- Silicon Design & Verification
- Silicon IP
- Software Integrity
- About Us
- Silicon Design & Verification Products
- Solutions
- Resources
- Services
- Community
- Training
- Silicon IP Products
- Solutions
- Resources
- Services
- Community
- Software Integrity
- Tools & Services
- Training & Education
- Solutions
- Resources
- Support
- Partners
- About Us
< Silicon Design & Verification Products
< Silicon Design & Verification Products
< Silicon Design & Verification Products
< Silicon Design & Verification Products
3D Image Processing
Simpleware Products
Simpleware for Life Sciences
Simpleware for Materials & Manufacturing
< Silicon Design & Verification Products
< Silicon Design & Verification Products
< Silicon Design & Verification Products
Photonic Solutions
PIC Design Suite
< overview
Silicon Design & Verification Products
+
Design
+
System Simulation & Modeling
+
Verification Continuum
+
3D Image Processing
+
Silicon Engineering
+
Optical Solutions
+
Photonic Solutions
< Solutions
< Solutions
< Solutions
< Solutions
< overview
< Resources
< Resources
< Resources
< overview
< Services
< Services
< Services
< Community
Community
Community Overview
< Community
< Community
< Community
< Community
< Community
< Community
< Community
< overview
Community
+
Community
+
SNUG
+
Partners
+
EmbARC.org
+
Interoperability
+
Academic Programs
+
Company Blogs
+
BSIMM
< Training
< overview
< main menu
< Silicon IP Products
< Silicon IP Products
Memories & Libraries
Logic Libraries
Memory Compliers
Duet Packages
HPC Design Kit
Embedded Test & Repair
Non-Volatile Memory
< Silicon IP Products
< Silicon IP Products
Processor Solutions
ARC Processor IP
Embedded Vision Processor IP
Development Tools
Operating Systems
Ecosystem
ASIP Tools
< Silicon IP Products
< Silicon IP Products
< Silicon IP Products
< Silicon IP Products
< Silicon IP Products
< overview
Silicon IP Products
+
Interface IP
+
Memories & Libraries
+
Analog IP
+
Processor Solutions
+
IP Subsystems
+
Security IP
+
Market Segments
+
IP Accelerated
+
SoC Infrastructure IP
< Solutions
< Resources
< Services
< Services
< Services
< Community
Community
Community Overview
< Community
< Community
< Community
< Community
< Community
< Community
< Community
< overview
Community
+
Community
+
SNUG
+
Partners
+
EmbARC.org
+
Interoperability
+
Academic Programs
+
Company Blogs
+
BSIMM
< overview
Software Integrity
< Tools & Services
< Tools & Services
Professional Services
Strategy and Planning (BSIMM)
Architecture & Design
DevSecOps Integration
Cloud Security
Industry Solutions
< Tools & Services
Open Source Audits
< overview
< Training & Education
< Training & Education
Product Education
< overview
< Solutions
< Solutions
< Resources
< Resources
< Support
< Support
Contact Support
< Partners
< main menu
Software Integrity
+
Software Integrity
+
Tools & Services
+
Training & Education
+
Solutions
+
Resources
+
Support
+
Partners
< About Us
< About Us
< About Us
< About Us
< About Us
< About Us
DesignWare ARC EV CNN Engine Option
The DesignWare ARC EV6x Embedded Vision Processors offer an optional convolutional neural network (CNN) engine for fast and accurate object detection, classification and scene segmentation. The EV6x supports any CNN, including popular networks such as AlexNet, VGG16, GoogLeNet, Yolo, Faster R-CNN, SqueezeNet, and ResNet.
Designers can run CNN graphs originally trained for 32-bit floating point hardware on the EV6x’s 12-bit CNN engine, significantly reducing the power and area of their designs while maintaining the same levels of detection accuracy as a 16-bit engine. The EV6x’s CNN hardware also supports 8-bit precision for lower memory bandwidth and power use.
The EV6x’s CNN engine delivers power efficiency of up to 2,000 GMACs/sec/W when implemented in 16-nm FinFET process technologies (worst-case operating conditions).
The MetaWare EV Development Toolkit includes a CNN mapping tool that analyzes neural networks trained using popular frameworks like Caffe and Tensorflow, and automatically generates the executable for the programmable CNN engine. For maximum flexibility and future-proofing, the tool can also distribute computations between the vision CPU and CNN resources to support new and emerging neural network algorithms as well as customer-specific CNN layers.
Inuitive Demonstrates NU4000 Artificial Intelligence SoC with DesignWare EV6x at CES 2019
Highlights
Products
Downloads and Documentation
- Fast, accurate object detection with a programmable CNN engine
- Offers power efficiency of up to 2000 GMACs/sec/W in worst-case operating conditions when implemented in 16-nm FinFET processes
- Supports both coefficient and feature map compression/decompression to reduce data bandwidth requirements and decrease power consumption
- High productivity MetaWare EV Development Toolkit’s CNN mapping tool automatically dispatches processing tasks to available hardware resources for faster execution
| Description: | CNN 1760 MAC Option |
| Name: | dwc_ev_cnn_1760_mac_option |
| Version: | 2.1b |
| STARs: | Open and/or Closed STARs |
| myDesignWare: | Subscribe for Notifications |
| Product Type: | DesignWare Cores |
| Documentation: | Contact Us for More Information |
| Download: | ev-vision_processor |
| Product Code: | C623-0 |
| Description: | CNN 3520 MAC Option |
| Name: | dwc_ev_cnn_3520_mac_option |
| Version: | 2.1b |
| STARs: | Open and/or Closed STARs |
| myDesignWare: | Subscribe for Notifications |
| Product Type: | DesignWare Cores |
| Documentation: | Contact Us for More Information |
| Download: | ev-vision_processor |
| Product Code: | C624-0 |
| Description: | CNN 880 MAC Option |
| Name: | dwc_ev_cnn_880_mac_option |
| STARs: | Open and/or Closed STARs |
| myDesignWare: | Subscribe for Notifications |
| Product Type: | DesignWare Cores |
| Documentation: | Contact Us for More Information |
| Product Code: | C173-0 |