GPU Programming and Architecture

Catalog description

This course examines the architecture and capabilities of modern GPUs. The graphics processing unit (GPU) is orders of magnitude faster for computation than traditional CPU, and with the power of general purpose programming, GPUs can be used for a diverse set of applications far removed from their traditional graphics usage. In this course, students will learn to program and optimize GPUs for computationally intensive algorithms. Topics covered include architectural aspects of modern GPUs, with a special focus on massively parallel programming, writing programs using CUDA, and using the GPU for graphics and general purpose applications in the area of geometry modeling, physical simulation, scientific computing and games. Students are expected to have a basic understanding of computer architecture and graphics, and should be proficient in C/C++. This course is appropriate as an upper-level undergraduate CIS elective. Computer Graphics background is strongly recommended, which can be met with CIS 4600 , CIS 5600 , or an equivalent Computer Graphics course.