Use intersphinx links for deep learning (#5859)

* Use intersphinx links for deep learning

* Update deep-learning-rocm.rst

remove Taichi

* Update deep-learning-rocm.rst

Change Install link to "link"

* Apply suggestion from @randyh62

OK

.azuredevops/ci-builds/aomp-mainline.yml

@@ -1,42 +0,0 @@
-variables:
-- group: common
-- template: /.azuredevops/variables-global.yml
-
-resources:
-  repositories:
-  - repository: aomp_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/aomp
-    ref: amd-mainline
-  - repository: aomp-extras_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/aomp-extras
-    ref: amd-mainline
-  - repository: flang_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/flang
-    ref: amd-mainline
-  - repository: llvm-project_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/llvm-project
-    ref: amd-mainline
-  pipelines:
-  - pipeline: rocr-runtime_pipeline
-    source: \ROCR-Runtime
-    trigger:
-      branches:
-        include:
-        - amd-mainline
-# this job will only be triggered after successful build sequence of llvm-project and ROCR-Runtime
-
-trigger: none
-pr: none
-
-jobs:
-  - template: ${{ variables.CI_COMPONENT_PATH }}/aomp.yml
-    parameters:
-      checkoutRepo: aomp_repo

.azuredevops/components/AMDMIGraphX.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: AMDMIGraphX
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+# - name: sparseCheckoutDir
+#   type: string
+#   default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -93,7 +112,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: AMDMIGraphX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -121,6 +144,8 @@ jobs:
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         extraBuildFlags: >-
@@ -146,12 +171,12 @@ jobs:
         gpuTarget: ${{ job.target }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: AMDMIGraphX_test_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    dependsOn: AMDMIGraphX_build_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
         eq(${{ parameters.aggregatePipeline }}, False)
       )
     variables:
@@ -183,6 +208,8 @@ jobs:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: CMake@1
       displayName: MIGraphXTest CMake Flags
       inputs:
@@ -199,7 +226,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
-        componentName: AMDMIGraphX
+        componentName: ${{ parameters.componentName }}
         testExecutable: make
         testParameters: -j$(nproc) check
         testPublishResults: false

.azuredevops/components/HIP.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hip_clr_combined
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -35,93 +54,24 @@ parameters:
   type: object
   default:
     - llvm-project
-
+    - ROCR-Runtime
-# hip and clr are tightly-coupled
-# run this same template for both repos
-# any changes for clr should just trigger HIP pipeline
-# similarly for hipother repo, for Nvidia backend
 
 - name: jobMatrix
   type: object
   default:
     buildJobs:
-      - { os: ubuntu2204, packageManager: apt }
+      - { os: ubuntu2204, packageManager: apt, platform: amd }
-      - { os: almalinux8, packageManager: dnf }
+      - { os: ubuntu2204, packageManager: apt, platform: nvidia }
+      - { os: almalinux8, packageManager: dnf, platform: amd }
+      - { os: almalinux8, packageManager: dnf, platform: nvidia }
 
-# HIP with AMD backend
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hip_clr_combined_${{ job.os }}_amd
+  - job: ${{ parameters.componentName }}_${{ job.os }}_${{ job.platform }}
-    pool:
+    ${{ if parameters.buildDependsOn }}:
-      vmImage: 'ubuntu-22.04'
+      dependsOn:
-    ${{ if eq(job.os, 'almalinux8') }}:
+        - ${{ each build in parameters.buildDependsOn }}:
-      container:
+          - ${{ build }}_${{ job.os }}
-        image: rocmexternalcicd.azurecr.io/manylinux228:latest
-        endpoint: ContainerService3
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        packageManager: ${{ job.packageManager }}
-  # checkout triggering repo (either HIP or clr)
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-      parameters:
-        checkoutRepo: ${{ parameters.checkoutRepo }}
-  # if this is triggered by HIP repo, matching repo is clr
-  # if this is triggered by clr repo, matching repo is HIP
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-      parameters:
-        checkoutRepo: matching_repo
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-      parameters:
-        checkoutRepo: hipother_repo
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependenciesAMD }}
-        aggregatePipeline: ${{ parameters.aggregatePipeline }}
-        os: ${{ job.os }}
-  # compile clr
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-      parameters:
-        componentName: clr
-        cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
-        os: ${{ job.os }}
-        useAmdclang: false
-        extraBuildFlags: >-
-          -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
-          -DHIP_PLATFORM=amd
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
-          -DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
-          -DCLR_BUILD_HIP=ON
-          -DCLR_BUILD_OCL=ON
-          -GNinja
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-      parameters:
-        artifactName: amd
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-      parameters:
-        artifactName: amd
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    #   parameters:
-    #     aptPackages: ${{ parameters.aptPackages }}
-    #     pipModules: ${{ parameters.pipModules }}
-    #     environment: amd
-
-# HIP with Nvidia backend
-- ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hip_clr_combined_${{ job.os }}_nvidia
     pool:
       vmImage: 'ubuntu-22.04'
     ${{ if eq(job.os, 'almalinux8') }}:
@@ -140,49 +90,45 @@ jobs:
         pipModules: ${{ parameters.pipModules }}
         packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  # checkout triggering repo (either HIP or clr)
+    # full checkout of rocm-systems superrepo, we need clr, hip, and hipother
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
-  # if this is triggered by HIP repo, matching repo is clr
+        # sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
-  # if this is triggered by clr repo, matching repo is HIP
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-      parameters:
-        checkoutRepo: matching_repo
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-      parameters:
-        checkoutRepo: hipother_repo
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependenciesNvidia }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         os: ${{ job.os }}
-    - script: 'ls -1R $(Agent.BuildDirectory)/rocm'
+        ${{ if eq(job.platform, 'amd') }}:
-      displayName: 'Artifact listing'
+          dependencyList: ${{ parameters.rocmDependenciesAMD }}
-  # compile clr
+        ${{ elseif eq(job.platform, 'nvidia') }}:
+          dependencyList: ${{ parameters.rocmDependenciesNvidia }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         componentName: clr
-        cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
+        cmakeBuildDir: $(Agent.BuildDirectory)/s/projects/clr/build
-        cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
+        cmakeSourceDir: $(Agent.BuildDirectory)/s/projects/clr
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
-          -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-          -DHIP_PLATFORM=nvidia
+          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
+          -DHIP_COMMON_DIR=$(Agent.BuildDirectory)/s/projects/hip
+          -DHIPNV_DIR=$(Agent.BuildDirectory)/s/projects/hipother/hipnv
+          -DHIP_PLATFORM=${{ job.platform }}
           -DCLR_BUILD_HIP=ON
-          -DCLR_BUILD_OCL=OFF
+          -DCLR_BUILD_OCL=ON
-          -DHIPNV_DIR=$(Build.SourcesDirectory)/hipother/hipnv
           -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        artifactName: ${{ job.platform }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
-        artifactName: nvidia
+        artifactName: ${{ job.platform }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    #   parameters:
-    #     aptPackages: ${{ parameters.aptPackages }}
-    #     pipModules: ${{ parameters.pipModules }}
-    #     environment: nvidia

.azuredevops/components/HIPIFY.yml

@@ -79,7 +79,7 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
         packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
     - task: Bash@3
       displayName: Add lit to PATH
       inputs:

.azuredevops/components/MIOpen.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: MIOpen
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -74,16 +93,37 @@ parameters:
         target: gfx942
       - gfx90a:
         target: gfx90a
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - MIVisionX:
+      name: MIVisionX
+      checkoutRepo: mivisionx_repo
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - MIOpen_build
+    - AMDMIGraphX:
+      name: AMDMIGraphX
+      checkoutRepo: amdmigraphx_repo
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - MIOpen_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: MIOpen_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     - name: ROCM_PATH
       value: $(Agent.BuildDirectory)/rocm
-    pool: ${{ variables.HIGH_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
     workspace:
       clean: all
     steps:
@@ -91,10 +131,12 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/miopen-get-ck-build.yml
       parameters:
         gpuTarget: ${{ job.target }}
@@ -104,11 +146,14 @@ jobs:
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: Bash@3
       displayName: Build and install other dependencies
+      retryCountOnTaskFailure: 3
       inputs:
         targetType: inline
-        workingDirectory: $(Build.SourcesDirectory)
+        workingDirectory: $(Agent.BuildDirectory)/s
         script: |
           sed -i '/composable_kernel/d' requirements.txt
           mkdir -p $(Agent.BuildDirectory)/miopen-deps
@@ -130,8 +175,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -143,9 +190,9 @@ jobs:
           - miopen-deps
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: MIOpen_test_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
     timeoutInMinutes: 180
-    dependsOn: MIOpen_build_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -165,10 +212,12 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/miopen-get-ck-build.yml
       parameters:
@@ -178,11 +227,14 @@ jobs:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: Bash@3
       displayName: Build and install other dependencies
+      retryCountOnTaskFailure: 3
       inputs:
         targetType: inline
-        workingDirectory: $(Build.SourcesDirectory)
+        workingDirectory: $(Agent.BuildDirectory)/s
         script: |
           sed -i '/composable_kernel/d' requirements.txt
           mkdir -p $(Agent.BuildDirectory)/miopen-deps
@@ -193,7 +245,7 @@ jobs:
       displayName: 'MIOpen Test CMake Flags'
       inputs:
         cmakeArgs: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Build.SourcesDirectory)/bin;$(Agent.BuildDirectory)/miopen-deps
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/s/bin;$(Agent.BuildDirectory)/miopen-deps
           -DCMAKE_INSTALL_PREFIX=$(Agent.BuildDirectory)/rocm
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
@@ -203,19 +255,19 @@ jobs:
           -DBUILD_DEV=OFF
           -DMIOPEN_USE_MLIR=ON
           -DMIOPEN_GPU_SYNC=OFF
-          ..
+          $(Agent.BuildDirectory)/s
     - task: Bash@3
       displayName: 'MIOpen Test Build'
       inputs:
         targetType: inline
+        workingDirectory: build
         script: |
           cmake --build . --target tests -- -j$(nproc)
-        workingDirectory: $(Build.SourcesDirectory)/build
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
-        componentName: MIOpen
+        componentName: ${{ parameters.componentName }}
-        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "test_rnn_seq_api|GPU_Conv2dTuningAsm_FP32"'
+        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "test_rnn_seq_api|GPU_Conv2dTuningAsm_FP32|GPU_Conv2dTuningAsmBwdWrw_FP32"'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
@@ -224,3 +276,15 @@ jobs:
         gpuTarget: ${{ job.target }}
         extraCopyDirectories:
           - miopen-deps
+
+# - ${{ if parameters.triggerDownstreamJobs }}:
+#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+#         parameters:
+#           checkoutRepo: ${{ component.checkoutRepo }}
+#           # sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+#           buildDependsOn: ${{ component.buildDependsOn }}
+#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+#           triggerDownstreamJobs: true
+#           unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/MIVisionX.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: MIVisionX
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+# - name: sparseCheckoutDir
+#   type: string
+#   default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -60,6 +79,7 @@ parameters:
 - name: rocmTestDependencies
   type: object
   default:
+    - aomp
     - clr
     - half
     - hipBLAS-common
@@ -88,7 +108,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: MIVisionX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -110,6 +134,8 @@ jobs:
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         extraBuildFlags: >-
@@ -131,12 +157,12 @@ jobs:
     #     gpuTarget: ${{ job.target }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: MIVisionX_test_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    dependsOn: MIVisionX_build_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
         eq(${{ parameters.aggregatePipeline }}, False)
       )
     variables:
@@ -161,6 +187,8 @@ jobs:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: Bash@3
       displayName: Build MIVisionX tests
       inputs:
@@ -174,7 +202,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
-        componentName: MIVisionX
+        componentName: ${{ parameters.componentName }}
         testDir: 'mivisionx-tests'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:

.azuredevops/components/ROCR-Runtime.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: ROCR-Runtime
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -18,6 +37,7 @@ parameters:
     - libdrm-dev
     - libelf-dev
     - libnuma-dev
+    - libsimde-dev
     - ninja-build
     - pkg-config
 - name: rocmDependencies
@@ -28,8 +48,8 @@ parameters:
 - name: rocmTestDependencies
   type: object
   default:
+    - amdsmi
     - llvm-project
-    - rocm_smi_lib
     - rocprofiler-register
 
 - name: jobMatrix
@@ -45,6 +65,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: ROCR_Runtime_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     pool:
       vmImage: 'ubuntu-22.04'
     ${{ if eq(job.os, 'almalinux8') }}:
@@ -65,14 +89,18 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         os: ${{ job.os }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -82,109 +110,112 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     #   parameters:
     #     aptPackages: ${{ parameters.aptPackages }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: ROCR_Runtime_test_${{ job.os }}_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: ROCR_Runtime_build_${{ job.os }}
+    - job: ROCR_Runtime_test_${{ job.os }}_${{ job.target }}
-    condition:
+      dependsOn: ROCR_Runtime_build_${{ job.os }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        packageManager: ${{ job.packageManager }}
+          aptPackages: ${{ parameters.aptPackages }}
-    - task: Bash@3
+          packageManager: ${{ job.packageManager }}
-      displayName: Install libhwloc5
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      inputs:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-        targetType: 'inline'
+        parameters:
-        script: |
+          os: ${{ job.os }}
-          wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc5_1.11.12-3_amd64.deb
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-          wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc-dev_1.11.12-3_amd64.deb
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-          sudo apt install -y --allow-downgrades ./libhwloc5_1.11.12-3_amd64.deb ./libhwloc-dev_1.11.12-3_amd64.deb
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          checkoutRef: ${{ parameters.checkoutRef }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-      parameters:
+          gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
+          os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+          ${{ if parameters.triggerDownstreamJobs }}:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+        parameters:
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-        gpuTarget: ${{ job.target }}
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
-        os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+        parameters:
-      parameters:
+          runRocminfo: false
-        checkoutRepo: ${{ parameters.checkoutRepo }}
+      - task: Bash@3
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+        displayName: Build kfdtest
-      parameters:
+        inputs:
-        runRocminfo: false
+          targetType: 'inline'
-    - task: Bash@3
+          workingDirectory: $(Agent.BuildDirectory)/s/libhsakmt/tests/kfdtest
-      displayName: Build kfdtest
+          script: |
-      inputs:
+            if [ -e /opt/rh/gcc-toolset-14/enable ]; then
-        targetType: 'inline'
+              source /opt/rh/gcc-toolset-14/enable
-        workingDirectory: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest
+            fi
-        script: |
+            mkdir build && cd build
-          if [ -e /opt/rh/gcc-toolset-14/enable ]; then
+            cmake -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm ..
-            source /opt/rh/gcc-toolset-14/enable
+            make
-          fi
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-          mkdir build && cd build
+        parameters:
-          cmake -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm ..
+          componentName: kfdtest
-          make
+          testExecutable: BIN_DIR=$(Agent.BuildDirectory)/s/libhsakmt/tests/kfdtest/build ./run_kfdtest.sh
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          testParameters: '-p core --gtest_output=xml:./test_output.xml --gtest_color=yes'
-      parameters:
+          testDir: $(Agent.BuildDirectory)/s/libhsakmt/tests/kfdtest/scripts
-        componentName: kfdtest
+          os: ${{ job.os }}
-        testExecutable: BIN_DIR=$(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/build ./run_kfdtest.sh
+      - task: Bash@3
-        testParameters: '-p core --gtest_output=xml:./test_output.xml --gtest_color=yes'
+        displayName: Build rocrtst
-        testDir: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/scripts
+        inputs:
-        os: ${{ job.os }}
+          targetType: 'inline'
-    - task: Bash@3
+          workingDirectory: $(Agent.BuildDirectory)/s/rocrtst/suites/test_common
-      displayName: Build rocrtst
+          script: |
-      inputs:
+            echo $(Agent.BuildDirectory)/s/rocrtst/thirdparty/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
-        targetType: 'inline'
+            sudo cat /etc/ld.so.conf.d/rocm-ci.conf
-        workingDirectory: $(Build.SourcesDirectory)/rocrtst/suites/test_common
+            sudo ldconfig -v
-        script: |
+            ldconfig -p
-          if [ -e /opt/rh/gcc-toolset-14/enable ]; then
+            if [ -e /opt/rh/gcc-toolset-14/enable ]; then
-            source /opt/rh/gcc-toolset-14/enable
+              source /opt/rh/gcc-toolset-14/enable
-          fi
+            fi
-          BASE_CLANG_DIR=$(Agent.BuildDirectory)/rocm/llvm/lib/clang
+            BASE_CLANG_DIR=$(Agent.BuildDirectory)/rocm/llvm/lib/clang
-          export NEWEST_CLANG_VER=$(ls -1 $BASE_CLANG_DIR | sort -V | tail -n 1)
+            export NEWEST_CLANG_VER=$(ls -1 $BASE_CLANG_DIR | sort -V | tail -n 1)
-          mkdir build && cd build
+            mkdir build && cd build
-          cmake .. \
+            cmake .. \
-            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm \
+              -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm \
-            -DTARGET_DEVICES=${{ job.target }} \
+              -DTARGET_DEVICES=${{ job.target }} \
-            -DROCM_DIR=$(Agent.BuildDirectory)/rocm \
+              -DROCM_DIR=$(Agent.BuildDirectory)/rocm \
-            -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin \
+              -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin \
-            -DOPENCL_INC_DIR=$BASE_CLANG_DIR/$NEWEST_CLANG_VER/include
+              -DOPENCL_INC_DIR=$BASE_CLANG_DIR/$NEWEST_CLANG_VER/include
-          make
+            make
-          make rocrtst_kernels
+            make rocrtst_kernels
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
+        parameters:
-        componentName: rocrtst
+          componentName: rocrtst
-        testExecutable: ./rocrtst64
+          testExecutable: ./rocrtst64
-        testParameters: '--gtest_filter="-rocrtstNeg.Memory_Negative_Tests:rocrtstFunc.Memory_Max_Mem" --gtest_output=xml:./test_output.xml --gtest_color=yes'
+          testParameters: '--gtest_filter="-rocrtstNeg.Memory_Negative_Tests:rocrtstFunc.Memory_Max_Mem" --gtest_output=xml:./test_output.xml --gtest_color=yes'
-        testDir: $(Build.SourcesDirectory)/rocrtst/suites/test_common/build/${{ job.target }}
+          testDir: $(Agent.BuildDirectory)/s//rocrtst/suites/test_common/build/${{ job.target }}
-        os: ${{ job.os }}
+          os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
+        parameters:
-        aptPackages: ${{ parameters.aptPackages }}
+          aptPackages: ${{ parameters.aptPackages }}
-        environment: test
+          environment: test
-        gpuTarget: ${{ job.target }}
+          gpuTarget: ${{ job.target }}
-  # docker image will be missing libhwloc5
+    # docker image will be missing libhwloc5

.azuredevops/components/ROCmValidationSuite.yml

@@ -86,8 +86,7 @@ jobs:
       value: $(Agent.BuildDirectory)/rocm
     - name: HIP_INC_DIR
       value: $(Agent.BuildDirectory)/rocm
-    pool:
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/Tensile.yml

@@ -33,8 +33,9 @@ parameters:
   type: object
   default:
     - cmake
-    - libmsgpack-dev
+    - libboost-filesystem-dev
     - libboost-program-options-dev
+    - libmsgpack-dev
 - name: pipModules
   type: object
   default:
@@ -170,6 +171,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - task: DownloadPipelineArtifact@2
       displayName: 'Download Pipeline Wheel Files'
+      retryCountOnTaskFailure: 3
       inputs:
         itemPattern: '**/*${{ job.os }}*.whl'
         targetPath: $(Agent.BuildDirectory)

.azuredevops/components/aqlprofile.yml

@@ -0,0 +1,174 @@
+parameters:
+- name: componentName
+  type: string
+  default: aqlprofile
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
+# set to true if doing full build of ROCm stack
+# and dependencies are pulled from same pipeline
+- name: aggregatePipeline
+  type: boolean
+  default: false
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+    - python3-pip
+- name: rocmDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - ROCR-Runtime
+- name: rocmTestDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - ROCR-Runtime
+    - rocprofiler-register
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+    testJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    workspace:
+      clean: all
+    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/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/aqlprofile/cmake_modules
+          -DAQLPROFILE_BUILD_TESTS=ON
+          -DGPU_TARGETS=${{ job.target }}
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
+
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: $(Agent.BuildDirectory)/rocm/share/hsa-amd-aqlprofile/
+          testExecutable: ./run_tests.sh
+          testParameters: ''
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/composable_kernel.yml

@@ -107,6 +107,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
         gpuTarget: ${{ job.target }}
+    # if this artifact name is changed, please also update $ARTIFACT_URL inside miopen-get-ck-build.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
         gpuTarget: ${{ job.target }}

.azuredevops/components/copyHIP.yml

@@ -39,4 +39,6 @@ jobs:
       parameters:
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      inputs:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml

.azuredevops/components/hip-tests.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hip-tests
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -60,6 +79,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: hip_tests_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -76,15 +99,18 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     # compile hip-tests
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
-        componentName: hip-tests
+        componentName: ${{ parameters.componentName }}
         cmakeSourceDir: '../catch'
         customBuildTarget: build_tests
         extraBuildFlags: >-
@@ -96,9 +122,12 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -108,52 +137,56 @@ jobs:
         extraEnvVars:
           - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: hip_tests_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    timeoutInMinutes: 240
+    - job: hip_tests_test_${{ job.target }}
-    dependsOn: hip_tests_build_${{ job.target }}
+      timeoutInMinutes: 240
-    condition:
+      dependsOn: hip_tests_build_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          aptPackages: ${{ parameters.aptPackages }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          gpuTarget: ${{ job.target }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+        parameters:
-        gpuTarget: ${{ job.target }}
+          checkoutRef: ${{ parameters.checkoutRef }}
-    - task: Bash@3
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-      displayName: Symlink rocm_agent_enumerator
+          gpuTarget: ${{ job.target }}
-      inputs:
+          ${{ if parameters.triggerDownstreamJobs }}:
-        targetType: inline
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        script: |
+      - task: Bash@3
-          # Assuming that /opt is no longer persistent across runs, test environments are fully ephemeral
+        displayName: Symlink rocm_agent_enumerator
-          sudo mkdir -p /opt/rocm/bin
+        inputs:
-          sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rocm_agent_enumerator /opt/rocm/bin/rocm_agent_enumerator
+          targetType: inline
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          script: |
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+            # Assuming that /opt is no longer persistent across runs, test environments are fully ephemeral
-      parameters:
+            sudo mkdir -p /opt/rocm/bin
-        componentName: hip_tests
+            sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rocm_agent_enumerator /opt/rocm/bin/rocm_agent_enumerator
-        testDir: $(Agent.BuildDirectory)/rocm/share/hip
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
+        parameters:
-        aptPackages: ${{ parameters.aptPackages }}
+          componentName: ${{ parameters.componentName }}
-        environment: test
+          testDir: $(Agent.BuildDirectory)/rocm/share/hip
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        optSymLink: true
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+          optSymLink: true

.azuredevops/components/hipBLAS-common.yml

@@ -51,15 +51,15 @@ parameters:
     buildJobs:
       - { os: ubuntu2204, packageManager: apt }
       - { os: almalinux8, packageManager: dnf }
-# - name: downstreamComponentMatrix
+- name: downstreamComponentMatrix
-#   type: object
+  type: object
-#   default:
+  default:
-#     - hipBLASLt:
+    - hipBLASLt:
-#       name: hipBLASLt
+      name: hipBLASLt
-#       sparseCheckoutDir: projects/hipblaslt
+      sparseCheckoutDir: projects/hipblaslt
-#       skipUnifiedBuild: 'false'
+      skipUnifiedBuild: 'false'
-#       buildDependsOn:
+      buildDependsOn:
-#         - hipBLAS_common_build
+        - hipBLAS_common_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -122,14 +122,14 @@ jobs:
     #     extraEnvVars:
     #       - ROCM_PATH:::/home/user/workspace/rocm
 
-# - ${{ if parameters.triggerDownstreamJobs }}:
+- ${{ if parameters.triggerDownstreamJobs }}:
-#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
-#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
-#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
-#         parameters:
+        parameters:
-#           checkoutRepo: ${{ parameters.checkoutRepo }}
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
-#           buildDependsOn: ${{ component.buildDependsOn }}
+          buildDependsOn: ${{ component.buildDependsOn }}
-#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
-#           triggerDownstreamJobs: true
+          triggerDownstreamJobs: true
-#           unifiedBuild: ${{ parameters.unifiedBuild }}
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/hipBLAS.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipBLAS
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -69,10 +88,30 @@ parameters:
         target: gfx942
       - gfx90a:
         target: gfx90a
+# MIOpen depends on both rocRAND and hipBLAS
+# for a unified build, hipBLAS will be the one to call MIOpen
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - MIOpen:
+      name: MIOpen
+      sparseCheckoutDir: projects/miopen
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - hipBLAS_build
+      unifiedBuild:
+        downstreamAggregateNames: hipBLAS+rocRAND
+        buildDependsOn:
+          - hipBLAS_build
+          - rocRAND_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipBLAS_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -88,6 +127,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aocl.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
@@ -95,6 +135,8 @@ jobs:
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         extraBuildFlags: >-
@@ -109,9 +151,12 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -121,46 +166,67 @@ jobs:
         installAOCL: true
         gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: hipBLAS_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: hipBLAS_build_${{ job.target }}
+    - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        pipModules: ${{ parameters.pipModules }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          pipModules: ${{ parameters.pipModules }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          preTargetFilter: ${{ parameters.componentName }}
-      parameters:
+          gpuTarget: ${{ job.target }}
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          checkoutRef: ${{ parameters.checkoutRef }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-      parameters:
+          gpuTarget: ${{ job.target }}
-        componentName: hipBLAS
+          ${{ if parameters.triggerDownstreamJobs }}:
-        testExecutable: $(Agent.BuildDirectory)/rocm/bin/hipblas-test
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        testParameters: '--yaml hipblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
-      parameters:
+          componentName: ${{ parameters.componentName }}
-        aptPackages: ${{ parameters.aptPackages }}
+          testExecutable: $(Agent.BuildDirectory)/rocm/bin/hipblas-test
-        pipModules: ${{ parameters.pipModules }}
+          testParameters: '--yaml hipblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
-        environment: test
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}
+          ${{ if parameters.unifiedBuild }}:
+            buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
+          ${{ else }}:
+            buildDependsOn: ${{ component.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}

.azuredevops/components/hipBLASLt.yml

@@ -35,9 +35,13 @@ parameters:
     - ccache
     - gfortran
     - git
+    - libboost-filesystem-dev
+    - libboost-program-options-dev
     - libdrm-dev
+    - liblapack-dev
     - libmsgpack-dev
     - libnuma-dev
+    - libopenblas-dev
     - ninja-build
     - python3-pip
     - python3-venv
@@ -46,6 +50,12 @@ parameters:
   default:
     - joblib
     - "packaging>=22.0"
+    - pyyaml
+    - msgpack
+    - simplejson
+    - ujson
+    - orjson
+    - yappi
     - --upgrade
 - name: rocmDependencies
   type: object
@@ -67,6 +77,7 @@ parameters:
     - clr
     - hipBLAS-common
     - llvm-project
+    - rocm-cmake
     - rocminfo
     - rocm_smi_lib
     - rocprofiler-register
@@ -77,28 +88,28 @@ parameters:
   type: object
   default:
     buildJobs:
-      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { pool: rocm-ci_ultra_build_pool, os: ubuntu2204, packageManager: apt, target: gfx942 }
-      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1201 }
-      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1100 }
-      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      #- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1030 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { pool: rocm-ci_ultra_build_pool, os: almalinux8, packageManager: dnf, target: gfx942 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx90a }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1201 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1100 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
+      #- { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-# - name: downstreamComponentMatrix
+- name: downstreamComponentMatrix
-#   type: object
+  type: object
-#   default:
+  default:
-#     - rocBLAS:
+    - rocBLAS:
-#       name: rocBLAS
+      name: rocBLAS
-#       sparseCheckoutDir: projects/rocblas
+      sparseCheckoutDir: projects/rocblas
-#       skipUnifiedBuild: 'false'
+      skipUnifiedBuild: 'false'
-#       buildDependsOn:
+      buildDependsOn:
-#         - hipBLASLt_build
+        - hipBLASLt_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -121,7 +132,7 @@ jobs:
       value: $(Agent.BuildDirectory)/rocm
     - name: DAY_STRING
       value: $[format('{0:ddMMyyyy}', pipeline.startTime)]
-    pool: ${{ variables.ULTRA_BUILD_POOL }}
+    pool: ${{ job.pool }}
     ${{ if eq(job.os, 'almalinux8') }}:
       container:
         image: rocmexternalcicd.azurecr.io/manylinux228:latest
@@ -134,12 +145,16 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
         packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
         sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
@@ -156,19 +171,16 @@ jobs:
         script: |
           echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
           echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
-    # hipBLASLt has a script for gtest and lapack
-    # https://github.com/ROCm/hipBLASLt/blob/develop/deps/CMakeLists.txt
-    # $(Agent.BuildDirectory)/deps is a temporary folder for the build process
-    # $(Agent.BuildDirectory)/s/deps is part of the hipBLASLt repo
     - task: Bash@3
-      displayName: Build and install external dependencies
+      displayName: Build and install LAPACK
       inputs:
         targetType: inline
         script: |
-          mkdir -p $(Agent.BuildDirectory)/deps
+          mkdir -p $(Agent.BuildDirectory)/temp-deps
-          cd $(Agent.BuildDirectory)/deps
+          cd $(Agent.BuildDirectory)/temp-deps
-          cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/s/deps
+          # position-independent LAPACK is required for almalinux8 builds
-          make
+          cmake -DBUILD_GTEST=OFF -DBUILD_LAPACK=ON -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/sparse/projects/hipblaslt/deps
+          make -j
           sudo make install
     - script: |
         mkdir -p $(CCACHE_DIR)
@@ -186,15 +198,21 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}
+        cmakeSourceDir: $(Agent.BuildDirectory)/sparse/projects/hipblaslt
+        cmakeBuildDir: $(Agent.BuildDirectory)/sparse/projects/hipblaslt/build
         extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
           -DCMAKE_INCLUDE_PATH=$(Agent.BuildDirectory)/rocm/llvm/include
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
           -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
           -DCMAKE_C_COMPILER_LAUNCHER=ccache
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DGPU_TARGETS=${{ job.target }}
           -DBUILD_CLIENTS_TESTS=ON
+          -DHIPBLASLT_ENABLE_ROCROLLER=ON
+          -DHIPBLASLT_ENABLE_FETCH=ON
+          -DHIPBLASLT_ENABLE_BLIS=OFF
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
@@ -244,6 +262,7 @@ jobs:
       workspace:
         clean: all
       steps:
+      - checkout: none
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
         parameters:
           aptPackages: ${{ parameters.aptPackages }}
@@ -280,14 +299,14 @@ jobs:
           environment: test
           gpuTarget: ${{ job.target }}
 
