The source code should be updated for compute capability 120; Please let us know #270
Description
cc120 is RTX50xx series (https://developer.nvidia.com/cuda-gpus).
The two numbers seem to be same as cc90:
a.max_blocks_per_multiprocessor = 32;
a.cores_per_multiprocessor = 128;
https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#compute-capability-12-x
https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#features-and-technical-specifications-technical-specifications-per-compute-capability
After the edit to src/cudart/gpucard.cpp the code compiled and all tests passed (tested on RTX5090, cuda 12.9.41. Compile: FC=gfortran CXX=g++ CUDACXX=nvcc compute_capability=120 gpu_lang=cuda cmake -D CMAKE_INSTALL_PREFIX=$HOME/.local ..).