corepointer opened a new pull request #1180: URL: https://github.com/apache/systemds/pull/1180
This PR contains support for sparse inputs to the CUDA code generation operators and also a new template (rowwise). * A few limitations are there, which will be coming up in subsequent commits to not futher delay the merging of the major parts of these two new features. * No binaries are provided yet. The interested can compile with these three commands (having CUDA 10.2, CMake and a supported C++ compiler (MSVC, GCC-8) from the SYSTEMDS_ROOT directory: ``` cmake -S src/main/cuda -B target/build-cuda cmake --build target/build-cuda --config Debug --target install mvn package ``` ---------------------------------------------------------------- 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: [email protected]
