Sorry for my late reply! I'm also very interested in the
implementation of distributed matrix multiplication. As Shivaram
mentioned, the communication is the concern here. But maybe we can
start with a reasonable implementation and then iterate on its
performance. It would be great if eventually
Hi Xiangrui Meng,
Thank you for your comment and creating tickets.
The ticket which I created would be moved to your tickets.
I will close my ticket, and then will link it to yours later.
Best,
Yu Ishikawa
--
View this message in context:
Yeah, I think https://github.com/apache/spark/pull/2315 should have fixed
the Mima issue. We're still seeing some intermittent failures due to
DriverSuite and SparkSubmitSuite tests failing, so I'd appreciate any help
in diagnosing that issue.
On Sun, Sep 7, 2014 at 10:08 PM, Prashant Sharma
