Pierre Paulin
Synopsys, Canada
Scaling Deep Neural Network Accelerator Performance
Abstract
Deep-learning based solutions for embedded vision have emerged as a key application of the growing class of artificial intelligence-based solutions. Specialized accelerators for deep neural networks (DNN) have emerged in order to achieve the highest performance at low-cost and low-power. Computational requirements for DNN accelerators continues to increase, driven in particular by autonomous driving applications. This presentation introduces some techniques for efficient scaling of DNN graph performance on multiple DNN accelerators, with a particular focus on bandwidth reduction technologies. This includes data compression, layer merging and efficient data sharing across multiple accelerators.
Biography
Dr. Pierre G. Paulin is Director of R&D for Embedded Vision at Synopsys. He is responsible for the application development, architecture design and S/W programming tools for embedded vision processors supporting classical computer vision and neural-network based solutions. Prior to this, he was director of System-on-Chip Platform Automation at STMicroelectronics in Canada, working on platform programming tools for multi-processor systems-on-a-chip, targeting computer vision, video codecs and network processors. This followed his previous positions as director of Embedded Systems Technologies for STMicroelectronics in Grenoble, France, and manager of Embedded Software and High-level synthesis tools with Nortel Networks in Canada. His interests include embedded vision, video processing, multi-processor systems, and system-level design. He obtained a Ph.D. from Carleton University, Ottawa, and B.Sc. and M.Sc. degrees from Laval University, Quebec.