[kristjansson]

> I was expecting a little variation in execution time for each comparison, but what I wasn't expecting was the bimodal nature of the results. For each function, there were two distinct groups of execution times. These peaks existed for all the function types at consistent relative spacings, which suggests that certain vector comparisons took longer than others no matter which distance function was being used

Surely pre- and post- JIT?

[sgt101]

May be the author could test with realistic data set sizes. Recently I've worked with 26M and 300M data sets. Perhaps something along those lines.