-# - ${{ if parameters.triggerDownstreamJobs }}:
+- ${{ if parameters.triggerDownstreamJobs }}:
-#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
-#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
-#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
-#         parameters:
+        parameters:
-#           checkoutRepo: ${{ parameters.checkoutRepo }}
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
-#           buildDependsOn: ${{ component.buildDependsOn }}
+          buildDependsOn: ${{ component.buildDependsOn }}
-#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
-#           triggerDownstreamJobs: true
+          triggerDownstreamJobs: true
-#           unifiedBuild: ${{ parameters.unifiedBuild }}
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/hipFFT.yml

@@ -80,11 +80,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
     ${{ if parameters.buildDependsOn }}:
       dependsOn:
         - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_${{ job.target }} # todo: add OS
+          - ${{ build }}_ubuntu2204_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -141,12 +141,12 @@ jobs:
     #     gpuTarget: ${{ job.target }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ${{ parameters.componentName }}_test_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
         eq(${{ parameters.aggregatePipeline }}, False)
       )
     variables:
@@ -156,6 +156,7 @@ jobs:
     workspace:
       clean: all
     steps:
+    - checkout: none
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/hipRAND.yml

@@ -72,15 +72,15 @@ parameters:
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-# - name: downstreamComponentMatrix
+- name: downstreamComponentMatrix
-#   type: object
+  type: object
-#   default:
+  default:
-#     - rocFFT:
+    - rocFFT:
-#       name: rocFFT
+      name: rocFFT
-#       sparseCheckoutDir: projects/rocfft
+      sparseCheckoutDir: projects/rocfft
-#       skipUnifiedBuild: 'false'
+      skipUnifiedBuild: 'false'
-#       buildDependsOn:
+      buildDependsOn:
-#         - hipRAND_build
+        - hipRAND_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -206,14 +206,14 @@ jobs:
           environment: test
           gpuTarget: ${{ job.target }}
 
-# - ${{ if parameters.triggerDownstreamJobs }}:
+- ${{ if parameters.triggerDownstreamJobs }}:
-#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
-#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
-#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
-#         parameters:
+        parameters:
-#           checkoutRepo: ${{ parameters.checkoutRepo }}
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
-#           buildDependsOn: ${{ component.buildDependsOn }}
+          buildDependsOn: ${{ component.buildDependsOn }}
-#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
-#           triggerDownstreamJobs: true
+          triggerDownstreamJobs: true
-#           unifiedBuild: ${{ parameters.unifiedBuild }}
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/hipSOLVER.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipSOLVER
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -66,12 +85,15 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipSOLVER_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
-    pool:
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
     workspace:
       clean: all
     steps:
@@ -82,18 +104,21 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
   # build external gtest and lapack
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         componentName: external
-        cmakeBuildDir: '$(Build.SourcesDirectory)/deps/build'
+        cmakeBuildDir: '$(Agent.BuildDirectory)/s/deps/build'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/deps'
+        cmakeSourceDir: '$(Agent.BuildDirectory)/s/deps'
         installDir: '$(Pipeline.Workspace)/deps-install'
         extraBuildFlags: >-
           -DBUILD_BOOST=OFF
@@ -112,8 +137,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -123,44 +150,49 @@ jobs:
     #     extraCopyDirectories:
     #       - deps-install
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: hipSOLVER_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: hipSOLVER_build_${{ job.target }}
+    - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          aptPackages: ${{ parameters.aptPackages }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          preTargetFilter: ${{ parameters.componentName }}
-      parameters:
+          gpuTarget: ${{ job.target }}
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          checkoutRef: ${{ parameters.checkoutRef }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-      parameters:
+          gpuTarget: ${{ job.target }}
-        componentName: hipSOLVER
+          ${{ if parameters.triggerDownstreamJobs }}:
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        testExecutable: './hipsolver-test'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        testParameters: '--gtest_filter="*checkin*" --gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
-      parameters:
+          componentName: ${{ parameters.componentName }}
-        aptPackages: ${{ parameters.aptPackages }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        environment: test
+          testExecutable: './hipsolver-test'
-        gpuTarget: ${{ job.target }}
+          testParameters: '--gtest_filter="*checkin*" --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.target }}

.azuredevops/components/hipSPARSE.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipSPARSE
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -14,13 +33,11 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
-    - libboost-program-options-dev
-    - googletest
-    - libfftw3-dev
-    - git
     - gfortran
-    - libgtest-dev
+    - git
+    - libboost-program-options-dev
+    - libfftw3-dev
+    - ninja-build
     - python3-pip
 - name: rocmDependencies
   type: object
@@ -49,19 +66,31 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
-        target: gfx90a
+      #- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
     testJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
+- name: downstreamComponentMatrix
-        target: gfx90a
+  type: object
+  default:
+    - hipSPARSELt:
+      name: hipSPARSELt
+      sparseCheckoutDir: projects/hipsparselt
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - hipSPARSE_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipSPARSE_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -73,42 +102,57 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
         extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
           -DCMAKE_BUILD_TYPE=Release
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
           -DBUILD_CLIENTS_TESTS=ON
           -DBUILD_CLIENTS_SAMPLES=OFF
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
-        artifactName: hipSPARSE
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
-        artifactName: hipSPARSE
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         publish: false
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
       parameters:
-        sourceDir: $(Build.SourcesDirectory)/build/clients
+        sourceDir: $(Agent.BuildDirectory)/s/build/clients
         contentsString: matrices/**
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         artifactName: testMatrices
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     #   parameters:
@@ -116,44 +160,65 @@ jobs:
     #     environment: test
     #     gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: hipSPARSE_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: hipSPARSE_build_${{ job.target }}
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          aptPackages: ${{ parameters.aptPackages }}
-      parameters:
+          packageManager: ${{ job.packageManager }}
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
-      parameters:
+          preTargetFilter: ${{ parameters.componentName }}
-        checkoutRef: ${{ parameters.checkoutRef }}
+          gpuTarget: ${{ job.target }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+          os: ${{ job.os }}
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
-      parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
-        componentName: hipSPARSE
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          gpuTarget: ${{ job.target }}
-        testExecutable: './hipsparse-test'
+          os: ${{ job.os }}
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+          ${{ if parameters.triggerDownstreamJobs }}:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        environment: test
+        parameters:
-        gpuTarget: ${{ job.target }}
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './hipsparse-test'
+          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.target }}
+
+  - ${{ if parameters.triggerDownstreamJobs }}:
+    - ${{ each component in parameters.downstreamComponentMatrix }}:
+      - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+        - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+          parameters:
+            checkoutRepo: ${{ parameters.checkoutRepo }}
+            sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+            buildDependsOn: ${{ component.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+            triggerDownstreamJobs: true
+            unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/hipSPARSELt.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipSPARSELt
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -21,10 +40,12 @@ parameters:
     - gfortran
     - libgfortran5
     - libopenblas-dev
+    - liblapack-dev
 - name: pipModules
   type: object
   default:
     - joblib
+    - msgpack
 - name: rocmDependencies
   type: object
   default:
@@ -33,6 +54,7 @@ parameters:
     - hipSPARSE
     - llvm-project
     - rocBLAS
+    - rocm-cmake
     - rocm_smi_lib
     - rocminfo
     - rocprofiler-register
@@ -46,6 +68,7 @@ parameters:
     - llvm-project
     - hipBLAS-common
     - hipBLASLt
+    - rocm-cmake
     - rocBLAS
     - rocminfo
     - rocprofiler-register
@@ -56,15 +79,17 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
     testJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipSPARSELt_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -86,25 +111,37 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        # ignore sparse checkout for monorepo case, we want access to hipblaslt directory
+        # sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+  # NOTE: content between `---` is for transition support between old/new build systems
+  # and should be removed once transition is complete.
+  # -----------------------------
   # Build and install gtest and lapack
   # $(Pipeline.Workspace)/deps is a temporary folder for the build process
   # $(Pipeline.Workspace)/s/deps is part of the hipSPARSELt repo
-    - script: mkdir $(Pipeline.Workspace)/deps
+    - script: mkdir -p $(Pipeline.Workspace)/deps
       displayName: Create temp folder for external dependencies
   # hipSPARSELt already has a CMake script for external deps, so we can just run that
   # https://github.com/ROCm/hipSPARSELt/blob/develop/deps/CMakeLists.txt
-    - script: cmake $(Pipeline.Workspace)/s/deps
+    - ${{ if ne(parameters.sparseCheckoutDir, '') }}:
+        script: cmake $(Pipeline.Workspace)/s/projects/hipsparselt/deps
+      ${{ else }}:
+        script: cmake $(Pipeline.Workspace)/s/deps
       displayName: Configure hipSPARSELt external dependencies
       workingDirectory: $(Pipeline.Workspace)/deps
     - script: make
@@ -113,81 +150,115 @@ jobs:
     - script: sudo make install
       displayName: Install hipSPARSELt external dependencies
       workingDirectory: $(Pipeline.Workspace)/deps
+  # -----------------------------
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        # NOTE: the following options are old build only 
+        # and can be removed after full transition to new build
+        # -DAMDGPU_TARGETS=${{ job.target }}
+        # -DCMAKE_Fortran_COMPILER=f95
+        # -DTensile_LOGIC=
+        # -DTensile_CPU_THREADS=
+        # -DTensile_LIBRARY_FORMAT=msgpack
+        # -DROCM_PATH=$(Agent.BuildDirectory)/rocm
+        # -DBUILD_CLIENTS_TESTS=ON
+        # -DBUILD_USE_LOCAL_TENSILE=OFF
         extraBuildFlags: >-
           -DCMAKE_BUILD_TYPE=Release
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-          -DCMAKE_Fortran_COMPILER=f95
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
+          -DGPU_TARGETS=${{ job.target }}
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DCMAKE_Fortran_COMPILER=f95
           -DTensile_LOGIC=
           -DTensile_CPU_THREADS=
           -DTensile_LIBRARY_FORMAT=msgpack
-          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DBUILD_CLIENTS_TESTS=ON
+          -DBUILD_USE_LOCAL_TENSILE=OFF
+          -DHIPSPARSELT_ENABLE_FETCH=ON
           -GNinja
+        ${{ if ne(parameters.sparseCheckoutDir, '') }}:
+          cmakeSourceDir: $(Build.SourcesDirectory)/projects/hipsparselt
+          cmakeBuildDir: $(Build.SourcesDirectory)/projects/hipsparselt
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        pipModules: ${{ parameters.pipModules }}
+          aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
+          pipModules: ${{ parameters.pipModules }}
-        extraCopyDirectories:
+          gpuTarget: ${{ job.target }}
-          - deps
+          extraCopyDirectories:
-        extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
+            - deps
-        extraEnvVars:
+          extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+          extraEnvVars:
-          - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-          - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/llvm/bin/hipcc
+            - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
-          - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
+            - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/llvm/bin/hipcc
-        installLatestCMake: true
+            - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
+          installLatestCMake: true
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: hipSPARSELt_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: hipSPARSELt_build_${{ job.target }}
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
-    condition:
+      timeoutInMinutes: 120
-      and(succeeded(),
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+      condition:
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        and(succeeded(),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-      )
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-    variables:
+          eq(${{ parameters.aggregatePipeline }}, False)
-    - group: common
+        )
-    - template: /.azuredevops/variables-global.yml
+      variables:
-    pool: ${{ job.target }}_test_pool
+      - group: common
-    workspace:
+      - template: /.azuredevops/variables-global.yml
-      clean: all
+      pool: ${{ job.target }}_test_pool
-    steps:
+      workspace:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        clean: all
-      parameters:
+      steps:
-        aptPackages: ${{ parameters.aptPackages }}
+      - checkout: none
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
-      parameters:
+          aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
+          packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+        parameters:
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+          preTargetFilter: ${{ parameters.componentName }}
-        gpuTarget: ${{ job.target }}
+          gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
+        parameters:
-        componentName: hipSPARSELt
+          checkoutRef: ${{ parameters.checkoutRef }}
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-        testExecutable: './hipsparselt-test'
+          gpuTarget: ${{ job.target }}
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes --gtest_filter=*pre_checkin*'
+          os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+          ${{ if parameters.triggerDownstreamJobs }}:
-      parameters:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        pipModules: ${{ parameters.pipModules }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        environment: test
+        parameters:
-        gpuTarget: ${{ job.target }}
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './hipsparselt-test'
+          testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes --gtest_filter=*pre_checkin*'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/hipTensor.yml

@@ -77,6 +77,7 @@ jobs:
         extraBuildFlags: >-
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/llvm
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DCMAKE_BUILD_TYPE=Release
           -DHIPTENSOR_BUILD_TESTS=ON
@@ -129,7 +130,7 @@ jobs:
       parameters:
         componentName: hipTensor
         testDir: '$(Agent.BuildDirectory)/rocm/bin/hiptensor'
-        testParameters: '-E ".*-extended" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+        testParameters: '-E ".*-extended" --extra-verbose --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/hipfort.yml

@@ -71,7 +71,7 @@ jobs:
     - 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/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:

.azuredevops/components/llvm-project.yml

@@ -30,7 +30,7 @@ parameters:
   default:
     buildJobs:
       - { os: ubuntu2204, packageManager: apt }
-      - { os: ubuntu2404, packageManager: apt }
+      # - { os: ubuntu2404, packageManager: apt }
       - { os: almalinux8, packageManager: dnf }
 
 jobs:
@@ -67,7 +67,6 @@ jobs:
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
-        skipLlvmSymlink: true
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml

.azuredevops/components/origami.yml

@@ -0,0 +1,251 @@
+parameters:
+- name: componentName
+  type: string
+  default: origami
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
+# set to true if doing full build of ROCm stack
+# and dependencies are pulled from same pipeline
+- name: aggregatePipeline
+  type: boolean
+  default: false
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+    - wget
+    - python3
+    - python3-dev
+    - python3-pip
+    - libgtest-dev
+    - libboost-filesystem-dev
+    - libboost-program-options-dev
+- name: pipModules
+  type: object
+  default:
+    - nanobind>=2.0.0
+- name: rocmDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - rocm-cmake
+    - rocminfo
+    - ROCR-Runtime
+    - rocprofiler-register
+- name: rocmTestDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - rocm-cmake
+    - rocminfo
+    - ROCR-Runtime
+    - rocprofiler-register
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+    testJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipBLASLt:
+      name: hipBLASLt
+      sparseCheckoutDir: projects/hipblaslt
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - origami_build
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: origami_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: ROCM_PATH
+      value: $(Agent.BuildDirectory)/rocm
+    pool:
+      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DORIGAMI_BUILD_SHARED_LIBS=ON
+          -DORIGAMI_ENABLE_PYTHON=ON
+          -DORIGAMI_BUILD_TESTING=ON
+          -GNinja
+    - ${{ if ne(job.os, 'almalinux8') }}:
+      - task: PublishPipelineArtifact@1
+        displayName: 'Publish Build Directory Artifact'
+        inputs:
+          targetPath: '$(Agent.BuildDirectory)/s/build'
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
+          publishLocation: 'pipeline'
+      - task: PublishPipelineArtifact@1
+        displayName: 'Publish Python Source Artifact'
+        inputs:
+          targetPath: '$(Agent.BuildDirectory)/s/python'
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
+          publishLocation: 'pipeline'
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+        componentName: ${{ parameters.componentName }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: origami_test_${{ job.os }}_${{ job.target }}
+      timeoutInMinutes: 120
+      dependsOn: origami_build_${{ job.os }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+      - task: DownloadPipelineArtifact@2
+        displayName: 'Download Build Directory Artifact'
+        inputs:
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
+          path: '$(Agent.BuildDirectory)/s/build'
+      - task: DownloadPipelineArtifact@2
+        displayName: 'Download Python Source Artifact'
+        inputs:
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
+          path: '$(Agent.BuildDirectory)/s/python'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './origami-tests'
+          testParameters: '--yaml origami-tests.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - script: |
+          set -e
+          export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH
+
+          echo "--- Running origami_test.py ---"
+          python3 $(Agent.BuildDirectory)/s/python/origami_test.py
+          
+          echo "--- Running origami_grid_test.py ---"
+          python3 $(Agent.BuildDirectory)/s/python/origami_grid_test.py
+        displayName: 'Run Python Binding Tests'
+        condition: succeeded()
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rccl.yml

@@ -1,10 +1,35 @@
 parameters:
+- name: componentName
+  type: string
+  default: rccl
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+- name: systemsRepo
+  type: string
+  default: systems_repo
+- name: systemsSparseCheckoutDir
+  type: string
+  default: 'projects/rocprofiler-sdk'
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -57,37 +82,52 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
-        target: gfx90a
     testJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
+- name: downstreamComponentMatrix
-        target: gfx90a
+  type: object
+  default:
+    - rocprofiler-sdk:
+      name: rocprofiler-sdk
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rccl_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rccl_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
-    timeoutInMinutes: 90
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
+    timeoutInMinutes: 120
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     - name: HIP_ROCCLR_HOME
       value: $(Build.BinariesDirectory)/rocm
-    pool: ${{ variables.HIGH_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         submoduleBehaviour: recursive
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
       parameters:
@@ -97,10 +137,14 @@ jobs:
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
@@ -112,58 +156,87 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        gpuTarget: ${{ job.target }}
+          aptPackages: ${{ parameters.aptPackages }}
-        extraEnvVars:
+          gpuTarget: ${{ job.target }}
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+          extraEnvVars:
-        installLatestCMake: true
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+          installLatestCMake: true
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rccl_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    timeoutInMinutes: 120
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
-    dependsOn: rccl_build_${{ job.target }}
+      timeoutInMinutes: 120
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+          preTargetFilter: ${{ parameters.componentName }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          os: ${{ job.os }}
-      parameters:
+          gpuTarget: ${{ job.target }}
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          checkoutRef: ${{ parameters.checkoutRef }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-      parameters:
+          os: ${{ job.os }}
-        componentName: rccl
+          gpuTarget: ${{ job.target }}
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          ${{ if parameters.triggerDownstreamJobs }}:
-        testExecutable: './rccl-UnitTests'
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
+        parameters:
-        aptPackages: ${{ parameters.aptPackages }}
+          componentName: ${{ parameters.componentName }}
-        environment: test
+          os: ${{ job.os }}
-        gpuTarget: ${{ job.target }}
+          testDir: '$(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.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.systemsRepo }}
+          sparseCheckoutDir: ${{ parameters.systemsSparseCheckoutDir }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}
+          ${{ if parameters.unifiedBuild }}:
+            buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
+          ${{ else }}:
+            buildDependsOn: ${{ component.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}

.azuredevops/components/rdc.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rdc
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -33,6 +52,7 @@ parameters:
     - clr
     - hipBLAS-common
     - hipBLASLt
+    - hipRAND
     - llvm-project
     - rocBLAS
     - rocm-cmake
@@ -43,6 +63,7 @@ parameters:
     - rocprofiler
     - rocprofiler-register
     - rocprofiler-sdk
+    - rocRAND
     - ROCR-Runtime
 - name: rocmTestDependencies
   type: object
@@ -74,7 +95,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rdc_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -85,16 +110,22 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
   # Build grpc
     - task: Bash@3
       displayName: 'git clone grpc'
@@ -104,6 +135,7 @@ jobs:
         workingDirectory: $(Build.SourcesDirectory)
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         cmakeBuildDir: $(Build.SourcesDirectory)/grpc/build
         cmakeSourceDir: $(Build.SourcesDirectory)/grpc
         installDir: $(Build.SourcesDirectory)/bin
@@ -117,6 +149,7 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         extraBuildFlags: >-
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
           -DGRPC_ROOT="$(Build.SourcesDirectory)/bin"
@@ -126,9 +159,12 @@ jobs:
           -DAMDGPU_TARGETS=${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -136,60 +172,64 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rdc_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: rdc_build_${{ job.target }}
+    - job: ${{ parameters.componentName }}_test_${{ job.target }}
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    - name: ROCM_PATH
+      - template: /.azuredevops/variables-global.yml
-      value: $(Agent.BuildDirectory)/rocm
+      - name: ROCM_PATH
-    - name: ROCM_DIR
+        value: $(Agent.BuildDirectory)/rocm
-      value: $(Agent.BuildDirectory)/rocm
+      - name: ROCM_DIR
-    pool: ${{ job.target }}_test_pool
+        value: $(Agent.BuildDirectory)/rocm
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          aptPackages: ${{ parameters.aptPackages }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          gpuTarget: ${{ job.target }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+        parameters:
-        gpuTarget: ${{ job.target }}
+          checkoutRef: ${{ parameters.checkoutRef }}
-    - task: Bash@3
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-      displayName: Setup test environment
+          gpuTarget: ${{ job.target }}
-      inputs:
+          ${{ if parameters.triggerDownstreamJobs }}:
-        targetType: inline
+              downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        script: |
+      - task: Bash@3
-          sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rdcd /usr/sbin/rdcd
+        displayName: Setup test environment
-          echo $(Agent.BuildDirectory)/rocm/lib/rdc/grpc/lib | sudo tee /etc/ld.so.conf.d/grpc.conf
+        inputs:
-          sudo ldconfig -v
+          targetType: inline
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          script: |
-    - task: Bash@3
+            sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rdcd /usr/sbin/rdcd
-      displayName: Test rdc
+            echo $(Agent.BuildDirectory)/rocm/lib/rdc/grpc/lib | sudo tee /etc/ld.so.conf.d/grpc.conf
-      inputs:
+            sudo ldconfig -v
-        targetType: inline
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        script: >-
+      - task: Bash@3
-          $(Agent.BuildDirectory)/rocm/share/rdc/rdctst_tests/rdctst
+        displayName: Test rdc
-          --batch_mode
+        inputs:
-          --start_rdcd
+          targetType: inline
-          --unauth_comm
+          script: >-
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+            $(Agent.BuildDirectory)/rocm/share/rdc/rdctst_tests/rdctst
-      parameters:
+            --batch_mode
-        aptPackages: ${{ parameters.aptPackages }}
+            --start_rdcd
-        environment: test
+            --unauth_comm
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        extraPaths: /home/user/workspace/rocm/bin
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+          extraPaths: /home/user/workspace/rocm/bin

.azuredevops/components/rocAL.yml

@@ -86,8 +86,7 @@ jobs:
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
-    pool:
+    pool:  ${{ variables.MEDIUM_BUILD_POOL }}
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/rocALUTION.yml

@@ -73,8 +73,7 @@ jobs:
     - template: /.azuredevops/variables-global.yml
     - name: HIP_ROCCLR_HOME
       value: $(Build.BinariesDirectory)/rocm
-    pool:
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/rocBLAS.yml

@@ -33,17 +33,15 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
-    - python3-venv
     - git
-    - libmsgpack-dev
     - gfortran
-    - libopenblas-dev
-    - googletest
-    - libgtest-dev
-    - wget
-    - python3-pip
     - libdrm-dev
+    - libmsgpack-dev
+    - libopenblas-dev
+    - ninja-build
+    - python3-pip
+    - python3-venv
+    - wget
 - name: pipModules
   type: object
   default:
@@ -52,18 +50,17 @@ parameters:
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
-    - clr
-    - rocminfo
-    - rocprofiler-register
-    - rocm_smi_lib
-    - rocm-core
     - aomp
-    - aomp-extras
+    - clr
     - hipBLAS-common
     - hipBLASLt
+    - llvm-project
+    - rocm-cmake
+    - rocm-core
+    - rocm_smi_lib
+    - rocminfo
+    - rocprofiler-register
+    - ROCR-Runtime
     - roctracer
 - name: rocmTestDependencies
   type: object
@@ -73,6 +70,7 @@ parameters:
     - hipBLAS-common
     - hipBLASLt
     - llvm-project
+    - rocm-cmake
     - rocminfo
     - rocprofiler-register
     - rocm_smi_lib
@@ -86,32 +84,45 @@ parameters:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
       - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
-      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
-      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      #- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
+      #- { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-# - name: downstreamComponentMatrix
+- name: downstreamComponentMatrix
-#   type: object
+  type: object
-#   default:
+  default:
-#     # rocSOLVER depends on both rocBLAS and rocPRIM
+    - rocSPARSE:
-#     # for a unified build, rocBLAS will be the one to call rocSOLVER
+      name: rocSPARSE
-#     - rocSOLVER:
+      sparseCheckoutDir: projects/rocsparse
-#       name: rocSOLVER
+      skipUnifiedBuild: 'false'
-#       sparseCheckoutDir: projects/rocsolver
+      buildDependsOn:
-#       skipUnifiedBuild: 'false'
+        - rocBLAS_build
-#       buildDependsOn:
+    # rocSOLVER depends on both rocBLAS and rocPRIM
-#         - rocBLAS_build
+    # for a unified build, rocBLAS will be the one to call rocSOLVER
-#       unifiedBuild:
+#    - rocSOLVER:
-#         downstreamAggregateNames: rocBLAS+rocPRIM
+#      name: rocSOLVER
-#         buildDependsOn:
+#      sparseCheckoutDir: projects/rocsolver
-#           - rocBLAS_build
+#      skipUnifiedBuild: 'false'
-#           - rocPRIM_build
+#      buildDependsOn:
+#        - rocBLAS_build
+#      unifiedBuild:
+#        downstreamAggregateNames: rocBLAS+rocPRIM
+#        buildDependsOn:
+#          - rocBLAS_build
+#          - rocPRIM_build
+    # temporary rocblas->hipblas downstream path while the SOLVERs are disabled
+    - hipBLAS:
+      name: hipBLAS
+      sparseCheckoutDir: projects/hipblas
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocBLAS_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -144,13 +155,19 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
         packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
         sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aocl.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
@@ -163,22 +180,15 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}
+        cmakeSourceDir: $(Agent.BuildDirectory)/sparse/projects/rocblas
+        cmakeBuildDir: $(Agent.BuildDirectory)/sparse/projects/rocblas/build
         extraBuildFlags: >-
-          -DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
           -DCMAKE_BUILD_TYPE=Release
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
           -DGPU_TARGETS=${{ job.target }}
-          -DTensile_CODE_OBJECT_VERSION=default
-          -DTensile_LOGIC=asm_full
-          -DTensile_SEPARATE_ARCHITECTURES=ON
-          -DTensile_LAZY_LIBRARY_LOADING=ON
-          -DTensile_LIBRARY_FORMAT=msgpack
           -DBUILD_CLIENTS_TESTS=ON
-          -DBUILD_CLIENTS_BENCHMARKS=OFF
-          -DBUILD_CLIENTS_SAMPLES=OFF
-          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
@@ -208,6 +218,7 @@ jobs:
 - ${{ if eq(parameters.unifiedBuild, False) }}:
   - ${{ each job in parameters.jobMatrix.testJobs }}:
     - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      timeoutInMinutes: 120
       dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
       condition:
         and(succeeded(),
@@ -222,6 +233,7 @@ jobs:
       workspace:
         clean: all
       steps:
+      - checkout: none
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
         parameters:
           aptPackages: ${{ parameters.aptPackages }}
@@ -258,18 +270,18 @@ jobs:
           environment: test
           gpuTarget: ${{ job.target }}
 
-# - ${{ if parameters.triggerDownstreamJobs }}:
+- ${{ if parameters.triggerDownstreamJobs }}:
-#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
-#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
-#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
-#         parameters:
+        parameters:
-#           checkoutRepo: ${{ parameters.checkoutRepo }}
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
-#           triggerDownstreamJobs: true
+          triggerDownstreamJobs: true
-#           unifiedBuild: ${{ parameters.unifiedBuild }}
+          unifiedBuild: ${{ parameters.unifiedBuild }}
-#           ${{ if parameters.unifiedBuild }}:
+          ${{ if parameters.unifiedBuild }}:
-#             buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
+            buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
-#             downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
-#           ${{ else }}:
+          ${{ else }}:
-#             buildDependsOn: ${{ component.buildDependsOn }}
+            buildDependsOn: ${{ component.buildDependsOn }}
-#             downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}

.azuredevops/components/rocDecode.yml

@@ -8,6 +8,25 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
+- name: rocPyDecodeRepo
+  type: string
+  default: rocpydecode_repo
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -56,10 +75,23 @@ parameters:
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocPyDecode:
+      name: rocPyDecode
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocDecode_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -83,12 +115,15 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}
@@ -169,3 +204,15 @@ jobs:
         registerROCmPackages: true
         environment: test
         gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.rocPyDecodeRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocFFT.yml

