Update license

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

@@ -0,0 +1,42 @@
+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

@@ -1,29 +1,10 @@
 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
@@ -112,11 +93,7 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
-    ${{ if parameters.buildDependsOn }}:
-      dependsOn:
-        - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_ubuntu2204_${{ job.target }}
+  - job: AMDMIGraphX_build_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -144,8 +121,6 @@ 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: >-
@@ -171,12 +146,12 @@ jobs:
         gpuTarget: ${{ job.target }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+  - job: AMDMIGraphX_test_${{ job.target }}
+    dependsOn: AMDMIGraphX_build_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
         eq(${{ parameters.aggregatePipeline }}, False)
       )
     variables:
@@ -208,8 +183,6 @@ jobs:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
-        ${{ if parameters.triggerDownstreamJobs }}:
-          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: CMake@1
       displayName: MIGraphXTest CMake Flags
       inputs:
@@ -226,7 +199,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
-        componentName: ${{ parameters.componentName }}
+        componentName: AMDMIGraphX
         testExecutable: make
         testParameters: -j$(nproc) check
         testPublishResults: false

.azuredevops/components/MIOpen.yml

@@ -1,29 +1,10 @@
 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
@@ -93,31 +74,10 @@ 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: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
-    ${{ if parameters.buildDependsOn }}:
-      dependsOn:
-        - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_ubuntu2204_${{ job.target }}
+  - job: MIOpen_build_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -135,7 +95,6 @@ jobs:
     - 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 }}
@@ -145,13 +104,11 @@ 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
       inputs:
         targetType: inline
-        workingDirectory: $(Agent.BuildDirectory)/s
+        workingDirectory: $(Build.SourcesDirectory)
         script: |
           sed -i '/composable_kernel/d' requirements.txt
           mkdir -p $(Agent.BuildDirectory)/miopen-deps
@@ -173,10 +130,8 @@ 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
@@ -188,9 +143,9 @@ jobs:
           - miopen-deps
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
+  - job: MIOpen_test_${{ job.target }}
     timeoutInMinutes: 180
-    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    dependsOn: MIOpen_build_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -214,7 +169,6 @@ 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/miopen-get-ck-build.yml
       parameters:
@@ -224,13 +178,11 @@ 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
       inputs:
         targetType: inline
-        workingDirectory: $(Agent.BuildDirectory)/s
+        workingDirectory: $(Build.SourcesDirectory)
         script: |
           sed -i '/composable_kernel/d' requirements.txt
           mkdir -p $(Agent.BuildDirectory)/miopen-deps
@@ -241,7 +193,7 @@ jobs:
       displayName: 'MIOpen Test CMake Flags'
       inputs:
         cmakeArgs: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/s/bin;$(Agent.BuildDirectory)/miopen-deps
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Build.SourcesDirectory)/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
@@ -251,19 +203,19 @@ 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: ${{ 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"'
+        componentName: MIOpen
+        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "test_rnn_seq_api|GPU_Conv2dTuningAsm_FP32"'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
@@ -272,15 +224,3 @@ 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

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

.azuredevops/components/hipBLAS.yml

@@ -90,24 +90,24 @@ parameters:
         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
+# - 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: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.target }}
     ${{ if parameters.buildDependsOn }}:
       dependsOn:
         - ${{ each build in parameters.buildDependsOn }}:
@@ -168,8 +168,8 @@ jobs:
 
 - ${{ 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 }}
+    - job: ${{ parameters.componentName }}_test_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
       condition:
         and(succeeded(),
           eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -215,18 +215,18 @@ 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/hipFFT.yml

@@ -80,11 +80,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.target }}
     ${{ if parameters.buildDependsOn }}:
       dependsOn:
         - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_ubuntu2204_${{ job.target }}
+          - ${{ build }}_${{ job.target }} # todo: add OS
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -141,12 +141,12 @@ jobs:
     #     gpuTarget: ${{ job.target }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+  - 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'], ','), '${{ parameters.componentName }}')),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
         eq(${{ parameters.aggregatePipeline }}, False)
       )
     variables:

.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

@@ -1,29 +1,10 @@
 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
@@ -85,11 +66,7 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
-    ${{ if parameters.buildDependsOn }}:
-      dependsOn:
-        - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_ubuntu2204_${{ job.target }}
+  - job: hipSOLVER_build_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -104,21 +81,18 @@ 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 }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
-        ${{ if parameters.triggerDownstreamJobs }}:
-          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
   # build external gtest and lapack
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         componentName: external
-        cmakeBuildDir: '$(Agent.BuildDirectory)/s/deps/build'
-        cmakeSourceDir: '$(Agent.BuildDirectory)/s/deps'
+        cmakeBuildDir: '$(Build.SourcesDirectory)/deps/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/deps'
         installDir: '$(Pipeline.Workspace)/deps-install'
         extraBuildFlags: >-
           -DBUILD_BOOST=OFF
@@ -137,10 +111,8 @@ 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
@@ -150,49 +122,44 @@ jobs:
     #     extraCopyDirectories:
     #       - deps-install
 
-- ${{ 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 }}
+- ${{ each job in parameters.jobMatrix.testJobs }}:
+  - job: hipSOLVER_test_${{ 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 }}

.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: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ 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: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
-    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+  - 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'], ','), '${{ parameters.componentName }}')),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
         eq(${{ parameters.aggregatePipeline }}, False)
       )
     variables:
@@ -196,14 +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/rocRAND.yml

@@ -79,12 +79,6 @@ 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

@@ -94,17 +94,17 @@ parameters:
         - 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
+    # - 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 }}:

.azuredevops/components/rocm-libraries.yml

@@ -1,163 +0,0 @@
-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
-    - libmsgpack-dev
-    - libnuma-dev
-    - ninja-build
-    - python3-pip
-    - python3-venv
-- name: pipModules
-  type: object
-  default:
-    - joblib
-    - "packaging>=22.0"
-    - --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-other.yml
-      parameters:
-        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/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 }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-      parameters:
-        os: ${{ job.os }}
-        extraBuildFlags: >-
-          -DROCM_LIBRARIES_SUPERBUILD=ON
-          -GNinja
-    - 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/rocprofiler-compute.yml

@@ -65,19 +65,43 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
+      - gfx942-staging:
+        name: gfx942_staging
         target: gfx942
-      - gfx90a:
+        dependencySource: staging
+      - gfx942-mainline:
+        name: gfx942_mainline
+        target: gfx942
+        dependencySource: mainline
+      - gfx90a-staging:
+        name: gfx90a_staging
         target: gfx90a
+        dependencySource: staging
+      - gfx90a-mainline:
+        name: gfx90a_mainline
+        target: gfx90a
+        dependencySource: mainline
     testJobs:
-      - gfx942:
+      - gfx942-staging:
+        name: gfx942_staging
         target: gfx942
-      - gfx90a:
+        dependencySource: staging
+      - gfx942-mainline:
+        name: gfx942_mainline
+        target: gfx942
+        dependencySource: mainline
+      - gfx90a-staging:
+        name: gfx90a_staging
         target: gfx90a
+        dependencySource: staging
+      - gfx90a-mainline:
+        name: gfx90a_mainline
+        target: gfx90a
+        dependencySource: mainline
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocprofiler_compute_build_${{ job.target }}
+  - job: rocprofiler_compute_build_${{ job.name }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -100,9 +124,11 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        artifactName: ${{ job.dependencySource }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        artifactName: ${{ job.dependencySource }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -112,9 +138,9 @@ jobs:
     #     gpuTarget: ${{ job.target }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocprofiler_compute_test_${{ job.target }}
+  - job: rocprofiler_compute_test_${{ job.name }}
     timeoutInMinutes: 120
-    dependsOn: rocprofiler_compute_build_${{ job.target }}
+    dependsOn: rocprofiler_compute_build_${{ job.name }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -140,12 +166,14 @@ jobs:
         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

