Fix broken link for AMDGPU installer (#4990)

* 6.1.5 column added to compatibility matrix

.azuredevops/components/AMDMIGraphX.yml

@@ -84,8 +84,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -146,9 +144,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/HIP.yml

@@ -41,8 +41,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -86,19 +85,18 @@ jobs:
     parameters:
       artifactName: amd
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     environment: amd
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      environment: amd
 
 # HIP with Nvidia backend
 - job: hip_clr_combined_nvidia
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -141,8 +139,8 @@ jobs:
     parameters:
       artifactName: nvidia
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     environment: nvidia
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      environment: nvidia

.azuredevops/components/MIOpen.yml

@@ -67,8 +67,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -103,7 +101,7 @@ jobs:
         -DMIOPEN_BACKEND=HIP
         -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/miopen-deps
-        -DGPU_TARGETS=$(JOB_GPU_TARGET)
+        -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
         -DMIOPEN_ENABLE_AI_KERNEL_TUNING=OFF
         -DMIOPEN_ENABLE_AI_IMMED_MODE_FALLBACK=OFF
         -DCMAKE_BUILD_TYPE=Release
@@ -131,8 +129,6 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
   pool: $(JOB_TEST_POOL)
   workspace:
     clean: all
@@ -141,9 +137,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -199,7 +192,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:
       componentName: MIOpen
-      testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex test_rnn_seq_api'
+      testParameters: '-VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex test_rnn_seq_api'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/MIVisionX.yml

@@ -70,16 +70,13 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -108,11 +105,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: MIVisionX_testing
   dependsOn: MIVisionX
@@ -128,9 +125,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/ROCR-Runtime.yml

@@ -32,8 +32,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -57,9 +56,9 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
 
 - job: ROCR_Runtime_testing
   dependsOn: ROCR_Runtime
@@ -75,9 +74,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -127,13 +123,16 @@ jobs:
       targetType: 'inline'
       workingDirectory: $(Build.SourcesDirectory)/rocrtst/suites/test_common
       script: |
+        sudo rm -rf $(Agent.BuildDirectory)/external/llvm-project
+        mkdir -p $(Agent.BuildDirectory)/external/llvm-project/clang/lib
+        sudo ln -s $(Agent.BuildDirectory)/rocm/llvm/lib/clang/20/include $(Agent.BuildDirectory)/external/llvm-project/clang/lib/Headers
         mkdir build && cd build
         cmake .. \
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm \
           -DTARGET_DEVICES=$(JOB_GPU_TARGET) \
           -DROCM_DIR=$(Agent.BuildDirectory)/rocm \
           -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin \
-          -DOPENCL_INC_DIR=$(Agent.BuildDirectory)/rocm/llvm/lib/clang/21/include
+          -DOPENCL_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin
         make
         make rocrtst_kernels
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml

.azuredevops/components/ROCdbgapi.yml

@@ -24,8 +24,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -49,6 +48,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/ROCmValidationSuite.yml

@@ -60,16 +60,13 @@ jobs:
     value: $(Agent.BuildDirectory)/rocm
   - name: HIP_INC_DIR
     value: $(Agent.BuildDirectory)/rocm
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -98,14 +95,14 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     extraEnvVars:
-  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-  #       - ROCM_PATH:::/home/user/workspace/rocm
-  #       - HIP_INC_DIR:::/home/user/workspace/rocm
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
+      extraEnvVars:
+        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+        - ROCM_PATH:::/home/user/workspace/rocm
+        - HIP_INC_DIR:::/home/user/workspace/rocm
 
 - job: ROCmValidationSuite_testing
   dependsOn: ROCmValidationSuite
@@ -121,11 +118,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-        TEST_CONF_DIR: MI300X
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
-        TEST_CONF_DIR: MI210
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -144,7 +136,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:
       componentName: ROCmValidationSuite
-      testExecutable: $(Agent.BuildDirectory)/rocm/bin/rvs -c $(Agent.BuildDirectory)/rocm/share/rocm-validation-suite/conf/$(TEST_CONF_DIR)/gst_single.conf
+      testExecutable: $(Agent.BuildDirectory)/rocm/bin/rvs -c $(Agent.BuildDirectory)/rocm/share/rocm-validation-suite/conf/MI300X/gst_single.conf
       testParameters: ''
       testDir: $(Agent.BuildDirectory)
       testPublishResults: false

.azuredevops/components/Tensile.yml

@@ -35,8 +35,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -84,10 +83,11 @@ jobs:
           echo $(basename "$whlFile") >> pipelineArtifacts.txt
         fi
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: Tensile_testing
   timeoutInMinutes: 90
@@ -104,9 +104,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/TransferBench.yml

@@ -35,16 +35,13 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -72,10 +69,10 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: TransferBench_testing
   dependsOn: TransferBench
@@ -91,9 +88,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/amdsmi.yml

@@ -18,8 +18,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -37,9 +36,9 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
 
 - job: amdsmi_testing
   dependsOn: amdsmi
@@ -55,9 +54,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/aomp-extras.yml

@@ -23,8 +23,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -52,6 +51,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/aomp.yml

@@ -456,9 +456,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/composable_kernel.yml

@@ -48,8 +48,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -119,9 +117,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/half.yml

@@ -25,8 +25,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -60,7 +59,7 @@ jobs:
         ./bin/test
       workingDirectory: $(Build.SourcesDirectory)/test
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     environment: combined
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      environment: combined

.azuredevops/components/hip-tests.yml

@@ -52,8 +52,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -108,9 +106,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipBLAS-common.yml

@@ -29,8 +29,7 @@ jobs:
   - name: ROCM_PATH
     value: $(Agent.BuildDirectory)/rocm
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -54,8 +53,8 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     extraEnvVars:
-  #       - ROCM_PATH:::/home/user/workspace/rocm
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      extraEnvVars:
+        - ROCM_PATH:::/home/user/workspace/rocm

.azuredevops/components/hipBLAS.yml

@@ -63,8 +63,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -120,9 +118,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipBLASLt.yml

@@ -59,10 +59,14 @@ jobs:
     value: $(Build.BinariesDirectory)/rocm
   - name: TENSILE_ROCM_ASSEMBLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
+  - name: CMAKE_CXX_COMPILER
+    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
   - name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
+  - name: TENSILE_ROCM_PATH
+    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
+  - name: PATH
+    value: $(Agent.BuildDirectory)/rocm/llvm/bin:$(Agent.BuildDirectory)/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin
   - name: DAY_STRING
     value: $[format('{0:ddMMyyyy}', pipeline.startTime)]
   pool: ${{ variables.ULTRA_BUILD_POOL }}
@@ -72,8 +76,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -152,13 +154,13 @@ jobs:
       extraEnvVars:
         - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
         - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/amdclang
+        - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/bin/hipcc
         - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-        - ROCM_PATH:::/home/user/workspace/rocm
+        - TENSILE_ROCM_PATH:::/home/user/workspace/rocm/bin/hipcc
       extraCopyDirectories:
         - deps
 
 - job: hipBLASLt_testing
-  timeoutInMinutes: 120
   dependsOn: hipBLASLt
   condition: and(succeeded(), eq(variables.ENABLE_GFX942_TESTS, 'true'), not(containsValue(split(variables.DISABLED_GFX942_TESTS, ','), variables['Build.DefinitionName'])))
   variables:
@@ -172,9 +174,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipCUB.yml

@@ -43,8 +43,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -93,9 +91,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipFFT.yml

@@ -47,16 +47,13 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -92,10 +89,10 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: hipFFT_testing
   dependsOn: hipFFT
@@ -111,9 +108,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipRAND.yml

@@ -38,16 +38,13 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -79,12 +76,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     extraEnvVars:
-  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
+      extraEnvVars:
+        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - job: hipRAND_testing
   dependsOn: hipRAND
@@ -100,9 +97,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipSOLVER.yml

@@ -50,16 +50,13 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -100,12 +97,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     extraCopyDirectories:
-  #       - deps-install
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
+      extraCopyDirectories:
+        - deps-install
 
 - job: hipSOLVER_testing
   dependsOn: hipSOLVER
@@ -121,9 +118,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipSPARSE.yml

@@ -45,16 +45,13 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -95,11 +92,11 @@ jobs:
       artifactName: testMatrices
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     environment: test
-  #     gpuTarget: $(JOB_GPU_TARGET)
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      environment: test
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: hipSPARSE_testing
   dependsOn: hipSPARSE
@@ -115,9 +112,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipSPARSELt.yml

@@ -105,7 +105,6 @@ jobs:
         -DCMAKE_BUILD_TYPE=Release
         -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
         -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-        -DCMAKE_Fortran_COMPILER=f95
         -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
         -DTensile_LOGIC=
         -DTensile_CPU_THREADS=

.azuredevops/components/hipTensor.yml

@@ -42,8 +42,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -94,9 +92,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -116,7 +111,7 @@ jobs:
     parameters:
       componentName: hipTensor
       testDir: '$(Agent.BuildDirectory)/rocm/bin/hiptensor'
-      testParameters: '-E ".*-extended" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+      testParameters: '-E ".*-extended" -VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/hipfort.yml

@@ -51,8 +51,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -110,9 +108,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/llvm-project.yml

@@ -29,7 +29,7 @@ jobs:
     value: '$(Build.BinariesDirectory)/amdgcn/bitcode'
   - name: HIP_PATH
     value: '$(Agent.BuildDirectory)/rocm'
-  pool: ${{ variables.ULTRA_BUILD_POOL }}
+  pool: ${{ variables.MEDIUM_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -51,7 +51,7 @@ jobs:
       extraBuildFlags: >-
         -DCMAKE_PREFIX_PATH="$(Build.BinariesDirectory)/llvm;$(Build.BinariesDirectory)"
         -DCMAKE_BUILD_TYPE=Release
-        -DLLVM_ENABLE_PROJECTS=clang;lld;clang-tools-extra;mlir;flang
+        -DLLVM_ENABLE_PROJECTS=clang;lld;clang-tools-extra;mlir
         -DLLVM_ENABLE_RUNTIMES=compiler-rt;libunwind;libcxx;libcxxabi
         -DCLANG_ENABLE_AMDCLANG=ON
         -DLLVM_TARGETS_TO_BUILD=AMDGPU;X86
@@ -85,7 +85,7 @@ jobs:
       componentName: check-llvm
       testDir: 'llvm/build'
       testExecutable: './bin/llvm-lit'
-      testParameters: '-q --xunit-xml-output=llvm_test_output.xml --filter-out="live-debug-values-spill-tracking" ./test'
+      testParameters: '-q --xunit-xml-output=llvm_test_output.xml ./test'
       testOutputFile: llvm_test_output.xml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:

.azuredevops/components/omnitrace.yml

@@ -0,0 +1,140 @@
+# largely referenced from: https://github.com/ROCm/omnitrace/blob/main/.github/workflows/ubuntu-jammy.yml
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - autoconf
+    - autotools-dev
+    - bison
+    - build-essential
+    - bzip2
+    - clang
+    - cmake
+    - environment-modules
+    - g++-12
+    - libdrm-dev
+    - libfabric-dev
+    - libiberty-dev
+    - libpapi-dev
+    - libpfm4-dev
+    - libtool
+    - libopenmpi-dev
+    - m4
+    - openmpi-bin
+    - software-properties-common
+    - python3-pip
+    - texinfo
+    - zlib1g-dev
+- name: pipModules
+  type: object
+  default:
+    - numpy
+    - perfetto
+    - dataclasses
+- name: rocmDependencies
+  type: object
+  default:
+    - aomp
+    - clr
+    - llvm-project
+    - rccl
+    - rocm-core
+    - rocm_smi_lib
+    - rocminfo
+    - ROCR-Runtime
+    - rocprofiler
+    - rocprofiler-register
+    - roctracer
+
+jobs:
+- job: omnitrace
+  variables:
+  - group: common
+  - template: /.azuredevops/variables-global.yml
+  pool: ${{ variables.MEDIUM_BUILD_POOL }}
+  workspace:
+    clean: all
+  strategy:
+    matrix:
+      gfx942:
+        JOB_GPU_TARGET: gfx942
+  steps:
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+    parameters:
+      checkoutRepo: ${{ parameters.checkoutRepo }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+    parameters:
+      checkoutRef: ${{ parameters.checkoutRef }}
+      dependencyList: ${{ parameters.rocmDependencies }}
+      gpuTarget: $(JOB_GPU_TARGET)
+  - task: Bash@3
+    displayName: ROCm symbolic link
+    inputs:
+      targetType: inline
+      script: |
+        sudo rm -rf /opt/rocm
+        sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
+  - task: Bash@3
+    displayName: Add ROCm binaries to PATH
+    inputs:
+      targetType: inline
+      script: echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+  - task: Bash@3
+    displayName: Add ROCm compilers to PATH
+    inputs:
+      targetType: inline
+      script: echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+    parameters:
+# build flags reference: https://rocm.docs.amd.com/projects/omnitrace/en/latest/install/install.html
+      extraBuildFlags: >-
+        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+        -DOMNITRACE_BUILD_TESTING=ON
+        -DOMNITRACE_BUILD_DYNINST=ON
+        -DOMNITRACE_BUILD_LIBUNWIND=ON
+        -DDYNINST_BUILD_TBB=ON
+        -DDYNINST_BUILD_ELFUTILS=ON
+        -DDYNINST_BUILD_LIBIBERTY=ON
+        -DDYNINST_BUILD_BOOST=ON
+        -DOMNITRACE_USE_PAPI=ON
+        -DOMNITRACE_USE_MPI=ON
+        -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
+      multithreadFlag: -- -j32
+  - task: Bash@3
+    displayName: Set up omnitrace env
+    inputs:
+      targetType: inline
+      script: source share/omnitrace/setup-env.sh
+      workingDirectory: build
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+    parameters:
+      componentName: omnitrace
+  - task: Bash@3
+    displayName: Remove ROCm binaries from PATH
+    condition: always()
+    inputs:
+      targetType: inline
+      script: echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$(Agent.BuildDirectory)/rocm/bin;;' -e 's;^/;;' -e 's;/$;;')"
+  - task: Bash@3
+    displayName: Remove ROCm compilers from PATH
+    condition: always()
+    inputs:
+      targetType: inline
+      script: echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$(Agent.BuildDirectory)/rocm/llvm/bin;;' -e 's;^/;;' -e 's;/$;;')"
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+    parameters:
+      gpuTarget: $(JOB_GPU_TARGET)
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+    parameters:
+      gpuTarget: $(JOB_GPU_TARGET)

.azuredevops/components/rccl.yml

@@ -51,7 +51,6 @@ parameters:
 
 jobs:
 - job: rccl
-  timeoutInMinutes: 90
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
@@ -64,8 +63,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -81,6 +78,7 @@ jobs:
       checkoutRef: ${{ parameters.checkoutRef }}
       dependencyList: ${{ parameters.rocmDependencies }}
       gpuTarget: $(JOB_GPU_TARGET)
+  - script: chmod +x $(Agent.BuildDirectory)/rocm/bin/hipify-perl
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
       extraBuildFlags: >-
@@ -90,7 +88,7 @@ jobs:
         -DCMAKE_BUILD_TYPE=Release
         -DROCM_PATH=$(Agent.BuildDirectory)/rocm
         -DBUILD_TESTS=ON
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake;$(Agent.BuildDirectory)/rocm/libexec/hipify
+        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
         -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
         -GNinja
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
@@ -123,9 +121,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rdc.yml

@@ -65,8 +65,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -134,9 +132,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocAL.yml

@@ -66,16 +66,13 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - task: Bash@3
     displayName: 'Register libjpeg-turbo packages'
@@ -158,14 +155,14 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     registerJPEGPackages: true
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     extraCopyDirectories:
-  #       - /opt/libjpeg-turbo
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      registerJPEGPackages: true
+      gpuTarget: $(JOB_GPU_TARGET)
+      extraCopyDirectories:
+        - /opt/libjpeg-turbo
 
 - job: rocAL_testing
   dependsOn: rocAL
@@ -187,9 +184,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - task: Bash@3
     displayName: 'Register libjpeg-turbo packages'

.azuredevops/components/rocALUTION.yml

@@ -53,16 +53,13 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -95,12 +92,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     extraEnvVars:
-  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
+      extraEnvVars:
+        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - job: rocALUTION_testing
   dependsOn: rocALUTION
@@ -116,9 +113,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocBLAS.yml

@@ -64,10 +64,10 @@ jobs:
     value: $(Build.BinariesDirectory)/rocm
   - name: TENSILE_ROCM_ASSEMBLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang
+  - name: CMAKE_CXX_COMPILER
+    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
   - name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
   pool: ${{ variables.MEDIUM_BUILD_POOL }}
   workspace:
     clean: all
@@ -75,8 +75,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -98,8 +96,8 @@ jobs:
         -DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
         -DCMAKE_BUILD_TYPE=Release
-        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang++
-        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
+        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
+        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
         -DGPU_TARGETS=$(JOB_GPU_TARGET)
         -DTensile_CODE_OBJECT_VERSION=default
         -DTensile_LOGIC=asm_full
@@ -127,8 +125,8 @@ jobs:
       extraEnvVars:
         - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
         - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
+        - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/bin/hipcc
         - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-        - ROCM_PATH:::/home/user/workspace/rocm
 
 - job: rocBLAS_testing
   dependsOn: rocBLAS
@@ -144,9 +142,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocDecode.yml

@@ -45,15 +45,25 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
+  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
+  - task: Bash@3
+    displayName: 'Register ROCm packages'
+    inputs:
+      targetType: inline
+      script: |
+        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
+        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
+        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -72,10 +82,10 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     registerROCmPackages: true
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      registerROCmPackages: true
 
 - job: rocDecode_testing
   dependsOn: rocDecode
@@ -93,14 +103,22 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
+  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
+  - task: Bash@3
+    displayName: 'Register ROCm packages'
+    inputs:
+      targetType: inline
+      script: |
+        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
+        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
+        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml

.azuredevops/components/rocFFT.yml

@@ -55,8 +55,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -112,9 +110,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocJPEG.yml

@@ -40,21 +40,29 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
+  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
+  - task: Bash@3
+    displayName: 'Register ROCm packages'
+    inputs:
+      targetType: inline
+      script: |
+        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
+        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
+        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -75,11 +83,11 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     registerROCmPackages: true
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
+      registerROCmPackages: true
 
 - job: rocJPEG_testing
   dependsOn: rocJPEG
@@ -97,14 +105,22 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
+  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
+  - task: Bash@3
+    displayName: 'Register ROCm packages'
+    inputs:
+      targetType: inline
+      script: |
+        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
+        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
+        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml

.azuredevops/components/rocMLIR.yml

@@ -9,25 +9,21 @@ parameters:
   type: object
   default:
     - cmake
+    - ninja-build
     - git
+    - python3-pip
     - libdrm-dev
     - libstdc++-12-dev
-    - ninja-build
-    - python3-pip
 - name: pipModules
   type: object
   default:
-    - hip-python --extra-index-url https://test.pypi.org/simple
-    - ml_dtypes
-    - numpy
     - tomli
-    - scipy
 - name: rocmDependencies
   type: object
   default:
-    - clr
     - llvm-project
     - rocm-cmake
+    - clr
     - rocminfo
     - rocprofiler-register
     - ROCR-Runtime
@@ -60,7 +56,6 @@ jobs:
         -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
         -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -DROCM_PATH=$(Agent.BuildDirectory)/rocm
         -DBUILD_FAT_LIBROCKCOMPILER=1
         -GNinja
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
@@ -86,9 +81,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -119,7 +111,6 @@ jobs:
         -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
         -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -DROCM_PATH=$(Agent.BuildDirectory)/rocm
         -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
         -DROCM_TEST_CHIPSET=$(JOB_GPU_TARGET)
         -GNinja

.azuredevops/components/rocPRIM.yml

@@ -42,8 +42,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -92,9 +90,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocPyDecode.yml

@@ -22,41 +22,42 @@ parameters:
 - name: pipModules
   type: object
   default:
-    - hip-python --extra-index-url https://test.pypi.org/simple
     - numpy
     - pybind11
 - name: rocmDependencies
   type: object
   default:
-    - clr
-    - llvm-project
-    - rocDecode
     - rocm-cmake
-    - rocm-core
-    - rocminfo
+    - llvm-project
     - ROCR-Runtime
+    - clr
+    - rocminfo
+    - rocm-core
     - rocprofiler-register
+    - rocDecode
 
 jobs:
 - job: rocPyDecode
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
+  - task: Bash@3
+    displayName: 'pip install hip-python'
+    inputs:
+      targetType: inline
+      script: pip install -i https://test.pypi.org/simple hip-python
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -83,7 +84,6 @@ jobs:
         echo "##vso[task.setvariable variable=PYBIND11_PATH;]$(python3 -c 'import pybind11; print(pybind11.get_cmake_dir())')"
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
-      installEnabled: false
       extraBuildFlags: >-
         -DROCM_PATH=$(Agent.BuildDirectory)/rocm
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(PYTHON_USER_SITE)/pybind11;$(PYTHON_DIST_PACKAGES)/pybind11;$(PYBIND11_PATH)
@@ -91,14 +91,6 @@ jobs:
         -DGPU_TARGETS=$(JOB_GPU_TARGET)
         -DCMAKE_INSTALL_PREFIX_PYTHON=$(Build.BinariesDirectory)
         -GNinja
-  - task: Bash@3
-    displayName: 'rocPyDecode install'
-    inputs:
-      targetType: inline
-      script: |
-        sudo cmake --build . --target install
-        sudo chown -R $(whoami):$(id -gn) $(Build.BinariesDirectory)
-      workingDirectory: $(Build.SourcesDirectory)/build
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
@@ -113,8 +105,7 @@ jobs:
       script: |
         export ROCM_PATH=$(Agent.BuildDirectory)/rocm
         export HIP_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include/hip
-        sudo python3 setup.py bdist_wheel
-        sudo chown -R $(whoami):$(id -gn) $(find . -name "*.whl")
+        python3 setup.py bdist_wheel
       workingDirectory: $(Build.SourcesDirectory)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
     parameters:
@@ -138,12 +129,12 @@ jobs:
           echo $(basename "$whlFile") >> pipelineArtifacts.txt
         fi
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     optSymLink: true
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      gpuTarget: $(JOB_GPU_TARGET)
+      optSymLink: true
 
 - job: rocPyDecode_testing
   dependsOn: rocPyDecode
@@ -161,9 +152,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - task: Bash@3
     displayName: Ensure pybind11-dev is not installed
@@ -180,6 +168,11 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
+  - task: Bash@3
+    displayName: 'pip install hip-python'
+    inputs:
+      targetType: inline
+      script: pip install -i https://test.pypi.org/simple hip-python
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - task: DownloadPipelineArtifact@2
     displayName: 'Download Pipeline Wheel Files'

.azuredevops/components/rocRAND.yml

@@ -38,16 +38,13 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -76,12 +73,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     extraEnvVars:
-  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
+      extraEnvVars:
+        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - job: rocRAND_testing
   dependsOn: rocRAND
@@ -97,9 +94,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocSOLVER.yml

@@ -58,8 +58,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -130,9 +128,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocSPARSE.yml

@@ -56,8 +56,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -125,9 +123,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocThrust.yml

@@ -47,8 +47,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -97,9 +95,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocWMMA.yml

@@ -57,8 +57,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -82,7 +80,6 @@ jobs:
         -DROCWMMA_BUILD_SAMPLES=OFF
         -DGPU_TARGETS=$(JOB_GPU_TARGET)
         -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON
-        -DROCM_PLATFORM_VERSION=$(NEXT_RELEASE_VERSION)
         -GNinja
 # gfx1030 not supported in documentation
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
@@ -98,7 +95,7 @@ jobs:
       gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rocWMMA_testing
-  timeoutInMinutes: 120
+  timeoutInMinutes: 90
   dependsOn: rocWMMA
   condition: and(succeeded(), eq(variables.ENABLE_GFX942_TESTS, 'true'), not(containsValue(split(variables.DISABLED_GFX942_TESTS, ','), variables['Build.DefinitionName'])))
   variables:
@@ -112,9 +109,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocm-cmake.yml

@@ -8,6 +8,7 @@ parameters:
 - name: aptPackages
   type: object
   default:
+    - cmake
     - doxygen
     - doxygen-doc
     - ninja-build
@@ -17,17 +18,14 @@ parameters:
   type: object
   default:
     - cget
-    - cmake==3.20.5
     - ninja
-    - rocm-docs-core
 
 jobs:
 - job: rocm_cmake
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -35,34 +33,27 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-  - task: Bash@3
-    displayName: Add CMake to PATH
-    inputs:
-      targetType: inline
-      script: echo "##vso[task.prependpath]$(python3 -m site --user-base)/bin"
   - 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/build-cmake.yml
-  - task: Bash@3
-    displayName: CTest setup
-    inputs:
-      targetType: inline
-      script: |
-        python -m pip install -r $(Build.SourcesDirectory)/docs/requirements.txt
-        python -m pip install -r $(Build.SourcesDirectory)/test/docsphinx/docs/.sphinx/requirements.txt
-        git config --global user.email "you@example.com"
-        git config --global user.name "Your Name"
+# extra steps for ctest suite
+  - script: |
+      python -m pip install -r $(Build.SourcesDirectory)/docs/requirements.txt
+      python -m pip install -r $(Build.SourcesDirectory)/test/docsphinx/docs/.sphinx/requirements.txt
+      git config --global user.email "you@example.com"
+      git config --global user.name "Your Name"
+    displayName: "ctest setup"
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:
       componentName: rocm-cmake
-      testParameters: '-E "pass-version-parent" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     environment: combined
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      environment: combined
+      gpuTarget: $(JOB_GPU_TARGET)

.azuredevops/components/rocm-core.yml

@@ -16,8 +16,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -37,10 +36,10 @@ jobs:
         -DCPACK_GENERATOR=DEB
         -DCPACK_DEBIAN_PACKAGE_RELEASE="local.9999~99.99"
         -DCPACK_RPM_PACKAGE_RELEASE="local.9999"
-        -DROCM_VERSION="$(NEXT_RELEASE_VERSION)"
+        -DROCM_VERSION="$(next-release)"
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocm-examples.yml

@@ -75,8 +75,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -135,9 +133,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocm_bandwidth_test.yml

@@ -40,8 +40,7 @@ jobs:
     value: $(Agent.BuildDirectory)/rocm
   - name: ROCR_LIB_DIR
     value: $(Agent.BuildDirectory)/rocm
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -67,13 +66,13 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     extraEnvVars:
-  #       - ROCR_INC_DIR:::/home/user/workspace/rocm
-  #       - ROCR_LIB_DIR:::/home/user/workspace/rocm
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      extraEnvVars:
+        - ROCR_INC_DIR:::/home/user/workspace/rocm
+        - ROCR_LIB_DIR:::/home/user/workspace/rocm
 
 - job: rocm_bandwidth_test_testing
   dependsOn: rocm_bandwidth_test
@@ -89,9 +88,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocm_smi_lib.yml

@@ -10,7 +10,6 @@ parameters:
   default:
     - cmake
     - libdrm-dev
-    - pkg-config
     - python3-pip
 
 jobs:
@@ -18,8 +17,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -38,9 +36,10 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rocm_smi_lib_testing
   dependsOn: rocm_smi_lib
@@ -56,13 +55,7 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml

.azuredevops/components/rocminfo.yml

@@ -28,15 +28,14 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
+      registerRadeon: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -54,10 +53,9 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     registerROCmPackages: true
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
 
 - job: rocminfo_testing
   dependsOn: rocminfo
@@ -73,9 +71,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -107,6 +102,5 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
       environment: test
       gpuTarget: $(JOB_GPU_TARGET)

