onnxruntime/tools/ci_build/github/azure-pipelines/linux-gpu-ci-pipeline.yml
Yi Zhang aa9fbed3d4
Add compilation cache for Linux GPU (#13995)
### Description
<!-- Describe your changes. -->



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2022-12-16 16:38:12 +08:00

148 lines
6.4 KiB
YAML

resources:
repositories:
- repository: manylinux
type: Github
endpoint: Microsoft
name: pypa/manylinux
ref: 1a61614cabfd6b91c6afd6d9e172cc5b838c65fe
jobs:
- job: Linux_Build
timeoutInMinutes: 120
variables:
skipComponentGovernanceDetection: true
CCACHE_DIR: $(Pipeline.Workspace)/ccache
workspace:
clean: all
pool: Linux-CPU-2019
steps:
- task: mspremier.PostBuildCleanup.PostBuildCleanup-task.PostBuildCleanup@3
displayName: 'Clean Agent Directories'
condition: always()
- checkout: self
clean: true
submodules: none
- template: templates/get-docker-image-steps.yml
parameters:
Dockerfile: tools/ci_build/github/linux/docker/Dockerfile.manylinux2014_cuda11
Context: tools/ci_build/github/linux/docker
DockerBuildArgs: "--network=host --build-arg POLICY=manylinux2014 --build-arg PLATFORM=x86_64 --build-arg BASEIMAGE=nvidia/cuda:11.6.2-cudnn8-devel-centos7 --build-arg DEVTOOLSET_ROOTPATH=/opt/rh/devtoolset-11/root --build-arg PREPEND_PATH=/opt/rh/devtoolset-11/root/usr/bin: --build-arg LD_LIBRARY_PATH_ARG=/opt/rh/devtoolset-11/root/usr/lib64:/opt/rh/devtoolset-11/root/usr/lib:/opt/rh/devtoolset-11/root/usr/lib64/dyninst:/opt/rh/devtoolset-11/root/usr/lib/dyninst:/usr/local/lib64 --build-arg BUILD_UID=$( 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 CC=/opt/rh/devtoolset-11/root/usr/bin/cc -e CXX=/opt/rh/devtoolset-11/root/usr/bin/c++ -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=11.6 --cuda_home=/usr/local/cuda-11.6 --cudnn_home=/usr/local/cuda-11.6 \
--enable_cuda_profiling \
--enable_pybind --build_java \
--use_cache \
--cmake_extra_defines CMAKE_CUDA_HOST_COMPILER=/opt/rh/devtoolset-11/root/usr/bin/cc CMAKE_CUDA_ARCHITECTURES=75; \
ccache -s"
workingDirectory: $(Build.SourcesDirectory)
- task: CmdLine@2
inputs:
script: |
rm -rf $(Build.BinariesDirectory)/Release/onnxruntime $(Build.BinariesDirectory)/Release/pybind11 $(Build.BinariesDirectory)/Release/_deps
rm -f $(Build.BinariesDirectory)/Release/models
rm -rf $(Build.BinariesDirectory)/Release/_deps
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'
- task: CmdLine@2
inputs:
script: |
set -e -x
# We assume the machine doesn't have gcc and python development header files
sudo rm -f /build /onnxruntime_src
sudo ln -s $(Build.SourcesDirectory) /onnxruntime_src
python3 -m pip uninstall -y ort-nightly-gpu ort-nightly onnxruntime onnxruntime-gpu onnxruntime-training onnxruntime-directml ort-nightly-directml onnx -qq
cp $(Build.SourcesDirectory)/tools/ci_build/github/linux/docker/scripts/manylinux/requirements.txt $(Build.BinariesDirectory)/requirements.txt
# Test ORT with the latest ONNX release.
sed -i "s/git+http:\/\/github\.com\/onnx\/onnx.*/onnx/" $(Build.BinariesDirectory)/requirements.txt
python3 -m pip install -r $(Build.BinariesDirectory)/requirements.txt
python3 -m pip install $(Build.BinariesDirectory)/Release/dist/*.whl
ln -s /data/models $(Build.BinariesDirectory)
cd $(Build.BinariesDirectory)/Release
# Restore file permissions
xargs -a $(Build.BinariesDirectory)/Release/perms.txt chmod a+x
cd $(Build.SourcesDirectory)/java
/usr/local/gradle/bin/gradle "cmakeCheck" "-DcmakeBuildDir=$(Build.BinariesDirectory)/Release" "-DUSE_CUDA=1"
cd /tmp
python3 $(Build.SourcesDirectory)/tools/ci_build/build.py \
--build_dir $(Build.BinariesDirectory) --cmake_generator Ninja \
--config Release --test \
--skip_submodule_sync \
--build_shared_lib \
--parallel \
--build_wheel \
--enable_onnx_tests --use_cuda --cuda_version=11.6 --cuda_home=/usr/local/cuda-11.6 --cudnn_home=/usr/local/cuda-11.6 \
--enable_pybind --build_java --ctest_path ''
- template: templates/clean-agent-build-directory-step.yml