Footnote update (#4967)

* 6.1.5 compatibility table added

.azuredevops/components/AMDMIGraphX.yml

@@ -51,26 +51,6 @@ parameters:
     - rocminfo
     - rocMLIR
     - rocprofiler-register
-    - roctracer
-- name: rocmTestDependencies
-  type: object
-  default:
-    - aomp
-    - aomp-extras
-    - clr
-    - composable_kernel
-    - hipBLAS
-    - hipBLAS-common
-    - hipBLASLt
-    - llvm-project
-    - MIOpen
-    - rocm-cmake
-    - ROCR-Runtime
-    - rocBLAS
-    - rocminfo
-    - rocMLIR
-    - rocprofiler-register
-    - roctracer
 
 jobs:
 - job: AMDMIGraphX
@@ -124,73 +104,7 @@ jobs:
         -DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
         -DBUILD_TESTING=ON
         -GNinja
+# REFERENCE: https://github.com/ROCm/composable_kernel/issues/782
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
-
-- job: AMDMIGraphX_testing
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  - name: MIGRAPHX_TRACE_BENCHMARKING
-    value: 1
-  pool: $(JOB_TEST_POOL)
-  workspace:
-    clean: all
-  strategy:
-    matrix:
-      gfx942:
-        JOB_GPU_TARGET: gfx942
-        JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      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-aqlprofile.yml
-    parameters:
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-# half version should be fixed to 5.6.0
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      dependencySource: fixed
-      fixedComponentName: half
-      fixedPipelineIdentifier: ${{ variables.HALF560_PIPELINE_ID }}
-      skipLibraryLinking: true
-      skipLlvmSymlink: true
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      dependencyList: ${{ parameters.rocmTestDependencies }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      # CI case: download latest default branch build
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      # manual build case: triggered by ROCm/ROCm repo
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-  - task: CMake@1
-    displayName: MIGraphXTest CMake Flags
-    inputs:
-      cmakeArgs: >-
-        -DCMAKE_BUILD_TYPE=Release
-        -DGPU_TARGETS=$(JOB_GPU_TARGET)
-        -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
-        -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
-        -DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
-        -DBUILD_TESTING=ON
-        -DMIGRAPHX_ENABLE_C_API_TEST=ON
-        ..
-  - task: Bash@3
-    displayName: Build and run MIGraphX tests
-    inputs:
-      targetType: inline
-      workingDirectory: build
-      script: make -j$(nproc) check

.azuredevops/components/MIOpen.yml

@@ -8,23 +8,15 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - cmake
-    - libbz2-dev
-    - libdrm-dev
-    - libeigen3-dev
-    - libgmock-dev
-    - libgtest-dev
-    - libsqlite3-dev
-    - libstdc++-12-dev
-    - ninja-build
-    - nlohmann-json3-dev
-    - python3-pip
     - software-properties-common
-    - zstd
-- name: pipModules
-  type: object
-  default:
-    - cget
+    - python3-pip
+    - cmake
+    - ninja-build
+    - libsqlite3-dev
+    - libbz2-dev
+    - nlohmann-json3-dev
+    - libgtest-dev
+    - libdrm-dev
 - name: rocmDependencies
   type: object
   default:
@@ -43,24 +35,6 @@ parameters:
     - clr
     - rocminfo
     - roctracer
-- name: rocmTestDependencies
-  type: object
-  default:
-    - clr
-    - composable_kernel
-    - half
-    - hipBLAS
-    - hipBLAS-common
-    - hipBLASLt
-    - llvm-project
-    - rocBLAS
-    - rocm-cmake
-    - rocminfo
-    - rocMLIR
-    - ROCR-Runtime
-    - rocprofiler-register
-    - rocRAND
-    - roctracer
 
 jobs:
 - job: MIOpen
@@ -80,16 +54,18 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
   # The default boost library from apt is 1.74, which does not satisfy MIOpen's build requirement (1.79+)
   # Upgrade boost from apt by following https://launchpad.net/~mhier/+archive/ubuntu/libboost-latest
   - task: Bash@3
-    displayName: 'Install Boost 1.83'
+    displayName: 'update boost version'
     inputs:
       targetType: inline
-      script: |
-        sudo add-apt-repository ppa:mhier/libboost-latest -y
-        sudo apt-get --yes install libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
+      script: sudo add-apt-repository ppa:mhier/libboost-latest -y
+  - task: Bash@3
+    displayName: 'install boost'
+    inputs:
+      targetType: inline
+      script: sudo apt-get --yes install libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -118,110 +94,3 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
-
-- job: MIOpen_testing
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool: $(JOB_TEST_POOL)
-  workspace:
-    clean: all
-  strategy:
-    matrix:
-      gfx942:
-        JOB_GPU_TARGET: gfx942
-        JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-  - task: Bash@3
-    displayName: 'Install Boost 1.83'
-    inputs:
-      targetType: inline
-      script: |
-        sudo add-apt-repository ppa:mhier/libboost-latest -y
-        sudo apt-get --yes install libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    parameters:
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      dependencyList: ${{ parameters.rocmTestDependencies }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-# MIOpen depends on a specific version of frugally-deep which is forked here: https://github.com/ROCm/frugally-deep
-# https://github.com/ROCm/frugally-deep/blob/master/INSTALL.md
-  - task: Bash@3
-    displayName: Add Python site-packages binaries to path
-    inputs:
-      targetType: inline
-      script: |
-        USER_BASE=$(python3 -m site --user-base)
-        echo "##vso[task.prependpath]$USER_BASE/bin"
-  - task: Bash@3
-    displayName: Install FunctionalPlus
-    inputs:
-      targetType: inline
-      script: cget install Dobiasd/FunctionalPlus
-  - task: Bash@3
-    displayName: Remove Python site-packages binaries from path
-    inputs:
-      targetType: inline
-      script: |
-        USER_BASE=$(python3 -m site --user-base)
-        echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$USER_BASE/bin;;' -e 's;^/;;' -e 's;/$;;')"
-  - task: Bash@3
-    displayName: git clone frugally-deep
-    inputs:
-      targetType: inline
-      script: git clone https://github.com/ROCm/frugally-deep --depth=1 --shallow-submodules
-      workingDirectory: $(Build.SourcesDirectory)
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: frugally-deep
-      cmakeBuildDir: $(Build.SourcesDirectory)/frugally-deep/build
-      installDir: $(Build.SourcesDirectory)/bin
-      extraBuildFlags: -DCMAKE_PREFIX_PATH=$(Build.SourcesDirectory)/cget/cget/pkg/Dobiasd__FunctionalPlus/install
-  - task: CMake@1
-    displayName: 'MIOpen Test CMake Flags'
-    inputs:
-      cmakeArgs: >-
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Build.SourcesDirectory)/bin;$(Build.SourcesDirectory)/cget/cget/pkg/Dobiasd__FunctionalPlus/install
-        -DCMAKE_INSTALL_PREFIX=$(Agent.BuildDirectory)/rocm
-        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-        -DMIOPEN_BACKEND=HIP
-        -DMIOPEN_TEST_FLAGS=" --disable-verification-cache"
-        -DCMAKE_BUILD_TYPE=release
-        -DBUILD_DEV=OFF
-        -DMIOPEN_USE_MLIR=ON
-        -DMIOPEN_GPU_SYNC=OFF
-        ..
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: MIOpen
-      testExecutable: 'CTEST_PARALLEL_LEVEL=4 make -j$(nproc) check'
-      testParameters: ''
-      reloadAMDGPU: true
-      testPublishResults: false
-  - task: Bash@3
-    condition: always()
-    displayName: Clean up Boost 1.83
-    inputs:
-      targetType: inline
-      script: |
-        sudo apt -y autoremove libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
-        sudo add-apt-repository --remove ppa:mhier/libboost-latest -y
-        sudo apt update

