ROCm/.azuredevops/components/rccl.yml

parameters:
- name: checkoutRepo
  type: string
  default: 'self'
- name: checkoutRef
  type: string
  default: ''
- name: aptPackages
  type: object
  default:
    - cmake
    - git
    - googletest
    - libboost-program-options-dev
    - libdrm-dev
    - libfftw3-dev
    - libnuma-dev
    - libstdc++-12-dev
    - ninja-build
    - python3-pip
- name: rocmDependencies
  type: object
  default:
    - aomp
    - aomp-extras
    - clr
    - HIPIFY
    - llvm-project
    - rocm-cmake
    - rocm-core
    - rocm_smi_lib
    - rocminfo
    - rocprofiler-register
    - ROCR-Runtime
    - roctracer
- name: rocmTestDependencies
  type: object
  default:
    - aomp
    - aomp-extras
    - clr
    - HIPIFY
    - llvm-project
    - rocm-cmake
    - rocm-core
    - rocm_smi_lib
    - rocminfo
    - rocprofiler-register
    - ROCR-Runtime
    - roctracer

jobs:
- job: rccl
  variables:
  - group: common
  - template: /.azuredevops/variables-global.yml
  - name: HIP_ROCCLR_HOME
    value: $(Build.BinariesDirectory)/rocm
  pool: ${{ variables.MEDIUM_BUILD_POOL }}
  workspace:
    clean: all
  strategy:
    matrix:
      gfx942:
        JOB_GPU_TARGET: gfx942
  steps:
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
    parameters:
      aptPackages: ${{ parameters.aptPackages }}
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
    parameters:
      checkoutRepo: ${{ parameters.checkoutRepo }}
      submoduleBehaviour: recursive
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
    parameters:
      checkoutRef: ${{ parameters.checkoutRef }}
      dependencyList: ${{ parameters.rocmDependencies }}
      gpuTarget: $(JOB_GPU_TARGET)
  - script: chmod +x $(Agent.BuildDirectory)/rocm/bin/hipify-perl
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
    parameters:
      extraBuildFlags: >-
        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
        -DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
        -DCMAKE_BUILD_TYPE=Release
        -DROCM_PATH=$(Agent.BuildDirectory)/rocm
        -DBUILD_TESTS=ON
        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
        -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
        -GNinja
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
    parameters:
      gpuTarget: $(JOB_GPU_TARGET)
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
    parameters:
      gpuTarget: $(JOB_GPU_TARGET)
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
    parameters:
      aptPackages: ${{ parameters.aptPackages }}
      gpuTarget: $(JOB_GPU_TARGET)
      extraEnvVars:
        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
      installLatestCMake: true

- job: rccl_testing
  timeoutInMinutes: 120
  dependsOn: rccl
  condition: and(succeeded(), eq(variables.ENABLE_GFX942_TESTS, 'true'), not(containsValue(split(variables.DISABLED_GFX942_TESTS, ','), variables['Build.DefinitionName'])))
  variables:
  - group: common
  - template: /.azuredevops/variables-global.yml
  pool: $(JOB_TEST_POOL)
  workspace:
    clean: all
  strategy:
    matrix:
      gfx942:
        JOB_GPU_TARGET: gfx942
        JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
  steps:
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
    parameters:
      aptPackages: ${{ parameters.aptPackages }}
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
    parameters:
      gpuTarget: $(JOB_GPU_TARGET)
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
    parameters:
      checkoutRef: ${{ parameters.checkoutRef }}
      dependencyList: ${{ parameters.rocmTestDependencies }}
      gpuTarget: $(JOB_GPU_TARGET)
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
    parameters:
      componentName: rccl
      testDir: '$(Agent.BuildDirectory)/rocm/bin'
      testExecutable: './rccl-UnitTests'
      testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
    parameters:
      aptPackages: ${{ parameters.aptPackages }}
      environment: test
      gpuTarget: $(JOB_GPU_TARGET)