.azuredevops/components/rocprofiler-compute.yml

@@ -52,16 +52,13 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -85,11 +82,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rocprofiler_compute_testing
   timeoutInMinutes: 120
@@ -108,9 +105,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -161,7 +155,7 @@ jobs:
     parameters:
       componentName: rocprofiler-compute
       testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
-      testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
+      testExecutable: ROCPROFCOMPUTE_ARCH_OVERRIDE="MI300X" ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
   - task: Bash@3
     displayName: Remove ROCm binaries from PATH
     condition: always()

.azuredevops/components/rocprofiler-register.yml

@@ -16,8 +16,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -45,7 +44,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     environment: combined
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      environment: combined

.azuredevops/components/rocprofiler-sdk.yml

@@ -37,8 +37,6 @@ parameters:
     - clr
     - llvm-project
     - rccl
-    - rocDecode
-    - rocJPEG
     - rocm-cmake
     - rocm-core
     - rocminfo
@@ -50,22 +48,19 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerROCmPackages: true
+      registerRadeon: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -99,12 +94,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     registerROCmPackages: true
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rocprofiler_sdk_testing
   dependsOn: rocprofiler_sdk
@@ -120,15 +114,12 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerROCmPackages: true
+      registerRadeon: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -164,4 +155,3 @@ jobs:
       pipModules: ${{ parameters.pipModules }}
       environment: test
       gpuTarget: $(JOB_GPU_TARGET)
-      registerROCmPackages: true

.azuredevops/components/rocprofiler-systems.yml

@@ -46,19 +46,17 @@ parameters:
 - name: rocmDependencies
   type: object
   default:
-    - amdsmi
     - aomp
     - clr
     - llvm-project
     - rccl
     - rocDecode
-    - rocJPEG
     - rocm-core
-    - rocminfo
     - rocm_smi_lib
+    - rocminfo
+    - ROCR-Runtime
     - rocprofiler-register
     - rocprofiler-sdk
-    - ROCR-Runtime
 
 jobs:
 - job: rocprofiler_systems
@@ -72,14 +70,12 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerROCmPackages: true
+      registerRadeon: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -158,15 +154,12 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerROCmPackages: true
+      registerRadeon: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:

.azuredevops/components/rocprofiler.yml

@@ -57,8 +57,6 @@ jobs:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -114,9 +112,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocr_debug_agent.yml

@@ -40,8 +40,7 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -67,9 +66,10 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rocr_debug_agent_testing
   dependsOn: rocr_debug_agent
@@ -85,9 +85,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/roctracer.yml

@@ -11,7 +11,6 @@ parameters:
     - cmake
     - doxygen
     - graphviz
-    - libdrm-amdgpu-dev
     - ninja-build
     - python3-pip
 - name: pipModules
@@ -43,22 +42,18 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -85,12 +80,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
-  #     registerROCmPackages: true
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: roctracer_testing
   dependsOn: roctracer
@@ -106,15 +100,10 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
     parameters:
@@ -139,4 +128,3 @@ jobs:
       pipModules: ${{ parameters.pipModules }}
       environment: test
       gpuTarget: $(JOB_GPU_TARGET)
-      registerROCmPackages: true

.azuredevops/components/rpp.yml

@@ -29,7 +29,6 @@ parameters:
     - clr
     - half
     - llvm-project
-    - rocm-cmake
     - rocminfo
     - ROCR-Runtime
 - name: rocmTestDependencies
@@ -50,16 +49,13 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: 
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
+  pool: ${{ variables.LOW_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
     matrix:
       gfx942:
         JOB_GPU_TARGET: gfx942
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -83,7 +79,6 @@ jobs:
         -DHALF_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include
         -DCMAKE_BUILD_TYPE=Release
         -DGPU_TARGETS=$(JOB_GPU_TARGET)
-        -DROCM_PLATFORM_VERSION=$(NEXT_RELEASE_VERSION)
         -GNinja
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
     parameters:
@@ -92,11 +87,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     gpuTarget: $(JOB_GPU_TARGET)
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      pipModules: ${{ parameters.pipModules }}
+      gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rpp_testing
   dependsOn: rpp
@@ -114,9 +109,6 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-      gfx90a:
-        JOB_GPU_TARGET: gfx90a
-        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/dependencies/half560.yml

@@ -19,7 +19,7 @@ jobs:
   pool:
     vmImage: ${{ variables.BASE_BUILD_POOL }}
   container:
-    image: rocm/dev-ubuntu-22.04:${{ variables.LATEST_RELEASE_VERSION }}
+    image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
   workspace:
     clean: all
   steps:

.azuredevops/tag-builds/TransferBench.yml

@@ -1,29 +0,0 @@
-variables:
-- group: common
-- template: /.azuredevops/variables-global.yml
-
-parameters:
-- name: checkoutRef
-  type: string
-  default: refs/tags/$(LATEST_RELEASE_TAG)
-
-resources:
-  repositories:
-  - repository: pipelines_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/ROCm
-  - repository: release_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/TransferBench
-    ref: ${{ parameters.checkoutRef }}
-
-trigger: none
-pr: none
-
-jobs:
-  - template: ${{ variables.CI_COMPONENT_PATH }}/TransferBench.yml
-    parameters:
-      checkoutRepo: release_repo
-      checkoutRef: ${{ parameters.checkoutRef }}

.azuredevops/templates/steps/build-cmake.yml

@@ -32,9 +32,6 @@ parameters:
 - name: installEnabled
   type: boolean
   default: true
-- name: printDiskSpace
-  type: boolean
-  default: true
 
 steps:
 # create workingDirectory if it does not exist and change into it
@@ -47,9 +44,8 @@ steps:
       cmakeArgs: -DCMAKE_INSTALL_PREFIX=${{ parameters.installDir }} ${{ parameters.extraBuildFlags }} ${{ parameters.cmakeSourceDir }}
     ${{ else }}:
       cmakeArgs: ${{ parameters.extraBuildFlags }} ..
-- ${{ if parameters.printDiskSpace }}:
-  - script: df -h
-    displayName: Disk space before build
+- script: df -h
+  displayName: Disk space before build
 # equivalent to running make $cmakeTargetDir from $cmakeBuildDir
 # i.e., cd $cmakeBuildDir; make $cmakeTargetDir
 - task: CMake@1
@@ -61,9 +57,8 @@ steps:
     ${{ else }}:
       cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} --target ${{ parameters.customBuildTarget }} ${{ parameters.multithreadFlag }}'
     retryCountOnTaskFailure: 10
-- ${{ if parameters.printDiskSpace }}:
-  - script: df -h
-    displayName: Disk space after build
+- script: df -h
+  displayName: Disk space after build
 # equivalent to running make $cmakeTarget from $cmakeBuildDir
 # e.g., make install
 - ${{ if eq(parameters.installEnabled, true) }}:

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

@@ -4,13 +4,13 @@ steps:
   inputs:
     targetType: inline
     script: |
-      export packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
+      export packageName=$(curl -s https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
       echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
 - task: Bash@3
   displayName: 'Download aqlprofile'
   inputs:
     targetType: inline
-    script: wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$(packageName)
+    script: wget -nv https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/$(packageName)
     workingDirectory: '$(Pipeline.Workspace)'
 - task: Bash@3
   displayName: 'Extract aqlprofile'

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

@@ -6,21 +6,21 @@ parameters:
 - name: pipModules
   type: object
   default: []
-- name: registerROCmPackages
+- name: registerRadeon
   type: boolean
   default: false
 
 steps:
-- ${{ if eq(parameters.registerROCmPackages, true) }}:
+- ${{ if eq(parameters.registerRadeon, true) }}:
   - task: Bash@3
-    displayName: 'Register AMDGPU & ROCm repos'
+    displayName: 'Register repo.radeon packages'
     inputs:
       targetType: inline
       script: |
         sudo mkdir --parents --mode=0755 /etc/apt/keyrings
         wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$(REPO_RADEON_VERSION)/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION) jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/latest/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/latest jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
         echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
         sudo apt update
 # firefox takes time to upgrade and is not needed for CI workloads, hold version
@@ -34,12 +34,7 @@ steps:
   displayName: 'sudo apt-get update'
   inputs:
     targetType: inline
-    script: |
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-backports main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-security main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
+    script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
 - task: Bash@3
   displayName: 'sudo apt-get upgrade'
   inputs:
@@ -55,7 +50,7 @@ steps:
     displayName: 'sudo apt-get install ...'
     inputs:
       targetType: inline
-      script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}
+      script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes install ${{ join(' ', parameters.aptPackages) }}
 - ${{ if gt(length(parameters.pipModules), 0) }}:
   - task: Bash@3
     displayName: 'pip install  ...'

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

@@ -222,13 +222,13 @@ parameters:
       hasGpuTarget: false
     rocm-examples:
       pipelineId: $(ROCM_EXAMPLES_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      stagingBranch: develop
+      mainlineBranch: develop
       hasGpuTarget: true
     rocminfo:
       pipelineId: $(ROCMINFO_PIPELINE_ID)
       stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      mainlineBranch: amd-master
       hasGpuTarget: false
     rocMLIR:
       pipelineId: $(ROCMLIR_PIPELINE_ID)
@@ -262,7 +262,7 @@ parameters:
       hasGpuTarget: true
     rocprofiler-compute:
       pipelineId: $(ROCPROFILER_COMPUTE_PIPELINE_ID)
-      stagingBranch: develop
+      stagingBranch: amd-staging
       mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocprofiler-register:
@@ -288,7 +288,7 @@ parameters:
     ROCR-Runtime:
       pipelineId: $(ROCR_RUNTIME_PIPELINE_ID)
       stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      mainlineBranch: amd-master
       hasGpuTarget: false
     rocRAND:
       pipelineId: $(ROCRAND_PIPELINE_ID)

.azuredevops/templates/steps/docker-container.yml

@@ -107,7 +107,7 @@ steps:
 # dynamically write to a Dockerfile
 # first is to do base setup of users, groups
   - task: Bash@3
-    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Create start of Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -126,7 +126,7 @@ steps:
 # for test jobs, setup GPU-related users and group
   - ${{ if eq(parameters.environment, 'test') }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: GPU setup of Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -137,7 +137,7 @@ steps:
 # now install a common set of packages through apt
   - ${{ if gt(length(parameters.baseAptPackages), 0) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Base Apt Packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -146,7 +146,7 @@ steps:
 # iterate through possible apt repos that might need to be added to the docker container
   - ${{ if eq(parameters.registerROCmPackages, true) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Register ROCm packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -154,13 +154,13 @@ steps:
         script: |
           echo "RUN mkdir --parents --mode=0755 /etc/apt/keyrings" >> Dockerfile
           echo "RUN wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | tee /etc/apt/keyrings/rocm.gpg > /dev/null" >> Dockerfile
-          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$(REPO_RADEON_VERSION)/ubuntu jammy main\" | tee /etc/apt/sources.list.d/amdgpu.list" >> Dockerfile
-          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION) jammy main\" | tee --append /etc/apt/sources.list.d/rocm.list" >> Dockerfile
+          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/latest/ubuntu jammy main\" | tee /etc/apt/sources.list.d/amdgpu.list" >> Dockerfile
+          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/latest jammy main\" | tee --append /etc/apt/sources.list.d/rocm.list" >> Dockerfile
           echo "RUN printf 'Package: *\\nPin: release o=repo.radeon.com\\nPin-Priority: 600' > /etc/apt/preferences.d/rocm-pin-600" >> Dockerfile
           echo "RUN DEBIAN_FRONTEND=noninteractive apt-get --yes update" >> Dockerfile
   - ${{ if eq(parameters.registerCUDAPackages, true) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Register CUDA packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -172,7 +172,7 @@ steps:
           echo 'RUN DEBIAN_FRONTEND=noninteractive apt-get --yes update' >> Dockerfile
   - ${{ if eq(parameters.registerJPEGPackages, true) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Register libjpeg-turbo packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -185,7 +185,7 @@ steps:
 # install AOCL to docker container, if needed
   - ${{ if eq(parameters.installAOCL, true) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: aocl install to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -197,7 +197,7 @@ steps:
 # since apt repo list is updated, install the extra apt packages
   - ${{ if gt(length(parameters.aptPackages), 0) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Extra Apt Packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -206,7 +206,7 @@ steps:
 # install latest cmake to docker container, if needed
   - ${{ if eq(parameters.installLatestCMake, true) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: latest cmake install to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -216,7 +216,7 @@ steps:
             echo "RUN pip install cmake --upgrade" >> Dockerfile
 # setup workspace where binaries, sources, and dependencies from the job will be copied to
   - task: Bash@3
-    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Workspace setup of Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -228,7 +228,7 @@ steps:
 # pip install is done here as non-root
   - ${{ if gt(length(parameters.pipModules), 0) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Extra Python Modules to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -236,7 +236,7 @@ steps:
         script: echo "RUN pip install -v ${{ join(' ', parameters.pipModules) }}" >> Dockerfile
 # copy common directories
   - task: Bash@3
-    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Copy base directories to Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -254,7 +254,7 @@ steps:
 # copy extra directories, if applicable to the job
   - ${{ each extraCopyDirectory in parameters.extraCopyDirectories }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Copy ${{ extraCopyDirectory }} to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -265,7 +265,7 @@ steps:
           fi
 # setup ldconfig
   - task: Bash@3
-    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: ldconfig to Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -279,7 +279,7 @@ steps:
 # create /opt/rocm symbolic link, if needed
   - ${{ if eq(parameters.optSymLink, true) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: /opt/rocm symbolic link to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -290,7 +290,7 @@ steps:
 # set environment variables needed for some python-based components
   - ${{ if eq(parameters.pythonEnvVars, true) }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: python environment variables
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -303,7 +303,7 @@ steps:
 # add to PATH environment variable
   - ${{ if ne(parameters.extraPaths, '') }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Add to PATH in Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -313,21 +313,21 @@ steps:
 # use ::: as delimiter to allow for colons to be in the environment variable values
   - ${{ each extraEnvVar in parameters.extraEnvVars }}:
     - task: Bash@3
-      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Set ${{ extraEnvVar }} to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
         targetType: inline
         script: echo "ENV ${{ split(extraEnvVar, ':::')[0] }}='${{ split(extraEnvVar, ':::')[1] }}'" >> Dockerfile
   - task: Bash@3
-    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Print Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
       targetType: inline
       script: cat Dockerfile
   - task: Docker@2
-    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
     inputs:
       containerRegistry: 'ContainerService'
       ${{ if ne(parameters.gpuTarget, '') }}:
@@ -337,7 +337,7 @@ steps:
       Dockerfile: '$(Pipeline.Workspace)/Dockerfile'
       buildContext: '$(Pipeline.Workspace)'
   - task: Bash@3
-    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: "!! Docker Image URL !!"
     inputs:
       workingDirectory: $(Pipeline.Workspace)

.azuredevops/templates/steps/manifest.yml

@@ -77,11 +77,11 @@ steps:
 
       dependencies_rows=$(cat $manifest_json | \
         jq -r '
-          .dependencies[] |
-          "<tr><td>" + .buildNumber + "</td>" +
-          "<td><a href=\"https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=" + .buildId + "\">" + .buildId + "</a></td>" +
-          "<td><a href=\"" + .repoUrl + "\">" + .repoName + "</a></td>" +
-          "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "\">" + .repoRef + "</a></td>" +
+          .dependencies[] | 
+          "<tr><td>" + .buildNumber + "</td>" + 
+          "<td><a href=\"https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=" + .buildId + "\">" + .buildId + "</a></td>" + 
+          "<td><a href=\"" + .repoUrl + "\">" + .repoName + "</a></td>" + 
+          "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "\">" + .repoRef + "</a></td>" + 
           "<td><a href=\"" + .repoUrl + "/commit/" + .repoVersion + "\">" + .repoVersion + "</a></td></tr>"
         ')
       dependencies_rows=$(echo $dependencies_rows)
@@ -130,11 +130,6 @@ steps:
       </html>
       EOF
 
-      sed -i -e 's|</tr> <tr>|</tr>\n<tr>|g' \
-        -e 's|</td><td>|</td>\n  <td>|g' \
-        -e 's|<tr><td>|<tr>\n  <td>|g' \
-        -e 's|</td></tr>|</td>\n</tr>|g' $manifest_html
-
       cat $manifest_html
 - task: PublishHtmlReport@1
   displayName: Publish manifest.html

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

@@ -20,37 +20,41 @@ steps:
       ARTIFACT_NAME="composablekernel.${{ parameters.gpuTarget }}"
       EXIT_CODE=0
 
-      # Try to find an Azure build for the specific CK commit called out in MIOpen's requirements.txt
+      # The commits that MIOpen reference are all merge commits from CK/develop to CK/amd-develop
+      # These commits are present on CK/amd-develop but not on CK/develop
+      # Ex-CI only builds CK/develop, so we need to find a commit present on both CK/develop and CK/amd-develop
+
       CK_COMMIT=$(grep 'ROCm/composable_kernel' requirements.txt | sed -E 's/.*@([a-f0-9]{40}).*/\1/')
       echo "Fetching CK build ID for commit $CK_COMMIT"
-      CK_CHECKS_URL="$GH_API/composable_kernel/commits/${CK_COMMIT}/check-runs"
-      CK_BUILD_ID=$(curl -s $CK_CHECKS_URL | \
+      CK_COMMIT_URL="$GH_API/composable_kernel/commits/${CK_COMMIT}"
+      PARENT_COMMIT=$(curl -s $CK_COMMIT_URL | jq '.parents[1].sha' | tr -d '"')
+      echo "Found parent commit: $PARENT_COMMIT"
+      PARENT_CHECKS_URL="$GH_API/composable_kernel/commits/${PARENT_COMMIT}/check-runs"
+      CK_BUILD_ID=$(curl -s $PARENT_CHECKS_URL | \
         jq '.check_runs[] | select(.name == "composable_kernel" and .app.slug == "azure-pipelines") | .details_url' | \
         tr -d '"' | grep -oP 'buildId=\K\d+')
 
-      # If none found, use latest successful CK build instead
-      if [[ -z "$CK_BUILD_ID" ]]; then
+      if [ -z "$CK_BUILD_ID" ]; then
         echo "Did not find specific CK build ID"
         LATEST_BUILD_URL="$AZ_API/build/builds?definitions=$(COMPOSABLE_KERNEL_PIPELINE_ID)&statusFilter=completed&resultFilter=succeeded&\$top=1&api-version=7.1"
         CK_BUILD_ID=$(curl -s $LATEST_BUILD_URL | jq '.value[0].id')
         echo "Found latest CK build ID: $CK_BUILD_ID"
         EXIT_CODE=1
-      else
-        echo "Found specific CK build ID: $CK_BUILD_ID"
       fi
 
       AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?artifactName=$ARTIFACT_NAME&api-version=7.1"
       ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
 
-      # If using the specific CK commit and it doesn't have any valid artifacts, use latest successful CK build instead
-      if { [[ -z "$ARTIFACT_URL" ]] || [[ "$ARTIFACT_URL" == "null" ]]; } && [[ $EXIT_CODE -eq 0 ]]; then
-        echo "Did not find valid specific CK build artifact"
-        LATEST_BUILD_URL="$AZ_API/build/builds?definitions=$(COMPOSABLE_KERNEL_PIPELINE_ID)&statusFilter=completed&resultFilter=succeeded&\$top=1&api-version=7.1"
+      if [ -z "$ARTIFACT_URL" ]; then
+        echo "Did not find specific CK build artifact"
+        LATEST_BUILD_URL="$AZ_API/build/builds?definitions=$(COMPOSABLE_KERNEL_PIPELINE_ID)&status=completed&result=succeeded&\$top=1&api-version=7.1"
         CK_BUILD_ID=$(curl -s $LATEST_BUILD_URL | jq '.value[0].id')
         echo "Found latest CK build ID: $CK_BUILD_ID"
         AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?artifactName=$ARTIFACT_NAME&api-version=7.1"
         ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
         EXIT_CODE=2
+      elif [ $EXIT_CODE -eq 0 ]; then
+        echo "Found specific CK build ID: $CK_BUILD_ID"
       fi
 
       echo "Downloading CK artifact from $ARTIFACT_URL"
@@ -60,13 +64,9 @@ steps:
       tar -zxvf $(System.ArtifactsDirectory)/$ARTIFACT_NAME/*.tar.gz -C $(Agent.BuildDirectory)/rocm
       rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/$ARTIFACT_NAME
 
-      if [[ $EXIT_CODE -ne 0 ]]; then
+      if [ $EXIT_CODE -ne 0 ]; then
         BUILD_COMMIT=$(curl -s $AZ_API/build/builds/$CK_BUILD_ID | jq '.sourceVersion' | tr -d '"')
-        if [[ $EXIT_CODE -eq 1 ]]; then
-          echo "WARNING: couldn't find a CK build for commit $CK_COMMIT"
-        elif [[ $EXIT_CODE -eq 2 ]]; then
-          echo "WARNING: couldn't find a valid CK artifact for commit $CK_COMMIT"
-        fi
+        echo "WARNING: couldn't find a CK build for commit $CK_COMMIT"
         echo "Instead used latest CK build $CK_BUILD_ID for commit $BUILD_COMMIT"
       fi
       exit $EXIT_CODE

.azuredevops/templates/steps/test.yml

@@ -10,7 +10,7 @@ parameters:
   default: 'ctest'
 - name: testParameters
   type: string
-  default: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+  default: '-VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
 - name: testOutputFile
   type: string
   default: test_output.xml
@@ -33,6 +33,7 @@ parameters:
     - aomp
     - HIPIFY
     - MIVisionX
+    - rocm-cmake
     - rocm_smi_lib
     - rocprofiler-sdk
     - roctracer

.azuredevops/variables-global.yml

@@ -27,18 +27,14 @@ variables:
   value: rocm-ci_larger_base_disk_pool
 - name: GFX942_TEST_POOL
   value: gfx942_test_pool
-- name: GFX90A_TEST_POOL
-  value: gfx90a_test_pool
-- name: LATEST_RELEASE_VERSION
-  value: 6.3.4
-- name: REPO_RADEON_VERSION
-  value: 6.3.4
-- name: NEXT_RELEASE_VERSION
-  value: 6.4.0
 - name: LATEST_RELEASE_TAG
-  value: rocm-6.3.4
-- name: DOCKER_SKIP_GFX
-  value: gfx90a
+  value: rocm-6.1.0
+- name: DOCKER_IMAGE_NAME
+  value: rocm/dev-ubuntu-22.04
+- name: LATEST_DOCKER_VERSION
+  value: 6.1
+- name: KEYRING_VERSION
+  value: 6.3
 - name: AMDMIGRAPHX_GFX942_TEST_PIPELINE_ID
   value: 197
 - name: AMDMIGRAPHX_PIPELINE_ID
@@ -155,6 +151,8 @@ variables:
   value: 105
 - name: HIPTENSOR_TAGGED_PIPELINE_ID
   value: 56
+- name: LAST_RELEASE
+  value: 6.1.0
 - name: LLVM_PROJECT_PIPELINE_ID
   value: 2
 - name: LLVM_PROJECT_TAGGED_PIPELINE_ID
@@ -185,6 +183,10 @@ variables:
   value: 100
 - name: RDC_TAGGED_PIPELINE_ID
   value: 59
+- name: REIMAGE_ORG
+  value: AGS-ROCm-CI
+- name: REIMAGE_REPO
+  value: cirrascale-reimage-automation
 - name: ROCAL_PIPELINE_ID
   value: 151
 - name: ROCALUTION_GFX942_TEST_PIPELINE_ID

.github/workflows/issue_retrieval.yml

@@ -2,7 +2,7 @@ name: Issue retrieval
 
 on:
   issues:
-    types: [opened, edited]
+    types: [opened]
 
 jobs:
   auto-retrieve:
@@ -15,7 +15,7 @@ jobs:
           app_id: ${{ secrets.ACTION_APP_ID }}
           private_key: ${{ secrets.ACTION_PEM }}
       - name: 'Retrieve Issue'
-        uses: harkgill-amd/rocm_issue_management@main
+        uses: abhimeda/rocm_issue_management@main
         with:
           authentication-token: ${{ steps.generate_token.outputs.token }}
           github-organization: 'ROCm'

.gitignore

@@ -11,7 +11,6 @@ _toc.yml
 docBin/
 _doxygen/
 _readthedocs/
-__pycache__/
 
 # avoid duplicating contributing.md due to conf.py
 docs/CHANGELOG.md

.wordlist.txt

@@ -132,7 +132,6 @@ GDS
 GEMM
 GEMMs
 GFortran
-GFXIP
 Gemma
 GiB
 GIM
@@ -156,6 +155,7 @@ HCA
 HGX
 HIPCC
 HIPExtension
+HIPification
 HIPIFY
 HIPification
 HIPify
@@ -340,7 +340,6 @@ RNNs
 ROC
 ROCProfiler
 ROCT
-ROCTx
 ROCTracer
 ROCclr
 ROCdbgapi
@@ -481,7 +480,6 @@ ZenDNN
 accuracies
 activations
 addr
-ai
 alloc
 allocatable
 allocator
@@ -547,7 +545,6 @@ cTDP
 dataset
 datasets
 dataspace
-datatemplate
 datatype
 datatypes
 dbgapi
@@ -576,7 +573,6 @@ el
 embeddings
 enablement
 encodings
-endfor
 endpgm
 enqueue
 env
@@ -697,7 +693,6 @@ pageable
 pallas
 parallelization
 parallelizing
-param
 parameterization
 passthrough
 perfcounter
@@ -775,7 +770,6 @@ rocm
 rocminfo
 rocprim
 rocprof
-rocprofv
 rocprofiler
 rocr
 rocrand
@@ -815,7 +809,6 @@ supercomputing
 symlink
 symlinks
 sys
-tabindex
 td
 tensorfloat
 th
@@ -861,7 +854,6 @@ vectorizes
 virtualize
 virtualized
 vjxb
-vllm
 voxel
 walkthrough
 walkthroughs

CONTRIBUTING.md

@@ -66,10 +66,11 @@ project-specific steps. Refer to each repository's PR process for any additional
   during our release cycle, as coordinated by the maintainer
 * We'll inform you once your change is committed
 
-> [!IMPORTANT]
-> By creating a PR, you agree to allow your contribution to be licensed under the
-> terms of the LICENSE.txt file in the corresponding repository. Different repositories may use different
-> licenses.
+:::{important}
+By creating a PR, you agree to allow your contribution to be licensed under the
+terms of the LICENSE.txt file in the corresponding repository. Different repositories may use different
+licenses.
+:::
 
 You can look up each license on the [ROCm licensing](https://rocm.docs.amd.com/en/latest/about/license.html) page.
 

README.md

@@ -50,7 +50,7 @@ The following example shows how to use the repo tool to download the ROCm source
 ```bash
 mkdir -p ~/ROCm/
 cd ~/ROCm/
-export ROCM_VERSION=6.3.3
+export ROCM_VERSION=6.3.2
 ~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.3.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
 ~/bin/repo sync
 ```
@@ -77,8 +77,8 @@ The Build time will reduce significantly if we limit the GPU Architecture/s agai
 
 mkdir -p ~/WORKSPACE/      # Or any folder name other than WORKSPACE
 cd ~/WORKSPACE/
-export ROCM_VERSION=6.3.3
-~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.3.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
+export ROCM_VERSION=6.3.2
+~/bin/repo init -u http://github.com/ROCm/ROCm.git -b develop -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
 ~/bin/repo sync
 
 # --------------------------------------
@@ -116,7 +116,7 @@ bash install-prerequisites.sh
 # For ubuntu22.04 system
 cd ROCm/tools/rocm-build/docker/ubuntu22
 cp * /tmp && cd /tmp
-bash install-prerequisites.sh
+bash install-prerequisities.sh
 # For ubuntu24.04 system
 cd ROCm/tools/rocm-build/docker/ubuntu24
 cp * /tmp && cd /tmp

RELEASE.md

@@ -10,7 +10,7 @@
 <!-- markdownlint-disable reference-links-images            -->
 <!-- markdownlint-disable no-missing-space-atx              -->
 <!-- spellcheck-disable                                     -->
-# ROCm 6.3.3 release notes
+# ROCm 6.3.2 release notes
 
 The release notes provide a summary of notable changes since the previous ROCm release.
 
