Starting in the spring 2013, I videotaped the lectures for my MATH 676: Finite element methods in scientific computing course at the KAMU TV studio at Texas A&M. These are lectures on many aspects of scientific computing, software, and the practical aspects of the finite element method, as well as their implementation in the deal.II software library. Support for creating these videos was also provided by the National Science Foundation and the Computational Infrastructure in Geodynamics.
Note: In some of the videos, I demonstrate code or user interfaces. If you can't read the text, change the video quality by clicking on the "gear" symbol at the bottom right of the YouTube player.
Lecture 39: Parallelization: Introduction
All computers today — even cell phones — have multiple processor cores that allow multiple computations to happen in parallel. If you have a problem that takes too long to solve on a single processor, then there is no other way than writing software that exploits the different levels of parallelism available on today's computers.
This lecture gives an introduction to the problem and, in particular, introduces the nomenclature describing both the hardware and software sides of parallelization and that is necessary for the next lectures. It also introduces Amdahl's Law defining how much faster a program can be when run in parallel.
Slides: click here