I’m using the L2 residency control API released on CUDA 11.0 together with Ampere architecture. And I’m wondering how can I determine the data are exactly residing on L2 cache?
Currently I’m using the APIs released on CUDA 11.5 to control the residency property of a data pointer:
https://developer.nvidia.com/blog/revealing-new-features-in-the-cuda-11-5-toolkit/