DDLB#

This workload (test_template_name is DDLB) allows you to execute DDLB (Distributed Deep Learning Benchmarks) within the CloudAI framework. Please find the DDLB README at samnordmann/ddlb.

Usage Example#

Test TOML example:

name = "my_ddlb_test"
description = "Example DDLB test"
test_template_name = "DDLB"

[cmd_args]
docker_image_url = "gitlab-master.nvidia.com/nsarkauskas/ddlb:latest"
primitive = "tp_columnwise"
dtype = "float16"

Test Scenario example:

name = "ddlb-test"

[[Tests]]
id = "ddlb.1"
num_nodes = 1
time_limit = "00:10:00"

test_name = "my_ddlb_test"

Test-in-Scenario example:

name = "ddlb-test"

[[Tests]]
id = "ddlb.1"
num_nodes = 1
time_limit = "00:10:00"

name = "my_ddlb_test"
description = "Example DDLB test"
test_template_name = "DDLB"

  [Tests.cmd_args]
  docker_image_url = "gitlab-master.nvidia.com/nsarkauskas/ddlb:latest"
  primitive = "tp_columnwise"
  m = 1024
  n = 128
  k = 1024
  dtype = "float16"
  num_iterations = 50
  num_warmups = 5
  impl = "pytorch;backend=nccl;order=AG_before"

API Documentation#

Command Arguments#

class cloudai.workloads.ddlb.ddlb.DDLBCmdArgs(

*,

docker_image_url: str,

primitive: str,

m: int | list[int] = 1024,

n: int | list[int] = 128,

k: int | list[int] = 1024,

dtype: str,

num_iterations: int = 50,

num_warmups: int = 5,

impl: str | list[str] = 'pytorch;backend=nccl;order=AG_before',

**extra_data: Any,

)[source]#

Bases: CmdArgs

DDLB test command arguments.

docker_image_url: str#

primitive: str#

m: int | list[int]#

n: int | list[int]#

k: int | list[int]#

dtype: str#

num_iterations: int#

num_warmups: int#

impl: str | list[str]#

Test Definition#

class cloudai.workloads.ddlb.ddlb.DDLBTestDefinition( *, name: str, description: str, test_template_name: str, cmd_args: DDLBCmdArgs, extra_env_vars: dict[str, str | List[str]] = {}, extra_cmd_args: dict[str, str] = {}, extra_container_mounts: list[str] = [], git_repos: list[GitRepo] = [], nsys: NsysConfiguration | None = None, predictor: PredictorConfig | None = None, agent: str = 'grid_search', agent_steps: int = 1, agent_metrics: list[str] = ['default'], agent_reward_function: str = 'inverse', )[source]#

Bases: TestDefinition

Test object for DDLB.

cmd_args: DDLBCmdArgs#

property extra_args_str: str#

property docker_image: DockerImage#

property installables: list[Installable]#

was_run_successful( tr: TestRun, ) → JobStatusResult[source]#