OSU#

This workload (test_template_name is OSUBench) allows you to execute OSU Micro Benchmarks within the CloudAI framework.

Usage example#

Test example:

name = "osu_example"
test_template_name = "OSUBench"
description = "OSU Benchmark example"

[cmd_args]
"docker_image_url" = "<docker container url here>"
"benchmarks_dir" = "/directory/with/osu/binaries/in/container"
"benchmark" = ["osu_allreduce", "osu_allgather"]
"iterations" = 10
"message_size" = "1024"

Test Scenario example:

name = "osu_example"

[[Tests]]
id = "Tests.1"
test_name = "osu_example"
num_nodes = "2"
time_limit = "00:20:00"

Test-in-Scenario example:

name = "osu-test"

[[Tests]]
id = "Tests.osu_allreduce"
num_nodes = 2
time_limit = "00:05:00"

name = "osu_example"
description = "OSU allreduce 1KB"
test_template_name = "OSUBench"

    [Tests.cmd_args]
    docker_image_url = "<docker container url here>"
    benchmarks_dir = "/directory/with/osu/binaries/in/container"
    benchmark = "osu_allreduce"
    iterations = 10
    message_size = "1024"

API Documentation#

Command Arguments#

class cloudai.workloads.osu_bench.osu_bench.OSUBenchCmdArgs(

*,

docker_image_url: str,

benchmarks_dir: str,

benchmark: str | List[str],

message_size: str | List[str] | None = None,

iterations: int | None = None,

warmup: int | None = None,

mem_limit: int | None = None,

full: bool = True,

**extra_data: Any,

)[source]#

Bases: CmdArgs

Command line arguments for a OSU Benchmark test.

docker_image_url: str#: URL of the Docker image to use for the test.

benchmarks_dir: str#: Directory with the OSU Benchmark binaries inside the container.

benchmark: str | List[str]#: Name of the benchmark to run.

message_size: str | List[str] | None#

Message size for the benchmark.

Examples:

  // min = default, max = 128
128  // min = 2, max = 128
    // min 2, max = default

iterations: int | None#: Number of iterations for the benchmark.

warmup: int | None#: Number of warmup iterations to skip before timing.

mem_limit: int | None#: Per-process maximum memory consumption in bytes.

full: bool#: Print full format listing of results.

Test Definition#

class cloudai.workloads.osu_bench.osu_bench.OSUBenchTestDefinition( *, name: str, description: str, test_template_name: str, cmd_args: OSUBenchCmdArgs, 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 definition for OSU Benchmark test.

cmd_args: OSUBenchCmdArgs#

property docker_image: DockerImage#

property installables: list[Installable]#

property cmd_args_dict: dict[str, Any]#

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