||Ricardo J. Barrientos. LITRP Laboratory, Catholic University of Maule, Chile
Currently, there is an alternative (which is efficient in computing and energy consumption), in the area of Parallel Computing for the acceleration of algorithms, which is the use of GPUs (Graphics Processing Units). A GPU is a device that is used as a high performance co-processor, specialized in maximizing the processing of floating point operations per second.
In this tutorial, the different components of a NVIDIA GPU architecture will be shown, and we will study the programming model offered by CUDA through several examples. These exercises will cover different points of view, giving to the student a vision and introductory training in GPU programming. It is recommended that the student has knowledge of the C language.
Ricardo Barrientos received the PhD in Computer Science from the Complutense University of Madrid (Spain). He received two MScs in Computer Sciences, the first from the University of Chile (Chile) and the second from the Complutense University of Madrid (Spain), and the Computer Engineering from the University of Magallanes (Chile). Areas of interest: Parallel Computing Information Retrieval and Biometrics. Currently, he is an academic in the Catholic University of Maule, and a researcher in the LITRP Laboratory where is the Director of a Fondef Project developing a massive identification system for the Chilean population using fingerprints.