Workshop on

Exploiting Parallelism using GPUs and other Hardware-Assisted Methods

EPHAM 2009

In conjunction with

The International Symposium on Code Generation and Optimization (CGO) 2009

Seattle, Washington.  March 22-25, 2009

Program

• Welcome – March 22, 8:45 am – 9:00 am
• Programming Models – March 22, 9:00 am – 10:30 am
  • Design and Implementation of a High Level Framework for GPUs – Michael Wolfe.
  • A MapReduce Framework in Heterogenous GPU Environment – Dehao Chen, Chuntao Hong, Wenguang Chen, Haibo Lin, Weimin Zheng
  • GPU Kernels as Data-Parallel Array Computations in Haskell – Sean Lee, Manuel M.T. Chakravarty, Vinod Grover, Gabriele Keller
• Break – 10:30 am – 11:00 am
• Application and Performance Frameworks – 11:00 am to 12:00 noon
  • Analytical Performance Prediction for Evaluation and Tuning of GPGPU Applications – Sara Baghsorkhi, Wen-mei Hwu
  • GPU-Accelerated Text Mining – Yongpeng Zhang, Frank Mueller, Xiaohui Cui, Thomas Potok
• Wrapup – 12:00 noon

Theme

This workshop will focus on compilation techniques for exploiting parallelism in emerging massively multi-threaded and multi-core architectures, with a particular focus on the use of general-purpose GPU computing techniques to overcome traditional barriers to parallelization. Recently, GPUs have evolved to address programming of general purpose computations, especially those exemplified by data parallel models. This change will have long-term implications for languages, compilers, and programming models. Development of higher level programming languages, models and compilers that exploit such processors will be important. Clearly, the economics and performance of applications is affected by a transition to general-purpose GPU computing. This will require new ideas and directions as well as recasting some older techniques to the new paradigm

Topics of Interest

We invite papers in this emerging discipline which include, but are not limited, to the following areas of interest.

• Static and dynamic parallelization for hybrid CPU/GPU systems
• Compiler optimizations for GPU computing
• Language constructs and extensions to enable parallel programming with GPUs
• Run-time techniques to off-load computation to the GPU
• Language, programming model, or compiler techniques for mapping irregular computations to GPUs
• Debugging support for GPU programs
• Performance analysis tools related to GPU computing
• Other hardware-assisted methods for extracting and exploiting parallelism

Important Dates

Feb. 9th 2009: Paper submission deadline
Mar. 8th 2009: Notification of acceptance
Mar. 15th 2009: Camera-ready version of papers due
Mar. 22nd 2009: The workshop

Workshop Organizers

Vinod Grover, NVIDIA Corporation
Richard Johnson, NVIDIA Corporation

Program Committee

Manuel M T Chakravarty, University of New South Wales
Rudi Eigenman, Purdue University
Anwar Ghuloum, Intel
Naga Govindaraju, Microsoft
Wen-mei Hwu, University of Illinois, Urbana-Champaign
Miriam Leeser, Northeastern University
Dinesh Manocha, University of North Carolina
Shane Ryoo, ZeroSoft
Bratin Saha, Intel
Bixia Zheng, AMD

Submission Guidelines

Papers of 6-10 pages may be submitted using any format. The abstract should clearly state the problem being studied, the methods used, and the results. If the results are preliminary, the authors should state their expectation for the final results. To submit, please send a pdf of your submission to epham2009@nvidia.com Final submissions should use the standard ACM conference format (two columns with 9 pt Times Roman font, etc.).