SCHEDULE: NOV 16-22, 2013

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.

An Improved Parallel Singular Value Algorithm and Its Implementation for Multicore Hardware

SESSION: Matrix Computations

EVENT TYPE: Papers

TIME: 11:30AM - 12:00PM

SESSION CHAIR: Laura Grigori

AUTHOR(S):Azzam Haidar, Jakub Kurzak, Piotr Luszczek

ROOM:401/402/403

ABSTRACT:
The enormous gap between the high-performance capabilities of today's CPUs and off-chip communication has made the development of numerical software that is scalable and performant extremely challenging. In this paper, we describe a successful methodology to address these challenges, starting from our algorithm design, kernel optimization and tuning, to our programming model in the development of a scalable high-performance singular-value-decomposition (SVD) solver. We developed a set of leading edge kernels combined with advanced optimization techniques featuring fine-grained, memory-aware kernels, a task-based approach and hybrid execution and scheduling that significantly increase the performance of the SVD solver. Our results demonstrate an enormous performance boost compared to current available software. In particular, our software is two-fold faster than the optimized Intel Math Kernel Library when all the singular vectors are required, achieves 4-times speedup when 20% of the vectors are computed and is significantly superior (12X) if only the singular-value is required.

Chair/Author Details:

Laura Grigori (Chair) - INRIA

Azzam Haidar - University of Tennessee, Knoxville

Jakub Kurzak - University of Tennessee, Knoxville

Piotr Luszczek - University of Tennessee, Knoxville

  Click here to download .ics calendar file

  Click here to download .vcs calendar file

  Click here to add event to your Google Calendar

The full paper can be found in the ACM Digital Library