Cool! I'll give it a read. :) Was this a paper you wrote for school?
It just bonus assignment since a lecturer who teach algorithm course found that few of her student bored with the course (I think).
A mouth ago, I just realize that this empirical approach very useful in parallel programming. That's Gustavson Law that suggest us to use latency as benchmark.
We're a place where coders share, stay up-to-date and grow their careers.
We strive for transparency and don't collect excess data.