Skip to content

[test][sagemaker][pytorch] Run smddp_smdmp test on correct region #1139

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 3, 2021
Merged

[test][sagemaker][pytorch] Run smddp_smdmp test on correct region #1139

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions test/sagemaker_tests/pytorch/training/integration/sagemaker/test_smdataparallel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,14 +140,14 @@ def test_smdataparallel_mnist(n_virginia_sagemaker_session, framework_version, n
@pytest.mark.integration("smdataparallel_smmodelparallel")
@pytest.mark.model("mnist")
@pytest.mark.parametrize('instance_types', ["ml.p3.16xlarge"])
def test_smmodelparallel_smdataparallel_mnist(instance_types, n_virginia_ecr_image, py_version, n_virginia_sagemaker_session, tmpdir):
def test_smmodelparallel_smdataparallel_mnist(instance_types, ecr_image, py_version, sagemaker_session, tmpdir):
"""
Tests SM Distributed DataParallel and ModelParallel single-node via script mode
This test has been added for SM DataParallelism and ModelParallelism tests for re:invent.
TODO: Consider reworking these tests after re:Invent releases are done
"""
can_run_modelparallel = can_run_smmodelparallel(n_virginia_ecr_image)
can_run_dataparallel = can_run_smdataparallel(n_virginia_ecr_image)
can_run_modelparallel = can_run_smmodelparallel(ecr_image)
can_run_dataparallel = can_run_smdataparallel(ecr_image)
if can_run_dataparallel and can_run_modelparallel:
entry_point = 'smdataparallel_smmodelparallel_mnist_script_mode.sh'
elif can_run_dataparallel:
Expand All @@ -160,12 +160,12 @@ def test_smmodelparallel_smdataparallel_mnist(instance_types, n_virginia_ecr_ima
with timeout(minutes=DEFAULT_TIMEOUT):
pytorch = PyTorch(entry_point=entry_point,
role='SageMakerRole',
image_uri=n_virginia_ecr_image,
image_uri=ecr_image,
source_dir=mnist_path,
instance_count=1,
instance_type=instance_types,
sagemaker_session=n_virginia_sagemaker_session)
sagemaker_session=sagemaker_session)

pytorch = _disable_sm_profiler(n_virginia_sagemaker_session.boto_region_name, pytorch)
pytorch = _disable_sm_profiler(sagemaker_session.boto_region_name, pytorch)

pytorch.fit()
18 changes: 9 additions & 9 deletions test/sagemaker_tests/tensorflow/tensorflow2_training/integration/sagemaker/test_mnist.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,9 +41,9 @@ def test_mnist(sagemaker_session, ecr_image, instance_type, framework_version):
sagemaker_session=sagemaker_session,
image_uri=ecr_image,
framework_version=framework_version)

estimator = _disable_sm_profiler(sagemaker_session.boto_region_name, estimator)

inputs = estimator.sagemaker_session.upload_data(
path=os.path.join(resource_path, 'mnist', 'data'),
key_prefix='scriptmode/mnist')
Expand Down Expand Up @@ -191,15 +191,15 @@ def test_smdebug(sagemaker_session, ecr_image, instance_type, framework_version)
@pytest.mark.model("mnist")
@pytest.mark.skip_cpu
@pytest.mark.skip_py2_containers
def test_smdataparallel_smmodelparallel_mnist(n_virginia_sagemaker_session, instance_type, n_virginia_ecr_image, tmpdir, framework_version):
def test_smdataparallel_smmodelparallel_mnist(sagemaker_session, instance_type, ecr_image, tmpdir, framework_version):
"""
Tests SM Distributed DataParallel and ModelParallel single-node via script mode
This test has been added for SM DataParallelism and ModelParallelism tests for re:invent.
TODO: Consider reworking these tests after re:Invent releases are done
"""
instance_type = "ml.p3.16xlarge"
_, image_framework_version = get_framework_and_version_from_tag(n_virginia_ecr_image)
image_cuda_version = get_cuda_version_from_tag(n_virginia_ecr_image)
_, image_framework_version = get_framework_and_version_from_tag(ecr_image)
image_cuda_version = get_cuda_version_from_tag(ecr_image)
if Version(image_framework_version) < Version("2.3.1") or image_cuda_version != "cu110":
pytest.skip("SMD Model and Data Parallelism are only supported on CUDA 11, and on TensorFlow 2.3.1 or higher")
smmodelparallel_path = os.path.join(RESOURCE_PATH, 'smmodelparallel')
Expand All @@ -209,12 +209,12 @@ def test_smdataparallel_smmodelparallel_mnist(n_virginia_sagemaker_session, inst
instance_count=1,
instance_type=instance_type,
source_dir=smmodelparallel_path,
sagemaker_session=n_virginia_sagemaker_session,
image_uri=n_virginia_ecr_image,
sagemaker_session=sagemaker_session,
image_uri=ecr_image,
framework_version=framework_version,
py_version='py3')
estimator = _disable_sm_profiler(n_virginia_sagemaker_session.boto_region_name, estimator)

estimator = _disable_sm_profiler(sagemaker_session.boto_region_name, estimator)

estimator.fit()

Expand Down