.azuredevops/components/hipSOLVER.yml

@@ -42,7 +42,6 @@ parameters:
     - ROCR-Runtime
     - rocSOLVER
     - rocSPARSE
-    - roctracer
 
 jobs:
 - job: hipSOLVER

.azuredevops/components/hipTensor.yml

@@ -117,4 +117,4 @@ jobs:
     parameters:
       componentName: hipTensor
       testDir: '$(Agent.BuildDirectory)/rocm/bin/hiptensor'
-      testParameters: '-E ".*-extended" -VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+      testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'

.azuredevops/components/rocPyDecode.yml

@@ -97,10 +97,7 @@ jobs:
     displayName: Create wheel file
     inputs:
       targetType: inline
-      script: |
-        export ROCM_PATH=$(Agent.BuildDirectory)/rocm
-        export HIP_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include/hip
-        python3 setup.py bdist_wheel
+      script: python setup.py bdist_wheel
       workingDirectory: $(Build.SourcesDirectory)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
     parameters:

.azuredevops/components/rocSOLVER.yml

@@ -44,7 +44,6 @@ parameters:
     - rocprofiler-register
     - ROCR-Runtime
     - rocSPARSE
-    - roctracer
 
 jobs:
 - job: rocSOLVER

.azuredevops/nightly/pytorch.yml

@@ -318,6 +318,13 @@ jobs:
       targetType: inline
       script: git clone https://github.com/pytorch/vision.git --depth=1 --recurse-submodules
       workingDirectory: $(Build.SourcesDirectory)
+  - task: Bash@3
+    displayName: Apply vision patch
+    inputs:
+      targetType: inline
+      script: |
+        git apply $(Build.SourcesDirectory)/.azuredevops/patches/torchvision-package-name.patch
+      workingDirectory: $(Build.SourcesDirectory)/vision
   - task: Bash@3
     displayName: Build vision
     inputs:

.azuredevops/nightly/rocm-nightly.yml

@@ -46,7 +46,6 @@ parameters:
     - rocm_smi_lib
     - rocPRIM
     - rocprofiler-register
-    - rocprofiler-sdk
     - rocprofiler
     - rocPyDecode
     - ROCR-Runtime

.azuredevops/patches/torchvision-package-name.patch

@@ -0,0 +1,34 @@
+From 036307033d5c187b3123dae46477feacbd06d0ab Mon Sep 17 00:00:00 2001
+From: Joseph Macaranas <Joseph.Macaranas@amd.com>
+Date: Sun, 22 Sep 2024 23:03:48 -0400
+Subject: [PATCH] Allow custom package name for CI builds of torchvision
+
+---
+ setup.py | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/setup.py b/setup.py
+index 4b0525d8e4..2c51ce04f2 100644
+--- a/setup.py
++++ b/setup.py
+@@ -42,7 +42,7 @@ CSRS_DIR = ROOT_DIR / "torchvision/csrc"
+ IS_ROCM = (torch.version.hip is not None) and (ROCM_HOME is not None)
+ BUILD_CUDA_SOURCES = (torch.cuda.is_available() and ((CUDA_HOME is not None) or IS_ROCM)) or FORCE_CUDA
+
+-PACKAGE_NAME = "torchvision"
++PACKAGE_NAME = os.getenv("TORCHVISION_PACKAGE_NAME", "torchvision")
+
+ print("Torchvision build configuration:")
+ print(f"{FORCE_CUDA = }")
+@@ -98,7 +98,7 @@ def get_requirements():
+         except DistributionNotFound:
+             return None
+
+-    pytorch_dep = "torch"
++    pytorch_dep = os.getenv("TORCH_PACKAGE_NAME", "torch")
+     if os.getenv("PYTORCH_VERSION"):
+         pytorch_dep += "==" + os.getenv("PYTORCH_VERSION")
+
+--
+2.44.0.windows.1
+

.azuredevops/scripts/compareDot.py

@@ -1,46 +0,0 @@
-import os
-import requests
-import hashlib
-import sys
-
-def download_dotfile(url, file_path):
-    response = requests.get(url)
-    if response.status_code == 200:
-        with open(file_path, 'wb') as f:
-            f.write(response.content)
-    else:
-        raise Exception(f"Failed to download file from {url}. Status code: {response.status_code}")
-
-def hash_file(file_path):
-    sha256_hash = hashlib.sha256()
-    with open(file_path, 'rb') as f:
-        for byte_block in iter(lambda: f.read(4096), b""):
-            sha256_hash.update(byte_block)
-    return sha256_hash.hexdigest()
-
-def compare_files(local_file, downloaded_file):
-    local_hash = hash_file(local_file)
-    downloaded_hash = hash_file(downloaded_file)
-    return local_hash == downloaded_hash
-
-def main():
-    script_directory = os.path.dirname(os.path.abspath(__file__))
-    local_dotfile = os.path.join(script_directory, 'input.dot')
-    downloaded_dotfile = os.path.join(script_directory, 'dependency_graph.dot')
-
-    url = 'https://raw.githubusercontent.com/ROCm/ROCm/refs/heads/generatedependencygraph/.azuredevops/scripts/dependency_graph.dot'
-
-    try:
-        download_dotfile(url, downloaded_dotfile)
-        if compare_files(local_dotfile, downloaded_dotfile):
-            print("The local DOT file and the downloaded DOT file are the same.")
-        else:
-            print("The local DOT file and the downloaded DOT file are different.")
-            # Exit with a non-zero status to signal failed/unstable build on Jenkins
-            # to trigger post-build email
-            sys.exit(1)
-    except Exception as e:
-        print(f"Error: {e}")
-
-if __name__ == "__main__":
-    main()

