#!/bin/bash lrank=$OMPI_COMM_WORLD_LOCAL_RANK APP=" python3 ./scripts/tf_cnn_benchmarks/tf_cnn_benchmarks.py --data_format=NCHW --batch_size=128 --model=resnet50 --optimizer=momentum --variable_update=horovod --print_training_accuracy=true --eval_during_training_every_n_epochs=1 --nodistortions --num_gpus=1 --num_epochs=90 --weight_decay=1e-4 --data_dir=$data_dir_path --use_fp16=False --data_name=imagenet --train_dir=$save_checkpoint_path case ${lrank} in [0]) export HIP_VISIBLE_DEVICES=0,1,2,3 export UCX_NET_DEVICES=mlx5_0:1 export UCX_IB_PCI_BW=mlx5_0:50Gbs echo numactl --cpunodebind=0 --membind=0 ${APP} numactl --cpunodebind=0 --membind=0 ${APP} ;; [1]) export HIP_VISIBLE_DEVICES=0,1,2,3 export UCX_NET_DEVICES=mlx5_1:1 export UCX_IB_PCI_BW=mlx5_1:50Gbs echo numactl --cpunodebind=1 --membind=1 ${APP} numactl --cpunodebind=1 --membind=1 ${APP} ;; [2]) export HIP_VISIBLE_DEVICES=0,1,2,3 export UCX_NET_DEVICES=mlx5_2:1 export UCX_IB_PCI_BW=mlx5_2:50Gbs echo numactl --cpunodebind=2 --membind=2 ${APP} numactl --cpunodebind=2 --membind=2 ${APP} ;; [3]) export HIP_VISIBLE_DEVICES=0,1,2,3 export UCX_NET_DEVICES=mlx5_3:1 export UCX_IB_PCI_BW=mlx5_3:50Gbs echo numactl --cpunodebind=3 --membind=3 ${APP} numactl --cpunodebind=3 --membind=3 ${APP} ;; esac