@@ -24,6 +24,8 @@ The release notes provide a summary of notable changes since the previous ROCm r
 
 - [ROCm known issues](#rocm-known-issues)
 
+- [ROCm resolved issues](#rocm-resolved-issues)
+
 - [ROCm upcoming changes](#rocm-upcoming-changes)
 
 ```{note}
@@ -32,43 +34,35 @@ documentation to verify compatibility and system requirements.
 ```
 ## Release highlights
 
-The following are notable new features and improvements in ROCm 6.3.3. For changes to individual components, see
+The following are notable improvements in ROCm 6.3.2. For changes to individual components, see
 [Detailed component changes](#detailed-component-changes).
 
-### ROCm Offline Installer Creator updates
-
-The ROCm Offline Installer Creator 6.3.3 adds a new Post-Install Options menu, which includes a new ``udev`` option for adding GPU resources access for all users. It also moves the user-specific GPU access option (for the ``video,render`` group) from the Driver Options menu to the Post-Install Options menu. See the [ROCm Offline Installer Creator](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/rocm-offline-installer.html#post-install-options-menu) documentation for more information.
-
 ### ROCm documentation updates
 
 ROCm documentation continues to be updated to provide clearer and more comprehensive guidance for a wider variety of user needs and use cases.
 
-* [Tutorials for AI developers](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/) have been added. These tutorials are Jupyter notebook-based, easy-to-follow documents. They are ideal for AI developers who want to learn about specific topics, including inference, fine-tuning, and training.
+* Documentation about ROCm compatibility with deep learning frameworks has been added. These topics outline ROCm-enabled features for each deep learning framework, key ROCm libraries that can influence the capabilities, validated Docker image tags, and features supported across the available ROCm and framework versions. For more information, see:
 
-* The [LLM inference performance validation guide for AMD Instinct MI300X](https://rocm.docs.amd.com/en/latest/how-to/rocm-for-ai/inference/vllm-benchmark.html)
-  now includes additional models for performance benchmarking. The accompanying ROCm vLLM Docker has been upgraded to ROCm 6.3.1.
- 
-* The HIP documentation has been updated with new resources for developers. To learn more about concurrency, parallelism, and stream management on devices and multiple GPUs, see [Asynchronous concurrent execution](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/asynchronous.html)
+    * [PyTorch compatibility](https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/pytorch-compatibility.html)
 
-* The following HIP documentation topics have been updated:
-    - [Virtual memory management](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/memory_management/virtual_memory.html)
-    - [Programming for HIP runtime compiler (RTC)](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_rtc.html)
-    - [HIP porting guide](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_porting_guide.html)
-    - [Porting CUDA driver API](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_porting_driver_api.html)
-    - [CUDA to HIP API function comparison](https://rocm.docs.amd.com/projects/HIP/en/latest/reference/api_syntax.html)
+    * [TensorFlow compatibility](https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/tensorflow-compatibility.html)
+
+    * [JAX compatibility](https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/jax-compatibility.html)
+
+* The [HIP C++ language extensions](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_cpp_language_extensions.html) and [Kernel language C++ support](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/kernel_language_cpp_support.html) topics have been reorganized to make them easier to find and review. The topics have also been enhanced with new content.
 
 ## Operating system and hardware support changes
 
-Operating system and hardware support remain unchanged in this release.
+ROCm 6.3.2 adds support for Azure Linux 3.0 (kernel: 6.6). Azure Linux is supported only on AMD Instinct accelerators. For more information, see [Azure Linux installation](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/quick-start.html).
 
 See the [Compatibility
-matrix](https://rocm.docs.amd.com/en/docs-6.3.3/compatibility/compatibility-matrix.html)
+matrix](https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html)
 for more information about operating system and hardware compatibility.
 
 ## ROCm components
 
-The following table lists the versions of ROCm components for ROCm 6.3.3, including any version
-changes from 6.3.2 to 6.3.3. Click the component's updated version to go to a list of its changes.
+The following table lists the versions of ROCm components for ROCm 6.3.2, including any version
+changes from 6.3.1 to 6.3.2. Click the component's updated version to go to a list of its changes.
 Click {fab}`github` to go to the component's source code on GitHub.
 
 <div class="pst-scrollable-table-container">
@@ -90,47 +84,47 @@ Click {fab}`github` to go to the component's source code on GitHub.
             <tr>
                 <th rowspan="9">Libraries</th>
                 <th rowspan="9">Machine learning and computer vision</th>
-                <td><a href="https://rocm.docs.amd.com/projects/composable_kernel/en/docs-6.3.3/index.html">Composable Kernel</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/composable_kernel/en/docs-6.3.2/index.html">Composable Kernel</a></td>
                 <td>1.1.0</td>
                 <td><a href="https://github.com/ROCm/composable_kernel"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/AMDMIGraphX/en/docs-6.3.3/index.html">MIGraphX</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/AMDMIGraphX/en/docs-6.3.2/index.html">MIGraphX</a></td>
                 <td>2.11.0</td>
                 <td><a href="https://github.com/ROCm/AMDMIGraphX"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/MIOpen/en/docs-6.3.3/index.html">MIOpen</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/MIOpen/en/docs-6.3.2/index.html">MIOpen</a></td>
                 <td>3.3.0</td>
                 <td><a href="https://github.com/ROCm/MIOpen"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/MIVisionX/en/docs-6.3.3/index.html">MIVisionX</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/MIVisionX/en/docs-6.3.2/index.html">MIVisionX</a></td>
                 <td>3.1.0</td>
                 <td><a href="https://github.com/ROCm/MIVisionX"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocAL/en/docs-6.3.3/index.html">rocAL</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocAL/en/docs-6.3.2/index.html">rocAL</a></td>
                 <td>2.1.0</td>
                 <td><a href="https://github.com/ROCm/rocAL"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocDecode/en/docs-6.3.3/index.html">rocDecode</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocDecode/en/docs-6.3.2/index.html">rocDecode</a></td>
                 <td>0.8.0</td>
                 <td><a href="https://github.com/ROCm/rocDecode"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocJPEG/en/docs-6.3.3/index.html">rocJPEG</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocJPEG/en/docs-6.3.2/index.html">rocJPEG</a></td>
                 <td>0.6.0</td>
                 <td><a href="https://github.com/ROCm/rocJPEG"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocPyDecode/en/docs-6.3.3/index.html">rocPyDecode</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocPyDecode/en/docs-6.3.2/index.html">rocPyDecode</a></td>
                 <td>0.2.0</td>
                 <td><a href="https://github.com/ROCm/rocPyDecode"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rpp/en/docs-6.3.3/index.html">RPP</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rpp/en/docs-6.3.2/index.html">RPP</a></td>
                 <td>1.9.1</td>
                 <td><a href="https://github.com/ROCm/rpp"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
@@ -139,7 +133,7 @@ Click {fab}`github` to go to the component's source code on GitHub.
             <tr>
                 <th rowspan="1"></th>
                 <th rowspan="1">Communication</th>
-                <td><a href="https://rocm.docs.amd.com/projects/rccl/en/docs-6.3.3/index.html">RCCL</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rccl/en/docs-6.3.2/index.html">RCCL</a></td>
                 <td>2.21.5</td>
                 <td><a href="https://github.com/ROCm/rccl"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
@@ -148,82 +142,82 @@ Click {fab}`github` to go to the component's source code on GitHub.
             <tr>
                 <th rowspan="16"></th>
                 <th rowspan="16">Math</th>
-                <td><a href="https://rocm.docs.amd.com/projects/hipBLAS/en/docs-6.3.3/index.html">hipBLAS</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipBLAS/en/docs-6.3.2/index.html">hipBLAS</a></td>
                 <td>2.3.0</td>
                 <td><a href="https://github.com/ROCm/hipBLAS"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipBLASLt/en/docs-6.3.3/index.html">hipBLASLt</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipBLASLt/en/docs-6.3.2/index.html">hipBLASLt</a></td>
                 <td>0.10.0</td>
                 <td><a href="https://github.com/ROCm/hipBLASLt"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipFFT/en/docs-6.3.3/index.html">hipFFT</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipFFT/en/docs-6.3.2/index.html">hipFFT</a></td>
                 <td>1.0.17</td>
                 <td><a href="https://github.com/ROCm/hipFFT"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipfort/en/docs-6.3.3/index.html">hipfort</a></td>
-                <td>0.5.1</td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipfort/en/docs-6.3.2/index.html">hipfort</a></td>
+                <td>0.5.0&nbsp;&Rightarrow;&nbsp;<a href="#hipfort-0-5-1">0.5.1</a></td>
                 <td><a href="https://github.com/ROCm/hipfort"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipRAND/en/docs-6.3.3/index.html">hipRAND</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipRAND/en/docs-6.3.2/index.html">hipRAND</a></td>
                 <td>2.11.1</td>
                 <td><a href="https://github.com/ROCm/hipRAND"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipSOLVER/en/docs-6.3.3/index.html">hipSOLVER</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipSOLVER/en/docs-6.3.2/index.html">hipSOLVER</a></td>
                 <td>2.3.0</td>
                 <td><a href="https://github.com/ROCm/hipSOLVER"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipSPARSE/en/docs-6.3.3/index.html">hipSPARSE</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipSPARSE/en/docs-6.3.2/index.html">hipSPARSE</a></td>
                 <td>3.1.2</td>
                 <td><a href="https://github.com/ROCm/hipSPARSE"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipSPARSELt/en/docs-6.3.3/index.html">hipSPARSELt</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipSPARSELt/en/docs-6.3.2/index.html">hipSPARSELt</a></td>
                 <td>0.2.2</td>
                 <td><a href="https://github.com/ROCm/hipSPARSELt"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocALUTION/en/docs-6.3.3/index.html">rocALUTION</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocALUTION/en/docs-6.3.2/index.html">rocALUTION</a></td>
                 <td>3.2.1</td>
                 <td><a href="https://github.com/ROCm/rocALUTION"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocBLAS/en/docs-6.3.3/index.html">rocBLAS</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocBLAS/en/docs-6.3.2/index.html">rocBLAS</a></td>
                 <td>4.3.0</td>
                 <td><a href="https://github.com/ROCm/rocBLAS"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocFFT/en/docs-6.3.3/index.html">rocFFT</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocFFT/en/docs-6.3.2/index.html">rocFFT</a></td>
                 <td>1.0.31</td>
                 <td><a href="https://github.com/ROCm/rocFFT"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocRAND/en/docs-6.3.3/index.html">rocRAND</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocRAND/en/docs-6.3.2/index.html">rocRAND</a></td>
                 <td>3.2.0</td>
                 <td><a href="https://github.com/ROCm/rocRAND"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocSOLVER/en/docs-6.3.3/index.html">rocSOLVER</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocSOLVER/en/docs-6.3.2/index.html">rocSOLVER</a></td>
                 <td>3.27.0</td>
                 <td><a href="https://github.com/ROCm/rocSOLVER"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocSPARSE/en/docs-6.3.3/index.html">rocSPARSE</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocSPARSE/en/docs-6.3.2/index.html">rocSPARSE</a></td>
                 <td>3.3.0</td>
                 <td><a href="https://github.com/ROCm/rocSPARSE"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocWMMA/en/docs-6.3.3/index.html">rocWMMA</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocWMMA/en/docs-6.3.2/index.html">rocWMMA</a></td>
                 <td>1.6.0</td>
                 <td><a href="https://github.com/ROCm/rocWMMA"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/Tensile/en/docs-6.3.3/src/index.html">Tensile</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/Tensile/en/docs-6.3.2/src/index.html">Tensile</a></td>
                 <td>4.42.0</td>
                 <td><a href="https://github.com/ROCm/Tensile"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
@@ -232,22 +226,22 @@ Click {fab}`github` to go to the component's source code on GitHub.
             <tr>
                 <th rowspan="4"></th>
                 <th rowspan="4">Primitives</th>
-                <td><a href="https://rocm.docs.amd.com/projects/hipCUB/en/docs-6.3.3/index.html">hipCUB</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipCUB/en/docs-6.3.2/index.html">hipCUB</a></td>
                 <td>3.3.0</td>
                 <td><a href="https://github.com/ROCm/hipCUB"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/hipTensor/en/docs-6.3.3/index.html">hipTensor</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/hipTensor/en/docs-6.3.2/index.html">hipTensor</a></td>
                 <td>1.4.0</td>
                 <td><a href="https://github.com/ROCm/hipTensor"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocPRIM/en/docs-6.3.3/index.html">rocPRIM</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocPRIM/en/docs-6.3.2/index.html">rocPRIM</a></td>
                 <td>3.3.0</td>
                 <td><a href="https://github.com/ROCm/rocPRIM"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocThrust/en/docs-6.3.3/index.html">rocThrust</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocThrust/en/docs-6.3.2/index.html">rocThrust</a></td>
                 <td>3.3.0</td>
                 <td><a href="https://github.com/ROCm/rocThrust"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
@@ -256,27 +250,27 @@ Click {fab}`github` to go to the component's source code on GitHub.
             <tr>
                 <th rowspan="7">Tools</th>
                 <th rowspan="7">System management</th>
-                <td><a href="https://rocm.docs.amd.com/projects/amdsmi/en/docs-6.3.3/index.html">AMD SMI</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/amdsmi/en/docs-6.3.2/index.html">AMD SMI</a></td>
                 <td>24.7.1</td>
                 <td><a href="https://github.com/ROCm/amdsmi"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rdc/en/docs-6.3.3/index.html">ROCm Data Center Tool</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rdc/en/docs-6.3.2/index.html">ROCm Data Center Tool</a></td>
                 <td>0.3.0</td>
                 <td><a href="https://github.com/ROCm/rdc"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocminfo/en/docs-6.3.3/index.html">rocminfo</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocminfo/en/docs-6.3.2/index.html">rocminfo</a></td>
                 <td>1.0.0</td>
                 <td><a href="https://github.com/ROCm/rocminfo"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocm_smi_lib/en/docs-6.3.3/index.html">ROCm SMI</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocm_smi_lib/en/docs-6.3.2/index.html">ROCm SMI</a></td>
                 <td>7.4.0</td>
                 <td><a href="https://github.com/ROCm/rocm_smi_lib"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/ROCmValidationSuite/en/docs-6.3.3/index.html">ROCmValidationSuite</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCmValidationSuite/en/docs-6.3.2/index.html">ROCmValidationSuite</a></td>
                 <td>1.1.0</td>
                 <td><a href="https://github.com/ROCm/ROCmValidationSuite"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
@@ -285,38 +279,38 @@ Click {fab}`github` to go to the component's source code on GitHub.
             <tr>
                 <th rowspan="6"></th>
                 <th rowspan="6">Performance</th>
-                <td><a href="https://rocm.docs.amd.com/projects/rocm_bandwidth_test/en/docs-6.3.3/index.html">ROCm Bandwidth
+                <td><a href="https://rocm.docs.amd.com/projects/rocm_bandwidth_test/en/docs-6.3.2/index.html">ROCm Bandwidth
                         Test</a></td>
                 <td>1.4.0</td>
                 <td><a href="https://github.com/ROCm/rocm_bandwidth_test/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-compute/en/docs-6.3.3/index.html">ROCm Compute Profiler</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-compute/en/docs-6.3.2/index.html">ROCm Compute Profiler</a></td>
                 <td>3.0.0</td>
                 <td><a href="https://github.com/ROCm/rocprofiler-compute"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-systems/en/docs-6.3.3/index.html">ROCm Systems Profiler</a></td>
-                <td>0.1.1&nbsp;&Rightarrow;&nbsp;<a href="#rocm-systems-profiler-0-1-2">0.1.2</td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-systems/en/docs-6.3.2/index.html">ROCm Systems Profiler</a></td>
+                <td>0.1.0&nbsp;&Rightarrow;&nbsp;<a href="#rocm-systems-profiler-0-1-1">0.1.1</td>
                 <td><a href="https://github.com/ROCm/rocprofiler-systems"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler/en/docs-6.3.3/index.html">ROCProfiler</a></td>
-                <td>2.0.0</td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler/en/docs-6.3.2/index.html">ROCProfiler</a></td>
+                <td>2.0.0&nbsp;&Rightarrow;&nbsp;<a href="#rocprofiler-2-0-0">2.0.0</a></td>
                 <td><a href="https://github.com/ROCm/ROCProfiler/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/docs-6.3.3/index.html">ROCprofiler-SDK</a></td>
-                <td>0.5.0</td>
+                <td><a href="https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/docs-6.3.2/index.html">ROCprofiler-SDK</a></td>
+                <td>0.5.0&nbsp;&Rightarrow;&nbsp;<a href="#rocprofiler-sdk-0-5-0">0.5.0</a></td>
                 <td><a href="https://github.com/ROCm/rocprofiler-sdk/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr >
-                <td><a href="https://rocm.docs.amd.com/projects/roctracer/en/docs-6.3.3/index.html">ROCTracer</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/roctracer/en/docs-6.3.2/index.html">ROCTracer</a></td>
                 <td>4.1.0</td>
                 <td><a href="https://github.com/ROCm/ROCTracer/"><i
                             class="fab fa-github fa-lg"></i></a></td>
@@ -326,32 +320,32 @@ Click {fab}`github` to go to the component's source code on GitHub.
             <tr>
                 <th rowspan="5"></th>
                 <th rowspan="5">Development</th>
-                <td><a href="https://rocm.docs.amd.com/projects/HIPIFY/en/docs-6.3.3/index.html">HIPIFY</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/HIPIFY/en/docs-6.3.2/index.html">HIPIFY</a></td>
                 <td>18.0.0</td>
                 <td><a href="https://github.com/ROCm/HIPIFY/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/ROCdbgapi/en/docs-6.3.3/index.html">ROCdbgapi</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCdbgapi/en/docs-6.3.2/index.html">ROCdbgapi</a></td>
                 <td>0.77.0</td>
                 <td><a href="https://github.com/ROCm/ROCdbgapi/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/ROCmCMakeBuildTools/en/docs-6.3.3/index.html">ROCm CMake</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCmCMakeBuildTools/en/docs-6.3.2/index.html">ROCm CMake</a></td>
                 <td>0.14.0</td>
                 <td><a href="https://github.com/ROCm/rocm-cmake/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/ROCgdb/en/docs-6.3.3/index.html">ROCm Debugger (ROCgdb)</a>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCgdb/en/docs-6.3.2/index.html">ROCm Debugger (ROCgdb)</a>
                 </td>
                 <td>15.2</td>
                 <td><a href="https://github.com/ROCm/ROCgdb/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/rocr_debug_agent/en/docs-6.3.3/index.html">ROCr Debug Agent</a>
+                <td><a href="https://rocm.docs.amd.com/projects/rocr_debug_agent/en/docs-6.3.2/index.html">ROCr Debug Agent</a>
                 </td>
                 <td>2.0.3</td>
                 <td><a href="https://github.com/ROCm/rocr_debug_agent/"><i
@@ -361,13 +355,13 @@ Click {fab}`github` to go to the component's source code on GitHub.
         <tbody class="rocm-components-compilers">
             <tr>
                 <th rowspan="2" colspan="2">Compilers</th>
-                <td><a href="https://rocm.docs.amd.com/projects/HIPCC/en/docs-6.3.3/index.html">HIPCC</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/HIPCC/en/docs-6.3.2/index.html">HIPCC</a></td>
                 <td>1.1.1</td>
                 <td><a href="https://github.com/ROCm/llvm-project/"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/llvm-project/en/docs-6.3.3/index.html">llvm-project</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/llvm-project/en/docs-6.3.2/index.html">llvm-project</a></td>
                 <td>18.0.0</td>
                 <td><a href="https://github.com/ROCm/llvm-project/"><i
                             class="fab fa-github fa-lg"></i></a></td>
@@ -376,12 +370,12 @@ Click {fab}`github` to go to the component's source code on GitHub.
         <tbody class="rocm-components-runtimes">
             <tr>
                 <th rowspan="2" colspan="2">Runtimes</th>
-                <td><a href="https://rocm.docs.amd.com/projects/HIP/en/docs-6.3.3/index.html">HIP</a></td>
-                <td>6.3.2</td>
+                <td><a href="https://rocm.docs.amd.com/projects/HIP/en/docs-6.3.2/index.html">HIP</a></td>
+                <td>6.3.1&nbsp;&Rightarrow;&nbsp;<a href="#hip-6-3-2">6.3.2</a></td>
                 <td><a href="https://github.com/ROCm/HIP/"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-                <td><a href="https://rocm.docs.amd.com/projects/ROCR-Runtime/en/docs-6.3.3/index.html">ROCr Runtime</a></td>
+                <td><a href="https://rocm.docs.amd.com/projects/ROCR-Runtime/en/docs-6.3.2/index.html">ROCr Runtime</a></td>
                 <td>1.14.0</td>
                 <td><a href="https://github.com/ROCm/ROCR-Runtime/"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
@@ -393,34 +387,112 @@ Click {fab}`github` to go to the component's source code on GitHub.
 
 The following sections describe key changes to ROCm components.
 
-### **ROCm Systems Profiler** (0.1.2)
+### **HIP** (6.3.2)
+
+#### Added
+
+* Tracking of Heterogeneous System Architecture (HSA) handlers:
+    - Adds an atomic counter to track the outstanding HSA handlers.
+    - Waits on CPU for the callbacks if the number exceeds the defined value.
+* Codes to capture Architected Queueing Language (AQL) packets for HIP graph memory copy node between host and device. HIP enqueues AQL packets during graph launch.
+* Control to use system pool implementation in runtime commands handling. By default, it is disabled.
+* A new path to avoid `WaitAny` calls in `AsyncEventsLoop`. The new path is selected by default.
+* Runtime control on decrement counter only if the event is popped. There is a new way to restore dead signals cleanup for the old path.
+* A new logic in runtime to track the age of events from the kernel mode driver.
+
+#### Optimized
+
+* HSA callback performance. The HIP runtime creates and submits commands in the queue and interacts with HSA through a callback function. HIP waits for the CPU status from HSA to optimize the handling of events, profiling, commands, and HSA signals for higher performance.
+* Runtime optimization which combines all logic of `WaitAny` in a single processing loop and avoids extra memory allocations or reference counting. The runtime won't spin on the CPU if all events are busy.
+* Multi-threaded dispatches for performance improvement.
+* Command submissions and processing between CPU and GPU by introducing a way to limit the software batch size.
+* Switch to `std::shared_mutex` in book/keep logic in streams from multiple threads simultaneously, for performance improvement in specific customer applications.
+* `std::shared_mutex` is used in memory object mapping, for performance improvement.
 
 #### Resolved issues
 
-* Fixed an error that prevented GPU hardware activity from being presented in certain workloads.  
+* Race condition in multi-threaded producer/consumer scenario with `hipMallocFromPoolAsync`.
+* Segmentation fault with `hipStreamLegacy` while using the API `hipStreamWaitEvent`.
+* Usage of `hipStreamLegacy` in HIP event record.
+* A soft hang in graph execution process from HIP user object. The fix handles the release of graph execution object properly considering synchronization on the device/stream. The user application now behaves the same with `hipUserObject` on both the AMD ROCm and NVIDIA CUDA platforms.
+
+### **hipfort** (0.5.1)
+
+#### Added
+
+* Support for building with LLVM Flang.
+
+#### Resolved issues
+
+* Fixed the exported `hipfort::hipsparse` CMake target.
+
+### **ROCm Systems Profiler** (0.1.1)
+
+#### Resolved issues
+
+* Fixed an error when building from source on some SUSE and RHEL systems when using the `ROCPROFSYS_BUILD_DYNINST` option.
+
+### **ROCProfiler** (2.0.0)
+
+#### Changed
+
+* Replaced `CU_UTILIZATION` metric with `SIMD_UTILIZATION` for better accuracy.
+
+#### Resolved issues
+
+* Fixed the `VALUBusy` and `SALUBusy` activity metrics for accuracy on MI300.
+
+### **ROCprofiler-SDK** (0.5.0)
+
+#### Added
+
+* Support for system-wide collection of SQ counters across all HSA processes.
+
+#### Changed
+
+* `rocprofiler_sample_device_counting_service` API updated to return counter output immediately, when called in synchronous mode.
 
 ## ROCm known issues
 
 ROCm known issues are noted on {fab}`github` [GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). For known
 issues related to individual components, review the [Detailed component changes](#detailed-component-changes).
 
-### Zero value is displayed in ROCTx aggregated statistics
+## ROCm resolved issues
 
-The ROCTx markers are standalone markers within the ROCProfiler-SDK library. Each marker reports only a single timestamp, which is recorded as the `start_timestamp` and `end_timestamp`. As a result, the value for aggregated statistics presented in `TotalDurationNs`, `maxNs`, and `minNs`, is zero. The zero value indicates that the actual execution time is not associated with the markers, which is an expected behavior. See [GitHub issue #4396](https://github.com/ROCm/ROCm/issues/4396).
+The following are previously known issues resolved in this release. For resolved issues related to
+individual components, review the [Detailed component changes](#detailed-component-changes).
+
+### TransferBench packages not functional
+
+Issue with TransferBench packages not being compiled properly has been fixed. For more information, See [GitHub issue #4081](https://github.com/ROCm/ROCm/issues/4081).
+
+### ROCm Compute Profiler CTest failure in CI
+
+When running the ROCm Compute Profiler (`rocprof-compute`) CTest in the Azure CI environment, the
+`rocprof-compute` execution test failed. This issue was due to an outdated test file that was not renamed
+(`omniperf` to `rocprof-compute`), and the `ROCM_PATH` environment variable not being set in
+the Azure CI environment, resulting in the tool being unable to extract chip information as expected.
+This issue has been fixed in the ROCm 6.3.2 release. See [GitHub issue #4085](https://github.com/ROCm/ROCm/issues/4085).
+
+### MIVisionX memory access fault in Canny edge detection
+
+An issue where Canny edge detection kernels accessed out-of-bounds memory locations while
+computing gradient intensities on edge pixels has been fixed. This issue was isolated to
+Canny-specific use cases on Instinct MI300 series accelerators. See [GitHub issue #4086](https://github.com/ROCm/ROCm/issues/4086).
+
+### AMD VCN instability with rocDecode
+
+A firmware crash on gfx942 devices when AMD Video Core Next (VCN) was used for rocDecode operations has been resolved.
 
 ## ROCm upcoming changes
 
 The following changes to the ROCm software stack are anticipated for future releases.
 
-### ROCTracer and ROCProfiler (rocprof and rocprofv2) deprecation
-
-Development and support for ROCTracer and ROCProfiler (`rocprof` and `rocprofv2`) will phase out in favor of ROCprofiler-SDK (`rocprofv3`) in upcoming ROCm releases. Going forward, only critical defect fixes will be addressed for older versions of profiling tools and libraries. Upgrade to the latest version of ROCprofiler-SDK (`rocprofv3`) library to ensure continued support and access to new features.
-
 ### AMDGPU wavefront size compiler macro deprecation
 
 The `__AMDGCN_WAVEFRONT_SIZE__` macro will be deprecated in an upcoming
 release. It is recommended to remove any use of this macro. For more information, see [AMDGPU
-support](https://rocm.docs.amd.com/projects/llvm-project/en/docs-6.3.3/LLVM/clang/html/AMDGPUSupport.html).
+support](https://rocm.docs.amd.com/projects/llvm-project/en/docs-6.3.2/LLVM/clang/html/AMDGPUSupport.html).
 