.azuredevops/scripts/dependencyGraph.py

@@ -1,149 +0,0 @@
-import os
-import yaml
-from graphviz import Digraph
-
-# Set DEBUG to False for normal output, True for debug output
-DEBUG = False
-
-def debug_print(message):
-    if DEBUG:
-        print(message)
-
-import os
-import yaml
-
-def extract_dependencies(exclude_nodes=[]):
-    dependencies = {}
-    debug_print("Extracting dependencies from YAML files...")
-
-    # Define a mapping of specific filenames to component names
-    component_name_mapping = {
-        'HIP.yml': 'clr',  # Remap HIP.yml to clr in graph
-    }
-
-    script_directory = os.path.dirname(os.path.abspath(__file__))
-    yaml_directory = os.path.join(script_directory, '..', 'components')
-
-    for filename in os.listdir(yaml_directory):
-        if filename.endswith(".yaml") or filename.endswith(".yml"):
-            debug_print(f"Processing file: {filename}")
-            try:
-                with open(os.path.join(yaml_directory, filename), 'r') as file:
-                    data = yaml.safe_load(file) or {}
-                    parameters = data.get('parameters', [])
-
-                    # Check for both 'rocmDependencies' and 'rocmDependenciesAMD'
-                    rocm_dependencies = next((param['default'] for param in parameters if param['name'] == 'rocmDependencies' or param['name'] == 'rocmDependenciesAMD'), [])
-                    test_dependencies = next((param['default'] for param in parameters if param['name'] == 'rocmTestDependencies'), [])
-
-                    unique_dependencies = list(set(rocm_dependencies + test_dependencies))
-                    unique_dependencies = [dep for dep in unique_dependencies if dep not in exclude_nodes]
-
-                    # Use the mapped component name if it exists
-                    component_name = component_name_mapping.get(filename, os.path.splitext(filename)[0])
-                    dependencies[component_name] = {
-                        'dependencies': unique_dependencies
-                    }
-                    debug_print(f"Found unique dependencies for {component_name}: {unique_dependencies}")
-            except Exception as e:
-                print(f"Error processing {filename}: {e}")
-
-    return dependencies
-
-def simplify_dependencies(graph):
-    simplified_graph = {}
-
-    for component, deps in graph.items():
-        if component not in simplified_graph:
-            simplified_graph[component] = set(deps)  # Use a set for uniqueness
-
-        for dep in deps:
-            if dep in graph:  # If the dependency has its own dependencies
-                for sub_dep in graph[dep]:
-                    simplified_graph[component].discard(sub_dep)  # Remove transitive dependencies
-
-    # Convert sets back to lists
-    for component in simplified_graph:
-        simplified_graph[component] = list(simplified_graph[component])
-
-    return simplified_graph
-
-def build_dependency_graph(dependencies, exclude_nodes=None):
-    if exclude_nodes is None:
-        exclude_nodes = []
-
-    graph = {}
-    debug_print("Building dependency graph...")
-
-    for component, deps in dependencies.items():
-        if component in exclude_nodes:
-            continue  # Skip excluded components
-
-        # Ensure uniqueness and prevent self-dependency
-        all_deps = [dep for dep in set(deps['dependencies']) if dep != component and dep not in exclude_nodes]
-        graph[component] = all_deps
-        debug_print(f"{component} -> {all_deps}")
-
-    # Simplify the dependencies to remove transitive dependencies
-    simplified_graph = simplify_dependencies(graph)
-
-    return simplified_graph
-
-def build_full_dependency_tree(graph):
-    tree = {}
-    debug_print("Building full dependency tree...")
-
-    def dfs(component, visited):
-        if component in visited:
-            return
-        visited.add(component)
-        for dep in graph.get(component, []):
-            # Prevent self-dependency in the tree
-            if dep != component:
-                if dep not in tree:
-                    tree[dep] = []
-                if component not in tree[dep]:  # Prevent duplicates
-                    tree[dep].append(component)
-                dfs(dep, visited)
-
-    for component in graph.keys():
-        dfs(component, set())
-
-    return tree
-
-def visualize_graph(graph):
-    dot = Digraph()
-
-    # sort edges for consistent dot file hash
-    for component in sorted(graph):
-        for dep in sorted(graph[component]):
-            dot.edge(component, dep)
-
-    script_directory = os.path.dirname(os.path.abspath(__file__))
-
-    # make an input dot file for comparisons
-    dot_file_path = os.path.join(script_directory, 'input.dot')
-    with open(dot_file_path, 'w') as f:
-        f.write(dot.source)
-
-    dot.render(os.path.join(script_directory, 'dependency_graph'), format='png', cleanup=True)  # Save as PNG
-
-def main():
-    exclude_deps = ['rocm-examples']
-    dependencies = extract_dependencies(exclude_nodes=exclude_deps)
-
-    if not dependencies:
-        debug_print("No dependencies found.")
-        return
-
-    graph = build_dependency_graph(dependencies, exclude_nodes=exclude_deps)
-    full_tree = build_full_dependency_tree(graph)
-
-    print("Dependency tree:")
-    print(full_tree)
-
-    # Call this function after building the graph
-    visualize_graph(full_tree)
-
-if __name__ == "__main__":
-    main()

.azuredevops/scripts/dependency_graph.dot

@@ -1,94 +0,0 @@
-digraph {
-	AMDMIGraphX -> MIVisionX
-	HIPIFY -> rccl
-	MIOpen -> AMDMIGraphX
-	MIVisionX -> rocAL
-	"ROCR-Runtime" -> clr
-	"ROCR-Runtime" -> rocminfo
-	ROCdbgapi -> ROCgdb
-	ROCdbgapi -> rocprofiler
-	ROCdbgapi -> rocr_debug_agent
-	ROCgdb -> aomp
-	ROCmValidationSuite -> rdc
-	amdsmi -> aomp
-	amdsmi -> rdc
-	aomp -> hipBLASLt
-	aomp -> rccl
-	aomp -> rocFFT
-	aomp -> rpp
-	"aomp-extras" -> rccl
-	"aomp-extras" -> rocBLAS
-	clr -> ROCdbgapi
-	clr -> composable_kernel
-	clr -> half
-	clr -> "hip-tests"
-	clr -> "hipBLAS-common"
-	clr -> rocDecode
-	clr -> rocMLIR
-	clr -> rocPRIM
-	clr -> rocRAND
-	clr -> rocm_bandwidth_test
-	clr -> roctracer
-	composable_kernel -> MIOpen
-	composable_kernel -> hipTensor
-	half -> MIOpen
-	half -> rpp
-	hipBLAS -> MIOpen
-	hipBLAS -> hipfort
-	"hipBLAS-common" -> hipBLASLt
-	hipBLASLt -> rocBLAS
-	hipFFT -> hipfort
-	hipRAND -> ROCmValidationSuite
-	hipRAND -> rocFFT
-	hipRAND -> rocThrust
-	hipSOLVER -> hipfort
-	hipSPARSE -> hipSPARSELt
-	hipSPARSE -> rocSOLVER
-	hipTensor -> rpp
-	"llvm-project" -> "ROCR-Runtime"
-	"llvm-project" -> "aomp-extras"
-	rccl -> omnitrace
-	rccl -> "rocprofiler-sdk"
-	rocBLAS -> ROCmValidationSuite
-	rocBLAS -> rocSPARSE
-	rocBLAS -> rocWMMA
-	rocDecode -> MIVisionX
-	rocDecode -> rocPyDecode
-	rocFFT -> hipFFT
-	rocMLIR -> MIOpen
-	rocPRIM -> hipCUB
-	rocPRIM -> rocSPARSE
-	rocPRIM -> rocThrust
-	rocRAND -> MIOpen
-	rocRAND -> hipRAND
-	rocRAND -> rocALUTION
-	rocSOLVER -> hipBLAS
-	rocSOLVER -> hipSOLVER
-	rocSPARSE -> hipSPARSE
-	rocSPARSE -> rocALUTION
-	"rocm-cmake" -> "llvm-project"
-	"rocm-core" -> aomp
-	"rocm-core" -> rocDecode
-	"rocm-core" -> rocprofiler
-	rocm_smi_lib -> "ROCR-Runtime"
-	rocminfo -> ROCdbgapi
-	rocminfo -> composable_kernel
-	rocminfo -> half
-	rocminfo -> "hip-tests"
-	rocminfo -> "hipBLAS-common"
-	rocminfo -> rocDecode
-	rocminfo -> rocMLIR
-	rocminfo -> rocPRIM
-	rocminfo -> rocRAND
-	rocminfo -> rocm_bandwidth_test
-	rocminfo -> roctracer
-	rocprofiler -> hipfort
-	rocprofiler -> omniperf
-	rocprofiler -> omnitrace
-	rocprofiler -> rdc
-	"rocprofiler-register" -> "ROCR-Runtime"
-	roctracer -> aomp
-	roctracer -> rocprofiler
-	roctracer -> "rocprofiler-sdk"
-	rpp -> MIVisionX
-}

