onnxruntime/tools/ci_build/github/azure-pipelines/linux-gpu-ci-pipeline.yml
Hariharan Seshadri 9356986730
Fix AMD builds and enable testing NHWC CUDA ops in one GPU CI (#17972)
### Description
This PR:

(1) Fixes AMD builds after #17200 broke them (Need to remember to run
AMD builds while trying to merge external CUDA PRs next time)

(2) Turn on the NHWC CUDA feature in the Linux GPU CI. The extra time
spent in building a few more files and running a few more tests will not
be much.

Test Linux GPU CI run :
https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=1170770

### Motivation and Context
Keep the NHWC CUDA ops tested
(https://github.com/microsoft/onnxruntime/pull/17200) and guard against
regressions
2023-10-17 09:23:52 -07:00

188 lines
7 KiB
YAML

##### start trigger Don't edit it manually, Please do edit set-trigger-rules.py ####
trigger:
branches:
include:
- main
- rel-*
paths:
exclude:
- docs/**
- README.md
- CONTRIBUTING.md
- BUILD.md
- 'js/web'
- 'onnxruntime/core/providers/js'
pr:
branches:
include:
- main
- rel-*
paths:
exclude:
- docs/**
- README.md
- CONTRIBUTING.md
- BUILD.md
- 'js/web'
- 'onnxruntime/core/providers/js'
#### end trigger ####
resources:
repositories:
- repository: manylinux
type: Github
endpoint: Microsoft
name: pypa/manylinux
ref: 5eda9aded5462201e6310105728d33016e637ea7
variables:
- template: templates/common-variables.yml
jobs:
- job: Linux_Build
timeoutInMinutes: 120
variables:
skipComponentGovernanceDetection: true
CCACHE_DIR: $(Pipeline.Workspace)/ccache
workspace:
clean: all
pool: onnxruntime-Ubuntu2004-AMD-CPU
steps:
- task: mspremier.PostBuildCleanup.PostBuildCleanup-task.PostBuildCleanup@3
displayName: 'Clean Agent Directories'
condition: always()
- checkout: self
clean: true
submodules: none
- template: templates/get-docker-image-steps.yml
parameters:
Dockerfile: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cuda11
Context: tools/ci_build/github/linux/docker
DockerBuildArgs: "--network=host --build-arg POLICY=manylinux_2_28 --build-arg PLATFORM=x86_64 --build-arg PREPEND_PATH=/usr/local/cuda/bin --build-arg LD_LIBRARY_PATH_ARG=/usr/local/lib64 --build-arg DEVTOOLSET_ROOTPATH=/usr --build-arg BUILD_UID=$( id -u )"
Repository: onnxruntimecuda11build
- task: Cache@2
inputs:
key: '"ccache" | "$(Build.SourceBranch)" | "$(Build.SourceVersion)"'
path: $(CCACHE_DIR)
restoreKeys: |
"ccache" | "$(Build.SourceBranch)"
"ccache"
cacheHitVar: CACHE_RESTORED
displayName: Cach Task
- script: |
sudo mkdir -p $(Pipeline.Workspace)/ccache
condition: ne(variables.CACHE_RESTORED, 'true')
displayName: Create Cache Dir
- task: CmdLine@2
inputs:
script: |
mkdir -p $HOME/.onnx
docker run -e CFLAGS="-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -fstack-protector-strong -fstack-clash-protection -fcf-protection -O3 -Wl,--strip-all" -e CXXFLAGS="-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -fstack-protector-strong -fstack-clash-protection -fcf-protection -O3 -Wl,--strip-all" --rm \
--volume /data/onnx:/data/onnx:ro \
--volume $(Build.SourcesDirectory):/onnxruntime_src \
--volume $(Build.BinariesDirectory):/build \
--volume /data/models:/build/models:ro \
--volume $HOME/.onnx:/home/onnxruntimedev/.onnx \
--volume $(Pipeline.Workspace)/ccache:/cache \
-e ALLOW_RELEASED_ONNX_OPSET_ONLY=0 \
-e NIGHTLY_BUILD \
-e BUILD_BUILDNUMBER \
-e CCACHE_DIR=/cache \
onnxruntimecuda11build \
/bin/bash -c "
set -ex; \
env; \
ccache -s; \
