Parallel Programming for Many-Core GPUs

Catalog description

This course will introduce an important trend in high-performance computing, the use of many-core graphics processing units (GPUs) to solve computation-intensive problems. Students will learn about new many-core GPU architecture, CUDA programming model, memory hierarchy design, parallel programming concepts, fundamental parallel algorithms, and compiling techniques to improve parallelism. Students in the course will also learn how to develop scalable parallel programs to achieve high performance on GPUs. The course will give students hands on experience in parallel programming on many-core GPUs.