UCC
This workload (test_template_name is UCCTest) allows users to execute UCC benchmarks within the CloudAI framework.
Usage Examples
Test TOML example:
Test Scenario example:
Test-in-Scenario example:
API Documentation
Command Arguments
class cloudai.workloads.ucc_test.ucc.UCCCmdArgs(
*,
docker_image_url: str,
collective: Literal[‘allgather’, ‘allgatherv’, ‘allreduce’, ‘alltoall’, ‘alltoallv’, ‘barrier’, ‘bcast’, ‘gather’, ‘gatherv’, ‘reduce’, ‘reduce_scatter’, ‘reduce_scatterv’, ‘scatter’, ‘scatterv’, ‘memcpy’, ‘reducedt’, ‘reducedt_strided’] | list[Literal[‘allgather’, ‘allgatherv’, ‘allreduce’, ‘alltoall’, ‘alltoallv’, ‘barrier’, ‘bcast’, ‘gather’, ‘gatherv’, ‘reduce’, ‘reduce_scatter’, ‘reduce_scatterv’, ‘scatter’, ‘scatterv’, ‘memcpy’, ‘reducedt’, ‘reducedt_strided’]] = ‘alltoall’,
b: int | list[int] = 1,
e: str | list[str] = ‘8M’,
gen: str | list[str] | None = None,
**extra_data: Any,
)
Bases: CmdArgs
UCC test command arguments.
Test Definition
class cloudai.workloads.ucc_test.ucc.UCCTestDefinition(
*,
name: str,
description: str,
test_template_name: str,
cmd_args: UCCCmdArgs,
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’,
agent_config: dict[str, Any] | None = None,
)
Bases: TestDefinition
Test object for UCC.