Understanding and Improving the Performance of Scientific Software and its Humans

Event Sponsor: 
Mathmatics and Computer Science Division Seminar - LANS
Start Date: 
Apr 24 2019 - 10:30am
Building/Room: 
Building 240/Room 1404-1405
Location: 
Argonne National Laboratory
Speaker(s): 
Boyana Norris
Speaker(s) Title: 
University of Oregon

Understanding the performance of scientific applications can be a challenging endeavor given the constant evolution of architectures, programming models, compilers, numerical methods and the applications themselves. Performance integration testing is still not a reality for the majority of high-performance applications because of the complexity, computational cost, and lack of reliable automation. Hence, as part of the DOE SciDAC program, we are working on creating robust performance analysis workflows that capture application-specific performance issues and can be maintained extended by the application scientists without requiring an external performance “expert”. The consumers of performance data include application developers, performance models, and autotuners. Once appropriate and sufficient performance data is available, our approach to using it to guide optimization is three-fold: (i) we investigate the most effective way to present performance results to the code deve lopers (ii) we automate the selection of numerical methods based on generic performance models (as part of the NSF-funded Lighthouse project) and (iii) we explore the use of different types of performance models in low-level autotuning systems to reduce the size of the parameter search space. While code generation and autotuning are important for achieving performance portability, the majority of code development (including optimization) is still performed by humans. As part of the DOE IDEAS project, we are developing data-based methodologies to try to understand better how human teams work most effectively in developing high-quality, high-performance, enduring scientific software.

Miscellaneous Information: 

This seminar will be streamed. See details at https://anlpress.cels.anl.gov/cels-seminars/

Please click here [schedule.ics] to add this event to your calendar.

Google Calendar: https://goo.gl/L7uhjK

Upcoming Seminars

================

March 27, 2019, "Solving distillation column equilibrium using interval methods" Charlie Vanaret, Researcher, Fraunhofer ITWM
April 3, 2019, "The mathematical dawn of fluid dynamics" Oana Marin, Assistant Applied Mathematics Specialist, MCS, ANL
April 10, 2019, "Cascading failures and energy landscapes for power systems" Jake Roth, Predoctoral Appointee, MCS/ANL
April 16, 2019, "AMR for Multiphysics Applications" Ann Almgren, Group Lead, Center for Computational Sciences and Engineering, LBNL
April 24, 2019, "Understanding and Improving the Performance of Scientific Software and its Humans" Boyana Norris, Associate Professor, Department of Computer and Information Science, University of Oregon
May 1, 2019, "TBA" Johann Rudi, Wilkinson Fellow, MCS/ANL
May 8, 2019, "TBA" Brian Dandurand, Postdoctoral Appointee, MCS/ANL
May 15, 2019, "TBA" Saurabh Chawdhary, Postdoctoral Appointee, MCS/ANL
May 29, 2019, "TBA" Mohammad Motamed, Associate Professor of Applied Mathematics, University of New Mexico
June 5, 2019, "TBA" Carlo Graziani, Computational Scientist, MCS/ANL
June 12, 2019, "Machine Learning for Efficient and Accurate Multiscale Modeling of Platelets" Yuefan Deng, Professor, Applied Mathematics & Statistics, Stony Brook University
June 19, 2019, "TBA" Hong Zhang, Assistant Computational Mathematician, MCS/ANL
June 26, 2019, "TBA" Valeria Barra, Postdoctoral Research Associate, Department of Computer Science, University of Colorado at Boulder
July 10, 2019, "TBA" Alp Dener, Postdoctoral Researcher, MCS/ANL
July 17, 2019, "TBA" Jed Brown, Assistant Professor, Computer Science, University of Colorado Boulder
July 24, 2019, "TBA" Mi Sun Min, Computational Scientist (MCS/ANL)
September 4, 2019, "TBA" Charlotte Haley, Assistant Computational Statistician, MCS/ANL