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

@@ -64,8 +64,7 @@ parameters:
     rocm_bandwidth_test: master
     rocm_smi_lib: develop
     rocPRIM: develop
-    rocprofiler-register: amd-staging
-    rocprofiler-sdk: amd-staging
+    rocprofiler-register: amd-mainline
     rocprofiler: amd-staging
     rocPyDecode: develop
     ROCR-Runtime: amd-staging

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

@@ -73,7 +73,6 @@ parameters:
     rocm_smi_lib: $(ROCM_SMI_LIB_PIPELINE_ID)
     rocPRIM: $(ROCPRIM_PIPELINE_ID)
     rocprofiler-register: $(ROCPROFILER_REGISTER_PIPELINE_ID)
-    rocprofiler-sdk: $(ROCPROFILER_SDK_PIPELINE_ID)
     rocprofiler: $(ROCPROFILER_PIPELINE_ID)
     rocPyDecode: $(ROCPYDECODE_PIPELINE_ID)
     ROCR-Runtime: $(ROCR_RUNTIME_PIPELINE_ID)
@@ -133,7 +132,6 @@ parameters:
     rocm_smi_lib: $(ROCM_SMI_LIB_TAGGED_PIPELINE_ID)
     rocPRIM: $(ROCPRIM_TAGGED_PIPELINE_ID)
     rocprofiler-register: $(ROCPROFILER_REGISTER_TAGGED_PIPELINE_ID)
-    rocprofiler-sdk: $(ROCPROFILER_SDK_TAGGED_PIPELINE_ID)
     rocprofiler: $(ROCPROFILER_TAGGED_PIPELINE_ID)
     rocPyDecode: $(ROCPYDECODE_TAGGED_PIPELINE_ID)
     ROCR-Runtime: $(ROCR_RUNTIME_TAGGED_PIPELINE_ID)
@@ -180,7 +178,6 @@ parameters:
     - rocFFT
     - rocm-examples
     - rocPRIM
-    - rocprofiler-sdk
     - rocprofiler
     - rocPyDecode
     - rocRAND

.azuredevops/variables-global.yml

@@ -259,10 +259,6 @@ variables:
   value: 1
 - name: ROCPROFILER_REGISTER_TAGGED_PIPELINE_ID
   value: 25
-- name: ROCPROFILER_SDK_PIPELINE_ID
-  value: 246
-- name: ROCPROFILER_SDK_TAGGED_PIPELINE_ID
-  value: 234
 - name: ROCPROFILER_PIPELINE_ID
   value: 143
 - name: ROCPROFILER_TAGGED_PIPELINE_ID

.wordlist.txt

@@ -36,6 +36,7 @@ Bluefield
 Bootloader
 CCD
 CDNA
+CHTML
 CIFAR
 CLI
 CLion
@@ -70,6 +71,7 @@ Concretized
 Conda
 ConnectX
 CuPy
+Dashboarding
 DDR
 DF
 DGEMM
@@ -227,6 +229,7 @@ Mellanox's
 Meta's
 Miniconda
 MirroredStrategy
+Mixtral
 Multicore
 Multithreaded
 MyEnvironment
@@ -272,6 +275,8 @@ OpenMPI
 OpenSSL
 OpenVX
 OpenXLA
+Oversubscription
+PagedAttention
 PCC
 PCI
 PCIe
@@ -293,6 +298,7 @@ PowerShell
 PyPi
 PyTorch
 Qcycles
+Qwen
 RAII
 RAS
 RCCL
@@ -562,6 +568,7 @@ hipfort
 hipify
 hipsolver
 hipsparse
+hlist
 hotspotting
 hpc
 hpp
@@ -585,6 +592,7 @@ intra
 invariants
 invocating
 ipo
+jax
 kdb
 kfd
 latencies
@@ -605,6 +613,7 @@ migraphx
 miopen
 miopengemm
 mivisionx
+mjx
 mkdir
 mlirmiopen
 mtypes
@@ -620,6 +629,7 @@ openmp
 openssl
 optimizers
 os
+oversubscription
 pageable
 parallelization
 parameterization

README.md

@@ -76,7 +76,7 @@ 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=6.2.2 # Or 6.2.0 or 6.2.1
+export ROCM_VERSION=6.2.1
 ~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.2.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
 ~/bin/repo sync
 

RELEASE.md

@@ -80,14 +80,16 @@ The [ROCm Offline Installer Creator 6.2.1](https://rocm.docs.amd.com/projects/in
 
 #### ROCm documentation changes 
 
-There have been no changes to supported hardware or operating systems from ROCm 6.2.0 to ROCm 6.2.1.
+The HIP documentation has been updated with several new topics aimed at improving usability
+and providing more detailed information.
 
