A Look at Chapel, D, and Julia Using Kernel Matrix Calculations

dlang.org

27 pointsaldacron2 comments

This was a nice writeup!

I know there was an explicit mention that non-standard library packages were omitted due to fiddlyness in installation, but with Julia using the manifest system, providing reproducible setups should be easy, and for things like this, Chris Elrod's LoopVectorization.jl [1] should offer substantial speedups with some simple macro annotations.

[1] https://github.com/chriselrod/LoopVectorization.jl

Chris deserves some sort of prize for that package. Delivered some factor of 2 or greater speedups for significant portions of my code with just an `@avx`

Reply on news.ycombinator.com