Seminars & Events

Mathematics and Computer Science Division
"Model-Based Automatic Performance Diagnosis of Parallel Computations"

DATE: April 12, 2007
TIME: 10:30am
SPEAKER: Li Li, Dept of Computer and Information Science, University of Oregon
LOCATION: Bldg: 221, Conference Room A216, Argonne National Laboratory
HOST: Boyana Norris and Lois Curfman McInnes

Description:
Scientific parallel programs often undergo significant performance tuning before meeting their performance expectations. Performance tuning naturally involves a diagnosis process -- locating performance bugs that make a program inefficient and explaining them in terms of high-level program design. Important performance measurement and analysis tools have been developed to support the performance analysis with the facilities of running experiments on parallel computers and generating measurement data to evaluate performance. However, current performance analysis technology does not yet allow for associating found performance problems with causes at a high-level program abstraction. Nor does it support the performance diagnosis process in a well automated manner.

We present a systematic method to guide the performance diagnosis process and support the process with minimum user intervention. Our approach exploits program execution abstraction and parallelism found in computational models to search and explain performance bugs. We have developed the Hercule automatic performance diagnosis system that implements the model-based diagnosis strategy. We used Hercule to analyze a variety of parallel applications. The experiment results show that, requiring minimum user intervention, model-based performance analysis is vital and effective in discovering and interpreting performance bugs at a high level of program abstraction.

Save the event to your calendar [schedule.ics]