single_process.sh

#!/bin/bash

export HSA_FORCE_FINE_GRAIN_PCIE=1
export MIOPEN_FIND_MODE=3
export MIOPEN_COMPILE_PARALLEL_LEVEL=1
export NCCL_PLUGIN_P2P=ucx
export RCCL_NCHANNELS=2
export NCCL_SOCKET_IFNAME=ib0
export NCCL_P2P_LEVEL=5
export NCCL_IB_HCA=mlx5_0
export NCCL_DEBUG=INFO
export NCCL_NET_GDR_LEVEL=SYS
export NCCL_NET_PLUGIN=none
unset RCCL_NCHANNELS
unset NCCL_NET_GDR_LEVEL
#export NCCL_IB_DISABLE=1 
#export NCCL_P2P_DISABLE=1
lrank=$OMPI_COMM_WORLD_LOCAL_RANK
echo "LRANK===============================$lrank"
comm_rank=$OMPI_COMM_WORLD_RANK
comm_size=$OMPI_COMM_WORLD_SIZE
export HIP_VISIBLE_DEVICES=0,1,2,3
echo "##################################"
#which hipcc
#pip3 list
APP="python3 `pwd`/driver_mpi.py --dist-url tcp://${1}:12345 --dist-backend nccl --world-size=${comm_size} --rank=${comm_rank}"


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
  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
  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
  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
  numactl --cpunodebind=3 --membind=3 ${APP}
  ;;
esac