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 provides a practical complement to the theoretical course on memory hierarchy and spatial locality, demonstrating the performance difference between calculating the sum of matrix elements line-by-line and column-by-column. By leveraging spatial locality, accessing data line-by-line results in better program performance compared to column-by-column access. The instructor illustrates this concept through code examples, measuring execution times for both methods and highlighting the significant impact of cache misses on performance.