Dense LU Factorization with Double Precision

Dear NVIDIA cuSolver developers,

Is there any plan for cuSolver to support double precision Dense LU Factorization using tensor core? Currently there is a function cusolverDnDgetrs to do this job, but it is unclear if this API uses ordinary GPU cores or tensor core.


For GETRS FP64, cuSOLVER calls cuBLAS, which runs on DMMA Tensor cores.
You should be able to see TC usage with the latest version of Nsight Systems