 ### HIPCC Perl scripts deprecation
 

default.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.3.3"
+    <default revision="refs/tags/rocm-6.3.2"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />

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

@@ -1,14 +1,14 @@
-ROCm Version,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
-      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,
-      ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
-      ,,,,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
-      ,"RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
-      ,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
-      ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
+ROCm Version,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
+      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,,
+      ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
+      ,,,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
+      ,"RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
+      ,RHEL 8.10,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
+      ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
       ,,,,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
-      ,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,,,
-,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,,,,,,,,,,
-,Azure Linux 3.0 [#mi300x-past-60]_,Azure Linux 3.0 [#mi300x-past-60]_,,,,,,,,,,,
+      ,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,,,
+,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,,,,,,,,,,,
+,Azure Linux 3.0 [#mi300x-past-60]_,,,,,,,,,,,,
       ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,,
       :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
       ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
@@ -18,103 +18,103 @@ ROCm Version,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.2, 6.1.1, 6.1.
       ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,
       :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
       ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
-      ,gfx942,gfx942,gfx942,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
+      ,gfx942,gfx942,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
       ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
       ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
 ,,,,,,,,,,,,,
       FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"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"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"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","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
-      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
+      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"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>`,"2.17.0, 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>`,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,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
       ,,,,,,,,,,,,,
       THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,,,,
       `UCC <https://github.com/ROCm/ucc>`_,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
-      `UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
+      `UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
       ,,,,,,,,,,,,,
       THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      Thrust,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      CUB,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      Thrust,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      CUB,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
 ,,,,,,,,,,,,,
       KMD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      Tested user space versions,"6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
+      Tested user space versions,"6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
       ,,,,,,,,,,,,,
       ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,
       :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
-      :doc:`MIGraphX <amdmigraphx:index>`,2.11.0,2.11.0,2.11.0,2.11.0,2.10.0,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
-      :doc:`MIOpen <miopen:index>`,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`MIVisionX <mivisionx:index>`,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
-      :doc:`rocAL <rocal:index>`,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`rocDecode <rocdecode:index>`,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
-      :doc:`rocJPEG <rocjpeg:index>`,0.6.0,0.6.0,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`rocPyDecode <rocpydecode:index>`,0.2.0,0.2.0,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A
-      :doc:`RPP <rpp:index>`,1.9.1,1.9.1,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
+      :doc:`MIGraphX <amdmigraphx:index>`,2.11.0,2.11.0,2.11.0,2.10.0,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
+      :doc:`MIOpen <miopen:index>`,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`MIVisionX <mivisionx:index>`,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
+      :doc:`rocAL <rocal:index>`,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`rocDecode <rocdecode:index>`,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
+      :doc:`rocJPEG <rocjpeg:index>`,0.6.0,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`rocPyDecode <rocpydecode:index>`,0.2.0,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`RPP <rpp:index>`,1.9.1,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
       ,,,,,,,,,,,,,
       COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      :doc:`RCCL <rccl:index>`,2.21.5,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
+      :doc:`RCCL <rccl:index>`,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
       ,,,,,,,,,,,,,
       MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,
       `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
-      :doc:`hipBLAS <hipblas:index>`,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
-      :doc:`hipBLASLt <hipblaslt:index>`,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
-      :doc:`hipFFT <hipfft:index>`,1.0.17,1.0.17,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
-      :doc:`hipfort <hipfort:index>`,0.5.1,0.5.1,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
-      :doc:`hipRAND <hiprand:index>`,2.11.1,2.11.1,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
-      :doc:`hipSOLVER <hipsolver:index>`,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
-      :doc:`hipSPARSE <hipsparse:index>`,3.1.2,3.1.2,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.2,0.2.2,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
-      :doc:`rocALUTION <rocalution:index>`,3.2.1,3.2.1,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
-      :doc:`rocBLAS <rocblas:index>`,4.3.0,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
-      :doc:`rocFFT <rocfft:index>`,1.0.31,1.0.31,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
-      :doc:`rocRAND <rocrand:index>`,3.2.0,3.2.0,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
-      :doc:`rocSOLVER <rocsolver:index>`,3.27.0,3.27.0,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
-      :doc:`rocSPARSE <rocsparse:index>`,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
-      :doc:`rocWMMA <rocwmma:index>`,1.6.0,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
-      :doc:`Tensile <tensile:src/index>`,4.42.0,4.42.0,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
+      :doc:`hipBLAS <hipblas:index>`,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
+      :doc:`hipBLASLt <hipblaslt:index>`,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
+      :doc:`hipFFT <hipfft:index>`,1.0.17,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
+      :doc:`hipfort <hipfort:index>`,0.5.1,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
+      :doc:`hipRAND <hiprand:index>`,2.11.1,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
+      :doc:`hipSOLVER <hipsolver:index>`,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
+      :doc:`hipSPARSE <hipsparse:index>`,3.1.2,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.2,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
+      :doc:`rocALUTION <rocalution:index>`,3.2.1,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
+      :doc:`rocBLAS <rocblas:index>`,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
+      :doc:`rocFFT <rocfft:index>`,1.0.31,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
+      :doc:`rocRAND <rocrand:index>`,3.2.0,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
+      :doc:`rocSOLVER <rocsolver:index>`,3.27.0,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
+      :doc:`rocSPARSE <rocsparse:index>`,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
+      :doc:`rocWMMA <rocwmma:index>`,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
+      :doc:`Tensile <tensile:src/index>`,4.42.0,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
       ,,,,,,,,,,,,,
       PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      :doc:`hipCUB <hipcub:index>`,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`hipTensor <hiptensor:index>`,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
-      :doc:`rocPRIM <rocprim:index>`,3.3.0,3.3.0,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`rocThrust <rocthrust:index>`,3.3.0,3.3.0,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      :doc:`hipCUB <hipcub:index>`,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`hipTensor <hiptensor:index>`,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
+      :doc:`rocPRIM <rocprim:index>`,3.3.0,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`rocThrust <rocthrust:index>`,3.3.0,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
       ,,,,,,,,,,,,,
       SUPPORT LIBS,,,,,,,,,,,,,
-      `hipother <https://github.com/ROCm/hipother>`_,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
-      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
+      `hipother <https://github.com/ROCm/hipother>`_,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
       ,,,,,,,,,,,,,
       SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      :doc:`AMD SMI <amdsmi:index>`,24.7.1,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
+      :doc:`AMD SMI <amdsmi:index>`,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
       :doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
       :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.4.0,7.4.0,7.4.0,7.4.0,7.3.0,7.3.0,7.3.0,7.3.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
-      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.4.0,7.4.0,7.4.0,7.3.0,7.3.0,7.3.0,7.3.0,7.2.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
+      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
       ,,,,,,,,,,,,,
       PERFORMANCE TOOLS,,,,,,,,,,,,,
       :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.0.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.2,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60303,2.0.60302,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCTracer <roctracer:index>`,4.1.60303,4.1.60302,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60302,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
+      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCTracer <roctracer:index>`,4.1.60302,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
       ,,,,,,,,,,,,,
       DEVELOPMENT TOOLS,,,,,,,,,,,,,
-      :doc:`HIPIFY <hipify:index>`,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.0,0.77.0,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,15.2.0,15.2.0,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,N/A,N/A
+      :doc:`HIPIFY <hipify:index>`,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.0,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,15.2.0,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
       :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
       ,,,,,,,,,,,,,
       COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
-      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      `Flang <https://github.com/ROCm/flang>`_,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`llvm-project <llvm-project:index>`,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
+      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      `Flang <https://github.com/ROCm/flang>`_,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`llvm-project <llvm-project:index>`,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
 ,,,,,,,,,,,,,
       RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,,,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      :doc:`HIP <hip:index>`,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      :doc:`HIP <hip:index>`,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
       `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
-      :doc:`ROCr Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
+      :doc:`ROCr Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0

docs/compatibility/compatibility-matrix.rst

@@ -23,7 +23,7 @@ compatibility and system requirements.
 .. container:: format-big-table
 
   .. csv-table::
-      :header: "ROCm Version", "6.3.3", "6.3.2", "6.2.0"
+      :header: "ROCm Version", "6.3.2", "6.3.1", "6.2.0"
       :stub-columns: 1
 
       :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04
@@ -33,7 +33,7 @@ compatibility and system requirements.
       ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5"
       ,Oracle Linux 8.10 [#mi300x]_,Oracle Linux 8.10 [#mi300x]_,Oracle Linux 8.9 [#mi300x]_
       ,Debian 12 [#single-node]_,Debian 12 [#single-node]_,
-      ,Azure Linux 3.0 [#mi300x]_,Azure Linux 3.0 [#mi300x]_,
+      ,Azure Linux 3.0 [#mi300x]_,,
       ,.. _architecture-support-compatibility-matrix:,,
       :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3
       ,CDNA2,CDNA2,CDNA2
@@ -83,7 +83,7 @@ compatibility and system requirements.
       :doc:`hipBLAS <hipblas:index>`,2.3.0,2.3.0,2.2.0
       :doc:`hipBLASLt <hipblaslt:index>`,0.10.0,0.10.0,0.8.0
       :doc:`hipFFT <hipfft:index>`,1.0.17,1.0.17,1.0.14
-      :doc:`hipfort <hipfort:index>`,0.5.1,0.5.1,0.4.0
+      :doc:`hipfort <hipfort:index>`,0.5.1,0.5.0,0.4.0
       :doc:`hipRAND <hiprand:index>`,2.11.1,2.11.1,2.11.0
       :doc:`hipSOLVER <hipsolver:index>`,2.3.0,2.3.0,2.2.0
       :doc:`hipSPARSE <hipsparse:index>`,3.1.2,3.1.2,3.1.1
@@ -104,8 +104,8 @@ compatibility and system requirements.
       :doc:`rocThrust <rocthrust:index>`,3.3.0,3.3.0,3.0.1
       ,,,
       SUPPORT LIBS,,,
-      `hipother <https://github.com/ROCm/hipother>`_,6.3.42134,6.3.42134,6.2.41133
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.3,6.3.2,6.2.0
+      `hipother <https://github.com/ROCm/hipother>`_,6.3.42134,6.3.42133,6.2.41133
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.2,6.3.1,6.2.0
       `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_,20240607.1.4246
       ,,,
       SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix:,,
@@ -118,41 +118,40 @@ compatibility and system requirements.
       PERFORMANCE TOOLS,,,
       :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0
       :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.0.0,3.0.0,2.0.1
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.2,0.1.1,1.11.2
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60303,2.0.60302,2.0.60200
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.1,0.1.0,1.11.2
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60302,2.0.60301,2.0.60200
       :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.5.0,0.5.0,0.4.0
-      :doc:`ROCTracer <roctracer:index>`,4.1.60303,4.1.60302,4.1.60200
+      :doc:`ROCTracer <roctracer:index>`,4.1.60302,4.1.60301,4.1.60200
       ,,,
       DEVELOPMENT TOOLS,,,
-      :doc:`HIPIFY <hipify:index>`,18.0.0.25012,18.0.0.25012,18.0.0.24232
+      :doc:`HIPIFY <hipify:index>`,18.0.0.25012,18.0.0.24491,18.0.0.24232
       :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.13.0
       :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.0,0.77.0,0.76.0
       :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,15.2.0,15.2.0,14.2.0
       `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.4.0
       :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3
       ,,,
-      COMPILERS,.. _compilers-support-compatibility-matrix:,,
+      COMPILERS,.. _compilers-support-compatibility-matrix:,..
       `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A
       :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1
-      `Flang <https://github.com/ROCm/flang>`_,18.0.0.25012,18.0.0.25012,18.0.0.24232
-      :doc:`llvm-project <llvm-project:index>`,18.0.0.25012,18.0.0.25012,18.0.0.24232
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.25012,18.0.0.25012,18.0.0.24232
+      `Flang <https://github.com/ROCm/flang>`_,18.0.0.25012,18.0.0.24491,18.0.0.24232
+      :doc:`llvm-project <llvm-project:index>`,18.0.0.25012,18.0.0.24491,18.0.0.24232
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.25012,18.0.0.24491,18.0.0.24232
       ,,,
-      RUNTIMES,.. _runtime-support-compatibility-matrix:,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42134,6.3.42134,6.2.41133
-      :doc:`HIP <hip:index>`,6.3.42134,6.3.42134,6.2.41133
+      RUNTIMES,.. _runtime-support-compatibility-matrix:,..
+      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42134,6.3.42133,6.2.41133
+      :doc:`HIP <hip:index>`,6.3.42134,6.3.42133,6.2.41133
       `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0
       :doc:`ROCr Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.13.0
 
 
 
-
 .. rubric:: Footnotes
 
 .. [#mi300x] Oracle Linux and Azure Linux are supported only on AMD Instinct MI300X.
 .. [#single-node] Debian 12 is supported only on AMD Instinct MI300X for single-node functionality. 
 .. [#mi300_620] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
-.. [#kfd_support] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported.
+.. [#kfd_support] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported. 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] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
 
 .. _OS-kernel-versions:
@@ -228,5 +227,5 @@ Expand for full historical view of:
    .. [#mi300_610-past-60] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
    .. [#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.
-   .. [#kfd_support-past-60] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported.
+   .. [#kfd_support-past-60] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software 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

@@ -4,8 +4,6 @@
    :description: JAX compatibility
    :keywords: GPU, JAX compatibility
 
-.. version-set:: rocm_version latest
-
 *******************************************************************************
 JAX compatibility
 *******************************************************************************
@@ -121,8 +119,7 @@ Critical ROCm libraries for JAX
 
 The functionality of JAX with ROCm is determined by its underlying library
 dependencies. These critical ROCm components affect the capabilities,
-performance, and feature set available to developers. The versions described
-are available in ROCm :version:`rocm_version`.
+performance, and feature set available to developers.
 
 .. list-table::
     :header-rows: 1
@@ -132,7 +129,7 @@ are available in ROCm :version:`rocm_version`.
       - Purpose
       - Used in
     * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - :version-ref:`hipBLAS rocm_version`
+      - 2.3.0
       - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
         matrix and vector operations.
       - Matrix multiplication in ``jax.numpy.matmul``, ``jax.lax.dot`` and
@@ -141,7 +138,7 @@ are available in ROCm :version:`rocm_version`.
         ``jax.numpy.einsum`` with matrix-multiplication patterns algebra
         operations.
     * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - :version-ref:`hipBLASLt rocm_version`
+      - 0.10.0
       - hipBLASLt is an extension of hipBLAS, providing additional
         features like epilogues fused into the matrix multiplication kernel or
         use of integer tensor cores.
@@ -150,7 +147,7 @@ are available in ROCm :version:`rocm_version`.
         operations, mixed-precision support, and hardware-specific
         optimizations.
     * - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - :version-ref:`hipCUB rocm_version`
+      - 3.3.0
       - Provides a C++ template library for parallel algorithms for reduction,
         scan, sort and select.
       - Reduction functions (``jax.numpy.sum``, ``jax.numpy.mean``,
@@ -158,23 +155,23 @@ are available in ROCm :version:`rocm_version`.
         (``jax.numpy.cumsum``, ``jax.numpy.cumprod``) and sorting
         (``jax.numpy.sort``, ``jax.numpy.argsort``).
     * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - :version-ref:`hipFFT rocm_version`
+      - 1.0.17
       - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
       - Used in functions like ``jax.numpy.fft``.
     * - `hipRAND <https://github.com/ROCm/hipRAND>`_
-      - :version-ref:`hipRAND rocm_version`
+      - 2.11.0
       - Provides fast random number generation for GPUs.
       - The ``jax.random.uniform``, ``jax.random.normal``,
         ``jax.random.randint`` and ``jax.random.split``.
     * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - :version-ref:`hipSOLVER rocm_version`
+      - 2.3.0
       - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
         singular value decompositions (SVD).
       - Solving linear systems (``jax.numpy.linalg.solve``), matrix
         factorizations, SVD (``jax.numpy.linalg.svd``) and eigenvalue problems
         (``jax.numpy.linalg.eig``).
     * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - :version-ref:`hipSPARSE rocm_version`
+      - 3.1.2
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse matrix multiplication (``jax.numpy.matmul``), sparse
@@ -182,28 +179,28 @@ are available in ROCm :version:`rocm_version`.
         (``jax.experimental.sparse.dot``), sparse linear system solvers and
         sparse data handling.
     * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
-      - :version-ref:`hipSPARSELt rocm_version`
+      - 0.2.2
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse matrix multiplication (``jax.numpy.matmul``), sparse
         matrix-vector and matrix-matrix products
         (``jax.experimental.sparse.dot``) and sparse linear system solvers.
     * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - :version-ref:`MIOpen rocm_version`
+      - 3.3.0
       - Optimized for deep learning primitives such as convolutions, pooling,
         normalization, and activation functions.
       - Speeds up convolutional neural networks (CNNs), recurrent neural
         networks (RNNs), and other layers. Used in operations like
         ``jax.nn.conv``, ``jax.nn.relu``, and ``jax.nn.batch_norm``.
     * - `RCCL <https://github.com/ROCm/rccl>`_
-      - :version-ref:`RCCL rocm_version`
+      - 2.21.5
       - Optimized for multi-GPU communication for operations like  all-reduce,
         broadcast, and scatter.
       - Distribute computations across multiple GPU with ``pmap`` and
         ``jax.distributed``. XLA automatically uses rccl when executing
         operations across multiple GPUs on AMD hardware.
     * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - :version-ref:`rocThrust rocm_version`
+      - 3.3.0
       - Provides a C++ template library for parallel algorithms like sorting,
         reduction, and scanning.
       - Reduction operations like ``jax.numpy.sum``, ``jax.pmap`` for

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

@@ -4,8 +4,6 @@
     :description: PyTorch compatibility
     :keywords: GPU, PyTorch compatibility
 
-.. version-set:: rocm_version latest
-
 ********************************************************************************
 PyTorch compatibility
 ********************************************************************************
@@ -58,7 +56,7 @@ Docker image compatibility
 
 AMD validates and publishes ready-made `PyTorch images <https://hub.docker.com/r/rocm/pytorch>`_
 with ROCm backends on Docker Hub. The following Docker image tags and
-associated inventories are validated for `ROCm 6.3.3 <https://repo.radeon.com/rocm/apt/6.3.3/>`_.
+associated inventories are validated for `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_.
 Click the |docker-icon| icon to view the image on Docker Hub.
 
 .. list-table:: PyTorch Docker image components
@@ -79,26 +77,11 @@ Click the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3.3_ubuntu24.04_py3.12_pytorch_release_2.4.0/images/sha256-6c798857b2c9526b44ba535710b93a1737546acea79b53a93c646195c272f1d5"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu24.04_py3.12_pytorch_release_2.4.0/images/sha256-98ddf20333bd01ff749b8092b1190ee369a75d3b8c71c2fac80ffdcb1a98d529?context=explore"><i class="fab fa-docker fa-lg"></i></a>
 
       - `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/>`_
-      - `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>`_
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
-      - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
-      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
-      - `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/rocm6.3.3_ubuntu22.04_py3.10_pytorch_release_2.4.0/images/sha256-a09b21248133876fc8912a5ff4e6ee2c8d62b14120313e426b3dadda5702713d"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
-      - 22.04
-      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `3.12 <https://www.python.org/downloads/release/python-3128/>`_
       - `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>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
@@ -109,11 +92,11 @@ Click the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3.3_ubuntu22.04_py3.9_pytorch_release_2.4.0/images/sha256-963187534467f0f9da77996762fc1d112a6faa5372277c348a505533e7876ec8"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.4.0/images/sha256-402c9b4f1a6b5a81c634a1932b56cbe01abb699cfcc7463d226276997c6cf8ea?context=explore"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
       - 22.04
-      - `3.9.21 <https://www.python.org/downloads/release/python-3921/>`_
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
       - `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>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
@@ -124,11 +107,26 @@ Click the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3.3_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-952f2621bd2bf3078bef19061e05b209105a82a7908e7e6cdf85014938a4d93a"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.9_pytorch_release_2.4.0/images/sha256-e0608b55d408c3bfe5c19fdd57a4ced3e0eb3a495b74c309980b60b156c526dd?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 22.04
+      - `3.9.18 <https://www.python.org/downloads/release/python-3918/>`_
+      - `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>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `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/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-652cf25263d05b1de548222970aeb76e60b12de101de66751264709c0d0ff9d8?context=explore"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`_
       - 22.04
-      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
       - `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/2.13.0>`_
@@ -139,7 +137,7 @@ Click the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3.3_ubuntu22.04_py3.10_pytorch_release_2.2.1/images/sha256-a2fe20e170feb9e05da3e5728bb98e40d08567e137be8e6ba797962ed2852608"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.2.1/images/sha256-051976f26beab8f9aa65d999e3ad546c027b39240a0cc3ee81b114a9024f2912?context=explore"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
       - 22.04
@@ -154,7 +152,7 @@ Click the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3.3_ubuntu20.04_py3.9_pytorch_release_2.2.1/images/sha256-7f231937c897cca5f89e360be33c70a2017d60f62d1fbe81292be48c15fe345b"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu20.04_py3.9_pytorch_release_2.2.1/images/sha256-88c839a364d109d3748c100385bfa100d28090d25118cc723fd0406390ab2f7e?context=explore"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
       - 20.04
@@ -169,14 +167,14 @@ Click the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3.3_ubuntu22.04_py3.9_pytorch_release_1.13.1/images/sha256-616a47758004f91951e2da6c1fe291f903de65a7b2318d4b18359b48fe3032f4"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.9_pytorch_release_1.13.1/images/sha256-994424ed07a63113f79dd9aa72159124c00f5fbfe18127151e6658f7d0b6f821?context=explore"><i class="fab fa-docker fa-lg"></i></a>
 
       - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
       - 22.04
       - `3.9.21 <https://www.python.org/downloads/release/python-3921/>`_
       - `1.0.0 <https://github.com/ROCm/apex/tree/release/1.0.0>`_
       - `0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
-      - `2.19.0 <https://github.com/tensorflow/tensorboard/tree/2.19>`_
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
       - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
       - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
@@ -184,7 +182,7 @@ Click the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3.3_ubuntu20.04_py3.9_pytorch_release_1.13.1/images/sha256-a2cfb365aea58b84595e241ffdb0d5ef3e6566e98c10b5499f4aa29983a74ea2"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu20.04_py3.9_pytorch_release_1.13.1/images/sha256-7b8139fe40a9aeb4bca3aecd15c22c1fa96e867d93479fa3a24fdeeeeafa1219?context=explore"><i class="fab fa-docker fa-lg"></i></a>
 
       - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
       - 20.04
@@ -202,8 +200,7 @@ Critical ROCm libraries for PyTorch
 
 The functionality of PyTorch with ROCm is determined by its underlying library
 dependencies. These critical ROCm components affect the capabilities,
-performance, and feature set available to developers. The versions described
-are available in ROCm :version:`rocm_version`.
+performance, and feature set available to developers.
 
 .. list-table::
     :header-rows: 1
@@ -213,28 +210,28 @@ are available in ROCm :version:`rocm_version`.
       - Purpose
       - Used in
     * - `Composable Kernel <https://github.com/ROCm/composable_kernel>`_
-      - :version-ref:`"Composable Kernel" rocm_version`
+      - 1.1.0
       - Enables faster execution of core operations like matrix multiplication
         (GEMM), convolutions and transformations.
       - Speeds up ``torch.permute``, ``torch.view``, ``torch.matmul``,
         ``torch.mm``, ``torch.bmm``, ``torch.nn.Conv2d``, ``torch.nn.Conv3d``
         and ``torch.nn.MultiheadAttention``.
     * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - :version-ref:`hipBLAS rocm_version`
+      - 2.3.0
       - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
         matrix and vector operations.
       - Supports operations like matrix multiplication, matrix-vector products,
         and tensor contractions. Utilized in both dense and batched linear
         algebra operations.
     * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - :version-ref:`hipBLASLt rocm_version`
+      - 0.10.0
       - hipBLASLt is an extension of the hipBLAS library, providing additional
         features like epilogues fused into the matrix multiplication kernel or
         use of integer tensor cores.
       - It accelerates operations like ``torch.matmul``, ``torch.mm``, and the
         matrix multiplications used in convolutional and linear layers.
     * - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - :version-ref:`hipCUB rocm_version`
+      - 3.3.0
       - Provides a C++ template library for parallel algorithms for reduction,
         scan, sort and select.
       - Supports operations like ``torch.sum``, ``torch.cumsum``, ``torch.sort``
@@ -242,93 +239,93 @@ are available in ROCm :version:`rocm_version`.
         irregular shapes often involve scanning, sorting, and filtering, which
         hipCUB handles efficiently.
     * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - :version-ref:`hipFFT rocm_version`
+      - 1.0.17
       - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
       - Used in functions like the ``torch.fft`` module.
     * - `hipRAND <https://github.com/ROCm/hipRAND>`_
-      - :version-ref:`hipRAND rocm_version`
+      - 2.11.0
       - Provides fast random number generation for GPUs.
       - The ``torch.rand``, ``torch.randn`` and stochastic layers like
         ``torch.nn.Dropout``.
     * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - :version-ref:`hipSOLVER rocm_version`
+      - 2.3.0
       - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
         singular value decompositions (SVD).
       - Supports functions like ``torch.linalg.solve``,
         ``torch.linalg.eig``, and ``torch.linalg.svd``.
     * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - :version-ref:`hipSPARSE rocm_version`
+      - 3.1.2
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse tensor operations ``torch.sparse``.
     * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
-      - :version-ref:`hipSPARSELt rocm_version`
+      - 0.2.2
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse tensor operations ``torch.sparse``.
     * - `hipTensor <https://github.com/ROCm/hipTensor>`_
-      - :version-ref:`hipTensor rocm_version`
+      - 1.4.0
       - Optimizes for high-performance tensor operations, such as contractions.
       - Accelerates tensor algebra, especially in deep learning and scientific
         computing.
     * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - :version-ref:`MIOpen rocm_version`
+      - 3.3.0
       - Optimizes deep learning primitives such as convolutions, pooling,
         normalization, and activation functions.
       - Speeds up convolutional neural networks (CNNs), recurrent neural
         networks (RNNs), and other layers. Used in operations like
         ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
     * - `MIGraphX <https://github.com/ROCm/AMDMIGraphX>`_
-      - :version-ref:`MIGraphX rocm_version`
+      - 2.11.0
       - Adds graph-level optimizations, ONNX models and mixed precision support
         and enable Ahead-of-Time (AOT) Compilation.
       - Speeds up inference models and executes ONNX models for
         compatibility with other frameworks.
         ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
     * - `MIVisionX <https://github.com/ROCm/MIVisionX>`_
-      - :version-ref:`MIVisionX rocm_version`
+      - 3.1.0
       - Optimizes acceleration for computer vision and AI workloads like
         preprocessing, augmentation, and inferencing.
       - Faster data preprocessing and augmentation pipelines for datasets like
         ImageNet or COCO and easy to integrate into PyTorch's ``torch.utils.data``
         and ``torchvision`` workflows.
     * - `rocAL <https://github.com/ROCm/rocAL>`_
-      - :version-ref:`rocAL rocm_version`
+      - 2.1.0
       - Accelerates the data pipeline by offloading intensive preprocessing and
         augmentation tasks. rocAL is part of MIVisionX.
       - Easy to integrate into PyTorch's ``torch.utils.data`` and
         ``torchvision`` data load workloads.
     * - `RCCL <https://github.com/ROCm/rccl>`_
-      - :version-ref:`RCCL rocm_version`
+      - 2.21.5
       - Optimizes for multi-GPU communication for operations like AllReduce and
         Broadcast.
       - Distributed data parallel training (``torch.nn.parallel.DistributedDataParallel``).
         Handles communication in multi-GPU setups.
     * - `rocDecode <https://github.com/ROCm/rocDecode>`_
-      - :version-ref:`rocDecode rocm_version`
+      - 0.8.0
       - Provides hardware-accelerated data decoding capabilities, particularly
         for image, video, and other dataset formats.
       - Can be integrated in ``torch.utils.data``, ``torchvision.transforms``
         and ``torch.distributed``.
     * - `rocJPEG <https://github.com/ROCm/rocJPEG>`_
-      - :version-ref:`rocJPEG rocm_version`
+      - 0.6.0
       - Provides hardware-accelerated JPEG image decoding and encoding.
       - GPU accelerated ``torchvision.io.decode_jpeg`` and
         ``torchvision.io.encode_jpeg`` and can be integrated in
         ``torch.utils.data`` and ``torchvision``.
     * - `RPP <https://github.com/ROCm/RPP>`_
-      - :version-ref:`RPP rocm_version`
+      - 1.9.1
       - Speeds up data augmentation, transformation, and other preprocessing steps.
       - Easy to integrate into PyTorch's ``torch.utils.data`` and
         ``torchvision`` data load workloads.
     * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - :version-ref:`rocThrust rocm_version`
+      - 3.3.0
       - Provides a C++ template library for parallel algorithms like sorting,
         reduction, and scanning.
       - Utilized in backend operations for tensor computations requiring
         parallel processing.
     * - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
-      - :version-ref:`rocWMMA rocm_version`
+      - 1.6.0
       - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
         multiplication (GEMM) and accumulation operations with mixed precision
         support.

