Joint Workshop on
High-Level Parallel Programming Models and Supportive Environments
Performance Optimization for High-Level Languages and Libraries

held in conjunction with the

22nd IEEE International Parallel & Distributed Processing Symposium (IPDPS 2008)

April 14th, 2008, Hyatt Regency Resort in Miami, Florida


HIPS-POHLL 2008 is a full-day workshop to be held at the IPDPS 2008 focusing on high level parallel programming models and performance optimization for high level languages and tools, and will bring together researchers working in these areas. The technical program will consist of presentations on the following topics:

Workshop program

08:00 Opening Comments
Chair: Martin Schulz (LLNL)
08:15 Tools
Chair: Martin Schulz, Lawrence Livermore National Lab, USA
08:15Keynote presentation:
A Framework for Automated Performance Bottleneck Detection,
David Klepacki, IBM T.J. Watson Research, USA
09:00 NoiseMiner: An Algorithm for Scalable Automatic Computational Noise and Software Interference Detection, Isaac Dooley, Chao Mei and Laxmikant Kale, University of Illinois at Urbana-Champaign, USA
09:30 Towards Scalable Performance Analysis and Visualization through Data Reduction, Chee Wai Lee, Celso Mendes and Laxmikant Kale University of Illinois at Urbana-Champaign, USA
Coffee Break

10:30 Runtime
Chair: Sam Midkiff, Purdue University, USA
00:30Keynote presentation:
Optimization via Reflection on Work Stealing in TBB, Arch Robison, Michael Voss and Alexey Kukanov, Intel, USA
11:15 Model Guided Performance Tuning of Parameter Values: A Case Study with Molecular Dynamics Visualization, Yoonju Nelson, Bhupesh Bansal, Mary Hall, Aiichiro Nakano and Kristina Lerman University of Southern California, USA.
11:45 Extended Characterization of DMA Transfers on the Cell BE Processor, Farshad Khunjush and Nikitas J. Dimopoulos, University of Victoria, Canada
Lunch Break

1:30 Languages and Compilers
Chair: P. (Saday) Sadayappan, Ohio State University, USA
1:30 Programmability of the HPCS Languages: A Case Study with a Quantum Chemistry Kernel, Aniruddha Shet, Wael Elwasif, Robert Harrison and David Bernholdt, Oak Ridge National Lab, USA
2:00 An Empirical Study of the Performance and Productivity of Two Parallel Programming Models, Imran Patel and John Gilbert, University of California at Santa Barbara, USA
2:30 Compiler-Controlled Extraction of Computation-Communication Overlap in MPI Applications, Dibyendu Das, Manish Gupta, Rajan Ravindran, W. Shivani, P. Sivakeshava and Rishabh Uppal, IBM, India
Coffee Break

3:30 Applications
Chair: J. (Ram) Ramanujam, Louisiana State University, USA
4:00 Build to Order Linear Algebra Kernels, Jeremy Siek, Ian Karlin and Elizabeth Jessup, University of Colorado at Boulder, USA
4:30 Cache optimization for mixed regular and irregular computations Michael Schwind and Gudula Rünger, TU Chemnitz, Germany
5:00 Array Optimizations for Parallel Implementations of High Productivity Languages, Mackale Joyner, Zoran Budimlic, Vivek Sarkar and Rui Zhang, Rice University, USA
5:30 Closing Discussion and Meeting Adjournment

Author information

Author information can be found at the HIPS 2008 and POHLL 2008 web pages. The HIPS-POHLL workshop proceedings will be published along with the IPDPS conference proceedings.

Workshop Co-Chairs

This page is maintained by Sam Midkiff, smidkiff@purdue.ede
last change: January 30, 2008.