High-Performance Computing for Medical Imaging on Graphics Processing Units (GPU) with CUDA

Level: Introductory Length: 4 hours Format: In-Person Lecture Intended Audience: Scientists, engineers, or technicians who wish to learn CUDA and GPU programming. Knowledge of the C programming language is assumed. Description: This course covers the basic principles of graphics processing unit (GPU) programming with CUDA. To become familiar with the programming model, we will start with a simple example, to be followed by more in-depth topics related to GPU programming. Some applications to medical imaging will be presented. Anyone who wants to know how to parallelize their code and make it run 10 times faster by harnessing the massively parallel capabilities of modern GPUs, will benefit from taking this course. Learning Outcomes: This course will enable you to: - design efficient general-purpose CUDA code tailored to the parallel capabilities of modern GPUs - be able to learn on your own, understand, and use advanced material on CUDA programming - analyze and debug existing CUDA code - modify code samples and use them as building blocks for more complex applications Instructor(s): Luca Caucci is an assistant professor in the Department of Medical Imaging at the University of Arizona. He earned his PhD in Optical Sciences from the University of Arizona. Dr. Caucci's research interests include emission computed tomography, list-mode data processing, photon-processing detectors, signal detection, parameter estimation, adaptive imaging, parallel computing, and digital radiology. Event: SPIE Medical Imaging 2020 Course Held: 16 February 2020