Update rocm-examples.yml

Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.26.0 to 1.27.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.26.0...v1.27.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-version: 1.27.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.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 }}
-    dependsOn: AMDMIGraphX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ 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
-
-# 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
+    - ROCR-Runtime
 
 - name: jobMatrix
   type: object
   default:
     buildJobs:
-      - { os: ubuntu2204, packageManager: apt }
-      - { os: almalinux8, packageManager: dnf }
+      - { os: ubuntu2204, packageManager: apt, platform: amd }
+      - { 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
-    pool:
-      vmImage: 'ubuntu-22.04'
-    ${{ if eq(job.os, 'almalinux8') }}:
-      container:
-        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
+  - job: ${{ parameters.componentName }}_${{ job.os }}_${{ job.platform }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     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
-  # 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
+        # sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - 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'
-      displayName: 'Artifact listing'
-  # compile clr
+        ${{ if eq(job.platform, 'amd') }}:
+          dependencyList: ${{ parameters.rocmDependenciesAMD }}
+        ${{ 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'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
+        cmakeBuildDir: $(Agent.BuildDirectory)/s/projects/clr/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/s/projects/clr
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
-          -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
-          -DHIP_PLATFORM=nvidia
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DROCM_PATH=$(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
-          -DHIPNV_DIR=$(Build.SourcesDirectory)/hipother/hipnv
+          -DCLR_BUILD_OCL=ON
           -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
-        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "test_rnn_seq_api|GPU_Conv2dTuningAsm_FP32"'
+        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|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 }}
-    dependsOn: MIVisionX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ 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 }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ROCR_Runtime_test_${{ job.os }}_${{ job.target }}
-    dependsOn: ROCR_Runtime_build_${{ job.os }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        packageManager: ${{ job.packageManager }}
-    - task: Bash@3
-      displayName: Install libhwloc5
-      inputs:
-        targetType: 'inline'
-        script: |
-          wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc5_1.11.12-3_amd64.deb
-          wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc-dev_1.11.12-3_amd64.deb
-          sudo apt install -y --allow-downgrades ./libhwloc5_1.11.12-3_amd64.deb ./libhwloc-dev_1.11.12-3_amd64.deb
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-      parameters:
-        checkoutRepo: ${{ parameters.checkoutRepo }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-      parameters:
-        runRocminfo: false
-    - task: Bash@3
-      displayName: Build kfdtest
-      inputs:
-        targetType: 'inline'
-        workingDirectory: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest
-        script: |
-          if [ -e /opt/rh/gcc-toolset-14/enable ]; then
-            source /opt/rh/gcc-toolset-14/enable
-          fi
-          mkdir build && cd build
-          cmake -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm ..
-          make
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: kfdtest
-        testExecutable: BIN_DIR=$(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/build ./run_kfdtest.sh
-        testParameters: '-p core --gtest_output=xml:./test_output.xml --gtest_color=yes'
-        testDir: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/scripts
-        os: ${{ job.os }}
-    - task: Bash@3
-      displayName: Build rocrtst
-      inputs:
-        targetType: 'inline'
-        workingDirectory: $(Build.SourcesDirectory)/rocrtst/suites/test_common
-        script: |
-          if [ -e /opt/rh/gcc-toolset-14/enable ]; then
-            source /opt/rh/gcc-toolset-14/enable
-          fi
-          BASE_CLANG_DIR=$(Agent.BuildDirectory)/rocm/llvm/lib/clang
-          export NEWEST_CLANG_VER=$(ls -1 $BASE_CLANG_DIR | sort -V | tail -n 1)
-          mkdir build && cd build
-          cmake .. \
-            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm \
-            -DTARGET_DEVICES=${{ job.target }} \
-            -DROCM_DIR=$(Agent.BuildDirectory)/rocm \
-            -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin \
-            -DOPENCL_INC_DIR=$BASE_CLANG_DIR/$NEWEST_CLANG_VER/include
-          make
-          make rocrtst_kernels
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocrtst
-        testExecutable: ./rocrtst64
-        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 }}
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
-  # docker image will be missing libhwloc5
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ROCR_Runtime_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ROCR_Runtime_build_${{ 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/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:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+        parameters:
+          runRocminfo: false
+      - task: Bash@3
+        displayName: Build kfdtest
+        inputs:
+          targetType: 'inline'
+          workingDirectory: $(Agent.BuildDirectory)/s/libhsakmt/tests/kfdtest
+          script: |
+            if [ -e /opt/rh/gcc-toolset-14/enable ]; then
+              source /opt/rh/gcc-toolset-14/enable
+            fi
+            mkdir build && cd build
+            cmake -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm ..
+            make
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: kfdtest
+          testExecutable: BIN_DIR=$(Agent.BuildDirectory)/s/libhsakmt/tests/kfdtest/build ./run_kfdtest.sh
+          testParameters: '-p core --gtest_output=xml:./test_output.xml --gtest_color=yes'
+          testDir: $(Agent.BuildDirectory)/s/libhsakmt/tests/kfdtest/scripts
+          os: ${{ job.os }}
+      - task: Bash@3
+        displayName: Build rocrtst
+        inputs:
+          targetType: 'inline'
+          workingDirectory: $(Agent.BuildDirectory)/s/rocrtst/suites/test_common
+          script: |
+            echo $(Agent.BuildDirectory)/s/rocrtst/thirdparty/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+            sudo cat /etc/ld.so.conf.d/rocm-ci.conf
+            sudo ldconfig -v
+            ldconfig -p
+            if [ -e /opt/rh/gcc-toolset-14/enable ]; then
+              source /opt/rh/gcc-toolset-14/enable
+            fi
+            BASE_CLANG_DIR=$(Agent.BuildDirectory)/rocm/llvm/lib/clang
+            export NEWEST_CLANG_VER=$(ls -1 $BASE_CLANG_DIR | sort -V | tail -n 1)
+            mkdir build && cd build
+            cmake .. \
+              -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm \
+              -DTARGET_DEVICES=${{ job.target }} \
+              -DROCM_DIR=$(Agent.BuildDirectory)/rocm \
+              -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin \
+              -DOPENCL_INC_DIR=$BASE_CLANG_DIR/$NEWEST_CLANG_VER/include
+            make
+            make rocrtst_kernels
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: rocrtst
+          testExecutable: ./rocrtst64
+          testParameters: '--gtest_filter="-rocrtstNeg.Memory_Negative_Tests:rocrtstFunc.Memory_Max_Mem" --gtest_output=xml:./test_output.xml --gtest_color=yes'
+          testDir: $(Agent.BuildDirectory)/s//rocrtst/suites/test_common/build/${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+    # 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:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_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
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hip_tests_test_${{ job.target }}
-    timeoutInMinutes: 240
-    dependsOn: hip_tests_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - task: Bash@3
-      displayName: Symlink rocm_agent_enumerator
-      inputs:
-        targetType: inline
-        script: |
-          # Assuming that /opt is no longer persistent across runs, test environments are fully ephemeral
-          sudo mkdir -p /opt/rocm/bin
-          sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rocm_agent_enumerator /opt/rocm/bin/rocm_agent_enumerator
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hip_tests
-        testDir: $(Agent.BuildDirectory)/rocm/share/hip
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
-        optSymLink: true
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: hip_tests_test_${{ job.target }}
+      timeoutInMinutes: 240
+      dependsOn: hip_tests_build_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ 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 }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - task: Bash@3
+        displayName: Symlink rocm_agent_enumerator
+        inputs:
+          targetType: inline
+          script: |
+            # Assuming that /opt is no longer persistent across runs, test environments are fully ephemeral
+            sudo mkdir -p /opt/rocm/bin
+            sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rocm_agent_enumerator /opt/rocm/bin/rocm_agent_enumerator
+      - 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/hip
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        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
-#   type: object
-#   default:
-#     - hipBLASLt:
-#       name: hipBLASLt
-#       sparseCheckoutDir: projects/hipblaslt
-#       skipUnifiedBuild: 'false'
-#       buildDependsOn:
-#         - hipBLAS_common_build
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipBLASLt:
+      name: hipBLASLt
+      sparseCheckoutDir: projects/hipblaslt
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - 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 }}:
-#   - ${{ 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 }}
+- ${{ 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/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 }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipBLAS_test_${{ job.target }}
-    dependsOn: hipBLAS_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipBLAS
-        testExecutable: $(Agent.BuildDirectory)/rocm/bin/hipblas-test
-        testParameters: '--yaml hipblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ 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'], ','), '${{ parameters.componentName }}')),
+          eq(${{ 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 }}
+          pipModules: ${{ parameters.pipModules }}
+      - 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 }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.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 }}
+          testExecutable: $(Agent.BuildDirectory)/rocm/bin/hipblas-test
+          testParameters: '--yaml hipblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+      - 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 }
-      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
-      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
-      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
+      - { pool: rocm-ci_ultra_build_pool, os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      #- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { pool: rocm-ci_ultra_build_pool, os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1100 }
+      #- { 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
-#   type: object
-#   default:
-#     - rocBLAS:
-#       name: rocBLAS
-#       sparseCheckoutDir: projects/rocblas
-#       skipUnifiedBuild: 'false'
-#       buildDependsOn:
-#         - hipBLASLt_build
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocBLAS:
+      name: rocBLAS
+      sparseCheckoutDir: projects/rocblas
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - 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
-          cd $(Agent.BuildDirectory)/deps
-          cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/s/deps
-          make
+          mkdir -p $(Agent.BuildDirectory)/temp-deps
+          cd $(Agent.BuildDirectory)/temp-deps
+          # position-independent LAPACK is required for almalinux8 builds
+          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 }}:
-#   - ${{ 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 }}
+- ${{ 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/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 }}
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ 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
-#   type: object
-#   default:
-#     - rocFFT:
-#       name: rocFFT
-#       sparseCheckoutDir: projects/rocfft
-#       skipUnifiedBuild: 'false'
-#       buildDependsOn:
-#         - hipRAND_build
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocFFT:
+      name: rocFFT
+      sparseCheckoutDir: projects/rocfft
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - hipRAND_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -206,14 +206,14 @@ jobs:
           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 }}
+- ${{ 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/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:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_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'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/deps'
+        cmakeBuildDir: '$(Agent.BuildDirectory)/s/deps/build'
+        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
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipSOLVER_test_${{ job.target }}
-    dependsOn: hipSOLVER_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipSOLVER
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        testExecutable: './hipsolver-test'
-        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 }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ 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'], ','), '${{ parameters.componentName }}')),
+          eq(${{ 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 }}