@@ -78,19 +78,19 @@ parameters:
         target: gfx942
       - gfx90a:
         target: gfx90a
-# - name: downstreamComponentMatrix
+- name: downstreamComponentMatrix
-#   type: object
+  type: object
-#   default:
+  default:
-#     - hipFFT:
+    - hipFFT:
-#       name: hipFFT
+      name: hipFFT
-#       sparseCheckoutDir: projects/hipfft
+      sparseCheckoutDir: projects/hipfft
-#       skipUnifiedBuild: 'false'
+      skipUnifiedBuild: 'false'
-#       buildDependsOn:
+      buildDependsOn:
-#         - rocFFT_build
+        - rocFFT_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
     ${{ if parameters.buildDependsOn }}:
       dependsOn:
         - ${{ each build in parameters.buildDependsOn }}:
@@ -151,12 +151,12 @@ jobs:
           - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ${{ parameters.componentName }}_test_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
         eq(${{ parameters.aggregatePipeline }}, False)
       )
     variables:
@@ -166,6 +166,7 @@ jobs:
     workspace:
       clean: all
     steps:
+    - checkout: none
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
@@ -195,14 +196,14 @@ jobs:
         environment: test
         gpuTarget: ${{ job.target }}
 
-# - ${{ if parameters.triggerDownstreamJobs }}:
+- ${{ if parameters.triggerDownstreamJobs }}:
-#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
-#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
-#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
-#         parameters:
+        parameters:
-#           checkoutRepo: ${{ parameters.checkoutRepo }}
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
-#           buildDependsOn: ${{ component.buildDependsOn }}
+          buildDependsOn: ${{ component.buildDependsOn }}
-#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
-#           triggerDownstreamJobs: true
+          triggerDownstreamJobs: true
-#           unifiedBuild: ${{ parameters.unifiedBuild }}
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocMLIR.yml

@@ -27,6 +27,7 @@ parameters:
     - numpy
     - tomli
     - scipy
+    - pybind11
 - name: rocmDependencies
   type: object
   default:

.azuredevops/components/rocPRIM.yml

@@ -91,12 +91,12 @@ parameters:
         - rocPRIM_build
     # rocSOLVER depends on both rocBLAS and rocPRIM
     # for a unified build, rocBLAS will be the one to call rocSOLVER
-    # - rocSOLVER:
+#    - rocSOLVER:
-    #   name: rocSOLVER
+#      name: rocSOLVER
-    #   sparseCheckoutDir: projects/rocsolver
+#      sparseCheckoutDir: projects/rocsolver
-    #   skipUnifiedBuild: 'true'
+#      skipUnifiedBuild: 'true'
-    #   buildDependsOn:
+#      buildDependsOn:
-    #     - rocPRIM_build
+#        - rocPRIM_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:

.azuredevops/components/rocPyDecode.yml

@@ -5,6 +5,22 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -36,6 +52,7 @@ parameters:
     - clr
     - llvm-project
     - rocDecode
+    - rocJPEG
     - rocm-cmake
     - rocm-core
     - rocminfo
@@ -46,19 +63,19 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
-        target: gfx90a
     testJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
-        target: gfx90a
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocPyDecode_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -73,16 +90,20 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: Bash@3
       displayName: 'Save Python Package Paths'
       inputs:
@@ -189,12 +210,13 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - task: DownloadPipelineArtifact@2
       displayName: 'Download Pipeline Wheel Files'
+      retryCountOnTaskFailure: 3
       inputs:
         itemPattern: '**/*.whl'
         targetPath: $(Agent.BuildDirectory)
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
       parameters:
-        checkoutRepo: ${{ parameters.checkoutRepo }}
+        gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
@@ -221,25 +243,17 @@ jobs:
     - task: CMake@1
       displayName: 'rocPyDecode Test CMake Flags'
       inputs:
+        workingDirectory: $(Agent.BuildDirectory)/rocm/share/rocpydecode/tests
         cmakeArgs: >-
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(PYTHON_USER_SITE)/pybind11;$(PYTHON_DIST_PACKAGES)/pybind11;$(PYBIND11_PATH)
           -DCMAKE_BUILD_TYPE=Release
           -DGPU_TARGETS=${{ job.target }}
-          ..
+          .
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
         componentName: rocPyDecode
-        testDir: $(Build.SourcesDirectory)/build
+        testDir: $(Agent.BuildDirectory)/rocm/share/rocpydecode/tests
-  # sudo required for pip install but screws up permissions for next pipeline run
-    - task: Bash@3
-      displayName: Clean up test environment
-      condition: always()
-      inputs:
-        targetType: inline
-        script: |
-          pip uninstall -y rocPyDecode
-          pip uninstall -y hip-python
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocRAND.yml

@@ -79,6 +79,12 @@ parameters:
       skipUnifiedBuild: 'false'
       buildDependsOn:
         - rocRAND_build
+    - MIOpen:
+      name: MIOpen
+      sparseCheckoutDir: projects/miopen
+      skipUnifiedBuild: 'true'
+      buildDependsOn:
+        - rocRAND_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:

.azuredevops/components/rocSOLVER.yml

@@ -33,13 +33,11 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
-    - libsuitesparse-dev
     - gfortran
-    - libfmt-dev
     - git
-    - googletest
+    - libfmt-dev
-    - libgtest-dev
+    - libsuitesparse-dev
+    - ninja-build
     - python3-pip
 - name: rocmDependencies
   type: object
@@ -75,16 +73,38 @@ parameters:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
       - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
-      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
-      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      #- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
+      #- { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipBLAS:
+      name: hipBLAS
+      sparseCheckoutDir: projects/hipblas
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocSOLVER_build
+    # hipSOLVER depends on both rocSOLVER and rocSPARSE
+    # for a unified build, rocSOLVER will be the one to call hipSOLVER
+#    - hipSOLVER:
+#      name: hipSOLVER
+#      sparseCheckoutDir: projects/hipsolver
+#      skipUnifiedBuild: 'false'
+#      buildDependsOn:
+#        - rocSOLVER_build
+#      unifiedBuild:
+#        downstreamAggregateNames: rocSOLVER+rocSPARSE
+#        buildDependsOn:
+#          - rocSOLVER_build
+#          - rocSPARSE_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -119,6 +139,10 @@ jobs:
         targetType: inline
         script: git clone --depth 1 --branch v3.9.1 https://github.com/Reference-LAPACK/lapack
         workingDirectory: '$(Build.SourcesDirectory)'
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
@@ -134,6 +158,7 @@ jobs:
         os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_BUILD_TYPE=Release
+          -DCMAKE_POSITION_INDEPENDENT_CODE=ON
           -DCMAKE_Fortran_FLAGS=-fno-optimize-sibling-calls
           -DBUILD_TESTING=OFF
           -DCBLAS=ON
@@ -146,7 +171,7 @@ jobs:
       parameters:
         os: ${{ job.os }}
         extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install;$(Agent.BuildDirectory)/vendor
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
           -DAMDGPU_TARGETS=${{ job.target }}
@@ -191,6 +216,7 @@ jobs:
       workspace:
         clean: all
       steps:
+      - checkout: none
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
         parameters:
           aptPackages: ${{ parameters.aptPackages }}
@@ -224,3 +250,19 @@ jobs:
           aptPackages: ${{ parameters.aptPackages }}
           environment: test
           gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}
+          ${{ if parameters.unifiedBuild }}:
+            buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
+          ${{ else }}:
+            buildDependsOn: ${{ component.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}

.azuredevops/components/rocSPARSE.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocSPARSE
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -13,27 +32,25 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - python3-pip
     - cmake
-    - ninja-build
-    - libboost-program-options-dev
-    - googletest
-    - libfftw3-dev
-    - git
     - gfortran
-    - libgtest-dev
+    - git
+    - libboost-program-options-dev
     - libdrm-dev
+    - libfftw3-dev
+    - ninja-build
+    - python3-pip
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
     - clr
+    - llvm-project
     - rocBLAS
+    - rocm-cmake
     - rocminfo
     - rocPRIM
     - rocprofiler-register
+    - ROCR-Runtime
     - roctracer
 - name: rocmTestDependencies
   type: object
@@ -52,19 +69,39 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      #- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
     testJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
+- name: downstreamComponentMatrix
-        target: gfx90a
+  type: object
+  default:
+    - hipSPARSE:
+      name: hipSPARSE
+      sparseCheckoutDir: projects/hipsparse
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocSPARSE_build
+    # hipSOLVER depends on both rocSOLVER and rocSPARSE
+    # for a unified build, rocSOLVER will be the one to call hipSOLVER
+    # - hipSOLVER:
+    #   name: hipSOLVER
+    #   sparseCheckoutDir: projects/hipsolver
+    #   skipUnifiedBuild: 'true'
+    #   buildDependsOn:
+    #     - rocSPARSE_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocSPARSE_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -77,22 +114,32 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
         extraBuildFlags: >-
-          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
-          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang++
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DCMAKE_BUILD_TYPE=Release
           -DAMDGPU_TARGETS=${{ job.target }}
@@ -103,68 +150,94 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
-        artifactName: rocSPARSE
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
-        artifactName: rocSPARSE
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         publish: false
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
       parameters:
-        sourceDir: $(Build.SourcesDirectory)/build/clients
+        sourceDir: $(Agent.BuildDirectory)/s/build/clients
         contentsString: matrices/**
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         artifactName: testMatrices
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        gpuTarget: ${{ job.target }}
+          aptPackages: ${{ parameters.aptPackages }}
-        extraEnvVars:
+          gpuTarget: ${{ job.target }}
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rocSPARSE_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    timeoutInMinutes: 90
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
-    dependsOn: rocSPARSE_build_${{ job.target }}
+      timeoutInMinutes: 120
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          aptPackages: ${{ parameters.aptPackages }}
-      parameters:
+          packageManager: ${{ job.packageManager }}
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
-      parameters:
+          preTargetFilter: ${{ parameters.componentName }}
-        checkoutRef: ${{ parameters.checkoutRef }}
+          gpuTarget: ${{ job.target }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+          os: ${{ job.os }}
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
-      parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
-        componentName: rocSPARSE
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          gpuTarget: ${{ job.target }}
-        testExecutable: './rocsparse-test'
+          os: ${{ job.os }}
-        testParameters: '--gtest_filter="*quick*" --gtest_output=xml:./test_output.xml --gtest_color=yes'
+          ${{ if parameters.triggerDownstreamJobs }}:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        environment: test
+        parameters:
-        gpuTarget: ${{ job.target }}
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './rocsparse-test'
+          testParameters: '--gtest_filter="*quick*" --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.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocWMMA.yml

@@ -70,7 +70,7 @@ jobs:
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
-    pool: ${{ variables.HIGH_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/rocm-cmake.yml

@@ -81,7 +81,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
         componentName: rocm-cmake
-        testParameters: '-E "pass-version-parent" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+        testParameters: '-E "pass-version-parent" --extra-verbose --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:

.azuredevops/components/rocm-core.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocm-core
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -27,6 +46,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocm_core_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+        dependsOn:
+          - ${{ each build in parameters.buildDependsOn }}:
+            - ${{ build }}_${{ job.os }}
     pool:
       ${{ if eq(job.os, 'ubuntu2404') }}:
         vmImage: 'ubuntu-24.04'
@@ -50,8 +73,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -65,9 +90,12 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml

.azuredevops/components/rocm-examples.yml

@@ -14,16 +14,26 @@ parameters:
   type: object
   default:
     - cmake
+    - libdw-dev
     - libglfw3-dev
     - libmsgpack-dev
+    - libopencv-dev
     - libtbb-dev
+    - libtiff-dev
+    - libva-amdgpu-dev
+    - libavcodec-dev
+    - libavformat-dev
+    - libavutil-dev
     - ninja-build
     - python3-pip
 - name: rocmDependencies
   type: object
   default:
     - AMDMIGraphX
+    - aomp
+    - aomp-extras
     - clr
+    - composable_kernel
     - hipBLAS
     - hipBLAS-common
     - hipBLASLt
@@ -33,21 +43,33 @@ parameters:
     - hipRAND
     - hipSOLVER
     - hipSPARSE
+    - hipTensor
     - llvm-project
+    - MIOpen
+    - MIVisionX
+    - rocALUTION
     - rocBLAS
+    - rocDecode
     - rocFFT
+    - rocJPEG
     - rocPRIM
     - rocprofiler-register
+    - rocprofiler-sdk
     - ROCR-Runtime
     - rocRAND
     - rocSOLVER
     - rocSPARSE
     - rocThrust
+    - rocWMMA
+    - rpp
 - name: rocmTestDependencies
   type: object
   default:
     - AMDMIGraphX
+    - aomp
+    - aomp-extras
     - clr
+    - composable_kernel
     - hipBLAS
     - hipBLAS-common
     - hipBLASLt
@@ -57,18 +79,27 @@ parameters:
     - hipRAND
     - hipSOLVER
     - hipSPARSE
+    - hipTensor
     - llvm-project
+    - MIOpen
+    - MIVisionX
+    - rocALUTION
     - rocBLAS
+    - rocDecode
     - rocFFT
     - rocminfo
     - rocPRIM
+    - rocJPEG
     - rocprofiler-register
+    - rocprofiler-sdk
     - ROCR-Runtime
     - rocRAND
     - rocSOLVER
     - rocSPARSE
     - rocThrust
     - roctracer
+    - rocWMMA
+    - rpp
 
 - name: jobMatrix
   type: object
@@ -97,6 +128,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        registerROCmPackages: true
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
@@ -158,6 +193,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        registerROCmPackages: true
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
@@ -184,7 +223,7 @@ jobs:
       parameters:
         componentName: rocm-examples
         testDir: $(Build.SourcesDirectory)/build
-        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "rocfft_callback"'
+        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocm-libraries.yml

@@ -0,0 +1,193 @@
+parameters:
+- name: componentName
+  type: string
+  default: rocm_libraries
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
+# set to true if doing full build of ROCm stack
+# and dependencies are pulled from same pipeline
+- name: aggregatePipeline
+  type: boolean
+  default: false
+- name: aptPackages
+  type: object
+  default:
+    - ccache
+    - gfortran
+    - git
+    - libdrm-dev
+    - liblapack-dev
+    - libmsgpack-dev
+    - libnuma-dev
+    - libopenblas-dev
+    - ninja-build
+    - python3-pip
+    - python3-venv
+    - googletest
+    - libgtest-dev
+    - libgmock-dev
+    - libboost-filesystem-dev
+- name: pipModules
+  type: object
+  default:
+    - msgpack
+    - joblib
+    - "packaging>=22.0"
+    - pytest
+    - pytest-cmake
+    - --upgrade
+- name: rocmDependencies
+  type: object
+  default:
+    - aomp
+    - clr
+    - llvm-project
+    - rocminfo
+    - rocm-cmake
+    - rocm_smi_lib
+    - rocprofiler-register
+    - ROCR-Runtime
+    - roctracer
+- name: rocmTestDependencies
+  type: object
+  default:
+    - aomp
+    - clr
+    - llvm-project
+    - rocminfo
+    - rocm_smi_lib
+    - rocprofiler-register
+    - ROCR-Runtime
+    - roctracer
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { pool: rocm-ci_ultra_build_pool, os: ubuntu2204, packageManager: apt, target: gfx942 }
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    timeoutInMinutes: 300
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: DAY_STRING
+      value: $[format('{0:ddMMyyyy}', pipeline.startTime)]
+    pool: ${{ job.pool }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        gpuTarget: ${{ job.target }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+    - script: |
+        mkdir -p $(CCACHE_DIR)
+        echo "##vso[task.prependpath]/usr/lib/ccache"
+      displayName: Update path for ccache
+    - task: Cache@2
+      displayName: Ccache caching
+      inputs:
+        key: rocm-libraries | ${{ job.os }} | ${{ job.target }} | $(DAY_STRING) | $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+        path: $(CCACHE_DIR)
+        restoreKeys: |
+          rocm-libraries | ${{ job.os }} | ${{ job.target }} | $(DAY_STRING)
+          rocm-libraries | ${{ job.os }} | ${{ job.target }}
+          rocm-libraries | ${{ job.os }}
+    - task: Bash@3
+      displayName: Add paths for CMake and Python site-packages binaries
+      inputs:
+        targetType: inline
+        script: |
+          USER_BASE=$(python3 -m site --user-base)
+          echo "##vso[task.prependpath]$USER_BASE/bin"
+          echo "##vso[task.setvariable variable=PytestCmakePath]$USER_BASE/share/Pytest/cmake"
+        displayName: Set cmake configure paths
+    - task: Bash@3
+      displayName: Add ROCm binaries to PATH
+      inputs:
+        targetType: inline
+        script: |
+          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        extraBuildFlags: >-
+          -D CMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor;$(PytestCmakePath)
+          -D CMAKE_INCLUDE_PATH=$(Agent.BuildDirectory)/rocm/llvm/include
+          -D CMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -D CMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
+          -D CMAKE_CXX_COMPILER_LAUNCHER=ccache
+          -D CMAKE_C_COMPILER_LAUNCHER=ccache
+          -G Ninja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+        gpuTarget: ${{ job.target }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+        gpuTarget: ${{ job.target }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          gpuTarget: ${{ job.target }}
+          extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
+          installLatestCMake: true
+          extraCopyDirectories:
+            - deps

.azuredevops/components/rocm_smi_lib.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocm_smi_lib
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -32,6 +51,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocm_smi_lib_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     pool:
       ${{ if eq(job.os, 'ubuntu2404') }}:
         vmImage: 'ubuntu-24.04'
@@ -55,8 +78,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -65,51 +90,56 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     #   parameters:
     #     aptPackages: ${{ parameters.aptPackages }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: rocm_smi_lib_build_${{ job.os }}
+    - job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
-    condition:
+      dependsOn: rocm_smi_lib_build_${{ job.os }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        packageManager: ${{ job.packageManager }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          packageManager: ${{ job.packageManager }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-        os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+        parameters:
-      parameters:
+          os: ${{ job.os }}
-        runRocminfo: false
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
-      parameters:
+          runRocminfo: false
-        componentName: rocm_smi_lib
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        testDir: '$(Agent.BuildDirectory)'
+        parameters:
-        testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
+          componentName: ${{ parameters.componentName }}
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+          testDir: '$(Agent.BuildDirectory)'
-        os: ${{ job.os }}
+          testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+          testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
-      parameters:
+          os: ${{ job.os }}
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        environment: test
+        parameters:
-        gpuTarget: ${{ job.target }}
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocminfo.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocminfo
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -40,7 +59,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocminfo_build_${{ job.os }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     pool:
       vmImage: 'ubuntu-22.04'
     ${{ if eq(job.os, 'almalinux8') }}:
@@ -62,15 +85,18 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
-        skipLlvmSymlink: true
         os: ${{ job.os }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -79,65 +105,71 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rocminfo_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: rocminfo_build_${{ job.os }}
+    - job: rocminfo_test_${{ job.target }}
-    condition:
+      dependsOn: rocminfo_build_${{ job.os }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        packageManager: ${{ job.packageManager }}
+          aptPackages: ${{ parameters.aptPackages }}
-        registerROCmPackages: true
+          packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          registerROCmPackages: true
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-        os: ${{ job.os }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          os: ${{ job.os }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+        parameters:
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+          checkoutRef: ${{ parameters.checkoutRef }}
-        gpuTarget: ${{ job.target }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-        os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          os: ${{ job.os }}
-      parameters:
+          ${{ if parameters.triggerDownstreamJobs }}:
-        runRocminfo: false
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-      parameters:
+        parameters:
-        componentName: rocminfo
+          runRocminfo: false
-        testDir: '$(Agent.BuildDirectory)'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        testExecutable: './rocm/bin/rocminfo'
+        parameters:
-        testParameters: ''
+          componentName: ${{ parameters.componentName }}
-        testPublishResults: false
+          testDir: '$(Agent.BuildDirectory)'
-        os: ${{ job.os }}
+          testExecutable: './rocm/bin/rocminfo'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          testParameters: ''
-      parameters:
+          testPublishResults: false
-        componentName: rocm_agent_enumerator
+          os: ${{ job.os }}
-        testDir: '$(Agent.BuildDirectory)'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        testExecutable: './rocm/bin/rocm_agent_enumerator'
+        parameters:
-        testParameters: ''
+          componentName: rocm_agent_enumerator
-        testPublishResults: false
+          testDir: '$(Agent.BuildDirectory)'
-        os: ${{ job.os }}
+          testExecutable: './rocm/bin/rocm_agent_enumerator'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+          testParameters: ''
-      parameters:
+          testPublishResults: false
-        aptPackages: ${{ parameters.aptPackages }}
+          os: ${{ job.os }}
-        registerROCmPackages: true
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        environment: test
+        parameters:
-        gpuTarget: ${{ job.target }}
+          aptPackages: ${{ parameters.aptPackages }}
+          registerROCmPackages: true
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocprofiler-compute.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocprofiler-compute
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -36,6 +55,7 @@ parameters:
     - pymongo
     - pyyaml
     - setuptools
+    - sqlalchemy
     - tabulate
     - textual
     - textual_plotext
@@ -65,43 +85,23 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942-staging:
+      - gfx942:
-        name: gfx942_staging
         target: gfx942
-        dependencySource: staging
+      - gfx90a:
-      - gfx942-mainline:
-        name: gfx942_mainline
-        target: gfx942
-        dependencySource: mainline
-      - gfx90a-staging:
-        name: gfx90a_staging
         target: gfx90a
-        dependencySource: staging
-      - gfx90a-mainline:
-        name: gfx90a_mainline
-        target: gfx90a
-        dependencySource: mainline
     testJobs:
-      - gfx942-staging:
+      - gfx942:
-        name: gfx942_staging
         target: gfx942
-        dependencySource: staging
+      - gfx90a:
-      - gfx942-mainline:
-        name: gfx942_mainline
-        target: gfx942
-        dependencySource: mainline
-      - gfx90a-staging:
-        name: gfx90a_staging
         target: gfx90a
-        dependencySource: staging
-      - gfx90a-mainline:
-        name: gfx90a_mainline
-        target: gfx90a
-        dependencySource: mainline
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocprofiler_compute_build_${{ job.name }}
+  - job: rocprofiler_compute_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -118,17 +118,19 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         extraBuildFlags: >-
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
-        artifactName: ${{ job.dependencySource }}
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
-        artifactName: ${{ job.dependencySource }}
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -137,80 +139,83 @@ jobs:
     #     pipModules: ${{ parameters.pipModules }}
     #     gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rocprofiler_compute_test_${{ job.name }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    timeoutInMinutes: 120
+    - job: rocprofiler_compute_test_${{ job.target }}
-    dependsOn: rocprofiler_compute_build_${{ job.name }}
+      timeoutInMinutes: 120
-    condition:
+      dependsOn: rocprofiler_compute_build_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    - name: PYTHON_VERSION
+      - template: /.azuredevops/variables-global.yml
-      value: 3.10
+      - name: PYTHON_VERSION
-    pool: ${{ job.target }}_test_pool
+        value: 3.10
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        pipModules: ${{ parameters.pipModules }}
+          aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-        checkoutRepo: ${{ parameters.checkoutRepo }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-      parameters:
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
-        postTargetFilter: ${{ job.dependencySource }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+          preTargetFilter: ${{ parameters.componentName }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          gpuTarget: ${{ job.target }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+        parameters:
-        dependencySource: ${{ job.dependencySource }}
+          checkoutRef: ${{ parameters.checkoutRef }}
-        gpuTarget: ${{ job.target }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-    - task: Bash@3
+          gpuTarget: ${{ job.target }}
-      displayName: Add en_US.UTF-8 locale
+          ${{ if parameters.triggerDownstreamJobs }}:
-      inputs:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        targetType: inline
+      - task: Bash@3
-        script: |
+        displayName: Add en_US.UTF-8 locale
-          sudo locale-gen en_US.UTF-8
+        inputs:
-          sudo update-locale
+          targetType: inline
-          locale -a
+          script: |
-    - task: Bash@3
+            sudo locale-gen en_US.UTF-8
-      displayName: Add ROCm binaries to PATH
+            sudo update-locale
-      inputs:
+            locale -a
-        targetType: inline
+      - task: Bash@3
-        script: |
+        displayName: Add ROCm binaries to PATH
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+        inputs:
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
+          targetType: inline
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+          script: |
-      parameters:
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
-        extraBuildFlags: >-
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
-          -DCMAKE_HIP_ARCHITECTURES=${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
+        parameters:
-          -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
+          extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+            -DCMAKE_HIP_ARCHITECTURES=${{ job.target }}
-          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
+            -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-          -DCMAKE_BUILD_TYPE=Release
+            -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-          -DENABLE_TESTS=ON
+            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-          -DINSTALL_TESTS=ON
+            -DROCM_PATH=$(Agent.BuildDirectory)/rocm
-          -GNinja
+            -DCMAKE_BUILD_TYPE=Release
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+            -DENABLE_TESTS=ON
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+            -DINSTALL_TESTS=ON
-      parameters:
+            -GNinja
-        componentName: rocprofiler-compute
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+          componentName: ${{ parameters.componentName }}
-      parameters:
+          testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
-        aptPackages: ${{ parameters.aptPackages }}
+          testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
-        pipModules: ${{ parameters.pipModules }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        environment: test
+        parameters:
-        gpuTarget: ${{ job.target }}
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocprofiler-register.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocprofiler-register
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -27,6 +46,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocprofiler_register_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     pool:
       ${{ if eq(job.os, 'ubuntu2404') }}:
         vmImage: 'ubuntu-24.04'
@@ -50,9 +73,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
-        componentName: rocprofiler-register
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -62,12 +86,16 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
-        componentName: rocprofiler-register
+        componentName: ${{ parameters.componentName }}
+        testDir: $(Agent.BuildDirectory)/s/build
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml

.azuredevops/components/rocprofiler-sdk.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocprofiler-sdk
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -60,23 +79,27 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
-        target: gfx90a
     testJobs:
-      - gfx942:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - gfx90a:
-        target: gfx90a
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocprofiler_sdk_build_${{ job.target }}
+  - job: rocprofiler_sdk_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os}}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
@@ -84,18 +107,23 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: Bash@3
       displayName: Add Python site-packages binaries to path
       inputs:
@@ -105,6 +133,8 @@ jobs:
           echo "##vso[task.prependpath]$USER_BASE/bin"
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
           -DROCPROFILER_BUILD_TESTS=ON
@@ -114,9 +144,13 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -126,62 +160,72 @@ jobs:
     #     gpuTarget: ${{ job.target }}
     #     registerROCmPackages: true
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rocprofiler_sdk_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: rocprofiler_sdk_build_${{ job.target }}
+    - job: rocprofiler_sdk_test_${{ job.os }}_${{ job.target }}
-    condition:
+      dependsOn: rocprofiler_sdk_build_${{ job.os }}_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        pipModules: ${{ parameters.pipModules }}
+          aptPackages: ${{ parameters.aptPackages }}
-        registerROCmPackages: true
+          pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+          registerROCmPackages: true
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-        checkoutRepo: ${{ parameters.checkoutRepo }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
-      parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        dependencyList: ${{ parameters.rocmDependencies }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-    - task: Bash@3
+          checkoutRef: ${{ parameters.checkoutRef }}
-      displayName: Add Python and ROCm binaries to path
+          dependencyList: ${{ parameters.rocmDependencies }}
-      inputs:
+          os: ${{ job.os }}
-        targetType: inline
+          gpuTarget: ${{ job.target }}
-        script: |
+          ${{ if parameters.triggerDownstreamJobs }}:
-          USER_BASE=$(python3 -m site --user-base)
+              downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-          echo "##vso[task.prependpath]$USER_BASE/bin"
+      - task: Bash@3
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+        displayName: Add Python and ROCm binaries to path
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+        inputs:
-      parameters:
+          targetType: inline
-        extraBuildFlags: >-
+          script: |
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+            USER_BASE=$(python3 -m site --user-base)
-          -DROCPROFILER_BUILD_TESTS=ON
+            echo "##vso[task.prependpath]$USER_BASE/bin"
-          -DROCPROFILER_BUILD_SAMPLES=ON
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
-          -DROCPROFILER_BUILD_RELEASE=ON
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-          -DGPU_TARGETS=${{ job.target }}
+        parameters:
-          -GNinja
+          componentName: ${{ parameters.componentName }}
-    - template: ${{ variables.CI_TEMPLATE_PATH}}/steps/gpu-diagnostics.yml
+          os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          extraBuildFlags: >-
-      parameters:
+            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        componentName: rocprofiler-sdk
+            -DROCPROFILER_BUILD_TESTS=ON
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+            -DROCPROFILER_BUILD_SAMPLES=ON
-      parameters:
+            -DROCPROFILER_BUILD_RELEASE=ON
-        aptPackages: ${{ parameters.aptPackages }}
+            -DGPU_TARGETS=${{ job.target }}
-        pipModules: ${{ parameters.pipModules }}
+            -GNinja
-        environment: test
+      - template: ${{ variables.CI_TEMPLATE_PATH}}/steps/gpu-diagnostics.yml
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        registerROCmPackages: true
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: $(Agent.BuildDirectory)/build
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+          registerROCmPackages: true