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

@@ -4,8 +4,6 @@
     :description: TensorFlow compatibility
     :keywords: GPU, TensorFlow compatibility
 
-.. version-set:: rocm_version latest
-
 *******************************************************************************
 TensorFlow compatibility
 *******************************************************************************
@@ -56,7 +54,7 @@ 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 6.3.3 <https://repo.radeon.com/rocm/apt/6.3.3/>`_. Click
+validated for `ROCm 6.3.1 <https://repo.radeon.com/rocm/apt/6.3.1/>`_. Click
 the |docker-icon| icon to view the image on Docker Hub.
 
 .. list-table:: TensorFlow Docker image components
@@ -70,47 +68,47 @@ the |docker-icon| icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.3-py3.12-tf2.17-dev/images/sha256-fd2653f436880366cc874aa24264ca9dabd892d76ccb63fb807debba459bcaaf"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.12-tf2.17.0-dev/images/sha256-804121ee4985718277ba7dcec53c57bdade130a1ef42f544b6c48090ad379c17"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
       - `tensorflow-rocm 2.17.0 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.17.0-cp312-cp312-manylinux_2_28_x86_64.whl>`__
       - dev
-      - `Python 3.12.4 <https://www.python.org/downloads/release/python-3124/>`_
+      - `Python 3.12 <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/rocm6.3.3-py3.10-tf2.17-dev/images/sha256-8a5eb7443798935dd269575e2abae847b702e1dfb06766ab84f081a6314d8b95"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.10-tf2.17.0-dev/images/sha256-776837ffa945913f6c466bfe477810a11453d21d5b6afb200be1c36e48fbc08e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
       - `tensorflow-rocm 2.17.0 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.17.0-cp310-cp310-manylinux_2_28_x86_64.whl>`__
       - dev
-      - `Python 3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`_
+      - `Python 3.10 <https://www.python.org/downloads/release/python-31012/>`_
+      - `TensorBoard 2.17.0 <https://github.com/tensorflow/tensorboard/tree/2.17.0>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.3-py3.12-tf2.16-dev/images/sha256-8fc939b10cdd6d2b11407474880d4c8ab2b52ab6e2d1743c921fc2adbfd0422f"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.12-tf2.16.2-dev/images/sha256-c793e1483e30809c3c28fc5d7805bedc033c73da224f839fff370717cb100944"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
       - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
       - dev
-      - `Python 3.12.4 <https://www.python.org/downloads/release/python-3124/>`_
+      - `Python 3.12 <https://www.python.org/downloads/release/python-3124/>`_
       - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.3-py3.10-tf2.16-dev/images/sha256-a4cc6ab23d59fdf5459ceac1f0a603e6c16ae7f885d30e42c0c2b3ac60c2ad10"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.10-tf2.16.0-dev/images/sha256-263e78414ae85d7bcd52a025a94131d0a279872a45ed632b9165336dfdcd4443"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
       - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.16.2-cp310-cp310-manylinux_2_28_x86_64.whl>`__
       - dev
-      - `Python 3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `Python 3.10 <https://www.python.org/downloads/release/python-31012/>`_
       - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.3-py3.10-tf2.15-dev/images/sha256-60887c488421184adcb60b9ed4f72a8bd7bdb64d238e50943ca7cbde38e4aa48"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.10-tf2.15.0-dev/images/sha256-479046a8477ca701a9494a813ab17e8ab4f6baa54641e65dc8d07629f1e6a880"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
       - `tensorflow-rocm 2.15.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.15.1-cp310-cp310-manylinux_2_28_x86_64.whl>`_
       - dev
-      - `Python 3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `Python 3.10 <https://www.python.org/downloads/release/python-31012/>`_
       - `TensorBoard 2.15.2 <https://github.com/tensorflow/tensorboard/tree/2.15.2>`_
 
 Critical ROCm libraries for TensorFlow
@@ -119,8 +117,7 @@ Critical ROCm libraries for TensorFlow
 TensorFlow depends on multiple components and the supported features of those
 components can affect the TensorFlow ROCm supported feature set. The versions
 in the following table refer to the first TensorFlow version where the ROCm
-library was introduced as a dependency. The versions described
-are available in ROCm :version:`rocm_version`.
+library was introduced as a dependency.
 
 .. list-table::
     :widths: 25, 10, 35, 30
@@ -131,43 +128,43 @@ are available in ROCm :version:`rocm_version`.
       - Purpose
       - Used in
     * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - :version-ref:`hipBLAS rocm_version`
+      - 2.3.0
       - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
         matrix and vector operations.
       - Accelerates operations like ``tf.matmul``, ``tf.linalg.matmul``, and
         other matrix multiplications commonly used in neural network layers.
     * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - :version-ref:`hipBLASLt rocm_version`
+      - 0.10.0
       - Extends hipBLAS with additional optimizations like fused kernels and
         integer tensor cores.
       - Optimizes matrix multiplications and linear algebra operations used in
         layers like dense, convolutional, and RNNs in TensorFlow.
     * - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - :version-ref:`hipCUB rocm_version`
+      - 3.3.0
       - Provides a C++ template library for parallel algorithms for reduction,
         scan, sort and select.
       - Supports operations like ``tf.reduce_sum``, ``tf.cumsum``, ``tf.sort``
         and other tensor operations in TensorFlow, especially those involving
         scanning, sorting, and filtering.
     * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - :version-ref:`hipFFT rocm_version`
+      - 1.0.17
       - Accelerates Fast Fourier Transforms (FFT) for signal processing tasks.
       - Used for operations like signal processing, image filtering, and
         certain types of neural networks requiring FFT-based transformations.
     * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - :version-ref:`hipSOLVER rocm_version`
+      - 2.3.0
       - Provides GPU-accelerated direct linear solvers for dense and sparse
         systems.
       - Optimizes linear algebra functions such as solving systems of linear
         equations, often used in optimization and training tasks.
     * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - :version-ref:`hipSPARSE rocm_version`
+      - 3.1.2
       - Optimizes sparse matrix operations for efficient computations on sparse
         data.
       - Accelerates sparse matrix operations in models with sparse weight
         matrices or activations, commonly used in neural networks.
     * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - :version-ref:`MIOpen rocm_version`
+      - 3.3.0
       - Provides optimized deep learning primitives such as convolutions,
         pooling,
         normalization, and activation functions.
@@ -175,13 +172,13 @@ are available in ROCm :version:`rocm_version`.
         in TensorFlow for layers like ``tf.nn.conv2d``, ``tf.nn.relu``, and
         ``tf.nn.lstm_cell``.
     * - `RCCL <https://github.com/ROCm/rccl>`_
-      - :version-ref:`RCCL rocm_version`
+      - 2.21.5
       - Optimizes for multi-GPU communication for operations like AllReduce and
         Broadcast.
       - Distributed data parallel training (``tf.distribute.MirroredStrategy``).
         Handles communication in multi-GPU setups.
     * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - :version-ref:`rocThrust rocm_version`
+      - 3.3.0
       - Provides a C++ template library for parallel algorithms like sorting,
         reduction, and scanning.
       - Reduction operations like ``tf.reduce_sum``, ``tf.cumsum`` for computing

docs/compatibility/pytorch-compatibility.rst

@@ -0,0 +1,916 @@
+.. meta::
+    :description: PyTorch compatibility
+    :keywords: GPU, PyTorch compatibility
+
+********************************************************************************
+PyTorch compatibility
+********************************************************************************
+
+`PyTorch <https://pytorch.org/>`_ is an open-source tensor library designed for
+deep learning. PyTorch on ROCm provides mixed-precision and large-scale training
+using `MIOpen <https://github.com/ROCm/MIOpen>`_ and
+`RCCL <https://github.com/ROCm/rccl>`_ libraries.
+
+ROCm support for PyTorch is upstreamed into the official PyTorch repository. Due to independent
+compatibility considerations, this results in two distinct release cycles for PyTorch on ROCm:
+
+- ROCm PyTorch release:
+
+  - Provides the latest version of ROCm but doesn't immediately support the latest stable PyTorch
+    version.
+
+  - Offers :ref:`Docker images <pytorch-docker-compat>` with ROCm and PyTorch
+    pre-installed.
+
+  - ROCm PyTorch repository: `<https://github.com/rocm/pytorch>`__
+
+  - See the :doc:`ROCm PyTorch installation guide <rocm-install-on-linux:install/3rd-party/pytorch-install>` to get started.
+
+- Official PyTorch release:
+
+  - Provides the latest stable version of PyTorch but doesn't immediately support the latest ROCm version.
+
+  - Official PyTorch repository: `<https://github.com/pytorch/pytorch>`__
+
+  - See the `Nightly and latest stable version installation guide <https://pytorch.org/get-started/locally/>`_
+    or `Previous versions <https://pytorch.org/get-started/previous-versions/>`_ to get started.
+
+The upstream PyTorch includes an automatic HIPification solution that automatically generates HIP
+source code from the CUDA backend. This approach allows PyTorch to support ROCm without requiring
+manual code modifications.
+
+ROCm's development is aligned with the stable release of PyTorch while upstream PyTorch testing uses
+the stable release of ROCm to maintain consistency.
+
+.. _pytorch-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+AMD validates and publishes ready-made `PyTorch <https://hub.docker.com/r/rocm/pytorch>`_
+images with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories are validated for `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_.
+
+.. list-table:: PyTorch Docker image components
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker
+      - PyTorch
+      - Ubuntu
+      - Python
+      - Apex
+      - torchvision
+      - TensorBoard
+      - MAGMA
+      - UCX
+      - OMPI
+      - OFED
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu24.04_py3.12_pytorch_release_2.4.0/images/sha256-98ddf20333bd01ff749b8092b1190ee369a75d3b8c71c2fac80ffdcb1a98d529?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12 <https://www.python.org/downloads/release/python-3128/>`_
+      - `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>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `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/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.4.0/images/sha256-402c9b4f1a6b5a81c634a1932b56cbe01abb699cfcc7463d226276997c6cf8ea?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
+      - `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>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `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/rocm6.3_ubuntu22.04_py3.9_pytorch_release_2.4.0/images/sha256-e0608b55d408c3bfe5c19fdd57a4ced3e0eb3a495b74c309980b60b156c526dd?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 22.04
+      - `3.9 <https://www.python.org/downloads/release/python-3918/>`_
+      - `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>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `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/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-652cf25263d05b1de548222970aeb76e60b12de101de66751264709c0d0ff9d8?context=explore"><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 <https://www.python.org/downloads/release/python-31016/>`_
+      - `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/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `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/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.2.1/images/sha256-051976f26beab8f9aa65d999e3ad546c027b39240a0cc3ee81b114a9024f2912?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
+      - `1.2.0 <https://github.com/ROCm/apex/tree/release/1.2.0>`_
+      - `0.17.1 <https://github.com/pytorch/vision/tree/v0.17.1>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `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/rocm6.3_ubuntu20.04_py3.9_pytorch_release_2.2.1/images/sha256-88c839a364d109d3748c100385bfa100d28090d25118cc723fd0406390ab2f7e?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
+      - 20.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.2.0 <https://github.com/ROCm/apex/tree/release/1.2.0>`_
+      - `0.17.1 <https://github.com/pytorch/vision/tree/v0.17.1>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `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/rocm6.3_ubuntu22.04_py3.9_pytorch_release_1.13.1/images/sha256-994424ed07a63113f79dd9aa72159124c00f5fbfe18127151e6658f7d0b6f821?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
+      - 22.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.0.0 <https://github.com/ROCm/apex/tree/release/1.0.0>`_
+      - `0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `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/rocm6.3_ubuntu20.04_py3.9_pytorch_release_1.13.1/images/sha256-7b8139fe40a9aeb4bca3aecd15c22c1fa96e867d93479fa3a24fdeeeeafa1219?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
+      - 20.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.0.0 <https://github.com/ROCm/apex/tree/release/1.0.0>`_
+      - `0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `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>`_
+
+Critical ROCm libraries for PyTorch
+================================================================================
+
+The functionality of PyTorch with ROCm is shaped by its underlying library
+dependencies. These critical ROCm components affect the capabilities,
+performance, and feature set available to developers.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - Version
+      - Purpose
+      - Used in
+    * - `Composable Kernel <https://github.com/ROCm/composable_kernel>`_
+      - 1.1.0
+      - Enables faster execution of core operations like matrix multiplication
+        (GEMM), convolutions and transformations.
+      - Speeds up ``torch.permute``, ``torch.view``, ``torch.matmul``,
+        ``torch.mm``, ``torch.bmm``, ``torch.nn.Conv2d``, ``torch.nn.Conv3d``
+        and ``torch.nn.MultiheadAttention``. 
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
+      - 2.3.0
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations like matrix multiplication, matrix-vector products,
+        and tensor contractions. Utilized in both dense and batched linear
+        algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
+      - 0.10.0
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+      - It accelerates operations like ``torch.matmul``, ``torch.mm``, and the
+        matrix multiplications used in convolutional and linear layers.
+    * - `hipCUB <https://github.com/ROCm/hipCUB>`_
+      - 3.3.0
+      - Provides a C++ template library for parallel algorithms for reduction,
+        scan, sort and select.
+      - Supports operations like ``torch.sum``, ``torch.cumsum``, ``torch.sort``
+        and ``torch.topk``. Operations on sparse tensors or tensors with
+        irregular shapes often involve scanning, sorting, and filtering, which
+        hipCUB handles efficiently.
+    * - `hipFFT <https://github.com/ROCm/hipFFT>`_
+      - 1.0.17
+      - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
+      - Used in functions like the ``torch.fft`` module.
+    * - `hipRAND <https://github.com/ROCm/hipRAND>`_
+      - 2.11.0
+      - Provides fast random number generation for GPUs.
+      - The ``torch.rand``, ``torch.randn`` and stochastic layers like 
+        ``torch.nn.Dropout``.
+    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
+      - 2.3.0
+      - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
+        singular value decompositions (SVD).
+      - Supports functions like ``torch.linalg.solve``,
+        ``torch.linalg.eig``, and ``torch.linalg.svd``.
+    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
+      - 3.1.2
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
+      - 0.2.2
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipTensor <https://github.com/ROCm/hipTensor>`_
+      - 1.4.0
+      - Optimizes for high-performance tensor operations, such as contractions.
+      - Accelerates tensor algebra, especially in deep learning and scientific
+        computing.
+    * - `MIOpen <https://github.com/ROCm/MIOpen>`_
+      - 3.3.0
+      - Optimizes deep learning primitives such as convolutions, pooling,
+        normalization, and activation functions.
+      - Speeds up convolutional neural networks (CNNs), recurrent neural
+        networks (RNNs), and other layers. Used in operations like
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIGraphX <https://github.com/ROCm/AMDMIGraphX>`_
+      - 2.11.0
+      - Add graph-level optimizations, ONNX models and mixed precision support
+        and enable Ahead-of-Time (AOT) Compilation.
+      - Speeds up inference models and executes ONNX models for
+        compatibility with other frameworks.
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIVisionX <https://github.com/ROCm/MIVisionX>`_
+      - 3.1.0
+      - Optimizes acceleration for computer vision and AI workloads like
+        preprocessing, augmentation, and inferencing.
+      - Faster data preprocessing and augmentation pipelines for datasets like
+        ImageNet or COCO and easy to integrate into PyTorch's ``torch.utils.data``
+        and ``torchvision`` workflows.
+    * - `rocAL <https://github.com/ROCm/rocAL>`_
+      - 2.1.0
+      - Accelerates the data pipeline by offloading intensive preprocessing and
+        augmentation tasks. rocAL is part of MIVisionX.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads.
+    * - `RCCL <https://github.com/ROCm/rccl>`_
+      - 2.21.5
+      - Optimizes for multi-GPU communication for operations like AllReduce and
+        Broadcast.
+      - Distributed data parallel training (``torch.nn.parallel.DistributedDataParallel``).
+        Handles communication in multi-GPU setups.
+    * - `rocDecode <https://github.com/ROCm/rocDecode>`_
+      - 0.8.0
+      - Provide hardware-accelerated data decoding capabilities, particularly
+        for image, video, and other dataset formats.
+      - Can be integrated in ``torch.utils.data``, ``torchvision.transforms``
+        and ``torch.distributed``.
+    * - `rocJPEG <https://github.com/ROCm/rocJPEG>`_
+      - 0.6.0
+      - Provide hardware-accelerated JPEG image decoding and encoding.
+      - GPU accelerated ``torchvision.io.decode_jpeg`` and
+        ``torchvision.io.encode_jpeg`` and can be integrated in
+        ``torch.utils.data`` and ``torchvision``.
+    * - `RPP <https://github.com/ROCm/RPP>`_
+      - 1.9.1
+      - Speed up data augmentation, transformation, and other preprocessing step.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads.
+    * - `rocThrust <https://github.com/ROCm/rocThrust>`_
+      - 3.3.0
+      - Provides a C++ template library for parallel algorithms like sorting,
+        reduction, and scanning.
+      - Utilized in backend operations for tensor computations requiring
+        parallel processing.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
+      - 1.6.0
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Linear layers (``torch.nn.Linear``), convolutional layers
+        (``torch.nn.Conv2d``), attention layers, general tensor operations that
+        involve matrix products, such as ``torch.matmul``, ``torch.bmm``, and
+        more.
+
+Supported and unsupported features
+================================================================================
+
+The following section maps GPU-accelerated PyTorch features to their supported
+ROCm and PyTorch versions.
+
+torch
+--------------------------------------------------------------------------------
+
+`torch <https://pytorch.org/docs/stable/index.html>`_ is the central module of
+PyTorch, providing data structures for multi-dimensional tensors and
+implementing mathematical operations on them. It also includes utilities for
+efficient serialization of tensors and arbitrary data types, along with various
+other tools.
+
+Tensor data types
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The data type of a tensor is specified using the ``dtype`` attribute or argument, and PyTorch supports a wide range of data types for different use cases.
+
+The following table lists `torch.Tensor <https://pytorch.org/docs/stable/tensors.html>`_'s single data types:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``torch.float8_e4m3fn``
+      - 8-bit floating point, e4m3
+      - 2.3
+      - 5.5
+    * - ``torch.float8_e5m2``
+      - 8-bit floating point, e5m2
+      - 2.3
+      - 5.5
+    * - ``torch.float16`` or ``torch.half``
+      - 16-bit floating point
+      - 0.1.6
+      - 2.0
+    * - ``torch.bfloat16``
+      - 16-bit floating point
+      - 1.6
+      - 2.6
+    * - ``torch.float32`` or ``torch.float``
+      - 32-bit floating point
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.float64`` or ``torch.double``
+      - 64-bit floating point
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.complex32`` or ``torch.chalf``
+      - PyTorch provides native support for 32-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.complex64`` or ``torch.cfloat``
+      - PyTorch provides native support for 64-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.complex128`` or ``torch.cdouble``
+      - PyTorch provides native support for 128-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.uint8``
+      - 8-bit integer (unsigned)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.uint16``
+      - 16-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.uint32``
+      - 32-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.uint64``
+      - 32-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.int8``
+      - 8-bit integer (signed)
+      - 1.12
+      - 5.0
+    * - ``torch.int16`` or ``torch.short``
+      - 16-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.int32`` or ``torch.int``
+      - 32-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.int64`` or ``torch.long``
+      - 64-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.bool``
+      - Boolean
+      - 1.2
+      - 2.0
+    * - ``torch.quint8``
+      - Quantized 8-bit integer (unsigned)
+      - 1.8
+      - 5.0
+    * - ``torch.qint8``
+      - Quantized 8-bit integer (signed)
+      - 1.8
+      - 5.0
+    * - ``torch.qint32``
+      - Quantized 32-bit integer (signed)
+      - 1.8
+      - 5.0
+    * - ``torch.quint4x2``
+      - Quantized 4-bit integer (unsigned)
+      - 1.8
+      - 5.0
+
+.. note::
+
+  Unsigned types aside from ``uint8`` are currently only have limited support in
+  eager mode (they primarily exist to assist usage with ``torch.compile``).
+
+  The :doc:`ROCm precision support page <rocm:reference/precision-support>`
+  collected the native HW support of different data types.
+
+torch.cuda
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``torch.cuda`` in PyTorch is a module that provides utilities and functions for
+managing and utilizing AMD and NVIDIA GPUs. It enables GPU-accelerated
+computations, memory management, and efficient execution of tensor operations,
+leveraging ROCm and CUDA as the underlying frameworks.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - Device management
+      - Utilities for managing and interacting with GPUs.
+      - 0.4.0
+      - 3.8
+    * - Tensor operations on GPU
+      - Perform tensor operations such as addition and matrix multiplications on
+        the GPU.
+      - 0.4.0
+      - 3.8
+    * - Streams and events
+      - Streams allow overlapping computation and communication for optimized
+        performance, events enable synchronization.
+      - 1.6.0
+      - 3.8
+    * - Memory management
+      - Functions to manage and inspect memory usage like
+        ``torch.cuda.memory_allocated()``, ``torch.cuda.max_memory_allocated()``,
+        ``torch.cuda.memory_reserved()`` and ``torch.cuda.empty_cache()``.
+      - 0.3.0
+      - 1.9.2
+    * - Running process lists of memory management
+      - Return a human-readable printout of the running processes and their GPU
+        memory use for a given device with functions like 
+        ``torch.cuda.memory_stats()`` and ``torch.cuda.memory_summary()``.
+      - 1.8.0
+      - 4.0
+    * - Communication collectives
+      - A set of APIs that enable efficient communication between multiple GPUs,
+        allowing for distributed computing and data parallelism.
+      - 1.9.0
+      - 5.0
+    * - ``torch.cuda.CUDAGraph``
+      - Graphs capture sequences of GPU operations to minimize kernel launch
+        overhead and improve performance.
+      - 1.10.0
+      - 5.3
+    * - TunableOp
+      - A mechanism that allows certain operations to be more flexible and
+        optimized for performance. It enables automatic tuning of kernel
+        configurations and other settings to achieve the best possible
+        performance based on the specific hardware (GPU) and workload.
+      - 2.0
+      - 5.4
+    * - NVIDIA Tools Extension (NVTX)
+      - Integration with NVTX for profiling and debugging GPU performance using
+        NVIDIA's Nsight tools.
+      - 1.8.0
+      - ❌
+    * - Lazy loading NVRTC
+      - Delays JIT compilation with NVRTC until the code is explicitly needed.
+      - 1.13.0
+      - ❌
+    * - Jiterator (beta)
+      - Jiterator allows asynchronous data streaming into computation streams
+        during training loops.
+      - 1.13.0
+      - 5.2
+
+.. Need to validate and extend.
+
+torch.backends.cuda
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``torch.backends.cuda`` is a PyTorch module that provides configuration options
+and flags to control the behavior of CUDA or ROCm operations. It is part of the
+PyTorch backend configuration system, which allows users to fine-tune how
+PyTorch interacts with the CUDA or ROCm environment.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``cufft_plan_cache``
+      - Manages caching of GPU FFT plans to optimize repeated FFT computations.
+      - 1.7.0
+      - 5.0
+    * - ``matmul.allow_tf32``
+      - Enables or disables the use of TensorFloat-32 (TF32) precision for
+        faster matrix multiplications on GPUs with Tensor Cores.
+      - 1.10.0
+      - ❌
+    * - ``matmul.allow_fp16_reduced_precision_reduction``
+      - Reduced precision reductions (e.g., with fp16 accumulation type) are
+        allowed with fp16 GEMMs.
+      - 2.0
+      - ❌
+    * - ``matmul.allow_bf16_reduced_precision_reduction``
+      - Reduced precision reductions are allowed with bf16 GEMMs.
+      - 2.0
+      - ❌
+    * - ``enable_cudnn_sdp``
+      - Globally enables cuDNN SDPA's kernels within SDPA.
+      - 2.0
+      - ❌
+    * - ``enable_flash_sdp``
+      - Globally enables or disables FlashAttention for SDPA.
+      - 2.1
+      - ❌
+    * - ``enable_mem_efficient_sdp``
+      - Globally enables or disables Memory-Efficient Attention for SDPA.
+      - 2.1
+      - ❌
+    * - ``enable_math_sdp``
+      - Globally enables or disables the PyTorch C++ implementation within SDPA.
+      - 2.1
+      - ❌
+
+.. Need to validate and extend.
+
+torch.backends.cudnn
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Supported ``torch`` options:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``allow_tf32``
+      - TensorFloat-32 tensor cores may be used in cuDNN convolutions on NVIDIA
+        Ampere or newer GPUs.
+      - 1.12.0
+      - ❌
+    * - ``deterministic``
+      - A bool that, if True, causes cuDNN to only use deterministic
+        convolution algorithms.
+      - 1.12.0
+      - 6.0
+
+Automatic mixed precision: torch.amp
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+PyTorch that automates the process of using both 16-bit (half-precision,
+float16) and 32-bit (single-precision, float32) floating-point types in model
+training and inference.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - Autocasting
+      - Instances of autocast serve as context managers or decorators that allow
+        regions of your script to run in mixed precision.
+      - 1.9
+      - 2.5
+    * - Gradient scaling
+      - To prevent underflow, “gradient scaling” multiplies the network’s
+        loss(es) by a scale factor and invokes a backward pass on the scaled
+        loss(es). Gradients flowing backward through the network are then
+        scaled by the same factor. In other words, gradient values have a
+        larger magnitude, so they don’t flush to zero.
+      - 1.9
+      - 2.5
+    * - CUDA op-specific behavior
+      - These ops always go through autocasting whether they are invoked as part
+        of a ``torch.nn.Module``, as a function, or as a ``torch.Tensor`` method. If
+        functions are exposed in multiple namespaces, they go through
+        autocasting regardless of the namespace.
+      - 1.9
+      - 2.5
+
+Distributed library features
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The PyTorch distributed library includes a collective of parallelism modules, a
+communications layer, and infrastructure for launching and debugging large
+training jobs. See :ref:`rocm-for-ai-pytorch-distributed` for more information.
+
+The Distributed Library feature in PyTorch provides tools and APIs for building
+and running distributed machine learning workflows. It allows training models
+across multiple processes, GPUs, or nodes in a cluster, enabling efficient use
+of computational resources and scalability for large-scale tasks.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - TensorPipe
+      - TensorPipe is a point-to-point communication library integrated into
+        PyTorch for distributed training. It is designed to handle tensor data
+        transfers efficiently between different processes or devices, including
+        those on separate machines.
+      - 1.8
+      - 5.4
+    * - Gloo
+      - Gloo is designed for multi-machine and multi-GPU setups, enabling
+        efficient communication and synchronization between processes. Gloo is
+        one of the default backends for PyTorch's Distributed Data Parallel
+        (DDP) and RPC frameworks, alongside other backends like NCCL and MPI.
+      - 1.0
+      - 2.0
+
+torch.compiler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``torch.compiler`` (AOT Autograd)
+      - Autograd captures not only the user-level code, but also backpropagation,
+        which results in capturing the backwards pass “ahead-of-time”. This
+        enables acceleration of both forwards and backwards pass using
+        ``TorchInductor``.
+      - 2.0
+      - 5.3
+    * - ``torch.compiler`` (TorchInductor)
+      - The default ``torch.compile`` deep learning compiler that generates fast
+        code for multiple accelerators and backends. You need to use a backend
+        compiler to make speedups through ``torch.compile`` possible. For AMD,
+        NVIDIA, and Intel GPUs, it leverages OpenAI Triton as the key building block.
+      - 2.0
+      - 5.3
+
+torchaudio
+--------------------------------------------------------------------------------
+
+The `torchaudio <https://pytorch.org/audio/stable/index.html>`_ library provides
+utilities for processing audio data in PyTorch, such as audio loading,
+transformations, and feature extraction.
+
+To ensure GPU-acceleration with ``torchaudio.transforms``, you need to move audio
+data (waveform tensor) explicitly to GPU using ``.to('cuda')``.
+
+The following ``torchaudio`` features are GPU-accelerated.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since torchaudio version
+      - Since ROCm
+    * - ``torchaudio.transforms.Spectrogram``
+      - Generate spectrogram of an input waveform using STFT.
+      - 0.6.0
+      - 4.5
+    * - ``torchaudio.transforms.MelSpectrogram``
+      - Generate the mel-scale spectrogram of raw audio signals.
+      - 0.9.0
+      - 4.5
+    * - ``torchaudio.transforms.MFCC``
+      - Extract of MFCC features.
+      - 0.9.0
+      - 4.5
+    * - ``torchaudio.transforms.Resample``
+      - Resample a signal from one frequency to another
+      - 0.9.0
+      - 4.5
+
+torchvision
+--------------------------------------------------------------------------------
+
+The `torchvision <https://pytorch.org/vision/stable/index.html>`_ library
+provide datasets, model architectures, and common image transformations for
+computer vision.
+
+The following ``torchvision`` features are GPU-accelerated.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since torchvision version
+      - Since ROCm
+    * - ``torchvision.transforms.functional``
+      - Provides GPU-compatible transformations for image preprocessing like
+        resize, normalize, rotate and crop.
+      - 0.2.0
+      - 4.0
+    * - ``torchvision.ops``
+      - GPU-accelerated operations for object detection and segmentation tasks.
+        ``torchvision.ops.roi_align``, ``torchvision.ops.nms`` and
+        ``box_convert``.
+      - 0.6.0
+      - 3.3
+    * - ``torchvision.models`` with ``.to('cuda')``
+      - ``torchvision`` provides several pre-trained models (ResNet, Faster
+        R-CNN, Mask R-CNN, ...) that can run on CUDA for faster inference and
+        training.
+      - 0.1.6
+      - 2.x
+    * - ``torchvision.io``
+      - Video decoding and frame extraction using GPU acceleration with NVIDIA’s
+        NVDEC and nvJPEG (rocJPEG) on CUDA-enabled GPUs.
+      - 0.4.0
+      - 6.3
+
+torchtext
+--------------------------------------------------------------------------------
+
+The `torchtext <https://pytorch.org/text/stable/index.html>`_ library provides
+utilities for processing and working with text data in PyTorch, including
+tokenization, vocabulary management, and text embeddings. torchtext supports
+preprocessing pipelines and integration with PyTorch models, simplifying the
+implementation of natural language processing (NLP) tasks.
+
+To leverage GPU acceleration in torchtext, you need to move tensors
+explicitly to the GPU using ``.to('cuda')``.
+
+* torchtext does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+torchtune
+--------------------------------------------------------------------------------
+
+The `torchtune <https://pytorch.org/torchtune/stable/index.html>`_ library for
+authoring, fine-tuning and experimenting with LLMs.
+
+* Usage: It works out-of-the-box, enabling developers to fine-tune ROCm PyTorch solutions.
+
+* Only official release exists.
+
+torchserve
+--------------------------------------------------------------------------------
+
+The `torchserve <https://pytorch.org/torchserve/>`_ is a PyTorch domain library
+for common sparsity and parallelism primitives needed for large-scale recommender
+systems.
+
+* torchtext does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+torchrec
+--------------------------------------------------------------------------------
+
+The `torchrec <https://pytorch.org/torchrec/>`_ is a PyTorch domain library for
+common sparsity and parallelism primitives needed for large-scale recommender
+systems.
+
+* torchrec does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+Unsupported PyTorch features
+----------------------------
+
+The following are GPU-accelerated PyTorch features not currently supported by ROCm.
+
+.. list-table::
+    :widths: 30, 60, 10
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+    * - APEX batch norm
+      - Use APEX batch norm instead of PyTorch batch norm.
+      - 1.6.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_tf32``
+      - A bool that controls whether TensorFloat-32 tensor cores may be used in
+        matrix multiplications.
+      - 1.7
+    * - ``torch.cuda`` / NVIDIA Tools Extension (NVTX)
+      - Integration with NVTX for profiling and debugging GPU performance using
+        NVIDIA's Nsight tools.
+      - 1.7.0
+    * - ``torch.cuda`` / Lazy loading NVRTC
+      - Delays JIT compilation with NVRTC until the code is explicitly needed.
+      - 1.8.0
+    * - ``torch-tensorrt``
+      - Integrate TensorRT library for optimizing and deploying PyTorch models.
+        ROCm does not have equialent library for TensorRT.
+      - 1.9.0
+    * - ``torch.backends`` / ``cudnn.allow_tf32``
+      - TensorFloat-32 tensor cores may be used in cuDNN convolutions.
+      - 1.10.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_fp16_reduced_precision_reduction``
+      - Reduced precision reductions with fp16 accumulation type are
+        allowed with fp16 GEMMs.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_bf16_reduced_precision_reduction``
+      - Reduced precision reductions are allowed with bf16 GEMMs.
+      - 2.0
+    * - ``torch.nn.functional`` / ``scaled_dot_product_attention`` 
+      - Flash attention backend for SDPA to accelerate attention computation in
+        transformer-based models.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``enable_cudnn_sdp``
+      - Globally enables cuDNN SDPA's kernels within SDPA.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``enable_flash_sdp``
+      - Globally enables or disables FlashAttention for SDPA.
+      - 2.1
+    * - ``torch.backends.cuda`` / ``enable_mem_efficient_sdp``
+      - Globally enables or disables Memory-Efficient Attention for SDPA.
+      - 2.1
+    * - ``torch.backends.cuda`` / ``enable_math_sdp``
+      - Globally enables or disables the PyTorch C++ implementation within SDPA.
+      - 2.1
+    * - Dynamic parallelism
+      - PyTorch itself does not directly expose dynamic parallelism as a core
+        feature. Dynamic parallelism allow GPU threads to launch additional
+        threads which can be reached using custom operations via the
+        ``torch.utils.cpp_extension`` module.
+      - Not a core feature
+    * - Unified memory support in PyTorch
+      - Unified Memory is not directly exposed in PyTorch's core API, it can be
+        utilized effectively through custom CUDA extensions or advanced
+        workflows.
+      - Not a core feature
+
+Use cases and recommendations
+================================================================================
+
+* :doc:`Using ROCm for AI: training a model </how-to/rocm-for-ai/train-a-model>` provides
+  guidance on how to leverage the ROCm platform for training AI models. It covers the steps, tools, and best practices
+  for optimizing training workflows on AMD GPUs using PyTorch features.
+
+* :doc:`Single-GPU fine-tuning and inference </how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference>`
+  describes and demonstrates how to use the ROCm platform for the fine-tuning and inference of
+  machine learning models, particularly large language models (LLMs), on systems with a single AMD
+  Instinct MI300X accelerator. This page provides a detailed guide for setting up, optimizing, and
+  executing fine-tuning and inference workflows in such environments.
+
+* :doc:`Multi-GPU fine-tuning and inference optimization </how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference>`
+  describes and demonstrates the fine-tuning and inference of machine learning models on systems
+  with multi MI300X accelerators.
+
+* The :doc:`Instinct MI300X workload optimization guide </how-to/tuning-guides/mi300x/workload>` provides detailed
+  guidance on optimizing workloads for the AMD Instinct MI300X accelerator using ROCm. This guide is aimed at helping
+  users achieve optimal performance for deep learning and other high-performance computing tasks on the MI300X
+  accelerator.
+
+* The :doc:`Inception with PyTorch documentation </conceptual/ai-pytorch-inception>`
+  describes how PyTorch integrates with ROCm for AI workloads It outlines the use of PyTorch on the ROCm platform and
+  focuses on how to efficiently leverage AMD GPU hardware for training and inference tasks in AI applications.
+
+For more use cases and recommendations, see `ROCm PyTorch blog posts <https://rocm.blogs.amd.com/blog/tag/pytorch.html>`_

