Re:Giving up on Julia (2016)
by StefanKarpinski on Sunday August 18, 2019 @04:44PM
(#20732696)
It’s a fixed overhead like the JVM, CLR or any substantial runtime that includes a JIT.
Which, by the way, only applies to Julia programs under JIT. The AoT compiler will handle nearly 100% of vast the JIT or REPL will and vice versa, with a goal of 100%.
> … wondering if this is proportional, or simply an X megabyte overhead of the runtime…
Which is why the benchmarks game measures at more than one workload —
https://benchmarksgame-team.pages.debian.net/benchmarksgame/...
Again, I'm left wondering if this is proportional, or simply an X megabyte overhead of the runtime. Maybe it's even shared among all running programs, as some runtimes are. Or it looks like maybe stdio could be just particularly bad in Julia, and in practice I've never written a program for any environment where that was my performance bottleneck.
Performance is not easy to measure, and not easy to report. A single number makes a good headline but it's really not enough information.