#!/bin/bash #export MIOPEN_DEBUG_DISABLE_FIND_DB=1 #export NCCL_SOCKET_IFNAME=ib0 #export HSA_USERPTR_FOR_PAGED_MEM=0 #export MIOPEN_DEBUG_DISABLE_FIND_DB=1 #export NCCL_SOCKET_IFNAME=eno1 export HSA_FORCE_FINE_GRAIN_PCIE=1 #source /public/software/apps/DeepLearning/PyTorch/pytorch-env.sh export MIOPEN_FIND_MODE=3 #export MIOPEN_ENABLE_LOGGING_CMD=1 #export ROCBLAS_LAYER=3 module unload compiler/rocm/2.9 #export MIOPEN_DEBUG_CONV_DIRECT_ASM_3X3U=0 #export MIOPEN_DEBUG_CONV_DIRECT_ASM_WRW3X3=0 echo "MIOPEN_FIND_MODE=$MIOPEN_FIND_MODE" #module load apps/PyTorch/1.5.0a0/hpcx-2.4.1-gcc-7.3.1-rocm3.3 #source /public/home/aiss/Pytorch/env_rocm3.3_torch1.5.sh lrank=$OMPI_COMM_WORLD_LOCAL_RANK comm_rank=$OMPI_COMM_WORLD_RANK comm_size=$OMPI_COMM_WORLD_SIZE #module load compiler/rocm/3.9.1 APP="python3 run_squad_v1.py \ --train_file /public/home/hepj/data/sq1.1/train-v1.1.json \ --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json \ --init_checkpoint /public/home/hepj/model_source/pytorch_bert/model.ckpt-28252.pt \ --vocab_file /public/home/hepj/model_source/pytorch_bert/vocab.txt \ --output_dir /public/home/hepj/outdir/torch/SQuAD \ --config_file /public/home/hepj/model_source/pytorch_bert/bert_config.json \ --json-summary ./log/results.json \ --bert_model bert-large-uncased \ --do_train \ --do_predict \ --train_batch_size 4 \ --predict_batch_size 4 \ --gpus_per_node 1 \ --local_rank -1 \ --eval_script ./evaluate-v1.1.py " case ${lrank} in [0]) export HIP_VISIBLE_DEVICES=0 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} #echo GLOO_SOCKET_IFNAME=ib0 numactl --cpunodebind=0 --membind=0 ${APP} #GLOO_SOCKET_IFNAME=ib0 numactl --cpunodebind=0 --membind=0 ${APP} ;; [1]) export HIP_VISIBLE_DEVICES=1 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=2 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=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