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 covers the implementation of custom instructions on NIOS II processors, including the addition of custom logic to the ALU, different types of instruction implementations, and the use of internal register files. It also discusses the methodology of profiling software and hardware to evaluate program execution time, with a focus on real-time embedded systems. The lecture explores the challenges and benefits of software profiling, dynamic profiling with timers, and hardware profiling using external interfaces. Various performance counter functions and their usage are explained, along with the advantages and disadvantages of GNU profilers. The importance of profiling for optimizing program execution and identifying areas for hardware acceleration is highlighted.