# SuperBench Config
version: v0.2
superbench:
  enable: null
  var:
    default_local_mode: &default_local_mode
      enable: true
      modes:
        - name: local
          proc_num: 8
          prefix: CUDA_VISIBLE_DEVICES={proc_rank}
          parallel: yes
    default_pytorch_mode: &default_pytorch_mode
      enable: true
      modes:
        - name: torch.distributed
          proc_num: 8
          node_num: 1
      frameworks:
        - pytorch
    common_model_config: &common_model_config
      duration: 0
      num_warmup: 16
      num_steps: 128
      precision:
        - float32
        - float16
      model_action:
        - train
  benchmarks:
    kernel-launch:
      <<: *default_local_mode
    gemm-flops:
      <<: *default_local_mode
    cudnn-function:
      <<: *default_local_mode
    cublas-function:
      <<: *default_local_mode
    matmul:
      <<: *default_local_mode
      frameworks:
        - pytorch
    sharding-matmul:
      <<: *default_pytorch_mode
    computation-communication-overlap:
      <<: *default_pytorch_mode
    gpt_models:
      <<: *default_pytorch_mode
      models:
        - gpt2-small
        - gpt2-large
      parameters:
        <<: *common_model_config
        batch_size: 4
    bert_models:
      <<: *default_pytorch_mode
      models:
        - bert-base
        - bert-large
      parameters:
        <<: *common_model_config
        batch_size: 8
    lstm_models:
      <<: *default_pytorch_mode
      models:
        - lstm
      parameters:
        <<: *common_model_config
        batch_size: 128
    resnet_models:
      <<: *default_pytorch_mode
      models:
        - resnet50
        - resnet101
        - resnet152
      parameters:
        <<: *common_model_config
        batch_size: 128
    densenet_models:
      <<: *default_pytorch_mode
      models:
        - densenet169
        - densenet201
      parameters:
        <<: *common_model_config
        batch_size: 128
    vgg_models:
      <<: *default_pytorch_mode
      models:
        - vgg11
        - vgg13
        - vgg16
        - vgg19
      parameters:
        <<: *common_model_config
        batch_size: 128