Applied Parallel Programming: Gpus for High-Performance Computing On Manycore Architectures

3 units

This course teaches parallel programming for manycore processor architectures, with an emphasis on Graphics Processing Units(GPUs) as the target architecture. Students learn fundamentals of a GPU architecture and its development platform, practice techniques for efficiently mapping parallel computation onto a GPU, study common parallel computation patterns and their application to real-world data processing tasks, and explore performance measurement and optimization. Hands-on studios and programming assignments are an integral part of the course.