Set the number of CPU nodes used by DP algorithms with:
mpirun -np $num_nodes dp
Set the number of threads used by DP algorithms with:
export OMP_NUM_THREADS=$num_threads
Set the number of CPU nodes used by TF kernels with:
export TF_INTRA_OP_PARALLELISM_THREADS=$num_nodes
export TF_INTER_OP_PARALLELISM_THREADS=$num_nodes