onnxruntime/tools/ci_build/github/azure-pipelines/orttraining-linux-gpu-distributed-test-ci-pipeline.yml
Changming Sun 4161758058
Remove openmp related packaging pipeline (#6991)
1. Remove openmp related packaging pipelines and build jobs.
2. Set continueOnError to true for the TSAUpload tasks. Their service is unstable recently.
3. Update Ubuntu 16 docker images to Ubuntu 18, in prepare for getting C++17 support
4. Cherry-pick the changes in 1.7.1 to the master: updating CFLAGS/CXXFLAGS to strip out debug symbols
2021-03-12 10:02:59 -08:00

49 lines
1.5 KiB
YAML

trigger: none
jobs:
- job: Onnxruntime_Linux_GPU_Distributed_Test
timeoutInMinutes: 120
pool: 'Linux-Multi-GPU-V100'
steps:
- checkout: self
clean: true
submodules: recursive
- template: templates/run-docker-build-steps.yml
parameters:
RunDockerBuildArgs: |
-o ubuntu18.04 -d gpu -r $(Build.BinariesDirectory) \
-t onnxruntime_distributed_tests_image \
-x " \
--config RelWithDebInfo \
--enable_training \
--update --build \
--build_wheel \
" \
-m
DisplayName: 'Build'
# Entry point for all distributed CI tests.
# Refer to orttraining/orttraining/test/python/how_to_add_distributed_ci_pipeline_tests.md for guidelines on how to add new tests to this pipeline.
- script: |
docker run \
--gpus all \
--shm-size=1024m \
--rm \
--volume $(Build.SourcesDirectory):/onnxruntime_src \
--volume $(Build.BinariesDirectory):/build \
onnxruntime_distributed_tests_image \
/build/RelWithDebInfo/launch_test.py \
--cmd_line_with_args "python orttraining_distributed_tests.py" \
--cwd /build/RelWithDebInfo \
displayName: 'Run orttraining_distributed_tests.py'
condition: succeededOrFailed()
timeoutInMinutes: 120
- template: templates/component-governance-component-detection-steps.yml
parameters:
condition: 'succeeded'
- template: templates/clean-agent-build-directory-step.yml