 * The Programming Model Reference and Understanding the Programming Model topics in HIP have been consolidated into one topic,
 [HIP programming model (conceptual)](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/understand/programming_model.html). 
+
 * The [HIP virtual memory management](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/how-to/virtual_memory.html) and [HIP virtual memory management API](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/reference/virtual_memory_reference.html) topics have been added.
 
 ```{note}
-The ROCm documentation, like all ROCm projects, is open source and available on GitHub. To contribute to ROCm documentation, see the [ROCm documentation contribution guidelines](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).
+To contribute to ROCm documentation, see the [ROCm documentation contribution guidelines](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).
 ```
 
 ### Operating system and hardware support changes
@@ -324,7 +326,7 @@ Click the component's updated version to go to a detailed list of its changes. C
             </tr>
             <tr>
                 <td><a href="https://rocm.docs.amd.com/projects/rdc/en/docs-6.2.1">ROCm Data Center Tool</a></td>
-                <td>1.0.0</td>
+                <td>0.3.0</td>
                 <td><a href="https://github.com/ROCm/rdc/releases/tag/rocm-6.2.1"><i
                             class="fab fa-github fa-lg"></i></a></td>
             </tr>

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

@@ -1,117 +1,117 @@
-ROCm Version,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 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,
-      ,"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 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
-      ,"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 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 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-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
-      ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
-      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
-      ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
-      ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
-      ,.. _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
-      ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
-      ,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]_
-      ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
-      ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
-      ,,,,,,,,
-      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,
-      :doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"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 <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"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 <rocm-install-on-linux:install/3rd-party/jax-install>`,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>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
-      ,,,,,,,,
-      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,>=1.2.0,>=1.2.0
-      `UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.15.0,>=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,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      CUB,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      ,,,,,,,,
-      KFD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,
-      Tested user space versions,"6.1.x, 6.0.x","6.1.x, 6.0.x","6.1.x, 6.0.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x, 5.6.x","6.2.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
-      :doc:`MIGraphX <amdmigraphx:index>`,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>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`MIVisionX <mivisionx:index>`,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
-      :doc:`rocAL <rocal:index>`,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`rocDecode <rocdecode:index>`,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
-      :doc:`rocPyDecode <rocpydecode:index>`,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A
-      :doc:`RPP <rpp:index>`,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
-      ,,,,,,,,
-      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,
-      :doc:`RCCL <rccl:index>`,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
-      ,,,,,,,,
-      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
-      :doc:`hipBLAS <hipblas:index>`,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>`,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
-      :doc:`hipFFT <hipfft:index>`,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
-      :doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
-      :doc:`hipRAND <hiprand:index>`,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
-      :doc:`hipSOLVER <hipsolver:index>`,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
-      :doc:`hipSPARSE <hipsparse:index>`,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.1,0.2.1,0.2.1,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
-      :doc:`rocALUTION <rocalution:index>`,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
-      :doc:`rocBLAS <rocblas:index>`,4.2.1,4.2.1,4.2.0,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
-      :doc:`rocFFT <rocfft:index>`,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
-      :doc:`rocRAND <rocrand:index>`,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
-      :doc:`rocSOLVER <rocsolver:index>`,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
-      :doc:`rocSPARSE <rocsparse:index>`,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
-      :doc:`rocWMMA <rocwmma:index>`,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
-      `Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
-      ,,,,,,,,
-      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,
-      :doc:`hipCUB <hipcub:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`hipTensor <hiptensor:index>`,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
-      :doc:`rocPRIM <rocprim:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`rocThrust <rocthrust:index>`,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      ,,,,,,,,
-      SUPPORT LIBS,,,,,,,,
-      `hipother <https://github.com/ROCm/hipother>`_,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.2,6.2.1,6.2.0,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
-      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.4.05,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
-      ,,,,,,,,
-      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,
-      :doc:`AMD SMI <amdsmi:index>`,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.0.0,1.0.0,1.0.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
-      :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
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,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>`,rocm-6.2.2,rocm-6.2.1,rocm-6.2.0,rocm-6.1.2,rocm-6.1.1,rocm-6.1.0,rocm-6.0.2,rocm-6.0.0
-      ,,,,,,,,
-      PERFORMANCE TOOLS,,,,,,,,
-      :doc:`Omniperf <omniperf:index>`,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A
-      :doc:`Omnitrace <omnitrace:index>`,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A
-      :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
-      :doc:`ROCProfiler <rocprofiler:index>`,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>`,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCTracer <roctracer:index>`,4.1.60202,4.1.60201,4.1.60200,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
-      ,,,,,,,,
-      DEVELOPMENT TOOLS,,,,,,,,
-      :doc:`HIPIFY <hipify:index>`,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>`,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,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>`_,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,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
-      ,,,,,,,,
-      COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,
-      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,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>`,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      `Flang <https://github.com/ROCm/flang>`_,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>`,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      ,,,,,,,,
-      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,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>`,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `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
-      :doc:`ROCR-Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
+ROCm Version,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 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,,
+      ,"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 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
+      ,"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 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 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-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
+      ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
+      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
+      ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
+      ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
+      ,.. _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
+      ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
+      ,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
+      ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
+      ,,,,,,,,,
+      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,
+      :doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"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 <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"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 <rocm-install-on-linux:install/3rd-party/jax-install>`,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>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
+      ,,,,,,,,,
+      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,>=1.2.0,>=1.2.0
+      `UCX <https://github.com/ROCm/ucx>`_,>=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,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      CUB,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      ,,,,,,,,,
+      KFD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,
+      Tested user space versions,"6.1.x, 6.0.x","6.1.x, 6.0.x","6.1.x, 6.0.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x, 5.6.x","6.2.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
+      :doc:`MIGraphX <amdmigraphx:index>`,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>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`MIVisionX <mivisionx:index>`,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
+      :doc:`rocAL <rocal:index>`,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`rocDecode <rocdecode:index>`,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
+      :doc:`rocPyDecode <rocpydecode:index>`,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>`,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
+      ,,,,,,,,,
+      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,
+      :doc:`RCCL <rccl:index>`,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
+      ,,,,,,,,,
+      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
+      :doc:`hipBLAS <hipblas:index>`,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>`,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
+      :doc:`hipFFT <hipfft:index>`,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
+      :doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
+      :doc:`hipRAND <hiprand:index>`,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
+      :doc:`hipSOLVER <hipsolver:index>`,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
+      :doc:`hipSPARSE <hipsparse:index>`,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
+      :doc:`rocALUTION <rocalution:index>`,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
+      :doc:`rocBLAS <rocblas:index>`,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
+      :doc:`rocFFT <rocfft:index>`,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
+      :doc:`rocRAND <rocrand:index>`,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
+      :doc:`rocSOLVER <rocsolver:index>`,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
+      :doc:`rocSPARSE <rocsparse:index>`,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
+      :doc:`rocWMMA <rocwmma:index>`,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
+      `Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
+      ,,,,,,,,,
+      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,
+      :doc:`hipCUB <hipcub:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`hipTensor <hiptensor:index>`,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
+      :doc:`rocPRIM <rocprim:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`rocThrust <rocthrust:index>`,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      ,,,,,,,,,
+      SUPPORT LIBS,,,,,,,,,
+      `hipother <https://github.com/ROCm/hipother>`_,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.4.05,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
+      ,,,,,,,,,
+      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,
+      :doc:`AMD SMI <amdsmi:index>`,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
+      :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
+      :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
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,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>`,rocm-6.2.2,rocm-6.2.1,rocm-6.2.0,rocm-6.1.5,rocm-6.1.2,rocm-6.1.1,rocm-6.1.0,rocm-6.0.2,rocm-6.0.0
+      ,,,,,,,,,
+      PERFORMANCE TOOLS,,,,,,,,,
+      :doc:`Omniperf <omniperf:index>`,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Omnitrace <omnitrace:index>`,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
+      :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
+      :doc:`ROCProfiler <rocprofiler:index>`,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>`,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCTracer <roctracer:index>`,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
+      ,,,,,,,,,
+      DEVELOPMENT TOOLS,,,,,,,,,
+      :doc:`HIPIFY <hipify:index>`,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,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>`_,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,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
+      ,,,,,,,,,
+      COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,,
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,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>`,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      `Flang <https://github.com/ROCm/flang>`_,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`llvm-project <llvm-project:index>`,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      ,,,,,,,,,
+      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,
+      :doc:`AMD CLR <hip:understand/amd_clr>`,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      :doc:`HIP <hip:index>`,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `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
+      :doc:`ROCR-Runtime <rocr-runtime:index>`,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

@@ -10,10 +10,7 @@ Use this matrix to view the ROCm compatibility and system requirements across su
 
 You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-rocm-compatibility-matrix>`.
 