+      - 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 }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.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: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './hipsolver-test'
+          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:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      #- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  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 }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipSPARSE_test_${{ job.target }}
-    dependsOn: hipSPARSE_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipSPARSE
-        testDir: '$(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 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-aqlprofile.yml
+      - 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 }}
+          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:
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
     testJobs:
-      - gfx942:
-        target: gfx942
+      - { os: ubuntu2204, packageManager: apt, 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
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        gpuTarget: ${{ job.target }}
-        extraCopyDirectories:
-          - deps
-        extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
-        extraEnvVars:
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-          - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
-          - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/llvm/bin/hipcc
-          - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-        installLatestCMake: true
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          gpuTarget: ${{ job.target }}
+          extraCopyDirectories:
+            - deps
+          extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+            - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
+            - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/llvm/bin/hipcc
+            - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
+          installLatestCMake: true
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipSPARSELt_test_${{ job.target }}
-    dependsOn: hipSPARSELt_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipSPARSELt
-        testDir: '$(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 }}
+- ${{ 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 }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ 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 }}
+          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:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  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 }}
-    timeoutInMinutes: 90
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ 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
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
-        extraEnvVars:
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-        installLatestCMake: true
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+          installLatestCMake: true
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rccl_test_${{ job.target }}
-    timeoutInMinutes: 120
-    dependsOn: rccl_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rccl
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        testExecutable: './rccl-UnitTests'
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ 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 }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ 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/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          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: './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 }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rdc_test_${{ job.target }}
-    dependsOn: rdc_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    - name: ROCM_PATH
-      value: $(Agent.BuildDirectory)/rocm
-    - name: ROCM_DIR
-      value: $(Agent.BuildDirectory)/rocm
-    pool: ${{ job.target }}_test_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/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - task: Bash@3
-      displayName: Setup test environment
-      inputs:
-        targetType: inline
-        script: |
-          sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rdcd /usr/sbin/rdcd
-          echo $(Agent.BuildDirectory)/rocm/lib/rdc/grpc/lib | sudo tee /etc/ld.so.conf.d/grpc.conf
-          sudo ldconfig -v
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - task: Bash@3
-      displayName: Test rdc
-      inputs:
-        targetType: inline
-        script: >-
-          $(Agent.BuildDirectory)/rocm/share/rdc/rdctst_tests/rdctst
-          --batch_mode
-          --start_rdcd
-          --unauth_comm
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
-        extraPaths: /home/user/workspace/rocm/bin
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ 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
+      - name: ROCM_PATH
+        value: $(Agent.BuildDirectory)/rocm
+      - name: ROCM_DIR
+        value: $(Agent.BuildDirectory)/rocm
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+              downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - task: Bash@3
+        displayName: Setup test environment
+        inputs:
+          targetType: inline
+          script: |
+            sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rdcd /usr/sbin/rdcd
+            echo $(Agent.BuildDirectory)/rocm/lib/rdc/grpc/lib | sudo tee /etc/ld.so.conf.d/grpc.conf
+            sudo ldconfig -v
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - task: Bash@3
+        displayName: Test rdc
+        inputs:
+          targetType: inline
+          script: >-
+            $(Agent.BuildDirectory)/rocm/share/rdc/rdctst_tests/rdctst
+            --batch_mode
+            --start_rdcd
+            --unauth_comm
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        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:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    pool:  ${{ variables.MEDIUM_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:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_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: gfx1030 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      #- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      #- { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-# - name: downstreamComponentMatrix
-#   type: object
-#   default:
-#     # rocSOLVER depends on both rocBLAS and rocPRIM
-#     # for a unified build, rocBLAS will be the one to call rocSOLVER
-#     - rocSOLVER:
-#       name: rocSOLVER
-#       sparseCheckoutDir: projects/rocsolver
-#       skipUnifiedBuild: 'false'
-#       buildDependsOn:
-#         - rocBLAS_build
-#       unifiedBuild:
-#         downstreamAggregateNames: rocBLAS+rocPRIM
-#         buildDependsOn:
-#           - rocBLAS_build
-#           - rocPRIM_build
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocSPARSE:
+      name: rocSPARSE
+      sparseCheckoutDir: projects/rocsparse
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocBLAS_build
+    # rocSOLVER depends on both rocBLAS and rocPRIM
+    # for a unified build, rocBLAS will be the one to call rocSOLVER
+#    - rocSOLVER:
+#      name: rocSOLVER
+#      sparseCheckoutDir: projects/rocsolver
+#      skipUnifiedBuild: 'false'
+#      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;$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
           -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 }}:
-#   - ${{ 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 }}
+- ${{ 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/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
-#   type: object
-#   default:
-#     - hipFFT:
-#       name: hipFFT
-#       sparseCheckoutDir: projects/hipfft
-#       skipUnifiedBuild: 'false'
-#       buildDependsOn:
-#         - rocFFT_build
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipFFT:
+      name: hipFFT
+      sparseCheckoutDir: projects/hipfft
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - 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 }}
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ 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 }}:
-#   - ${{ 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 }}
+- ${{ 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/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:
-    #   name: rocSOLVER
-    #   sparseCheckoutDir: projects/rocsolver
-    #   skipUnifiedBuild: 'true'
-    #   buildDependsOn:
-    #     - rocPRIM_build
+#    - rocSOLVER:
+#      name: rocSOLVER
+#      sparseCheckoutDir: projects/rocsolver
+#      skipUnifiedBuild: 'true'
+#      buildDependsOn:
+#        - 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:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, 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
-  # 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
+        testDir: $(Agent.BuildDirectory)/rocm/share/rocpydecode/tests
     - 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
-    - libgtest-dev
+    - libfmt-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: gfx1030 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
-      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      #- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      #- { 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:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { 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: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  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_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang++
+          -DCMAKE_C_COMPILER=$(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
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
-        extraEnvVars:
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocSPARSE_test_${{ job.target }}
-    timeoutInMinutes: 90
-    dependsOn: rocSPARSE_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocSPARSE
-        testDir: '$(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 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 }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ 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-aqlprofile.yml
+      - 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 }}
+          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 }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
-    dependsOn: rocm_smi_lib_build_${{ job.os }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        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/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:
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-      parameters:
-        runRocminfo: false
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocm_smi_lib
-        testDir: '$(Agent.BuildDirectory)'
-        testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
+      dependsOn: rocm_smi_lib_build_${{ 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:
+      - 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:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+        parameters:
+          runRocminfo: false
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)'
+          testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
+          testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          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
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocminfo_test_${{ job.target }}
-    dependsOn: rocminfo_build_${{ job.os }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        packageManager: ${{ job.packageManager }}
-        registerROCmPackages: true
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        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 }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-      parameters:
-        runRocminfo: false
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocminfo
-        testDir: '$(Agent.BuildDirectory)'
-        testExecutable: './rocm/bin/rocminfo'
-        testParameters: ''
-        testPublishResults: false
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocm_agent_enumerator
-        testDir: '$(Agent.BuildDirectory)'
-        testExecutable: './rocm/bin/rocm_agent_enumerator'
-        testParameters: ''
-        testPublishResults: false
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        registerROCmPackages: true
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: rocminfo_test_${{ job.target }}
+      dependsOn: rocminfo_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/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+          registerROCmPackages: true
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          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
+        parameters:
+          runRocminfo: false
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)'
+          testExecutable: './rocm/bin/rocminfo'
+          testParameters: ''
+          testPublishResults: false
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: rocm_agent_enumerator
+          testDir: '$(Agent.BuildDirectory)'
+          testExecutable: './rocm/bin/rocm_agent_enumerator'
+          testParameters: ''
+          testPublishResults: false
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          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:
-        name: gfx942_staging
+      - gfx942:
         target: gfx942
-        dependencySource: staging
-      - gfx942-mainline:
-        name: gfx942_mainline
-        target: gfx942
-        dependencySource: mainline
-      - gfx90a-staging:
-        name: gfx90a_staging
+      - gfx90a:
         target: gfx90a
-        dependencySource: staging
-      - gfx90a-mainline:
-        name: gfx90a_mainline
-        target: gfx90a
-        dependencySource: mainline
     testJobs:
-      - gfx942-staging:
-        name: gfx942_staging
+      - gfx942:
         target: gfx942
-        dependencySource: staging
-      - gfx942-mainline:
-        name: gfx942_mainline
-        target: gfx942
-        dependencySource: mainline
-      - gfx90a-staging:
-        name: gfx90a_staging
+      - gfx90a:
         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 }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocprofiler_compute_test_${{ job.name }}
-    timeoutInMinutes: 120
-    dependsOn: rocprofiler_compute_build_${{ job.name }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    - name: PYTHON_VERSION
-      value: 3.10
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-    - 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/local-artifact-download.yml