docs/conceptual/gpu-arch.md

@@ -32,7 +32,7 @@ architecture.
 
 * [AMD Instinct™ MI250 microarchitecture](./gpu-arch/mi250.md)
 * [AMD Instinct MI200/CDNA2 ISA](https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf)
-* [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna2-white-paper.pdf)
+* [White paper](https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf)
 * [Performance counters](./gpu-arch/mi300-mi200-performance-counters.rst)
 
 :::
@@ -45,7 +45,7 @@ architecture.
 
 * [AMD Instinct™ MI100 microarchitecture](./gpu-arch/mi100.md)
 * [AMD Instinct MI100/CDNA1 ISA](https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf)
-* [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna-white-paper.pdf)
+* [White paper](https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf)
 
 :::
 
@@ -55,6 +55,7 @@ architecture.
 * [AMD RDNA3 ISA](https://www.amd.com/system/files/TechDocs/rdna3-shader-instruction-set-architecture-feb-2023_0.pdf)
 * [AMD RDNA2 ISA](https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf)
 * [AMD RDNA ISA](https://www.amd.com/system/files/TechDocs/rdna-shader-instruction-set-architecture.pdf)
+* [AMD RDNA Architecture White Paper](https://www.amd.com/system/files/documents/rdna-whitepaper.pdf)
 
 :::
 

docs/conf.py

@@ -6,8 +6,6 @@
 
 import os
 import shutil
-import sys
-from pathlib import Path
 
 shutil.copy2("../RELEASE.md", "./about/release-notes.md")
 
@@ -32,15 +30,15 @@ if os.environ.get("READTHEDOCS", "") == "True":
 project = "ROCm Documentation"
 author = "Advanced Micro Devices, Inc."
 copyright = "Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved."
-version = "6.3.3"
-release = "6.3.3"
+version = "6.3.2"
+release = "6.3.2"
 setting_all_article_info = True
 all_article_info_os = ["linux", "windows"]
 all_article_info_author = ""
 
 # pages with specific settings
 article_pages = [
-    {"file": "about/release-notes", "os": ["linux"], "date": "2025-02-19"},
+    {"file": "about/release-notes", "os": ["linux"], "date": "2025-01-28"},
     {"file": "compatibility/compatibility-matrix", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/tensorflow-compatibility", "os": ["linux"]},
@@ -52,8 +50,8 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/training/index", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/train-a-model", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/prerequisite-system-validation", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/training/benchmark-docker/megatron-lm", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/train-a-model/benchmark-docker/megatron-lm", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/train-a-model/benchmark-docker/pytorch-training", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/scale-model-training", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/fine-tuning/index", "os": ["linux"]},
@@ -68,7 +66,7 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/inference/llm-inference-frameworks", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/vllm-benchmark", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/deploy-your-model", "os": ["linux"]},
-
+    
     {"file": "how-to/rocm-for-ai/inference-optimization/index", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference-optimization/model-quantization", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries", "os": ["linux"]},
@@ -91,16 +89,11 @@ article_pages = [
 
 external_toc_path = "./sphinx/_toc.yml"
 
-# Add the _extensions directory to Python's search path
-sys.path.append(str(Path(__file__).parent / 'extension'))
-
-extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap", "sphinxcontrib.datatemplates", "version-ref"]
-
-compatibility_matrix_file = str(Path(__file__).parent / 'compatibility/compatibility-matrix-historical-6.0.csv')
+extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap"]
 
 external_projects_current_project = "rocm"
 
-# Uncomment if facing rate limit exceed issue with local build
+# Uncomment if facing rate limit exceed issue with local build 
 # external_projects_remote_repository = ""
 
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "https://rocm-stg.amd.com/")
@@ -111,9 +104,8 @@ if os.environ.get("READTHEDOCS", "") == "True":
 html_theme = "rocm_docs_theme"
 html_theme_options = {"flavor": "rocm-docs-home"}
 
-html_static_path = ["sphinx/static/css", "extension/how-to/rocm-for-ai/inference"]
-html_css_files = ["rocm_custom.css", "rocm_rn.css", "vllm-benchmark.css"]
-html_js_files = ["vllm-benchmark.js"]
+html_static_path = ["sphinx/static/css"]
+html_css_files = ["rocm_custom.css", "rocm_rn.css"]
 
 html_title = "ROCm Documentation"
 

docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml

@@ -1,153 +0,0 @@
-vllm_benchmark:
-  unified_docker:
-    latest:
-      pull_tag: rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
-      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9
-      rocm_version: 6.3.1
-      vllm_version: 0.6.6
-      pytorch_version: 2.7.0 (2.7.0a0+git3a58512)
-  model_groups:
-    - group: Llama
-      tag: llama
-      models:
-      - model: Llama 3.1 8B
-        mad_tag: pyt_vllm_llama-3.1-8b
-        model_repo: meta-llama/Llama-3.1-8B-Instruct
-        url: https://huggingface.co/meta-llama/Llama-3.1-8B
-        precision: float16
-      - model: Llama 3.1 70B
-        mad_tag: pyt_vllm_llama-3.1-70b
-        model_repo: meta-llama/Llama-3.1-70B-Instruct
-        url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
-        precision: float16
-      - model: Llama 3.1 405B
-        mad_tag: pyt_vllm_llama-3.1-405b
-        model_repo: meta-llama/Llama-3.1-405B-Instruct
-        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
-        precision: float16
-      - model: Llama 3.2 11B Vision
-        mad_tag: pyt_vllm_llama-3.2-11b-vision-instruct
-        model_repo: meta-llama/Llama-3.2-11B-Vision-Instruct
-        url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
-        precision: float16
-      - model: Llama 2 7B
-        mad_tag: pyt_vllm_llama-2-7b
-        model_repo: meta-llama/Llama-2-7b-chat-hf
-        url: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
-        precision: float16
-      - model: Llama 2 70B
-        mad_tag: pyt_vllm_llama-2-70b
-        model_repo: meta-llama/Llama-2-70b-chat-hf
-        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
-        precision: float16
-      - model: Llama 3.1 70B FP8
-        mad_tag: pyt_vllm_llama-3.1-70b_fp8
-        model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
-        url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
-        precision: float8
-      - model: Llama 3.1 405B FP8
-        mad_tag: pyt_vllm_llama-3.1-405b_fp8
-        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
-        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
-        precision: float8
-    - group: Mistral
-      tag: mistral
-      models:
-      - model: Mixtral MoE 8x7B
-        mad_tag: pyt_vllm_mixtral-8x7b
-        model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
-        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
-        precision: float16
-      - model: Mixtral MoE 8x22B
-        mad_tag: pyt_vllm_mixtral-8x22b
-        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
-        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
-        precision: float16
-      - model: Mistral 7B
-        mad_tag: pyt_vllm_mistral-7b
-        model_repo: mistralai/Mistral-7B-Instruct-v0.3
-        url: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
-        precision: float16
-      - model: Mixtral MoE 8x7B FP8
-        mad_tag: pyt_vllm_mixtral-8x7b_fp8
-        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
-        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
-        precision: float8
-      - model: Mixtral MoE 8x22B FP8
-        mad_tag: pyt_vllm_mixtral-8x22b_fp8
-        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
-        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
-        precision: float8
-      - model: Mistral 7B FP8
-        mad_tag: pyt_vllm_mistral-7b_fp8
-        model_repo: amd/Mistral-7B-v0.1-FP8-KV
-        url: https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV
-        precision: float8
-    - group: Qwen
-      tag: qwen
-      models:
-      - model: Qwen2 7B
-        mad_tag: pyt_vllm_qwen2-7b
-        model_repo: Qwen/Qwen2-7B-Instruct
-        url: https://huggingface.co/Qwen/Qwen2-7B-Instruct
-        precision: float16
-      - model: Qwen2 72B
-        mad_tag: pyt_vllm_qwen2-72b
-        model_repo: Qwen/Qwen2-72B-Instruct
-        url: https://huggingface.co/Qwen/Qwen2-72B-Instruct
-        precision: float16
-    - group: JAIS
-      tag: jais
-      models:
-      - model: JAIS 13B
-        mad_tag: pyt_vllm_jais-13b
-        model_repo: core42/jais-13b-chat
-        url: https://huggingface.co/core42/jais-13b-chat
-        precision: float16
-      - model: JAIS 30B
-        mad_tag: pyt_vllm_jais-30b
-        model_repo: core42/jais-30b-chat-v3
-        url: https://huggingface.co/core42/jais-30b-chat-v3
-        precision: float16
-    - group: DBRX
-      tag: dbrx
-      models:
-      - model: DBRX Instruct
-        mad_tag: pyt_vllm_dbrx-instruct
-        model_repo: databricks/dbrx-instruct
-        url: https://huggingface.co/databricks/dbrx-instruct
-        precision: float16
-      - model: DBRX Instruct FP8
-        mad_tag: pyt_vllm_dbrx_fp8
-        model_repo: amd/dbrx-instruct-FP8-KV
-        url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
-        precision: float8
-    - group: Gemma
-      tag: gemma
-      models:
-      - model: Gemma 2 27B
-        mad_tag: pyt_vllm_gemma-2-27b
-        model_repo: google/gemma-2-27b
-        url: https://huggingface.co/google/gemma-2-27b
-        precision: float16
-    - group: Cohere
-      tag: cohere
-      models:
-      - model: C4AI Command R+ 08-2024
-        mad_tag: pyt_vllm_c4ai-command-r-plus-08-2024
-        model_repo: CohereForAI/c4ai-command-r-plus-08-2024
-        url: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024
-        precision: float16
-      - model: C4AI Command R+ 08-2024 FP8
-        mad_tag: pyt_vllm_command-r-plus_fp8
-        model_repo: amd/c4ai-command-r-plus-FP8-KV
-        url: https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV
-        precision: float8
-    - group: DeepSeek
-      tag: deepseek
-      models:
-      - model: DeepSeek MoE 16B
-        mad_tag: pyt_vllm_deepseek-moe-16b-chat
-        model_repo: deepseek-ai/deepseek-moe-16b-chat
-        url: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
-        precision: float16

docs/extension/how-to/rocm-for-ai/inference/vllm-benchmark.js

@@ -1,212 +0,0 @@
-function ready(proc) {
-  // Check if page is loaded. If so, init.
-  if (document.readyState !== "loading") {
-    proc();
-  } else {
-    // Otherwise, wait for DOMContentLoaded event.
-    document.addEventListener("DOMContentLoaded", proc);
-  }
-}
-
-ready(() => {
-  const ModelPicker = {
-    // Selector strings for DOM elements
-    SELECTORS: {
-      CONTAINER: "#vllm-benchmark-ud-params-picker",
-      MODEL_GROUP_BTN: 'div[data-param-k="model-group"][data-param-v]',
-      MODEL_PARAM_BTN: 'div[data-param-k="model"][data-param-v]',
-      MODEL_DOC: "div.model-doc",
-    },
-    CSS_CLASSES: {
-      HIDDEN: "hidden",
-    },
-    ATTRIBUTES: {
-      PARAM_KEY: "data-param-k", // URL search parameter key (i.e., "model")
-      PARAM_VALUE: "data-param-v", // URL search param value (e.g., "pyt_vllm_llama-3.1-8b", "pyt_vllm_llama-3.1-70b") -- these are MAD model tags
-      PARAM_GROUP: "data-param-group", // Model group (e.g., "llama", "mistral")
-      PARAM_STATE: "data-param-state", // Selection state
-    },
-
-    // Cache DOM elements
-    elements: {
-      container: null,
-      modelGroups: null,
-      modelParams: null,
-      modelDocs: null,
-    },
-
-    data: {
-      availableModels: new Set(),
-      modelsByGroup: new Map(),
-      modelToGroupMap: new Map(),
-      formattedModelClassMap: new Map(), //TODO
-    },
-
-    init() {
-      this.elements.container = document.querySelector(
-        this.SELECTORS.CONTAINER,
-      );
-      if (!this.elements.container) return;
-
-      this.cacheDOMElements();
-      if (!this.validateElements()) return;
-
-      this.buildModelData();
-      this.bindEvents();
-      this.initializeState();
-    },
-
-    cacheDOMElements() {
-      const { CONTAINER, MODEL_GROUP_BTN, MODEL_PARAM_BTN, MODEL_DOC } =
-        this.SELECTORS;
-      this.elements = {
-        container: document.querySelector(CONTAINER),
-        modelGroups: document.querySelectorAll(MODEL_GROUP_BTN),
-        modelParams: document.querySelectorAll(MODEL_PARAM_BTN),
-        modelDocs: document.querySelectorAll(MODEL_DOC),
-      };
-    },
-
-    validateElements() {
-      const { modelGroups, modelParams } = this.elements;
-      if (!modelGroups.length || !modelParams.length) {
-        console.warn("Model picker is missing required elements");
-        return false;
-      }
-      return true;
-    },
-
-    buildModelData() {
-      const { PARAM_VALUE, PARAM_GROUP } = this.ATTRIBUTES;
-
-      this.elements.modelParams.forEach((model) => {
-        const modelTag = model.getAttribute(PARAM_VALUE);
-        const groupTag = model.getAttribute(PARAM_GROUP);
-
-        if (!modelTag || !groupTag) return;
-
-        this.data.availableModels.add(modelTag);
-        this.data.modelToGroupMap.set(modelTag, groupTag);
-
-        // FIXME: this is because Sphinx auto-formats class names to use dashes
-        this.data.formattedModelClassMap.set(
-          modelTag,
-          modelTag.replace(/[^a-zA-Z0-9]/g, "-"),
-        );
-
-        if (!this.data.modelsByGroup.has(groupTag)) {
-          this.data.modelsByGroup.set(groupTag, []);
-        }
-        this.data.modelsByGroup.get(groupTag).push(modelTag);
-      });
-    },
-
-    // Event listeners for user interactions
-    bindEvents() {
-      const handleInteraction = (event) => {
-        const target = event.target.closest(`[${this.ATTRIBUTES.PARAM_KEY}]`);
-        if (!target) return;
-
-        const paramType = target.getAttribute(this.ATTRIBUTES.PARAM_KEY);
-        const paramValue = target.getAttribute(this.ATTRIBUTES.PARAM_VALUE);
-
-        if (paramType === "model") {
-          const groupTag = target.getAttribute(this.ATTRIBUTES.PARAM_GROUP);
-          if (groupTag) this.updateUI(paramValue, groupTag);
-        } else if (paramType === "model-group") {
-          const firstModelInGroup = this.data.modelsByGroup.get(paramValue)
-            ?.[0];
-          if (firstModelInGroup) this.updateUI(firstModelInGroup, paramValue);
-        }
-      };
-
-      this.elements.container.addEventListener("click", handleInteraction);
-      this.elements.container.addEventListener("keydown", (event) => {
-        if (event.key === "Enter" || event.key === " ") {
-          event.preventDefault();
-          handleInteraction(event);
-        }
-      });
-    },
-
-    // Update the page based on the selected model
-    updateUI(modelTag, groupTag) {
-      const validModel = this.setModelSearchParam(modelTag);
-
-      // Update model group buttons
-      this.elements.modelGroups.forEach((group) => {
-        const isSelected =
-          group.getAttribute(this.ATTRIBUTES.PARAM_VALUE) === groupTag;
-        group.setAttribute(
-          this.ATTRIBUTES.PARAM_STATE,
-          isSelected ? "selected" : "",
-        );
-        group.setAttribute("aria-selected", isSelected.toString());
-      });
-
-      // Update model buttons
-      this.elements.modelParams.forEach((model) => {
-        const isInSelectedGroup =
-          model.getAttribute(this.ATTRIBUTES.PARAM_GROUP) === groupTag;
-        const isSelectedModel =
-          model.getAttribute(this.ATTRIBUTES.PARAM_VALUE) === validModel;
-
-        model.classList.toggle(this.CSS_CLASSES.HIDDEN, !isInSelectedGroup);
-        model.setAttribute(
-          this.ATTRIBUTES.PARAM_STATE,
-          isSelectedModel ? "selected" : "",
-        );
-        model.setAttribute("aria-selected", isSelectedModel.toString());
-      });
-
-      // Update visibility of doc sections
-      const formattedClass = this.data.formattedModelClassMap.get(validModel);
-      if (formattedClass) {
-        this.elements.modelDocs.forEach((doc) => {
-          doc.classList.toggle(
-            this.CSS_CLASSES.HIDDEN,
-            !doc.classList.contains(formattedClass),
-          );
-        });
-      }
-    },
-
-    // Get the current model from the URL search parameters.
-    getModelSearchParam() {
-      return new URLSearchParams(location.search).get("model");
-    },
-
-    // Set the model in the URL search parameters, or fallback to the first available one.
-    setModelSearchParam(modelTag) {
-      const defaultModel = [...this.data.availableModels][0];
-      const model = this.data.availableModels.has(modelTag)
-        ? modelTag
-        : defaultModel;
-
-      const searchParams = new URLSearchParams(location.search);
-      searchParams.set("model", model);
-
-      history.replaceState(
-        {},
-        "",
-        `${location.pathname}?${searchParams.toString()}`,
-      );
-      return model;
-    },
-
-    // Initialize the UI state based on the current URL search parameter or default values.
-    initializeState() {
-      const currentModel = this.getModelSearchParam();
-      const validModel = this.setModelSearchParam(currentModel);
-
-      const initialGroup = this.data.modelToGroupMap.get(validModel) ??
-        [...this.data.modelsByGroup.keys()][0];
-
-      if (initialGroup) {
-        this.updateUI(validModel, initialGroup);
-      }
-    },
-  };
-
-  ModelPicker.init();
-});

