CoT named CUDA Teaching Center by NVIDIA
The College of Technology at Purdue University has been named a CUDA Teaching Center by NVIDIA Corporation. Bedrich Benes, associate professor of computer graphics technology, will coordinate the Teaching Center activities, which will include courses, training and outreach to industry and academia.
CUDA is NVIDIA’s parallel computing architecture that enables dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU). CUDA Teaching Centers have integrated GPU computing techniques into their mainstream computer programming curriculum, and are dedicated to training the next wave of parallel programmers to address today’s most challenging computing issues and drive the next wave of scientific discovery.
“We’re excited by NVIDIA’s recognition of our program and our ability to provide top-notch instruction about the CUDA architecture. As a Teaching Center, we will be able to provide our students even greater access to their courses, software and developers,” Benes said.
As part of the Teaching Center program, Benes will continue teaching a graduate course on the CUDA architecture in Fall 2011. The college will receive a CUDA teaching kit, which includes five CUDA-capable graphics processing units (GPU) for teaching and research purposes and one high-end GPU for timing and benchmarking. In addition, Benes said, students will have direct access to NVIDIA, beta versions of their software, toolkits, forums and more.
The CUDA architecture is increasingly being used in a wide range of non-visual contexts, from life sciences and medicine to energy discovery and quantum chemistry. There are more than 60,000 active CUDA developers around the world, and CUDA programming is taught at more than 400 universities in 49 countries.
The model for GPU computing is to use a traditional central processing unit (CPU) and GPU together in a co-processing computing model. The sequential part of the application runs on the CPU and the computationally intensive part is accelerated by the GPU. From the user’s perspective, the application just runs considerably faster because it is using the parallel processing capabilities of the GPU to boost performance.
The CUDA Teaching Center program was launched by NVIDIA in June 2010. Purdue’s College of Technology joins more than 40 other universities enrolled in the program worldwide.