corepointer opened a new pull request #924: URL: https://github.com/apache/systemml/pull/924
This PR adds initial cuda codegen support; stays marked WIP until the tests in CellwiseTmplTest run fine. What works: - dense cellwise codegen with non-vectorized functions (LibSpoofPrimitives not ported yet) and without aggregation ToDo and known bugs: - support functionality of LibSpoofPrimitives - handle sparse data - fallback to java in case no gpu is present - aggregations - fix a bug where the test system stays forever in wait() on the test thread ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