-
-.. note::
-
-   Like AMD Instinct accelerators, AMD Radeon and Radeon Pro GPUs can be used in environments for compute purposes (no display information or graphics). If using AMD Radeon or Radeon Pro GPUs with ROCm for graphics-related purposes (for example, display connected), review the `Compatibility matrices <https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility.html>`_ in the Use ROCm on Radeon GPU documentation to confirm system requirements.
+Accelerators and GPUs listed in the following table support compute workloads (no display information or graphics). If you’re using ROCm with AMD Radeon or Radeon Pro GPUs for graphics workloads, see the `Use ROCm on Radeon GPU documentation <https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility.html>`_ to verify compatibility and system requirements.
 
 .. |br| raw:: html
 
@@ -108,7 +105,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
       ,,,
       SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix:,,
       :doc:`AMD SMI <amdsmi:index>`,24.6.3,24.6.3,24.4.1
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.0.0,1.0.0,0.3.0
+      :doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0
       :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
       :doc:`ROCm SMI <rocm_smi_lib:index>`,7.3.0,7.3.0,7.0.0
       :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.2.2,rocm-6.2.1,rocm-6.1.0
@@ -150,7 +147,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
 .. [#mi300_622] **For ROCm 6.2.2** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
 .. [#mi300_621] **For ROCm 6.2.1** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
 .. [#mi300_610] **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.
-.. [#kfd_support] ROCm provides forward and backward compatibility between the Kernel Fusion Driver (KFD) 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 Kernel Fusion Driver (KFD) 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>`_.
 
 
 .. _OS-kernel-versions:
@@ -227,4 +224,4 @@ 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 Kernel Fusion Driver (KFD) 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 Kernel Fusion Driver (KFD) 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>`_.