.azuredevops/components/rocprofiler-systems.yml

@@ -37,7 +37,6 @@ parameters:
     - libpfm4-dev
     - libtool
     - libopenmpi-dev
-    - libsqlite3-dev
     - m4
     - ninja-build
     - openmpi-bin

.azuredevops/dependencies/boost.yml

@@ -40,6 +40,7 @@ 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/nightly/pytorch.yml

@@ -219,6 +219,7 @@ 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
@@ -405,6 +406,7 @@ jobs:
     parameters:
       dependencyList: ${{ parameters.rocmTestDependencies }}
       gpuTarget: $(JOB_GPU_TARGET)
+      dependencySource: staging
 # 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, 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 }
+    - { os: ubuntu2204, packageManager: apt, target: gfx942, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx90a, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1201, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1100, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1030, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx942, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx90a, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1201, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1100, source: staging }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1030, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx942, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx90a, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx1201, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx1100, source: staging }
+    - { os: almalinux8, packageManager: dnf, target: gfx1030, source: staging }
 - name: rocmDependencies
   type: object
   default:
@@ -92,7 +92,7 @@ schedules:
 
 jobs:
 - ${{ each job in parameters.jobList }}:
-  - job: nightly_${{ job.os }}_${{ job.target }}
+  - job: nightly_${{ job.os }}_${{ job.target }}_${{ job.source }}
     timeoutInMinutes: 90
     variables:
     - group: common
@@ -116,6 +116,7 @@ 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 }}
@@ -171,11 +172,11 @@ jobs:
                 && 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 }}${{ job.target }}&api-version=7.1" \
+              RUN ARTIFACT_URL="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis/build/builds/$(Build.BuildId)/artifacts?artifactName=nightly${{ job.os }}${{ job.target }}${{ job.source }}&api-version=7.1" \
                 && DOWNLOAD_URL=$(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 }}*${{ job.target }}*.tar.gz -C rocm
+                && tar -xf nightly${{ job.os }}${{ job.target }}${{ job.source }}/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
@@ -209,11 +210,11 @@ jobs:
                 && 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 }}${{ job.target }}&api-version=7.1" \
+              RUN ARTIFACT_URL="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis/build/builds/$(Build.BuildId)/artifacts?artifactName=nightly${{ job.os }}${{ job.target }}${{ job.source }}&api-version=7.1" \
                 && DOWNLOAD_URL=$(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 }}*${{ job.target }}*.tar.gz -C rocm
+                && tar -xf nightly${{ job.os }}${{ job.target }}${{ job.source }}/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
@@ -228,11 +229,11 @@ jobs:
       displayName: Build and upload Docker image
       inputs:
         containerRegistry: ContainerService3
-        repository: 'nightly-${{ job.os }}-${{ job.target }}'
+        repository: 'nightly-${{ job.os }}-${{ job.target }}-${{ job.source }}'
         Dockerfile: '$(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:]'
+        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 }}-${{ job.source }}:$(Build.BuildId)" | tr '[:upper:]' '[:lower:]'

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

@@ -3,6 +3,13 @@ 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: []
@@ -31,240 +38,309 @@ parameters:
   type: object
   default:
     AMDMIGraphX:
-      pipelineId: 113
-      developBranch: develop
+      pipelineId: $(AMDMIGRAPHX_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: master
       hasGpuTarget: true
     amdsmi:
-      pipelineId: 99
-      developBranch: amd-staging
+      pipelineId: $(AMDSMI_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     aomp-extras:
-      pipelineId: 111
-      developBranch: aomp-dev
+      pipelineId: $(AOMP_EXTRAS_PIPELINE_ID)
+      stagingBranch: aomp-dev
+      mainlineBranch: aomp-dev
       hasGpuTarget: false
     aomp:
-      pipelineId: 115
-      developBranch: aomp-dev
+      pipelineId: $(AOMP_PIPELINE_ID)
+      stagingBranch: aomp-dev
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     clr:
-      pipelineId: 145
-      developBranch: amd-staging
+      pipelineId: $(CLR_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     composable_kernel:
-      pipelineId: 86
-      developBranch: develop
+      pipelineId: $(COMPOSABLE_KERNEL_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     half:
-      pipelineId: 101
-      developBranch: rocm
+      pipelineId: $(HALF_PIPELINE_ID)
+      stagingBranch: rocm
+      mainlineBranch: rocm
       hasGpuTarget: false
     HIP:
-      pipelineId: 93
-      developBranch: amd-staging
+      pipelineId: $(HIP_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     hip-tests:
-      pipelineId: 233
-      developBranch: amd-staging
+      pipelineId: $(HIP_TESTS_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     hipBLAS:
-      pipelineId: 317
-      developBranch: develop
+      pipelineId: $(HIPBLAS_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     hipBLASLt:
-      pipelineId: 301
-      developBranch: develop
+      pipelineId: $(HIPBLASLT_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     hipBLAS-common:
-      pipelineId: 300
-      developBranch: develop
+      pipelineId: $(HIPBLAS_COMMON_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: false
     hipCUB:
-      pipelineId: 277
-      developBranch: develop
+      pipelineId: $(HIPCUB_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: develop
       hasGpuTarget: true
     hipFFT:
-      pipelineId: 283
-      developBranch: develop
+      pipelineId: $(HIPFFT_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     hipfort:
-      pipelineId: 102
-      developBranch: develop
+      pipelineId: $(HIPFORT_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: false
     HIPIFY:
-      pipelineId: 92
-      developBranch: amd-staging
+      pipelineId: $(HIPIFY_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     hipRAND:
-      pipelineId: 275
-      developBranch: develop
+      pipelineId: $(HIPRAND_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: develop
       hasGpuTarget: true
     hipSOLVER:
-      pipelineId: 84
-      developBranch: develop
+      pipelineId: $(HIPSOLVER_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     hipSPARSE:
-      pipelineId: 315
-      developBranch: develop
+      pipelineId: $(HIPSPARSE_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     hipSPARSELt:
-      pipelineId: 309
-      developBranch: develop
+      pipelineId: $(HIPSPARSELT_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     hipTensor:
-      pipelineId: 105
-      developBranch: develop
+      pipelineId: $(HIPTENSOR_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     llvm-project:
-      pipelineId: 2
-      developBranch: amd-staging
+      pipelineId: $(LLVM_PROJECT_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     MIOpen:
-      pipelineId: 320
-      developBranch: develop
+      pipelineId: $(MIOpen_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: amd-master
       hasGpuTarget: true
     MIVisionX:
-      pipelineId: 80
-      developBranch: develop
+      pipelineId: $(MIVISIONX_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: master
+      hasGpuTarget: true
+    omnitrace: # deprecated
+      pipelineId: $(OMNITRACE_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rccl:
-      pipelineId: 107
-      developBranch: develop
+      pipelineId: $(RCCL_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     rdc:
-      pipelineId: 100
-      developBranch: amd-staging
+      pipelineId: $(RDC_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocAL:
-      pipelineId: 151
-      developBranch: develop
+      pipelineId: $(ROCAL_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     rocALUTION:
-      pipelineId: 89
-      developBranch: develop
+      pipelineId: $(ROCALUTION_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     rocBLAS:
-      pipelineId: 302
-      developBranch: develop
+      pipelineId: $(ROCBLAS_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     ROCdbgapi:
-      pipelineId: 135
-      developBranch: amd-staging
+      pipelineId: $(ROCDBGAPI_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocDecode:
-      pipelineId: 79
-      developBranch: develop
+      pipelineId: $(ROCDECODE_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: false
     rocFFT:
-      pipelineId: 282
-      developBranch: develop
+      pipelineId: $(ROCFFT_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     ROCgdb:
-      pipelineId: 134
-      developBranch: amd-staging
+      pipelineId: $(ROCGDB_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline-rocgdb-15
       hasGpuTarget: false
     rocJPEG:
-      pipelineId: 262
-      developBranch: develop
+      pipelineId: $(ROCJPEG_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: false
     rocm-cmake:
-      pipelineId: 6
-      developBranch: develop
+      pipelineId: $(ROCM_CMAKE_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: false
     rocm-core:
-      pipelineId: 103
-      developBranch: master
+      pipelineId: $(ROCM_CORE_PIPELINE_ID)
+      stagingBranch: master
+      mainlineBranch: amd-master
       hasGpuTarget: false
     rocm-examples:
-      pipelineId: 216
-      developBranch: amd-staging
+      pipelineId: $(ROCM_EXAMPLES_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocminfo:
-      pipelineId: 91
-      developBranch: amd-staging
+      pipelineId: $(ROCMINFO_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocMLIR:
-      pipelineId: 229
-      developBranch: develop
+      pipelineId: $(ROCMLIR_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: false
     ROCmValidationSuite:
-      pipelineId: 106
-      developBranch: master
+      pipelineId: $(ROCMVALIDATIONSUITE_PIPELINE_ID)
+      stagingBranch: master
+      mainlineBranch: master
       hasGpuTarget: true
     rocm_bandwidth_test:
-      pipelineId: 88
-      developBranch: master
+      pipelineId: $(ROCM_BANDWIDTH_TEST_PIPELINE_ID)
+      stagingBranch: master
+      mainlineBranch: master
       hasGpuTarget: false
     rocm_smi_lib:
-      pipelineId: 96
-      developBranch: amd-staging
+      pipelineId: $(ROCM_SMI_LIB_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocPRIM:
-      pipelineId: 273
-      developBranch: develop
+      pipelineId: $(ROCPRIM_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: develop
       hasGpuTarget: true
     rocprofiler:
-      pipelineId: 143
-      developBranch: amd-staging
+      pipelineId: $(ROCPROFILER_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-master
       hasGpuTarget: true
     rocprofiler-compute:
-      pipelineId: 257
-      developBranch: develop
+      pipelineId: $(ROCPROFILER_COMPUTE_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocprofiler-register:
-      pipelineId: 1
-      developBranch: amd-staging
+      pipelineId: $(ROCPROFILER_REGISTER_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocprofiler-sdk:
-      pipelineId: 246
-      developBranch: amd-staging
+      pipelineId: $(ROCPROFILER_SDK_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocprofiler-systems:
-      pipelineId: 255
-      developBranch: amd-staging
+      pipelineId: $(ROCPROFILER_SYSTEMS_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocPyDecode:
-      pipelineId: 239
-      developBranch: develop
+      pipelineId: $(ROCPYDECODE_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     ROCR-Runtime:
-      pipelineId: 10
-      developBranch: amd-staging
+      pipelineId: $(ROCR_RUNTIME_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocRAND:
-      pipelineId: 274
-      developBranch: develop
+      pipelineId: $(ROCRAND_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: develop
       hasGpuTarget: true
     rocr_debug_agent:
-      pipelineId: 136
-      developBranch: amd-staging
+      pipelineId: $(ROCR_DEBUG_AGENT_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocSOLVER:
-      pipelineId: 81
-      developBranch: develop
+      pipelineId: $(ROCSOLVER_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     rocSPARSE:
-      pipelineId: 314
-      developBranch: develop
+      pipelineId: $(ROCSPARSE_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
+    ROCT-Thunk-Interface: # deprecated
+      pipelineId: $(ROCT_THUNK_INTERFACE_PIPELINE_ID)
+      stagingBranch: master
+      mainlineBranch: master
+      hasGpuTarget: false
     rocThrust:
-      pipelineId: 276
-      developBranch: develop
+      pipelineId: $(ROCTHRUST_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: develop
       hasGpuTarget: true
     roctracer:
-      pipelineId: 141
-      developBranch: amd-staging
+      pipelineId: $(ROCTRACER_PIPELINE_ID)
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocWMMA:
-      pipelineId: 109
-      developBranch: develop
+      pipelineId: $(ROCWMMA_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     rpp:
-      pipelineId: 78
-      developBranch: develop
+      pipelineId: $(RPP_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
     TransferBench:
-      pipelineId: 265
-      developBranch: develop
+      pipelineId: $(TRANSFERBENCH_PIPELINE_ID)
+      stagingBranch: develop
+      mainlineBranch: mainline
       hasGpuTarget: true
 
