Regi 25
Introduction to Parallel Programming with pMatlab
Introduction to Parallel Programming with pMatlab; Julia S. Mullen, Ph.D; MIT Lincoln Laboratory. Parallel computing has been around for decades, yet the active practitioners are a small subset of the science and engineering community because of the hurdles associated with developing parallel and distributed application codes. MATLAB®, a widely used programming tool for scientists and engineers has the characteristics that appeal to the scientific community – namely, ease of use, rapid prototyping capability and an interactive development environment. pMatlab, the open source parallel MATLAB® library created by MIT Lincoln Laboratory extends these characteristics to parallel processing. During this seminar we will demonstrate the use of the pMatlab library for applications ranging from signal and image processing to the numerical solution of partial differential equations. Following an introduction to pMatlab, we present case studies of the parallelization process for both coarse and fine grained applications with pMatlab. We close with brief overview of a software development process to convert serial MATLAB®/Octave code to real-time C/C++ code to be run on a desktop, cluster, or multicore embedded platform. The pMatlab v2.0 software and documentation is available for download at: http://www.ll.mit.edu/mission/isr/pmatlab/pmatlab.html
This course is intended for: Administrators, Alumni, Faculty, Graduate Students, Staff, Undergraduate Students
Back