-      parameters:
-        postTargetFilter: ${{ job.dependencySource }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        dependencySource: ${{ job.dependencySource }}
-        gpuTarget: ${{ job.target }}
-    - task: Bash@3
-      displayName: Add en_US.UTF-8 locale
-      inputs:
-        targetType: inline
-        script: |
-          sudo locale-gen en_US.UTF-8
-          sudo update-locale
-          locale -a
-    - task: Bash@3
-      displayName: Add ROCm binaries to PATH
-      inputs:
-        targetType: inline
-        script: |
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-      parameters:
-        extraBuildFlags: >-
-          -DCMAKE_HIP_ARCHITECTURES=${{ job.target }}
-          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-          -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
-          -DCMAKE_BUILD_TYPE=Release
-          -DENABLE_TESTS=ON
-          -DINSTALL_TESTS=ON
-          -GNinja
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocprofiler-compute
-        testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
-        testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: rocprofiler_compute_test_${{ job.target }}
+      timeoutInMinutes: 120
+      dependsOn: rocprofiler_compute_build_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ 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
+      - name: PYTHON_VERSION
+        value: 3.10
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+      - 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/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - task: Bash@3
+        displayName: Add en_US.UTF-8 locale
+        inputs:
+          targetType: inline
+          script: |
+            sudo locale-gen en_US.UTF-8
+            sudo update-locale
+            locale -a
+      - task: Bash@3
+        displayName: Add ROCm binaries to PATH
+        inputs:
+          targetType: inline
+          script: |
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+        parameters:
+          extraBuildFlags: >-
+            -DCMAKE_HIP_ARCHITECTURES=${{ job.target }}
+            -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
+            -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
+            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+            -DROCM_PATH=$(Agent.BuildDirectory)/rocm
+            -DCMAKE_BUILD_TYPE=Release
+            -DENABLE_TESTS=ON
+            -DINSTALL_TESTS=ON
+            -GNinja
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
+          testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          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:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, 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
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocprofiler_sdk_test_${{ job.target }}
-    dependsOn: rocprofiler_sdk_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        registerROCmPackages: true
-    - 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-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependencies }}
-        gpuTarget: ${{ job.target }}
-    - task: Bash@3
-      displayName: Add Python and ROCm binaries to path
-      inputs:
-        targetType: inline
-        script: |
-          USER_BASE=$(python3 -m site --user-base)
-          echo "##vso[task.prependpath]$USER_BASE/bin"
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-      parameters:
-        extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-          -DROCPROFILER_BUILD_TESTS=ON
-          -DROCPROFILER_BUILD_SAMPLES=ON
-          -DROCPROFILER_BUILD_RELEASE=ON
-          -DGPU_TARGETS=${{ job.target }}
-          -GNinja
-    - template: ${{ variables.CI_TEMPLATE_PATH}}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocprofiler-sdk
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        gpuTarget: ${{ job.target }}
-        registerROCmPackages: true
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: rocprofiler_sdk_test_${{ job.os }}_${{ job.target }}
+      dependsOn: rocprofiler_sdk_build_${{ 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:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        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:
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+      - 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 }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+              downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - task: Bash@3
+        displayName: Add Python and ROCm binaries to path
+        inputs:
+          targetType: inline
+          script: |
+            USER_BASE=$(python3 -m site --user-base)
+            echo "##vso[task.prependpath]$USER_BASE/bin"
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/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
+            -DROCPROFILER_BUILD_SAMPLES=ON
+            -DROCPROFILER_BUILD_RELEASE=ON
+            -DGPU_TARGETS=${{ job.target }}
+            -GNinja
+      - 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)/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
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocprofiler_systems_test_${{ job.target }}
-    dependsOn: rocprofiler_systems_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    timeoutInMinutes: 180
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    - name: ROCM_PATH
-      value: $(Agent.BuildDirectory)/rocm
-    pool:
-      name: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        registerROCmPackages: true
-    - 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-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependencies }}
-        gpuTarget: ${{ job.target }}
-    - task: Bash@3
-      displayName: Add ROCm binaries to PATH
-      inputs:
-        targetType: inline
-        script: |
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
-          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-      parameters:
-  # build flags reference: https://rocm.docs.amd.com/projects/omnitrace/en/latest/install/install.html
-        extraBuildFlags: >-
-          -DROCPROFSYS_BUILD_TESTING=ON
-          -DROCPROFSYS_BUILD_DYNINST=ON
-          -DROCPROFSYS_BUILD_LIBUNWIND=ON
-          -DROCPROFSYS_DISABLE_EXAMPLES="openmp-target"
-          -DDYNINST_BUILD_TBB=ON
-          -DDYNINST_BUILD_ELFUTILS=ON
-          -DDYNINST_BUILD_LIBIBERTY=ON
-          -DDYNINST_BUILD_BOOST=ON
-          -DROCPROFSYS_USE_PAPI=ON
-          -DROCPROFSYS_USE_MPI=ON
-          -DCMAKE_CXX_FLAGS=-I$(Agent.BuildDirectory)/rocm/include/rocjpeg
-          -DGPU_TARGETS=${{ job.target }}
-          -GNinja
-    - task: Bash@3
-      displayName: Set up rocprofiler-systems env
-      inputs:
-        targetType: inline
-        script: source share/rocprofiler-systems/setup-env.sh
-        workingDirectory: build
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocprofiler-systems
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-      parameters:
-        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
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: rocprofiler_systems_test_${{ job.target }}
+      dependsOn: rocprofiler_systems_build_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      timeoutInMinutes: 180
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      - name: ROCM_PATH
+        value: $(Agent.BuildDirectory)/rocm
+      pool:
+        name: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          registerROCmPackages: true
+      - 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-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmDependencies }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - task: Bash@3
+        displayName: Add ROCm binaries to PATH
+        inputs:
+          targetType: inline
+          script: |
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+        parameters:
+          cmakeSourceDir: $(Agent.BuildDirectory)/s/projects/rocprofiler-systems
+    # build flags reference: https://rocm.docs.amd.com/projects/omnitrace/en/latest/install/install.html
+          extraBuildFlags: >-
+            -DCMAKE_INSTALL_PREFIX=$(Agent.BuildDirectory)/rocprofiler-systems
+            -DROCPROFSYS_USE_PYTHON=ON
+            -DROCPROFSYS_BUILD_TESTING=ON
+            -DROCPROFSYS_BUILD_DYNINST=ON
+            -DROCPROFSYS_BUILD_LIBUNWIND=ON
+            -DROCPROFSYS_DISABLE_EXAMPLES="openmp-target"
+            -DDYNINST_BUILD_TBB=ON
+            -DDYNINST_BUILD_ELFUTILS=ON
+            -DDYNINST_BUILD_LIBIBERTY=ON
+            -DDYNINST_BUILD_BOOST=ON
+            -DROCPROFSYS_USE_PAPI=ON
+            -DROCPROFSYS_USE_MPI=ON
+            -DCMAKE_CXX_FLAGS=-I$(Agent.BuildDirectory)/rocm/include/rocjpeg
+            -DGPU_TARGETS=${{ job.target }}
+            -GNinja
+      - task: Bash@3
+        displayName: Set up rocprofiler-systems env
+        inputs:
+          targetType: inline
+          script: source $(Agent.BuildDirectory)/rocprofiler-systems/share/rocprofiler-systems/setup-env.sh
+          workingDirectory: $(Agent.BuildDirectory)/rocprofiler-systems/share/rocprofiler-systems
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: $(Agent.BuildDirectory)/s/build/tests/
+          testParameters: '--output-on-failure'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+        parameters:
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+        parameters:
+          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 }}:
-  - 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_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    - name: ROCM_PATH
-      value: $(Agent.BuildDirectory)/rocm
-    - name: LD_LIBRARY_PATH
-      value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - 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:
-        gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-      parameters:
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependencies }}
-        gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocprofilerV1
-        testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
-        testExecutable:  ./run.sh
-        testParameters: ''
-        testPublishResults: false
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocprofilerV2
-        testDir: $(Agent.BuildDirectory)/rocm
-        testExecutable:  share/rocprofiler/tests/runUnitTests
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        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_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      - name: ROCM_PATH
+        value: $(Agent.BuildDirectory)/rocm
+      - name: LD_LIBRARY_PATH
+        value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
+      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-aqlprofile.yml
+        parameters:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmDependencies }}
+          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: rocprofilerV1
+          testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
+          testExecutable:  ./run.sh
+          testParameters: ''
+          testPublishResults: false
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: rocprofilerV2
+          testDir: $(Agent.BuildDirectory)/rocm
+          testExecutable:  share/rocprofiler/tests/runUnitTests
+          testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+          os: ${{ job.os }}
+      - 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 }}:
-  - 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_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ 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/dependencies-other.yml
-      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/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: roctracer
-        testExecutable: $(Agent.BuildDirectory)/rocm/share/roctracer/run_tests.sh
-        testParameters: ''
-        testDir: $(Agent.BuildDirectory)
-        testPublishResults: false
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        gpuTarget: ${{ job.target }}
-        registerROCmPackages: true
+- ${{ 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:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        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/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.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 }}
+          testExecutable: $(Agent.BuildDirectory)/rocm/share/roctracer/run_tests.sh
+          testParameters: ''
+          testDir: $(Agent.BuildDirectory)
+          testPublishResults: false
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          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, target: gfx90a, source: staging }
-    - { os: ubuntu2204, target: gfx1201, source: staging }
-    - { os: ubuntu2204, target: gfx1100, source: staging }
-    - { os: ubuntu2204, target: gfx1030, source: staging }
-    - { os: ubuntu2404, target: gfx942, source: staging }
-    - { os: ubuntu2404, target: gfx90a, source: staging }
-    - { os: ubuntu2404, target: gfx1201, source: staging }
-    - { os: ubuntu2404, target: gfx1100, source: staging }
-    - { os: ubuntu2404, target: gfx1030, source: staging }
-    - { os: almalinux8, target: gfx942, source: staging }
-    - { os: almalinux8, target: gfx90a, source: staging }
-    - { os: almalinux8, target: gfx1201, source: staging }
-    - { os: almalinux8, target: gfx1100, source: staging }
-    - { os: almalinux8, target: gfx1030, source: staging }
+    - { 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: gfx1030 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx942 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx90a }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1201 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1100 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1030 }
+    - { os: almalinux8, packageManager: dnf, target: gfx942 }
+    - { os: almalinux8, packageManager: dnf, target: gfx90a }
+    - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+    - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+    - { 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
-  displayName: Extract ${{ parameters.componentName }}
-  inputs:
-    archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
-    destinationFolder: '$(Agent.BuildDirectory)/rocm'
-    cleanDestinationFolder: false
-    overwriteExistingFiles: true
-- task: DeleteFiles@1
-  displayName: Cleanup Compressed ${{ parameters.componentName }}
-  inputs:
-    SourceFolder: '$(Pipeline.Workspace)/d'
-    Contents: '**/*.tar.gz'
-    RemoveDotFiles: true
+- ${{ if eq(parameters.extractAndDeleteFiles, true) }}:
