Yankin Tanurhan
Synopsys, USA
Evolving Vision and Deep Neural Network Processors for Emerging Applications in the Edge
Abstract
Embedded applications in mobile, AR/VR, video-surveillance and autonomous driving require increasing intelligence and compute power to interpret data from multiple sensors, including video, audio, radar/lidar. This talk introduces trends in embedded multi-sensor processing and the associated processing, on-chip communication and memory architecture requirements. We also introduce some of the recent trends in the most commonly used machine-learning based approaches: CNN (convolution neural networks), RNN (recurrent neural networks) and SNN (spiking neural networks). We present the latest updates on the EV6 processor which combines a powerful scalable Vision CPU and a domain-specific, programmable neural network accelerator engine. We present the standards-based programming environment which supports well-known OpenCV, OpenVX and OpenCL C standards for classical vision and DSP processing, along with the latest Tensorflow, Caffe and many others via the recent ONNX (Open Neural Network eXchange) format for CNN and RNN processing. Experimental results for recent neural-network based graphs are provided to illustrate power, performance, area and accuracy trade-offs.
Biography
Dr. Yankin Tanurhan, Vice President Engineering, DesignWare Processor Cores, IP Subsystems, Non-Volatile Memory at Synopsys leading low power and high performance ARC and EV embedded Processor developments targeted from Mobile, IoT, Embedded Vision, Digital Home, Automotive/Industrial, Security to Storage markets, ASIP tool development with products like ASIP Designer and Programmer, IP Subsystems products like Sensor Fusion, Audio, Vision and Security Subsystems and CMOS based Non Volatile IP development. Dr Tanurhan has authored 100+ papers in refereed publications. He holds a B.S. and M.S. in Electrical and Computer Engineering from Rheinisch Westfaellische Technische Hochschule (RWTH) in Aachen, Germany and a Dr. Ing. degree summa cum laude in Electrical Engineering from the University of Karlsruhe (TH) in Karlsruhe, Germany.