/opt/python/cp38-cp38/bin/python3 /onnxruntime_src/tools/ci_build/build.py \
--build_dir /build --cmake_generator Ninja \
--config Release --update --build \
--skip_submodule_sync \
--build_shared_lib \
--parallel \
--build_wheel \
--enable_onnx_tests --use_cuda --cuda_version=${{variables.common_cuda_version}} --cuda_home=/usr/local/cuda-${{variables.common_cuda_version}} --cudnn_home=/usr/local/cuda-${{variables.common_cuda_version}} \
--enable_cuda_profiling --enable_cuda_nhwc_ops \
--enable_pybind --build_java \
--use_cache \
--cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=75; \
ccache -sv; \
ccache -z"
workingDirectory: $(Build.SourcesDirectory)
- task: CmdLine@2
inputs:
script: |
rm -rf $(Build.BinariesDirectory)/Release/onnxruntime $(Build.BinariesDirectory)/Release/pybind11
rm -f $(Build.BinariesDirectory)/Release/models
find $(Build.BinariesDirectory)/Release/_deps -mindepth 1 ! -regex '^$(Build.BinariesDirectory)/Release/_deps/onnx-src\(/.*\)?' -delete
cd $(Build.BinariesDirectory)/Release
find -executable -type f > $(Build.BinariesDirectory)/Release/perms.txt
- task: PublishPipelineArtifact@0
displayName: 'Publish Pipeline Artifact'
inputs:
artifactName: 'drop-linux'
targetPath: '$(Build.BinariesDirectory)/Release'
- template: templates/explicitly-defined-final-tasks.yml
- job: Linux_Test
timeoutInMinutes: 180
variables:
skipComponentGovernanceDetection: true
workspace:
clean: all
pool: Onnxruntime-Linux-GPU-T4
dependsOn:
- Linux_Build
steps:
- task: DownloadPipelineArtifact@2
displayName: 'Download Pipeline Artifact'
inputs:
buildType: 'current'
artifactName: 'drop-linux'
targetPath: '$(Build.BinariesDirectory)/Release'
- checkout: self
clean: true
submodules: none
- template: templates/get-docker-image-steps.yml
parameters:
Dockerfile: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cuda11
Context: tools/ci_build/github/linux/docker
DockerBuildArgs: "--network=host --build-arg POLICY=manylinux_2_28 --build-arg PLATFORM=x86_64 --build-arg PREPEND_PATH=/usr/local/cuda/bin --build-arg LD_LIBRARY_PATH_ARG=/usr/local/lib64 --build-arg DEVTOOLSET_ROOTPATH=/usr --build-arg BUILD_UID=$( id -u )"
Repository: onnxruntimecuda11build
- task: CmdLine@2
inputs:
script: |
set -e -x
mkdir -p $HOME/.onnx
docker run --gpus all --rm \
--volume $(Build.SourcesDirectory):/onnxruntime_src \
--volume $(Build.BinariesDirectory)/Release:/build/Release \
--volume /data/models:/build/models:ro \
--volume $HOME/.onnx:/home/onnxruntimedev/.onnx \
--volume /data/onnx:/data/onnx \
onnxruntimecuda11build \
/bin/bash -c "
set -ex; \
cp /onnxruntime_src/tools/ci_build/github/linux/docker/scripts/manylinux/requirements.txt /tmp/requirements.txt; \
ln -s /opt/python/cp38-cp38/bin/python3 /tmp/python3; \
/tmp/python3 -m pip install -r /tmp/requirements.txt; \
/tmp/python3 -m pip install /build/Release/dist/*.whl; \
cd /build/Release && xargs -a /build/Release/perms.txt chmod a+x; \
cd /onnxruntime_src/java && /onnxruntime_src/java/gradlew cmakeCheck -DcmakeBuildDir=/build/Release -DUSE_CUDA=1; \
cd /tmp; \
/tmp/python3 /onnxruntime_src/tools/ci_build/build.py \
--build_dir /build --config Release --test --skip_submodule_sync --build_shared_lib --parallel --build_wheel --enable_onnx_tests \
--use_cuda --cuda_version=${{variables.common_cuda_version}} --cuda_home=/usr/local/cuda --cudnn_home=/usr/local/cuda \
--enable_pybind --build_java --ctest_path '' "
- template: templates/clean-agent-build-directory-step.yml