docs/extension/version-ref.py

@@ -1,266 +0,0 @@
-from docutils import nodes
-from docutils.parsers.rst import Directive
-from sphinx.util import logging
-import csv
-from io import StringIO
-import re
-import shlex
-
-logger = logging.getLogger(__name__)
-
-class VersionReference(nodes.Inline, nodes.TextElement):
-    """Represents an inline version reference."""
-    pass
-
-class VersionSetDirective(Directive):
-    """Directive for setting version references within a page scope."""
-    required_arguments = 2  # name and value
-    optional_arguments = 0
-
-    def run(self):
-        env = self.state.document.settings.env
-        if not hasattr(env, 'doc_version_refs'):
-            env.doc_version_refs = {}
-        current_doc = env.docname
-        if current_doc not in env.doc_version_refs:
-            env.doc_version_refs[current_doc] = {}
-
-        name, value = self.arguments
-        if name.lower() == 'latest':
-            logger.warning('Cannot override the "latest" keyword with version-set')
-            return []
-
-        # Handle 'latest' value by getting the actual version
-        if value.lower() == 'latest':
-            data = getattr(env, 'compatibility_matrix', None)
-            if data:
-                latest_version = get_latest_rocm_version(data)
-                if latest_version:
-                    value = latest_version
-
-        env.doc_version_refs[current_doc][name] = value
-        return []
-
-def clean_library_name(name):
-    """Extract library name from RST formatting."""
-    # Handle :doc: format
-    doc_match = re.search(r':doc:`([^<]+)(?:\s+<[^>]+>)?`', name)
-    if doc_match:
-        return doc_match.group(1).strip()
-
-    # Handle other link formats
-    link_match = re.search(r'`([^<]+)(?:\s+<[^>]+>)?`_?', name)
-    if link_match:
-        return link_match.group(1).strip()
-
-    return name.strip()
-
-def get_latest_rocm_version(data):
-    """Get the latest ROCm version from the matrix headers."""
-    if not data or len(data) == 0:
-        return None
-
-    # Get all column names except 'ROCm Version'
-    columns = [col for col in data[0].keys() if col != 'ROCm Version']
-    # Return the first column name (assumed to be the latest version)
-    return columns[0] if columns else None
-
-def version_role(name, rawtext, text, lineno, inliner, options={}, content=[]):
-    """
-    Role function to print version value.
-    Usage: :version:`version_name`
-    """
-    try:
-        version_name = text.strip()
-        env = inliner.document.settings.env
-
-        if hasattr(env, 'doc_version_refs'):
-            current_doc = env.docname
-            if current_doc in env.doc_version_refs:
-                doc_refs = env.doc_version_refs[current_doc]
-                if version_name in doc_refs:
-                    version = doc_refs[version_name]
-                    node = nodes.Text(version)
-                    return [node], []
-
-        msg = inliner.reporter.warning(
-            f'No version defined for name {version_name}',
-            line=lineno
-        )
-        return [], [msg]
-
-    except Exception as e:
-        msg = inliner.reporter.error(
-            f'Error looking up version: {str(e)}',
-            line=lineno
-        )
-        prb = inliner.problematic(rawtext, rawtext, msg)
-        return [prb], [msg]
-
-def version_ref_role(name, rawtext, text, lineno, inliner, options={}, content=[]):
-    """
-    Role function for version references.
-    Usage: :version-ref:`library_name release`
-           :version-ref:`"library name" release`
-           :version-ref:`library_name latest`
-           :version-ref:`rocm latest`
-    """
-    try:
-        # Parse the text - handle both quoted and unquoted formats
-        if '"' in text:
-            parts = shlex.split(text)
-        else:
-            parts = text.split()
-
-        if len(parts) != 2:
-            msg = inliner.reporter.error(
-                'Version reference must be in format "library_name release" or "\\"library name\\" release"',
-                line=lineno
-            )
-            prb = inliner.problematic(rawtext, rawtext, msg)
-            return [prb], [msg]
-
-        library_name, release = parts
-        env = inliner.document.settings.env
-
-        # Check if release is a version reference in current document
-        if hasattr(env, 'doc_version_refs'):
-            current_doc = env.docname
-            if current_doc in env.doc_version_refs:
-                doc_refs = env.doc_version_refs[current_doc]
-                if release in doc_refs:
-                    release = doc_refs[release]
-
-        # Handle special case for "rocm latest"
-        if library_name.lower() == 'rocm' and release.lower() == 'latest':
-            data = getattr(env, 'compatibility_matrix', None)
-            if not data:
-                raise ValueError("Compatibility matrix not found in environment")
-
-            latest_version = get_latest_rocm_version(data)
-            if latest_version:
-                node = VersionReference()
-                node += nodes.Text(latest_version)
-                return [node], []
-            else:
-                msg = inliner.reporter.warning(
-                    'No ROCm versions found in compatibility matrix',
-                    line=lineno
-                )
-                return [], [msg]
-
-        version = lookup_version(inliner, library_name, release)
-
-        if version:
-            node = VersionReference()
-            node += nodes.Text(version)
-            return [node], []
-        else:
-            msg = inliner.reporter.warning(
-                f'No version found for library {library_name} in release {release}',
-                line=lineno
-            )
-            return [], [msg]
-
-    except Exception as e:
-        msg = inliner.reporter.error(
-            f'Error looking up version: {str(e)}',
-            line=lineno
-        )
-        prb = inliner.problematic(rawtext, rawtext, msg)
-        return [prb], [msg]
-
-def lookup_version(inliner, library_name, release):
-    """Look up the version in the compatibility matrix."""
-    env = inliner.document.settings.env
-    data = getattr(env, 'compatibility_matrix', None)
-
-    if not data:
-        raise ValueError("Compatibility matrix not found in environment")
-
-    # Handle the 'latest' keyword
-    if release.lower() == 'latest':
-        latest_version = get_latest_rocm_version(data)
-        if not latest_version:
-            return None
-        release = latest_version
-
-    # For ROCm, check if the version exists in column headers
-    if library_name.lower() == 'rocm':
-        columns = [col for col in data[0].keys() if col != 'ROCm Version']
-        if release in columns:
-            return release
-        return None
-
-    # Find the library version
-    for row in data:
-        row_lib_name = clean_library_name(row['ROCm Version'])
-        if row_lib_name == library_name:
-            # Get the version, removing any whitespace
-            version = row.get(release, '').strip()
-            if version:
-                return version
-
-    # If not found, try a case-insensitive search
-    for row in data:
-        row_lib_name = clean_library_name(row['ROCm Version'])
-        if row_lib_name.lower() == library_name.lower():
-            version = row.get(release, '').strip()
-            if version:
-                return version
-
-    return None
-
-def visit_version_reference(self, node):
-    self.body.append(f'<span class="version-reference">')
-
-def depart_version_reference(self, node):
-    self.body.append('</span>')
-
-def load_compatibility_matrix(app):
-    """Load the compatibility matrix content from CSV."""
-    if not app.config.compatibility_matrix_file:
-        logger.warning('No compatibility matrix file configured')
-        return
-
-    try:
-        with open(app.config.compatibility_matrix_file, 'r', encoding='utf-8') as f:
-            reader = csv.DictReader(f)
-            app.env.compatibility_matrix = list(reader)
-            logger.info('Successfully loaded compatibility matrix')
-
-            # Debug: print first few rows with their library names
-            for row in list(app.env.compatibility_matrix)[:5]:
-                if 'ROCm Version' in row:
-                    lib_name = clean_library_name(row['ROCm Version'])
-                    logger.debug(f"Loaded library: {lib_name}")
-
-    except Exception as e:
-        logger.error(f'Error loading compatibility matrix: {str(e)}')
-
-def purge_version_refs(app, env, docname):
-    """Remove version references for a document when it is purged"""
-    if hasattr(env, 'doc_version_refs'):
-        if docname in env.doc_version_refs:
-            del env.doc_version_refs[docname]
-
-def setup(app):
-    app.add_node(VersionReference,
-                 html=(visit_version_reference, depart_version_reference))
-    app.add_role('version-ref', version_ref_role)
-    app.add_role('version', version_role)
-    app.add_directive('version-set', VersionSetDirective)
-
-    # Add a config value for the compatibility matrix file path
-    app.add_config_value('compatibility_matrix_file', None, 'env')
-
-    # Connect to the builder-inited event to load the matrix
-    app.connect('builder-inited', load_compatibility_matrix)
-
-    # Connect to env-purge-doc event to clean up document-specific version refs
-    app.connect('env-purge-doc', purge_version_refs)
-
-    return {
-        'parallel_read_safe': True,
-        'parallel_write_safe': True,
-    }

docs/how-to/rocm-for-ai/inference/install.rst

@@ -28,7 +28,7 @@ ROCm supports multiple :doc:`installation methods <rocm-install-on-linux:install
 
 * :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:install/install-methods/package-manager-index>`
 
-* :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/amdgpu-install>`
+* :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/install-methods/amdgpu-installer-index>`
 
 * :ref:`Multi-version installation <rocm-install-on-linux:installation-types>`.
 

docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst

@@ -9,266 +9,422 @@ LLM inference performance validation on AMD Instinct MI300X
 
 .. _vllm-benchmark-unified-docker:
 
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
+a prebuilt, optimized environment for validating large language model (LLM)
+inference performance on the AMD Instinct™ MI300X accelerator. This ROCm vLLM
+Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
+accelerator and includes the following components:
 
-   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
-   {% set model_groups = data.vllm_benchmark.model_groups %}
+* `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
 
-   The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
-   a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on the AMD Instinct™ MI300X accelerator. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
-   accelerator and includes the following components:
+* `vLLM 0.6.6 <https://docs.vllm.ai/en/latest>`_
 
-   * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
+* `PyTorch 2.7.0 (2.7.0a0+git3a58512) <https://github.com/pytorch/pytorch>`_
 
-   * `vLLM {{ unified_docker.vllm_version }} <https://docs.vllm.ai/en/latest>`_
+With this Docker image, you can quickly validate the expected inference
+performance numbers for the MI300X accelerator. This topic also provides tips on
+optimizing performance with popular AI models. For more information, see the lists of
+:ref:`available models for MAD-integrated benchmarking <vllm-benchmark-mad-models>`
+and :ref:`standalone benchmarking <vllm-benchmark-standalone-options>`.
 
-   * `PyTorch {{ unified_docker.pytorch_version }} <https://github.com/pytorch/pytorch>`_
+.. _vllm-benchmark-vllm:
 
-   With this Docker image, you can quickly validate the expected inference
-   performance numbers for the MI300X accelerator. This topic also provides tips on
-   optimizing performance with popular AI models.
+.. note::
 
-   .. _vllm-benchmark-available-models:
+   vLLM is a toolkit and library for LLM inference and serving. AMD implements
+   high-performance custom kernels and modules in vLLM to enhance performance.
+   See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+   more information.
 
-   Available models
-   ================
+Getting started
+===============
 
-   .. raw:: html
+Use the following procedures to reproduce the benchmark results on an
+MI300X accelerator with the prebuilt vLLM Docker image.
 
-      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
-        <div class="row">
-          <div class="col-2 me-2 model-param-head">Model</div>
-          <div class="row col-10">
-   {% for model_group in model_groups %}
-            <div class="col-3 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
-   {% endfor %}
-          </div>
-        </div>
+.. _vllm-benchmark-get-started:
 
-        <div class="row mt-1">
-          <div class="col-2 me-2 model-param-head">Model variant</div>
-          <div class="row col-10">
-   {% for model_group in model_groups %}
-      {% set models = model_group.models %}
-      {% for model in models %}
-         {% if models|length % 3 == 0 %}
-            <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
-         {% else %}
-            <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
-         {% endif %}
-      {% endfor %}
-   {% endfor %}
-          </div>
-        </div>
-      </div>
+1. Disable NUMA auto-balancing.
 
-   .. _vllm-benchmark-vllm:
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
 
-   {% for model_group in model_groups %}
-      {% for model in model_group.models %}
+   .. code-block:: shell
 
-   .. container:: model-doc {{model.mad_tag}}
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
 
-      .. note::
+2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
 
-         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
-         Some models require access authorization prior to use via an external license agreement through a third party.
+   Use the following command to pull the Docker image from Docker Hub.
 
-      {% endfor %}
-   {% endfor %}
+   .. code-block:: shell
 
+      docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
 
-   .. note::
+Once the setup is complete, choose between two options to reproduce the
+benchmark results:
 
-      vLLM is a toolkit and library for LLM inference and serving. AMD implements
-      high-performance custom kernels and modules in vLLM to enhance performance.
-      See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
-      more information.
+-  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
 
-   Getting started
-   ===============
+-  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
 
-   Use the following procedures to reproduce the benchmark results on an
-   MI300X accelerator with the prebuilt vLLM Docker image.
+.. _vllm-benchmark-mad:
 
-   .. _vllm-benchmark-get-started:
+MAD-integrated benchmarking
+===========================
 
-   1. Disable NUMA auto-balancing.
+Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+directory and install the required packages on the host machine.
 
-      To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
-      might hang until the periodic balancing is finalized. For more information,
-      see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
+.. code-block:: shell
 
-      .. code-block:: shell
+   git clone https://github.com/ROCm/MAD
+   cd MAD
+   pip install -r requirements.txt
 
-         # disable automatic NUMA balancing
-         sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
-         # check if NUMA balancing is disabled (returns 0 if disabled)
-         cat /proc/sys/kernel/numa_balancing
-         0
+Use this command to run a performance benchmark test of the Llama 3.1 8B model
+on one GPU with ``float16`` data type in the host machine.
 
-   2. Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
+.. code-block:: shell
 
-      Use the following command to pull the Docker image from Docker Hub.
+   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+   python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
 
-      .. code-block:: shell
+ROCm MAD launches a Docker container with the name
+``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
+model are collected in the following path: ``~/MAD/reports_float16/``.
 
-         docker pull {{ unified_docker.pull_tag }}
+Although the following models are preconfigured to collect latency and
+throughput performance data, you can also change the benchmarking parameters.
+Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
 
-   Benchmarking
-   ============
+.. _vllm-benchmark-mad-models:
 
-   Once the setup is complete, choose between two options to reproduce the
-   benchmark results:
+Available models
+----------------
 
-   .. _vllm-benchmark-mad:
+.. list-table::
+   :header-rows: 1
+   :widths: 2, 3
 
-   {% for model_group in model_groups %}
-      {% for model in model_group.models %}
+   * - Model name
+     - Tag
 
-   .. container:: model-doc {{model.mad_tag}}
+   * - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
+     - ``pyt_vllm_llama-3.1-8b``
 
-      .. tab-set::
+   * - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-70b``
 
-         .. tab-item:: MAD-integrated benchmarking
+   * - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-405b``
 
-            Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
-            directory and install the required packages on the host machine.
+   * - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
+     - ``pyt_vllm_llama-3.2-11b-vision-instruct``
 
-            .. code-block:: shell
+   * - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
+     - ``pyt_vllm_llama-2-7b``
 
-               git clone https://github.com/ROCm/MAD
-               cd MAD
-               pip install -r requirements.txt
+   * - `Llama 2 70B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
+     - ``pyt_vllm_llama-2-70b``
 
-            Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
-            using one GPU with the ``{{model.precision}}`` data type on the host machine.
+   * - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x7b``
 
-            .. code-block:: shell
+   * - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x22b``
 
-               export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-               python3 tools/run_models.py --tags {{model.mad_tag}} --keep-model-dir --live-output --timeout 28800
+   * - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
+     - ``pyt_vllm_mistral-7b``
 
-            MAD launches a Docker container with the name
-            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
-            model are collected in the following path: ``~/MAD/reports_{{model.precision}}/``.
+   * - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
+     - ``pyt_vllm_qwen2-7b``
 
-            Although the :ref:`available models <vllm-benchmark-available-models>` are preconfigured
-            to collect latency and throughput performance data, you can also change the benchmarking
-            parameters. See the standalone benchmarking tab for more information.
+   * - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
+     - ``pyt_vllm_qwen2-72b``
 
-         .. tab-item:: Standalone benchmarking
+   * - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
+     - ``pyt_vllm_jais-13b``
 
-            Run the vLLM benchmark tool independently by starting the
-            `Docker container <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9>`_
-            as shown in the following snippet.
+   * - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
+     - ``pyt_vllm_jais-30b``
 
-            .. code-block::
+   * - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
+     - ``pyt_vllm_dbrx-instruct``
 
-               docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
-               docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.6 rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+   * - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
+     - ``pyt_vllm_gemma-2-27b``
 
-            In the Docker container, clone the ROCm MAD repository and navigate to the
-            benchmark scripts directory at ``~/MAD/scripts/vllm``.
+   * - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
+     - ``pyt_vllm_c4ai-command-r-plus-08-2024``
 
-            .. code-block::
+   * - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
+     - ``pyt_vllm_deepseek-moe-16b-chat``
 
-               git clone https://github.com/ROCm/MAD
-               cd MAD/scripts/vllm
+   * - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
+     - ``pyt_vllm_llama-3.1-70b_fp8``
 
-            To start the benchmark, use the following command with the appropriate options.
+   * - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
+     - ``pyt_vllm_llama-3.1-405b_fp8``
 
-            .. code-block::
+   * - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mixtral-8x7b_fp8``
 
-               ./vllm_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d {{model.precision}}
+   * - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mixtral-8x22b_fp8``
 
-            .. list-table::
-               :header-rows: 1
-               :align: center
+   * - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mistral-7b_fp8``
 
-               * - Name
-                 - Options
-                 - Description
+   * - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
+     - ``pyt_vllm_dbrx_fp8``
 
-               * - ``$test_option``
-                 - latency
-                 - Measure decoding token latency
+   * - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
+     - ``pyt_vllm_command-r-plus_fp8``
 
-               * -
-                 - throughput
-                 - Measure token generation throughput
+.. _vllm-benchmark-standalone:
 
-               * -
-                 - all
-                 - Measure both throughput and latency
+Standalone benchmarking
+=======================
 
-               * - ``$num_gpu``
-                 - 1 or 8
-                 - Number of GPUs
+You can run the vLLM benchmark tool independently by starting the
+:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
+snippet.
 
-               * - ``$datatype``
-                 - ``float16`` or ``float8``
-                 - Data type
+.. code-block::
 
-            .. note::
+   docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.6 rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
 
-               The input sequence length, output sequence length, and tensor parallel (TP) are
-               already configured. You don't need to specify them with this script.
+In the Docker container, clone the ROCm MAD repository and navigate to the
+benchmark scripts directory at ``~/MAD/scripts/vllm``.
 
-            .. note::
+.. code-block::
 
-               If you encounter the following error, pass your access-authorized Hugging
-               Face token to the gated models.
+   git clone https://github.com/ROCm/MAD
+   cd MAD/scripts/vllm
 
-               .. code-block::
+Command
+-------
 
-                  OSError: You are trying to access a gated repo.
+To start the benchmark, use the following command with the appropriate options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
 
-                  # pass your HF_TOKEN
-                  export HF_TOKEN=$your_personal_hf_token
+.. code-block:: shell
 
-            Here are some examples of running the benchmark with various options.
+   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
 
-            * Latency benchmark
+See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
 
-              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with the ``{{model.precision}}`` data type.
+.. note::
 
-              .. code-block::
+   The input sequence length, output sequence length, and tensor parallel (TP) are
+   already configured. You don't need to specify them with this script.
 
-                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
+.. note::
 
-              Find the latency report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
+   If you encounter the following error, pass your access-authorized Hugging
+   Face token to the gated models.
 
-            * Throughput benchmark
+   .. code-block:: shell
 
-              Use this command to throughput the latency of the {{model.model}} model on eight GPUs with the ``{{model.precision}}`` data type.
+      OSError: You are trying to access a gated repo.
 
-              .. code-block:: shell
+      # pass your HF_TOKEN
+      export HF_TOKEN=$your_personal_hf_token
 
-                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
+.. _vllm-benchmark-standalone-options:
 
-              Find the throughput report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
+Options and available models
+----------------------------
 
-            .. raw:: html
+.. list-table::
+   :header-rows: 1
+   :align: center
 
-               <style>
-               mjx-container[jax="CHTML"][display="true"] {
-                  text-align: left;
-                  margin: 0;
-               }
-               </style>
+   * - Name
+     - Options
+     - Description
 
-            .. note::
+   * - ``$test_option``
+     - latency
+     - Measure decoding token latency
 
-               Throughput is calculated as:
+   * -
+     - throughput
+     - Measure token generation throughput
 
-               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+   * -
+     - all
+     - Measure both throughput and latency
 
-               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
-      {% endfor %}
-   {% endfor %}
+   * - ``$model_repo``
+     - ``meta-llama/Llama-3.1-8B-Instruct``
+     - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
+
+   * - (``float16``)
+     - ``meta-llama/Llama-3.1-70B-Instruct``
+     - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
+
+   * -
+     - ``meta-llama/Llama-3.1-405B-Instruct``
+     - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
+
+   * -
+     - ``meta-llama/Llama-3.2-11B-Vision-Instruct``
+     - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
+
+   * -
+     - ``meta-llama/Llama-2-7b-chat-hf``
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
+
+   * -
+     - ``meta-llama/Llama-2-70b-chat-hf``
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
+
+   * -
+     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
+     - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
+
+   * -
+     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
+     - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
+
+   * -
+     - ``mistralai/Mistral-7B-Instruct-v0.3``
+     - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
+
+   * -
+     - ``Qwen/Qwen2-7B-Instruct``
+     - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
+
+   * -
+     - ``Qwen/Qwen2-72B-Instruct``
+     - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
+
+   * -
+     - ``core42/jais-13b-chat``
+     - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
+
+   * -
+     - ``core42/jais-30b-chat-v3``
+     - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
+
+   * -
+     - ``databricks/dbrx-instruct``
+     - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
+
+   * -
+     - ``google/gemma-2-27b``
+     - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
+
+   * -
+     - ``CohereForAI/c4ai-command-r-plus-08-2024``
+     - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
+
+   * -
+     - ``deepseek-ai/deepseek-moe-16b-chat``
+     - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
+
+   * - ``$model_repo``
+     - ``amd/Llama-3.1-70B-Instruct-FP8-KV``
+     - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
+
+   * - (``float8``)
+     - ``amd/Llama-3.1-405B-Instruct-FP8-KV``
+     - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
+
+   * -
+     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
+     - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
+     - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/Mistral-7B-v0.1-FP8-KV``
+     - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/dbrx-instruct-FP8-KV``
+     - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
+
+   * -
+     - ``amd/c4ai-command-r-plus-FP8-KV``
+     - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
+
+   * - ``$num_gpu``
+     - 1 or 8
+     - Number of GPUs
+
+   * - ``$datatype``
+     - ``float16`` or ``float8``
+     - Data type
+
+.. _vllm-benchmark-run-benchmark:
+
+Running the benchmark on the MI300X accelerator
+-----------------------------------------------
+
+Here are some examples of running the benchmark with various options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+Example 1: latency benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+ 
+Use this command to benchmark the latency of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
+
+.. code-block::
+
+   ./vllm_benchmark_report.sh -s latency -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
+   ./vllm_benchmark_report.sh -s latency -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
+
+Find the latency reports at:
+
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_latency_report.csv``
+
+- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_latency_report.csv``
+
+Example 2: throughput benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Use this command to benchmark the throughput of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
+   ./vllm_benchmark_report.sh -s throughput -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
+
+Find the throughput reports at:
+
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_throughput_report.csv``
+
+- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_throughput_report.csv``
+
+.. raw:: html
+
+   <style>
+   mjx-container[jax="CHTML"][display="true"] {
+       text-align: left;
+       margin: 0;
+   }
+   </style>
+
+.. note::
+
+   Throughput is calculated as:
+
+   - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+   - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
 
 Further reading
 ===============
@@ -290,3 +446,33 @@ Further reading
 
 - To learn how to fine-tune LLMs, see
   :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
+
+Previous versions
+=================
+
+This table lists previous versions of the ROCm vLLM Docker image for inference
+performance validation. For detailed information about available models for
+benchmarking, see the version-specific documentation.
+
+.. list-table::
+   :header-rows: 1
+   :stub-columns: 1
+
+   * - ROCm version
+     - vLLM version
+     - PyTorch version
+     - Resources
+
+   * - 6.2.1
+     - 0.6.4
+     - 2.5.0
+     - 
+       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4/images/sha256-ccbb74cc9e7adecb8f7bdab9555f7ac6fc73adb580836c2a35ca96ff471890d8>`_
+
+   * - 6.2.0
+     - 0.4.3
+     - 2.4.0
+     -
+       * `Documentation <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50/images/sha256-9e4dd4788a794c3d346d7d0ba452ae5e92d39b8dfac438b2af8efdc7f15d22c0>`_

docs/how-to/system-optimization/mi300x.rst

@@ -308,24 +308,6 @@ Otherwise, if the system has Intel host CPUs add this instead to
 
    intel_iommu=on iommu=pt
 
-``modprobe.blacklist=amdgpu``
-  For some system configurations, the ``amdgpu`` driver needs to be blocked during kernel initialization to avoid an issue where after boot, the GPUs are not listed when running the command ``rocm-smi`` or ``amd-smi``.
-
-  Alternatively, configuring the AMD recommended system optimized BIOS settings might remove the need for using this setting. Some manufacturers and users might not implement the recommended system optimized BIOS settings.
-
-If you experience the mentioned issue, then add this to ``GRUB_CMDLINE_LINUX``:
-
-.. code-block:: text
-
-  modprobe.blacklist=amdgpu
-
-After the change, the ``amdgpu`` module must be loaded to support the ROCm framework
-software tools and utilities. Run the following command to load the ``amdgpu`` module:
-
-.. code-block:: text
-
-  sudo modprobe amdgpu
-
 Update GRUB
 -----------
 

docs/reference/gpu-arch-specs.rst

@@ -32,8 +32,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - L1 Instruction Cache (KiB)
           - VGPR File (KiB)
           - SGPR File (KiB)
-          - GFXIP Major version
-          - GFXIP Minor version
         *
           - MI325X
           - CDNA3
@@ -49,8 +47,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 64 per 2 CUs
           - 512
           - 12.5
-          - 9
-          - 4
         *
           - MI300X
           - CDNA3
@@ -66,8 +62,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 64 per 2 CUs
           - 512
           - 12.5
-          - 9
-          - 4
         *
           - MI300A
           - CDNA3
@@ -83,8 +77,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 64 per 2 CUs
           - 512
           - 12.5
-          - 9
-          - 4
         *
           - MI250X
           - CDNA2
@@ -100,8 +92,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 2 CUs
           - 512
           - 12.5
-          - 9
-          - 0
         *
           - MI250
           - CDNA2
@@ -117,8 +107,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 2 CUs
           - 512
           - 12.5
-          - 9
-          - 0
         *
           - MI210
           - CDNA2
@@ -134,8 +122,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 2 CUs
           - 512
           - 12.5
-          - 9
-          - 0
         *
           - MI100
           - CDNA
@@ -151,8 +137,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 3 CUs
           - 256 VGPR and 256 AccVGPR
           - 12.5
-          - 9
-          - 0
         *
           - MI60
           - GCN5.1
@@ -168,8 +152,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 3 CUs
           - 256
           - 12.5
-          - 9
-          - 0
         *
           - MI50 (32GB)
           - GCN5.1
@@ -185,8 +167,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 3 CUs
           - 256
           - 12.5
-          - 9
-          - 0
         *
           - MI50 (16GB)
           - GCN5.1
@@ -202,8 +182,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 3 CUs
           - 256
           - 12.5
-          - 9
-          - 0
         *
           - MI25
           - GCN5.0
@@ -219,8 +197,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 3 CUs
           - 256
           - 12.5
-          - 9
-          - 0
         *
           - MI8
           - GCN3.0
@@ -236,8 +212,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 4 CUs
           - 256
           - 12.5
-          - 8
-          - 0
         *
           - MI6
           - GCN4.0
@@ -253,8 +227,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 4 CUs
           - 256
           - 12.5
-          - 8
-          - 0
 
   .. tab-item:: AMD Radeon PRO GPUs
 
@@ -266,7 +238,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - Model
           - Architecture
           - LLVM target name
-
           - VRAM (GiB)
           - Compute Units
           - Wavefront Size
@@ -279,8 +250,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - L0 Instruction Cache (KiB)
           - VGPR File (KiB)
           - SGPR File (KiB)
-          - GFXIP Major version
-          - GFXIP Minor version
         *
           - Radeon PRO V710
           - RDNA3
@@ -297,8 +266,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon PRO W7900 Dual Slot
           - RDNA3
@@ -315,8 +282,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon PRO W7900
           - RDNA3
@@ -333,8 +298,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon PRO W7800
           - RDNA3
@@ -351,8 +314,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon PRO W7700
           - RDNA3
@@ -369,8 +330,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon PRO W6800
           - RDNA2
@@ -387,8 +346,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon PRO W6600
           - RDNA2
@@ -405,8 +362,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon PRO V620
           - RDNA2
@@ -423,8 +378,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon Pro W5500
           - RDNA
@@ -441,8 +394,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 20
-          - 10
-          - 1
         *
           - Radeon Pro VII
           - GCN5.1
@@ -459,8 +410,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 3 CUs
           - 256
           - 12.5
-          - 9
-          - 0
 
   .. tab-item:: AMD Radeon GPUs
 
@@ -484,8 +433,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - L0 Instruction Cache (KiB)
           - VGPR File (KiB)
           - SGPR File (KiB)
-          - GFXIP Major version
-          - GFXIP Minor version
         *
           - Radeon RX 7900 XTX
           - RDNA3
@@ -502,8 +449,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon RX 7900 XT
           - RDNA3
@@ -520,8 +465,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon RX 7900 GRE
           - RDNA3
@@ -538,8 +481,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon RX 7800 XT
           - RDNA3
@@ -556,8 +497,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon RX 7700 XT
           - RDNA3
@@ -574,8 +513,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 768
           - 16
-          - 11
-          - 0
         *
           - Radeon RX 7600
           - RDNA3
@@ -592,8 +529,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 11
-          - 0
         *
           - Radeon RX 6950 XT
           - RDNA2
@@ -610,8 +545,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6900 XT
           - RDNA2
@@ -628,8 +561,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6800 XT
           - RDNA2
@@ -646,8 +577,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6800
           - RDNA2
@@ -664,8 +593,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6750 XT
           - RDNA2
@@ -682,8 +609,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6700 XT
           - RDNA2
@@ -700,8 +625,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6700
           - RDNA2
@@ -718,8 +641,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6650 XT
           - RDNA2
@@ -736,8 +657,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6600 XT
           - RDNA2
@@ -754,8 +673,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon RX 6600
           - RDNA2
@@ -772,8 +689,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32
           - 512
           - 16
-          - 10
-          - 3
         *
           - Radeon VII
           - GCN5.1
@@ -790,14 +705,12 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - 32 per 3 CUs
           - 256
           - 12.5
-          - 9
-          - 0
 
 Glossary
 ========
 
 For more information about the terms used, see the
-:ref:`specific documents and guides <gpu-arch-documentation>`, or
+:ref:`specific documents and guides <gpu-arch-documentation>`, or 
 :doc:`Understanding the HIP programming model<hip:understand/programming_model>`.
 
