Geo Min
f9a957bbab
* First commit for rccl multi node test workflow * Adding workflow dispatch * Added branch based pull trigger * Changed typo in branch name * Add input variables to push * Removed input variables to push * Added self hosted runner for Vultr cloud * Skipping build and only running test * Changed test runner label name * Made changes to executable paths in test script * Made changes to run * Made changes to cd into cvs dir * This is a dummy commit * Added cmake options * Modified build options * Commiting build changes * Adding rccl and rccl-tests * Re-ordering rccl and rccl-tests * adding --global command * modified cmake command * modified script paths * Testing OIDC for rccl repo * Testing OIDC for rccl repo * Testing build and upload workflow * use default env variable for AMDGPU families on push workflow trigger * Adding cleanup and correct role * Adding additional yml files * Fixing typo'; * Adding new sha * Adding correct gpu target * Adding back venv bin activate * Adding workflow dispatch for tests * Testing * Adding cat * Adding cat * Adding rocm dir change * Adding checkout * cat with sudo * rccl checkout * correcting branch * removing sudo * trying to adjust correct path' * Adding output dir path * Use docker container with pre-installed MPI * Adding back build steps * Fixing SHA * Adding exclusion logic: * Adding test * Adding CI check * Removing testing * Limit to build only rccl, rccl-tests and required dependencies * Adding test * Removing test * Removing quote * Reverting test * PR comments --------- Co-authored-by: arravikum <arravikum@amd.com> Co-authored-by: Marius Brehler <marius.brehler@amd.com>
82 lines
2.4 KiB
YAML
82 lines
2.4 KiB
YAML
name: TheRock CI for rccl
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- develop
|
|
workflow_dispatch:
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
concurrency:
|
|
# A PR number if a pull request and otherwise the commit hash. This cancels
|
|
# queued and in-progress runs for the same PR (presubmit) or commit
|
|
# (postsubmit). The workflow name is prepended to avoid conflicts between
|
|
# different workflows.
|
|
group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
setup:
|
|
runs-on: ubuntu-24.04
|
|
env:
|
|
# The commit being checked out is the merge commit for a PR. Its first
|
|
# parent will be the tip of the base branch.
|
|
BASE_REF: HEAD^
|
|
outputs:
|
|
enable_therock_ci: ${{ steps.configure.outputs.enable_therock_ci }}
|
|
steps:
|
|
- name: "Checking out repository"
|
|
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
|
|
with:
|
|
# We need the parent commit to do a diff
|
|
fetch-depth: 2
|
|
|
|
- name: "Configuring CI options"
|
|
id: configure
|
|
run: python .github/scripts/therock_configure_ci.py
|
|
|
|
therock-ci-linux:
|
|
name: TheRock CI Linux
|
|
needs: setup
|
|
if: ${{ needs.setup.outputs.enable_therock_ci == 'true' }}
|
|
permissions:
|
|
contents: read
|
|
id-token: write
|
|
uses: ./.github/workflows/therock-ci-linux.yml
|
|
secrets: inherit
|
|
with:
|
|
amdgpu_families: "gfx94X-dcgpu"
|
|
extra_cmake_options: >
|
|
-DTHEROCK_ENABLE_ALL=OFF
|
|
-DTHEROCK_BUILD_TESTING=ON
|
|
-DTHEROCK_BUNDLE_SYSDEPS=ON
|
|
-DTHEROCK_ENABLE_COMM_LIBS=ON
|
|
-DTHEROCK_ENABLE_ROCPROFV3=ON
|
|
-DTHEROCK_USE_EXTERNAL_RCCL=ON
|
|
-DTHEROCK_USE_EXTERNAL_RCCL_TESTS=ON
|
|
-DTHEROCK_RCCL_SOURCE_DIR=./rccl
|
|
-DTHEROCK_RCCL_TESTS_SOURCE_DIR=./rccl-tests
|
|
-DTHEROCK_ENABLE_MPI=ON
|
|
|
|
therock_ci_summary:
|
|
name: TheRock CI Summary
|
|
if: always()
|
|
needs:
|
|
- setup
|
|
- therock-ci-linux
|
|
runs-on: ubuntu-24.04
|
|
steps:
|
|
- name: Output failed jobs
|
|
run: |
|
|
echo '${{ toJson(needs) }}'
|
|
FAILED_JOBS="$(echo '${{ toJson(needs) }}' \
|
|
| jq --raw-output \
|
|
'map_values(select(.result!="success" and .result!="skipped")) | keys | join(",")' \
|
|
)"
|
|
if [[ "${FAILED_JOBS}" != "" ]]; then
|
|
echo "The following jobs failed: ${FAILED_JOBS}"
|
|
exit 1
|
|
fi
|