Add a generic lacpy codelet on CPU/CUDA workers
Add a generic copy codelet to be used in the case m == n, displA = displB = 0 to perfrom copies on CPU and GPU through the interface dat cpy function.
Edited by Mathieu Faverge
GitLab upgrade completed. Current version is 18.5.4
https://about.gitlab.com/releases/2025/09/18/gitlab-18-4-released/
https://about.gitlab.com/releases/2025/10/16/gitlab-18-5-released/
Add a generic copy codelet to be used in the case m == n, displA = displB = 0 to perfrom copies on CPU and GPU through the interface dat cpy function.