access2rohit opened a new pull request #18239: URL: https://github.com/apache/incubator-mxnet/pull/18239
## Description ## Making GPU kernel for argsort use int32_t. Existing implementation already uses optimized thrust library. Slowdown is only due to index_t -> int64_t when building with Large Tensor Support(LTS). Also, LTS is only supported for CPU for now. Changes are have been made in such a way that if MXNet support int64_t for GPU later the changes required would be minimal. ## Checklist ## ### Essentials ### Please feel free to remove inapplicable items for your PR. - [ ] Changes are complete (i.e. I finished coding on this PR) - [ ] All changes have test coverage: - Unit tests are added for small changes to verify correctness (e.g. adding a new operator) - [ ] To the best of my knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change ## Testing ## - will be updated ## Performance Results ## - will be updated ---------------------------------------------------------------- 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
