|Name:||Tutorial 07Dense Linear Algebra with MAGMA & PLASMA|
|Time:||Sunday, June 16, 2013
9:00 AM - 1:00 PM
|Room:||Seminar Room 13 (SR 13)
CCL - Congress Center Leipzig
|Breaks:||11:00 AM - 11:30 AM Coffee Break|
1:00 PM - 2:00 PM Lunch
|Presenter(s):||Jack Dongarra, University of Tennessee & ORNL|
|Jakub Kurzak, University of Tennessee|
|Hatem Ltaief, KAUST|
|Abstract:||Today, a desktop computer with a multicore processor and a GPU accelerator can already provide a TeraFlop/s of performance. This tremendous computational power can only be fully utilized with the appropriate software infrastructure. Most often a major part of the computational effort in scientific and engineering computing goes towards solving linear algebra sub-problems. This tutorial surveys the state-of-the-art numerical libraries for solving problems in dense linear algebra.
The tutorial consists of three parts. The first part provides a brief historical look at the development of dense linear algebra libraries, from LINPACK, to LAPACK, to ScaLAPACK. The second part focuses on the PLASMA project (Parallel Linear Algebra Software for Multicore Architectures). Finally, the third part discusses GPU acceleration issues and the MAGMA project, and also ongoing efforts in linear algebra software for distributed memory machines (the DPLASMA/PaRSEC projects).
One of the main objectives of the tutorial is to reveal the underlaying technology of developing high quality numerical software for modern architectures, such as: the use of performance-oriented data layout geared towards cache-based multicore processors and accelerators, the use of a runtime system for dynamic dataflow scheduling, etc.
50% Beginner, 35% Intermediate, 15% Advanced
Academia, research, industry, government
The tutorial is suitable for a broad range of attendees, but it will be most beneficial for attendees with certain prerequisites. Specifically, attendees should have a good understanding of fundamental concepts in parallel programming (with emphasis on multithreading). The tutorial will be of highest value to people with interest in linear algebra and some experience with packages like BLAS, LAPACK, and ScaLAPACK.