From 773e93461172c8cc20f2e746ce720730f11010e1 Mon Sep 17 00:00:00 2001 From: Ammar ELWazir Date: Fri, 15 Mar 2024 11:18:55 -0500 Subject: [PATCH] Update continuous_integration.yml (#638) * Update continuous_integration.yml Adding a more stable docker image to use * Fixing jobs dependencies * Fixing job image url [ROCm/rocprofiler-sdk commit: 1fa0b512633999d78f7dc7762a6363e1e5174cd3] --- .../workflows/continuous_integration.yml | 50 +++++++++---------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/projects/rocprofiler-sdk/.github/workflows/continuous_integration.yml b/projects/rocprofiler-sdk/.github/workflows/continuous_integration.yml index 471579e7a0..4456c3b026 100644 --- a/projects/rocprofiler-sdk/.github/workflows/continuous_integration.yml +++ b/projects/rocprofiler-sdk/.github/workflows/continuous_integration.yml @@ -24,20 +24,6 @@ env: PATH: "/usr/bin:$PATH" jobs: - get_latest_mainline_build_number: - # Run job on vega20 instead of mi200 as mi200 is unstable, as per ammar's instructions. - # TODO: Change it back when re-enabling on mi200 - #runs-on: mi200 - runs-on: vega20 - - outputs: - LATEST_BUILD_NUMBER: ${{ steps.get_build_number.outputs.LATEST_BUILD_NUMBER }} - - steps: - - id: get_build_number - run: echo "LATEST_BUILD_NUMBER=$(wget -qO- 'http://rocm-ci.amd.com/job/compute-rocm-dkms-component-staging-hip/lastSuccessfulBuild/buildNumber')" >> $GITHUB_OUTPUT - - # run: echo "LATEST_BUILD_NUMBER=$(wget -qO- 'http://rocm-ci.amd.com/job/compute-rocm-dkms-component-staging-hip/lastSuccessfulBuild/buildNumber')" >> $GITHUB_OUTPUT # Changed job name from mi200-ubuntu to vega20-ubuntu # TODO: Change it back when re-enabling on mi200 vega20-ubuntu: @@ -70,14 +56,20 @@ jobs: # TODO: Uncomment this when re-enabling tests on the mi200 as it contains --memory and --cpus flag for the mi200. Remove these 2 options when running on vega20. # vega20 machine only has 24 cpus available. # container: - # image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-component-staging-hip:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1 + # # TODO(aelwazir): Adding multiple os distros + # image: evuedsoacr.azurecr.io/ml-lang-comp-us/rocm-tools/rocm-rocprofiler-sdk-staging-base:latest # options: --memory=128g --cpus=32 --ipc=host --device=/dev/kfd --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined + # credentials: + # username: ${{ secrets.DOCKER_USERNAME }} + # password: ${{ secrets.DOCKER_PASSWORD }} container: - image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-component-staging-hip:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1 + # TODO(aelwazir): Adding multiple os distros + image: evuedsoacr.azurecr.io/ml-lang-comp-us/rocm-tools/rocm-rocprofiler-sdk-staging-base:latest options: --ipc=host --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined - - needs: get_latest_mainline_build_number + credentials: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} steps: - uses: actions/checkout@v4 @@ -201,14 +193,20 @@ jobs: # TODO: Uncomment this when re-enabling tests on the mi200 as it contains --memory and --cpus flag for the mi200. Remove these 2 options when running on vega20. # vega20 machine only has 24 cpus available. container: - image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-component-staging-hip:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1 + # TODO(aelwazir): Adding multiple os distros + image: evuedsoacr.azurecr.io/ml-lang-comp-us/rocm-tools/rocm-rocprofiler-sdk-staging-base:latest options: --ipc=host --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined + credentials: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} # container: - # image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-component-staging-hip:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1 + # # TODO(aelwazir): Adding multiple os distros + # image: evuedsoacr.azurecr.io/ml-lang-comp-us/rocm-tools/rocm-rocprofiler-sdk-staging-base:latest # options: --memory=128g --cpus=32 --ipc=host --device=/dev/kfd --device=/dev/dri${{ matrix.device }} --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined - - needs: get_latest_mainline_build_number + # credentials: + # username: ${{ secrets.DOCKER_USERNAME }} + # password: ${{ secrets.DOCKER_PASSWORD }} steps: - name: Patch Git @@ -451,10 +449,12 @@ jobs: GIT_DISCOVERY_ACROSS_FILESYSTEM: 1 container: - image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-component-staging-hip:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1 + # TODO(aelwazir): Adding multiple os distros + image: evuedsoacr.azurecr.io/ml-lang-comp-us/rocm-tools/rocm-rocprofiler-sdk-staging-base:latest options: --privileged --ipc=host --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined - - needs: get_latest_mainline_build_number + credentials: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} steps: - uses: actions/checkout@v4