 steps:
@@ -280,30 +356,72 @@ steps:
       parameters:
         componentName: ${{ split(dependency, ':')[0] }}
         pipelineId: ${{ parameters.componentVarList[split(dependency, ':')[0]].pipelineId }}
-        branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].developBranch }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         extractAndDeleteFiles: false
+        ${{ if parameters.componentVarList[split(dependency, ':')[0]].hasGpuTarget }}:
+          fileFilter: "${{ 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 }}
 # no colon (:) found in this item in the list
   - ${{ elseif containsValue(split(parameters.downstreamAggregateNames, '+'), dependency) }}:
     - template: local-artifact-download.yml
       parameters:
-        buildType: current
-        preTargetFilter: ${{ dependency }}
-        os: ${{ parameters.os }}
         ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
           gpuTarget: ${{ parameters.gpuTarget }}
+        preTargetFilter: ${{ dependency }}
+        os: ${{ parameters.os }}
+        buildType: current
   - ${{ 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 }}
 - task: ExtractFiles@1
   displayName: Extract ROCm artifacts
   inputs:

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

@@ -13,7 +13,7 @@ steps:
     CC: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
   inputs:
     targetType: inline
-    workingDirectory: $(Agent.BuildDirectory)/s
+    workingDirectory: $(Build.SourcesDirectory)
     script: |
       AZ_API="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis"
       GH_API="https://api.github.com/repos/ROCm"

.azuredevops/variables-global.yml

@@ -23,6 +23,10 @@ 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
@@ -37,11 +41,127 @@ variables:
   value: rocm-6.4.2
 - 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: 300
+- name: HIPBLAS_PIPELINE_ID
+  value: 317
+- name: HIPBLASLT_PIPELINE_ID
+  value: 301
+- 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: 315
+- name: HIPSPARSELT_PIPELINE_ID
+  value: 309
+- 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: 302
+- 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: 314
+- 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

@@ -45,7 +45,6 @@ Bootloader
 CAS
 CCD
 CDNA
-CGUI
 CHTML
 CIFAR
 CLI
@@ -116,7 +115,6 @@ DevCap
 DirectX
 Dockerfile
 Doxygen
-dropless
 ELMo
 ENDPGM
 EPYC
@@ -178,7 +176,6 @@ HBM
 HCA
 HGX
 HIPCC
-hipDataType
 HIPExtension
 HIPIFY
 HIPification
@@ -273,7 +270,6 @@ Makefiles
 Matplotlib
 Matrox
 MaxText
-Megablocks
 Megatrends
 Megatron
 Mellanox
@@ -283,7 +279,6 @@ Miniconda
 MirroredStrategy
 Mixtral
 MosaicML
-MoEs
 Mpops
 Multicore
 Multithreaded
@@ -458,8 +453,6 @@ TPS
 TPU
 TPUs
 TSME
-Taichi
-Taichi's
 Tagram
 TensileLite
 TensorBoard

README.md

@@ -23,6 +23,9 @@ 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
 

docs/about/license.md

@@ -29,6 +29,7 @@ additional licenses. Please review individual repositories for more information.
 | [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] | [MIT](https://github.com/ROCm/aqlprofile/blob/amd-staging/LICENSE) |
 | [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) |
@@ -46,7 +47,6 @@ additional licenses. Please review individual repositories for more information.
 | [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) |
-| hsa-amd-aqlprofile | [AMD Software EULA](https://www.amd.com/en/legal/eula/amd-software-eula.html) |
 | [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) |
@@ -132,12 +132,10 @@ companies.
 ### Package licensing
 