docs/conceptual/ai-migraphx-optimization.md

@@ -1,333 +0,0 @@
-<head>
-  <meta charset="UTF-8">
-  <meta name="description" content="Inference optimization with MIGraphX">
-  <meta name="keywords" content="Inference optimization, MIGraphX, deep-learning, MIGraphX
-  installation, AMD, ROCm">
-</head>
-
-# Inference optimization with MIGraphX
-
-The following sections cover inferencing and introduces [MIGraphX](https://rocm.docs.amd.com/projects/AMDMIGraphX/en/latest/).
-
-## Inference
-
-The inference is where capabilities learned during deep-learning training are put to work. It refers to using a fully trained neural network to make conclusions (predictions) on unseen data that the model has never interacted with before. Deep-learning inferencing is achieved by feeding new data, such as new images, to the network, giving the Deep Neural Network a chance to classify the image.
-
-Taking our previous example of MNIST, the DNN can be fed new images of handwritten digit images, allowing the neural network to classify digits. A fully trained DNN should make accurate predictions about what an image represents, and inference cannot happen without training.
-
-## MIGraphX introduction
-
-MIGraphX is a graph compiler focused on accelerating the machine-learning inference that can target AMD GPUs and CPUs. MIGraphX accelerates the machine-learning models by leveraging several graph-level transformations and optimizations. These optimizations include:
-
-* Operator fusion
-* Arithmetic simplifications
-* Dead-code elimination
-* Common subexpression elimination (CSE)
-* Constant propagation
-
-After doing all these transformations, MIGraphX emits code for the AMD GPU by calling to MIOpen or rocBLAS or creating HIP kernels for a particular operator. MIGraphX can also target CPUs using DNNL or ZenDNN libraries.
-
-MIGraphX provides easy-to-use APIs in C++ and Python to import machine models in ONNX or TensorFlow. Users can compile, save, load, and run these models using the MIGraphX C++ and Python APIs. Internally, MIGraphX parses ONNX or TensorFlow models into internal graph representation where each operator in the model gets mapped to an operator within MIGraphX. Each of these operators defines various attributes such as:
-
-* Number of arguments
-* Type of arguments
-* Shape of arguments
-
-After optimization passes, all these operators get mapped to different kernels on GPUs or CPUs.
-
-After importing a model into MIGraphX, the model is represented as `migraphx::program`. `migraphx::program` is made up of `migraphx::module`. The program can consist of several modules, but it always has one main_module. Modules are made up of `migraphx::instruction_ref`. Instructions contain the `migraphx::op` and arguments to the operator.  
-
-## Installing MIGraphX
-
-There are three options to get started with MIGraphX installation. MIGraphX depends on ROCm libraries; assume that the machine has ROCm installed.
-
-### Option 1: installing binaries
-
-To install MIGraphX on Debian-based systems like Ubuntu, use the following command:
-
-```bash
-sudo apt update && sudo apt install -y migraphx
-```
-
-The header files and libraries are installed under `/opt/rocm-\<version\>`, where \<version\> is the ROCm version.
-
-### Option 2: building from source
-
-There are two ways to build the MIGraphX sources.
-
-* [Use the ROCm build tool](https://github.com/ROCm/AMDMIGraphX#use-the-rocm-build-tool-rbuild) - This approach uses `[rbuild](https://github.com/ROCm/rbuild)` to install the prerequisites and build the libraries with just one command.
-
-  or
-
-* [Use CMake](https://github.com/ROCm/AMDMIGraphX#use-cmake-to-build-migraphx) - This approach uses a script to install the prerequisites, then uses CMake to build the source.
-
-For detailed steps on building from source and installing dependencies, refer to the following `README` file:
-
-[https://github.com/ROCm/AMDMIGraphX#building-from-source](https://github.com/ROCm/AMDMIGraphX#building-from-source)
-
-### Option 3: use docker
-
-To use Docker, follow these steps:
-
-1. The easiest way to set up the development environment is to use Docker. To build Docker from scratch, first clone the MIGraphX repository by running:
-
-    ```bash
-    git clone --recursive https://github.com/ROCm/AMDMIGraphX
-    ```
-
-2. The repository contains a Dockerfile from which you can build a Docker image as:
-
-    ```bash
-    docker build -t migraphx .
-    ```
-
-3. Then to enter the development environment, use Docker run:
-
-    ```bash
-    docker run --device='/dev/kfd' --device='/dev/dri' -v=`pwd`:/code/AMDMIGraphX -w /code/AMDMIGraphX --group-add video -it migraphx
-    ```
-
-The Docker image contains all the prerequisites required for the installation, so users can go to the folder `/code/AMDMIGraphX` and follow the steps mentioned in [Option 2: Building from Source](#option-2-building-from-source).
-
-## MIGraphX example
-
-MIGraphX provides both C++ and Python APIs. The following sections show examples of both using the Inception v3 model. To walk through the examples, fetch the Inception v3 ONNX model by running the following:
-
-```py
-import torch
-import torchvision.models as models
-inception = models.inception_v3(pretrained=True)
-torch.onnx.export(inception,torch.randn(1,3,299,299), "inceptioni1.onnx")
-```
-
-This will create `inceptioni1.onnx`, which can be imported in MIGraphX using C++ or Python API.
-
-### MIGraphX Python API
-
-Follow these steps:
-
-1. To import the MIGraphX module in Python script, set `PYTHONPATH` to the MIGraphX libraries installation. If binaries are installed using steps mentioned in [Option 1: Installing Binaries](#option-1-installing-binaries), perform the following action:
-
-    ```bash
-    export PYTHONPATH=$PYTHONPATH:/opt/rocm/
-    ```
-
-2. The following script shows the usage of Python API to import the ONNX model, compile it, and run inference on it. Set `LD_LIBRARY_PATH` to `/opt/rocm/` if required.
-
-    ```py
-    # import migraphx and numpy
-    import migraphx
-    import numpy as np
-    # import and parse inception model
-    model = migraphx.parse_onnx("inceptioni1.onnx")
-    # compile model for the GPU target
-    model.compile(migraphx.get_target("gpu"))
-    # optionally print compiled model
-    model.print()
-    # create random input image
-    input_image = np.random.rand(1, 3, 299, 299).astype('float32')
-    # feed image to model, 'x.1` is the input param name
-    results = model.run({'x.1': input_image})
-    # get the results back
-    result_np = np.array(results[0])
-    # print the inferred class of the input image
-    print(np.argmax(result_np))
-    ```
-
-    Find additional examples of Python API in the `/examples` directory of the MIGraphX repository.
-
-## MIGraphX C++ API
-
-Follow these steps:
-
-1. The following is a minimalist example that shows the usage of MIGraphX C++ API to load ONNX file, compile it for the GPU, and run inference on it. To use MIGraphX C++ API, you only need to load the `migraphx.hpp` file. This example runs inference on the Inception v3 model.
-
-    ```c++
-    #include <vector>
-    #include <string>
-    #include <algorithm>
-    #include <ctime>
-    #include <random>
-    #include <migraphx/migraphx.hpp>
-
-    int main(int argc, char** argv)
-    {
-        migraphx::program prog;
-        migraphx::onnx_options onnx_opts;
-        // import and parse onnx file into migraphx::program
-        prog = parse_onnx("inceptioni1.onnx", onnx_opts);
-        // print imported model
-        prog.print();
-        migraphx::target targ = migraphx::target("gpu");
-        migraphx::compile_options comp_opts;
-        comp_opts.set_offload_copy();
-        // compile for the GPU
-        prog.compile(targ, comp_opts);
-        // print the compiled program
-        prog.print();
-        // randomly generate input image
-        // of shape (1, 3, 299, 299)
-        std::srand(unsigned(std::time(nullptr)));
-        std::vector<float> input_image(1*299*299*3);
-        std::generate(input_image.begin(), input_image.end(), std::rand);
-        // users need to provide data for the input
-        // parameters in order to run inference
-        // you can query into migraph program for the parameters
-        migraphx::program_parameters prog_params;
-        auto param_shapes = prog.get_parameter_shapes();
-        auto input        = param_shapes.names().front();
-        // create argument for the parameter
-        prog_params.add(input, migraphx::argument(param_shapes[input], input_image.data()));
-        // run inference
-        auto outputs = prog.eval(prog_params);
-        // read back the output
-        float* results = reinterpret_cast<float*>(outputs[0].data());
-        float* max     = std::max_element(results, results + 1000);
-        int answer = max - results;
-        std::cout << "answer: " << answer << std::endl;
-    }
-    ```
-
-2. To compile this program, you can use CMake and you only need to link the `migraphx::c` library to use MIGraphX's C++ API. The following is the `CMakeLists.txt` file that can build the earlier example:
-
-    ```cmake
-    cmake_minimum_required(VERSION 3.5)
-    project (CAI)
-
-    set (CMAKE_CXX_STANDARD 14)
-    set (EXAMPLE inception_inference)
-
-    list (APPEND CMAKE_PREFIX_PATH /opt/rocm/hip /opt/rocm)
-    find_package (migraphx)
-
-    message("source file: " ${EXAMPLE}.cpp " ---> bin: " ${EXAMPLE})
-    add_executable(${EXAMPLE} ${EXAMPLE}.cpp)
-
-    target_link_libraries(${EXAMPLE} migraphx::c)
-    ```
-
-3. To build the executable file, run the following from the directory containing the `inception_inference.cpp` file:
-
-    ```bash
-    mkdir build
-    cd build
-    cmake ..
-    make -j$(nproc)
-    ./inception_inference
-    ```
-
-:::{note}
-    Set `LD_LIBRARY_PATH` to `/opt/rocm/lib` if required during the build. Additional examples can be found in the MIGraphX repository under the `/examples/` directory.
-:::
-
-## Tuning MIGraphX
-
-MIGraphX uses MIOpen kernels to target AMD GPU. For the model compiled with MIGraphX, tune MIOpen to pick the best possible kernel implementation. The MIOpen tuning results in a significant performance boost. Tuning can be done by setting the environment variable `MIOPEN_FIND_ENFORCE=3`.
-
-:::{note}
-    The tuning process can take a long time to finish.
-:::
-
-**Example:** The average inference time of the inception model example shown previously over 100 iterations using untuned kernels is 0.01383ms. After tuning, it reduces to 0.00459ms, which is a 3x improvement. This result is from ROCm v4.5 on a MI100 GPU.
-
-:::{note}
-    The results may vary depending on the system configurations.
-:::
-
-For reference, the following code snippet shows inference runs for only the first 10 iterations for both tuned and untuned kernels:
-
-```console
-### UNTUNED ###
-iterator : 0
-Inference complete
-Inference time: 0.063ms
-iterator : 1
-Inference complete
-Inference time: 0.008ms
-iterator : 2
-Inference complete
-Inference time: 0.007ms
-iterator : 3
-Inference complete
-Inference time: 0.007ms
-iterator : 4
-Inference complete
-Inference time: 0.007ms
-iterator : 5
-Inference complete
-Inference time: 0.008ms
-iterator : 6
-Inference complete
-Inference time: 0.007ms
-iterator : 7
-Inference complete
-Inference time: 0.028ms
-iterator : 8
-Inference complete
-Inference time: 0.029ms
-iterator : 9
-Inference complete
-Inference time: 0.029ms
-
-### TUNED ###
-iterator : 0
-Inference complete
-Inference time: 0.063ms
-iterator : 1
-Inference complete
-Inference time: 0.004ms
-iterator : 2
-Inference complete
-Inference time: 0.004ms
-iterator : 3
-Inference complete
-Inference time: 0.004ms
-iterator : 4
-Inference complete
-Inference time: 0.004ms
-iterator : 5
-Inference complete
-Inference time: 0.004ms
-iterator : 6
-Inference complete
-Inference time: 0.004ms
-iterator : 7
-Inference complete
-Inference time: 0.004ms
-iterator : 8
-Inference complete
-Inference time: 0.004ms
-iterator : 9
-Inference complete
-Inference time: 0.004ms
-```
-
-### YModel
-
-The best inference performance through MIGraphX is conditioned upon having tuned kernel configurations stored in a `/home` local User Database (DB). If a user were to move their model to a different server or allow a different user to use it, they would have to run through the MIOpen tuning process again to populate the next User DB with the best kernel configurations and corresponding solvers.
-
-Tuning is time consuming, and if the users have not performed tuning, they would see discrepancies between expected or claimed inference performance and actual inference performance. This has led to repetitive and time-consuming tuning tasks for each user.
-
-MIGraphX introduces a feature, known as YModel, that stores the kernel config parameters found during tuning into a `.mxr` file. This ensures the same level of expected performance, even when a model is copied to a different user/system.
-
-The YModel feature is available starting from ROCm 5.4.1 and UIF 1.1.
-
-#### YModel example
-
-Through the `migraphx-driver` functionality, you can generate `.mxr` files with tuning information stored inside it by passing additional `--binary --output model.mxr` to `migraphx-driver` along with the rest of the necessary flags.
-
-For example, to generate `.mxr` file from the ONNX model, use the following:
-
-```bash
-./path/to/migraphx-driver compile --onnx resnet50.onnx --enable-offload-copy --binary --output resnet50.mxr
-```
-
-To run generated `.mxr` files through `migraphx-driver`, use the following:
-
-```bash
-./path/to/migraphx-driver run --migraphx resnet50.mxr --enable-offload-copy
-```
-
-Alternatively, you can use the MIGraphX C++ or Python API to generate `.mxr` files.
-
-![Generating an MXR file](../data/conceptual/image018.png "Generating an MXR file")

