Github user mpjlu commented on the issue:
https://github.com/apache/spark/pull/17742
I don't think we should use BLAS 3 here, because no matter use output or
not here, you need a big buffer to save the BLAS result. That still cause GC
problem.
I also want to test: build a handwritten native gemm, which not returns C
(C=A*B), but only return the topK elements of each row. This maybe better
performance than current solution.
---
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]