+  - task: ExtractFiles@1
+    displayName: Extract ${{ parameters.componentName }}
+    inputs:
+      archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
+      destinationFolder: '$(Agent.BuildDirectory)/rocm'
+      cleanDestinationFolder: false
+      overwriteExistingFiles: true
+  - task: DeleteFiles@1
+    displayName: Clean up Compressed ${{ parameters.componentName }}
+    inputs:
+      SourceFolder: '$(Pipeline.Workspace)/d'
+      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 $(Agent.JobName) | sed 's/ /./g; s/[-_]//g')
-      ARTIFACT_STRING="pipelineartifact://ROCm-CI/projectId/$(DOWNLOAD_PROJECT_ID)/buildId/$(Build.BuildId)/artifactName/${FORMATTED_JOB_NAME}"
+      ARTIFACT_NAME="$(Agent.JobName)_$(System.JobAttempt)"
+      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
-  default: aocl-linux-gcc-4.2.0_1_amd64.deb
+  type: object
+  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
-- task: Bash@3
-  displayName: 'sudo apt-get fix'
-  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) }}
+      sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update && \
+        sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-broken install && \
+        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
-  inputs:
-    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'
+  displayName: Download and install aqlprofile
+  retryCountOnTaskFailure: 3
   inputs:
     targetType: inline
+    workingDirectory: $(Agent.BuildDirectory)
     script: |
-      mkdir -p $(Agent.BuildDirectory)/rocm
-      cp -R hsa-amd-aqlprofile/opt/rocm-*/* $(Agent.BuildDirectory)/rocm
-    workingDirectory: '$(Pipeline.Workspace)'
-- task: Bash@3
-  displayName: 'Clean up aqlprofile'
-  inputs:
-    targetType: inline
-    script: rm -rf hsa-amd-aqlprofile $(packageName)
-    workingDirectory: '$(Pipeline.Workspace)'
+      set -e
+      if [ "${{ parameters.os }}" = "ubuntu2204" ]; then
+        packageName=$(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") && \
+        wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$packageName && \
+        mkdir -p hsa-amd-aqlprofile && \
+        dpkg-deb -R $packageName hsa-amd-aqlprofile
+      elif [ "${{ parameters.os }}" = "almalinux8" ]; then
+        sudo dnf -y install rpm-build cpio && \
+        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
-          unzip ninja-linux.zip
-          sudo mv ninja /usr/local/bin/ninja
-          sudo chmod +x /usr/local/bin/ninja
+          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 && \
+          sudo mv ninja /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)
-      stagingBranch: develop
-      mainlineBranch: master
+      pipelineId: 113
+      developBranch: develop
       hasGpuTarget: true
     amdsmi:
-      pipelineId: $(AMDSMI_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 99
+      developBranch: amd-staging
       hasGpuTarget: false
     aomp-extras:
-      pipelineId: $(AOMP_EXTRAS_PIPELINE_ID)
-      stagingBranch: aomp-dev
-      mainlineBranch: aomp-dev
+      pipelineId: 111
+      developBranch: aomp-dev
       hasGpuTarget: false
     aomp:
-      pipelineId: $(AOMP_PIPELINE_ID)
-      stagingBranch: aomp-dev
-      mainlineBranch: amd-mainline
+      pipelineId: 115
+      developBranch: aomp-dev
+      hasGpuTarget: false
+    aqlprofile:
+      pipelineId: 365
+      developBranch: develop
       hasGpuTarget: false
     clr:
-      pipelineId: $(CLR_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 335
+      developBranch: develop
       hasGpuTarget: false
     composable_kernel:
-      pipelineId: $(COMPOSABLE_KERNEL_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 86
+      developBranch: develop
       hasGpuTarget: true
     half:
-      pipelineId: $(HALF_PIPELINE_ID)
-      stagingBranch: rocm
-      mainlineBranch: rocm
+      pipelineId: 101
+      developBranch: rocm
       hasGpuTarget: false
     HIP:
-      pipelineId: $(HIP_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 335
+      developBranch: develop
       hasGpuTarget: false
     hip-tests:
-      pipelineId: $(HIP_TESTS_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 362
+      developBranch: develop
       hasGpuTarget: false
     hipBLAS:
-      pipelineId: $(HIPBLAS_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 317
+      developBranch: develop
       hasGpuTarget: true
     hipBLASLt:
-      pipelineId: $(HIPBLASLT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 301
+      developBranch: develop
       hasGpuTarget: true
     hipBLAS-common:
-      pipelineId: $(HIPBLAS_COMMON_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 300
+      developBranch: develop
       hasGpuTarget: false
     hipCUB:
-      pipelineId: $(HIPCUB_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 277
+      developBranch: develop
       hasGpuTarget: true
     hipFFT:
-      pipelineId: $(HIPFFT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 283
+      developBranch: develop
       hasGpuTarget: true
     hipfort:
-      pipelineId: $(HIPFORT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 102
+      developBranch: develop
       hasGpuTarget: false
     HIPIFY:
-      pipelineId: $(HIPIFY_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 92
+      developBranch: amd-staging
       hasGpuTarget: false
     hipRAND:
-      pipelineId: $(HIPRAND_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 275
+      developBranch: develop
       hasGpuTarget: true
     hipSOLVER:
-      pipelineId: $(HIPSOLVER_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 84
+      developBranch: develop
       hasGpuTarget: true
     hipSPARSE:
-      pipelineId: $(HIPSPARSE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 315
+      developBranch: develop
       hasGpuTarget: true
     hipSPARSELt:
-      pipelineId: $(HIPSPARSELT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 309
+      developBranch: develop
       hasGpuTarget: true
     hipTensor:
-      pipelineId: $(HIPTENSOR_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 105
+      developBranch: develop
       hasGpuTarget: true
     llvm-project:
-      pipelineId: $(LLVM_PROJECT_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 2
+      developBranch: amd-staging
       hasGpuTarget: false
     MIOpen:
-      pipelineId: $(MIOpen_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: amd-master
+      pipelineId: 320
+      developBranch: develop
       hasGpuTarget: true
     MIVisionX:
-      pipelineId: $(MIVISIONX_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: master
+      pipelineId: 80
+      developBranch: develop
       hasGpuTarget: true
-    omnitrace: # deprecated
-      pipelineId: $(OMNITRACE_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+    origami:
+      pipelineId: 364
+      developBranch: develop
       hasGpuTarget: true
     rccl:
-      pipelineId: $(RCCL_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 107
+      developBranch: develop
       hasGpuTarget: true
     rdc:
-      pipelineId: $(RDC_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 360
+      developBranch: develop
       hasGpuTarget: false
     rocAL:
-      pipelineId: $(ROCAL_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 151
+      developBranch: develop
       hasGpuTarget: true
     rocALUTION:
-      pipelineId: $(ROCALUTION_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 89
+      developBranch: develop
       hasGpuTarget: true
     rocBLAS:
-      pipelineId: $(ROCBLAS_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 302
+      developBranch: develop
       hasGpuTarget: true
     ROCdbgapi:
-      pipelineId: $(ROCDBGAPI_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 135
+      developBranch: amd-staging
       hasGpuTarget: false
     rocDecode:
-      pipelineId: $(ROCDECODE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 79
+      developBranch: develop
       hasGpuTarget: false
     rocFFT:
-      pipelineId: $(ROCFFT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 282
+      developBranch: develop
       hasGpuTarget: true
     ROCgdb:
-      pipelineId: $(ROCGDB_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline-rocgdb-15
+      pipelineId: 134
+      developBranch: amd-staging
       hasGpuTarget: false
     rocJPEG:
-      pipelineId: $(ROCJPEG_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 262
+      developBranch: develop
       hasGpuTarget: false
     rocm-cmake:
-      pipelineId: $(ROCM_CMAKE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 6
+      developBranch: develop
       hasGpuTarget: false
     rocm-core:
-      pipelineId: $(ROCM_CORE_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: amd-master
+      pipelineId: 349
+      developBranch: develop
       hasGpuTarget: false
     rocm-examples:
-      pipelineId: $(ROCM_EXAMPLES_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 216
+      developBranch: amd-staging
       hasGpuTarget: true
     rocminfo:
-      pipelineId: $(ROCMINFO_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 356
+      developBranch: develop
       hasGpuTarget: false
     rocMLIR:
-      pipelineId: $(ROCMLIR_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 229
+      developBranch: develop
       hasGpuTarget: false
     ROCmValidationSuite:
-      pipelineId: $(ROCMVALIDATIONSUITE_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: master
+      pipelineId: 106
+      developBranch: master
       hasGpuTarget: true
     rocm_bandwidth_test:
-      pipelineId: $(ROCM_BANDWIDTH_TEST_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: master
+      pipelineId: 88
+      developBranch: master
       hasGpuTarget: false
     rocm_smi_lib:
-      pipelineId: $(ROCM_SMI_LIB_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 358
+      developBranch: develop
       hasGpuTarget: false
     rocPRIM:
-      pipelineId: $(ROCPRIM_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 273
+      developBranch: develop
       hasGpuTarget: true
     rocprofiler:
-      pipelineId: $(ROCPROFILER_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-master
+      pipelineId: 329
+      developBranch: develop
       hasGpuTarget: true
     rocprofiler-compute:
-      pipelineId: $(ROCPROFILER_COMPUTE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: amd-mainline
+      pipelineId: 344
+      developBranch: develop
       hasGpuTarget: true
     rocprofiler-register:
-      pipelineId: $(ROCPROFILER_REGISTER_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 327
+      developBranch: develop
       hasGpuTarget: false
     rocprofiler-sdk:
-      pipelineId: $(ROCPROFILER_SDK_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 347
+      developBranch: develop
       hasGpuTarget: true
     rocprofiler-systems:
-      pipelineId: $(ROCPROFILER_SYSTEMS_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 345
+      developBranch: develop
       hasGpuTarget: true
     rocPyDecode:
-      pipelineId: $(ROCPYDECODE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 239
+      developBranch: develop
       hasGpuTarget: true
     ROCR-Runtime:
-      pipelineId: $(ROCR_RUNTIME_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 354
+      developBranch: develop
       hasGpuTarget: false
     rocRAND:
-      pipelineId: $(ROCRAND_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 274
+      developBranch: develop
       hasGpuTarget: true
     rocr_debug_agent:
-      pipelineId: $(ROCR_DEBUG_AGENT_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 136
+      developBranch: amd-staging
       hasGpuTarget: false
     rocSOLVER:
-      pipelineId: $(ROCSOLVER_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 81
+      developBranch: develop
       hasGpuTarget: true
     rocSPARSE:
-      pipelineId: $(ROCSPARSE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 314
+      developBranch: develop
       hasGpuTarget: true
-    ROCT-Thunk-Interface: # deprecated
-      pipelineId: $(ROCT_THUNK_INTERFACE_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: master
-      hasGpuTarget: false
     rocThrust:
-      pipelineId: $(ROCTHRUST_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 276
+      developBranch: develop
       hasGpuTarget: true
     roctracer:
-      pipelineId: $(ROCTRACER_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 331
+      developBranch: develop
       hasGpuTarget: true
     rocWMMA:
-      pipelineId: $(ROCWMMA_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 109
+      developBranch: develop
       hasGpuTarget: true
     rpp:
-      pipelineId: $(RPP_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 78
+      developBranch: develop
       hasGpuTarget: true
     TransferBench:
-      pipelineId: $(TRANSFERBENCH_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 265
+      developBranch: develop
       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 }}
-        ${{ if parameters.componentVarList[split(dependency, ':')[0]].hasGpuTarget }}:
-          fileFilter: "${{ 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 }}
+        extractAndDeleteFiles: false
 # 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 }}:
-          gpuTarget: ${{ parameters.gpuTarget }}
+        buildType: current
         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
-        ${{ if eq(parameters.dependencySource, 'staging')}}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
-        # dependencySource = mainline
-        ${{ elseif eq(parameters.dependencySource, 'mainline')}}:
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
-        # checkoutRef = staging
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].stagingBranch) }}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
-        # checkoutRef = mainline
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
-        # SourceBranchName = staging
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].stagingBranch) }}:
-          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: ExtractFiles@1
+  displayName: Extract ROCm artifacts
+  inputs:
+    archiveFilePatterns: $(Pipeline.Workspace)/d/**/*.tar.gz
+    destinationFolder: $(Agent.BuildDirectory)/rocm
+    cleanDestinationFolder: false
+    overwriteExistingFiles: true
+- task: DeleteFiles@1
+  displayName: Clean up ROCm artifacts
+  inputs:
+    SourceFolder: $(Pipeline.Workspace)/d
+    Contents: '**/*.tar.gz'
+    RemoveDotFiles: true
+- ${{ if containsValue(parameters.dependencyList, 'llvm-project') }}:
   - 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
-    displayName: 'Link ROCm shared libraries'
-    inputs:
-      targetType: inline
-# OS ignores if the ROCm lib folder shows up more than once
