I think that your next big win is going to come from using Immutable Arrays for your matrix / vector ops. One of the first toy projects I did with Julia was port the "business card raytracer" to Julia ( https://github.com/jakebolewski/rays/tree/master/juliarays) and currently it is only 14% slower than the single threaded c++ version. This is actually quite an improvement since October (back then it was more like 2x slower than the cpp version). If you continue to work on this, it would be interesting to see the performance impact of using immutable types.
Best, Jake On Tuesday, May 20, 2014 9:31:13 AM UTC-4, mike c wrote: > > > Hi Jason > >> >> I'm curious: do you have a link you can share to the python source? >> >> Sorry. No link to my python source as yet. The correspondence between > the julia and python code is pretty much 1:1 >
