Accelerating Matlab with GPU
A Primer with ExamplesBy
- Jung Suh, Jung W. Suh is a senior scientist at HeartFlow, Inc. Dr. Suh received his Ph.D. from Virginia Tech in 2007 for his 3D medical image processing work. He was involved in the development of MPEG-4 and Digital Mobile Broadcasting (DMB) systems in Samsung Electronics. His research interests are in the fields of biomedical image processing, pattern recognition and image compression.
- Youngmin Kim, Youngmin Kim is a staff software engineer at Life Technologies where he has been programming in the area that requires real-time image acquisition and high-throughput image analysis. His previous works involved designing and developing software for automated microscopy and integrating imaging algorithms for real time analysis. He received his BS and MS from the University of Illinois at Urbana-Champaign in electrical engineering. Since then he developed 3D medical software at Samsung and led a software team at the startup company, prior to joining Life Technologies.
Matlab is a widely used simulation tools for rapid prototyping and algorithm development. In many laboratories and research institutions, there is growing interest in running Matlab codes faster for computationally heavy projects, and leveraging the distributed parallelism of Graphics Processing Units (GPUs). However, Matlab users come from various backgrounds and do not necessarily have strong programming experience. Without guidance, those users may find their work delayed due to the learning curve of GPUs and the CUDA library. This book will target readers who have experience with Matlab coding but dont have enough depth in either C coding or computer architecture. As a primer, the book starts with basics, setting up Matlab for CUDA (in Windows and Mac OSX), profiling, and then guides the users through advanced topics such as OpenACC, third-party CUDA libraries and debugging. It will also provide many practical ways to modify Matlab codes to better utilize the computational power of GPUs. The authors have extensive experience developing algorithms using Matlab, C++ and GPUs for huge datasets in both industrial and research fields, and integrating them into commercial software products. They have published more than a dozen papers on these subjects.
Paperback, 150 Pages
Published: October 2013
Imprint: Morgan Kaufmann