-      script: |
-        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/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 ldconfig -v
-        ldconfig -p
+- task: Bash@3
+  displayName: 'Link ROCm shared libraries'
+  inputs:
+    targetType: inline
+    # OS ignores if the ROCm lib folder shows up more than once
+    script: |
+      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/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 ldconfig -v
+      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"
-
-      cat $manifest_json
+- task: Bash@3
+  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 }}_${{ parameters.artifactName }}.html" >> pipelineArtifacts.txt
-      echo "manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.json" >> pipelineArtifacts.txt
+      echo "$(manifest_filename).html" >> 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=$ARTIFACT_NAME&api-version=7.1"
-      ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
+      AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?api-version=7.1"
+      ARTIFACT_URL=$(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"
-        ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
+        AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?api-version=7.1"
+        ARTIFACT_URL=$(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)
-      mkdir -p $(Agent.BuildDirectory)/rocm
-      tar -zxvf $(System.ArtifactsDirectory)/$ARTIFACT_NAME/*.tar.gz -C $(Agent.BuildDirectory)/rocm
-      rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/$ARTIFACT_NAME
+
+      RETRIES=0
+      MAX_RETRIES=5
+      SUCCESS=false
+      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

.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 +35,9 @@ AlexNet
 Andrej
 Arb
 Autocast
+autograd
 BARs
+BatchNorm
 BLAS
 BMC
 BabelStream
@@ -80,9 +45,11 @@ Blit
 Blockwise
 Bluefield
 Bootloader
+Broadcom
 CAS
 CCD
 CDNA
+CGUI
 CHTML
 CIFAR
 CLI
@@ -98,6 +65,7 @@ CPU
 CPUs
 Cron
 CSC
+CSDATA
 CSE
 CSV
 CSn
@@ -107,6 +75,7 @@ CU
 CUDA
 CUs
 CXX
+CX
 Cavium
 CentOS
 ChatGPT
@@ -117,19 +86,26 @@ 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 +117,29 @@ 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
+FIFOs
 FFT
 FFTs
 FFmpeg
@@ -166,10 +151,14 @@ FX
 Filesystem
 FindDb
 Flang
+FlashAttention
+FlashInfer’s
+FlashInfer
 FluxBenchmark
 Fortran
 Fuyu
 GALB
+GAT
 GCC
 GCD
 GCDs
@@ -183,6 +172,7 @@ GEMMs
 GFLOPS
 GFortran
 GFXIP
+GGUF
 Gemma
 GiB
 GIM
@@ -196,8 +186,12 @@ GPR
 GPT
 GPU
 GPU's
+GPUDirect
 GPUs
+GraphBolt
+GraphSage
 GRBM
+GRE
 GenAI
 GenZ
 GitHub
@@ -206,9 +200,11 @@ HBM
 HCA
 HGX
 HIPCC
+hipDataType
 HIPExtension
 HIPIFY
 HIPification
+hipification
 HIPify
 HPC
 HPCG
@@ -220,17 +216,24 @@ 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
@@ -257,6 +260,7 @@ KV
 KVM
 Karpathy's
 KiB
+Kineto
 Keras
 Khronos
 LAPACK
@@ -266,11 +270,15 @@ LLM
 LLMs
 LLVM
 LM
+LRU
 LSAN
 LSan
 LTS
+LSTMs
+LteAll
 LanguageCrossEntropy
 LoRA
+MECO
 MEM
 MERCHANTABILITY
 MFMA
@@ -289,6 +297,7 @@ MNIST
 MPI
 MPT
 MSVC
+mul
 MVAPICH
 MVFFR
 Makefile
@@ -296,6 +305,8 @@ Makefiles
 Matplotlib
 Matrox
 MaxText
+MBT
+Megablocks
 Megatrends
 Megatron
 Mellanox
@@ -304,11 +315,17 @@ Meta's
 Miniconda
 MirroredStrategy
 Mixtral
+MLA
 MosaicML
+MoEs
+Mooncake
+Mpops
 Multicore
 Multithreaded
+MXFP
 MyEnvironment
 MyST
+NANOO
 NBIO
 NBIOs
 NCCL
@@ -318,6 +335,7 @@ NIC
 NICs
 NLI
 NLP
+NN
 NPKit
 NPS
 NSP
@@ -340,6 +358,7 @@ OFED
 OMM
 OMP
 OMPI
+OOM
 OMPT
 OMPX
 ONNX
@@ -354,6 +373,7 @@ OpenMPI
 OpenSSL
 OpenVX
 OpenXLA
+Optim
 Oversubscription
 PagedAttention
 Pallas
@@ -361,6 +381,7 @@ PCC
 PCI
 PCIe
 PEFT
+perf
 PEQT
 PIL
 PILImage
@@ -378,10 +399,12 @@ PowerEdge
 PowerShell
 Pretrained
 Pretraining
+Primus
 Profiler's
 PyPi
 Pytest
 PyTorch
+QPS
 Qcycles
 Qwen
 RAII
@@ -392,6 +415,7 @@ RDC's
 RDMA
 RDNA
 README
+Recomputation
 RHEL
 RMW
 RNN
@@ -424,11 +448,13 @@ Ryzen
 SALU
 SBIOS
 SCA
+ScaledGEMM
 SDK
 SDMA
 SDPA
 SDRAM
 SENDMSG
+SGLang
 SGPR
 SGPRs
 SHA
@@ -440,7 +466,9 @@ SKU
 SKUs
 SLES
 SLURM
+Slurm
 SMEM
+SMFMA
 SMI
 SMT
 SPI
@@ -452,18 +480,26 @@ 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
@@ -471,6 +507,8 @@ TPS
 TPU
 TPUs
 TSME
+Taichi
+Taichi's
 Tagram
 TensileLite
 TensorBoard
@@ -503,9 +541,11 @@ UltraChat
 Uncached
 Unittests
 Unhandled
+unwindowed
 VALU
 VBIOS
 VCN
+verl's
 VGPR
 VGPRs
 VM
@@ -518,11 +558,13 @@ Vanhoucke
 Vulkan
 WGP
 WGPs
+WR
 WX
 WikiText
 Wojna
 Workgroups
 Writebacks
+xcc
 XCD
 XCDs
 XGBoost
@@ -535,6 +577,7 @@ Xilinx
 Xnack
 Xteam
 YAML
+YAMLs
 YML
 YModel
 ZeRO
@@ -542,6 +585,7 @@ ZenDNN
 accuracies
 activations
 addr
+addEventListener
 ade
 ai
 alloc
@@ -550,12 +594,14 @@ allocator
 allocators
 amdgpu
 api
+aten
 atmi
 atomics
 autogenerated
 autotune
 avx
 awk
+az
 backend
 backends
 bb
@@ -573,6 +619,7 @@ boson
 bosons
 br
 BrainFloat
+btn
 buildable
 bursty
 bzip
@@ -584,17 +631,21 @@ centric
 changelog
 checkpointing
 chiplet
+classList
 cmake
 cmd
 coalescable
 codename
 collater
 comgr
+compat
 completers
 composable
 concretization
 config
+configs
 conformant
+const
 constructible
 convolutional
 convolves
@@ -629,12 +680,14 @@ denoised
 denoises
 denormalize
 dequantization
+dequantized
 dequantizes
 deserializers
 detections
 dev
 devicelibs
 devsel
+dgl
 dimensionality
 disambiguates
 distro
@@ -658,6 +711,7 @@ exascale
 executables
 ffmpeg
 filesystem
+forEach
 fortran
 fp
 framebuffer
@@ -666,13 +720,16 @@ galb
 gcc
 gdb
 gemm
+getAttribute
 gfortran
 gfx
 githooks
 github
 globals
 gnupg
+gpu
 grayscale
+gx
 gzip
 heterogenous
 hipBLAS
@@ -720,10 +777,12 @@ installable
 interop
 interprocedural
 intra
+intrinsics
 invariants
 invocating
 ipo
 jax
+json
 kdb
 kfd
 kv
@@ -737,12 +796,17 @@ linalg
 linearized
 linter
 linux
+llm
 llvm
+lm
 localscratch
 logits
 lossy
 macOS
 matchers
+maxtext
+megablocks
+megatron
 microarchitecture
 migraphx
 migratable
@@ -770,6 +834,7 @@ opencv
 openmp
 openssl
 optimizers
+ol
 os
 oversubscription
 pageable
@@ -779,8 +844,10 @@ parallelizing
 param
 parameterization
 passthrough
+pe
 perfcounter
 performant
+piecewise
 perl
 pragma
 pre
@@ -801,11 +868,14 @@ preprocessing
 preprocessor
 prequantized
 prerequisites
+pretrain
 pretraining
+primus
 profiler
 profilers
 protobuf
 pseudorandom
+px
 py
 pytorch
 recommender
@@ -813,7 +883,10 @@ recommenders
 quantile
 quantizer
 quasirandom
+querySelector
+querySelectorAll
 queueing
+qwen
 radeon
 rccl
 rdc
@@ -822,6 +895,7 @@ reStructuredText
 redirections
 refactorization
 reformats
+reinforcememt
 repo
 repos
 representativeness
@@ -829,6 +903,9 @@ req
 resampling
 rescaling
 reusability
+rhel
+rl
+RLHF
 roadmap
 roc
 rocAL
@@ -866,22 +943,29 @@ 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 +973,7 @@ subdirectory
 subexpression
 subfolder
 subfolders
+submatrix
 submodule
 submodules
 subnet
@@ -897,8 +982,10 @@ symlink
 symlinks
 sys
 tabindex
+targetContainer
 td
 tensorfloat
+tf
 th
 tokenization
 tokenize
@@ -907,12 +994,16 @@ tokenizer
 tokenizes
 toolchain
 toolchains
+topk
 toolset
 toolsets
+torchtitan
 torchvision
+tp
 tqdm
 tracebacks
 txt
+TopK
 uarch
 uncached
 uncacheable
@@ -931,6 +1022,7 @@ USM
 UTCL
 UTIL
 utils
+UX
 vL
 variational
 vdi
@@ -940,6 +1032,7 @@ 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
 

RELEASE.md

@@ -0,0 +1,777 @@
+<!-- Do not edit this file!                                 -->
+<!-- This file is autogenerated with                        -->
+<!--   tools/autotag/tag_script.py                          -->
+<!-- Disable lints since this is an auto-generated file.    -->
+<!-- markdownlint-disable blanks-around-headers             -->
+<!-- markdownlint-disable no-duplicate-header               -->
+<!-- markdownlint-disable no-blanks-blockquote              -->
+<!-- markdownlint-disable ul-indent                         -->
+<!-- markdownlint-disable no-trailing-spaces                -->
+<!-- markdownlint-disable reference-links-images            -->
+<!-- markdownlint-disable no-missing-space-atx              -->
+<!-- spellcheck-disable                                     -->
+# ROCm 7.0.2 release notes
+
+The release notes provide a summary of notable changes since the previous ROCm release.
+
+- [Release highlights](#release-highlights)
+
+- [Supported hardware, operating system, and virtualization changes](#supported-hardware-operating-system-and-virtualization-changes)
+
+- [User space, driver, and firmware dependent changes](#user-space-driver-and-firmware-dependent-changes)
+
+- [ROCm components versioning](#rocm-components)
+
+- [Detailed component changes](#detailed-component-changes)
+
+- [ROCm known issues](#rocm-known-issues)
+
+- [ROCm upcoming changes](#rocm-upcoming-changes)
+
+```{note}
+If you’re using AMD Radeon GPUs or Ryzen APUs in a workstation setting with a display connected, see the [Use ROCm on Radeon and Ryzen](https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/index.html)
+documentation to verify compatibility and system requirements.
+```
+
+## Release highlights
+
+The following are notable new features and improvements in ROCm 7.0.2. For changes to individual components, see
+[Detailed component changes](#detailed-component-changes).
+
+### Supported hardware, operating system, and virtualization changes
+
+ROCm 7.0.2 adds support for the RDNA4 architecture-based [AMD Radeon RX 9060](https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9060.html). For more information about supported AMD hardware, see [Supported GPUs (Linux)](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.0.2/reference/system-requirements.html#supported-gpus).
+
+ROCm 7.0.2 adds support for the following operating systems and kernel versions:
+
+* Debian 13 (kernel: 6.12)
+* Oracle Linux 10 (kernel: 6.12.0 [UEK])
+* RHEL 10.0 (kernel: 6.12.0-55)
+
+For more information about supported operating systems, see [Supported operating systems](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.0.2/reference/system-requirements.html#supported-operating-systems) and [install instructions](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.0.2/).
+
+#### Virtualization support
+
+Virtualization support remains unchanged in this release. For more information, see  [Virtualization Support](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.0.2/reference/system-requirements.html#virtualization-support).
+
+### User space, driver, and firmware dependent changes
+
+The software for AMD Datacenter GPU products requires maintaining a hardware
+and software stack with interdependencies between the GPU and baseboard
+firmware, AMD GPU drivers, and the ROCm user space software.
+
+<div class="pst-scrollable-table-container">
+  <table class="table" align="left" valign="middle">
+    <thead>
+      <tr>
+          <th class="head">
+            <p>ROCm Version</p>
+          </th>
+          <th class="head">
+            <p>GPU</p>
+          </th>
+          <th class="head">
+            <p>PLDM Bundle (Firmware)</p>
+          </th>
+          <th class="head">
+            <p>AMD GPU Driver (amdgpu)</p>
+          </th>
+          <th class="head">
+            <p>AMD GPU <br>
+              Virtualization Driver (GIM)</p>
+          </th>
+      </tr>
+    </thead>
+    <style>
+        tbody#virtualization-support-instinct tr:last-child {
+          border-bottom: 2px solid var(--pst-color-primary);
+        }
+    </style>
+      <tr>
+          <td rowspan="9" style="vertical-align: middle;">ROCm 7.0.2</td>
+          <td>MI355X</td>
+          <td>
+              01.25.15.04<br>
+              01.25.13.09
+          </td>
+          <td>30.10.2<br>
+              30.10.1<br>
+              30.10</td>
+          <td rowspan="3" style="vertical-align: middle;">8.4.1.K</td>
+      </tr>
+      <tr>
+          <td>MI350X</td>
+          <td>
+              01.25.15.04<br>
+              01.25.13.09
+          </td>
+          <td>30.10.2<br>
+              30.10.1<br>
+              30.10</td>
+      </tr>
+      <tr>
+          <td>MI325X</td>
+          <td>
+              01.25.04.02<br>
+              01.25.03.03
+          </td>
+          <td>
+              30.10.2<br>
+              30.10.1<br>
+              30.10<br>
+              6.4.z where z (0-3)<br>
+              6.3.y where y (1-3)
+          </td>
+      </tr>
+      <tr>
+          <td>MI300X</td>
+          <td>01.25.05.00 (or later)<a href="#footnote1"><sup>[1]</sup></a><br>
+              01.25.03.12</td>
+          <td rowspan="6" style="vertical-align: middle;">
+              30.10.2<br>
+              30.10.1<br>
+              30.10<br>
+              6.4.z where z (0–3)<br>
+              6.3.y where y (0–3)<br>
+              6.2.x where x (1–4)
+          </td>
+          <td>8.4.1.K</td>
+      </tr>
+      <tr>
+          <td>MI300A</td>
+          <td>BKC 26<br>
+              BKC 25</td>
+          <td rowspan="3" style="vertical-align: middle;">Not Applicable</td>
+      </tr>
+      <tr>
+          <td>MI250X</td>
+          <td>IFWI 47</td>
+      </tr>
+      <tr>
+          <td>MI250</td>
+          <td>MU3 w/ IFWI 73</td>
+      </tr>
+      <tr>
+          <td>MI210</td>
+          <td>MU3 w/ IFWI 73</td>
+          <td>8.4.0.K</td>
+      </tr>
+      <tr>
+          <td>MI100</td>
+          <td>VBIOS D3430401-037</td>
+          <td>Not Applicable</td>
+      </tr>
+  </table>
+</div>
+
+<p id="footnote1">[1]: PLDM bundle 01.25.05.00 will be available by October 31, 2025.</p>
+
+#### AMD Instinct MI300X GPU resiliency improvement
+
+Multimedia Engine Reset is now supported in AMD GPU Driver (amdgpu) 30.10.2 for AMD Instinct MI300X GPUs. This finer-grain GPU resiliency feature allows recovery from faults related to VCN or JPEG without requiring a full GPU reset, thereby improving system stability and fault tolerance. Note that VCN queue reset functionality requires PLDM bundle 01.25.05.00 (or later) firmware.
+
+#### New OS support in ROCm dependent on AMD GPU Driver
+
+ROCm support for RHEL 10.0 and Oracle 10 requires AMD GPU Driver 30.10.2 or later.
+
+### RAG AI support enabled for ROCm
+
+In September 2025, Retrieval-Augmented Generation (RAG) was added to the ROCm platform. Use RAG to build and deploy end-to-end AI pipelines on AMD GPUs. It enhances the accuracy and reliability of a large language model (LLM) by exposing it to up-to-date, relevant information. When queried, RAG retrieves relevant data from its knowledge base and uses it in conjunction with the query to generate accurate and informed responses. This approach minimizes hallucinations (the creation of false information) while also enabling the model to access current information not present in its original training data. For more information, see the [ROCm-RAG documentation](https://rocm.docs.amd.com/projects/rocm-rag/en/latest/index.html).
