When viewing the Technical Program schedule, on the far righthand side
is a column labeled "PLANNER." Use this planner to build your own
schedule. Once you select an event and want to add it to your personal
schedule, just click on the calendar icon of your choice (outlook
calendar, ical calendar or google calendar) and that event will be
stored there. As you select events in this manner, you will have your
own schedule to guide you through the week.
You can also create your personal schedule on the SC11 app (Boopsie) on your smartphone. Simply select a session you want to attend and "add" it to your plan. Continue in this manner until you have created your own personal schedule. All your events will appear under "My Event Planner" on your smartphone.
Performance Tuning and Analysis of the Fast Multipole Method from Multicore to Exascale
SESSION: George Michael Fellowship Presentation
EVENT TYPE: George Michael HPC Fellow Presentation
TIME: 11:00AM - 11:30AM
SESSION CHAIR: Mark Hoemmen
ABSTRACT: N-body computations form an important class of problems and a deep understanding of the process to improve its scalability has wide-ranging implications in scientific computing. Towards this end, we present our process for improving the performance and scalability of a N-body method, the Fast Multipole Method (FMM). FMM has asymptotically linear time complexity with a guaranteed approximation accuracy making it an attractive candidate for future exascale systems.
This talk consists of three parts. First, we describe a process of transforming a naïve FMM into a highly tuned one, which includes cross-platform evaluations of performance and scalability. Second, we determine lower bounds on cache complexity for important phases of the FMM and use these bounds to derive analytical performance models. Finally, we use these performance models to make predictions on FMM at exascale based on current technology trends. Our FMM code represents the state-of-the art, and our study sheds light on a more general process of performance analysis and tuning along with insights for future system design.
Mark Hoemmen (Chair) - Sandia National Laboratories
Aparna Chandramowlishwaran - Georgia Institute of Technology