.azuredevops/components/rocprofiler-systems.yml

@@ -6,6 +6,25 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: componentName
+  type: string
+  default: rocprofiler-systems
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -37,6 +56,7 @@ parameters:
     - libpfm4-dev
     - libtool
     - libopenmpi-dev
+    - libsqlite3-dev
     - m4
     - ninja-build
     - openmpi-bin
@@ -86,6 +106,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocprofiler_systems_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+        dependsOn:
+          - ${{ each build in parameters.buildDependsOn }}:
+            - ${{ build }}_${{ job.os }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -104,6 +128,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
@@ -135,12 +160,16 @@ jobs:
           -DCMAKE_CXX_FLAGS=-I$(Agent.BuildDirectory)/rocm/include/rocjpeg
           -DGPU_TARGETS=${{ job.target }}
           -GNinja
+        componentName: ${{ parameters.componentName }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        componentName: ${{ parameters.componentName }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
@@ -150,85 +179,93 @@ jobs:
         registerROCmPackages: true
         extraPaths: /home/user/workspace/rocm/bin:/home/user/workspace/rocm/llvm/bin
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: rocprofiler_systems_test_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: rocprofiler_systems_build_${{ job.target }}
+    - job: rocprofiler_systems_test_${{ job.target }}
-    condition:
+      dependsOn: rocprofiler_systems_build_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    timeoutInMinutes: 180
+        )
-    variables:
+      timeoutInMinutes: 180
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    - name: ROCM_PATH
+      - template: /.azuredevops/variables-global.yml
-      value: $(Agent.BuildDirectory)/rocm
+      - name: ROCM_PATH
-    pool:
+        value: $(Agent.BuildDirectory)/rocm
-      name: ${{ job.target }}_test_pool
+      pool:
-    workspace:
+        name: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        pipModules: ${{ parameters.pipModules }}
+          aptPackages: ${{ parameters.aptPackages }}
-        registerROCmPackages: true
+          pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          registerROCmPackages: true
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-        checkoutRepo: ${{ parameters.checkoutRepo }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+          checkoutRepo: ${{ parameters.checkoutRepo }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+        parameters:
-        dependencyList: ${{ parameters.rocmDependencies }}
+          checkoutRef: ${{ parameters.checkoutRef }}
-        gpuTarget: ${{ job.target }}
+          dependencyList: ${{ parameters.rocmDependencies }}
-    - task: Bash@3
+          gpuTarget: ${{ job.target }}
-      displayName: Add ROCm binaries to PATH
+          ${{ if parameters.triggerDownstreamJobs }}:
-      inputs:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        targetType: inline
+      - task: Bash@3
-        script: |
+        displayName: Add ROCm binaries to PATH
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+        inputs:
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
+          targetType: inline
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+          script: |
-      parameters:
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
-  # build flags reference: https://rocm.docs.amd.com/projects/omnitrace/en/latest/install/install.html
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
-        extraBuildFlags: >-
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-          -DROCPROFSYS_BUILD_TESTING=ON
+        parameters:
-          -DROCPROFSYS_BUILD_DYNINST=ON
+          cmakeSourceDir: $(Agent.BuildDirectory)/s/projects/rocprofiler-systems
-          -DROCPROFSYS_BUILD_LIBUNWIND=ON
+    # build flags reference: https://rocm.docs.amd.com/projects/omnitrace/en/latest/install/install.html
-          -DROCPROFSYS_DISABLE_EXAMPLES="openmp-target"
+          extraBuildFlags: >-
-          -DDYNINST_BUILD_TBB=ON
+            -DCMAKE_INSTALL_PREFIX=$(Agent.BuildDirectory)/rocprofiler-systems
-          -DDYNINST_BUILD_ELFUTILS=ON
+            -DROCPROFSYS_USE_PYTHON=ON
-          -DDYNINST_BUILD_LIBIBERTY=ON
+            -DROCPROFSYS_BUILD_TESTING=ON
-          -DDYNINST_BUILD_BOOST=ON
+            -DROCPROFSYS_BUILD_DYNINST=ON
-          -DROCPROFSYS_USE_PAPI=ON
+            -DROCPROFSYS_BUILD_LIBUNWIND=ON
-          -DROCPROFSYS_USE_MPI=ON
+            -DROCPROFSYS_DISABLE_EXAMPLES="openmp-target"
-          -DCMAKE_CXX_FLAGS=-I$(Agent.BuildDirectory)/rocm/include/rocjpeg
+            -DDYNINST_BUILD_TBB=ON
-          -DGPU_TARGETS=${{ job.target }}
+            -DDYNINST_BUILD_ELFUTILS=ON
-          -GNinja
+            -DDYNINST_BUILD_LIBIBERTY=ON
-    - task: Bash@3
+            -DDYNINST_BUILD_BOOST=ON
-      displayName: Set up rocprofiler-systems env
+            -DROCPROFSYS_USE_PAPI=ON
-      inputs:
+            -DROCPROFSYS_USE_MPI=ON
-        targetType: inline
+            -DCMAKE_CXX_FLAGS=-I$(Agent.BuildDirectory)/rocm/include/rocjpeg
-        script: source share/rocprofiler-systems/setup-env.sh
+            -DGPU_TARGETS=${{ job.target }}
-        workingDirectory: build
+            -GNinja
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      - task: Bash@3
-      parameters:
+        displayName: Set up rocprofiler-systems env
-        componentName: rocprofiler-systems
+        inputs:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+          targetType: inline
-      parameters:
+          script: source $(Agent.BuildDirectory)/rocprofiler-systems/share/rocprofiler-systems/setup-env.sh
-        gpuTarget: ${{ job.target }}
+          workingDirectory: $(Agent.BuildDirectory)/rocprofiler-systems/share/rocprofiler-systems
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
+        parameters:
-        gpuTarget: ${{ job.target }}
+          componentName: ${{ parameters.componentName }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+          testDir: $(Agent.BuildDirectory)/s/build/tests/
-      parameters:
+          testParameters: '--output-on-failure'
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-        pipModules: ${{ parameters.pipModules }}
+        parameters:
-        environment: test
+          gpuTarget: ${{ job.target }}
-        registerROCmPackages: true
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-        extraPaths: /home/user/workspace/rocm/bin:/home/user/workspace/rocm/llvm/bin
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          registerROCmPackages: true
+          gpuTarget: ${{ job.target }}
+          extraPaths: /home/user/workspace/rocm/bin:/home/user/workspace/rocm/llvm/bin

.azuredevops/components/rocprofiler.yml

@@ -8,6 +8,22 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -70,6 +86,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -94,6 +114,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
       parameters:
         dependencyList:
@@ -108,6 +129,8 @@ jobs:
         gpuTarget: ${{ job.target }}
         os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}
@@ -115,6 +138,7 @@ jobs:
         extraBuildFlags: >-
           -DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules;$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip;$(Agent.BuildDirectory)/rocm/lib64/cmake;$(Agent.BuildDirectory)/rocm/lib64/cmake/hip
           -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor"
+          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DCMAKE_POSITION_INDEPENDENT_CODE=ON
           -DENABLE_LDCONFIG=OFF
           -DUSE_PROF_API=1
@@ -122,10 +146,13 @@ jobs:
         multithreadFlag: -- -j32
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
         os: ${{ job.os }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
@@ -139,63 +166,68 @@ jobs:
             - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
             - ROCM_PATH:::/home/user/workspace/rocm
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    - name: ROCM_PATH
+      - template: /.azuredevops/variables-global.yml
-      value: $(Agent.BuildDirectory)/rocm
+      - name: ROCM_PATH
-    - name: LD_LIBRARY_PATH
+        value: $(Agent.BuildDirectory)/rocm
-      value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
+      - name: LD_LIBRARY_PATH
-    pool: ${{ job.target }}_test_pool
+        value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - checkout: none
-        aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        packageManager: ${{ job.packageManager }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+          packageManager: ${{ job.packageManager }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-        os: ${{ job.os }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+          preTargetFilter: ${{ parameters.componentName }}
-      parameters:
+          gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
+          os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-      parameters:
+        parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
+          os: ${{ job.os }}
-        dependencyList: ${{ parameters.rocmDependencies }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-        os: ${{ job.os }}
+          checkoutRef: ${{ parameters.checkoutRef }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          dependencyList: ${{ parameters.rocmDependencies }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          gpuTarget: ${{ job.target }}
-      parameters:
+          os: ${{ job.os }}
-        componentName: rocprofilerV1
+          ${{ if parameters.triggerDownstreamJobs }}:
-        testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        testExecutable:  ./run.sh
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        testParameters: ''
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        testPublishResults: false
+        parameters:
-        os: ${{ job.os }}
+          componentName: rocprofilerV1
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
-      parameters:
+          testExecutable:  ./run.sh
-        componentName: rocprofilerV2
+          testParameters: ''
-        testDir: $(Agent.BuildDirectory)/rocm
+          testPublishResults: false
-        testExecutable:  share/rocprofiler/tests/runUnitTests
+          os: ${{ job.os }}
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        os: ${{ job.os }}
+        parameters:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+          componentName: rocprofilerV2
-      parameters:
+          testDir: $(Agent.BuildDirectory)/rocm
-        aptPackages: ${{ parameters.aptPackages }}
+          testExecutable:  share/rocprofiler/tests/runUnitTests
-        pipModules: ${{ parameters.pipModules }}
+          testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
-        environment: test
+          os: ${{ job.os }}
-        gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/roctracer.yml

@@ -8,6 +8,22 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -65,6 +81,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -87,6 +107,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
@@ -94,6 +115,8 @@ jobs:
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         os: ${{ job.os }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     # the linker flags will not affect ubuntu2204 builds as the paths do not exist
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
@@ -109,10 +132,13 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
@@ -123,53 +149,57 @@ jobs:
     #     gpuTarget: ${{ job.target }}
     #     registerROCmPackages: true
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
+- ${{ if eq(parameters.unifiedBuild, False) }}:
-  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
-    condition:
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
-      and(succeeded(),
+      condition:
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+        and(succeeded(),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        eq(${{ parameters.aggregatePipeline }}, False)
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
-      )
+          eq(${{ parameters.aggregatePipeline }}, False)
-    variables:
+        )
-    - group: common
+      variables:
-    - template: /.azuredevops/variables-global.yml
+      - group: common
-    pool: ${{ job.target }}_test_pool
+      - template: /.azuredevops/variables-global.yml
-    workspace:
+      pool: ${{ job.target }}_test_pool
-      clean: all
+      workspace:
-    steps:
+        clean: all
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      steps:
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-        aptPackages: ${{ parameters.aptPackages }}
+        parameters:
-        pipModules: ${{ parameters.pipModules }}
+          aptPackages: ${{ parameters.aptPackages }}
-        packageManager: ${{ job.packageManager }}
+          pipModules: ${{ parameters.pipModules }}
-        registerROCmPackages: true
+          packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+          registerROCmPackages: true
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-        os: ${{ job.os }}
+          preTargetFilter: ${{ parameters.componentName }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+          gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+          os: ${{ job.os }}
-      parameters:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-        checkoutRef: ${{ parameters.checkoutRef }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-        dependencyList: ${{ parameters.rocmTestDependencies }}
+        parameters:
-        gpuTarget: ${{ job.target }}
+          checkoutRef: ${{ parameters.checkoutRef }}
-        os: ${{ job.os }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+          gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+          os: ${{ job.os }}
-      parameters:
+          ${{ if parameters.triggerDownstreamJobs }}:
-        componentName: roctracer
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-        testExecutable: $(Agent.BuildDirectory)/rocm/share/roctracer/run_tests.sh
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-        testParameters: ''
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-        testDir: $(Agent.BuildDirectory)
+        parameters:
-        testPublishResults: false
+          componentName: ${{ parameters.componentName }}
-        os: ${{ job.os }}
+          testExecutable: $(Agent.BuildDirectory)/rocm/share/roctracer/run_tests.sh
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+          testParameters: ''
-      parameters:
+          testDir: $(Agent.BuildDirectory)
-        aptPackages: ${{ parameters.aptPackages }}
+          testPublishResults: false
-        pipModules: ${{ parameters.pipModules }}
+          os: ${{ job.os }}
-        environment: test
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-        gpuTarget: ${{ job.target }}
+        parameters:
-        registerROCmPackages: true
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+          registerROCmPackages: true

.azuredevops/dependencies/boost.yml

@@ -40,7 +40,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
     parameters:
       dependencyList: ${{ parameters.rocmDependencies }}
-      dependencySource: staging
   - task: Bash@3
     displayName: Add ROCm binaries to PATH
     inputs:

.azuredevops/dependencies/catch2.yml

@@ -0,0 +1,63 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: catch2Version
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: catch2_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone catch2 ${{ parameters.catch2Version }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/catchorg/Catch2.git -b ${{ parameters.catch2Version }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/Catch2/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/Catch2
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/dependencies/cli11.yml

@@ -0,0 +1,63 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: cli11Version
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: cli11_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone cli11 ${{ parameters.cli11Version }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/CLIUtils/CLI11.git -b ${{ parameters.cli11Version }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/CLI11/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/CLI11
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/dependencies/fmtlib.yml

@@ -0,0 +1,67 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: fmtlibVersion
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+    - libfmt-dev
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: fmtlib_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone fmtlib ${{ parameters.fmtlibVersion }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/fmtlib/fmt.git -b ${{ parameters.fmtlibVersion }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/fmt/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/fmt
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -DFMT_SYSTEM_HEADERS=ON
+          -DFMT_INSTALL=ON
+          -DFMT_TEST=OFF
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/dependencies/libdivide.yml

@@ -0,0 +1,64 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: libdivideVersion
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: libdivide_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone libdivide ${{ parameters.libdivideVersion }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/ridiculousfish/libdivide.git -b ${{ parameters.libdivideVersion }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/libdivide/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/libdivide
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -DLIBDIVIDE_BUILD_TESTS=OFF
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/dependencies/spdlog.yml

@@ -0,0 +1,71 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: spdlogVersion
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: spdlog_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - fmtlib
+    - task: Bash@3
+      displayName: Clone spdlog ${{ parameters.spdlogVersion }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/gabime/spdlog.git -b ${{ parameters.spdlogVersion }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/spdlog/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/spdlog
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/vendor
+          -DCMAKE_BUILD_TYPE=Release
+          -DSPDLOG_USE_STD_FORMAT=OFF
+          -DSPDLOG_FMT_EXTERNAL_HO=ON
+          -DSPDLOG_INSTALL=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/dependencies/yamlcpp.yml

@@ -0,0 +1,66 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: yamlcppVersion
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: yamlcpp_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone yaml-cpp ${{ parameters.yamlcppVersion }}
+      inputs:
+        targetType: inline
+        script: git clone  https://github.com/jbeder/yaml-cpp.git -b ${{ parameters.yamlcppVersion }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/yaml-cpp/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/yaml-cpp
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -DYAML_CPP_BUILD_TOOLS=OFF
+          -DYAML_BUILD_SHARED_LIBS=OFF
+          -DYAML_CPP_INSTALL=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/nightly/pytorch.yml

@@ -219,7 +219,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
     parameters:
       dependencyList: ${{ parameters.rocmDependencies }}
-      dependencySource: staging
       gpuTarget: $(JOB_GPU_TARGET)
       setupHIPLibrarySymlinks: true
   - task: Bash@3
@@ -398,6 +397,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - task: DownloadPipelineArtifact@2
     displayName: 'Download Pipeline Wheel Files'
+    retryCountOnTaskFailure: 3
     inputs:
       itemPattern: '**/*.whl'
       targetPath: $(Agent.BuildDirectory)
@@ -406,8 +406,6 @@ jobs:
     parameters:
       dependencyList: ${{ parameters.rocmTestDependencies }}
       gpuTarget: $(JOB_GPU_TARGET)
-      dependencySource: staging
-      skipLlvmSymlink: true
 # get sources to run test scripts
   - task: Bash@3
     displayName: git clone upstream pytorch

.azuredevops/nightly/rocm-nightly.yml

@@ -3,21 +3,21 @@ parameters:
 - name: jobList
   type: object
   default:
-    - { os: ubuntu2204, target: gfx942, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx942 }
-    - { os: ubuntu2204, target: gfx90a, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-    - { os: ubuntu2204, target: gfx1201, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
-    - { os: ubuntu2204, target: gfx1100, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
-    - { os: ubuntu2204, target: gfx1030, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
-    - { os: ubuntu2404, target: gfx942, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx942 }
-    - { os: ubuntu2404, target: gfx90a, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx90a }
-    - { os: ubuntu2404, target: gfx1201, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1201 }
-    - { os: ubuntu2404, target: gfx1100, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1100 }
-    - { os: ubuntu2404, target: gfx1030, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1030 }
-    - { os: almalinux8, target: gfx942, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx942 }
-    - { os: almalinux8, target: gfx90a, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx90a }
-    - { os: almalinux8, target: gfx1201, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx1201 }
-    - { os: almalinux8, target: gfx1100, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx1100 }
-    - { os: almalinux8, target: gfx1030, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx1030 }
 - name: rocmDependencies
   type: object
   default:
@@ -92,7 +92,8 @@ schedules:
 
 jobs:
 - ${{ each job in parameters.jobList }}:
-  - job: rocm_nightly_${{ job.os }}_${{ job.target }}_${{ job.source }}
+  - job: nightly_${{ job.os }}_${{ job.target }}
+    timeoutInMinutes: 120
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -115,11 +116,9 @@ jobs:
       displayName: System disk space before ROCm
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
-        dependencySource: ${{ job.source }}
         dependencyList: ${{ parameters.rocmDependencies }}
         os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
-        skipLibraryLinking: true
     - script: df -h
       displayName: System disk space after ROCm
     - script: du -sh $(Agent.BuildDirectory)/rocm
@@ -132,7 +131,7 @@ jobs:
         includeRootFolder: false
         archiveType: tar
         tarCompression: gz
-        archiveFile: $(Build.ArtifactStagingDirectory)/$(Build.DefinitionName)_$(Build.BuildNumber)_ubuntu2204_${{ job.target }}.tar.gz
+        archiveFile: $(Build.ArtifactStagingDirectory)/$(Build.DefinitionName)_$(Build.BuildNumber)_${{ job.os }}_${{ job.target }}.tar.gz
     - script: du -sh $(Build.ArtifactStagingDirectory)
       displayName: Compressed ROCm size
     - task: PublishPipelineArtifact@1
@@ -145,5 +144,96 @@ jobs:
       inputs:
         workingDirectory: $(Pipeline.Workspace)
         targetType: inline
-        script: echo "$(Build.DefinitionName)_$(Build.BuildNumber)_ubuntu2204_${{ job.target }}.tar.gz" >> pipelineArtifacts.txt
+        script: echo "$(Build.DefinitionName)_$(Build.BuildNumber)_${{ job.os }}_${{ job.target }}.tar.gz" >> pipelineArtifacts.txt
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.packageManager, 'apt') }}:
+      - task: Bash@3
+        displayName: Create Dockerfile
+        inputs:
+          workingDirectory: $(Agent.BuildDirectory)
+          targetType: inline
+          script: |
+            cat <<'EOF' > Dockerfile
+              ${{ iif(eq(job.os, 'ubuntu2204'), 'FROM ubuntu:22.04', '') }}
+              ${{ iif(eq(job.os, 'ubuntu2404'), 'FROM ubuntu:24.04', '') }}
+
+              WORKDIR /root
+              RUN mkdir rocm
+
+              RUN apt update \
+                && apt upgrade -y \
+                && apt install -y cmake curl git gcc g++ gpg lsb-release lsof ninja-build pkg-config python3 python3-pip wget zip libdrm-dev libelf-dev libgtest-dev libhsakmt-dev libhwloc-dev libnuma-dev libstdc++-12-dev libtbb-dev jq \
+                && apt clean all
+
+              RUN PACKAGE_NAME=$(curl -s https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb") \
+                && wget -nv --retry-connrefused https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/$PACKAGE_NAME \
+                && mkdir hsa-amd-aqlprofile \
+                && dpkg-deb -R $PACKAGE_NAME hsa-amd-aqlprofile \
+                && cp -R hsa-amd-aqlprofile/opt/rocm-*/* rocm
+
+              RUN ARTIFACT_URL="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis/build/builds/$(Build.BuildId)/artifacts?artifactName=nightly${{ job.os }}${{ job.target }}&api-version=7.1" \
+                && DOWNLOAD_URL=$(curl -s $ARTIFACT_URL | jq ".resource.downloadUrl" | tr -d '"') \
+                && wget -nv --retry-connrefused $DOWNLOAD_URL -O nightly.zip \
+                && unzip nightly.zip \
+                && tar -xf nightly${{ job.os }}${{ job.target }}/rocm-nightly*${{ job.os }}*${{ job.target }}*.tar.gz -C rocm
+
+              RUN echo /root/rocm/lib | tee /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN ldconfig -v
+              ENV PATH="$PATH:/root/rocm/bin"
+              ENTRYPOINT ["/bin/bash"]
+            EOF
+            cat Dockerfile
+    - ${{ elseif eq(job.packageManager, 'dnf') }}:
+      - task: Bash@3
+        displayName: Create Dockerfile
+        inputs:
+          workingDirectory: $(Agent.BuildDirectory)
+          targetType: inline
+          script: |
+            cat <<'EOF' > Dockerfile
+              ${{ iif(eq(job.os, 'almalinux8'), 'FROM almalinux:8', '') }}
+
+              WORKDIR /root
+              RUN mkdir rocm
+
+              RUN dnf install -y cmake curl git gcc gcc-c++ gnupg2 redhat-lsb-core lsof pkgconf python3 python3-pip wget zip libdrm-devel elfutils-libelf-devel numactl-devel libstdc++-devel tbb-devel jq \
+                && dnf clean all
+
+              RUN PACKAGE_NAME=$(curl -s https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/ | grep -oP "hsa-amd-aqlprofile-[^\"]+\.rpm" | head -n1) \
+                && wget -nv --retry-connrefused https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/$PACKAGE_NAME \
+                && mkdir hsa-amd-aqlprofile \
+                && dnf -y install rpm-build cpio \
+                && rpm2cpio $PACKAGE_NAME | (cd hsa-amd-aqlprofile && cpio -idmv) \
+                && cp -R hsa-amd-aqlprofile/opt/rocm-*/* rocm
+
+              RUN ARTIFACT_URL="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis/build/builds/$(Build.BuildId)/artifacts?artifactName=nightly${{ job.os }}${{ job.target }}&api-version=7.1" \
+                && DOWNLOAD_URL=$(curl -s $ARTIFACT_URL | jq ".resource.downloadUrl" | tr -d '"') \
+                && wget -nv --retry-connrefused $DOWNLOAD_URL -O nightly.zip \
+                && UNZIP_DISABLE_ZIPBOMB_DETECTION=TRUE unzip nightly.zip \
+                && tar -xf nightly${{ job.os }}${{ job.target }}/rocm-nightly*${{ job.os }}*${{ job.target }}*.tar.gz -C rocm
+
+              RUN echo /root/rocm/lib | tee /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN ldconfig -v
+              ENV PATH="$PATH:/root/rocm/bin"
+              ENTRYPOINT ["/bin/bash"]
+            EOF
+            cat Dockerfile
+    - task: Docker@2
+      displayName: Build and upload Docker image
+      retryCountOnTaskFailure: 3
+      inputs:
+        containerRegistry: ContainerService3
+        repository: 'nightly-${{ job.os }}-${{ job.target }}'
+        Dockerfile: '$(Agent.BuildDirectory)/Dockerfile'
+        buildContext: '$(Agent.BuildDirectory)'
+    - task: Bash@3
+      displayName: '!! Docker Run Command !!'
+      inputs:
+        targetType: inline
+        script: echo "docker run -it --network=host --device=/dev/kfd --device=/dev/dri --security-opt seccomp=unconfined rocmexternalcicd.azurecr.io/nightly-${{ job.os }}-${{ job.target }}:$(Build.BuildId)" | tr '[:upper:]' '[:lower:]'

.azuredevops/tag-builds/catch2.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: catch2Version
+  type: string
+  default: "v3.7.0"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/catch2.yml
+    parameters:
+      catch2Version: ${{ parameters.catch2Version }}

.azuredevops/tag-builds/cli11.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: cli11Version
+  type: string
+  default: "main"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/cli11.yml
+    parameters:
+      cli11Version: ${{ parameters.cli11Version }}

.azuredevops/tag-builds/fmtlib.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: fmtlibVersion
+  type: string
+  default: "11.1.3"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/fmtlib.yml
+    parameters:
+      fmtlibVersion: ${{ parameters.fmtlibVersion }}

.azuredevops/tag-builds/libdivide.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: libdivideVersion
+  type: string
+  default: master
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/libdivide.yml
+    parameters:
+      libdivideVersion: ${{ parameters.libdivideVersion }}

.azuredevops/tag-builds/spdlog.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: spdlogVersion
+  type: string
+  default: "v1.15.1"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/spdlog.yml
+    parameters:
+      spdlogVersion: ${{ parameters.spdlogVersion }}

.azuredevops/tag-builds/yaml-cpp.yml

@@ -0,0 +1,24 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: yamlcppVersion
+  type: string
+  default: "0.8.0"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/yamlcpp.yml
+    parameters:
+      yamlcppVersion: ${{ parameters.yamlcppVersion }}
+      

.azuredevops/templates/steps/artifact-download.yml

@@ -12,6 +12,9 @@ parameters:
 - name: fileFilter
   type: string
   default: ''
+- name: extractAndDeleteFiles
+  type: boolean
+  default: true
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -21,8 +24,12 @@ parameters:
 steps:
 - task: DownloadPipelineArtifact@2
   displayName: Download ${{ parameters.componentName }}
+  retryCountOnTaskFailure: 3
   inputs:
-    itemPattern: '**/*${{ parameters.componentName }}*${{ parameters.fileFilter }}*'
+    ${{ if eq(parameters.componentName, 'clr') }}:
+      itemPattern: '**/*${{ parameters.componentName }}*${{ parameters.fileFilter }}*amd*' # filter out nvidia clr artifacts
+    ${{ else }}:
+      itemPattern: '**/*${{ parameters.componentName }}*${{ parameters.fileFilter }}*'
     targetPath: '$(Pipeline.Workspace)/d'
     allowPartiallySucceededBuilds: true
     ${{ if parameters.aggregatePipeline }}:
@@ -37,16 +44,17 @@ steps:
         buildVersionToDownload: latest # aomp trigger lives in ROCm/ROCm, so cannot use ROCm/aomp branch names
       ${{ else }}:
         buildVersionToDownload: latestFromBranch
-- task: ExtractFiles@1
+- ${{ if eq(parameters.extractAndDeleteFiles, true) }}:
-  displayName: Extract ${{ parameters.componentName }}
+  - task: ExtractFiles@1
-  inputs:
+    displayName: Extract ${{ parameters.componentName }}
-    archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
+    inputs:
-    destinationFolder: '$(Agent.BuildDirectory)/rocm'
+      archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
-    cleanDestinationFolder: false
+      destinationFolder: '$(Agent.BuildDirectory)/rocm'
-    overwriteExistingFiles: true
+      cleanDestinationFolder: false
-- task: DeleteFiles@1
+      overwriteExistingFiles: true
-  displayName: Cleanup Compressed ${{ parameters.componentName }}
+  - task: DeleteFiles@1
-  inputs:
+    displayName: Clean up Compressed ${{ parameters.componentName }}
-    SourceFolder: '$(Pipeline.Workspace)/d'
+    inputs:
-    Contents: '**/*.tar.gz'
+      SourceFolder: '$(Pipeline.Workspace)/d'
-    RemoveDotFiles: true
+      Contents: '**/*.tar.gz'
+      RemoveDotFiles: true

.azuredevops/templates/steps/artifact-links.yml

@@ -15,8 +15,8 @@ steps:
       URL_BEGIN="https://artprodcus3.artifacts.visualstudio.com/"
       URL_MIDDLE="/_apis/artifact/"
       URL_END="/content?format=file&subPath=%2F"
-      FORMATTED_JOB_NAME=$(echo $(Agent.JobName) | sed 's/ /./g; s/[-_]//g')
+      ARTIFACT_NAME="$(Agent.JobName)_$(System.JobAttempt)"
-      ARTIFACT_STRING="pipelineartifact://ROCm-CI/projectId/$(DOWNLOAD_PROJECT_ID)/buildId/$(Build.BuildId)/artifactName/${FORMATTED_JOB_NAME}"
+      ARTIFACT_STRING="pipelineartifact://ROCm-CI/projectId/$(DOWNLOAD_PROJECT_ID)/buildId/$(Build.BuildId)/artifactName/${ARTIFACT_NAME}"
       ENCODED_STRING=$(echo -n "${ARTIFACT_STRING}" | base64 -w 0)
       PADDING_COUNT=$(echo -n "${ENCODED_STRING}" | awk -F= '{print NF-1}')
       if [ "$PADDING_COUNT" -gt 0 ]; then

.azuredevops/templates/steps/artifact-upload.yml

@@ -46,5 +46,6 @@ steps:
     displayName: '${{ parameters.artifactName }} Publish'
     retryCountOnTaskFailure: 3
     inputs:
-      artifactName: ${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}_$(System.JobAttempt)
+      # if this artifact name is changed, please also update $ARTIFACT_URL inside miopen-get-ck-build.yml
+      artifactName: $(Agent.JobName)_$(System.JobAttempt)
       targetPath: '$(Build.ArtifactStagingDirectory)'

.azuredevops/templates/steps/checkout.yml

@@ -20,7 +20,7 @@ steps:
     retryCountOnTaskFailure: 3
     fetchFilter: blob:none
     ${{ if ne(parameters.sparseCheckoutDir, '') }}:
-      sparseCheckoutDirectories: ${{ parameters.sparseCheckoutDir }}
+      sparseCheckoutDirectories: ${{ parameters.sparseCheckoutDir }} shared
       path: sparse
   - ${{ if ne(parameters.sparseCheckoutDir, '') }}:
     - task: Bash@3

