Smart Embedded Vision
Overview
As compute workloads move to the edge, PolarFire FPGAs offer 30-50% lower total power than competing mid-range FPGAs, with 5-10x lower static power, making them ideal for a new range of compute-intensive edge devices, including those deployed in thermally and power-constrained environments. PolarFire FPGA Smart Embedded Vision solutions include video, imaging, and machine learning IP and tools for accelerating designs that require high performance in low-power, small form-factors across the industrial, medical, broadcast, automotive, aerospace and defense markets.
Key PolarFire Benefits in Smart Embedded Vision
1. Lowest Total Power Consumption among competitive mid-density FPGAs
- 30% to 50% lower power consumption over competitive mid-density FPGAs
- Extended battery life in portable devices like drones, AR/ VR headset, HUDs, portable Ultrasound etc.
- Reduce system cost by eliminating thermal fans and heat sinks
- Realize lower power in 4kp60 HDMI 2.0, 12G SDI, 10G Ethernet, 12.5G CoaXPress etc. using SERDES lanes rated for 90 mW at 10G
2. Small form-factor packages starting at 11x11 mm for 100K LE
- Create compact modules with 100K (11x11 mm) and 200K (11x14.5 mm) LE devices
- Design your next-gen vision platform with small form-factor PolarFire FPGAs with unmatched features like DDR4, LPDDR3, 12.7G SERDES, 1.6 Gbps LVDS I/Os and PCIe Gen2x4
Power Consumption Competitive Benchmark with 16 Channel Audio-Video Bridge Design Example
The example design demonstrates an Audio-to-Video bridge implementation. It uses 56% LUTs, 35% Mathblocks, DDR3 and 16 channel transceivers in a PolarFire MPF500T device. Benchmarks demonstrate up to 52% lower power consumption when compared to similar density FPGAs.
16 Channel AVB Switcher Power Estimator Results
| AVB Switcher (4 Ch.) | Static (W) | Core Dynamic (W) | I/O* (W) | Transceiver* (W) | Total Power (W) |
|---|---|---|---|---|---|
| Polar Fire (MPF500TS) | 1.493 | 2.474 | 2.991 | 0.769 | 7.727 |
| Polar Fire (MPF500TLS**) | 1.059 | 2.474 | 2.991 | 0.769 | 7.293 |
| Kintex 7(XC7k325T-2) | 1.796 | 5.471 | 3.971 | 4.079 | 15.317 |
| Arria V(5AGXFB3H) | 2.572 | 4.350 | 5.451 | 1.651 | 14.025 |
| Zynq US+(XCZU7EV-1L(0.72v)) | 2.864 | 2.165 | 4.011 | 2.694 | 11.7 |
16 Channel AVB Switcher Resource Utilization
| Resources | Count | Interface | Lanes | I/Os | Rate |
|---|---|---|---|---|---|
| 4LUT | 271K | Transceivers | 16 | - | 2.97Gb/s |
| DFF | 188K | ||||
| LSRAM | 816 | ||||
| uSRAM | 249 | 3x72 bit DDR3 | - | 351 | 800 Mb/s |
| MathBlock | 500 |
Learn More
| Learn why Microchip FPGAs consume up to 50% lower-power than competitive mid-density FPGAs? | Learn More |
| Did you know that PolarFire is the world's best FPGA at protecting your IP? | Learn More |
| Do you know what makes Microchip FPGAs the most reliable in the Industry? | Learn More |
| Learn about Libero, the IDE for PolarFire. | Learn More |
| Learn how PolarFire will fulfill your next-generation vision platform requirements. | Learn More |
Getting Started
Design your video signal chain with lowest power mid-range PolarFire FPGAs
 |
|
PolarFire Video FMC Portfolio
CoaXPress FMC Card |
SDI FMC Card |
USXGMII FMC Card |
| The CoaXPress FMC daughter card is the hardware evaluation platform for evaluating and testing the CoaXPress protocol. Price: $849. | SDI FMC daughter card is the hardware evaluation platform for evaluating and testing the Serial Digital interface IP. Price: $499. | The USXGMII FMC daughter card is the hardware evaluation platform for evaluating and testing the quadrate PHY IP. Price: $499 |
| # | Description | Links |
|---|---|---|
|
1
|
Explore and Purchase the PolarFire Video Kit. | Kit Webpage |
|
2
|
Explore and Purchase the CoaXPress FMC Daughter Card. | FMC Webpage |
| 3 | Explore and Purchase the SDI FMC Daughter Card. | FMC Webpage |
| 4 | Explore and Purchase the USXGMII FMC Daughter Card. | FMC Webpage |
| 5 | Download Libero SoC v12.1 Software for PolarFire FPGAs. | Libero SoC v12.1 Download |
| 6 | The kit comes with one-year free Libero SoC Gold license. Register your Software ID. | Licensing |
| 7 | Download the Dual Camera Video Kit Demo Guide. | DG0849 |
| 8 | Download Design File, Programming Files and GUI Installer. | Design File, Program Files, GUI Installer |
| 9 | Explore the Imaging and Video IPs tab for more information. | Go to the Imaging and Video IPs tab. |
| 10 | Explore Low-Power PolarFire designs. Download the Power Estimator UG and Excel Tool. | Low Power UG, Power Estimator |
Out of Box Demo Design for the PolarFire Video Kit
Demo Guide & Programming Files
DG0849: PolarFire FPGA Dual Camera Video Kit Demo Guide
|
12/2019 |
Imaging and Video IPs
Microchip's FPGA product portfolio offers scalable production-ready IPs through in-house development and using our third-party partner ecosystem. Our in-house IP portfolio covers the latest embedded vision IPs like MIPI, SLVS-EC, CoaXPress, Serial Digital Interface (SDI), HDMI, etc, while our partners cover offerings in Machine Learning, H.264, DisplayPort and HDCP IPs, with many more IPs being added continuously. 