 **LLVM target name**
@@ -887,26 +800,6 @@ Purpose Vector Registers, used specifically in matrix instructions.
 Size of the Scalar General Purpose Register (SGPR) file. Holds data used in
 scalar instructions.
 
-**GFXIP**
-
-GFXIP (Graphics IP) is a versioning system used by AMD to identify the GPU
-architecture and its instruction set. It helps categorize different generations
-of GPUs and their feature sets.
-
-**GFXIP major version**
-
-Defines the GPU's core instruction set and architecture, which determines
-compatibility with software stacks such as HIP and OpenCL. For example, a GFXIP
-11 major version corresponds to the RDNA 3 (Navi 3x) architecture, influencing
-driver support and available compute features.
-
-**GFXIP minor version**
-
-Represents specific variations within a GFXIP major version and affects feature sets,
-optimizations, and driver behavior in software stacks such as HIP and OpenCL. Different
-GPU models within the same major version can have unique capabilities, impacting
-performance and supported instructions.
-
 **GCD**
 
 Graphics Compute Die.

docs/reference/precision-support.rst

@@ -1,22 +1,20 @@
 .. meta::
-  :description: Supported data types of AMD GPUs and libraries in ROCm.
-  :keywords: precision, data types, HIP types, int8, float8, float8 (E4M3),
-             float8 (E5M2), bfloat8, float16, half, bfloat16, tensorfloat32,
-             float, float32, float64, double, AMD data types, HIP data types,
-             ROCm precision, ROCm data types
+  :description: Supported data types in ROCm
+  :keywords: int8, float8, float8 (E4M3), float8 (E5M2), bfloat8, float16, half, bfloat16, tensorfloat32, float,
+   float32, float64, double, AMD, ROCm, AMDGPU
 
 *************************************************************
-Data types and precision support
+Precision support
 *************************************************************
 
-This topic lists the data types support on AMD GPUs, ROCm libraries along
-with corresponding :doc:`HIP <hip:index>` data types.
+Use the following sections to identify data types and HIP types ROCm™ supports.
 
 Integral types
-==============
+==========================================
+
+The signed and unsigned integral types that are supported by ROCm are listed in the following table,
+together with their corresponding HIP type and a short description.
 
-The signed and unsigned integral types supported by ROCm are listed in
-the following table.
 
 .. list-table::
     :header-rows: 1
@@ -46,9 +44,10 @@ the following table.
 .. _precision_support_floating_point_types:
 
 Floating-point types
-====================
+==========================================
 
-The floating-point types supported by ROCm are listed in the following table.
+The floating-point types that are supported by ROCm are listed in the following table, together with
+their corresponding HIP type and a short description.
 
 .. image:: ../data/about/compatibility/floating-point-data-types.png
     :alt: Supported floating-point types
@@ -63,66 +62,44 @@ The floating-point types supported by ROCm are listed in the following table.
       - Description
     *
       - float8 (E4M3)
-      - ``__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.
+      - ``-``
+      - 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 with no infinity or signed zero. NaN is represented as negative zero.
     *
       - float8 (E5M2)
-      - ``__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.
+      - ``-``
+      - 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 with no infinity or signed zero. NaN is represented as negative zero.
     *
       - float16
       - ``half``
-      - A 16-bit floating-point number that conforms to the IEEE 754-2008
-        half-precision storage format.
+      - A 16-bit floating-point number that conforms to the IEEE 754-2008 half-precision storage format.
     *
       - bfloat16
       - ``bfloat16``
-      - A shortened 16-bit version of the IEEE 754 single-precision storage
-        format.
+      - A shortened 16-bit version of the IEEE 754 single-precision storage format.
     *
       - tensorfloat32
-      - Not available
-      - A floating-point number that occupies 32 bits or less of storage,
-        providing improved range compared to half (16-bit) format, at
-        (potentially) greater throughput than single-precision (32-bit) formats.
+      - ``-``
+      - A floating-point number that occupies 32 bits or less of storage, providing improved range compared to half (16-bit) format, at (potentially) greater throughput than single-precision (32-bit) formats.
     *
       - float32
       - ``float``
-      - A 32-bit floating-point number that conforms to the IEEE 754
-        single-precision storage format.
+      - A 32-bit floating-point number that conforms to the IEEE 754 single-precision storage format.
     *
       - float64
       - ``double``
-      - A 64-bit floating-point number that conforms to the IEEE 754
-        double-precision storage format.
+      - A 64-bit floating-point number that conforms to the IEEE 754 double-precision storage format.
 
 .. note::
 
-  * 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.
-
-  * 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>`_).
-
+  * 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.
+  * The encodings for FP8 (E5M2) and FP8 (E4M3) that are natively supported by MI300 differ from the FP8 (E5M2) and FP8 (E4M3) encodings used in 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.
 
-  * The :doc:`low precision floating point types page <hip:reference/low_fp_types>`
-    describes how to use these types in HIP with examples.
+ROCm support icons
+==========================================
 
-Level of support definitions
-============================
-
-In the following sections, icons represent the level of support. These icons,
-described in the following table, are also used in the library data type support
-pages.
+In the following sections, we use icons to represent the level of support. These icons, described in the
+following table, are also used on the library data type support pages.
 
 .. list-table::
     :header-rows: 1
@@ -130,11 +107,6 @@ pages.
     *
       -  Icon
       - Definition
-
-    *
-      - NA
-      - Not applicable
-
     *
       - ❌
       - Not supported
@@ -149,29 +121,17 @@ pages.
 
 .. note::
 
-  * Full support means that the type is supported natively or with hardware
-    emulation.
+  * Full support means that the type is supported natively or with hardware emulation.
+  * Native support means that the operations for that type are implemented in hardware. Types that are not natively supported are emulated with the available hardware. The performance of non-natively supported types can differ from the full instruction throughput rate. For example, 16-bit integer operations can be performed on the 32-bit integer ALUs at full rate; however, 64-bit integer operations might need several instructions on the 32-bit integer ALUs.
+  * Any type can be emulated by software, but this page does not cover such cases.
 
-  * Native support means that the operations for that type are implemented in
-    hardware. Types that are not natively supported are emulated with the
-    available hardware. The performance of non-natively supported types can
-    differ from the full instruction throughput rate. For example, 16-bit
-    integer operations can be performed on the 32-bit integer ALUs at full rate;
-    however, 64-bit integer operations might need several instructions on the
-    32-bit integer ALUs.
-
-  * Any type can be emulated by software, but this page does not cover such
-    cases.
-
-Data type support by Hardware Architecture
+Hardware type support
 ==========================================
 
-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.
+AMD GPU hardware support for data types is listed in the following tables.
 
 Compute units support
----------------------
+-------------------------------------------------------------------------------
 
 The following table lists data type support for compute units.
 
@@ -252,7 +212,7 @@ The following table lists data type support for compute units.
         - ✅
 
 Matrix core support
--------------------
+-------------------------------------------------------------------------------
 
 The following table lists data type support for AMD GPU matrix cores.
 
@@ -333,7 +293,7 @@ The following table lists data type support for AMD GPU matrix cores.
         - ✅
 
 Atomic operations support
--------------------------
+-------------------------------------------------------------------------------
 
 The following table lists data type support for atomic operations.
 
@@ -415,23 +375,21 @@ The following table lists data type support for atomic operations.
 
 .. note::
 
-  You can emulate atomic operations using software for cases that are not
-  natively supported. Software-emulated atomic operations have a high negative
-  performance impact when they frequently access the same memory address.
+  For cases that are not natively supported, you can emulate atomic operations using software.
+  Software-emulated atomic operations have high negative performance impact when they frequently
+  access the same memory address.
 
-Data type support in ROCm libraries
-===================================
+Data Type support in ROCm Libraries
+==========================================
 
-ROCm library support for int8, float8 (E4M3), float8 (E5M2), int16, float16,
-bfloat16, int32, tensorfloat32, float32, int64, and float64 is listed in the
-following tables.
+ROCm library support for int8, float8 (E4M3), float8 (E5M2), int16, float16, bfloat16, int32,
+tensorfloat32, float32, int64, and float64 is listed in the following tables.
 
 Libraries input/output type support
------------------------------------
+-------------------------------------------------------------------------------
 
-The following tables list ROCm library support for specific input and output
-data types. Refer to the corresponding library data type support page for a
-detailed description.
+The following tables list ROCm library support for specific input and output data types. For a detailed
+description, refer to the corresponding library data type support page.
 
 .. tab-set::
 
@@ -448,37 +406,37 @@ detailed description.
         - int32
         - int64
       *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
         - ✅/✅
         - ❌/❌
         - ❌/❌
         - ❌/❌
       *
-        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
-        - NA/✅
-        - NA/✅
-        - NA/✅
-        - NA/✅
+        - rocRAND (:doc:`details <rocrand:api-reference/data-type-support>`)
+        - -/✅
+        - -/✅
+        - -/✅
+        - -/✅
       *
-        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
-        - NA/✅
-        - NA/✅
-        - NA/✅
-        - NA/✅
+        - hipRAND (:doc:`details <hiprand:api-reference/data-type-support>`)
+        - -/✅
+        - -/✅
+        - -/✅
+        - -/✅
       *
-        -  :doc:`rocPRIM <rocprim:reference/data-type-support>`
+        - rocPRIM (:doc:`details <rocprim:reference/data-type-support>`)
         - ✅/✅
         - ✅/✅
         - ✅/✅
         - ✅/✅
       *
-        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
+        - hipCUB (:doc:`details <hipcub:api-reference/data-type-support>`)
         - ✅/✅
         - ✅/✅
         - ✅/✅
         - ✅/✅
       *
-        - :doc:`rocThrust <rocthrust:data-type-support>`
+        - rocThrust (:doc:`details <rocthrust:data-type-support>`)
         - ✅/✅
         - ✅/✅
         - ✅/✅
@@ -500,7 +458,7 @@ detailed description.
         - float32
         - float64
       *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
         - ❌/❌
         - ❌/❌
         - ✅/✅
@@ -509,25 +467,25 @@ detailed description.
         - ❌/❌
         - ❌/❌
       *
-        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/✅
+        - rocRAND (:doc:`details <rocrand:api-reference/data-type-support>`)
+        - -/❌
+        - -/❌
+        - -/✅
+        - -/❌
+        - -/❌
+        - -/✅
+        - -/✅
       *
-        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/✅
+        - hipRAND (:doc:`details <hiprand:api-reference/data-type-support>`)
+        - -/❌
+        - -/❌
+        - -/✅
+        - -/❌
+        - -/❌
+        - -/✅
+        - -/✅
       *
-        - :doc:`rocPRIM <rocprim:reference/data-type-support>`
+        - rocPRIM (:doc:`details <rocprim:reference/data-type-support>`)
         - ❌/❌
         - ❌/❌
         - ✅/✅
@@ -536,7 +494,7 @@ detailed description.
         - ✅/✅
         - ✅/✅
       *
-        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
+        - hipCUB (:doc:`details <hipcub:api-reference/data-type-support>`)
         - ❌/❌
         - ❌/❌
         - ✅/✅
@@ -545,7 +503,7 @@ detailed description.
         - ✅/✅
         - ✅/✅
       *
-        - :doc:`rocThrust <rocthrust:data-type-support>`
+        - rocThrust (:doc:`details <rocthrust:data-type-support>`)
         - ❌/❌
         - ❌/❌
         - ⚠️/⚠️
@@ -554,18 +512,12 @@ detailed description.
         - ✅/✅
         - ✅/✅
 
-.. 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.
 
 Libraries internal calculations type support
---------------------------------------------
+-------------------------------------------------------------------------------
 
-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.
+The following tables list ROCm library support for specific internal data types. For a detailed
+description, refer to the corresponding library data type support page.
 
 .. tab-set::
 
@@ -582,7 +534,7 @@ description.
         - int32
         - int64
       *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
         - ❌
         - ❌
         - ✅
@@ -605,7 +557,7 @@ description.
         - float32
         - float64
       *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
         - ❌
         - ❌
         - ❌

docs/release/versions.md

@@ -10,7 +10,6 @@
 
 | Version | Release date |
 | ------- | ------------ |
-| [6.3.3](https://rocm.docs.amd.com/en/docs-6.3.3/) | February 19, 2025 |
 | [6.3.2](https://rocm.docs.amd.com/en/docs-6.3.2/) | January 28, 2025 |
 | [6.3.1](https://rocm.docs.amd.com/en/docs-6.3.1/) | December 20, 2024 |
 | [6.3.0](https://rocm.docs.amd.com/en/docs-6.3.0/) | December 3, 2024 |

docs/sphinx/_toc.yml.in

@@ -154,7 +154,7 @@ subtrees:
         - entries:
           - url: https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf
             title: AMD Instinct MI200/CDNA2 ISA
-          - url: https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna2-white-paper.pdf
+          - url: https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf
             title: White paper
       - file: conceptual/gpu-arch/mi100.md
         title: MI100 microarchitecture
@@ -162,7 +162,7 @@ subtrees:
         - entries:
           - url: https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf
             title: AMD Instinct MI100/CDNA1 ISA
-          - url: https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna-white-paper.pdf
+          - url: https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf
             title: White paper
   - file: conceptual/iommu.rst
     title: Input-Output Memory Management Unit (IOMMU)

docs/sphinx/requirements.in

@@ -1,4 +1,3 @@
-rocm-docs-core==1.17.1
+rocm-docs-core==1.15.0
 sphinx-reredirects
 sphinx-sitemap
-sphinxcontrib.datatemplates==0.11.0

docs/sphinx/requirements.txt

@@ -2,7 +2,7 @@
 # This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
-#    pip-compile docs/sphinx/requirements.in
+#    pip-compile requirements.in
 #
 accessible-pygments==0.0.5
     # via pydata-sphinx-theme
@@ -15,23 +15,23 @@ attrs==25.1.0
     #   jsonschema
     #   jupyter-cache
     #   referencing
-babel==2.16.0
+babel==2.17.0
     # via
     #   pydata-sphinx-theme
     #   sphinx
-beautifulsoup4==4.12.3
+beautifulsoup4==4.13.3
     # via pydata-sphinx-theme
 breathe==4.35.0
     # via rocm-docs-core
-certifi==2024.8.30
+certifi==2025.1.31
     # via requests
 cffi==1.17.1
     # via
     #   cryptography
     #   pynacl
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via requests
-click==8.1.7
+click==8.1.8
     # via
     #   jupyter-cache
     #   sphinx-external-toc
@@ -43,9 +43,7 @@ debugpy==1.8.12
     # via ipykernel
 decorator==5.1.1
     # via ipython
-defusedxml==0.7.1
-    # via sphinxcontrib-datatemplates
-deprecated==1.2.15
+deprecated==1.2.18
     # via pygithub
 docutils==0.21.2
     # via
@@ -57,13 +55,13 @@ exceptiongroup==1.2.2
     # via ipython
 executing==2.2.0
     # via stack-data
-fastjsonschema==2.20.0
+fastjsonschema==2.21.1
     # via
     #   nbformat
     #   rocm-docs-core
-gitdb==4.0.11
+gitdb==4.0.12
     # via gitpython
-gitpython==3.1.43
+gitpython==3.1.44
     # via rocm-docs-core
 greenlet==3.1.1
     # via sqlalchemy
@@ -77,7 +75,7 @@ importlib-metadata==8.6.1
     #   myst-nb
 ipykernel==6.29.5
     # via myst-nb
-ipython==8.31.0
+ipython==8.32.0
     # via
     #   ipykernel
     #   myst-nb
@@ -117,7 +115,7 @@ mdit-py-plugins==0.4.2
     # via myst-parser
 mdurl==0.1.2
     # via markdown-it-py
-myst-nb==1.1.2
+myst-nb==1.2.0
     # via rocm-docs-core
 myst-parser==4.0.0
     # via myst-nb
@@ -152,19 +150,19 @@ pure-eval==0.2.3
     # via stack-data
 pycparser==2.22
     # via cffi
-pydata-sphinx-theme==0.16.0
+pydata-sphinx-theme==0.16.1
     # via
     #   rocm-docs-core
     #   sphinx-book-theme
 pygithub==2.5.0
     # via rocm-docs-core
-pygments==2.18.0
+pygments==2.19.1
     # via
     #   accessible-pygments
     #   ipython
     #   pydata-sphinx-theme
     #   sphinx
-pyjwt[crypto]==2.10.0
+pyjwt[crypto]==2.10.1
     # via pygithub
 pynacl==1.5.0
     # via pygithub
@@ -177,8 +175,7 @@ pyyaml==6.0.2
     #   myst-parser
     #   rocm-docs-core
     #   sphinx-external-toc
-    #   sphinxcontrib-datatemplates
-pyzmq==26.2.0
+pyzmq==26.2.1
     # via
     #   ipykernel
     #   jupyter-client
@@ -190,7 +187,7 @@ requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.17.1
+rocm-docs-core==1.15.0
     # via -r requirements.in
 rpds-py==0.22.3
     # via
@@ -198,7 +195,7 @@ rpds-py==0.22.3
     #   referencing
 six==1.17.0
     # via python-dateutil
-smmap==5.0.1
+smmap==5.0.2
     # via gitdb
 snowballstemmer==2.2.0
     # via sphinx
@@ -218,8 +215,6 @@ sphinx==8.1.3
     #   sphinx-notfound-page
     #   sphinx-reredirects
     #   sphinx-sitemap
-    #   sphinxcontrib-datatemplates
-    #   sphinxcontrib-runcmd
 sphinx-book-theme==1.1.3
     # via rocm-docs-core
 sphinx-copybutton==0.5.2
@@ -228,7 +223,7 @@ sphinx-design==0.6.1
     # via rocm-docs-core
 sphinx-external-toc==1.0.1
     # via rocm-docs-core
-sphinx-notfound-page==1.0.4
+sphinx-notfound-page==1.1.0
     # via rocm-docs-core
 sphinx-reredirects==0.1.5
     # via -r requirements.in
@@ -236,8 +231,6 @@ sphinx-sitemap==2.6.0
     # via -r requirements.in
 sphinxcontrib-applehelp==2.0.0
     # via sphinx
-sphinxcontrib-datatemplates==0.11.0
-    # via -r requirements.in
 sphinxcontrib-devhelp==2.0.0
     # via sphinx
 sphinxcontrib-htmlhelp==2.1.0
@@ -246,17 +239,15 @@ sphinxcontrib-jsmath==1.0.1
     # via sphinx
 sphinxcontrib-qthelp==2.0.0
     # via sphinx
-sphinxcontrib-runcmd==0.2.0
-    # via sphinxcontrib-datatemplates
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
-sqlalchemy==2.0.37
+sqlalchemy==2.0.38
     # via jupyter-cache
 stack-data==0.6.3
     # via ipython
 tabulate==0.9.0
     # via jupyter-cache
-tomli==2.1.0
+tomli==2.2.1
     # via sphinx
 tornado==6.4.2
     # via
@@ -274,19 +265,20 @@ traitlets==5.14.3
     #   nbformat
 typing-extensions==4.12.2
     # via
+    #   beautifulsoup4
     #   ipython
     #   myst-nb
     #   pydata-sphinx-theme
     #   pygithub
     #   referencing
     #   sqlalchemy
-urllib3==2.2.3
+urllib3==2.3.0
     # via
     #   pygithub
     #   requests
 wcwidth==0.2.13
     # via prompt-toolkit
-wrapt==1.17.0
+wrapt==1.17.2
     # via deprecated
 zipp==3.21.0
     # via importlib-metadata

docs/sphinx/static/css/vllm-benchmark.css

@@ -1,102 +0,0 @@
-/* ------------------ Compatibility options grid ------------------ */
-html {
-  --compat-border-radius: 2px;
-  --compat-accent-color: var(--pst-color-primary);
-  --compat-bg-color: var(--pst-color-on-background);
-  --compat-fg-color: var(--pst-color-primary-text);
-  --compat-head-color: var(--pst-color-surface);
-  --compat-param-hover-color: var(--pst-color-link-hover);
-  --compat-param-selected-color: var(--pst-color-primary);
-}
-
-html[data-theme="light"] {
-  --compat-border-color: var(--pst-gray-500);
-  --compat-param-disabled-color: var(--pst-gray-300);
-}
-
-html[data-theme="dark"] {
-  --compat-border-color: var(--pst-gray-600);
-  --compat-param-disabled-color: var(--pst-gray-600);
-}
-
-div#vllm-benchmark-ud-params-picker.container-fluid {
-  padding: 0 0 1rem 0;
-}
-
-div[data-param-k="model"] {
-  background-color: var(--compat-bg-color);
-  padding: 2px;
-  border: solid 1px var(--compat-border-color);
-  font-weight: 500;
-  cursor: pointer;
-}
-
-div[data-param-k="model"][data-param-state="selected"] {
-  background-color: var(--compat-param-selected-color);
-  color: var(--compat-fg-color);
-}
-
-div[data-param-k="model"][data-param-state="latest-version"] {
-  background-color: var(--compat-param-selected-color);
-  color: var(--compat-fg-color);
-}
-
-div[data-param-k="model"][data-param-state="disabled"] {
-  background-color: var(--compat-param-disabled-color);
-  text-decoration: line-through;
-  /* text-decoration-color: var(--pst-color-danger); */
-  cursor: auto;
-}
-
-div[data-param-k="model"]:not([data-param-state]):hover {
-  background-color: var(--compat-param-hover-color);
-}
-
-div[data-param-k="model-group"] {
-  background-color: var(--compat-bg-color);
-  padding: 2px;
-  border: solid 1px var(--compat-border-color);
-  font-weight: 500;
-  cursor: pointer;
-}
-
-div[data-param-k="model-group"][data-param-state="selected"] {
-  background-color: var(--compat-param-selected-color);
-  color: var(--compat-fg-color);
-}
-
-div[data-param-k="model-group"][data-param-state="latest-version"] {
-  background-color: var(--compat-param-selected-color);
-  color: var(--compat-fg-color);
-}
-
-div[data-param-k="model-group"][data-param-state="disabled"] {
-  background-color: var(--compat-param-disabled-color);
-  text-decoration: line-through;
-  /* text-decoration-color: var(--pst-color-danger); */
-  cursor: auto;
-}
-
-div[data-param-k="model-group"]:not([data-param-state]):hover {
-  background-color: var(--compat-param-hover-color);
-}
-
-.model-param-head {
-  background-color: var(--compat-head-color);
-  padding: 0.15rem 0.15rem 0.15rem 0.67rem;
-  /* margin: 2px; */
-  border-right: solid 2px var(--compat-accent-color);
-  font-weight: 600;
-}
-
-.model-param {
-  /* padding: 2px; */
-  /* margin: 0 2px 0 2px; */
-  /* margin: 2px; */
-  border: solid 1px var(--compat-border-color);
-  font-weight: 500;
-}
-
-.hidden {
-  display: none !important;
-}

tools/autotag/components.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.3.3"
+    <default revision="refs/tags/rocm-6.3.2"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />

tools/autotag/templates/highlights/6.3.3.md

@@ -1,47 +0,0 @@
-# ROCm 6.3.3 release notes
-
-The release notes provide a summary of notable changes since the previous ROCm release.
-
-- [Release highlights](#release-highlights)
-
-- [Operating system and hardware support changes](#operating-system-and-hardware-support-changes)
-
-- [ROCm components versioning](#rocm-components)
-
-- [Detailed component changes](#detailed-component-changes)
-
-- [ROCm known issues](#rocm-known-issues)
-
-- [ROCm upcoming changes](#rocm-upcoming-changes)
-
-```{note}
-If you’re using Radeon™ PRO or Radeon GPUs in a workstation setting with a display connected, see the [Use ROCm on Radeon GPUs](https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility/native_linux/native_linux_compatibility.html)
-documentation to verify compatibility and system requirements.
-```
-## Release highlights
-
-The following are notable new features and improvements in ROCm 6.3.3. For changes to individual components, see
-[Detailed component changes](#detailed-component-changes).
-
-### ROCm Offline Installer Creator updates
-
-The ROCm Offline Installer Creator 6.3.3 adds a new Post-Install Options menu, which includes a new ``udev`` option for adding GPU resources access for all users. It also moves the user-specific GPU access option (for the ``video,render`` group) from the Driver Options menu to the Post-Install Options menu. See the [ROCm Offline Installer Creator](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/rocm-offline-installer.html#post-install-options-menu) documentation for more information.
-
-### ROCm documentation updates
-
-ROCm documentation continues to be updated to provide clearer and more comprehensive guidance for a wider variety of user needs and use cases.
-
-* [Tutorials for AI developers](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/) have been added. These tutorials are Jupyter notebook-based, easy-to-follow documents. They are ideal for AI developers who want to learn about specific topics, including inference, fine-tuning, and training.
-
-* The [LLM inference performance validation guide for AMD Instinct MI300X](https://rocm.docs.amd.com/en/latest/how-to/rocm-for-ai/inference/vllm-benchmark.html)
-  now includes additional models for performance benchmarking. The accompanying ROCm vLLM Docker has been upgraded to ROCm 6.3.1.
- 
-* The HIP documentation has been updated with new resources for developers. To learn more about concurrency, parallelism, and stream management on devices and multiple GPUs, see [Asynchronous concurrent execution](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/asynchronous.html)
-
-* The following HIP documentation topics have been updated:
-    - [Virtual memory management](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/memory_management/virtual_memory.html)
-    - [Programming for HIP runtime compiler (RTC)](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_rtc.html)
-    - [HIP porting guide](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_porting_guide.html)
-    - [Porting CUDA driver API](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_porting_driver_api.html)
-    - [CUDA to HIP API function comparison](https://rocm.docs.amd.com/projects/HIP/en/latest/reference/api_syntax.html)
-