+
+### gsplat support enabled for ROCm
+
+[Gaussian splatting (gsplat)](https://rocm.docs.amd.com/projects/gsplat/en/latest/index.html) is an open-source library for GPU-accelerated differentiable rasterization of 3D Gaussians with Python bindings. This ROCm-enabled release of gsplat is built on top of [PyTorch for ROCm](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.3/install/3rd-party/pytorch-install.html), enabling innovators in computer graphics, machine learning, and 3D vision to leverage GPU acceleration with AMD Instinct GPUs. With gsplat, you can build, research, and innovate with Gaussian splatting. To install gsplat on ROCm, see [installation instructions](https://rocm.docs.amd.com/projects/gsplat/en/latest/install/gsplat-install.html).
+
+### Introducing ROCm Life Science (ROCm-LS) toolkit
+
+The ROCm Life Science (ROCm-LS) toolkit is an open-source software collection for high-performance life science and healthcare applications built on the core ROCm platform. It helps you accelerate life science processing and analyze workloads on AMD GPUs. ROCm-LS is in an early access state. Running production workloads is not recommended. For more information, see the [AMD ROCm-LS documentation](https://rocm.docs.amd.com/projects/rocm-ls/en/latest/).
+
+ROCm-LS provides the following tools to build a complete workflow for life science acceleration on AMD GPUs:
+
+* The hipCIM library provides powerful support for GPU-accelerated I/O operations, coupled with an array of computer vision and image processing primitives designed for N-dimensional image data in fields such as biomedical imaging. For more information, see the [hipCIM documentation](https://rocm.docs.amd.com/projects/hipCIM/en/latest/).
+
+* MONAI for AMD ROCm, a ROCm-enabled version of [MONAI](https://monai.io/), is built on top of [PyTorch for AMD ROCm](https://pytorch.org/blog/pytorch-for-amd-rocm-platform-now-available-as-python-package/), helping healthcare and life science innovators to leverage GPU acceleration with AMD Instinct GPUs for high-performance inference and training of medical AI applications. For more information, see the [MONAI for AMD ROCm documentation](https://rocm.docs.amd.com/projects/monai/en/latest/).
+
+### Deep learning and AI framework updates
+
+ROCm provides a comprehensive ecosystem for deep learning development. For more information, see [Deep learning frameworks for ROCm](https://rocm.docs.amd.com/en/docs-7.0.2/how-to/deep-learning-rocm.html) and the [Compatibility
+matrix](../../docs/compatibility/compatibility-matrix.rst) for the complete list of Deep learning and AI framework versions tested for compatibility with ROCm.
+
+#### Updated framework support
+
+ROCm 7.0.0 introduces several newly supported versions of Deep learning and AI frameworks:
+
+##### PyTorch
+
+ROCm 7.0.2 enables support for PyTorch 2.8.
+
+#### New frameworks
+
+AMD ROCm has officially added support for the following Deep learning and AI frameworks:
+
+* FlashInfer is a library and kernel generator for Large Language Models (LLMs) that provides a high-performance implementation of graphics processing units (GPUs) kernels. FlashInfer focuses on LLM serving and inference, as well as advanced performance across diverse scenarios. It is supported on ROCm 6.4.1. For more information, see [FlashInfer compatibility](https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/flashinfer-compatibility.html).
+
+* llama.cpp is an open-source framework for Large Language Model (LLM) inference that runs on both central processing units (CPUs) and graphics processing units (GPUs). It is written in plain C/C++, providing a simple, dependency-free setup. It is now supported on ROCm 7.0.0 and 6.4.x. For more information, see [llama.cpp compatibility](https://rocm.docs.amd.com/en/docs-7.0.0/compatibility/ml-compatibility/llama-cpp-compatibility.html).
+
+### ROCm Offline Installer Creator updates
+
+The ROCm Offline Installer Creator 7.0.2 includes the following features and improvements:
+
+* Added support for RHEL 10.0, Oracle Linux 10, and Debian 13.
+* Added support for creating an offline installer for Debian 12 when the kernel version of the target operating system differs from the operating system of the host creating the installer.
+* Removed the restriction requiring the kernels for the host and target systems to match when creating a ROCm-only (no AMD GPU Driver) offline installer.
+
+See [ROCm Offline Installer Creator](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.0.2/install/rocm-offline-installer.html) for more information.
+
+### ROCm Runfile Installer updates
+
+The ROCm Runfile Installer 7.0.2 adds the following features and improvements:
+
+* Added support for RHEL 10.0, Oracle Linux 10, and Debian 13.
+* Minor fixes for the `untar` mode.
+For more information, see [ROCm Runfile Installer](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.0.2/install/rocm-runfile-installer.html).
+
+### ROCm documentation updates
+
+ROCm documentation continues to be updated to provide clearer and more comprehensive guidance for a wider variety of user needs and use cases.
+
+* [Tutorials for AI developers](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/) have been expanded with the following two new inference tutorials:
+    * [Accelerating DeepSeek-V3 inference using multi-token prediction in SGLang](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/notebooks/inference/mtp.html)
+    * [Multi-agents with Google ADK and A2A protocol](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/notebooks/inference/power-Google-ADK-on-AMD-platform-and-local-LLMs.html)
+
+    For more information about the changes, see the [Changelog for the AI Developer Hub](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/changelog.html).
+
+* ROCm components support a wide range of environment variables that can be used for testing, logging, debugging, experimental features, and more. The [rocBLAS](https://rocm.docs.amd.com/projects/rocBLAS/en/docs-7.0.2/reference/env-variables.html) and [RCCL](https://rocm.docs.amd.com/projects/rccl/en/docs-7.0.2/api-reference/env-variables.html) components have been updated with new environment variable content. 
+
+## ROCm components
+
+The following table lists the versions of ROCm components for ROCm 7.0.2, including any version
+changes from 7.0.1 to 7.0.2. Click the component's updated version to go to a list of its changes.
+
+Click {fab}`github` to go to the component's source code on GitHub.
+
+<div class="pst-scrollable-table-container">
+    <table id="rocm-rn-components" class="table">
+        <thead>
+            <tr>
+                <th>Category</th>
+                <th>Group</th>
+                <th>Name</th>
+                <th>Version</th>
+                <th></th>
+            </tr>
+        </thead>
+        <colgroup>
+            <col span="1">
+            <col span="1">
+        </colgroup>
+        <tbody class="rocm-components-libs rocm-components-ml">
+            <tr>
+                <th rowspan="9">Libraries</th>
+                <th rowspan="9">Machine learning and computer vision</th>
+                <td><a href="https://rocm.docs.amd.com/projects/composable_kernel/en/docs-7.0.2/index.html">Composable Kernel</a></td>
+                <td>1.1.0</td>
+                <td><a href="https://github.com/ROCm/composable_kernel"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/AMDMIGraphX/en/docs-7.0.2/index.html">MIGraphX</a></td>
+                <td>2.13.0</td>
+                <td><a href="https://github.com/ROCm/AMDMIGraphX"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/MIOpen/en/docs-7.0.2/index.html">MIOpen</a></td>
+                <td>3.5.0</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/miopen"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/MIVisionX/en/docs-7.0.2/index.html">MIVisionX</a></td>
+                <td>3.3.0</td>
+                <td><a href="https://github.com/ROCm/MIVisionX"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocAL/en/docs-7.0.2/index.html">rocAL</a></td>
+                <td>2.3.0</td>
+                <td><a href="https://github.com/ROCm/rocAL"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocDecode/en/docs-7.0.2/index.html">rocDecode</a></td>
+                <td>1.0.0</td>
+                <td><a href="https://github.com/ROCm/rocDecode"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocJPEG/en/docs-7.0.2/index.html">rocJPEG</a></td>
+                <td>1.1.0</td>
+                <td><a href="https://github.com/ROCm/rocJPEG"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocPyDecode/en/docs-7.0.2/index.html">rocPyDecode</a></td>
+                <td>0.6.0</td>
+                <td><a href="https://github.com/ROCm/rocPyDecode"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rpp/en/docs-7.0.2/index.html">RPP</a></td>
+                <td>2.0.0</td>
+                <td><a href="https://github.com/ROCm/rpp"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-libs rocm-components-communication tbody-reverse-zebra">
+            <tr>
+                <th rowspan="2"></th>
+                <th rowspan="2">Communication</th>
+                <td><a href="https://rocm.docs.amd.com/projects/rccl/en/docs-7.0.2/index.html">RCCL</a></td>
+                <td>2.26.6&nbsp;&Rightarrow;&nbsp;<a href="#rccl-2-26-6">2.26.6</a></td>
+                <td><a href="https://github.com/ROCm/rccl"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+            <td><a href="https://rocm.docs.amd.com/projects/rocSHMEM/en/docs-7.0.2/index.html">rocSHMEM</a></td>
+                <td>3.0.0</td>
+                <td><a href="https://github.com/ROCm/rocSHMEM"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-libs rocm-components-math tbody-reverse-zebra">
+            <tr>
+                <th rowspan="16"></th>
+                <th rowspan="16">Math</th>
+                <td><a href="https://rocm.docs.amd.com/projects/hipBLAS/en/docs-7.0.2/index.html">hipBLAS</a></td>
+                <td>3.0.0&nbsp;&Rightarrow;&nbsp;<a href="#hipblas-3-0-2">3.0.2</a></td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipblas"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipBLASLt/en/docs-7.0.2/index.html">hipBLASLt</a></td>
+                <td>1.0.0</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipblaslt"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipFFT/en/docs-7.0.2/index.html">hipFFT</a></td>
+                <td>1.0.20</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipfft"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipfort/en/docs-7.0.2/index.html">hipfort</a></td>
+                <td>0.7.0</td>
+                <td><a href="https://github.com/ROCm/hipfort"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipRAND/en/docs-7.0.2/index.html">hipRAND</a></td>
+                <td>3.0.0</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/hiprand"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipSOLVER/en/docs-7.0.2/index.html">hipSOLVER</a></td>
+                <td>3.0.0</td>
+                <td><a href="https://github.com/ROCm/hipSOLVER"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipSPARSE/en/docs-7.0.2/index.html">hipSPARSE</a></td>
+                <td>4.0.1</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipsparse"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipSPARSELt/en/docs-7.0.2/index.html">hipSPARSELt</a></td>
+                <td>0.2.4</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipsparselt"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocALUTION/en/docs-7.0.2/index.html">rocALUTION</a></td>
+                <td>4.0.0</td>
+                <td><a href="https://github.com/ROCm/rocALUTION"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocBLAS/en/docs-7.0.2/index.html">rocBLAS</a></td>
+                <td>5.0.0&nbsp;&Rightarrow;&nbsp;<a href="#rocblas-5-0-2">5.0.2</a></td></td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocblas"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocFFT/en/docs-7.0.2/index.html">rocFFT</a></td>
+                <td>1.0.34</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocfft"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocRAND/en/docs-7.0.2/index.html">rocRAND</a></td>
+                <td>4.0.0</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocrand"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocSOLVER/en/docs-7.0.2/index.html">rocSOLVER</a></td>
+                <td>3.30.0&nbsp;&Rightarrow;&nbsp;<a href="#rocsolver-3-30-1">3.30.1</a></td>
+                <td><a href="https://github.com/ROCm/rocSOLVER"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocSPARSE/en/docs-7.0.2/index.html">rocSPARSE</a></td>
+                <td>4.0.2&nbsp;&Rightarrow;&nbsp;<a href="#rocsparse-4-0-3">4.0.3</a></td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocsparse"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocWMMA/en/docs-7.0.2/index.html">rocWMMA</a></td>
+                <td>2.0.0</td>
+                <td><a href="https://github.com/ROCm/rocWMMA"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/Tensile/en/docs-7.0.2/src/index.html">Tensile</a></td>
