Visualizing Parallel Dynamic Programming using the Thread Safe Graphics Library

Abstract

The design and analysis of parallel algorithms are both fundamental to the set of high-performance, parallel, and distributed computing skills required to use modern computing resources efficiently. In this work, we present an approach of teaching parallel computing within an undergraduate algorithms course that combines the paradigms of dynamic programming and multithreaded parallelization. We have developed a visualization tool built with the Thread Safe Graphics Library that enables interactive demonstration of parallelization techniques for two fundamental dynamic programming problems, 0/1 Knapsack and Longest Common Subsequence. We describe the implementation of the tool, the real-time animation it produces, and the results of using it in class. The tool is publicly available to be used directly or as a basis on which to build visualizations of other parallel dynamic programming algorithms.