.azuredevops/templates/steps/dependencies-aocl.yml

@@ -1,10 +1,15 @@
 parameters:
+- name: os
+  type: string
+  default: ubuntu2204
 - name: repositoryUrl
   type: string
   default: https://download.amd.com/developer/eula/aocl/aocl-4-2
 - name: packageName
-  type: string
+  type: object
-  default: aocl-linux-gcc-4.2.0_1_amd64.deb
+  default:
+    ubuntu2204: aocl-linux-gcc-4.2.0_1_amd64.deb
+    almalinux8: aocl-linux-gcc-4.2.0-1.x86_64.rpm
 
 steps:
 - task: Bash@3
@@ -12,16 +17,19 @@ steps:
   inputs:
     targetType: inline
     workingDirectory: $(Pipeline.Workspace)
-    script: wget -nv ${{ parameters.repositoryUrl }}/${{ parameters.packageName }}
+    script: wget -nv ${{ parameters.repositoryUrl }}/${{ parameters.packageName[parameters.os] }}
 - task: Bash@3
   displayName: Install AOCL
   inputs:
     targetType: inline
     workingDirectory: $(Pipeline.Workspace)
-    script: sudo apt install -y ./${{ parameters.packageName }}
+    ${{ if eq(parameters.os, 'ubuntu2204') }}:
+      script: sudo apt install -y ./${{ parameters.packageName[parameters.os] }}
+    ${{ elseif eq(parameters.os, 'almalinux8') }}:
+      script: sudo dnf install -y ./${{ parameters.packageName[parameters.os] }}
 - task: Bash@3
   displayName: Clean up AOCL
   inputs:
     targetType: inline
     workingDirectory: $(Pipeline.Workspace)
-    script: rm -f ${{ parameters.packageName }}
+    script: rm -f ${{ parameters.packageName[parameters.os] }}

.azuredevops/templates/steps/dependencies-apt.yml

@@ -10,6 +10,7 @@ steps:
 - ${{ if eq(parameters.registerROCmPackages, true) }}:
   - task: Bash@3
     displayName: 'Register AMDGPU & ROCm repos (apt)'
+    retryCountOnTaskFailure: 3
     inputs:
       targetType: inline
       script: |
@@ -20,7 +21,8 @@ steps:
         echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
         sudo apt update
 - task: Bash@3
-  displayName: 'sudo apt-get update'
+  displayName: 'APT update and install packages'
+  retryCountOnTaskFailure: 3
   inputs:
     targetType: inline
     script: |
@@ -28,15 +30,6 @@ steps:
       echo "deb http://archive.ubuntu.com/ubuntu/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
       echo "deb http://archive.ubuntu.com/ubuntu/ jammy-backports main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
       echo "deb http://archive.ubuntu.com/ubuntu/ jammy-security main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
+      sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update && \
-- task: Bash@3
+        sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-broken install && \
-  displayName: 'sudo apt-get fix'
+        sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}
-  inputs:
-    targetType: inline
-    script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-broken install
-- ${{ if gt(length(parameters.aptPackages), 0) }}:
-  - task: Bash@3
-    displayName: 'sudo apt-get install ...'
-    inputs:
-      targetType: inline
-      script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}

.azuredevops/templates/steps/dependencies-aqlprofile.yml

@@ -5,51 +5,28 @@ parameters:
 
 steps:
 - task: Bash@3
-  displayName: Get aqlprofile package name
+  displayName: Download and install aqlprofile
-  inputs:
+  retryCountOnTaskFailure: 3
-    targetType: inline
-    ${{ if eq(parameters.os, 'ubuntu2204') }}:
-      script: |
-        export packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
-        echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
-    ${{ if eq(parameters.os, 'almalinux8') }}:
-      script: |
-        export packageName=$(curl -s https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/ | grep -oP "hsa-amd-aqlprofile-[^\"]+\.rpm" | head -n1)
-        echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
-- task: Bash@3
-  displayName: 'Download aqlprofile'
-  inputs:
-    targetType: inline
-    workingDirectory: '$(Pipeline.Workspace)'
-    ${{ if eq(parameters.os, 'ubuntu2204') }}:
-      script: wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$(packageName)
-    ${{ if eq(parameters.os, 'almalinux8') }}:
-      script: wget -nv https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/$(packageName)
-- task: Bash@3
-  displayName: 'Extract aqlprofile'
-  inputs:
-    targetType: inline
-    workingDirectory: '$(Pipeline.Workspace)'
-    ${{ if eq(parameters.os, 'ubuntu2204') }}:
-      script: |
-        mkdir hsa-amd-aqlprofile
-        dpkg-deb -R $(packageName) hsa-amd-aqlprofile
-    ${{ if eq(parameters.os, 'almalinux8') }}:
-      script: |
-        mkdir hsa-amd-aqlprofile
-        sudo dnf -y install rpm-build cpio
-        rpm2cpio $(packageName) | (cd hsa-amd-aqlprofile && cpio -idmv)
-- task: Bash@3
-  displayName: 'Copy aqlprofile files'
   inputs:
     targetType: inline
+    workingDirectory: $(Agent.BuildDirectory)
     script: |
-      mkdir -p $(Agent.BuildDirectory)/rocm
+      set -e
-      cp -R hsa-amd-aqlprofile/opt/rocm-*/* $(Agent.BuildDirectory)/rocm
+      if [ "${{ parameters.os }}" = "ubuntu2204" ]; then
-    workingDirectory: '$(Pipeline.Workspace)'
+        packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb") && \
-- task: Bash@3
+        wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$packageName && \
-  displayName: 'Clean up aqlprofile'
+        mkdir -p hsa-amd-aqlprofile && \
-  inputs:
+        dpkg-deb -R $packageName hsa-amd-aqlprofile
-    targetType: inline
+      elif [ "${{ parameters.os }}" = "almalinux8" ]; then
-    script: rm -rf hsa-amd-aqlprofile $(packageName)
+        sudo dnf -y install rpm-build cpio && \
-    workingDirectory: '$(Pipeline.Workspace)'
+        packageName=$(curl -s https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/ | grep -oP "hsa-amd-aqlprofile-[^\"]+\.rpm" | head -n1) && \
+        wget -nv https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/$packageName && \
+        mkdir -p hsa-amd-aqlprofile && \
+        rpm2cpio $packageName | (cd hsa-amd-aqlprofile && cpio -idmv)
+      else
+        echo "Unsupported OS: ${{ parameters.os }}"
+        exit 1
+      fi && \
+      mkdir -p $(Agent.BuildDirectory)/rocm && \
+      cp -R hsa-amd-aqlprofile/opt/rocm-*/* $(Agent.BuildDirectory)/rocm && \
+      rm -rf hsa-amd-aqlprofile $packageName

.azuredevops/templates/steps/dependencies-cmake-custom.yml

@@ -1,10 +1,15 @@
+parameters:
+  - name: cmakeVersion
+    type: string
+    default: '3.31.0'
+
 steps:
 - task: Bash@3
-  displayName: Install CMake 3.31
+  displayName: Install CMake ${{ parameters.cmakeVersion }}
   inputs:
     targetType: inline
     script: |
-      CMAKE_VERSION=3.31.0
+      CMAKE_VERSION=${{ parameters.cmakeVersion }}
       CMAKE_ROOT="$(Pipeline.Workspace)/cmake"
 
       echo "Downloading CMake $CMAKE_VERSION..."

.azuredevops/templates/steps/dependencies-dnf.yml

@@ -52,12 +52,15 @@ parameters:
     libexpat-dev: expat-devel
     libffi-dev: libffi-devel
     libfftw3-dev: fftw-devel
+    libfmt-dev: fmt-devel
     libgmp-dev: gmp-devel
+    liblapack-dev: lapack-devel
     liblzma-dev: xz-devel
     libmpfr-dev: mpfr-devel
     libmsgpack-dev: msgpack-devel
     libncurses5-dev: ncurses-devel
     libnuma-dev: numactl-devel
+    libopenblas-dev: openblas-devel
     libopenmpi-dev: openmpi-devel
     libpci-dev: libpciaccess-devel
     libssl-dev: openssl-devel
@@ -86,6 +89,7 @@ steps:
 - ${{ if eq(parameters.registerROCmPackages, true) }}:
   - task: Bash@3
     displayName: 'Register AMDGPU & ROCm repos (dnf)'
+    retryCountOnTaskFailure: 3
     inputs:
       targetType: inline
       script: |
@@ -106,12 +110,13 @@ steps:
         sudo dnf makecache
 - task: Bash@3
   displayName: 'Install base dnf packages'
+  retryCountOnTaskFailure: 3
   inputs:
     targetType: inline
     script: |
-      sudo dnf config-manager --set-enabled powertools
       # rpm fusion free repo for some dependencies
-      sudo dnf -y install https://download1.rpmfusion.org/free/el/rpmfusion-free-release-8.noarch.rpm
+      sudo dnf config-manager --set-enabled powertools && \
+      sudo dnf -y install https://download1.rpmfusion.org/free/el/rpmfusion-free-release-8.noarch.rpm && \
       sudo dnf -y install ${{ join(' ', parameters.basePackages) }}
 - task: Bash@3
   displayName: 'Check gcc environment'
@@ -125,6 +130,7 @@ steps:
       g++ -print-file-name=libstdc++.so
 - task: Bash@3
   displayName: 'Set python 3.11 as default'
+  retryCountOnTaskFailure: 3
   inputs:
     targetType: inline
     script: |
@@ -139,18 +145,20 @@ steps:
   - ${{ if eq(pkg, 'ninja-build') }}:
     - task: Bash@3
       displayName: 'Install ninja 1.11.1'
+      retryCountOnTaskFailure: 3
       inputs:
         targetType: inline
         script: |
-          curl -LO https://github.com/ninja-build/ninja/releases/download/v1.11.1/ninja-linux.zip
+          sudo dnf -y install unzip && \
-          sudo dnf -y install unzip
+          curl -LO https://github.com/ninja-build/ninja/releases/download/v1.11.1/ninja-linux.zip && \
-          unzip ninja-linux.zip
+          unzip ninja-linux.zip && \
-          sudo mv ninja /usr/local/bin/ninja
+          sudo mv ninja /usr/local/bin/ninja && \
-          sudo chmod +x /usr/local/bin/ninja
+          sudo chmod +x /usr/local/bin/ninja && \
           echo "##vso[task.prependpath]/usr/local/bin"
   - ${{ if ne(parameters.aptToDnfMap[pkg], '') }}:
     - task: Bash@3
       displayName: 'dnf install ${{ parameters.aptToDnfMap[pkg] }}'
+      retryCountOnTaskFailure: 3
       inputs:
         targetType: inline
         script: |

.azuredevops/templates/steps/dependencies-other.yml

@@ -27,6 +27,7 @@ steps:
 - ${{ if gt(length(parameters.pipModules), 0) }}:
   - task: Bash@3
     displayName: 'pip install  ...'
+    retryCountOnTaskFailure: 3
     inputs:
       targetType: inline
       script: python3 -m pip install -v --force-reinstall ${{ join(' ', parameters.pipModules) }}

.azuredevops/templates/steps/dependencies-rocm.yml

@@ -3,13 +3,6 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
-- name: dependencySource # optional, overrides checkoutRef
-  type: string
-  default: null
-  values:
-    - null # empty strings aren't allowed as values, use null instead
-    - staging
-    - mainline
 - name: dependencyList
   type: object
   default: []
@@ -19,16 +12,6 @@ parameters:
 - name: gpuTarget
   type: string
   default: ''
-# set to true if you're calling this template file multiple files in same pipeline
-# only leave last call false to optimize sequence
-- name: skipLibraryLinking
-  type: boolean
-  default: false
-# set to true if llvm-project is not downloaded in a particular call
-# or if you just don't want the symlink
-- name: skipLlvmSymlink
-  type: boolean
-  default: false
 # set to true if dlopen calls for HIP libraries are causing failures
 # because they do not follow shared library symlink convention
 - name: setupHIPLibrarySymlinks
@@ -48,309 +31,248 @@ parameters:
   type: object
   default:
     AMDMIGraphX:
-      pipelineId: $(AMDMIGRAPHX_PIPELINE_ID)
+      pipelineId: 113
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: master
       hasGpuTarget: true
     amdsmi:
-      pipelineId: $(AMDSMI_PIPELINE_ID)
+      pipelineId: 99
-      stagingBranch: amd-staging
+      developBranch: amd-staging
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     aomp-extras:
-      pipelineId: $(AOMP_EXTRAS_PIPELINE_ID)
+      pipelineId: 111
-      stagingBranch: aomp-dev
+      developBranch: aomp-dev
-      mainlineBranch: aomp-dev
       hasGpuTarget: false
     aomp:
-      pipelineId: $(AOMP_PIPELINE_ID)
+      pipelineId: 115
-      stagingBranch: aomp-dev
+      developBranch: aomp-dev
-      mainlineBranch: amd-mainline
+      hasGpuTarget: false
+    aqlprofile:
+      pipelineId: 365
+      developBranch: develop
       hasGpuTarget: false
     clr:
-      pipelineId: $(CLR_PIPELINE_ID)
+      pipelineId: 335
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     composable_kernel:
-      pipelineId: $(COMPOSABLE_KERNEL_PIPELINE_ID)
+      pipelineId: 86
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     half:
-      pipelineId: $(HALF_PIPELINE_ID)
+      pipelineId: 101
-      stagingBranch: rocm
+      developBranch: rocm
-      mainlineBranch: rocm
       hasGpuTarget: false
     HIP:
-      pipelineId: $(HIP_PIPELINE_ID)
+      pipelineId: 335
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     hip-tests:
-      pipelineId: $(HIP_TESTS_PIPELINE_ID)
+      pipelineId: 362
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     hipBLAS:
-      pipelineId: $(HIPBLAS_PIPELINE_ID)
+      pipelineId: 317
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     hipBLASLt:
-      pipelineId: $(HIPBLASLT_PIPELINE_ID)
+      pipelineId: 301
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     hipBLAS-common:
-      pipelineId: $(HIPBLAS_COMMON_PIPELINE_ID)
+      pipelineId: 300
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: false
     hipCUB:
-      pipelineId: $(HIPCUB_PIPELINE_ID)
+      pipelineId: 277
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: develop
       hasGpuTarget: true
     hipFFT:
-      pipelineId: $(HIPFFT_PIPELINE_ID)
+      pipelineId: 283
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     hipfort:
-      pipelineId: $(HIPFORT_PIPELINE_ID)
+      pipelineId: 102
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: false
     HIPIFY:
-      pipelineId: $(HIPIFY_PIPELINE_ID)
+      pipelineId: 92
-      stagingBranch: amd-staging
+      developBranch: amd-staging
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     hipRAND:
-      pipelineId: $(HIPRAND_PIPELINE_ID)
+      pipelineId: 275
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: develop
       hasGpuTarget: true
     hipSOLVER:
-      pipelineId: $(HIPSOLVER_PIPELINE_ID)
+      pipelineId: 84
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     hipSPARSE:
-      pipelineId: $(HIPSPARSE_PIPELINE_ID)
+      pipelineId: 315
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     hipSPARSELt:
-      pipelineId: $(HIPSPARSELT_PIPELINE_ID)
+      pipelineId: 309
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     hipTensor:
-      pipelineId: $(HIPTENSOR_PIPELINE_ID)
+      pipelineId: 105
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     llvm-project:
-      pipelineId: $(LLVM_PROJECT_PIPELINE_ID)
+      pipelineId: 2
-      stagingBranch: amd-staging
+      developBranch: amd-staging
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     MIOpen:
-      pipelineId: $(MIOpen_PIPELINE_ID)
+      pipelineId: 320
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: amd-master
       hasGpuTarget: true
     MIVisionX:
-      pipelineId: $(MIVISIONX_PIPELINE_ID)
+      pipelineId: 80
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: master
       hasGpuTarget: true
-    omnitrace: # deprecated
+    origami:
-      pipelineId: $(OMNITRACE_PIPELINE_ID)
+      pipelineId: 364
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rccl:
-      pipelineId: $(RCCL_PIPELINE_ID)
+      pipelineId: 107
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     rdc:
-      pipelineId: $(RDC_PIPELINE_ID)
+      pipelineId: 360
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocAL:
-      pipelineId: $(ROCAL_PIPELINE_ID)
+      pipelineId: 151
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     rocALUTION:
-      pipelineId: $(ROCALUTION_PIPELINE_ID)
+      pipelineId: 89
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     rocBLAS:
-      pipelineId: $(ROCBLAS_PIPELINE_ID)
+      pipelineId: 302
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     ROCdbgapi:
-      pipelineId: $(ROCDBGAPI_PIPELINE_ID)
+      pipelineId: 135
-      stagingBranch: amd-staging
+      developBranch: amd-staging
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocDecode:
-      pipelineId: $(ROCDECODE_PIPELINE_ID)
+      pipelineId: 79
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: false
     rocFFT:
-      pipelineId: $(ROCFFT_PIPELINE_ID)
+      pipelineId: 282
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     ROCgdb:
-      pipelineId: $(ROCGDB_PIPELINE_ID)
+      pipelineId: 134
-      stagingBranch: amd-staging
+      developBranch: amd-staging
-      mainlineBranch: amd-mainline-rocgdb-15
       hasGpuTarget: false
     rocJPEG:
-      pipelineId: $(ROCJPEG_PIPELINE_ID)
+      pipelineId: 262
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: false
     rocm-cmake:
-      pipelineId: $(ROCM_CMAKE_PIPELINE_ID)
+      pipelineId: 6
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: false
     rocm-core:
-      pipelineId: $(ROCM_CORE_PIPELINE_ID)
+      pipelineId: 349
-      stagingBranch: master
+      developBranch: develop
-      mainlineBranch: amd-master
       hasGpuTarget: false
     rocm-examples:
-      pipelineId: $(ROCM_EXAMPLES_PIPELINE_ID)
+      pipelineId: 216
-      stagingBranch: amd-staging
+      developBranch: amd-staging
-      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocminfo:
-      pipelineId: $(ROCMINFO_PIPELINE_ID)
+      pipelineId: 356
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocMLIR:
-      pipelineId: $(ROCMLIR_PIPELINE_ID)
+      pipelineId: 229
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: false
     ROCmValidationSuite:
-      pipelineId: $(ROCMVALIDATIONSUITE_PIPELINE_ID)
+      pipelineId: 106
-      stagingBranch: master
+      developBranch: master
-      mainlineBranch: master
       hasGpuTarget: true
     rocm_bandwidth_test:
-      pipelineId: $(ROCM_BANDWIDTH_TEST_PIPELINE_ID)
+      pipelineId: 88
-      stagingBranch: master
+      developBranch: master
-      mainlineBranch: master
       hasGpuTarget: false
     rocm_smi_lib:
-      pipelineId: $(ROCM_SMI_LIB_PIPELINE_ID)
+      pipelineId: 358
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocPRIM:
-      pipelineId: $(ROCPRIM_PIPELINE_ID)
+      pipelineId: 273
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: develop
       hasGpuTarget: true
     rocprofiler:
-      pipelineId: $(ROCPROFILER_PIPELINE_ID)
+      pipelineId: 329
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-master
       hasGpuTarget: true
     rocprofiler-compute:
-      pipelineId: $(ROCPROFILER_COMPUTE_PIPELINE_ID)
+      pipelineId: 344
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocprofiler-register:
-      pipelineId: $(ROCPROFILER_REGISTER_PIPELINE_ID)
+      pipelineId: 327
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocprofiler-sdk:
-      pipelineId: $(ROCPROFILER_SDK_PIPELINE_ID)
+      pipelineId: 347
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocprofiler-systems:
-      pipelineId: $(ROCPROFILER_SYSTEMS_PIPELINE_ID)
+      pipelineId: 345
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocPyDecode:
-      pipelineId: $(ROCPYDECODE_PIPELINE_ID)
+      pipelineId: 239
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     ROCR-Runtime:
-      pipelineId: $(ROCR_RUNTIME_PIPELINE_ID)
+      pipelineId: 354
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocRAND:
-      pipelineId: $(ROCRAND_PIPELINE_ID)
+      pipelineId: 274
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: develop
       hasGpuTarget: true
     rocr_debug_agent:
-      pipelineId: $(ROCR_DEBUG_AGENT_PIPELINE_ID)
+      pipelineId: 136
-      stagingBranch: amd-staging
+      developBranch: amd-staging
-      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocSOLVER:
-      pipelineId: $(ROCSOLVER_PIPELINE_ID)
+      pipelineId: 81
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     rocSPARSE:
-      pipelineId: $(ROCSPARSE_PIPELINE_ID)
+      pipelineId: 314
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
-    ROCT-Thunk-Interface: # deprecated
-      pipelineId: $(ROCT_THUNK_INTERFACE_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: master
-      hasGpuTarget: false
     rocThrust:
-      pipelineId: $(ROCTHRUST_PIPELINE_ID)
+      pipelineId: 276
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: develop
       hasGpuTarget: true
     roctracer:
-      pipelineId: $(ROCTRACER_PIPELINE_ID)
+      pipelineId: 331
-      stagingBranch: amd-staging
+      developBranch: develop
-      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocWMMA:
-      pipelineId: $(ROCWMMA_PIPELINE_ID)
+      pipelineId: 109
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     rpp:
-      pipelineId: $(RPP_PIPELINE_ID)
+      pipelineId: 78
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
     TransferBench:
-      pipelineId: $(TRANSFERBENCH_PIPELINE_ID)
+      pipelineId: 265
-      stagingBranch: develop
+      developBranch: develop
-      mainlineBranch: mainline
       hasGpuTarget: true
 
 steps:
@@ -366,72 +288,44 @@ steps:
       parameters:
         componentName: ${{ split(dependency, ':')[0] }}
         pipelineId: ${{ parameters.componentVarList[split(dependency, ':')[0]].pipelineId }}
+        branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].developBranch }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
-        ${{ if parameters.componentVarList[split(dependency, ':')[0]].hasGpuTarget }}:
+        extractAndDeleteFiles: false
-          fileFilter: "${{ split(dependency, ':')[1] }}*_${{ parameters.os }}_${{ parameters.gpuTarget }}"
-        # dependencySource = staging
-        ${{ if eq(parameters.dependencySource, 'staging')}}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
-        # dependencySource = mainline
-        ${{ elseif eq(parameters.dependencySource, 'mainline')}}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].mainlineBranch }}
-        # checkoutRef = staging
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].stagingBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
-        # checkoutRef = mainline
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].mainlineBranch }}
-        # SourceBranchName = staging
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].stagingBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
-        # SourceBranchName = mainline
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].mainlineBranch }}
-        # default = staging
-        ${{ else }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
 # no colon (:) found in this item in the list
   - ${{ elseif containsValue(split(parameters.downstreamAggregateNames, '+'), dependency) }}:
     - template: local-artifact-download.yml
       parameters:
-        ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
+        buildType: current
-          gpuTarget: ${{ parameters.gpuTarget }}
         preTargetFilter: ${{ dependency }}
         os: ${{ parameters.os }}
-        buildType: current
+        ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
+          gpuTarget: ${{ parameters.gpuTarget }}
   - ${{ else }}:
     - template: artifact-download.yml
       parameters:
         componentName: ${{ dependency }}
         pipelineId: ${{ parameters.componentVarList[dependency].pipelineId }}
+        branchName: ${{ parameters.componentVarList[dependency].developBranch }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        extractAndDeleteFiles: false
         ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
           fileFilter: ${{ parameters.os }}_${{ parameters.gpuTarget }}
         ${{ else }}:
           fileFilter: ${{ parameters.os }}
-        # dependencySource = staging
+- task: ExtractFiles@1
-        ${{ if eq(parameters.dependencySource, 'staging')}}:
+  displayName: Extract ROCm artifacts
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
+  inputs:
-        # dependencySource = mainline
+    archiveFilePatterns: $(Pipeline.Workspace)/d/**/*.tar.gz
-        ${{ elseif eq(parameters.dependencySource, 'mainline')}}:
+    destinationFolder: $(Agent.BuildDirectory)/rocm
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
+    cleanDestinationFolder: false
-        # checkoutRef = staging
+    overwriteExistingFiles: true
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].stagingBranch) }}:
+- task: DeleteFiles@1
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
+  displayName: Clean up ROCm artifacts
-        # checkoutRef = mainline
+  inputs:
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].mainlineBranch) }}:
+    SourceFolder: $(Pipeline.Workspace)/d
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
+    Contents: '**/*.tar.gz'
-        # SourceBranchName = staging
+    RemoveDotFiles: true
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].stagingBranch) }}:
+- ${{ if containsValue(parameters.dependencyList, 'llvm-project') }}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
-        # SourceBranchName = mainline
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
-        # default = staging
-        ${{ else }}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
-# Set link to redirect llvm folder
-- ${{ if eq(parameters.skipLlvmSymlink, false) }}:
   - task: Bash@3
     displayName: Symlink from rocm/llvm to rocm/lib/llvm
     inputs:
@@ -439,6 +333,7 @@ steps:
       script: |
         sudo mkdir -p $(Agent.BuildDirectory)/rocm/lib
         sudo ln -sr $(Agent.BuildDirectory)/rocm/llvm $(Agent.BuildDirectory)/rocm/lib/llvm
+        echo "Created symlink from rocm/llvm to rocm/lib/llvm"
   - task: Bash@3
     displayName: Symlink executables from rocm/llvm/bin to rocm/bin
     inputs:
@@ -446,7 +341,14 @@ steps:
       script: |
         for file in amdclang amdclang++ amdclang-cl amdclang-cpp amdflang amdlld aompcc mygpu mycpu offload-arch; do
           sudo ln -sr $(Agent.BuildDirectory)/rocm/llvm/bin/$file $(Agent.BuildDirectory)/rocm/bin/$file
+          echo "Created symlink from rocm/llvm/bin/$file to rocm/bin/$file"
         done
+- ${{ if containsValue(parameters.dependencyList, 'rocm-core') }}:
+  - task: Bash@3
+    displayName: Print rocm/.info/version
+    inputs:
+      targetType: inline
+      script: cat $(Agent.BuildDirectory)/rocm/.info/version
 # dlopen calls within a ctest or pytest sequence runs into issues when shared library symlink convention is not followed
 # the convention is as follows:
 # unversioned .so is a symlink to major version .so
@@ -483,17 +385,16 @@ steps:
   inputs:
     targetType: inline
     script: ls -la1R $(Agent.BuildDirectory)/rocm
-- ${{ if eq(parameters.skipLibraryLinking, false) }}:
+- task: Bash@3
-  - task: Bash@3
+  displayName: 'Link ROCm shared libraries'
-    displayName: 'Link ROCm shared libraries'
+  inputs:
-    inputs:
+    targetType: inline
-      targetType: inline
+    # OS ignores if the ROCm lib folder shows up more than once
-# OS ignores if the ROCm lib folder shows up more than once
+    script: |
-      script: |
+      echo $(Agent.BuildDirectory)/rocm/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
-        echo $(Agent.BuildDirectory)/rocm/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+      echo $(Agent.BuildDirectory)/rocm/llvm/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
-        echo $(Agent.BuildDirectory)/rocm/llvm/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+      echo $(Agent.BuildDirectory)/rocm/lib64 | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
-        echo $(Agent.BuildDirectory)/rocm/lib64 | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+      echo $(Agent.BuildDirectory)/rocm/llvm/lib64 | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
-        echo $(Agent.BuildDirectory)/rocm/llvm/lib64 | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+      sudo cat /etc/ld.so.conf.d/rocm-ci.conf
-        sudo cat /etc/ld.so.conf.d/rocm-ci.conf
+      sudo ldconfig -v
-        sudo ldconfig -v
+      ldconfig -p
-        ldconfig -p

.azuredevops/templates/steps/dependencies-vendor.yml

@@ -8,15 +8,20 @@ parameters:
   type: object
   default:
     boost: 250
+    catch2: 343
+    fmtlib: 341
     grpc: 72
     gtest: 73
     half560: 68
     lapack: 69
+    libdivide: 342
+    spdlog: 340
 
 steps:
 - ${{ each dependency in parameters.dependencyList }}:
   - task: DownloadPipelineArtifact@2
     displayName: Download ${{ dependency }}
+    retryCountOnTaskFailure: 3
     inputs:
       project: ROCm-CI
       buildType: specific
@@ -28,7 +33,7 @@ steps:
     inputs:
       archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
       destinationFolder: $(Agent.BuildDirectory)/vendor
-      cleanDestinationFolder: true
+      cleanDestinationFolder: false
       overwriteExistingFiles: true
   - task: DeleteFiles@1
     displayName: Clean up ${{ dependency }}

.azuredevops/templates/steps/local-artifact-download.yml

@@ -33,6 +33,7 @@ parameters:
 steps:
   - task: DownloadPipelineArtifact@2
     displayName: Download ${{ parameters.preTargetFilter}}*${{ parameters.os }}_${{ parameters.gpuTarget}}*${{ parameters.postTargetFilter}}
+    retryCountOnTaskFailure: 3
     inputs:
       ${{ if eq(parameters.buildType, 'specific') }}:
         buildType: specific

.azuredevops/templates/steps/manifest.yml

@@ -23,13 +23,14 @@ steps:
   inputs:
     targetType: inline
     script: |
-      sudo apt-get install -y jq
+      ${{ iif(or(eq(parameters.os, 'ubuntu2204'), eq(parameters.os, 'ubuntu2404')), 'sudo apt-get install -y jq', '') }}
 
       # RESOURCES_REPOSITORIES is a runtime variable (not an env var!) that contains quotations and newlines
       # So we need to save it to a file to properly preserve its formatting and contents
       cat <<EOF > resources.repositories
       $(RESOURCES_REPOSITORIES)
       EOF
+      echo "Value of resources.repositories:"
       cat resources.repositories
 
       IS_TAG_BUILD=$(jq 'has("release_repo")' resources.repositories)
@@ -66,8 +67,6 @@ steps:
         )
       ' resources.repositories)
 
-      manifest_json=$(Build.ArtifactStagingDirectory)/manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.json
-
       dependencies=()
       for manifest_file in $(Pipeline.Workspace)/d/**/manifest_*.json; do
         echo "Processing $manifest_file"
@@ -78,6 +77,10 @@ steps:
       done
       dependencies_json=$(printf '%s\n' "${dependencies[@]}" | jq -s '.')
 