+                <td>4.44.0</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/shared/tensile"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-libs rocm-components-primitives tbody-reverse-zebra">
+            <tr>
+                <th rowspan="4"></th>
+                <th rowspan="4">Primitives</th>
+                <td><a href="https://rocm.docs.amd.com/projects/hipCUB/en/docs-7.0.2/index.html">hipCUB</a></td>
+                <td>4.0.0</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipcub"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/hipTensor/en/docs-7.0.2/index.html">hipTensor</a></td>
+                <td>2.0.0</td>
+                <td><a href="https://github.com/ROCm/hipTensor"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocPRIM/en/docs-7.0.2/index.html">rocPRIM</a></td>
+                <td>4.0.0&nbsp;&Rightarrow;&nbsp;<a href="#rocprim-4-0-1">4.0.1</a></td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocprim"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocThrust/en/docs-7.0.2/index.html">rocThrust</a></td>
+                <td>4.0.0</td>
+                <td><a href="https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocthrust"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-tools rocm-components-system tbody-reverse-zebra">
+            <tr>
+                <th rowspan="7">Tools</th>
+                <th rowspan="7">System management</th>
+                <td><a href="https://rocm.docs.amd.com/projects/amdsmi/en/docs-7.0.2/index.html">AMD SMI</a></td>
+                <td>26.0.0&nbsp;&Rightarrow;&nbsp;<a href="#amd-smi-26-0-2">26.0.2</a></td>
+                <td><a href="https://github.com/ROCm/amdsmi"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rdc/en/docs-7.0.2/index.html">ROCm Data Center Tool</a></td>
+                <td>1.1.0</td>
+                <td><a href="https://github.com/ROCm/rdc"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocminfo/en/docs-7.0.2/index.html">rocminfo</a></td>
+                <td>1.0.0</td>
+                <td><a href="https://github.com/ROCm/rocminfo"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocm_smi_lib/en/docs-7.0.2/index.html">ROCm SMI</a></td>
+                <td>7.8.0</td>
+                <td><a href="https://github.com/ROCm/rocm_smi_lib"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCmValidationSuite/en/docs-7.0.2/index.html">ROCm Validation Suite</a></td>
+                <td>1.2.0</td>
+                <td><a href="https://github.com/ROCm/ROCmValidationSuite"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-tools rocm-components-perf">
+            <tr>
+                <th rowspan="6"></th>
+                <th rowspan="6">Performance</th>
+                <td><a href="https://rocm.docs.amd.com/projects/rocm_bandwidth_test/en/docs-7.0.2/index.html">ROCm Bandwidth
+                        Test</a></td>
+                <td>2.6.0</td>
+                <td><a href="https://github.com/ROCm/rocm_bandwidth_test/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-compute/en/docs-7.0.2/index.html">ROCm Compute Profiler</a></td>
+                <td>3.2.3</td>
+                <td><a href="https://github.com/ROCm/rocprofiler-compute"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-systems/en/docs-7.0.2/index.html">ROCm Systems Profiler</a></td>
+                <td>1.1.0&nbsp;&Rightarrow;&nbsp;<a href="#rocm-systems-profiler-1-1-1">1.1.1</a></td>
+                <td><a href="https://github.com/ROCm/rocprofiler-systems"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler/en/docs-7.0.2/index.html">ROCProfiler</a></td>
+                <td>2.0.0</td>
+                <td><a href="https://github.com/ROCm/ROCProfiler/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/docs-7.0.2/index.html">ROCprofiler-SDK</a></td>
+                <td>1.0.0</td>
+                <td><a href="https://github.com/ROCm/rocprofiler-sdk/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr >
+                <td><a href="https://rocm.docs.amd.com/projects/roctracer/en/docs-7.0.2/index.html">ROCTracer</a></td>
+                <td>4.1.0</td>
+                <td><a href="https://github.com/ROCm/ROCTracer/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-tools rocm-components-dev">
+            <tr>
+                <th rowspan="5"></th>
+                <th rowspan="5">Development</th>
+                <td><a href="https://rocm.docs.amd.com/projects/HIPIFY/en/docs-7.0.2/index.html">HIPIFY</a></td>
+                <td>20.0.0</td>
+                <td><a href="https://github.com/ROCm/HIPIFY/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCdbgapi/en/docs-7.0.2/index.html">ROCdbgapi</a></td>
+                <td>0.77.3&nbsp;&Rightarrow;&nbsp;<a href="#rocdbgapi-0-77-4">0.77.4</a></td>
+                <td><a href="https://github.com/ROCm/ROCdbgapi/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCmCMakeBuildTools/en/docs-7.0.2/index.html">ROCm CMake</a></td>
+                <td>0.14.0</td>
+                <td><a href="https://github.com/ROCm/rocm-cmake/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCgdb/en/docs-7.0.2/index.html">ROCm Debugger (ROCgdb)</a>
+                </td>
+                <td>16.3</td>
+                <td><a href="https://github.com/ROCm/ROCgdb/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/rocr_debug_agent/en/docs-7.0.2/index.html">ROCr Debug Agent</a>
+                </td>
+                <td>2.1.0</td>
+                <td><a href="https://github.com/ROCm/rocr_debug_agent/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-compilers tbody-reverse-zebra">
+            <tr>
+                <th rowspan="2" colspan="2">Compilers</th>
+                <td><a href="https://rocm.docs.amd.com/projects/HIPCC/en/docs-7.0.2/index.html">HIPCC</a></td>
+                <td>1.1.1</td>
+                <td><a href="https://github.com/ROCm/llvm-project/tree/amd-staging/amd/hipcc"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/llvm-project/en/docs-7.0.2/index.html">llvm-project</a></td>
+                <td>20.0.0</td>
+                <td><a href="https://github.com/ROCm/llvm-project/"><i
+                            class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+        <tbody class="rocm-components-runtimes tbody-reverse-zebra">
+            <tr>
+                <th rowspan="2" colspan="2">Runtimes</th>
+                <td><a href="https://rocm.docs.amd.com/projects/HIP/en/docs-7.0.2/index.html">HIP</a></td>
+                <td>7.0.0&nbsp;&Rightarrow;&nbsp;<a href="#hip-7-0-2">7.0.2</a></td>
+                <td><a href="https://github.com/ROCm/HIP/"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+            <tr>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCR-Runtime/en/docs-7.0.2/index.html">ROCr Runtime</a></td>
+                <td>1.18.0</td>
+                <td><a href="https://github.com/ROCm/ROCR-Runtime/"><i class="fab fa-github fa-lg"></i></a></td>
+            </tr>
+        </tbody>
+    </table>
+</div>
+
+## Detailed component changes
+
+The following sections describe key changes to ROCm components.
+
+```{note}
+For a historical overview of ROCm component updates, see the {doc}`ROCm consolidated changelog </release/changelog>`.
+```
+
+### **AMD SMI** (26.0.1)
+
+#### Added
+
+* Added `bad_page_threshold_exceeded` field to `amd-smi static --ras`, which compares retired pages count against bad page threshold. This field displays `True` if retired pages exceed the threshold, `False` if within threshold, or `N/A` if threshold data is unavailable. Note that `sudo` is required to have the `bad_page_threshold_exceeded` field populated.
+
+#### Removed
+
+* Removed gpuboard and baseboard temperatures enums in amdsmi Python Library.
+    * `AmdSmiTemperatureType` had issues with referencing the correct attribute. As such, the following duplicate enums have been removed:
+        - `AmdSmiTemperatureType.GPUBOARD_NODE_FIRST`
+        - `AmdSmiTemperatureType.GPUBOARD_VR_FIRST`
+        - `AmdSmiTemperatureType.BASEBOARD_FIRST`
+
+#### Resolved Issues
+
+* Fixed `attribute error` in `amd-smi monitor` on Linux Guest systems, where the violations argument caused CLI to break.
+* Fixed certain output in `amd-smi monitor` when GPUs are partitioned.  
+  * It fixes the amd-smi monitor such as: `amd-smi monitor -Vqt`, `amd-smi monitor -g 0 -Vqt -w 1`, `amd-smi monitor -Vqt --file /tmp/test1`, etc. These commands will now be able to display as normal in partitioned GPU scenarios.
+
+* Fixed an issue where using `amd-smi ras --folder <folder_name>` was forcing the created folder's name to be lowercase. This fix also allows all string input options to be case insensitive.
+
+* Fixed an issue of some processes not being detected by AMD SMI despite making use of KFD resources. This fix, with the addition of KFD Fallback for process detection, ensures that all KFD processes will be detected.
+
+* Multiple CPER issues were fixed.  
+  - Issue of being unable to query for additional CPERs after 20 were generated on a single device.
+  - Issue where the RAS HBM CRC read was failing due to an incorrect AFID value.
+  - Issue where RAS injections were not consistently producing related CPERs.
+
+### **HIP** (7.0.2)
+
+#### Added
+
+* Support for the `hipMemAllocationTypeUncached` flag, enabling developers to allocate uncached memory. This flag is now supported in the following APIs:
+    - `hipMemGetAllocationGranularity` determines the recommended allocation granularity for uncached memory.
+    - `hipMemCreate` allocates memory with uncached properties.
+
+#### Resolved issues
+
+* A compilation failure affecting applications that compile kernels using `hiprtc` with the compiler option `std=c++11`.
+* A permission-related error occurred during the execution of `hipLaunchHostFunc`. This API is now supported and permitted to run during stream capture, aligning its behavior with CUDA.
+* A numerical error during graph capture of kernels that rely on a remainder in `globalWorkSize`, in frameworks like MIOpen and PyTorch, where the grid size is not a multiple of the block size. To ensure correct replay behavior, HIP runtime now stores this remainder in `hip::GraphKernelNode` during `hipExtModuleLaunchKernel` capture, enabling accurate execution and preventing corruption.
+* A page fault occurred during viewport rendering while running the file undo.blend in Blender. The issue was resolved by the HIP runtime, which reused the same context during image creation.
+* Resolved a segmentation fault in `gpu_metrics`, which is used in threshold logic for command submission patches to GPU device(s) during CPU synchronization.
+
+### **hipBLAS** (3.0.2)
+ 
+#### Added
+ 
+* Enabled support for gfx1150, gfx1151, gfx1200, and gfx1201 AMD hardware.
+
+### **RCCL** (2.26.6)
+
+#### Added
+
+* Enabled double-buffering in `reduceCopyPacks` to trigger pipelining, especially to overlap bf16 arithmetic.
+* Added `--force-reduce-pipeline` as an option that can be passed to the `install.sh` script. Passing this option will enable software-triggered pipelining `bfloat16` reductions (that is, `all_reduce`, `reduce_scatter`, and `reduce`).
+
+### **rocBLAS** (5.0.2)
+ 
+#### Added
+ 
+* Enabled gfx1150 and gfx1151.
+* The `ROCBLAS_USE_HIPBLASLT_BATCHED` variable to independently control the batched hipblaslt backend. Set `ROCBLAS_USE_HIPBLASLT_BATCHED=0` to disable batched GEMM use of the hipblaslt backend.
+
+#### Resolved issues
+ 
+* Set the imaginary portion of the main diagonal of the output matrix to zero in syrk and herk.
+
+### **ROCdbgapi** (0.77.4)
+
+#### Added
+
+* ROCdbgapi documentation link in the README.md file.
+
+### **ROCm Systems Profiler** (1.1.1)
+
+#### Resolved issues
+
+* Fixed an issue where ROC-TX ranges were displayed as two separate events instead of a single spanning event.
+
+### **rocPRIM** (4.0.1)
+
+#### Resolved issues
+
+* Fixed compilation issue when using `rocprim::texture_cache_iterator`.
+* Fixed a HIP version check used to determine whether `hipStreamLegacy` is supported. This resolves runtime errors that occur when `hipStreamLegacy` is used in ROCm 7.0.0 and later.
+
+### **rocSPARSE** (4.0.3)
+
+#### Resolved issues
+
+* Fixed an issue causing premature deallocation of internal buffers while still in use.
+
+### **rocSOLVER** (3.30.1)
+
+#### Optimized
+
+Improved the performance of:
+
+* LARFT and downstream functions such as GEQRF and ORMTR.
+* LARF and downstream functions such as GEQR2.
+* ORMTR and downstream functions such as SYEVD.
+* GEQR2 and downstream functions such as GEQRF.
+
+## ROCm known issues
+
+ROCm known issues are noted on {fab}`github` [GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). For known
+issues related to individual components, review the [Detailed component changes](#detailed-component-changes).
+
+### ROCm debugging tools might become unresponsive in SELinux-enabled distributions
+
+Red Hat Enterprise Linux (RHEL) and related distributions automatically enable a security feature named Security-Enhanced Linux (SELinux), which may prevent ROCm debugging tools, such as ROCgdb, ROCdbgapi, and ROCR Debug Agent, from working correctly.
