Dynamic Neural Accelerator
Overview
EdgeCortix Dynamic Neural Accelerator (DNA) is a flexible neural accelerator IP core with run-time reconfigurable interconnects between compute units, achieving exceptional parallelism and efficiency through dynamic grouping. A single core can scale from 1024 MACs to 32768 MACs, running at clock speeds up to 1 GHz. Configuration is done with the EdgeCortix MERA compiler and software framework.
Key Features
- Proprietary reconfigurable Data Flow architecture
- Ground breaking efficiency for deep neural network deployment
- Seamless integration with standard deep
- Proprietary, automatic, neural network model and hardware accelerator IP co-design
- Hyper scalable design with custom interconnect
- Integer 8bit precision optimized
- DNA-IP available for custom SoC, PCI-E processor
- learning SW frameworks - Pytorch, Tensorflow or on edge-server deployment with Xilinx ALVEO and Zynq Ultrascale+ FPGAs
Benefits
- Run-time reconfigurable
- Efficient AI inference core in FPGAs or SoCs
- Low latency
- < 4 msec when under demanding workloads
- High utilization
- +80% for concurrent neural network models
Applications
- Automotive
- Robotics
- Smart City
- Drones
- Industry 4.0
Technical Specifications
Related IPs
- Convolutional Neural Network (CNN) Compact Accelerator
- PowerVR Neural Network Accelerator
- PowerVR Neural Network Accelerator - cost-sensitive solution for low power and smallest area
- PowerVR Neural Network Accelerator - perfect choice for cost-sensitive devices
- PowerVR Neural Network Accelerator - The ideal choice for mid-range requirements
- PowerVR Neural Network Accelerator - The perfect choice for cost-sensitive devices