+      manifest_filename="manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}"
+      echo "##vso[task.setvariable variable=manifest_filename]$manifest_filename"
+      manifest_json=$(Build.ArtifactStagingDirectory)/$manifest_filename.json
+
       jq -n \
         --argjson current "$current" \
         --argjson dependencies "$dependencies_json" \
@@ -111,8 +114,14 @@ steps:
         ')
       dependencies_rows=$(echo $dependencies_rows)
       echo "##vso[task.setvariable variable=dependencies_rows;]$dependencies_rows"
-
+- task: Bash@3
-      cat $manifest_json
+  displayName: Print manifest.json
+  condition: always()
+  continueOnError: true
+  inputs:
+    targetType: inline
+    script: |
+      cat $(Build.ArtifactStagingDirectory)/$(manifest_filename).json
 - task: Bash@3
   displayName: Create manifest.html
   condition: always()
@@ -120,10 +129,10 @@ steps:
   inputs:
     targetType: inline
     script: |
-      manifest_html=$(Build.ArtifactStagingDirectory)/manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html
+      manifest_html="$(Build.ArtifactStagingDirectory)/$(manifest_filename).html"
       cat <<EOF > $manifest_html
       <html>
-      <h1>Manifest</h1>
+      <h1>$(manifest_filename)</h1>
       <h2>Current</h2>
       <table border="1">
       <tr>
@@ -163,7 +172,7 @@ steps:
   continueOnError: true
   inputs:
     tabName: Manifest
-    reportDir: $(Build.ArtifactStagingDirectory)/manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html
+    reportDir: $(Build.ArtifactStagingDirectory)/$(manifest_filename).html
 - task: Bash@3
   displayName: Save manifest artifact file name
   condition: always()
@@ -172,5 +181,5 @@ steps:
     workingDirectory: $(Pipeline.Workspace)
     targetType: inline
     script: |
-      echo "manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html" >> pipelineArtifacts.txt
+      echo "$(manifest_filename).html" >> pipelineArtifacts.txt
-      echo "manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.json" >> pipelineArtifacts.txt
+      echo "$(manifest_filename).json" >> pipelineArtifacts.txt

.azuredevops/templates/steps/miopen-get-ck-build.yml

@@ -7,17 +7,16 @@ steps:
 - task: Bash@3
   name: downloadCKBuild
   displayName: Download specific CK build
-  continueOnError: true
+  retryCountOnTaskFailure: 3
   env:
     CXX: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
     CC: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
   inputs:
     targetType: inline
-    workingDirectory: $(Build.SourcesDirectory)
+    workingDirectory: $(Agent.BuildDirectory)/s
     script: |
       AZ_API="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis"
       GH_API="https://api.github.com/repos/ROCm"
-      ARTIFACT_NAME="composablekernelbuild${{ parameters.gpuTarget }}"
       EXIT_CODE=0
 
       # Try to find an Azure build for the specific CK commit called out in MIOpen's requirements.txt
@@ -39,8 +38,15 @@ steps:
         echo "Found specific CK build ID: $CK_BUILD_ID"
       fi
 
-      AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?artifactName=$ARTIFACT_NAME&api-version=7.1"
+      AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?api-version=7.1"
-      ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
+      ARTIFACT_URL=$(curl -s $AZURE_URL | \
+        jq --arg gfx "${{ parameters.gpuTarget }}" '
+          .value
+          | map(select(.name | test($gfx)))
+          | max_by(.name | capture("_(?<dropNumber>\\d+)").dropNumber | tonumber)
+          | .resource.downloadUrl
+        ' | \
+        tr -d '"')
 
       # If using the specific CK commit and it doesn't have any valid artifacts, use latest successful CK build instead
       if { [[ -z "$ARTIFACT_URL" ]] || [[ "$ARTIFACT_URL" == "null" ]]; } && [[ $EXIT_CODE -eq 0 ]]; then
@@ -48,17 +54,45 @@ steps:
         LATEST_BUILD_URL="$AZ_API/build/builds?definitions=$(COMPOSABLE_KERNEL_PIPELINE_ID)&statusFilter=completed&resultFilter=succeeded&\$top=1&api-version=7.1"
         CK_BUILD_ID=$(curl -s $LATEST_BUILD_URL | jq '.value[0].id')
         echo "Found latest CK build ID: $CK_BUILD_ID"
-        AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?artifactName=$ARTIFACT_NAME&api-version=7.1"
+        AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?api-version=7.1"
-        ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
+        ARTIFACT_URL=$(curl -s $AZURE_URL | \
+          jq --arg os "ubuntu2204" --arg gfx "${{ parameters.gpuTarget }}" '
+            .value
+            | map(select(.name | test($os) and test($gfx)))
+            | max_by(.name | capture("_(?<dropNumber>\\d+)").dropNumber | tonumber)
+            | .resource.downloadUrl
+          ' | \
+          tr -d '"')
         EXIT_CODE=2
       fi
 
       echo "Downloading CK artifact from $ARTIFACT_URL"
-      wget --tries=5 --waitretry=10 --retry-connrefused -nv $ARTIFACT_URL -O $(System.ArtifactsDirectory)/ck.zip
+
-      unzip $(System.ArtifactsDirectory)/ck.zip -d $(System.ArtifactsDirectory)
+      RETRIES=0
-      mkdir -p $(Agent.BuildDirectory)/rocm
+      MAX_RETRIES=5
-      tar -zxvf $(System.ArtifactsDirectory)/$ARTIFACT_NAME/*.tar.gz -C $(Agent.BuildDirectory)/rocm
+      SUCCESS=false
-      rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/$ARTIFACT_NAME
+      while [ $RETRIES -lt $MAX_RETRIES ]; do
+        wget -nv $ARTIFACT_URL -O $(System.ArtifactsDirectory)/ck.zip && \
+          unzip $(System.ArtifactsDirectory)/ck.zip -d $(System.ArtifactsDirectory) && \
+          mkdir -p $(Agent.BuildDirectory)/rocm && \
+          tar -zxvf $(System.ArtifactsDirectory)/composable_kernel*/*.tar.gz -C $(Agent.BuildDirectory)/rocm && \
+          rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/composable_kernel*
+
+        if [ $? -eq 0 ]; then
+          SUCCESS=true
+          echo "Successfully downloaded CK."
+          break
+        else
+          RETRIES=$((RETRIES + 1))
+          echo "Failed to download CK on attempt $RETRIES/$MAX_RETRIES, retrying..."
+          sleep 1
+        fi
+      done
+
+      if [ "$SUCCESS" = false ]; then
+        echo "ERROR: failed to download CK after $MAX_RETRIES attempts."
+        exit 1
+      fi
 
       if [[ $EXIT_CODE -ne 0 ]]; then
         BUILD_COMMIT=$(curl -s $AZ_API/build/builds/$CK_BUILD_ID | jq '.sourceVersion' | tr -d '"')
@@ -69,4 +103,3 @@ steps:
         fi
         echo "Instead used latest CK build $CK_BUILD_ID for commit $BUILD_COMMIT"
       fi
-      exit $EXIT_CODE

.azuredevops/templates/steps/test.yml

@@ -13,7 +13,7 @@ parameters:
   default: ctest
 - name: testParameters
   type: string
-  default: --output-on-failure --force-new-ctest-process --output-junit test_output.xml
+  default: --extra-verbose --output-on-failure --force-new-ctest-process --output-junit test_output.xml
 - name: extraTestParameters
   type: string
   default: ''

.azuredevops/variables-global.yml

@@ -23,145 +23,25 @@ variables:
   value: rocm-ci_high_build_pool
 - name: ULTRA_BUILD_POOL
   value: rocm-ci_ultra_build_pool
-- name: ON_PREM_BUILD_POOL
-  value: rocm-ci_build_pool
-- name: LARGE_DISK_BUILD_POOL
-  value: rocm-ci_larger_base_disk_pool
 - name: GFX942_TEST_POOL
   value: gfx942_test_pool
 - name: GFX90A_TEST_POOL
   value: gfx90a_test_pool
 - name: LATEST_RELEASE_VERSION
-  value: 6.4.1
+  value: 6.4.3
 - name: REPO_RADEON_VERSION
-  value: 6.4.1
+  value: 6.4.3
 - name: NEXT_RELEASE_VERSION
   value: 7.0.0
 - name: LATEST_RELEASE_TAG
-  value: rocm-6.4.1
+  value: rocm-6.4.3
 - name: DOCKER_SKIP_GFX
   value: gfx90a
-- name: AMDMIGRAPHX_PIPELINE_ID
-  value: 113
-- name: AMDSMI_PIPELINE_ID
-  value: 99
-- name: AOMP_EXTRAS_PIPELINE_ID
-  value: 111
-- name: AOMP_PIPELINE_ID
-  value: 115
-- name: CLR_PIPELINE_ID
-  value: 145
 - name: COMPOSABLE_KERNEL_PIPELINE_ID
   value: 86
-- name: FLANG_LEGACY_PIPELINE_ID
-  value: 77
-- name: HALF_PIPELINE_ID
-  value: 101
 - name: HALF560_PIPELINE_ID
   value: 68
 - name: HALF560_BUILD_ID
   value: 621
 - name: HIP_PIPELINE_ID
   value: 93
-- name: HIP_TESTS_PIPELINE_ID
-  value: 233
-- name: HIPBLAS_COMMON_PIPELINE_ID
-  value: 223
-- name: HIPBLAS_PIPELINE_ID
-  value: 87
-- name: HIPBLASLT_PIPELINE_ID
-  value: 112
-- name: HIPCUB_PIPELINE_ID
-  value: 277
-- name: HIPFFT_PIPELINE_ID
-  value: 121
-- name: HIPFORT_PIPELINE_ID
-  value: 102
-- name: HIPIFY_PIPELINE_ID
-  value: 92
-- name: HIPRAND_PIPELINE_ID
-  value: 275
-- name: HIPSOLVER_PIPELINE_ID
-  value: 84
-- name: HIPSPARSE_PIPELINE_ID
-  value: 83
-- name: HIPSPARSELT_PIPELINE_ID
-  value: 104
-- name: HIPTENSOR_PIPELINE_ID
-  value: 105
-- name: LLVM_PROJECT_PIPELINE_ID
-  value: 2
-- name: MIOPEN_PIPELINE_ID
-  value: 108
-- name: MIVISIONX_PIPELINE_ID
-  value: 80
-- name: RCCL_PIPELINE_ID
-  value: 107
-- name: RDC_PIPELINE_ID
-  value: 100
-- name: ROCAL_PIPELINE_ID
-  value: 151
-- name: ROCALUTION_PIPELINE_ID
-  value: 89
-- name: ROCBLAS_PIPELINE_ID
-  value: 85
-- name: ROCDBGAPI_PIPELINE_ID
-  value: 135
-- name: ROCDECODE_PIPELINE_ID
-  value: 79
-- name: ROCFFT_PIPELINE_ID
-  value: 120
-- name: ROCGDB_PIPELINE_ID
-  value: 134
-- name: ROCJPEG_PIPELINE_ID
-  value: 262
-- name: ROCM_BANDWIDTH_TEST_PIPELINE_ID
-  value: 88
-- name: ROCM_CMAKE_PIPELINE_ID
-  value: 6
-- name: ROCM_CORE_PIPELINE_ID
-  value: 103
-- name: ROCM_EXAMPLES_PIPELINE_ID
-  value: 216
-- name: ROCM_SMI_LIB_PIPELINE_ID
-  value: 96
-- name: ROCMINFO_PIPELINE_ID
-  value: 91
-- name: ROCMLIR_PIPELINE_ID
-  value: 229
-- name: ROCMVALIDATIONSUITE_PIPELINE_ID
-  value: 106
-- name: ROCPRIM_PIPELINE_ID
-  value: 273
-- name: ROCPROFILER_COMPUTE_PIPELINE_ID
-  value: 257
-- name: ROCPROFILER_REGISTER_PIPELINE_ID
-  value: 1
-- name: ROCPROFILER_SDK_PIPELINE_ID
-  value: 246
-- name: ROCPROFILER_SYSTEMS_PIPELINE_ID
-  value: 255
-- name: ROCPROFILER_PIPELINE_ID
-  value: 143
-- name: ROCPYDECODE_PIPELINE_ID
-  value: 239
-- name: ROCR_DEBUG_AGENT_PIPELINE_ID
-  value: 136
-- name: ROCR_RUNTIME_PIPELINE_ID
-  value: 10
-- name: ROCRAND_PIPELINE_ID
-  value: 274
-- name: ROCSOLVER_PIPELINE_ID
-  value: 81
-- name: ROCSPARSE_PIPELINE_ID
-  value: 98
-- name: ROCTHRUST_PIPELINE_ID
-  value: 276
-- name: ROCTRACER_PIPELINE_ID
-  value: 141
-- name: ROCWMMA_PIPELINE_ID
-  value: 109
-- name: RPP_PIPELINE_ID
-  value: 78
-- name: TRANSFERBENCH_PIPELINE_ID
-  value: 265

.gitignore

@@ -1,6 +1,7 @@
 .venv
 .vscode
 build
+__pycache__
 
 # documentation artifacts
 _build/

.wordlist.txt

@@ -1,44 +1,3 @@
-GovReport
-MLPerf
-QKV
-summarization
-gpt
-openai
-oss
-MXFP
-SGLang
-VMware
-amd
-bdf
-compatiblity
-csv
-enum
-json
-subproject
-ROCpd
-rocpd
-STL
-XCCs
-chiplets
-hipRTC
-nvRTC
-warpSize
-Datacenter
-GST
-IET
-LTO
-MX
-Microscaling
-NANOO
-ROCprof
-affinitization
-amdclang
-benefitting
-demangled
-inlined
-microscaling
-roofline
-torchtitan
 AAC
 ABI
 ACE
@@ -46,7 +5,9 @@ ACEs
 ACS
 AccVGPR
 AccVGPRs
+AITER
 ALU
+AllReduce
 AMD
 AMDGPU
 AMDGPUs
@@ -54,6 +15,7 @@ AMDMIGraphX
 AMI
 AOCC
 AOMP
+AOT
 AOTriton
 APBDIS
 APIC
@@ -65,6 +27,7 @@ ASICs
 ASan
 ASAN
 ASm
+Async
 ATI
 atomicRMW
 AddressSanitizer
@@ -72,7 +35,10 @@ AlexNet
 Andrej
 Arb
 Autocast
+autograd
+Backported
 BARs
+BatchNorm
 BLAS
 BMC
 BabelStream
@@ -80,9 +46,11 @@ Blit
 Blockwise
 Bluefield
 Bootloader
+Broadcom
 CAS
 CCD
 CDNA
+CGUI
 CHTML
 CIFAR
 CLI
@@ -98,6 +66,7 @@ CPU
 CPUs
 Cron
 CSC
+CSDATA
 CSE
 CSV
 CSn
@@ -107,6 +76,7 @@ CU
 CUDA
 CUs
 CXX
+CX
 Cavium
 CentOS
 ChatGPT
@@ -117,19 +87,26 @@ CommonMark
 Concretized
 Conda
 ConnectX
+CountOnes
 CuPy
+customizable
 da
 Dashboarding
+Dataloading
+dataflows
 DBRX
 DDR
 DF
 DGEMM
+DGL
+DGLGraph
 dGPU
 dGPUs
 DIMM
 DKMS
 DL
 DMA
+DOMContentLoaded
 DNN
 DNNL
 DPM
@@ -141,20 +118,30 @@ DataFrame
 DataLoader
 DataParallel
 Debian
+decompositions
 DeepSeek
 DeepSpeed
 Dependabot
 Deprecations
 DevCap
 DirectX
+Disaggregated
+disaggregated
 Dockerfile
+Dockerized
 Doxygen
+dropless
 ELMo
 ENDPGM
 EPYC
 ESXi
+EP
 EoS
+etcd
+fas
 FBGEMM
+FiLM
+FIFOs
 FFT
 FFTs
 FFmpeg
@@ -166,14 +153,20 @@ FX
 Filesystem
 FindDb
 Flang
+FlashAttention
+FlashInfer’s
+FlashInfer
 FluxBenchmark
 Fortran
 Fuyu
 GALB
+GAT
+GATNE
 GCC
 GCD
 GCDs
 GCN
+GCNN
 GDB
 GDDR
 GDR
@@ -183,6 +176,7 @@ GEMMs
 GFLOPS
 GFortran
 GFXIP
+GGUF
 Gemma
 GiB
 GIM
@@ -191,24 +185,34 @@ Glibc
 GLXT
 Gloo
 GMI
+GNN
+GNNs
 GPG
 GPR
 GPT
 GPU
 GPU's
+GPUDirect
 GPUs
+GraphBolt
+GraphSage
 GRBM
+GRE
 GenAI
 GenZ
 GitHub
 Gitpod
+hardcoded
 HBM
 HCA
 HGX
+HLO
 HIPCC
+hipDataType
 HIPExtension
 HIPIFY
 HIPification
+hipification
 HIPify
 HPC
 HPCG
@@ -220,17 +224,24 @@ HWE
 HWS
 Haswell
 Higgs
+href
 Hyperparameters
+HybridEngine
 Huggingface
+IB
 ICD
+ICT
 ICV
 IDE
 IDEs
 IFWI
 IMDb
 IncDec
+instrSize
+interpolators
 IOMMU
 IOP
+IOPS
 IOPM
 IOV
 IRQ
@@ -247,6 +258,7 @@ Intersphinx
 Intra
 Ioffe
 JAX's
+JAXLIB
 Jinja
 JSON
 Jupyter
@@ -257,6 +269,7 @@ KV
 KVM
 Karpathy's
 KiB
+Kineto
 Keras
 Khronos
 LAPACK
@@ -266,11 +279,15 @@ LLM
 LLMs
 LLVM
 LM
+LRU
 LSAN
 LSan
 LTS
+LSTMs
+LteAll
 LanguageCrossEntropy
 LoRA
+MECO
 MEM
 MERCHANTABILITY
 MFMA
@@ -289,6 +306,7 @@ MNIST
 MPI
 MPT
 MSVC
+mul
 MVAPICH
 MVFFR
 Makefile
@@ -296,6 +314,8 @@ Makefiles
 Matplotlib
 Matrox
 MaxText
+MBT
+Megablocks
 Megatrends
 Megatron
 Mellanox
@@ -304,11 +324,18 @@ Meta's
 Miniconda
 MirroredStrategy
 Mixtral
+MLA
 MosaicML
+MoEs
+Mooncake
+Mpops
 Multicore
+multihost
 Multithreaded
+MXFP
 MyEnvironment
 MyST
+NANOO
 NBIO
 NBIOs
 NCCL
@@ -318,6 +345,7 @@ NIC
 NICs
 NLI
 NLP
+NN
 NPKit
 NPS
 NSP
@@ -340,6 +368,7 @@ OFED
 OMM
 OMP
 OMPI
+OOM
 OMPT
 OMPX
 ONNX
@@ -354,6 +383,7 @@ OpenMPI
 OpenSSL
 OpenVX
 OpenXLA
+Optim
 Oversubscription
 PagedAttention
 Pallas
@@ -361,9 +391,11 @@ PCC
 PCI
 PCIe
 PEFT
+perf
 PEQT
 PIL
 PILImage
+PJRT
 POR
 PRNG
 PRs
@@ -378,10 +410,12 @@ PowerEdge
 PowerShell
 Pretrained
 Pretraining
+Primus
 Profiler's
 PyPi
 Pytest
 PyTorch
+QPS
 Qcycles
 Qwen
 RAII
@@ -392,6 +426,7 @@ RDC's
 RDMA
 RDNA
 README
+Recomputation
 RHEL
 RMW
 RNN
@@ -424,11 +459,13 @@ Ryzen
 SALU
 SBIOS
 SCA
+ScaledGEMM
 SDK
 SDMA
 SDPA
 SDRAM
 SENDMSG
+SGLang
 SGPR
 SGPRs
 SHA
@@ -440,7 +477,9 @@ SKU
 SKUs
 SLES
 SLURM
+Slurm
 SMEM
+SMFMA
 SMI
 SMT
 SPI
@@ -452,18 +491,26 @@ SWE
 SerDes
 ShareGPT
 Shlens
+simd
 Skylake
 Softmax
 Spack
 SplitK
 Supermicro
 Szegedy
+TagRAM
 TCA
 TCC
+TCCs
 TCI
 TCIU
 TCP
 TCR
+TVM
+THREADGROUPS
+threadgroups
+TensorRT
+TensorFloat
 TF
 TFLOPS
 TP
@@ -503,9 +550,11 @@ UltraChat
 Uncached
 Unittests
 Unhandled
+unwindowed
 VALU
 VBIOS
 VCN
+verl's
 VGPR
 VGPRs
 VM
@@ -518,11 +567,13 @@ Vanhoucke
 Vulkan
 WGP
 WGPs
+WR
 WX
 WikiText
 Wojna
 Workgroups
 Writebacks
+xcc
 XCD
 XCDs
 XGBoost
@@ -535,6 +586,7 @@ Xilinx
 Xnack
 Xteam
 YAML
+YAMLs
 YML
 YModel
 ZeRO
@@ -542,6 +594,7 @@ ZenDNN
 accuracies
 activations
 addr
+addEventListener
 ade
 ai
 alloc
@@ -550,12 +603,14 @@ allocator
 allocators
 amdgpu
 api
+aten
 atmi
 atomics
 autogenerated
 autotune
 avx
 awk
+az
 backend
 backends
 bb
@@ -573,6 +628,7 @@ boson
 bosons
 br
 BrainFloat
+btn
 buildable
 bursty
 bzip
@@ -584,17 +640,21 @@ centric
 changelog
 checkpointing
 chiplet
+classList
 cmake
 cmd
 coalescable
 codename
 collater
 comgr
+compat
 completers
 composable
 concretization
 config
+configs
 conformant
+const
 constructible
 convolutional
 convolves
@@ -629,12 +689,14 @@ denoised
 denoises
 denormalize
 dequantization
+dequantized
 dequantizes
 deserializers
 detections
 dev
 devicelibs
 devsel
+dgl
 dimensionality
 disambiguates
 distro
@@ -658,6 +720,7 @@ exascale
 executables
 ffmpeg
 filesystem
+forEach
 fortran
 fp
 framebuffer
@@ -666,13 +729,16 @@ galb
 gcc
 gdb
 gemm
+getAttribute
 gfortran
 gfx
 githooks
 github
 globals
 gnupg
+gpu
 grayscale
+gx
 gzip
 heterogenous
 hipBLAS
@@ -720,10 +786,12 @@ installable
 interop
 interprocedural
 intra
+intrinsics
 invariants
 invocating
 ipo
 jax
+json
 kdb
 kfd
 kv
@@ -737,12 +805,17 @@ linalg
 linearized
 linter
 linux
+llm
 llvm
+lm
 localscratch
 logits
 lossy
 macOS
 matchers
+maxtext
+megablocks
+megatron
 microarchitecture
 migraphx
 migratable
@@ -770,6 +843,7 @@ opencv
 openmp
 openssl
 optimizers
+ol
 os
 oversubscription
 pageable
@@ -779,8 +853,10 @@ parallelizing
 param
 parameterization
 passthrough
+pe
 perfcounter
 performant
+piecewise
 perl
 pragma
 pre
@@ -801,11 +877,14 @@ preprocessing
 preprocessor
 prequantized
 prerequisites
+pretrain
 pretraining
+primus
 profiler
 profilers
 protobuf
 pseudorandom
+px
 py
 pytorch
 recommender
@@ -813,7 +892,10 @@ recommenders
 quantile
 quantizer
 quasirandom
+querySelector
+querySelectorAll
 queueing
+qwen
 radeon
 rccl
 rdc
@@ -822,6 +904,7 @@ reStructuredText
 redirections
 refactorization
 reformats
+reinforcememt
 repo
 repos
 representativeness
@@ -829,6 +912,9 @@ req
 resampling
 rescaling
 reusability
+rhel
+rl
+RLHF
 roadmap
 roc
 rocAL
@@ -866,22 +952,29 @@ roctracer
 rst
 runtime
 runtimes
+ResNet
 sL
 scalability
 scalable
 scipy
 seealso
+selectedTag
 sendmsg
 seqs
 serializers
+setAttribute
+sglang
 shader
 sharding
 sigmoid
+sles
 sm
 smi
 softmax
 spack
+spmm
 src
+stanford
 stochastically
 strided
 subcommand
@@ -889,6 +982,7 @@ subdirectory
 subexpression
 subfolder
 subfolders
+submatrix
 submodule
 submodules
 subnet
@@ -897,8 +991,10 @@ symlink
 symlinks
 sys
 tabindex
+targetContainer
 td
 tensorfloat
+tf
 th
 tokenization
 tokenize
@@ -907,18 +1003,23 @@ tokenizer
 tokenizes
 toolchain
 toolchains
+topk
 toolset
 toolsets
+torchtitan
 torchvision
+tp
 tqdm
 tracebacks
 txt
+TopK
 uarch
 uncached
 uncacheable
 uncorrectable
 underoptimized
 unhandled
+unfused
 uninstallation
 unmapped
 unsqueeze
@@ -931,6 +1032,7 @@ USM
 UTCL
 UTIL
 utils
+UX
 vL
 variational
 vdi
@@ -940,6 +1042,7 @@ vectorize
 vectorized
 vectorizer
 vectorizes
+verl
 virtualize
 virtualized
 vjxb

README.md

@@ -23,9 +23,6 @@ source software compilers, debuggers, and libraries. ROCm is fully integrated in
 > A new open source build platform for ROCm is under development at
 > https://github.com/ROCm/TheRock, featuring a unified CMake build with bundled
 > dependencies, Windows support, and more.
->
-> The instructions below describe the prior process for building from source
-> which will be replaced once TheRock is mature enough.
 