 :::{attention}
-AQL Profiler and AOCC CPU optimization are both provided in binary form, each
-subject to the license agreement enclosed in the directory for the binary available
-in `/opt/rocm/share/doc/hsa-amd-aqlprofile/EULA`. By using, installing,
-copying or distributing AQL Profiler and/or AOCC CPU Optimizations, you agree to
+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 the AQL Profiler and/or the
+terms of this agreement, do not install, copy or use ROCprof Trace Decoder or the
 AOCC CPU Optimizations.
 :::
 

docs/compatibility/compatibility-matrix-historical-6.0.csv

@@ -30,11 +30,9 @@ ROCm Version,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,
       :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
       :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
       :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A
-      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,N/A,85f95ae,85f95ae,85f95ae,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`,N/A,N/A,N/A,0.7.0,0.7.0,0.7.0,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat]_,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`,2.4.0,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,N/A
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.2,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
 ,,,,,,,,,,,,,,,,,
       ,,,,,,,,,,,,,,,,,

docs/compatibility/compatibility-matrix.rst

@@ -56,7 +56,7 @@ compatibility and system requirements.
       :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1"
       :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.4.35,0.4.35,0.4.31  
       :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,85f95ae
-      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`,N/A,N/A,0.7.0
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`,2.4.0,2.4.0,N/A
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.17.3
       ,,,
       THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
@@ -241,8 +241,6 @@ Expand for full historical view of:
    .. [#mi300_602-past-60] **For ROCm 6.0.2** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
    .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
    .. [#verl_compat] verl is only supported on ROCm 6.2.0.
-   .. [#dgl_compat] DGL is only supported on ROCm 6.4.0.
-   .. [#taichi_compat] Taichi is only supported on ROCm 6.3.2.
    .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
    .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
    

docs/compatibility/ml-compatibility/jax-compatibility.rst

@@ -97,7 +97,7 @@ Docker image compatibility
 AMD validates and publishes ready-made `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax>`_
 with ROCm backends on Docker Hub. The following Docker image tags and
 associated inventories represent the latest JAX version from the official Docker Hub and are validated for
-`ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`_. Click the |docker-icon|
+`ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_. Click the |docker-icon|
 icon to view the image on Docker Hub.
 
 .. list-table:: JAX Docker image components
@@ -110,7 +110,7 @@ icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.2-jax0.4.35-py3.12/images/sha256-8918fa806a172c1a10eb2f57131eb31b5d7c8fa1656b8729fe7d3d736112de83"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.12/images/sha256-7a0745a2a2758bdf86397750bac00e9086cbf67d170cfdbb08af73f7c7d18a6a"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
 
       - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
       - Ubuntu 24.04
@@ -118,7 +118,7 @@ icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.2-jax0.4.35-py3.10/images/sha256-a394be13c67b7fc602216abee51233afd4b6cb7adaa57ca97e688fba82f9ad79"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.10/images/sha256-5f9e8d6e6e69fdc9a1a3f2ba3b1234c3f46c53b7468538c07fd18b00899da54f"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
 
       - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
       - Ubuntu 22.04

docs/compatibility/ml-compatibility/megablocks-compatibility.rst

@@ -1,93 +0,0 @@
-:orphan:
-
-.. meta::
-    :description: Megablocks compatibility
-    :keywords: GPU, megablocks, compatibility
-
-.. version-set:: rocm_version latest
-
-********************************************************************************
-Megablocks compatibility
-********************************************************************************
-
-Megablocks is a light-weight library for mixture-of-experts (MoE) training. 
-The core of the system is efficient "dropless-MoE" and standard MoE layers. 
-Megablocks is integrated with `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`_, 
-where data and pipeline parallel training of MoEs is supported.
-
-* ROCm support for Megablocks is hosted in the official `https://github.com/ROCm/megablocks <https://github.com/ROCm/megablocks>`_ repository. 
-* Due to independent compatibility considerations, this location differs from the `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`_ upstream repository. 
-* Use the prebuilt :ref:`Docker image <megablocks-docker-compat>` with ROCm, PyTorch, and Megablocks preinstalled. 
-* See the :doc:`ROCm Megablocks installation guide <rocm-install-on-linux:install/3rd-party/megablocks-install>` to install and get started.
-
-.. note::
-
-  Megablocks is supported on ROCm 6.3.0.
-
-Supported devices
-================================================================================
-
-- **Officially Supported**: AMD Instinct MI300X
-- **Partially Supported** (functionality or performance limitations): AMD Instinct MI250X, MI210X
-
-Supported models and features
-================================================================================
-
-This section summarizes the Megablocks features supported by ROCm.
-
-* Distributed Pre-training
-* Activation Checkpointing and Recomputation
-* Distributed Optimizer
-* Mixture-of-Experts
-* dropless-Mixture-of-Experts
-
-
-.. _megablocks-recommendations:
-
-Use cases and recommendations
-================================================================================
-
-The `ROCm Megablocks blog posts <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`_ 
-guide how to leverage the ROCm platform for pre-training using the Megablocks framework. 
-It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
-
-* Single-GPU pre-training
-* Multi-GPU pre-training
-
-
-.. _megablocks-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes `ROCm Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`_
-with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
-inventories represent the latest Megatron-LM version from the official Docker Hub.
-The Docker images have been validated for `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_.
-Click |docker-icon| to view the image on Docker Hub.
-
-.. list-table:: 
-    :header-rows: 1
-    :class: docker-image-compatibility
-
-    * - Docker image
-      - ROCm
-      - Megablocks
-      - PyTorch
-      - Ubuntu
-      - Python
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
-      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
-      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
-      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
-      - 24.04
-      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
-
-

docs/compatibility/ml-compatibility/pytorch-compatibility.rst

@@ -95,7 +95,7 @@ Docker image compatibility
 
 AMD validates and publishes `PyTorch images <https://hub.docker.com/r/rocm/pytorch>`__
 with ROCm backends on Docker Hub. The following Docker image tags and associated
-inventories were tested on `ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__.
+inventories were tested on `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__.
 Click |docker-icon| to view the image on Docker Hub.
 
 .. list-table:: PyTorch Docker image components
@@ -112,118 +112,127 @@ Click |docker-icon| to view the image on Docker Hub.
       - MAGMA
       - UCX
       - OMPI
+      - OFED
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-6a287591500b4048a9556c1ecc92bc411fd3d552f6c8233bc399f18eb803e8d6"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-c76af9bfb1c25b0f40d4c29e8652105c57250bf018d23ff595b06bd79666fdd7"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`__
       - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`__
       - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
+      - `1.16.0 <https://github.com/openucx/ucx/tree/v1.16.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-06b967629ba6657709f04169832cd769a11e6b491e8b1394c361d42d7a0c8b43"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-f9d226135d51831c810dcb1251636ec61f85c65fcdda03e188c053a5d4f6585b"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`__
       - 22.04
-      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
       - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`__
       - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
       - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-62022414217ef6de33ac5b1341e57db8a48e8573fa2ace12d48aa5edd4b99ef0"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-3490e74d4f43dcdb3351dd334108d1ccd47e5a687c0523a2424ac1bcdd3dd6dd"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
       - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
       - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.10.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.11_pytorch_release_2.5.1/images/sha256-469a7f74fc149aff31797e011ee41978f6a190adc69fa423b3c6a718a77bd985"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-26c5dfffb4a54625884abca83166940f17dd27bc75f1b24f6e80fbcb7d4e9afb"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
       - 22.04
-      - `3.11 <https://www.python.org/downloads/release/python-31113/>`__
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
       - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
       - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
       - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-37f41a1cd94019688669a1b20d33ea74156e0c129ef6b8270076ef214a6a1a2c"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
-      - 22.04
-      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
-      - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
-      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-60824ba83dc1b9d94164925af1f81c0235c105dd555091ec04c57e05177ead1b"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-f378a24561fa6efc178b6dc93fc7d82e5b93653ecd59c89d4476674d29e1284d"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`__
       - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`__
       - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-fe944fe083312f901be6891ab4d3ffebf2eaf2cf4f5f0f435ef0b76ec714fabd"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-2308dbd0e650b7bf8d548575cbb6e2bdc021f9386384ce570da16d58ee684d22"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`__
       - 22.04
-      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
       - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`__
       - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
       - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-1d59251c47170c5b8960d1172a4dbe52f5793d8966edd778f168eaf32d56661a"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-eefd2ab019728f91f94c5e6a9463cb0ea900b3011458d18fe5d88e50c0b57d86"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`__
       - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`__
       - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`__
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`__
       - `master <https://bitbucket.org/icl/magma/src/master/>`__
       - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
       - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-473643226ab0e93a04720b256ed772619878abf9c42b9f84828cefed522696fd"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`__
+      - 22.04
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`__
+      - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`__
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`__
+      - `master <https://bitbucket.org/icl/magma/src/master/>`__
+      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
+      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
 
