Open giordano opened 4 months ago
This might be something @krishnakumarg1984 would be interested in
@krishnakumarg1984 started working on this. I added tasks in the main comment
How do we get cuSparse and cuBlas?
Those should presumably be in the cuda
package? For example py-cupy
claims to use those libraries
Those should presumably be in the cuda package?
That'd be great! It wasn't clear to me when I looked at it yesterday
https://github.com/spack/spack/blob/905e7b9b4559691fb1fdde3340f33ef0214e60dc/var/spack/repos/builtin/packages/kokkos-kernels/package.py#L147-L166 when for this package the variants cusparse
and cublas
are enabled, the cuda
package is added as dependency. This seems to settle it.
The Nvidia HPCG benchmark used to available only via containers, but it was open-sourced last week and it's available at https://github.com/NVIDIA/nvidia-hpcg. This works on both CPU (x86-64 and aarch64, with specific optimisations for Nvidia Grace, aka Neoverse V2) and GPU, and also mixed CPU-GPU configuration (maybe only on Grace-Hopper/Blackwell systems?).
@christophermaynard you may be interested in this.
USE_CUDA =0
)nccl
, cuSparse and cuBlas are included in thecuda
package).