 ## Getting and Building ROCm from Source
 

default.xml

@@ -1,32 +1,17 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.4.1"
+    <default revision="refs/tags/rocm-7.1.0"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />
 <!--list of projects for ROCm-->
     <project name="ROCK-Kernel-Driver" />
-    <project name="ROCR-Runtime" />
     <project name="amdsmi" />
-    <project name="rdc" />
     <project name="rocm_bandwidth_test" />
-    <project name="rocm_smi_lib" />
-    <project name="rocm-core" />
     <project name="rocm-examples" />
-    <project name="rocminfo" />
-    <project name="rocprofiler" />
-    <project name="rocprofiler-register" />
-    <project name="rocprofiler-sdk" />
-    <project name="rocprofiler-compute" />
-    <project name="rocprofiler-systems" />
-    <project name="roctracer" />
 <!--HIP Projects-->
-    <project name="HIP" />
-    <project name="hip-tests" />
     <project name="HIPIFY" />
-    <project name="clr" />
-    <project name="hipother" />
 <!-- The following projects are all associated with the AMDGPU LLVM compiler -->
     <project name="half" />
     <project name="llvm-project" />
@@ -37,36 +22,30 @@
     <project name="rocr_debug_agent" />
 <!-- ROCm Libraries -->
     <project groups="mathlibs" name="AMDMIGraphX" />
-    <project groups="mathlibs" name="MIOpen" />
     <project groups="mathlibs" name="MIVisionX" />
     <project groups="mathlibs" name="ROCmValidationSuite" />
-    <project groups="mathlibs" name="Tensile" />
     <project groups="mathlibs" name="composable_kernel" />
-    <project groups="mathlibs" name="hipBLAS-common" />
-    <project groups="mathlibs" name="hipBLAS" />
-    <project groups="mathlibs" name="hipBLASLt" />
-    <project groups="mathlibs" name="hipCUB" />
-    <project groups="mathlibs" name="hipFFT" />
-    <project groups="mathlibs" name="hipRAND" />
-    <project groups="mathlibs" name="hipSOLVER" />
-    <project groups="mathlibs" name="hipSPARSE" />
-    <project groups="mathlibs" name="hipSPARSELt" />
     <project groups="mathlibs" name="hipTensor" />
     <project groups="mathlibs" name="hipfort" />
     <project groups="mathlibs" name="rccl" />
     <project groups="mathlibs" name="rocAL" />
     <project groups="mathlibs" name="rocALUTION" />
-    <project groups="mathlibs" name="rocBLAS" />
     <project groups="mathlibs" name="rocDecode" />
     <project groups="mathlibs" name="rocJPEG" />
+    <!-- The following components have been migrated to rocm-libraries:
+        hipBLAS-common hipBLAS hipBLASLt hipCUB
+        hipFFT hipRAND hipSPARSE hipSPARSELt
+        MIOpen rocBLAS rocFFT rocPRIM rocRAND
+        rocSPARSE rocThrust Tensile -->
+    <project groups="mathlibs" name="rocm-libraries" />
+    <!-- The following components have been migrated to rocm-systems:
+        aqlprofile clr hip hip-tests hipother
+        rdc rocm-core rocm_smi_lib rocminfo rocprofiler-compute 
+        rocprofiler-register rocprofiler-sdk rocprofiler-systems 
+        rocprofiler rocr-runtime roctracer -->
+    <project groups="mathlibs" name="rocm-systems" />
     <project groups="mathlibs" name="rocPyDecode" />
-    <project groups="mathlibs" name="rocFFT" />
-    <project groups="mathlibs" name="rocPRIM" />
-    <project groups="mathlibs" name="rocRAND" />
     <project groups="mathlibs" name="rocSHMEM" />
-    <project groups="mathlibs" name="rocSOLVER" />
-    <project groups="mathlibs" name="rocSPARSE" />
-    <project groups="mathlibs" name="rocThrust" />
     <project groups="mathlibs" name="rocWMMA" />
     <project groups="mathlibs" name="rocm-cmake" />
     <project groups="mathlibs" name="rpp" />

docs/about/license.md

@@ -0,0 +1,147 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="ROCm licensing terms">
+  <meta name="keywords" content="license, licensing terms">
+</head>
+
+# ROCm license
+
+```{include} ../../LICENSE
+```
+
+:::{note}
+The preceding license applies to the [ROCm repository](https://github.com/ROCm/ROCm), which
+primarily contains documentation. For licenses related to other ROCm components, refer to the
+following section.
+:::
+
+## ROCm component licenses
+
+ROCm is released by Advanced Micro Devices, Inc. (AMD) and is licensed per component separately.
+The following table is a list of ROCm components with links to their respective license
+terms. These components may include third party components subject to
+additional licenses. Please review individual repositories for more information.
+
+<!-- spellcheck-disable -->
+| Component | License |
+|:---------------------|:-------------------------|
+| [AMD Compute Language Runtime (CLR)](https://github.com/ROCm/clr) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/LICENSE.txt) |
+| [AMD SMI](https://github.com/ROCm/amdsmi) | [MIT](https://github.com/ROCm/amdsmi/blob/amd-staging/LICENSE) |
+| [aomp](https://github.com/ROCm/aomp/) | [Apache 2.0](https://github.com/ROCm/aomp/blob/aomp-dev/LICENSE) |
+| [aomp-extras](https://github.com/ROCm/aomp-extras/) | [MIT](https://github.com/ROCm/aomp-extras/blob/aomp-dev/LICENSE) |
+| [AQLprofile](https://github.com/rocm/aqlprofile/) | [MIT](https://github.com/ROCm/aqlprofile/blob/amd-staging/LICENSE.md) |
+| [Code Object Manager (Comgr)](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/comgr) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/comgr/LICENSE.txt) |
+| [Composable Kernel](https://github.com/ROCm/composable_kernel) | [MIT](https://github.com/ROCm/composable_kernel/blob/develop/LICENSE) |
+| [half](https://github.com/ROCm/half/) | [MIT](https://github.com/ROCm/half/blob/rocm/LICENSE.txt) |
+| [HIP](https://github.com/ROCm/HIP/) | [MIT](https://github.com/ROCm/HIP/blob/amd-staging/LICENSE.txt) |
+| [hipamd](https://github.com/ROCm/clr/tree/amd-staging/hipamd) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/hipamd/LICENSE.txt) |
+| [hipBLAS](https://github.com/ROCm/hipBLAS/) | [MIT](https://github.com/ROCm/hipBLAS/blob/develop/LICENSE.md) |
+| [hipBLASLt](https://github.com/ROCm/hipBLASLt/) | [MIT](https://github.com/ROCm/hipBLASLt/blob/develop/LICENSE.md) |
+| [HIPCC](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/hipcc) | [MIT](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/hipcc/LICENSE.txt) |
+| [hipCUB](https://github.com/ROCm/hipCUB/) | [Custom](https://github.com/ROCm/hipCUB/blob/develop/LICENSE.txt) |
+| [hipFFT](https://github.com/ROCm/hipFFT/) | [MIT](https://github.com/ROCm/hipFFT/blob/develop/LICENSE.md) |
+| [hipfort](https://github.com/ROCm/hipfort/) | [MIT](https://github.com/ROCm/hipfort/blob/develop/LICENSE) |
+| [HIPIFY](https://github.com/ROCm/HIPIFY/) | [MIT](https://github.com/ROCm/HIPIFY/blob/amd-staging/LICENSE.txt) |
+| [hipRAND](https://github.com/ROCm/hipRAND/) | [MIT](https://github.com/ROCm/hipRAND/blob/develop/LICENSE.txt) |
+| [hipSOLVER](https://github.com/ROCm/hipSOLVER/) | [MIT](https://github.com/ROCm/hipSOLVER/blob/develop/LICENSE.md) |
+| [hipSPARSE](https://github.com/ROCm/hipSPARSE/) | [MIT](https://github.com/ROCm/hipSPARSE/blob/develop/LICENSE.md) |
+| [hipSPARSELt](https://github.com/ROCm/hipSPARSELt/) | [MIT](https://github.com/ROCm/hipSPARSELt/blob/develop/LICENSE.md) |
+| [hipTensor](https://github.com/ROCm/hipTensor) | [MIT](https://github.com/ROCm/hipTensor/blob/develop/LICENSE) |
+| [llvm-project](https://github.com/ROCm/llvm-project/) | [Apache](https://github.com/ROCm/llvm-project/blob/amd-staging/LICENSE.TXT) |
+| [llvm-project/flang](https://github.com/ROCm/llvm-project/tree/amd-staging/flang) | [Apache 2.0](https://github.com/ROCm/llvm-project/blob/amd-staging/flang/LICENSE.TXT) |
+| [MIGraphX](https://github.com/ROCm/AMDMIGraphX/) | [MIT](https://github.com/ROCm/AMDMIGraphX/blob/develop/LICENSE) |
+| [MIOpen](https://github.com/ROCm/MIOpen/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/miopen/LICENSE.md) |
+| [MIVisionX](https://github.com/ROCm/MIVisionX/) | [MIT](https://github.com/ROCm/MIVisionX/blob/develop/LICENSE.txt) |
+| [rocAL](https://github.com/ROCm/rocAL) | [MIT](https://github.com/ROCm/rocAL/blob/develop/LICENSE.txt) |
+| [rocALUTION](https://github.com/ROCm/rocALUTION/) | [MIT](https://github.com/ROCm/rocALUTION/blob/develop/LICENSE.md) |
+| [rocBLAS](https://github.com/ROCm/rocBLAS/) | [MIT](https://github.com/ROCm/rocBLAS/blob/develop/LICENSE.md) |
+| [ROCdbgapi](https://github.com/ROCm/ROCdbgapi/) | [MIT](https://github.com/ROCm/ROCdbgapi/blob/amd-staging/LICENSE.txt) |
+| [rocDecode](https://github.com/ROCm/rocDecode) | [MIT](https://github.com/ROCm/rocDecode/blob/develop/LICENSE) |
+| [rocFFT](https://github.com/ROCm/rocFFT/) | [MIT](https://github.com/ROCm/rocFFT/blob/develop/LICENSE.md) |
+| [ROCgdb](https://github.com/ROCm/ROCgdb/) | [GNU General Public License v3.0](https://github.com/ROCm/ROCgdb/blob/amd-staging/COPYING3) |
+| [rocJPEG](https://github.com/ROCm/rocJPEG/) | [MIT](https://github.com/ROCm/rocJPEG/blob/develop/LICENSE) |
+| [ROCK-Kernel-Driver](https://github.com/ROCm/ROCK-Kernel-Driver/) | [GPL 2.0 WITH Linux-syscall-note](https://github.com/ROCm/ROCK-Kernel-Driver/blob/master/COPYING) |
+| [rocminfo](https://github.com/ROCm/rocminfo/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocminfo/blob/amd-staging/License.txt) |
+| [ROCm Bandwidth Test](https://github.com/ROCm/rocm_bandwidth_test/) | [MIT](https://github.com/ROCm/rocm_bandwidth_test/blob/master/LICENSE.txt) |
+| [ROCm CMake](https://github.com/ROCm/rocm-cmake/) | [MIT](https://github.com/ROCm/rocm-cmake/blob/develop/LICENSE) |
+| [ROCm Communication Collectives Library (RCCL)](https://github.com/ROCm/rccl/) | [Custom](https://github.com/ROCm/rccl/blob/develop/LICENSE.txt) |
+| [ROCm-Core](https://github.com/ROCm/rocm-core) | [MIT](https://github.com/ROCm/rocm-core/blob/master/copyright) |
+| [ROCm Compute Profiler](https://github.com/ROCm/rocprofiler-compute) | [MIT](https://github.com/ROCm/rocprofiler-compute/blob/amd-staging/LICENSE) |
+| [ROCm Data Center (RDC)](https://github.com/ROCm/rdc/) | [MIT](https://github.com/ROCm/rdc/blob/amd-staging/LICENSE.md) |
+| [ROCm-Device-Libs](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/device-libs) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/device-libs/LICENSE.TXT) |
+| [ROCm-OpenCL-Runtime](https://github.com/ROCm/clr/tree/amd-staging/opencl) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/opencl/LICENSE.txt) |
+| [ROCm Performance Primitives (RPP)](https://github.com/ROCm/rpp) | [MIT](https://github.com/ROCm/rpp/blob/develop/LICENSE) |
+| [ROCm SMI Lib](https://github.com/ROCm/rocm_smi_lib/) | [MIT](https://github.com/ROCm/rocm_smi_lib/blob/amd-staging/LICENSE.md) |
+| [ROCm Systems Profiler](https://github.com/ROCm/rocprofiler-systems) | [MIT](https://github.com/ROCm/rocprofiler-systems/blob/amd-staging/LICENSE.md) |
+| [ROCm Validation Suite](https://github.com/ROCm/ROCmValidationSuite/) | [MIT](https://github.com/ROCm/ROCmValidationSuite/blob/master/LICENSE) |
+| [rocPRIM](https://github.com/ROCm/rocPRIM/) | [MIT](https://github.com/ROCm/rocPRIM/blob/develop/LICENSE.txt) |
+| [ROCProfiler](https://github.com/ROCm/rocprofiler/) | [MIT](https://github.com/ROCm/rocprofiler/blob/amd-staging/LICENSE.md) |
+| [ROCprofiler-SDK](https://github.com/ROCm/rocprofiler-sdk) | [MIT](https://github.com/ROCm/rocprofiler-sdk/blob/amd-mainline/LICENSE) |
+| [rocPyDecode](https://github.com/ROCm/rocPyDecode) | [MIT](https://github.com/ROCm/rocPyDecode/blob/develop/LICENSE.txt) |
+| [rocRAND](https://github.com/ROCm/rocRAND/) | [MIT](https://github.com/ROCm/rocRAND/blob/develop/LICENSE.txt) |
+| [ROCr Debug Agent](https://github.com/ROCm/rocr_debug_agent/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocr_debug_agent/blob/amd-staging/LICENSE.txt) |
+| [ROCR-Runtime](https://github.com/ROCm/ROCR-Runtime/) | [The University of Illinois/NCSA](https://github.com/ROCm/ROCR-Runtime/blob/amd-staging/LICENSE.txt) |
+| [rocSHMEM](https://github.com/ROCm/rocSHMEM/) | [MIT](https://github.com/ROCm/rocSHMEM/blob/develop/LICENSE.md) |
+| [rocSOLVER](https://github.com/ROCm/rocSOLVER/) | [BSD-2-Clause](https://github.com/ROCm/rocSOLVER/blob/develop/LICENSE.md) |
+| [rocSPARSE](https://github.com/ROCm/rocSPARSE/) | [MIT](https://github.com/ROCm/rocSPARSE/blob/develop/LICENSE.md) |
+| [rocThrust](https://github.com/ROCm/rocThrust/) | [Apache 2.0](https://github.com/ROCm/rocThrust/blob/develop/LICENSE) |
+| [ROCTracer](https://github.com/ROCm/roctracer/) | [MIT](https://github.com/ROCm/roctracer/blob/amd-master/LICENSE) |
+| [rocWMMA](https://github.com/ROCm/rocWMMA/) | [MIT](https://github.com/ROCm/rocWMMA/blob/develop/LICENSE.md) |
+| [Tensile](https://github.com/ROCm/Tensile/) | [MIT](https://github.com/ROCm/Tensile/blob/develop/LICENSE.md) |
+| [TransferBench](https://github.com/ROCm/TransferBench) | [MIT](https://github.com/ROCm/TransferBench/blob/develop/LICENSE.md) |
+
+Open sourced ROCm components are released via public GitHub
+repositories, packages on [https://repo.radeon.com](https://repo.radeon.com) and other distribution channels.
+Proprietary products are only available on [https://repo.radeon.com](https://repo.radeon.com).
+Proprietary components are organized in a proprietary subdirectory in the package
+repositories to distinguish from open sourced packages.
+
+```{note}
+The following additional terms and conditions apply to your use of ROCm technical documentation.
+```
+
+©2023 - 2025 Advanced Micro Devices, Inc. All rights reserved.
+
+The information presented in this document is for informational purposes only
+and may contain technical inaccuracies, omissions, and typographical errors. The
+information contained herein is subject to change and may be rendered inaccurate
+for many reasons, including but not limited to product and roadmap changes,
+component and motherboard version changes, new model and/or product releases,
+product differences between differing manufacturers, software changes, BIOS
+flashes, firmware upgrades, or the like. Any computer system has risks of
+security vulnerabilities that cannot be completely prevented or mitigated. AMD
+assumes no obligation to update or otherwise correct or revise this information.
+However, AMD reserves the right to revise this information and to make changes
+from time to time to the content hereof without obligation of AMD to notify any
+person of such revisions or changes.
+
+THIS INFORMATION IS PROVIDED “AS IS.” AMD MAKES NO REPRESENTATIONS OR WARRANTIES
+WITH RESPECT TO THE CONTENTS HEREOF AND ASSUMES NO RESPONSIBILITY FOR ANY
+INACCURACIES, ERRORS, OR OMISSIONS THAT MAY APPEAR IN THIS INFORMATION. AMD
+SPECIFICALLY DISCLAIMS ANY IMPLIED WARRANTIES OF NON-INFRINGEMENT,
+MERCHANTABILITY, OR FITNESS FOR ANY PARTICULAR PURPOSE. IN NO EVENT WILL AMD BE
+LIABLE TO ANY PERSON FOR ANY RELIANCE, DIRECT, INDIRECT, SPECIAL, OR OTHER
+CONSEQUENTIAL DAMAGES ARISING FROM THE USE OF ANY INFORMATION CONTAINED HEREIN,
+EVEN IF AMD IS EXPRESSLY ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+AMD, the AMD Arrow logo, ROCm, and combinations thereof are trademarks of
+Advanced Micro Devices, Inc. Other product names used in this publication are
+for identification purposes only and may be trademarks of their respective
+companies.
+
+### Package licensing
+
+:::{attention}
+ROCprof Trace Decoder and AOCC CPU optimizations are provided in binary form, subject to the license agreement enclosed on [GitHub](https://github.com/ROCm/rocprof-trace-decoder/blob/amd-mainline/LICENSE) for ROCprof Trace Decoder, and [Developer Central](https://www.amd.com/en/developer/aocc.html) for AOCC. By using, installing,
+copying or distributing ROCprof Trace Decoder or AOCC CPU Optimizations, you agree to
+the terms and conditions of this license agreement. If you do not agree to the
+terms of this agreement, do not install, copy or use ROCprof Trace Decoder or the
+AOCC CPU Optimizations.
+:::
+
+For the rest of the ROCm packages, you can find the licensing information at the
+following location: `/opt/rocm/share/doc/<component-name>/` or in the locations
+specified in the preceding table.
+
+For example, you can fetch the licensing information of the `amd_comgr`
+component (Code Object Manager) from the `/opt/rocm/share/doc/amd_comgr/LICENSE.txt` file.

docs/benchmark-docker/index.rst

@@ -1,55 +0,0 @@
-***************************************************
-AI training and inference performance with ROCm 7.0
-***************************************************
-
-AMD ROCm is an open-source software platform optimized to extract HPC and AI
-workload performance from AMD Instinct™ accelerators and GPUs while maintaining
-compatibility with industry software frameworks.
-
-.. note::
-
-   ROCm 7.0 is now available. See the documentation at `ROCm 7.0 documentation
-   <https://rocm.docs.amd.com/en/docs-7.0.0/>`__.
-
-This documentation accompanies preview Docker images designed to reproduce
-training and inference performance on AMD Instinct™ MI355X, MI350X, and MI300X
-series accelerators with ROCm 7.0. The images provide the 7.0 release of the
-ROCm software stack and are targeted at users evaluating AI inference workloads
-using next-generation AMD accelerators. See the Docker image repository at
-`rocm/7.0 <https://hub.docker.com/r/rocm/7.0/>`__.
-
-.. important::
-
-   The following AI workload benchmarks use ROCm 7.0 on AMD Instinct MI355X,
-   MI350X, and MI300X series accelerators.
-
-   For other workloads for MI300X series accelerators, see
-   `Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html>`_.
-
-.. grid:: 2
-
-   .. grid-item-card:: Training
-
-      * :doc:`training-maxtext-llama-3`
-
-      * :doc:`training-maxtext-mixtral-8x7b`
-
-      * :doc:`training-megatron-lm-llama-3`
-
-      * :doc:`training-mlperf-fine-tuning-llama-2-70b`
-
-      * :doc:`training-torchtitan-llama-3`
-
-   .. grid-item-card:: Inference
-
-      * :doc:`inference-vllm-llama-3.1-405b-fp4`
-
-      * :doc:`inference-vllm-llama-3.3-70b-fp8`
-
-      * :doc:`inference-vllm-deepseek-r1-fp8`
-
-      * :doc:`inference-vllm-gpt-oss-120b`
-
-      * :doc:`inference-sglang-deepseek-r1-fp4`
-
-      * :doc:`inference-sglang-deepseek-r1-fp8`

docs/benchmark-docker/inference-sglang-deepseek-r1-fp4.rst

@@ -1,99 +0,0 @@
-***********************************************
-Benchmark DeepSeek R1 FP4 inference with SGLang
-***********************************************
-
-This section provides instructions to test the inference performance of
-DeepSeek R1 with FP4 precision via the SGLang serving framework. The
-accompanying Docker image integrates `ROCm 7.0
-<https://rocm.docs.amd.com/en/latest/>`__ with SGLang, and is supported only on AMD
-Instinct MI355X and MI350X GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the benchmark.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image
-<https://hub.docker.com/r/rocm/7.0/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915
-
-Download the model
-==================
-
-See the model card on Hugging Face at `DeepSeek-R1-MXFP4-Preview
-<https://huggingface.co/amd/DeepSeek-R1-MXFP4-Preview>`__. This model uses
-microscaling 4-bit floating point (MXFP4) quantization through `AMD Quark
-<https://quark.docs.amd.com/latest/>`_ for efficient inference on AMD
-accelerators.
-
-.. code-block:: shell
-
-   pip install huggingface_hub[cli] hf_transfer hf_xet
-   HF_HUB_ENABLE_HF_TRANSFER=1 \
-   HF_HOME=/data/huggingface-cache \
-   HF_TOKEN="<HF_TOKEN>" \
-   huggingface-cli download amd/DeepSeek-R1-0528-MXFP4-Preview --exclude "original/*"
-
-Run the inference benchmark
-===========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-          --user root \
-          --group-add video \
-          --cap-add=SYS_PTRACE \
-          --security-opt seccomp=unconfined \
-          -w /app/ \
-          --ipc=host \
-          --network=host \
-          --shm-size 64G \
-          --mount type=bind,src=/data,dst=/data \
-          --device=/dev/kfd \
-          --device=/dev/dri \
-          -e SGLANG_USE_AITER=1 \
-          rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915
-
-2. Start the server.
-
-   .. code-block:: shell
-
-      python3 -m sglang.launch_server \
-          --model-path amd/DeepSeek-R1-0528-MXFP4-Preview \
-          --host localhost \
-          --port 8000 \
-          --tensor-parallel-size 8 \
-          --trust-remote-code \
-          --chunked-prefill-size 196608 \
-          --mem-fraction-static 0.8 \
-          --disable-radix-cache \
-          --num-continuous-decode-steps 4 \
-          --max-prefill-tokens 196608 \
-          --cuda-graph-max-bs 128 &
-
-3. Run the benchmark with the following options.
-
-   .. code-block:: shell
-
-      input_tokens=1024
-      output_tokens=1024
-      max_concurrency=64
-      num_prompts=128
-
-      python3 -m sglang.bench_serving \
-          --host localhost \
-          --port 8000 \
-          --model amd/DeepSeek-R1-0528-MXFP4-Preview \
-          --dataset-name random \
-          --random-input ${input_tokens} \
-          --random-output ${output_tokens} \
-          --random-range-ratio 1.0 \
-          --max-concurrency ${max_concurrency} \
-          --num-prompt ${num_prompts}
-

docs/benchmark-docker/inference-sglang-deepseek-r1-fp8.rst

@@ -1,132 +0,0 @@
-***********************************************
-Benchmark DeepSeek R1 FP8 inference with SGLang
-***********************************************
-
-This section provides instructions to test the inference performance of DeepSeek R1
-with FP8 precision via the SGLang serving framework.
-The accompanying Docker image integrates ROCm 7.0 with SGLang, and is
-supported on AMD Instinct MI355X, MI350X, MI325X, and MI300X GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the benchmark.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the appropriate `Docker image <https://hub.docker.com/r/rocm/7.0/tags>`__
-for your system.
-
-.. tab-set::
-
-   .. tab-item:: MI355X and MI350X
-      :sync: mi35x
-
-      .. code-block:: shell
-
-         docker pull rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915
-
-   .. tab-item:: MI300X series
-      :sync: mi30x
-
-      .. code-block:: shell
-
-         docker pull rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi30x-20250915
-
-Download the model
-==================
-
-See the model card on Hugging Face at `deepseek-ai/DeepSeek-R1-0528
-<https://huggingface.co/deepseek-ai/DeepSeek-R1-0528>`__.
-
-.. code-block:: shell
-
-   pip install huggingface_hub[cli] hf_transfer hf_xet
-   HF_HUB_ENABLE_HF_TRANSFER=1 \
-   HF_HOME=/data/huggingface-cache \
-   HF_TOKEN="<HF_TOKEN>" \
-   huggingface-cli download deepseek-ai/DeepSeek-R1-0528 --exclude "original/*"
-
-Run the inference benchmark
-===========================
-
-1. Start the container using the following command.
-
-   .. tab-set::
-
-      .. tab-item:: MI355X and MI350X
-         :sync: mi35x
-
-         .. code-block:: shell
-
-            docker run -it \
-                --user root \
-                --group-add video \
-                --cap-add=SYS_PTRACE \
-                --security-opt seccomp=unconfined \
-                -w /app/ \
-                --ipc=host \
-                --network=host \
-                --shm-size 64G \
-                --mount type=bind,src=/data,dst=/data \
-                --device=/dev/kfd \
-                --device=/dev/dri \
-                -e SGLANG_USE_AITER=1 \
-                rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915
-
-      .. tab-item:: MI300X series
-         :sync: mi30x
-
-         .. code-block:: shell
-
-            docker run -it \
-                --user root \
-                --group-add video \
-                --cap-add=SYS_PTRACE \
-                --security-opt seccomp=unconfined \
-                -w /app/ \
-                --ipc=host \
-                --network=host \
-                --shm-size 64G \
-                --mount type=bind,src=/data,dst=/data \
-                --device=/dev/kfd \
-                --device=/dev/dri \
-                -e SGLANG_USE_AITER=1 \
-                rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi30x-20250915
-
-2. Start the server.
-
-   .. code-block:: shell
-
-      python3 -m sglang.launch_server \
-          --model-path deepseek-ai/DeepSeek-R1-0528 \
-          --host localhost \
-          --port 8000 \
-          --tensor-parallel-size 8 \
-          --trust-remote-code \
-          --chunked-prefill-size 196608 \
-          --mem-fraction-static 0.8 \
-          --disable-radix-cache \
-          --num-continuous-decode-steps 4 \
-          --max-prefill-tokens 196608 \
-          --cuda-graph-max-bs 128 &
-
-3. Run the benchmark with the following options.
-
-   .. code-block:: shell
-
-      input_tokens=1024
-      output_tokens=1024
-      max_concurrency=64
-      num_prompts=128
-
-      python3 -m sglang.bench_serving \
-          --host localhost \
-          --port 8000 \
-          --model deepseek-ai/DeepSeek-R1-0528 \
-          --dataset-name random \
-          --random-input ${input_tokens} \
-          --random-output ${output_tokens} \
-          --random-range-ratio 1.0 \
-          --max-concurrency ${max_concurrency} \
-          --num-prompt ${num_prompts}
-

docs/benchmark-docker/inference-vllm-deepseek-r1-fp8.rst

@@ -1,122 +0,0 @@
-************************************************
-Benchmark DeepSeek R1 FP8 inference with vLLM
-************************************************
-
-This section provides instructions to test the inference performance of DeepSeek R1
-with FP8 precision on the vLLM inference engine. The provided Docker image integrates
-`ROCm 7.0 <https://rocm.docs.amd.com/en/docs-7.0.0/about/release-notes.html>`__ with vLLM.
-This benchmark supports AMD Instinct MI355X, MI350X, MI325X, and MI300X GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the benchmark.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image <https://hub.docker.com/r/rocm/7.x-preview/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-Download the model
-==================
-
-While vLLM can download model weights at runtime, it's recommended to
-download ahead of time. You will need:
-
-* A valid `Hugging Face access token <https://huggingface.co/docs/hub/security-tokens>`__.
-  Remember to set ``HF_TOKEN`` to your access token.
-
-* Access granted to the specific model from your Hugging Face account
-
-See the model card on Hugging Face at
-`deepseek-ai/DeepSeek-R1-0528 <https://huggingface.co/deepseek-ai/DeepSeek-R1-0528>`__.
-
-.. code-block:: shell
-
-   model=deepseek-ai/DeepSeek-R1-0528
-
-   pip install huggingface_hub[cli] hf_transfer hf_xet
-   HF_HUB_ENABLE_HF_TRANSFER=1 \
-   HF_HOME=/data/huggingface-cache \
-   HF_TOKEN="<HF_TOKEN>" \ # Replace with your HF_TOKEN Hugging Face access token.
-   huggingface-cli download ${model} --exclude "original/*"
-
-Run the inference benchmark
-===========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-        --ipc=host \
-        --network=host \
-        --privileged \
-        --cap-add=CAP_SYS_ADMIN \
-        --device=/dev/kfd \
-        --device=/dev/dri \
-        --cap-add=SYS_PTRACE \
-        --security-opt seccomp=unconfined \
-        -v /data:/data \
-        -e HF_HOME=/data/huggingface-cache \
-        -e HF_HUB_OFFLINE=1 \
-        --name vllm-server \
-        rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-2. Start the server.
-
-   .. code-block:: shell
-
-      model=deepseek-ai/DeepSeek-R1-0528
-      max_model_len=16384           # Must be >= the input + the output lengths.
-      max_seq_len_to_capture=10240  # Beneficial to set this to max_model_len.
-      max_num_seqs=1024
-      max_num_batched_tokens=131072 # Smaller values may result in better TTFT but worse TPOT / throughput.
-      tensor_parallel_size=8
-
-      # Note: this flag may not be compatible with MI325X GPUs
-      export VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4
-
-      # Note: Using `--kv-cache-dtype fp8` with DeepSeek may cause accuracy issues
-      vllm serve ${model} \
-          --host localhost \
-          --port 8000 \
-          --swap-space 64 \
-          --tensor-parallel-size ${tensor_parallel_size} \
-          --max-num-seqs ${max_num_seqs} \
-          --no-enable-prefix-caching \
-          --max-num-batched-tokens ${max_num_batched_tokens} \
-          --max-model-len ${max_model_len} \
-          --block-size 1 \
-          --gpu-memory-utilization 0.95 \
-          --max-seq-len-to-capture ${max_seq_len_to_capture} \
-          --async-scheduling
-
-       # Wait for model to load and server is ready to accept requests.
-
-3. Open another terminal on the same machine, connect to your running
-   ``vllm-server`` container, and run the benchmark with the appropriate
-   options. For example:
-
-   .. code-block:: shell
-
-      # Connect to server
-      docker exec -it vllm-server bash
-
-      # Run the client benchmark
-      input_tokens=8192
-      output_tokens=1024
-      max_concurrency=4
-      num_prompts=32
-
-      python3 /app/vllm/benchmarks/benchmark_serving.py --host localhost --port 8000 \
-          --model ${model} \
-          --dataset-name random \
-          --random-input-len ${input_tokens} \
-          --random-output-len ${output_tokens} \
-          --max-concurrency ${max_concurrency} \
-          --num-prompts ${num_prompts} \
-          --percentile-metrics ttft,tpot,itl,e2el \
-          --ignore-eos

