Github user debasish83 commented on the pull request:
https://github.com/apache/spark/pull/5005#issuecomment-83021207
Can you take a look at breeze.optimize.linear.NNLS ? I added a timer inside
the compute and there is timer outside...looks like for first 2 ALS iterations,
there is an overhead due to iterator but then it decreases...
I am not sure how much impact is this in overall distributed
runtime...@mengxr can comment on that...I can time the whole ALS flow but I
doubt this difference will show up over there...
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
