Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture explores the concept of Field-Programmable Gate Arrays (FPGAs), focusing on their post-fabrication programmability and applications in rapidly changing workloads and machine learning. It delves into FPGA architecture components like Look-Up Tables (LUTs) and Clustered Logic Blocks (CLBs), discussing the challenges in parameter optimization and switch-pattern design. The instructor presents a novel approach to FPGA architecture exploration by leveraging the router to automatically design architectures, leading to improved performance metrics. The lecture concludes with insights on future research directions in FPGA design.