+ 
+The problem occurs when attempting to debug a program that contains code that runs on the GPU. The debugging session might become unresponsive while attempting to reach a breakpoint or executing instruction-stepping in device code. ROCgdb will still be responsive and accept interruptions by pressing `Control+C`, but the breakpoint in device code won't be hit, and the instruction-stepping operation will not be completed.
+ 
+The ROCR Debug Agent might also become unresponsive when attempting to capture data from a program that is experiencing queue errors, memory faults, or other triggering events.
+ 
+For a detailed workaround, see the [Installation troubleshooting](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/install-faq.html#issue-10-rocm-debugging-tools-might-become-unresponsive-in-selinux-enabled-distributions) documentation. This issue will be fixed in a future ROCm release. See [GitHub issue #5498](https://github.com/ROCm/ROCm/issues/5498).
+
+### MIGraphX Python API will fail when running on Python 3.13
+
+Applications using the MIGraphX Python API will fail when running on Python 3.13 and return the error message `AttributeError: module 'migraphx' has no attribute 'parse_onnx'`. The issue does not occur when you manually build MIGraphX. For detailed instructions, see [Building from source](https://rocm.docs.amd.com/projects/AMDMIGraphX/en/latest/install/building_migraphx.html). As a workaround, change the Python version to the one found in the installed location:
+
+```
+ls -l /opt/rocm-7.0.0/lib/libmigraphx_py_*.so
+```
+The issue will be resolved in a future ROCm release. See [GitHub issue #5500](https://github.com/ROCm/ROCm/issues/5500).
+
+### Applications using OpenCV might fail due to package incompatibility between the OS
+
+OpenCV packages built on Ubuntu 24.04 are incompatible with Debian 13 due to a version conflict. As a result, applications, tests, and samples that use OpenCV might fail. To avoid the version conflict, rebuild OpenCV with the version corresponding to Debian 13, then rebuild MIVisionX on top of it. As a workaround, rebuild OpenCV from source, followed by the application that uses OpenCV. This issue will be fixed in a future ROCm release. See [GitHub issue #5501](https://github.com/ROCm/ROCm/issues/5501).
+
+## ROCm upcoming changes
+
+The following changes to the ROCm software stack are anticipated for future releases.
+
+### ROCm Execution Provider (ROCm-EP) deprecation
+
+ROCm 7.0.2 is the last official AMD-supported distribution of ROCm Execution Provider (ROCm-EP). ROCm EP will be removed from all upcoming ROCm releases. Refer to this [Pull Request](https://github.com/microsoft/onnxruntime/pull/25181) for more information. Migrate your applications to use the [MIGraphX Execution Provider](https://onnxruntime.ai/docs/execution-providers/MIGraphX-ExecutionProvider.html#migraphx-execution-provider).
+
+### ROCm SMI deprecation
+
+[ROCm SMI](https://github.com/ROCm/rocm_smi_lib) will be phased out in an
+upcoming ROCm release and will enter maintenance mode. After this transition,
+only critical bug fixes will be addressed and no further feature development
+will take place.
+ 
+It's strongly recommended to transition your projects to [AMD
+SMI](https://github.com/ROCm/amdsmi), the successor to ROCm SMI. AMD SMI
+includes all the features of the ROCm SMI and will continue to receive regular
+updates, new functionality, and ongoing support. For more information on AMD
+SMI, see the [AMD SMI documentation](https://rocm.docs.amd.com/projects/amdsmi/en/latest/).
+
+### ROCTracer, ROCProfiler, rocprof, and rocprofv2 deprecation
+
+Development and support for ROCTracer, ROCProfiler, `rocprof`, and `rocprofv2` are being phased out in favor of ROCprofiler-SDK in upcoming ROCm releases. Starting with ROCm 6.4, only critical defect fixes will be addressed for older versions of the profiling tools and libraries. All users are encouraged to upgrade to the latest version of the ROCprofiler-SDK library and the (`rocprofv3`) tool to ensure continued support and access to new features. ROCprofiler-SDK is still in beta today and will be production-ready in a future ROCm release.
+ 
+It's anticipated that ROCTracer, ROCProfiler, `rocprof`, and `rocprofv2` will reach end-of-life by future releases, aligning with Q1 of 2026.
+
+### AMDGPU wavefront size compiler macro deprecation
+
+Access to the wavefront size as a compile-time constant via the `__AMDGCN_WAVEFRONT_SIZE`
+and `__AMDGCN_WAVEFRONT_SIZE__` macros are deprecated and will be disabled in a future release. In ROCm 7.0.0 `warpSize` is only available as a non-`constexpr` variable. You're encouraged to update your code if needed to ensure future compatibility.
+
+* The `__AMDGCN_WAVEFRONT_SIZE__` macro and `__AMDGCN_WAVEFRONT_SIZE` alias will be removed in an upcoming release.
+  It is recommended to remove any use of this macro. For more information, see
+  [AMDGPU support](https://rocm.docs.amd.com/projects/llvm-project/en/docs-7.0.2/LLVM/clang/html/AMDGPUSupport.html).
+* `warpSize` is only available as a non-`constexpr` variable. Where required,
+  the wavefront size should be queried via the `warpSize` variable in device code,
+  or via `hipGetDeviceProperties` in host code. Neither of these will result in a compile-time constant. For more information, see [warpSize](https://rocm.docs.amd.com/projects/HIP/en/docs-7.0.2/how-to/hip_cpp_language_extensions.html#warpsize).
+* For cases where compile-time evaluation of the wavefront size cannot be avoided,
+  uses of `__AMDGCN_WAVEFRONT_SIZE`, `__AMDGCN_WAVEFRONT_SIZE__`, or `warpSize`
+  can be replaced with a user-defined macro or `constexpr` variable with the wavefront
+  size(s) for the target hardware. For example: 
+
+```
+   #if defined(__GFX9__)
+   #define MY_MACRO_FOR_WAVEFRONT_SIZE 64
+   #else
+   #define MY_MACRO_FOR_WAVEFRONT_SIZE 32
+   #endif
+```
+
+### Changes to ROCm Object Tooling
+
+ROCm Object Tooling tools ``roc-obj-ls``, ``roc-obj-extract``, and ``roc-obj`` were
+deprecated in ROCm 6.4, and will be removed in a future release. Functionality
+has been added to the ``llvm-objdump --offloading`` tool option to extract all
+clang-offload-bundles into individual code objects found within the objects
+or executables passed as input.  The ``llvm-objdump --offloading`` tool option also
+supports the ``--arch-name`` option, and only extracts code objects found with
+the specified target architecture. See [llvm-objdump](https://llvm.org/docs/CommandGuide/llvm-objdump.html)
+for more information. 

default.xml

@@ -1,7 +1,7 @@
 <?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-7.0.2"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />
@@ -9,6 +9,7 @@
     <project name="ROCK-Kernel-Driver" />
     <project name="ROCR-Runtime" />
     <project name="amdsmi" />
+    <project name="aqlprofile" />
     <project name="rdc" />
     <project name="rocm_bandwidth_test" />
     <project name="rocm_smi_lib" />
@@ -22,7 +23,7 @@
     <project name="rocprofiler-systems" />
     <project name="roctracer" />
 <!--HIP Projects-->
-    <project name="HIP" />
+    <project name="hip" />
     <project name="hip-tests" />
     <project name="HIPIFY" />
     <project name="clr" />
@@ -37,36 +38,24 @@
     <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" />
     <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``).

docs/benchmark-docker/training-mlperf-fine-tuning-llama-2-70b.rst

@@ -1,151 +0,0 @@
-**************************************************
-Benchmark Llama 2 70B LoRA fine-tuning with MLPerf
-**************************************************
-
-This guide provides instructions to benchmark LoRA fine-tuning on the Llama 2
-70B model. The benchmark follows the MLPerf training submission for
-long-document summarization using the GovReport dataset.
-
-The provided Docker image integrates the `ROCm 7.0 <https://rocm.docs.amd.com/en/latest/>`__
-software stack and is optimized for AMD Instinct MI355X, MI350X, MI325X, and MI300X
-GPUs.
-
-Pull the Docker image
-=====================
-
-1. 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_ubuntu22.04_llama2_70B_training_ml_perf_instinct_20250915
-
-2. Copy the benchmark scripts from the container to your host. These scripts
-   are used to configure the environment and launch the benchmark.
-
-   .. code-block:: shell
-
-      container_id=$(docker create rocm/7.0:rocm7.0_ubuntu22.04_llama2_70B_training_ml_perf_instinct_20250915) && \
-      docker cp $container_id:/workspace/code/runtime_tunables.sh . && \
-      docker cp $container_id:/workspace/code/run_with_docker.sh . && \
-      docker cp $container_id:/workspace/code/config_MI355X_1x8x1.sh . && \
-      docker rm $container_id
-
-   .. note::
-
-      The ``config_*.sh`` files contain system-specific hyperparameters used in
-      the :ref:`run step <system-config>`. You will need to copy the one that
-      matches your hardware configuration.
-
-Prepare the GovReport dataset
-=============================
-
-This benchmark uses the Llama 2 70B model with fused QKV and the GovReport dataset.
-GovReport is a dataset for long document summarization that consists of
-reports written by government research agencies. The dataset hosted on the
-MLPerf drive is already tokenized and packed so that each sequence has
-length 8192.
-
-1. Download and preprocess the dataset.
-
-   Start the Docker container by mounting the volume you want to use for
-   downloading the data under ``/data`` within the container. This example uses
-   ``/data/mlperf_llama2`` as the host's download directory:
-
-   .. code-block:: shell
-
-      docker run -it \
-          --net=host \
-          --uts=host \
-          --ipc=host \
-          --device /dev/dri \
-          --device /dev/kfd \
-          --privileged \
-          --security-opt=seccomp=unconfined \
-          --volume=/data/mlperf_llama2:/data \
-          --volume=/data/mlperf_llama2/model:/ckpt \
-          rocm/7.0:rocm7.0_ubuntu22.04_llama2_70B_training_ml_perf_instinct_20250915
-
-2. From within the container, run the preparation script. This will download and
-   preprocess the dataset and model.
-
-   .. code-block:: shell
-
-      bash ./scripts/prepare_data_and_model.sh
-
-3. Verify the preprocessed files. After the script completes, check for the
-   following files in the mounted directories.
-
-   After preprocessing, you should see the following files in the ``/data/model`` directory:
-
-   .. code-block:: shell-session
-
-      <hash>_tokenizer.model  llama2-70b.nemo
-      model_config.yaml       model_weights
-
-   And the following files in ``/data/data``:
-
-   .. code-block:: shell-session
-
-      train.npy  validation.npy
-
-4. Exit the container and return to your host shell.
-
-   .. code-block:: shell
-
-      exit
-
-Run the benchmark
-=================
-
-With the dataset prepared, you can now configure and run the fine-tuning
-benchmark from your host machine.
-
-1. Set the environment variables. These variables point to the directories you used
-   for data, the model, and where the resulting logs should be stored.
-
-   .. code-block:: shell
-
-      export DATADIR=/data/mlperf_llama2
-      export LOGDIR=/data/mlperf_llama2/results
-      export CONT=rocm/7.0:rocm7.0_ubuntu22.04_llama2_70B_training_ml_perf_instinct_20250915
-
-   .. tip::
-
-      Ensure the log directory exists and is writable by the container user.
-
-      .. code-block:: shell
-
-         mkdir -p $LOGDIR
-         sudo chmod -R 777 $LOGDIR
-
-.. _system-config:
-
-2. Source the system-specific configuration file. The ``config_*.sh`` files
-   contain optimized hyperparameters for different hardware configurations.
-
-   .. code-block:: shell
-
-      # Use the appropriate config
-      source config_MI355X_1x8x1.sh
-
-3. To perform a single training run, use the following command.
-
-   .. code-block:: shell
-
-      export NEXP=1
-      bash run_with_docker.sh
-
-   Optionally, to perform 10 consecutive training runs:
-
-   .. code-block:: shell
-
-      export NEXP=10
-      bash run_with_docker.sh
-
-   .. note::
-
-      To optimize performance, the ``run_with_docker.sh`` script automatically
-      executes ``runtime_tunables.sh`` to apply system-level optimizations
-      before starting the training job.
-
-Upon run completion, the logs will be available under ``$LOGDIR``.