Building FPGA-based Machine Learning Accelerators in Python

Explore the development of a simple machine learning accelerator deployed on a commodity FPGA using a Python-based toolchain in this 34-minute PyCon US talk. Witness a demonstration of an accelerator built on an entry-level Xilinx FPGA with a total cost under $200. Learn about the combination of open-source software tools used, including PyTorch and ONNX for modeling, and Migen and LiteX for System-on-chip construction. Gain insights into the array of open-source and proprietary vendor tools required for this project, and discover the broader landscape of open-source silicon development.

Talks - Tim Paine: Building FPGA-based Machine Learning Accelerators in Python