Click here to see our Partner IPs.
In-house DirectCore Smart Embedded Vision IPs for PolarFire FPGA
| IP | Features | Documentation |
| MIPI CSI-2 Rx | Up to 1.5 Gbps per lane x 4 lanes, 4Kp60 | UG0806: MIPI CSI-2 Rx UG |
| MIPI CSI-2 Tx | Up to 1 Gbps per lane x 4 lanes, 4Kp30 | UG0826: PolarFire MIPI CSI-2 Tx UG |
| HDMI 2.0 Rx | Supports HDMI 2.0, 8-bit color, 1080p60 | UG0863: HDMI RX IP UG |
| HDMI 2.0 Tx | Supports HDMI 2.0 and 1.4, 4Kp60 | UG0862: HDMI TX IP UG |
| USXGMII | Supports 1, 2.5, 5 and 10G over Ethernet Cu PHY: EDCS-1150953 | Request Information |
| 3G/HD SDI Rx | 1.485 Gbps HD-SDI and 2.97 Gbps 3G-SDI | CoreSDIRX v2.2 Hand Book |
| 3G/HD SDI Tx | 1.485 Gbps HD-SDI and 2.97 Gbps 3G-SDI | CoreSDITX v2.2 Hand Book |
| 6G/12G SDI Rx | 6 Gbps (1080p120, 2160p30) and 12Gbps (2160p60) | CoreUHD_SDIRX v2.0 Hand Book |
| 6G/12G SDI Tx | 6 Gbps (1080p120, 2160p30) and 12 Gbps (2160p60) | CoreUHD_SDITX v2.0 Hand Book |
| SLVS-EC | Supports 2.3 Gbps per lane x 2 lanes in RAW8 data type | UG0877: SLVS-EC Rx UG |
| CoaXPress v1.1 | 6.25 Gbps down, 20.83 Mbps up connections, Host and Device IP | UG0875: CoaXPress IP UG |
| ISP Bundle | Bayer, Video DMA, Alpha Blending, Color Space (RGB, YCbCr), Image Sharpening, Display Enhancement, Edge Detection, Display Controller, Pattern Generation, MIPI CSI-2 Rx/ Tx and LVDS 7:1 Display Rx/ Tx | UG0640: Bayer Interpolation UG UG0693: Edge Detection UG UG0639: Color Space Conversion UG UG0641: Alpha Blending UG UG0646: Display Enhancement UG UG0651: Scaler UG UG0682: Pattern Generator UG UG0649: Display Controller UG |
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 |
 |
|
PolarFire FPGAs |
 |
|
PolarFire FPGAs |
 |
|
PolarFire FPGAs |
 |
|
PolarFire FPGAs SmartFusion2 SoC FPGAs IGLOO2 FPGAs |
 |
|
PolarFire FPGAs |
 |
|
SmartFusion2 SoC FPGAs IGLOO2 FPGAs |
 |
|
SmartFusion2 SoC FPGAs IGLOO2 FPGAs |
 |
|
PolarFire FPGAs |
Request Information
Machine Learning Inference IP
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. |  |
| CNN | Lenet | Squeezenet | Pose | VGG | VVG(SVD) | Tiny-Yolo v2 |
|---|---|---|---|---|---|---|
| Network GOPS | 0.005 | 0.782 | 3.587 | 30.941 | 30.764 | 6.970 |
| Fabric 4LUT | 59,469 | 78,268 | 73,000 | 85,531 | 68,484 | 59,991 |
| Fabric DFF | 80,968 | 84,048 | 84,782 | 96,103 | 77,554 | 76,674 |
| uSRAM Blocks (64x12) | 1,440 | 1,024 | 1,024 | 1,008 | 1,024 | 1,024 |
| LSRAM Blocks (20k bit) | 126 | 578 | 578 | 550 | 434 | 306 |
| Total RAM (Mbits) | 3.52 | 12.04 | 12.04 | 11.48 | 9.23 | 6.73 |
| Math Blocks (18x18 MACC) | 720 | 512 | 512 | 504 | 512 | 512 |
| FPS | 2,747 | 155 | 23 | 6 | 9 | 39 |
| Power (W) | 3.7 | 4.5 | 4.4 | 4.2 | 3.8 | 3.5 |
| Performance (GOPs/s) | 12.60 | 121.19 | 82.79 | 175.43 | 261.80 | 275.11 |
| Power Efficiency (GOPs/s/W) | 3.45 | 26.80 | 18.72 | 41.96 | 68.83 | 79.60 |
| DSP Efficiency (GOPs/s/DSP) | 0.02 | 0.24 | 0.16 | 0.35 | 0.51 | 0.54 |
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
F
- 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
