June 22–26, 2014
Leipzig, Germany

Session Details

Name: Tutorial 05: Dense Linear Algebra Libraries for High Performance Computing
Time: Sunday, June 22, 2014
09:00 am - 01:00 pm
Room:   Lecture Room 12
CCL - Congress Center Leipzig
Breaks:08:00 am - 10:30 am Welcome Coffee
Presenter:   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 presents recent developments in dense linear algebra software for multicore
systems (PLASMA package/QUARK runtime), multicore processors with GPU accelerators or Xeon Phi co-processors (MAGMA package), and large, distributed memory systems, with GPU accelerators or co-processors (DPLASMA package/PaRSEC runtime).

Content Level
Beginner: 50%, Intermediate: 35%, Advanced: 15%

Target Audience
Academia, research, industry, government.

Audience Prerequisites
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. The tutorial will be of highest value to people with interest in linear algebra and some experience with packages like BLAS, LAPACK, and ScaLAPACK.