Products + All Products + Software Integrity + Semiconductor IP + Verification + Design + Silicon Engineering
May 1- 3, 2017
Use code Synopsys17 for a 10% discount
Wednesday, May 3, 2017
9:00 am – 4:00 pm
Learn how to use the latest embedded vision processors and CNNs to design low-power, low-cost vision solutions for surveillance, augmented reality and automotive/ADAS applications. This workshop provides a deep-dive into new technologies for deep learning, embedded vision capabilities, and standards-based programming tools. In addition, it will describe case studies on the implementation of computer vision in an embedded environment. You do not need to be registered for the conference to attend the workshop.
Topics covered will include:
Practical application reference examples, including OpenVX standard kernels, face tracking, and Deep Learning/CNN demonstrations
Brief overview of Synopsys’ latest Embedded Vision offerings
Use of standards-based programming tools such as OpenCV, OpenVX, C/C++, OpenCL C
Case studies of video surveillance and ADAS-based applications
Moving CNNs from Academic Theory to Embedded Reality
Tom Michiels, Synopsys System Architect
Tuesday, May 2, 12:00 PM - 12:30 PM
Abstract: Learn to recognize and avoid the pitfalls of moving from an academic CNN/deep learning graph to a commercial embedded vision design. Designers will learn about the cost vs. accuracy trade-offs of CNN bit-width, balancing internal memory size with external memory bandwidth, and the importance of keeping data local to the CNN processor to improve bandwidth. We will walk through an example customer design for a power- and cost-sensitive automotive scene segmentation application that requires high flexibility to adapt to future CNN graph evolutions.
Designing Scalable Embedded Vision SoCs from Day 1
Pierre Paulin, Director of R&D
Tuesday, May 2, 11:15 AM - 11:45 AM
Abstract: Some of the most critical EV design decisions are made early on and affect the design’s ultimate scalability. Will the processor architecture support the needed vision algorithms? Is the CNN flexible enough? Are the tools capable of supporting HW/SW trade-offs and architecture scalability? This presentation will discuss Synopsys’ DesignWare EV6x Embedded Vision Processors, which offer a combination of high-performance vision CPU cores and a CNN engine with high-productivity programming tools based on OpenCL C and OpenVX. The programmable and configurable EV6x processors support a broad range of embedded vision applications including ADAS, video surveillance, augmented reality, and SLAM. Using representative EV applications, this presentation will illustrate the flexibility, efficiency, and PPA benefits of the EV6x processors. These applications will also show the flexibility and high performance of the integrated CNN engine for low-power embedded systems.
Monday, May 1 - 2:00 – 8:00 pm
Tuesday, May 2 - 10:30 am – 7:30 pm
Be sure to visit us in the Technology Showcase for demos of our latest vision solutions, including deep learning and real-time object detection.