 Key ROCm libraries for PyTorch
 ================================================================================

docs/compatibility/ml-compatibility/taichi-compatibility.rst

@@ -1,76 +0,0 @@
-:orphan:
-
-.. meta::
-    :description: Taichi compatibility
-    :keywords: GPU, Taichi compatibility
-
-.. version-set:: rocm_version latest
-
-*******************************************************************************
-Taichi compatibility
-*******************************************************************************
-
-`Taichi <https://www.taichi-lang.org/>`_ is an open-source, imperative, and parallel 
-programming language designed for high-performance numerical computation. 
-Embedded in Python, it leverages just-in-time (JIT) compilation frameworks such as LLVM to accelerate 
-compute-intensive Python code by compiling it to native GPU or CPU instructions.
-
-Taichi is widely used across various domains, including real-time physical simulation, 
-numerical computing, augmented reality, artificial intelligence, computer vision, robotics, 
-visual effects in film and gaming, and general-purpose computing.
-
-* ROCm support for Taichi is hosted in the official `https://github.com/ROCm/taichi <https://github.com/ROCm/taichi>`_ repository.
-* Due to independent compatibility considerations, this location differs from the `https://github.com/taichi-dev <https://github.com/taichi-dev>`_ upstream repository.
-* Use the prebuilt :ref:`Docker image <taichi-docker-compat>` with ROCm, PyTorch, and Taichi preinstalled.
-* See the :doc:`ROCm Taichi installation guide <rocm-install-on-linux:install/3rd-party/taichi-install>` to install and get started.
-
-.. note::
-
-	Taichi is supported on ROCm 6.3.2.
-
-Supported devices and features
-===============================================================================
-There is support through the ROCm software stack for all Taichi GPU features on AMD Instinct MI250X and MI210X series GPUs with the exception of Taichi’s GPU rendering system, CGUI.
-AMD Instinct MI300X series GPUs will be supported by November.
-
-.. _taichi-recommendations:
-
-Use cases and recommendations
-================================================================================
-To fully leverage Taichi's performance capabilities in compute-intensive tasks, it is best to adhere to specific coding patterns and utilize Taichi decorators. 
-A collection of example use cases is available in the `https://github.com/ROCm/taichi_examples <https://github.com/ROCm/taichi_examples>`_ repository, 
-providing practical insights and foundational knowledge for working with the Taichi programming language. 
-You can also refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`_ to search for Taichi examples and best practices to optimize your workflows on AMD GPUs.
-
-.. _taichi-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `ROCm Taichi Docker images <https://hub.docker.com/r/rocm/taichi/tags>`_
-with ROCm backends on Docker Hub. The following Docker image tags and associated inventories 
-represent the latest Taichi version from the official Docker Hub.
-The Docker images have been validated for `ROCm 6.3.2 <https://rocm.docs.amd.com/en/docs-6.3.2/about/release-notes.html>`_. 
-Click |docker-icon| to view the image on Docker Hub.
-
-.. list-table:: 
-    :header-rows: 1
-    :class: docker-image-compatibility
-
-    * - Docker image
-      - ROCm
-      - Taichi
-      - Ubuntu
-      - Python
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/taichi/taichi-1.8.0b1_rocm6.3.2_ubuntu22.04_py3.10.12/images/sha256-e016964a751e6a92199032d23e70fa3a564fff8555afe85cd718f8aa63f11fc6"><i class="fab fa-docker fa-lg"></i> rocm/taichi</a>
-      - `6.3.2 <https://repo.radeon.com/rocm/apt/6.3.2/>`_
-      - `1.8.0b1 <https://github.com/taichi-dev/taichi>`_
-      - 22.04
-      - `3.10.12 <https://www.python.org/downloads/release/python-31012/>`_

docs/compatibility/ml-compatibility/tensorflow-compatibility.rst

@@ -56,7 +56,7 @@ Docker image compatibility
 AMD validates and publishes ready-made `TensorFlow images
 <https://hub.docker.com/r/rocm/tensorflow>`__ with ROCm backends on
 Docker Hub. The following Docker image tags and associated inventories are
-validated for `ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__. Click
+validated for `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__. Click
 the |docker-icon| icon to view the image on Docker Hub.
 
 .. list-table:: TensorFlow Docker image components
@@ -65,61 +65,128 @@ the |docker-icon| icon to view the image on Docker Hub.
     * - Docker image
       - TensorFlow
       - Ubuntu
+      - Dev
       - Python
       - TensorBoard
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.18-dev/images/sha256-96754ce2d30f729e19b497279915b5212ba33d5e408e7e5dd3f2304d87e3441e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.12-tf2.18-dev/images/sha256-fa9cf5fa6c6079a7118727531ccd0056c6e3224a42c3d6e78a49e7781daafff4"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - dev
       - 24.04
-      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.18-dev/images/sha256-fa741508d383858e86985a9efac85174529127408102558ae2e3a4ac894eea1e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.18-runtime/images/sha256-d14d8c4989e7c9a60f4e72461b9e349de72347c6162dcd6897e6f4f80ffbb440"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - 22.04
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - runtime
+      - 24.04
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.17-dev/images/sha256-3a0aef09f2a8833c2b64b85874dd9449ffc2ad257351857338ff5b706c03a418"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.18-dev/images/sha256-081e5bd6615a5dc17247ebd2ccc26895c3feeff086720400fa39b477e60a77c0"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - 24.04
-      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.17-dev/images/sha256-bc7341a41ebe7ab261aa100732874507c452421ef733e408ac4f05ed453b0bc5"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - dev
       - 22.04
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.18-runtime/images/sha256-bf369637378264f4af6ddad5ca8b8611d3e372ffbea9ab7a06f1e122f0a0867b"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - runtime
+      - 22.04
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.17-dev/images/sha256-5a502008c50d0b6508e6027f911bdff070a7493700ae064bed74e1d22b91ed50"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - dev
+      - 24.04
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.16-dev/images/sha256-4841a8df7c340dab79bf9362dad687797649a00d594e0832eb83ea6880a40d3b"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.17-runtime/images/sha256-1ee5dfffceb71ac66617ada33de3a10de0cb74199cc4b82441192e5e92fa2ddf"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - runtime
       - 24.04
-      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-3124/>`__
+      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.17-dev/images/sha256-109218ad92bfae83bbd2710475f7502166e1ed54ca0b9748a9cbc3f5a1d75af1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - dev
+      - 22.04
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.17-runtime/images/sha256-5d78bd5918d394f92263daa2990e88d695d27200dd90ed83ec64d20c7661c9c1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - runtime
+      - 22.04
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.16-dev/images/sha256-b09b1ad921c09c687b7c916141051e9fcf15539a5686e5aa67c689195a522719"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - dev
+      - 24.04
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
       - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.16-dev/images/sha256-883fa95aba960c58a3e46fceaa18f03ede2c7df89b8e9fd603ab2d47e0852897"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.16-runtime/images/sha256-20dbd824e85558abfe33fc9283cc547d88cde3c623fe95322743a5082f883a64"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/tensorflow_rocm-2.16.2-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - runtime
+      - 24.04
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.16.2 <https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377>`__
+      - dev
       - 22.04
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-runtime/images/sha256-a94150ffb81365234ebfa34e764db5474bc6ab7d141b56495eac349778dafcf3"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - runtime
+      - 22.04
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
       - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
 
 

docs/compatibility/ml-compatibility/verl-compatibility.rst

@@ -16,25 +16,56 @@ verl offers a scalable, open-source fine-tuning solution optimized for AMD Insti
 * See the `verl documentation <https://verl.readthedocs.io/en/latest/>`_ for more information about verl. 
 * The official verl GitHub repository is `https://github.com/volcengine/verl <https://github.com/volcengine/verl>`_.
 * Use the AMD-validated :ref:`Docker images <verl-docker-compat>` with ROCm and verl preinstalled. 
-* See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>` to install and get started.
+* See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>` to get started.
 
