LogicTronix is “Xilinx Certified Partner [Link]“ and “Design Service Partner of Xilinx Kria SoM for AI/ML [Link]”, know more about LogicTronix-Xilinx Partnership[Link].
We had organized Webinar on “Xilinx Kria-SoM Development and Machine Learning Acceleration” hosted by Xilinx at March 3rd 2022: Xilinx Kria SoM Webinar. Watch the Kria SoM Webinar On-Demand [Link].
We offer following services to our Customers:
- Turnkey Solution on Machine Learning Acceleration with Xilinx MPSoC and Kria SoM FPGAs: AI/ML Model development (Dataset Preparation, Neural Network customization, Training, Pruning, Quantizing-Vitis AI, Compiling-Vitis AI) and MPSoC/SoM deployment. We work with Caffe/Tensorflow/Darknet , Pytorch framework and use Vitis AI methodology for Quantization/Pruning and Compile the Model for specific MPSoC FPGA Board (Evaluation Board-EVK or Custom Board).
- Machine Learning Acceleration with Vitis-AI on Xilinx Kria SoM-KV260, Zynq MPSoC/7000 FPGA, Cloud & Edge. Check our “Machine Learning Portfolio” or Visit: LogicTronix-ML-Solutions.
- Creating custom solutions with Xilinx VVAS for Kria SoM-KV260 and MPSoC FPGA devices.
- Developing Solutions as Kria Apps for Kria KV260 and MPSoC boards [CG, EG or EV devices].
- Creating Multi channel Video System with Multiple Model AI inferencing over it with Xilinx MPSoC FPGA and Kria SoM.
- Solution development for Computer/Machine/Industrial/Medical Vision, ADAS, Security and Surveillance applications with 4k/2k based video processing capability with Xilinx MPSoC and SoC’s and Baremetal | FreeRTOS | Petalinux or OpenAMP flow.
- With our PCB Partners, we also offer custom PCB or Carrier(for SoM) design services on MPSoC for ML/Computer Vision Solutions/Products. By this, you get product of your idea, we do all in-between works to make “idea into product”.
- Vitis/VIVADO based custom solution implementation on computer vision, signal processing and embedded applications
- FPGA Design and Development with RTL/HDL Flow | HLS flow |IP Flow | OpenCL Flow.
- IP Design & Verification and Migration
- GUI (GTK/QT for MPSoC/SoC) Development & Driver Development [Linux/Windows]
- SDAccel/OpenCL acceleration on Accelerator FPGA and Cloud for Custom applications
- Crypto-Algorithm & Blockchain implementation on FPGA [High End FPGAs]
- Developing ultra-low latency designs or IP Cores for Finance (HFT), Medical and Mission Critical applications.
Embedded Linux based Development: Petalinux | Yocto | Buildroot
- Embedded System development with SoC FPGA’s.
- Linux driver development, Tcl Scripting & Bash Scripting
- Petalinux Development: Developing Petalinux Applications as Gstreamer-app for video streaming with ML acceleration
- Petalinux Development: developing solution with Multi threading, multi-processing , implementing Baremetal+Petalinux flow on OpenAMP. Developing time/latency critical applications and solutions.
- FreeRTOS Development for Computer Vision and Signal Processing Applications with Xilinx Zynq MPSoC and 7000 FPGA
Consultation and Design Migration:
- Consulting on FPGA Selection, Design Methodology and Product Development.
- Migrating Xilinx 6 series of FPGA design into Xilinx 7 Series FPGA.
- Inter-vendor FPGA design Migration: Migrating design from one to another vendor-tool or platform- Xilinx, Intel & Microchip.
Interfaces we mostly work for Design Service:
- Computer Vision+ Machine Learning: MIPI, IAS, RTSP, USB , USB 3 Vision, SATA, GbE (Gigabit Ethernet), 10G ETH, SDI (3G-SDI, UHD, 12G-SDI), HDMI, TMDS/DVI, LVDS, Coexpress , SPI, I2C etc.
- ADAS-Automotive: GMSL, FPD Link, CAN, GbE (RADAR, LIDAR), SPI
- Medical Vision and Systems: GMSL, SFP/SFP+, IAS, MIPI etc.
Protocols we mostly work for Design Service:
- AXI, Aurora, PCIe, Native Video, BT656, TMDS, SDI(SDI/3G-SDI/6G-SDI/12G-SDI), SFP, HDMI, DP, SPI, I2C, MIPI CSI/DSI etc.
Machine Learning Framework we used for ML Acceleration:
We offer turnkey solution on Machine Learning Acceleration from Dataset Preparation –> Training–> Network Optimiztion–> Pruning–> Quantization–> Compilation–> Xmodel deployment on MPSoC Boards. We also offer custom PCB or Carrier(for SoM) design services on MPSoC for ML/Computer Vision Solutions/Products.
- Caffe : Large number of Vitis AI Models at Model Zoo are in Caffe and we do have sound expertise with caffe based training, optimizing and customizing neural network and converging model with Vitis AI. Due to vast number of models, caffe is highly preferred framework with Vitis AI, even though there is very less resources on caffe publicly available.
- Tensorflow (TF1/TF2)/ Pytorch/Darknet: We work with tensorflow/pytorch/darknet framework for training, quantization , pruning and compilation to model deployment on MPSoC Board.