作者: Erwan Fabiani
DOI: 10.1155/2009/923415
关键词:
摘要: This paper presents the "reconfigurable computing" teaching part of a computer science master course (first year) on parallel architectures. The practical work sessions this rely active pedagogy using problem-based learning, focused designing reconfigurable architecture for implementation an application class image processing algorithms. We show how successive steps project permit student to experiment with several fundamental concepts computing at different levels. Specific experiments include exploitation architectural parallelism, dataflow and communicating component-based design, configurability-specificity tradeoffs.