single.sh

#!/bin/bash
export HSA_FORCE_FINE_GRAIN_PCIE=1
export MIOPEN_FIND_MODE=1
export MIOPEN_DEBUG_DISABLE_FIND_DB=1
export NCCL_SOCKET_IFNAME=ib0
export HSA_USERPTR_FOR_PAGED_MEM=0
lrank=$OMPI_COMM_WORLD_LOCAL_RANK
comm_rank=$OMPI_COMM_WORLD_RANK
comm_size=$OMPI_COMM_WORLD_SIZE
TOKENS=2056
DATA_PATH=~/data/wmt14_en_de_joined_dict
APP="python3 train.py $DATA_PATH --arch transformer_wmt_en_de --share-decoder-input-output-embed --optimizer adam --adam-betas '(0.9,0.98)' --clip-norm 0.0 --lr 5e-4 --lr-scheduler inverse_sqrt --warmup-updates 4000 --dropout 0.3 --weight-decay 0.0001 --criterion label_smoothed_cross_entropy --label-smoothing 0.1 --max-tokens $TOKENS --eval-bleu --eval-bleu-args {\"beam\":5,\"max_len_a\":1.2,\"max_len_b\":10} --eval-bleu-detok moses --eval-bleu-remove-bpe --eval-bleu-print-samples --best-checkpoint-metric bleu --maximize-best-checkpoint-metric --distributed-rank ${comm_rank} --distributed-world-size ${comm_size} --device-id ${lrank} --local_rank ${lrank} --distributed-init-method tcp://${1}:34567 --distributed-no-spawn --max-epoch 1"

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 NCCL_SOCKET_IFNAME=ib0 numactl --cpunodebind=0 --membind=0 ${APP}
  NCCL_SOCKET_IFNAME=ib0 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 NCCL_SOCKET_IFNAME=ib0 numactl --cpunodebind=1 --membind=1 ${APP}
  NCCL_SOCKET_IFNAME=ib0 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 NCCL_SOCKET_IFNAME=ib0 numactl --cpunodebind=2 --membind=2 ${APP} 
  NCCL_SOCKET_IFNAME=ib0 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 NCCL_SOCKET_IFNAME=ib0 numactl --cpunodebind=3 --membind=3 ${APP}
  NCCL_SOCKET_IFNAME=ib0 numactl --cpunodebind=3 --membind=3 ${APP}
  ;;
esac