aeup opened a new pull request, #2197: URL: https://github.com/apache/systemds/pull/2197
This pull request adds two new linearizers for the LOP DAG linearization. The linearizers focus on reducing the minimal memory requirement by scheduling the LOPs in a way that affects the memory requirement for live intermediates. **RESOURCE_AWARE_OPTIMAL** uses a brute-force approach that generates the optimal sequence but requires a lot of time to compile which makes it impractical for larger algorithms and most real world use cases. **RESOURCE_AWARE_FAST** uses a heuristic approach that does not always generate the optimal sequence but is a lot faster than the other approach. The linearizer can be used for tasks with large data sets, but there are also some cases where the compile time is larger than expected or the memory requirement is larger in comparison to other linearizer. cc @mboehm7 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@systemds.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
