DesignWare EV Embedded Vision Processors provide high-performance processing capabilities at a power and cost point low enough for embedded applications, while maintaining flexibility to support any neural network graph and real-time performance requirements.
Machine vision and deep learning are being embedded in highly integrated SoCs and expanding into high-volume applications such as automotive ADAS, surveillance, and augmented reality. A major challenge in enabling mass adoption of embedded vision applications is in providing the processing capability at a power and cost point low enough for embedded applications, while maintaining sufficient flexibility to cater to rapidly evolving markets.
The DesignWare® ARC EV Processors are fully programmable and configurable IP cores that are optimized for embedded vision applications, combining the flexibility of software solutions with the low cost and low power consumption of hardware. For fast, accurate object detection and recognition, the EV Processors integrate an optional high-performance convolutional neural network (CNN) engine.
The EV Processors are designed to integrate seamlessly into an SoC and can be used with any host processors and operate in parallel with the host. To speed application software development, the EV processors are supported by a comprehensive software programming environment based on existing and emerging embedded vision and neural network standards including OpenCV, OpenVX™, OpenCL™ C, and Caffe with Synopsys' ARC MetaWare EV Development Toolkit.
- Optimized for high frame-rate and video resolution embedded vision applications
- Fast, accurate object detection with a programmable CNN engine
- CNN engine: Offers power efficiency of up to 2000 GMACs/sec/W in worst-case operating conditions when implemented in 16-nm FinFET processes
- CNN engine: Supports both coefficient and feature map compression/decompression to reduce data bandwidth requirements and decrease power consumption
- High-performance vision CPU with 512-bit wide SIMD vision DSP and 32-bit scalar CPU
- Vision CPU scales from 1 to 4 vector DSPs and operates in parallel to the CNN engine
- Supports data- and task-level parallelism
- Runs full range of vision algorithms for HD resolutions up to 4Kp
- Works with all host processors for vision offload
- High productivity MetaWare EV Development Toolkit supports C/C++, OpenCL C, OpenCV and OpenVX
- CNN mapping tool automatically dispatches processing tasks to available hardware resources for faster execution