DesignWare ARC EV Processors for Embedded Vision

DesignWare EV Processors for Embedded Vision

Machine Vision and Deep Learning for AI SoCs

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.

Programmable Processor IP for Real-time Vision Processing

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 execution of convolutional neural networks (CNNs) or recurrent neural networks (RNNs), the EV Processors integrate an optional high-performance deep neural network (DNN) accelerator.

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.

Kyocera Super Resolution Printer with ARC EV Vision IP

Watch Now

Products and Licensable Options

Synopsys offers multiple options to enhance the functionality of the DesignWare EV7x prcoessors:

 

EV7x

EV7xFS

# Vision Processing Cores

1, 2, or 4

1, 2, or 4

DNN Accelerator option

(880, 1760, 3520 MACs)

Floating Point Unit (FPU) option

Real-Time Trace (RTT) option

Functional Safety

 

Integrated
(ASIL B, C, or D)

Fast & Accurate 3D Object Detection for LiDAR with DesignWare ARC EV Processor IP

This demo, developed in partnership with Sensor Cortek, executes the FA3D algorithm on ARC EV7x processor with DNN engine. It shows 3D boxes rendered onto objects detected in the video frames, enabling the development of driver assistance systems.