 .. note::
 
 	verl is supported on ROCm 6.2.0.
 
+
 .. _verl-recommendations:
 
 Use cases and recommendations
 ================================================================================
 
-The benefits of verl in large-scale reinforcement learning from human feedback (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`_ blog.
+The benefits of verl in large-scale reinforcement leaning from human feedback (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`_ blog.
+
+.. _verl-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes ready-made `ROCm verl Docker images <https://hub.docker.com/r/rocm/verl>`_
+with ROCm backends on Docker Hub. The following Docker image tags and associated inventories represent the latest verl version from the official Docker Hub. The Docker images have been validated for `ROCm 6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`_. 
+
+.. list-table:: 
+    :header-rows: 1
+
+    *   - Docker image
+        - verl
+        - Linux
+        - Pytorch
+        - Python
+        - vllm
+
+    *   - .. raw:: html
+
+            <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+        - `0.3.0post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`_
+        - Ubuntu 20.04
+        - `2.5.0 <https://download.pytorch.org/whl/cu118/torch-2.5.0%2Bcu118-cp39-cp39-linux_x86_64.whl#sha256=1ee24b267418c37b297529ede875b961e382c1c365482f4142af2398b92ed127>`_
+        - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`_
+        - `0.6.4 <https://github.com/vllm-project/vllm/releases/tag/v0.6.4>`_
 
-.. _verl-supported_features:
 
 Supported features
 ===============================================================================
 
-The following table shows verl on ROCm support for GPU-accelerated modules.
+The following table shows verl and ROCm support for GPU-accelerated modules.
 
 .. list-table::
     :header-rows: 1
@@ -46,41 +77,9 @@ The following table shows verl on ROCm support for GPU-accelerated modules.
     * - ``FSDP``
       - Training engine
       - 0.3.0.post0
-      - 6.2.0
+      - 6.2
     * - ``vllm``
       - Inference engine
       - 0.3.0.post0
-      - 6.2.0
-
-.. _verl-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `ROCm verl Docker images <https://hub.docker.com/r/rocm/verl/tags>`_
-with ROCm backends on Docker Hub. The following Docker image tags and associated inventories represent the available verl versions from the official Docker Hub. 
-
-.. list-table:: 
-    :header-rows: 1
-
-    *   - Docker image
-        - ROCm
-        - verl
-        - Ubuntu
-        - Pytorch
-        - Python
-        - vllm
-
-    *   - .. raw:: html
-
-            <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
-        - `6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`_
-        - `0.3.0post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`_
-        - 20.04
-        - `2.5.0 <https://github.com/ROCm/pytorch/tree/release/2.5>`_
-        - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`_
-        - `0.6.3 <https://github.com/vllm-project/vllm/releases/tag/v0.6.3>`_
+      - 6.2
+  

docs/conf.py

@@ -96,11 +96,6 @@ article_pages = [
     {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/tensorflow-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/jax-compatibility", "os": ["linux"]},
-    {"file": "compatibility/ml-compatibility/verl-compatibility", "os": ["linux"]},
-    {"file": "compatibility/ml-compatibility/stanford-megatron-lm-compatibility", "os": ["linux"]},
-    {"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
-    {"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
-    {"file": "compatibility/ml-compatibility/taichi-compatibility", "os": ["linux"]},
     {"file": "how-to/deep-learning-rocm", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},

docs/how-to/deep-learning-rocm.rst

@@ -20,8 +20,6 @@ features for these ROCm-enabled deep learning frameworks.
 * :doc:`verl compatibility <../compatibility/ml-compatibility/verl-compatibility>`
 * :doc:`Stanford Megatron-LM compatibility <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
 * :doc:`DGL compatibility <../compatibility/ml-compatibility/dgl-compatibility>`
-* :doc:`Megablocks compatibility <../compatibility/ml-compatibility/megablocks-compatibility>`
-* :doc:`Taichi compatibility <../compatibility/ml-compatibility/taichi-compatibility>`
 
 This chart steps through typical installation workflows for installing deep learning frameworks for ROCm.
 
@@ -37,8 +35,6 @@ See the installation instructions to get started.
 * :doc:`verl for ROCm <rocm-install-on-linux:install/3rd-party/verl-install>`
 * :doc:`Stanford Megatron-LM for ROCm <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
 * :doc:`DGL for ROCm <rocm-install-on-linux:install/3rd-party/dgl-install>`
-* :doc:`Megablocks for ROCm <rocm-install-on-linux:install/3rd-party/megablocks-install>`
-* :doc:`Taichi for ROCm <rocm-install-on-linux:install/3rd-party/taichi-install>`
 
 .. note::
 

docs/reference/precision-support.rst

@@ -55,7 +55,7 @@ The floating-point types supported by ROCm are listed in the following table.
 
 .. list-table::
     :header-rows: 1
-    :widths: 15,25,60
+    :widths: 15,15,70
 
     *
       - Type name
@@ -63,19 +63,18 @@ The floating-point types supported by ROCm are listed in the following table.
       - Description
     *
       - float8 (E4M3)
-      - | ``__hip_fp8_e4m3_fnuz``,
-        | ``__hip_fp8_e4m3``
-      - An 8-bit floating-point number with **S1E4M3** bit layout, as described in :doc:`low precision floating point types page <hip:reference/low_fp_types>`.
-        The FNUZ variant has expanded range with no infinity or signed zero (NaN represented as negative zero),
-        while the OCP variant follows the Open Compute Project specification.
+      - ``__hip_fp8_e4m3_fnuz``
+      - An 8-bit floating-point number that mostly follows IEEE-754 conventions
+        and **S1E4M3** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_,
+        with expanded range and no infinity or signed zero. NaN is represented
+        as negative zero.
     *
       - float8 (E5M2)
-      - | ``__hip_fp8_e5m2_fnuz``,
-        | ``__hip_fp8_e5m2``
-      - An 8-bit floating-point number with **S1E5M2** bit layout, as described in :doc:`low precision floating point types page <hip:reference/low_fp_types>`.
-        The FNUZ variant has expanded range with no infinity or signed zero (NaN represented as negative zero),
-        while the OCP variant follows the Open Compute Project specification.
-
+      - ``__hip_fp8_e5m2_fnuz``
+      - An 8-bit floating-point number mostly following IEEE-754 conventions and
+        **S1E5M2** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_,
+        with expanded range and no infinity or signed zero. NaN is represented
+        as negative zero.
     *
       - float16
       - ``half``
@@ -108,8 +107,9 @@ The floating-point types supported by ROCm are listed in the following table.
   * The float8 and tensorfloat32 types are internal types used in calculations
     in Matrix Cores and can be stored in any type of the same size.
 
-  * CNDA3 natively supports FP8 FNUZ (E4M3 and E5M2), which differs from the customised
-    FP8 format used in NVIDIA's H100
+  * The encodings for FP8 (E5M2) and FP8 (E4M3) that the
+    MI300 series natively supports differ from the FP8 (E5M2) and FP8 (E4M3)
+    encodings used in NVIDIA H100
     (`FP8 Formats for Deep Learning <https://arxiv.org/abs/2209.05433>`_).
 
