Github user srowen commented on the issue:
https://github.com/apache/spark/pull/14898
Does it actually call BLAS though? I understand it could, but that was the
issue last time, that it actually doesn't. It is not necessarily faster because
of the overhead, but could be.
The copy may be fast but it's still overhead that does not exist in the
current code. It's not clear this is a win. I think you'd have to check it out
with a little benchmark to know.
---
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]
