- About ECE
- Faculty & Staff
ECE Professors Help OSU Garner CUDA Teaching Center Designation
Oklahoma State University has been recently named a CUDA® Teaching Center by NVIDIA, the world leader in visual computing. The designation was granted in response to a proposal submitted by Professors Damon M. Chandler and Keith A. Teague from the School of Electrical and Computer Engineering (ECE).
CUDA is a parallel computing platform and programming model that enables dramatic increases in computing performance by harnessing the power of NVIDIA® GPU accelerators. CUDA Teaching Centers are recognized institutions that have integrated GPU computing techniques into their mainstream computer programming curriculum, and OSU was recognized for its commitment to advancing the state of parallel education using CUDA C/C++.
Dr. Chandler's research and teaching expertise is on image and video processing. Dr. Teague's research and teaching expertise is on audio and speech processing. Both PIs are very active in instruction and best-practice pedagogy at OSU, with a particular emphasis on real-time multimedia signal processing, an area which is highly dependent on parallel programming and which has seen a recent shift toward GPU-accelerated computing.
Parallel programming using CUDA C++ will now become a part of the ECE signal-processing curriculum. The objective is to provide students with firsthand, structured exposure to parallel programming on GPUs, allowing them to experience the benefits and programming considerations of massively parallel implementations. This training represents a unique opportunity for students to learn signal processing while simultaneously learning how to program GPUs, a skill which is highly sought after by employers.
Beginning in the spring 2015 semester, parallel programming with CUDA C++ will be included in two courses: ECEN 4773: Real-Time Digital Signal Processing and ECEN 5793: Digital Image Processing. In addition, Chandler and Teague plan to hold workshops on using CUDA C++ for general data processing.
To support these teaching efforts, OSU will leverage new GPU accelerators provided by NVIDIA for timing and benchmarking, as well as for student training. The GPUs will be housed in the recently established ECE computing cluster, which is remotely accessible to all students. In addition, as a CUDA Teaching Center OSU will have access to NVIDIA parallel programming experts and resources, including educational webinars, teaching materials, and the NVIDIA CUDA Cloud Training Program.