Smart Embedded Vision

Getting Started

 Out of Box Demo Design for the PolarFire Video Kit

Demo Guide & Programming Files

Imaging and Video IPs

Click here to see our Partner IPs.

In-house DirectCore Smart Embedded Vision IPs for PolarFire FPGA

For evaluation/purchase of any of the IPs, please fill in the Request Information form, or contact Local Sales in your area.

CompanionCore Smart Embedded Vision Partner IPs

Partners	Description	Supported FPGAs
	HDMI 2.0b/ 1.4, DisplayPort 1.4a HDCP 1.x/ 2.x	PolarFire FPGAs
	CoaXPress 12.5Gbps Host and Device 10GigE Vision (in development), Turnkey Solutions	PolarFire FPGAs
	H.264 Encoder JPEG 2000 Compression	PolarFire FPGAs
	DDR4/3, LPDDR4 CSI-2, DSI-2	PolarFire FPGAs SmartFusion2 SoC FPGAs IGLOO2 FPGAs
	Core Deep Learning (CDL) Caffe CNN Compiler	PolarFire FPGAs
	Alpha Blender, Chroma Resample, Image Rotation SD, SDIO and MMC Controllers	SmartFusion2 SoC FPGAs IGLOO2 FPGAs
	H.264 Encoder	SmartFusion2 SoC FPGAs IGLOO2 FPGAs

Request Information

Deep Learning Inference Acceleration for sensor / edge inference

It is now possible to make your sensors (e.g. camera for industrial, drone, robotics or UAV) very smart with Microchip Deep Learning Inference toolkit – within your power budget. Highly optimized CNN implementation with 8bit quantization enables Microchip PolarFire FPGAs deliver 100 Giga ops per Watt – 2x to 4x of any competitive FPGA devices in the market today.

Traffic Monitoring	Machine Vision	ADAS
Surveillance	PCB Inspection	Drone Vision

Microchip FPGAs for Edge Inference

Microchip FPGAs enable power-optimized machine learning inference on the edge. Compared to MCU, CPU, GPUs and AI ASICs, Microchip FPGAs:

• Offer large DSP compute capacity (up to 1480 x18 x 18 Math Blocks) vs. MCU/ MPU/ CPU
• Have lower power dissipation (~3-4W Core Power) vs. CPU/ GPU (>20W)
• Have up to 50% lower power dissipation over competitive mid-density FPGAs
• Offer scalability based on required performance
• Integrate video, connectivity, security etc. vs. ASICs

Low Power CNN Benchmarks using PolarFire FPGAs

ASIC Design Services is Microchip's IP partner for Artificial Intelligence solutions. They provide a scalable and flexible Convolutional Neural Network (CNN) solution called the Core Deep Learning (CDL) framewor. CDL enables platform-specific optimized inference solutions on the edge to be implemented in Microchip FPGAs. The table below illustrates low-power capabilities of PolarFire FPGAs while running typical CNN models using the CDL framework.

2x to 4x GOPS/Watt vs. Competing Mid-Range FPGAs

Combining PolarFire’s low-power consumption, efficient 18x18 math blocks with INT8 Dot Product Mode operations and ASIC Design Services' network optimized compiler, implementing inference on the edge provides 2x to 4x advantage in terms of GOPs / Watt against competing mid-range FPGAs.

Scalable Solution with Microchip FPGAs

Microchip FPGAs including PolarFire, SmartFusion2 and IGLOO2 share compatible fabric and Math block architecture. This enables inference engines to be easily configured across the different FPGA families. You choose the FPGA based on your cost and performance requirements

 

• Click here to learn how ASIC Design Services provides an integrated person detection solution
• Read the technical paper on How to implement power efficient machine learning using Microchips PolarFire FPGAs
• Click here to know how PolarFire FPGA's math block offers 14% higher efficieny vs. competing FPGAs for INT8 Dot Product operations

Request More Information

Request More Information