   * In some AMD documents and articles, float8 (E5M2) is referred to as bfloat8.
@@ -128,7 +128,7 @@ pages.
     :header-rows: 1
 
     *
-      - Icon
+      -  Icon
       - Definition
 
     *
@@ -163,137 +163,12 @@ pages.
   * Any type can be emulated by software, but this page does not cover such
     cases.
 
-Data type support by hardware architecture
+Data type support by Hardware Architecture
 ==========================================
 
-AMD's GPU lineup spans multiple architecture generations:
-
-* CDNA1 architecture: includes models such as MI100
-* CDNA2 architecture: includes models such as MI210, MI250, and MI250X
-* CDNA3 architecture: includes models such as MI300A, MI300X, and MI325X
-* RDNA3 architecture: includes models such as RX 7900XT and RX 7900XTX
-* RDNA4 architecture: includes models such as RX 9070 and RX 9070XT
-
-HIP C++ type implementation support
------------------------------------
-
-The HIP C++ types available on different hardware platforms are listed in the
-following table.
-
-.. list-table::
-    :header-rows: 1
-
-    *
-      - HIP C++ Type
-      - CDNA1
-      - CDNA2
-      - CDNA3
-      - RDNA3
-      - RDNA4
-
-    *
-      - ``int8_t``, ``uint8_t``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-    *
-      - ``int16_t``, ``uint16_t``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-    *
-      - ``int32_t``, ``uint32_t``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-    *
-      - ``int64_t``, ``uint64_t``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-    *
-      - ``__hip_fp8_e4m3_fnuz``
-      - ❌
-      - ❌
-      - ✅
-      - ❌
-      - ❌
-
-    *
-      - ``__hip_fp8_e5m2_fnuz``
-      - ❌
-      - ❌
-      - ✅
-      - ❌
-      - ❌
-
-    *
-      - ``__hip_fp8_e4m3``
-      - ❌
-      - ❌
-      - ❌
-      - ❌
-      - ✅
-
-    *
-      - ``__hip_fp8_e5m2``
-      - ❌
-      - ❌
-      - ❌
-      - ❌
-      - ✅
-
-    *
-      - ``half``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-    *
-      - ``bfloat16``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-    *
-      - ``float``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-    *
-      - ``double``
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-      - ✅
-
-.. note::
-
-  Library support for specific data types is contingent upon hardware support.
-  Even if a ROCm library indicates support for a particular data type, that type
-  will only be fully functional if the underlying hardware architecture (as shown
-  in the table above) also supports it. For example, fp8 types are only available
-  on architectures shown with a checkmark in the relevant rows.
+The MI200 series GPUs, which include MI210, MI250, and MI250X, are based on the
+CDNA2 architecture. The MI300 series GPUs, consisting of MI300A, MI300X, and
+MI325X, are based on the CDNA3 architecture.
 
 Compute units support
 ---------------------
@@ -315,33 +190,19 @@ The following table lists data type support for compute units.
         - int32
         - int64
       *
-        - CDNA1
+        - MI100
         - ✅
         - ✅
         - ✅
         - ✅
       *
-        - CDNA2
+        - MI200 series
         - ✅
         - ✅
         - ✅
         - ✅
       *
-        - CDNA3
-        - ✅
-        - ✅
-        - ✅
-        - ✅
-
-      *
-        - RDNA3
-        - ✅
-        - ✅
-        - ✅
-        - ✅
-
-      *
-        - RDNA4
+        - MI300 series
         - ✅
         - ✅
         - ✅
@@ -363,7 +224,7 @@ The following table lists data type support for compute units.
         - float32
         - float64
       *
-        - CDNA1
+        - MI100
         - ❌
         - ❌
         - ✅
@@ -372,7 +233,7 @@ The following table lists data type support for compute units.
         - ✅
         - ✅
       *
-        - CDNA2
+        - MI200 series
         - ❌
         - ❌
         - ✅
@@ -381,27 +242,7 @@ The following table lists data type support for compute units.
         - ✅
         - ✅
       *
-        - CDNA3
-        - ❌
-        - ❌
-        - ✅
-        - ✅
-        - ❌
-        - ✅
-        - ✅
-
-      *
-        - RDNA3
-        - ❌
-        - ❌
-        - ✅
-        - ✅
-        - ❌
-        - ✅
-        - ✅
-
-      *
-        - RDNA4
+        - MI300 series
         - ❌
         - ❌
         - ✅
@@ -430,33 +271,19 @@ The following table lists data type support for AMD GPU matrix cores.
         - int32
         - int64
       *
-        - CDNA1
+        - MI100
         - ✅
         - ❌
         - ❌
         - ❌
       *
-        - CDNA2
+        - MI200 series
         - ✅
         - ❌
         - ❌
         - ❌
       *
-        - CDNA3
-        - ✅
-        - ❌
-        - ❌
-        - ❌
-
-      *
-        - RDNA3
-        - ✅
-        - ❌
-        - ❌
-        - ❌
-
-      *
-        - RDNA4
+        - MI300 series
         - ✅
         - ❌
         - ❌
@@ -478,7 +305,7 @@ The following table lists data type support for AMD GPU matrix cores.
         - float32
         - float64
       *
-        - CDNA1
+        - MI100
         - ❌
         - ❌
         - ✅
@@ -487,7 +314,7 @@ The following table lists data type support for AMD GPU matrix cores.
         - ✅
         - ❌
       *
-        - CDNA2
+        - MI200 series
         - ❌
         - ❌
         - ✅
@@ -496,7 +323,7 @@ The following table lists data type support for AMD GPU matrix cores.
         - ✅
         - ✅
       *
-        - CDNA3
+        - MI300 series
         - ✅
         - ✅
         - ✅
@@ -505,26 +332,6 @@ The following table lists data type support for AMD GPU matrix cores.
         - ✅
         - ✅
 
-      *
-        - RDNA3
-        - ❌
-        - ❌
-        - ✅
-        - ✅
-        - ❌
-        - ❌
-        - ❌
-
-      *
-        - RDNA4
-        - ✅
-        - ✅
-        - ✅
-        - ✅
-        - ❌
-        - ❌
-        - ❌
-
 Atomic operations support
 -------------------------
 
@@ -550,33 +357,19 @@ page.
         - int32
         - int64
       *
-        - CDNA1
+        - MI100
         - ❌
         - ❌
         - ✅
         - ✅
       *
-        - CDNA2
+        - MI200 series
         - ❌
         - ❌
         - ✅
         - ✅
       *
-        - CDNA3
-        - ❌
-        - ❌
-        - ✅
-        - ✅
-
-      *
-        - RDNA3
-        - ❌
-        - ❌
-        - ✅
-        - ✅
-
-      *
-        - RDNA4
+        - MI300 series
         - ❌
         - ❌
         - ✅
@@ -598,7 +391,7 @@ page.
         - float32
         - float64
       *
-        - CDNA1
+        - MI100
         - ❌
         - ❌
         - ✅
@@ -607,7 +400,7 @@ page.
         - ✅
         - ❌
       *
-        - CDNA2
+        - MI200 series
         - ❌
         - ❌
         - ✅
@@ -616,7 +409,7 @@ page.
         - ✅
         - ✅
       *
-        - CDNA3
+        - MI300 series
         - ❌
         - ❌
         - ✅
@@ -625,26 +418,6 @@ page.
         - ✅
         - ✅
 
-      *
-        - RDNA3
-        - ❌
-        - ❌
-        - ❌
-        - ❌
-        - ❌
-        - ✅
-        - ❌
-
-      *
-        - RDNA4
-        - ❌
-        - ❌
-        - ✅
-        - ✅
-        - ❌
-        - ✅
-        - ❌
-
 .. note::
 
