[mlpack-git] [mlpack] Add OpenMP support to density estimation tree code (#438)

[Ryan Curtin]

The speedup looks reasonable to me; I expect that most users will use 10-fold cross-validation, so the speedup isn't amazing but it certainly is a net improvement.  Two last minor questions before I merge this:

* Did you try any other parallelization strategies?  i.e. the for loops inside of SplitNode(), or something like that.
* What's the overhead for the OpenMP-ized code using only one core (do you happen to know)?  No need for extensive benchmarks; I just want to make sure that OpenMP isn't incurring huge overhead even in the singlethreaded case.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/438#issuecomment-103537525
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20150519/03657534/attachment.html>