Neural Processing Unit (NPU) IP
ENLIGHT
TM
Discover a deep learning accelerator that accelerates inferencing computation with excellent efficiency and unmatched compute density.
Get to know the ORBIT Memory Subsystem IP that consists of an interconnect, memory controller, and PHY IPs that work in unison to create maximum system synergies.
ENLIGHT
TM
Features a highly optimized network model compiler that reduces DRAM traffic from intermediate activation data by grouped layer partitioning and scheduling. ENLIGHT is easy to customize to different core sizes and performance for customers' targeted market applications and achieves significant efficiencies in size, power, performance, and DRAM bandwidth, based on the industry's first adoption of 4-/8-bit mixed-quantization.
Performs various operations of deep neural networks such as convolution, pooling, and non-linear activation functions for edge computing environments. This NPU IP far surpasses alternative solutions, delivering unparalleled compute density with energy efficiency (power, performance, and area).
Hardware Key Advantages
Mixed Precision (4-/8-bit) Computation
-
Higher efficiency in PPAs (power, performance, and area), DRAM bandwidth
Deep Neural Networks (DNN)-optimized Vector Engine
-
Better adaptation to future DNN changes
Scale-out with Multi-core
-
Even higher performance by parallel processing of DNN layers
Modern DNN Algorithm Support
-
Depth-wise convolution, feature pyramid network (FPN), swish/mish activation, etc.
Software Key Advantages
High-level Inter-layer Optimization
-
Grouped layer partitioning and scheduling for reducing DRAM traffic from intermediate data
DNN-layers Parallelization
-
Efficiently utilize multi-core resources for higher performance
-
Optimize data movements among cores
Aggressive Quantization
-
Maximize use of 4-bit computation capability
ENLIGHT Toolkit Overview
NN Converter
-
Converts a network file into internal network format (.enlight)
-
Supports ONNX (PyTorch), TF-Lite, and CFG (Darknet)
NN Quantizer
-
Generates quantized network: float to 4-/8-bit integer
-
Supports per-layer quantization of activation and per-channel quantization of weight
NN Simulator
-
Evaluates full precision network and quantized network
-
Estimates accuracy loss due to quantization
NN Compiler
-
Generates NPU handling code for target architecture and network
ENLIGHT Toolkit Applications
-
Person, Vehicle, Bike, Traffic Sign Detection
- Parking Lot Vehicle Location Detection & Recognition
-
License Plate Detection & Recognition
-
Detection, Tracking, and Action Recognition for Surveillance
Deliverables
ENLIGHT Toolkit is available to all eligible companies with the following items:
-
RTL design for synthesis
-
User guide
-
Integration guide
