GPU Computing 101: Why University Educators Are Pulling NVIDIA Teaching Kits into Their Classrooms

by Ahana Dave

Along with the usual elements of university curriculums — lectures, assignments, lab exercises — there’s a new tool that educators are increasingly leaning into: NVIDIA Teaching Kits.

University educators around the world are tapping into these kits, which include downloadable teaching materials and online courses that provide the foundation to understand and build hands-on expertise in areas like deep learning, accelerated computing and robotics.

The kits are offered by the NVIDIA Deep Learning Institute, a hands-on training program in AI, accelerated computing, and data science to help technologists solve challenging problems.

Co-developed with university faculty, NVIDIA Teaching Kits provide content to enhance a university curriculum, including lecture slides, videos, hands-on labs, online DLI certificate courses, e-books and GPU cloud resources.

Accelerated Computing at University of California, Riverside

Daniel Wong, an assistant professor of electrical and computer engineering at the University of California, Riverside, used the Accelerated Computing Teaching Kit for two GPU-centric computer science courses — a graduate course and an undergrad course on “GPU Computing and Programming.”

“The teaching kit presented a very well structured way to teach GPU programming, especially given the way many of our students come from very diverse backgrounds,” Wong said.

Wong’s undergrad course took place over 10 weeks with an enrollment of about three dozen students and is currently in its second offering. The kit was central in teaching the basics of CUDA, such as CUDA threading models, parallel patterns, common optimizations and other important parallel programming primitives, Wong said.

“Students know that the material we present is state of the art and up to date so it gives them confidence in the material and drew a lot of excitement,” he said.

The course built up to a final project with students accelerating an application of their choice, such as implementations and performance comparison of CNNs in cuDNN, TensorFlow, Keras, facial recognition on NVIDIA Jetson boards, and fluid dynamics and visualization. In addition, several of Wong’s undergraduate students have gone on to pursue GPU-related undergraduate research.

Deep Learning at University Hospital Erlangen

At the Institute of Neuropathology of the University Hospital Erlangen in Germany, a deep learning morphology research group applies deep learning algorithms to various problems around histopathologic brain tumors.

The university’s medical students have little background in computer science, so principal investigator Samir Jabari uses the NVIDIA Teaching Kit as part of sessions he conducts every few weeks on the field of computer vision.

Through lecture slides on convolutional neural networks and lab assignments, the teaching kit helps provide insights into the field of computer vision and its specific challenges toward histopathology.

Robotics at Georgia State University

Georgia State University’s Computer Science department used the Robotics Teaching Kit in its “Introduction to Robotics” course, first introduced in spring 2018.

The course grouped two to three students per kit to engage them in learning basic sensor interaction and path-planning experiments. At the end of the class, students presented projects during the department’s biannual poster and demonstration day.

The course was a hit. When first taught, it registered 32 students. The upcoming fall course has already received 60 registration requests — nearly double the registration capacity.

Beyond the classroom, Georgia State faculty and students are using NVIDIA Teaching Kits to facilitate projects in the greater community in interdisciplinary areas such as environmental sensing and cybersecurity.

“This kind of in-class hardware kit-based teaching is new to the department,” said Ashwin Ashok, assistant professor of computer science at Georgia State. “These kits have really gained a lot of traction for potential uses in courses as well as research at Georgia State.”

Watch Teaching Kits in Action

At the University of Delaware, undergraduate students trained with NVIDIA Teaching Kits, assistant professor Sunita Chandrasekaran said. At the end of their training, the students took a serial code, which ran for 14 hours, and optimized its performance to run in two minutes using OpenACC on NVIDIA Volta GPU accelerators.

Cristina Nader Vasconcelos, assistant professor at Universidad Federal Fluminense in Rio de Janeiro, Brazil, said NVIDIA Teaching Kits help make sure her course aligns with the state of the art in industry research.

Watch their stories in the video below.