Living on the bleeding edge of Big Data [Andrej Krevl, Stanford University]

"Taming Big Data on Big Hardware with distributed systems"

Abstract of the talk:
Your boss gave you some data. A lot of data. You have to process it. Fast. Your back of the envelope calculation says you need a month to do it. Your boss needs it in a week. What do you do? Throw more hardware at it, of course. But with great power, comes great responsibility. We'll go through the above process on a couple of examples and learn that we might need to care about malloc and memory management even if all of our code is written in Python, and that learning Computer Architecture is very useful if you're trying to grep through 50 terabytes of data. We might even learn that Linux behaves like a bad airline... sometimes.

About the speaker:
Andrej Krevl is currently taming big memory systems, high performance compute clusters and petabyte storage systems at the Stanford University. He was previously developing kitchen robotics prototypes and researching food delivery models at the Stanford Robotics Lab. Andrej started his career as a teaching assistant at the University of Ljubljana where he taught Computer Communications, Web Development and Computer Architecture. He likes to mess with computer security and digital identity management.