future using field programmable gate arrays (FPGAs) on a common hardware platform being developed by a consortium of universities and companies (see ramp.eecs.berkeley.edu).
   IEEE Computer Society  /  ACM     2 0   Y E A R S   -   U N L E A S H I N G   T H E   P O W E R   O F   H P C