From zero to Julia Lesson 9. Working with packages

Edit: Some very upset conspiracy theorists are accusing me of intentionally not editing clarifications in, so I'm gonna duplicate them up here as...

Questions about MKL vs OpenBLAS come up a lot, for example in comparisons with Matlab (linked to MKL), and a lot of users have issues building with MKL, eg here. Of course, one can easily download an MKL binary with JuliaPro, but then you may have to face down an army of dependency conflicts.  My point here is to compare MKL and OpenBLAS with an AMD processor (Ryzen Threadripper 1950x).  Lots of performance comparisons are already out there, but I figured I would add one without an intel chip.  B...

Julia Computing was founded with a mission to make Julia easy to use, easy to deploy and easy to scale. We operate out of Boston, London and Bangalore and we serve customers worldwide.

Something that has been bothering me about discussions about microbenchmarks is that people seem to ignore that the benchmarks are highly application-dependent. The easiest way to judge whether the benchmark really matters to a particular application is the operation overhead of the largest and most common calls. If you have a single operation dominating all of your runtime 99.9%, making everything else 100x faster still won't do anything to your real runtime performance. But at the same time, if your bottleneck is some small operation that's in a tight loop, then that operation may be your bottleneck. This is a classic chart to keep in the back of your mind when considering optimizations. Here is a very brief overview on what to think about when optimizing code and how to figure out when to stop. Function Call Overhead When dealing with ... READ MORE