This configuration works with multiple MPI ranks, but it quite slow

Author: Daniel Vickers

toolchain/modules

@@ -88,3 +88,13 @@ n-gpu CC=nvc CXX=nvc++ FC=nvfortran
 san   CSCS Santis
 san-all cmake python
 san-gpu nvhpc cuda cray-mpich
+
+h     hipergator
+h-gpu nvhpc/25.9
+h-gpu CUDA_HOME="/apps/compilers/cuda/12.8.1"
+h-all HPC_OMPI_DIR="/apps/mpi/cuda/12.8.1/nvhpc/25.3/openmpi/5.0.7"
+h-all HPC_OMPI_BIN="/apps/mpi/cuda/12.8.1/nvhpc/25.3/openmpi/5.0.7/bin"
+h-all OMPI_MCA_pml=ob1 OMPI_MCA_coll_hcoll_enable=0
+h-gpu PATH="/apps/mpi/cuda/12.8.1/nvhpc/25.3/openmpi/5.0.7/bin:/apps/compilers/cuda/12.8.1/bin:${PATH}"
+h-gpu LD_LIBRARY_PATH="/apps/compilers/cuda/12.8.1/lib64:${LD_LIBRARY_PATH}"
+h-gpu MFC_CUDA_CC=100 NVHPC_CUDA_HOME=$CUDA_HOME