Parallel programming and computational thinking
Abstract
This chapter introduces the concept of computational thinking. It first reviews the main goals of parallel programming. It then discusses the thinking process of algorithm selection and problem decomposition. For a given problem the programmer will typically have to select from a variety of algorithms. Some of these algorithms achieve different tradeoffs while maintaining the same numerical accuracy. Others involve sacrificing some level of accuracy to achieve much more scalable running times. For the selected algorithm, different choices of problem decomposition can result in different levels of interference between threads, parallelism exposed, load imbalance, and other performance ...
Get Programming Massively Parallel Processors, 4th Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