   You can emulate atomic operations using software for cases that are not
@@ -679,98 +452,36 @@ detailed description.
         - int16
         - int32
         - int64
-
-      *
-        - :doc:`Composable Kernel <composable_kernel:reference/Composable_Kernel_supported_scalar_types>`
-        - ✅/✅
-        - ❌/❌
-        - ✅/✅
-        - ❌/❌
-
-      *
-        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
-        - NA/✅
-        - NA/✅
-        - NA/✅
-        - NA/✅
-
-      *
-        - :doc:`hipSOLVER <hipsolver:reference/precision>`
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-
       *
         - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
         - ✅/✅
         - ❌/❌
         - ❌/❌
         - ❌/❌
-
-      *
-        - :doc:`hipTensor <hiptensor:api-reference/api-reference>`
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-
-      *
-        - :doc:`MIGraphX <amdmigraphx:reference/cpp>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`MIOpen <miopen:reference/datatypes>`
-        - ⚠️/⚠️
-        - ❌/❌
-        - ⚠️/⚠️
-        - ❌/❌
-
-      *
-        - :doc:`RCCL <rccl:api-reference/library-specification>`
-        - ✅/✅
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`rocFFT <rocfft:reference/api>`
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-
-      *
-        -  :doc:`rocPRIM <rocprim:reference/data-type-support>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-
       *
         - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
         - NA/✅
         - NA/✅
         - NA/✅
         - NA/✅
-
       *
-        - :doc:`rocSOLVER <rocsolver:reference/precision>`
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-
+        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
+        - NA/✅
+        - NA/✅
+        - NA/✅
+        - NA/✅
+      *
+        -  :doc:`rocPRIM <rocprim:reference/data-type-support>`
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+      *
+        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
       *
         - :doc:`rocThrust <rocthrust:data-type-support>`
         - ✅/✅
@@ -778,14 +489,6 @@ detailed description.
         - ✅/✅
         - ✅/✅
 
-      *
-        - :doc:`rocWMMA <rocwmma:api-reference/api-reference-guide>`
-        - ✅/✅
-        - ❌/❌
-        - ❌/✅
-        - ❌/❌
-
-
   .. tab-item:: Floating-point types
     :sync: floating-point-type
 
@@ -801,117 +504,15 @@ detailed description.
         - tensorfloat32
         - float32
         - float64
-
-      *
-        - :doc:`Composable Kernel <composable_kernel:reference/Composable_Kernel_supported_scalar_types>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
-        - ❌/❌
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/✅
-
-      *
-        - :doc:`hipSOLVER <hipsolver:reference/precision>`
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
       *
         - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-
-      *
-        - :doc:`hipTensor <hiptensor:api-reference/api-reference>`
         - ❌/❌
         - ❌/❌
         - ✅/✅
         - ✅/✅
         - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`MIGraphX <amdmigraphx:reference/cpp>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`MIOpen <miopen:reference/datatypes>`
-        - ⚠️/⚠️
-        - ⚠️/⚠️
-        - ✅/✅
-        - ⚠️/⚠️
-        - ❌/❌
-        - ✅/✅
-        - ⚠️/⚠️
-
-      *
-        - :doc:`RCCL <rccl:api-reference/library-specification>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`rocFFT <rocfft:reference/api>`
         - ❌/❌
         - ❌/❌
-        - ✅/✅
-        - ❌/❌
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
-      *
-        - :doc:`rocPRIM <rocprim:reference/data-type-support>`
-        - ❌/❌
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-        - ❌/❌
-        - ✅/✅
-        - ✅/✅
-
       *
         - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
         - NA/❌
@@ -921,17 +522,33 @@ detailed description.
         - NA/❌
         - NA/✅
         - NA/✅
-
       *
-        - :doc:`rocSOLVER <rocsolver:reference/precision>`
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
+        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/✅
+      *
+        - :doc:`rocPRIM <rocprim:reference/data-type-support>`
         - ❌/❌
         - ❌/❌
         - ✅/✅
         - ✅/✅
-
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+      *
+        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
+        - ❌/❌
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
       *
         - :doc:`rocThrust <rocthrust:data-type-support>`
         - ❌/❌
@@ -942,123 +559,62 @@ detailed description.
         - ✅/✅
         - ✅/✅
 
-      *
-        - :doc:`rocWMMA <rocwmma:api-reference/api-reference-guide>`
-        - ✅/❌
-        - ✅/❌
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-
 .. note::
-
+   
   As random number generation libraries, rocRAND and hipRAND only specify output
   data types for the random values they generate, with no need for input data
   types.
 
-hipDataType enumeration
------------------------
+Libraries internal calculations type support
+--------------------------------------------
 
-The ``hipDataType`` enumeration defines data precision types and is primarily
-used when the data reference itself does not include type information, such as
-in ``void*`` pointers. This enumeration is mainly utilized in BLAS libraries.
-The HIP type equivalents of the ``hipDataType`` enumeration are listed in the
-following table with descriptions and values.
+The following tables list ROCm library support for specific internal data types.
+Refer to the corresponding library data type support page for a detailed
+description.
 
-.. list-table::
-    :header-rows: 1
-    :widths: 25,25,10,40
+.. tab-set::
 
-    *
-      - hipDataType
-      - HIP type
-      - Value
-      - Description
+  .. tab-item:: Integral types
+    :sync: integral-type
 
-    *
-      - ``HIP_R_8I``
-      - ``int8_t``
-      - 3
-      - 8-bit real signed integer.
+    .. list-table::
+      :header-rows: 1
 
-    *
-      - ``HIP_R_8U``
-      - ``uint8_t``
-      - 8
-      - 8-bit real unsigned integer.
+      *
+        - Library internal data type name
+        - int8
+        - int16
+        - int32
+        - int64
+      *
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - ❌
+        - ❌
+        - ✅
+        - ❌
 
-    *
-      - ``HIP_R_16I``
-      - ``int16_t``
-      - 20
-      - 16-bit real signed integer.
 
-    *
-      - ``HIP_R_16U``
-      - ``uint16_t``
-      - 22
-      - 16-bit real unsigned integer.
+  .. tab-item:: Floating-point types
+    :sync: floating-point-type
 
-    *
-      - ``HIP_R_32I``
-      - ``int32_t``
-      - 10
-      - 32-bit real signed integer.
+    .. list-table::
+      :header-rows: 1
 
-    *
-      - ``HIP_R_32U``
-      - ``uint32_t``
-      - 12
-      - 32-bit real unsigned integer.
-
-    *
-      - ``HIP_R_32F``
-      - ``float``
-      - 0
-      - 32-bit real single precision floating-point.
-
-    *
-      - ``HIP_R_64F``
-      - ``double``
-      - 1
-      - 64-bit real double precision floating-point.
-
-    *
-      - ``HIP_R_16F``
-      - ``half``
-      - 2
-      - 16-bit real half precision floating-point.
-
-    *
-      - ``HIP_R_16BF``
-      - ``bfloat16``
-      - 14
-      - 16-bit real bfloat16 precision floating-point.
-
-    *
-      - ``HIP_R_8F_E4M3``
-      - ``__hip_fp8_e4m3``
-      - 28
-      - 8-bit real float8 precision floating-point (OCP version).
-
-    *
-      - ``HIP_R_8F_E5M2``
-      - ``__hip_fp8_e5m2``
-      - 29
-      - 8-bit real bfloat8 precision floating-point (OCP version).
-
-    *
-      - ``HIP_R_8F_E4M3_FNUZ``
-      - ``__hip_fp8_e4m3_fnuz``
-      - 1000
-      - 8-bit real float8 precision floating-point (FNUZ version).
-
-    *
-      - ``HIP_R_8F_E5M2_FNUZ``
-      - ``__hip_fp8_e5m2_fnuz``
-      - 1001
-      - 8-bit real bfloat8 precision floating-point (FNUZ version).
-
-The full list of the ``hipDataType`` enumeration listed in `library_types.h <https://github.com/ROCm/hip/blob/amd-staging/include/hip/library_types.h>`_ .
+      *
+        - Library internal data type name
+        - float8 (E4M3)
+        - float8 (E5M2)
+        - float16
+        - bfloat16
+        - tensorfloat32
+        - float32
+        - float64
+      *
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - ❌
+        - ❌
+        - ❌
+        - ❌
+        - ❌
+        - ✅
+        - ❌