docs/benchmark-docker/inference-vllm-gpt-oss-120b.rst

@@ -1,163 +0,0 @@
-**********************************************
-Benchmark GPT OSS 120B inference with vLLM
-**********************************************
-
-This section provides instructions to test the inference performance of OpenAI
-GPT OSS 120B on the vLLM inference engine. The provided Docker
-image integrates `ROCm 7.0
-<https://rocm.docs.amd.com/en/docs-7.0.0/about/release-notes.html>`__ with
-vLLM. This benchmark supports AMD Instinct MI355X, MI350X, MI325X, and MI300X
-GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the throughput test.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image <https://hub.docker.com/r/rocm/7.x-preview/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-Download the model
-==================
-
-While vLLM can download model weights at runtime, it's recommended to
-download ahead of time. You will need:
-
-* A valid `Hugging Face access token <https://huggingface.co/docs/hub/security-tokens>`__.
-  Remember to set ``HF_TOKEN`` to your access token.
-
-* Access granted to the specific model from your Hugging Face account
-
-See the model card on Hugging Face at
-`openai/gpt-oss-120b <https://huggingface.co/openai/gpt-oss-120b>`__.
-
-.. code-block:: shell
-
-   model=openai/gpt-oss-120b
-
-   pip install huggingface_hub[cli] hf_transfer hf_xet
-   HF_HUB_ENABLE_HF_TRANSFER=1 \
-   HF_HOME=/data/huggingface-cache \
-   HF_TOKEN="<HF_TOKEN>" \ # Replace with your HF_TOKEN Hugging Face access token.
-   huggingface-cli download ${model} --exclude "original/*"
-
-Run the inference benchmark
-===========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-        --ipc=host \
-        --network=host \
-        --privileged \
-        --cap-add=CAP_SYS_ADMIN \
-        --device=/dev/kfd \
-        --device=/dev/dri \
-        --cap-add=SYS_PTRACE \
-        --security-opt seccomp=unconfined \
-        -v /data:/data \
-        -e HF_HOME=/data/huggingface-cache \
-        -e HF_HUB_OFFLINE=1 \
-        --name vllm-server \
-        rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-2. Start the server.
-
-   .. tab-set::
-
-      .. tab-item:: MI355X and MI350X
-         :sync: mi35x
-
-         .. code-block:: shell
-
-            model=openai/gpt-oss-120b
-            max_model_len=10368           # 1.125 x (input sequence length + output sequence length); e.g. 1.125 x (8192 + 1024) = 10368.
-            max_seq_len_to_capture=10368  # Beneficial to set this to max_model_len.
-            max_num_seqs=1024             # Set to max_concurrency of the client to get better throughput.
-            tensor_parallel_size=8
-
-            export VLLM_USE_AITER_UNIFIED_ATTENTION=1
-            export VLLM_ROCM_USE_AITER_MHA=0
-            export VLLM_ROCM_USE_AITER_FUSED_MOE_A16W4=1
-
-            vllm serve ${model} \
-                --port 8000 \
-                --swap-space 64 \
-                --max-model-len ${max_model_len} \
-                --tensor-parallel-size ${tensor_parallel_size} \
-                --max-num-seqs ${max_num_seqs} \
-                --gpu-memory-utilization 0.95 \
-                --max-seq-len-to-capture ${max_seq_len_to_capture} \
-                --compilation-config '{"compile_sizes":[1,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126,128,256,512,1024,2048,8192] , "cudagraph_capture_sizes":[1,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126,128,136,144,152,160,168,176,184,192,200,208,216,224,232,240,248,256,264,272,280,288,296,304,312,320,328,336,344,352,360,368,376,384,392,400,408,416,424,432,440,448,456,464,472,480,488,496,504,512,520,528,536,544,552,560,568,576,584,592,600,608,616,624,632,640,648,656,664,672,680,688,696,704,712,720,728,736,744,752,760,768,776,784,792,800,808,816,824,832,840,848,856,864,872,880,888,896,904,912,920,928,936,944,952,960,968,976,984,992,1000,1008,1016,1024,2048,4096,8192] , "cudagraph_mode": "FULL_AND_PIECEWISE"}' \
-                --block-size=64 \
-                --no-enable-prefix-caching \
-                --async-scheduling
-
-             # Wait for model to load and server is ready to accept requests.
-
-      .. tab-item:: MI325X and MI300X
-         :sync: mi30x
-
-         .. code-block:: shell
-
-            model=openai/gpt-oss-120b
-            max_model_len=10368           # 1.125 x (input sequence length + output sequence length); e.g. 1.125 x (8192 + 1024) = 10368.
-            max_seq_len_to_capture=10368  # Beneficial to set this to max_model_len.
-            max_num_seqs=1024             # Set to max_concurrency of the client to get better throughput.
-            tensor_parallel_size=8
-
-            export VLLM_USE_AITER_UNIFIED_ATTENTION=1
-            export VLLM_ROCM_USE_AITER_MHA=0
-            export VLLM_ROCM_USE_AITER_TRITON_BF16_GEMM=0
-
-            # Set this flag for MI300X only; it is not yet compatible with MI325X.
-            # export VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4
-
-            vllm serve ${model} \
-                --port 8000 \
-                --swap-space 64 \
-                --max-model-len ${max_model_len} \
-                --tensor-parallel-size ${tensor_parallel_size} \
-                --max-num-seqs ${max_num_seqs} \
-                --gpu-memory-utilization 0.95 \
-                --max-seq-len-to-capture ${max_seq_len_to_capture} \
-                --compilation-config '{"cudagraph_mode": "FULL_AND_PIECEWISE"}' \
-                --block-size=64 \
-                --no-enable-prefix-caching \
-                --async-scheduling
-
-             # Wait for model to load and server is ready to accept requests.
-
-3. Open another terminal on the same machine, connect to your running
-   ``vllm-server`` container, and run the benchmark with the appropriate
-   options. For example:
-
-   .. code-block:: shell
-
-      # Connect to server
-      docker exec -it vllm-server bash
-
-   .. code-block:: shell
-
-      # Run the client benchmark
-      model=openai/gpt-oss-120b
-      input_tokens=1024
-      output_tokens=1024
-      max_concurrency=4
-      num_prompts=32
-
-      python3 /app/vllm/benchmarks/benchmark_serving.py --host localhost --port 8000 \
-          --model ${model} \
-          --dataset-name random \
-          --random-input-len ${input_tokens} \
-          --random-output-len ${output_tokens} \
-          --max-concurrency ${max_concurrency} \
-          --num-prompts ${num_prompts} \
-          --percentile-metrics ttft,tpot,itl,e2el \
-          --ignore-eos

docs/benchmark-docker/inference-vllm-llama-3.1-405b-fp4.rst

@@ -1,193 +0,0 @@
-************************************************
-Benchmark Llama 3.3/3.1 FP4 inference with vLLM
-************************************************
-
-This section provides instructions to test the inference performance of Llama
-3.3 70B and Llama 3.1 405B with MXFP4 precision on the vLLM inference engine.
-The provided Docker image integrates `ROCm 7.0
-<https://rocm.docs.amd.com/en/docs-7.0.0/about/release-notes.html>`__ with vLLM.
-This benchmark supports AMD Instinct MI355X and MI350X GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the throughput test.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image <https://hub.docker.com/r/rocm/7.x-preview/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-Download the model
-==================
-
-While vLLM can download model weights at runtime, it's recommended to
-download ahead of time. You will need:
-
-* A valid `Hugging Face access token <https://huggingface.co/docs/hub/security-tokens>`__.
-  Remember to set ``HF_TOKEN`` to your access token.
-
-* Access granted to the specific model from your Hugging Face account
-
-.. tab-set::
-
-   .. tab-item:: Llama 3.3 70B MXFP4
-      :sync: Llama-3.3-70B-Instruct-MXFP4-Preview
-
-      See the model card on Hugging Face at
-      `amd/Llama-3.3-70B-Instruct-MXFP4-Preview <https://huggingface.co/amd/Llama-3.3-70B-Instruct-MXFP4-Preview>`__.
-      This model uses FP4 quantization via `AMD Quark
-      <https://quark.docs.amd.com/latest/>`_ for efficient inference on AMD
-      accelerators.
-
-      .. code-block:: shell
-
-         model=amd/Llama-3.3-70B-Instruct-MXFP4-Preview
-
-         pip install huggingface_hub[cli] hf_transfer hf_xet
-         HF_HUB_ENABLE_HF_TRANSFER=1 \
-         HF_HOME=/data/huggingface-cache \
-         HF_TOKEN="<HF_TOKEN>" \ # Replace with your HF_TOKEN Hugging Face access token.
-         huggingface-cli download ${model} --exclude "original/*"
-
-   .. tab-item:: Llama 3.1 405B MXFP4
-      :sync: Llama-3.1-405B-Instruct-MXFP4-Preview
-
-      See the model card on Hugging Face at
-      `amd/Llama-3.1-405B-Instruct-MXFP4-Preview <https://huggingface.co/amd/Llama-3.1-405B-Instruct-MXFP4-Preview>`__.
-      This model uses FP4 quantization via `AMD Quark
-      <https://quark.docs.amd.com/latest/>`_ for efficient inference on AMD
-      accelerators.
-
-      .. code-block:: shell
-
-         model=amd/Llama-3.1-405B-Instruct-MXFP4-Preview
-
-         pip install huggingface_hub[cli] hf_transfer hf_xet
-         HF_HUB_ENABLE_HF_TRANSFER=1 \
-         HF_HOME=/data/huggingface-cache \
-         HF_TOKEN="<HF_TOKEN>" \ # Replace with your HF_TOKEN Hugging Face access token.
-         huggingface-cli download ${model} --exclude "original/*"
-
-Run the inference benchmark
-===========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-        --ipc=host \
-        --network=host \
-        --privileged \
-        --cap-add=CAP_SYS_ADMIN \
-        --device=/dev/kfd \
-        --device=/dev/dri \
-        --cap-add=SYS_PTRACE \
-        --security-opt seccomp=unconfined \
-        -v /data:/data \
-        -e HF_HOME=/data/huggingface-cache \
-        -e HF_HUB_OFFLINE=1 \
-        --name vllm-server \
-        rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-2. Start the server.
-
-   .. tab-set::
-
-      .. tab-item:: Llama 3.3 70B MXFP4
-         :sync: Llama-3.3-70B-Instruct-MXFP4-Preview
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.3-70B-Instruct-MXFP4-Preview
-
-      .. tab-item:: Llama 3.1 405B MXFP4
-         :sync: Llama-3.1-405B-Instruct-MXFP4-Preview
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.1-405B-Instruct-MXFP4-Preview
-
-   .. code-block:: shell
-
-      max_model_len=10240           # Must be >= the input + the output lengths.
-      max_seq_len_to_capture=10240  # Beneficial to set this to max_model_len.
-      max_num_seqs=1024
-      max_num_batched_tokens=131072 # Smaller values may result in better TTFT but worse TPOT / throughput.
-      tensor_parallel_size=8
-
-      # The following setting is recommended for most configurations:
-      export VLLM_TRITON_FP4_GEMM_USE_ASM=1
-
-      # For tensor parallelism >1 at low concurrency (<= 16 for input length 1024, <= 4 for input length 8192),
-      # uncomment these lines:
-      # export VLLM_TRITON_FP4_GEMM_USE_ASM=0
-      # export VLLM_ROCM_USE_AITER_TRITON_BF16_GEMM=0
-
-      # 0 is recommended for most configurations.
-      # 1 (the default) is faster for input lengths of 8192 with concurrency > 16.
-      export VLLM_ROCM_USE_AITER_MHA=0
-
-      export VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4
-
-      vllm serve ${model} \
-          --host localhost \
-          --port 8000 \
-          --swap-space 64 \
-          --max-model-len ${max_model_len} \
-          --tensor-parallel-size ${tensor_parallel_size} \
-          --max-num-seqs ${max_num_seqs} \
-          --kv-cache-dtype fp8 \
-          --gpu-memory-utilization 0.94 \
-          --max-seq-len-to-capture ${max_seq_len_to_capture} \
-          --max-num-batched-tokens ${max_num_batched_tokens} \
-          --no-enable-prefix-caching \
-          --async-scheduling
-
-          # Wait for model to load and server is ready to accept requests.
-
-3. Open another terminal on the same machine, connect to your running
-   ``vllm-server`` container, and run the benchmark with the appropriate
-   options. For example:
-
-   .. code-block:: shell
-
-      # Connect to server
-      docker exec -it vllm-server bash
-
-   .. tab-set::
-
-      .. tab-item:: Llama 3.3 70B MXFP4
-         :sync: Llama-3.3-70B-Instruct-MXFP4-Preview
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.3-70B-Instruct-MXFP4-Preview
-
-      .. tab-item:: Llama 3.1 405B MXFP4
-         :sync: Llama-3.1-405B-Instruct-MXFP4-Preview
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.1-405B-Instruct-MXFP4-Preview
-
-   .. code-block:: shell
-
-      # Run the client benchmark
-      input_tokens=1024
-      output_tokens=1024
-      max_concurrency=64
-      num_prompts=32
-
-      python3 /app/vllm/benchmarks/benchmark_serving.py --host localhost --port 8000 \
-          --model ${model} \
-          --dataset-name random \
-          --random-input-len ${input_tokens} \
-          --random-output-len ${output_tokens} \
-          --max-concurrency ${max_concurrency} \
-          --num-prompts ${num_prompts} \
-          --percentile-metrics ttft,tpot,itl,e2el \
-          --ignore-eos

docs/benchmark-docker/inference-vllm-llama-3.3-70b-fp8.rst

@@ -1,189 +0,0 @@
-************************************************
-Benchmark Llama 3.3/3.1 FP8 inference with vLLM
-************************************************
-
-This section provides instructions to test the inference performance of Llama
-3.3 70B and Llama 3.1 405B with FP8 precision on the vLLM inference engine. The provided Docker image integrates
-`ROCm 7.0 <https://rocm.docs.amd.com/en/docs-7.0.0/about/release-notes.html>`__ with vLLM.
-This benchmark supports AMD Instinct MI355X, MI350X, MI325X, and MI300X GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the throughput test.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image <https://hub.docker.com/r/rocm/7.x-preview/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-Download the model
-==================
-
-While vLLM can download model weights at runtime, it's recommended to
-download ahead of time. You will need:
-
-* A valid `Hugging Face access token <https://huggingface.co/docs/hub/security-tokens>`__.
-  Remember to set ``HF_TOKEN`` to your access token.
-
-* Access granted to the specific model from your Hugging Face account
-
-In the following snippet, set ``HF_TOKEN`` to your access token.
-
-.. tab-set::
-
-   .. tab-item:: Llama 3.3 70B FP8
-      :sync: Llama-3.3-70B-Instruct-FP8-KV
-
-      See the model card on Hugging Face at
-      `amd/Llama-3.3-70B-Instruct-FP8-KV <https://huggingface.co/amd/Llama-3.3-70B-Instruct-FP8-KV>`__.
-      This model uses FP8 quantization via `AMD Quark
-      <https://quark.docs.amd.com/latest/>`_ for efficient inference on AMD
-      accelerators.
-
-      .. code-block:: shell
-
-         model=amd/Llama-3.3-70B-Instruct-FP8-KV
-
-         pip install huggingface_hub[cli] hf_transfer hf_xet
-         HF_HUB_ENABLE_HF_TRANSFER=1 \
-         HF_HOME=/data/huggingface-cache \
-         HF_TOKEN="<HF_TOKEN>" \ # Replace with your HF_TOKEN Hugging Face access token.
-         huggingface-cli download ${model} --exclude "original/*"
-
-   .. tab-item:: Llama 3.1 405B FP8
-      :sync: Llama-3.1-405B-Instruct-FP8-KV
-
-      See the model card on Hugging Face at
-      `amd/Llama-3.1-405B-Instruct-FP8-KV <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`__.
-      This model uses FP8 quantization via `AMD Quark
-      <https://quark.docs.amd.com/latest/>`_ for efficient inference on AMD
-      accelerators.
-
-      .. code-block:: shell
-
-         model=amd/Llama-3.1-405B-Instruct-FP8-KV
-
-         pip install huggingface_hub[cli] hf_transfer hf_xet
-         HF_HUB_ENABLE_HF_TRANSFER=1 \
-         HF_HOME=/data/huggingface-cache \
-         HF_TOKEN="<HF_TOKEN>" \ # Replace with your HF_TOKEN Hugging Face access token.
-         huggingface-cli download ${model} --exclude "original/*"
-
-Run the inference benchmark
-===========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-        --ipc=host \
-        --network=host \
-        --privileged \
-        --cap-add=CAP_SYS_ADMIN \
-        --device=/dev/kfd \
-        --device=/dev/dri \
-        --cap-add=SYS_PTRACE \
-        --security-opt seccomp=unconfined \
-        -v /data:/data \
-        -e HF_HOME=/data/huggingface-cache \
-        -e HF_HUB_OFFLINE=1 \
-        --name vllm-server \
-        rocm/7.x-preview:rocm7.2_preview_ubuntu_22.04_vlm_0.10.1_instinct_20251029
-
-2. Start the server. On MI300X and MI325X GPUs, include ``--dtype float16`` in your ``vllm serve`` arguments.
-   This is not necessary on MI350X and MI355X GPUs.
-
-   .. tab-set::
-
-      .. tab-item:: Llama 3.3 70B FP8
-         :sync: Llama-3.3-70B-Instruct-FP8-KV
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.3-70B-Instruct-FP8-KV
-
-      .. tab-item:: Llama 3.1 405B FP8
-         :sync: Llama-3.1-405B-Instruct-FP8-KV
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.1-405B-Instruct-FP8-KV
-
-   .. code-block:: shell
-
-      max_model_len=10240           # Must be >= the input + the output lengths.
-      max_seq_len_to_capture=10240  # Beneficial to set this to max_model_len.
-      max_num_seqs=1024
-      max_num_batched_tokens=131072 # Smaller values may result in better TTFT but worse TPOT / throughput.
-      tensor_parallel_size=8
-
-      # Note: this flag may not be compatible with MI325X GPUs
-      export VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4
-
-      # 0 is recommended for most configurations.
-      # 1 (the default) is faster for input lengths of 8192 with concurrency > 16.
-      export VLLM_ROCM_USE_AITER_MHA=0
-
-      vllm serve ${model} \
-          --host localhost \
-          --port 8000 \
-          --swap-space 64 \
-          --max-model-len ${max_model_len} \
-          --tensor-parallel-size ${tensor_parallel_size} \
-          --max-num-seqs ${max_num_seqs} \
-          --distributed-executor-backend mp \
-          --kv-cache-dtype fp8 \
-          --gpu-memory-utilization 0.94 \
-          --max-seq-len-to-capture ${max_seq_len_to_capture} \
-          --max-num-batched-tokens ${max_num_batched_tokens} \
-          --no-enable-prefix-caching \
-          --async-scheduling
-
-          # Wait for model to load and server is ready to accept requests.
-
-3. Open another terminal on the same machine, connect to your running
-   ``vllm-server`` container, and run the benchmark with the appropriate
-   options. For example:
-
-   .. code-block:: shell
-
-      # Connect to server
-      docker exec -it vllm-server bash
-
-   .. tab-set::
-
-      .. tab-item:: Llama 3.3 70B FP8
-         :sync: Llama-3.3-70B-Instruct-FP8-KV
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.3-70B-Instruct-FP8-KV
-
-      .. tab-item:: Llama 3.1 405B FP8
-         :sync: Llama-3.1-405B-Instruct-FP8-KV
-
-         .. code-block:: shell
-
-            model=amd/Llama-3.1-405B-Instruct-FP8-KV
-
-   .. code-block:: shell
-
-      # Run the client benchmark
-      input_tokens=1024
-      output_tokens=1024
-      max_concurrency=4
-      num_prompts=32
-
-      python3 /app/vllm/benchmarks/benchmark_serving.py --host localhost --port 8000 \
-          --model ${model} \
-          --dataset-name random \
-          --random-input-len ${input_tokens} \
-          --random-output-len ${output_tokens} \
-          --max-concurrency ${max_concurrency} \
-          --num-prompts ${num_prompts} \
-          --percentile-metrics ttft,tpot,itl,e2el \
-          --ignore-eos

docs/benchmark-docker/training-maxtext-llama-3.rst

@@ -1,122 +0,0 @@
-*******************************************
-Benchmark Llama 3 pre-training with MaxText
-*******************************************
-
-This page describes how to benchmark Llama 3 8B and 70B pre-training using the
-MaxText framework. It includes configurations for both
-FP8 and BF16 precision to measure throughput. The provided Docker
-image integrates ROCm 7.0 with MaxText
--- and is supported on AMD Instinct MI355X and MI350X GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the throughput test.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image <https://hub.docker.com/r/rocm/7.0/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.0:rocm7.0_jax_training_mi35x_20250915
-
-Run the training benchmark
-==========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-          --device /dev/dri \
-          --device /dev/kfd \
-          --network host \
-          --ipc host \
-          --group-add video \
-          --cap-add SYS_PTRACE \
-          --security-opt seccomp=unconfined \
-          --privileged \
-          -v $HOME:$HOME \
-          -v $HOME/.ssh:/root/.ssh \
-          --shm-size 64G \
-          -w /workspace/maxtext \
-          --name training_benchmark \
-          rocm/7.0:rocm7.0_jax_training_mi35x_20250915
-
-   .. note::
-
-      This containerized environment includes all necessary dependencies and pre-tuned
-      configurations for the supported models and precision types.
-
-2. Run the training script with the following options for your desired precision.
-
-   .. tab-set::
-
-      .. tab-item:: Llama 3 8B
-
-         .. tab-set::
-
-            .. tab-item:: BF16
-
-               .. code-block:: shell
-
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/llama3_8b.yml
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/llama3_8b_env.sh
-                  bash llama3_8b_env.sh
-                  python3 -m MaxText.train llama3_8b.yml
-
-            .. tab-item:: FP8
-
-               .. code-block:: shell
-
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/llama3_8b.yml
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/llama3_8b_env.sh
-                  bash llama3_8b_env.sh
-                  python3 -m MaxText.train llama3_8b.yml quantization=fp8
-
-      .. tab-item:: Llama 3 70B
-
-         .. tab-set::
-
-            .. tab-item:: BF16
-
-               .. code-block:: shell
-
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/llama3_70b.yml
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/llama3_70b_env.sh
-                  bash llama3_70b_env.sh
-                  python3 -m MaxText.train llama3_70b.yml
-
-   .. rubric:: Options
-
-   The ``MaxText.train`` script accepts the following options:
-
-   * ``per_device_batch_size``: Per-device batch size
-
-   * ``quantization``: quantization
-
-   * ``max_target_length``: Maximum input token sequence length
-
-   * ``steps``: Number of training iterations to execute
-
-   See this base [config](https://github.com/AI-Hypercomputer/maxtext/blob/main/src/MaxText/configs/base.yml)
-   for the full list of settings you can change.
-
-Other supported models
-======================
-
-* Llama-2-7B FP8 and BF16
-
-* Llama-2-70B FP8 and BF16
-
-* Llama-3.3-70B BF16
-
-* DeepSeek-V2-Lite FP8 and BF16
-
-* Mixtral 8x7B FP8 and BF16
-
-Known issue
-===========
-
-Some models and configurations may trigger a "Memory Access Fault" error.
-Updates to improve stability are planned for upcoming releases.

docs/benchmark-docker/training-maxtext-mixtral-8x7b.rst

@@ -1,111 +0,0 @@
-************************************************
-Benchmark Mixtral 8x7B pre-training with MaxText
-************************************************
-
-This page describes how to benchmark the Mixtral 8x7B pre-training using the
-MaxText framework. It includes configurations for both
-FP8 and BF16 precision to measure throughput. The provided Docker
-image integrates a ROCm 7.0 with MaxText
--- and is supported on AMD Instinct MI355X and MI350X GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the throughput test.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image <https://hub.docker.com/r/rocm/7.0/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.0:rocm7.0_jax_training_mi35x_20250915
-
-Run the training benchmark
-==========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-          --device /dev/dri \
-          --device /dev/kfd \
-          --network host \
-          --ipc host \
-          --group-add video \
-          --cap-add SYS_PTRACE \
-          --security-opt seccomp=unconfined \
-          --privileged \
-          -v $HOME:$HOME \
-          -v $HOME/.ssh:/root/.ssh \
-          --shm-size 64G \
-          -w /workspace/maxtext \
-          --name training_benchmark \
-          rocm/7.0:rocm7.0_jax_training_mi35x_20250915
-
-   .. note::
-
-      This containerized environment includes all necessary dependencies and pre-tuned
-      configurations for the supported models and precision types.
-
-2. Run the training script with the following options for your desired precision.
-
-   .. tab-set::
-
-      .. tab-item:: Mixtral 8x7B
-
-         .. tab-set::
-
-            .. tab-item:: BF16
-
-               .. code-block:: shell
-
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/mixtral_8x7b.yml
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/mixtral_8x7b_env.sh
-                  bash mixtral_8x7b_env.sh
-                  python3 -m MaxText.train mixtral_8x7b.yml
-
-            .. tab-item:: FP8
-
-               .. code-block:: shell
-
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/mixtral_8x7b.yml
-                  wget https://raw.githubusercontent.com/ROCm/MAD/refs/heads/develop/scripts/jax-maxtext/env_scripts/mixtral_8x7b_env.sh
-                  bash mixtral_8x7b_env.sh
-                  python3 -m MaxText.train mixtral_8x7b.yml quantization=fp8
-
-   .. rubric:: Options
-
-   The ``MaxText.train`` script accepts the following options:
-
-   * ``per_device_batch_size``: Per-device batch size
-
-   * ``quantization``: quantization
-
-   * ``max_target_length``: Maximum input token sequence length
-
-   * ``steps``: Number of training iterations to execute
-
-   See this base [config](https://github.com/AI-Hypercomputer/maxtext/blob/main/src/MaxText/configs/base.yml)
-   for the full list of settings you can change.
-
-Other supported models
-======================
-
-* Llama-2-7B FP8 and BF16
-
-* Llama-2-70B FP8 and BF16
-
-* Llama-3.1-8B FP8 and BF16
-
-* Llama-3.1-70B BF16
-
-* Llama-3.3-70B BF16
-
-* DeepSeek-V2-Lite FP8 and BF16
-
-Known issue
-===========
-
-Some models and configurations may trigger a "Memory Access Fault" error.
-Updates to improve stability are planned for upcoming releases.

docs/benchmark-docker/training-megatron-lm-llama-3.rst

@@ -1,171 +0,0 @@
-***********************************************
-Benchmark Llama 3 pre-training with Megatron-LM
-***********************************************
-
-This page describes how to benchmark Llama 3 8B and 70B pre-training using the
-Megatron-LM framework. It includes configurations for both FP8 and BF16
-precision to measure throughput. The provided Docker image integrates ROCm
-7.0 with Megatron-LM -- and is supported on AMD Instinct MI355X and MI350X
-GPUs.
-
-Follow these steps to pull the required image, spin up the container with the
-appropriate options, download the model, and run the throughput test.
-
-Pull the Docker image
-=====================
-
-Use the following command to pull the `Docker image <https://hub.docker.com/r/rocm/7.0/tags>`__.
-
-.. code-block:: shell
-
-   docker pull rocm/7.0:rocm7.0_pytorch_training_instinct_20250915
-
-Run the training benchmark
-==========================
-
-1. Start the container using the following command.
-
-   .. code-block:: shell
-
-      docker run -it \
-          --device /dev/dri \
-          --device /dev/kfd \
-          --network host \
-          --ipc host \
-          --group-add video \
-          --cap-add SYS_PTRACE \
-          --security-opt seccomp=unconfined \
-          --privileged \
-          -v $HOME:$HOME \
-          -v $HOME/.ssh:/root/.ssh \
-          --shm-size 64G \
-          -w /workspace/Megatron-LM \
-          --name training_benchmark \
-          rocm/7.0:rocm7.0_pytorch_training_instinct_20250915
-
-   .. note::
-
-      This containerized environment includes all necessary dependencies and pre-tuned
-      configurations for the supported models and precision types.
-
-2. Run the training script with the following options for your desired precision.
-
-   .. tab-set::
-
-      .. tab-item:: Llama 3 8B
-
-         .. tab-set::
-
-            .. tab-item:: BF16
-
-               .. code-block:: shell
-
-                  TEE_OUTPUT=1 \
-                  MBS=4 \
-                  BS=512 \
-                  TP=1 \
-                  TE_FP8=0 \
-                  SEQ_LENGTH=8192 \
-                  MODEL_SIZE=8 \
-                  TOTAL_ITERS=10 \
-                  GEMM_TUNING=1 \
-                  bash examples/llama/train_llama3.sh
-
-            .. tab-item:: FP8
-
-               .. code-block:: shell
-
-                  TEE_OUTPUT=1 \
-                  MBS=4 \
-                  BS=512 \
-                  TP=1 \
-                  TE_FP8=1 \
-                  SEQ_LENGTH=8192 \
-                  MODEL_SIZE=8 \
-                  TOTAL_ITERS=10 \
-                  GEMM_TUNING=0 \
-                  bash examples/llama/train_llama3.sh
-
-      .. tab-item:: Llama 3 70B
-
-         .. tab-set::
-
-            .. tab-item:: BF16
-
-               .. code-block:: shell
-
-                  CKPT_FORMAT=torch_dist \
-                  TEE_OUTPUT=1 \
-                  MBS=3 \
-                  BS=24 \
-                  TP=1 \
-                  TE_FP8=0 \
-                  FSDP=1 \
-                  RECOMPUTE=1 \
-                  SEQ_LENGTH=8192 \
-                  MODEL_SIZE=70 \
-                  TOTAL_ITERS=10 \
-                  bash examples/llama/train_llama3.sh
-
-            .. tab-item:: FP8
-
-               .. code-block:: shell
-
-                  CKPT_FORMAT=torch_dist \
-                  TEE_OUTPUT=1 \
-                  RECOMPUTE=1 \
-                  MBS=3 \
-                  BS=24 \
-                  TP=1 \
-                  TE_FP8=1 \
-                  SEQ_LENGTH=8192 \
-                  MODEL_SIZE=70 \
-                  FSDP=1 \
-                  TOTAL_ITERS=10 \
-                  NUM_LAYERS=40 \
-                  bash examples/llama/train_llama3.sh
-
-   .. rubric:: Options
-
-   The ``train_llama3.sh`` script accepts the following options:
-
-   * ``MBS``: Micro-batch size per GPU
-
-   * ``BS``: Global batch size
-
-   * ``TP``: Tensor parallelism
-
-   * ``SEQ_LENGTH``: Maximum input token sequence length
-
-   * ``TE_FP8``: Toggle to enable FP8
-
-   * ``TOTAL_ITERS``: Number of training iterations to execute
-
-Other supported models
-======================
-
-* Llama-2-7B
-
-* Llama-3.3-70B
-
-* DeepSeek-V2-Lite
-
-* Mixtral-8x7B
-
-* Qwen-2.5-7B
-
-* Qwen-2.5-72B
-
-Known issues
-============
-
-- Some models and configurations may trigger a "Memory Access Fault" error.
-  Updates to improve stability are planned for upcoming releases.
-
-- A regression related to Composable Kernel (CK) may cause errors in certain
-  cases. A fix is planned for an upcoming release.
-
-- Flash Attention forward may not pick the best performing ASM kernel with batch
-  size greater than 1 and impact model performance.
-  For best performance on MI355X and MI350X GPUs, use the ROCm 7.0 Preview beta Docker
-  (``rocm/7.0-preview:rocm7.0_preview_pytorch_training_mi35x_beta``).