Is there any benchmark comparing the speed and memory usage of Julia on different Operating Systems?
They should be pretty much the same, except for some things that deals directly with the OS, like files. What’s the reason for the question?
From my own experience, Julia is a bit faster in Linux (Mint) than in Windows (10) regardless of what the code does, I didn’t try OSX though.
Perhaps multithreading?
I don’t think so, may be it’s that Linux is more programmers friendly as they say. Also, the difference is around 25 to 30%, so definitely not multi-threading. Furthermore, I use other languages (e.g. Fortran, C) and observe a similar difference.
I like benchmarks and it can help to choose between operating systems.
What I’ve seen for large simulations taking a day or so to finish on my linux machine, that it simply slows to a crawl and basically stops on windows 10. This is even with setting the process priority for julia to real time.
It is a significant issue for running long simulations on windows 10. It’s difficult to provide a test case because of the complexity involved, and of course my code is proprietary.
Has anyone else seen this?