COMP 455

We live in the age of “big data,” where companies need to gather and analyze truly massive amounts of information. Companies specializing in web search need to essentially archive and analyze the entire web. Social media sites need to store and work with millions of user profiles. Programmers need tools that will efficiently scale up to these kinds of tasks. This course introduces the theory and practice of distributed programming and cluster computing, where such problems are tackled by dividing the tasks into smaller parts and running them across many machines at once. In particular, we will cover the MapReduce algorithm and its popular open-source software implementations. -- Prerequisite -- COMP 251. -- Corequisite -- None. -- Pre or Corequisite -- None. Section information text: Note: Final exam will take place in-person