GPU Architecture and Programming

Catalog description

This course introduces the students the concept of massively-parallel programming. It is divided into two parts: in the first part, the students are expected to develop multi-threaded programs in the C programming language using pthreads. In the second part, the concepts that are learned in the first part are extended to the GPU architecture. Nvidia CUDA programming language is used as the main tool to develop GPU programs. Prerequisite(s): I ECE 141 or I ECE/I CSI 201, and I ECE 233 or I ECE 332 or I CSI 333.