docs/conceptual/oversubscription.rst

@@ -0,0 +1,34 @@
+.. meta::
+   :description: Learn what causes oversubscription.
+   :keywords: warning, log, gpu, performance penalty, help
+
+*******************************************************************
+Oversubscription of hardware resources in AMD Instinct accelerators
+*******************************************************************
+
+When an AMD Instinct™ MI series accelerator enters an oversubscribed state, the ``amdgpu`` driver outputs the following
+message.
+
+``amdgpu: Runlist is getting oversubscribed. Expect reduced ROCm performance.``
+
+Oversubscription occurs when application demands exceed the available hardware resources. In an oversubscribed
+state, the hardware scheduler tries to manage resource usage in a round-robin fashion. However,
+this can result in reduced performance, as resources might be occupied by applications or queues not actively
+submitting work. The granularity of hardware resources occupied by an inactive queue can be in the order of
+milliseconds, during which the accelerator or GPU is effectively blocked and unable to process work submitted by other
+queues.
+
+What triggers oversubscription?
+===============================
+
+The system enters an oversubscribed state when one of the following conditions is met:
+
+* **Hardware queue limit exceeded**: The number of user-mode compute queues requested by applications exceeds the
+  hardware limit of 24 queues for current Instinct accelerators.
+
+* **Virtual memory context slots exceeded**: The number of user processes exceeds the number of available virtual memory
+  context slots, which is 11 for current Instinct accelerators.
+
+* **Multiple processes using cooperative workgroups**: More than one process attempts to use the cooperative workgroup
+  feature, leading to resource contention.
+

docs/conf.py

@@ -81,6 +81,7 @@ article_pages = [
         "file": "how-to/llm-fine-tuning-optimization/profiling-and-debugging",
         "os": ["linux"],
     },
+    {"file": "how-to/performance-validation/mi300x/vllm-benchmark", "os": ["linux"]},
     {"file": "how-to/system-optimization/index", "os": ["linux"]},
     {"file": "how-to/system-optimization/mi300x", "os": ["linux"]},
     {"file": "how-to/system-optimization/mi200", "os": ["linux"]},

docs/contribute/building.md

@@ -0,0 +1,150 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="Building ROCm documentation">
+  <meta name="keywords" content="documentation, Visual Studio Code, GitHub, command line,
+  AMD, ROCm">
+</head>
+
+# Building documentation
+
+## GitHub
+
+If you open a pull request and scroll down to the summary panel,
+there is a commit status section. Next to the line
+`docs/readthedocs.com:advanced-micro-devices-demo`, there is a `Details` link.
+If you click this, it takes you to the Read the Docs build for your pull request.
+
+![GitHub PR commit status](../data/contribute/commit-status.png)
+
+If you don't see this line, click `Show all checks` to get an itemized view.
+
+## Command line
+
+You can build our documentation via the command line using Python.
+
+See the `build.tools.python` setting in the [Read the Docs configuration file](https://github.com/ROCm/ROCm/blob/develop/.readthedocs.yaml) for the Python version used by Read the Docs to build documentation.
+
+See the [Python requirements file](https://github.com/ROCm/ROCm/blob/develop/docs/sphinx/requirements.txt) for Python packages needed to build the documentation.
+
+Use the Python Virtual Environment (`venv`) and run the following commands from the project root:
+
+```sh
+python3 -mvenv .venv
+
+.venv/bin/python     -m pip install -r docs/sphinx/requirements.txt
+.venv/bin/python     -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
+```
+
+Navigate to `_build/html/index.html` and open this file in a web browser.
+
+## Visual Studio Code
+
+With the help of a few extensions, you can create a productive environment to author and test
+documentation locally using Visual Studio (VS) Code. Follow these steps to configure VS Code:
+
+1. Install the required extensions:
+
+   * Python: `(ms-python.python)`
+   * Live Server: `(ritwickdey.LiveServer)`
+
+2. Add the following entries to `.vscode/settings.json`.
+
+    ```json
+      {
+        "liveServer.settings.root": "/.vscode/build/html",
+        "liveServer.settings.wait": 1000,
+        "python.terminal.activateEnvInCurrentTerminal": true
+      }
+    ```
+
+    * `liveServer.settings.root`: Sets the root of the output website for live previews. Must be changed
+      alongside the `tasks.json` command.
+    * `liveServer.settings.wait`: Tells the live server to wait with the update in order to give Sphinx time to
+      regenerate the site contents and not refresh before the build is complete.
+    * `python.terminal.activateEnvInCurrentTerminal`: Activates the automatic virtual environment, so you
+      can build the site from the integrated terminal.
+
+3. Add the following tasks to `.vscode/tasks.json`.
+
+    ```json
+      {
+        "version": "2.0.0",
+        "tasks": [
+          {
+            "label": "Build Docs",
+            "type": "process",
+            "windows": {
+              "command": "${workspaceFolder}/.venv/Scripts/python.exe"
+            },
+            "command": "${workspaceFolder}/.venv/bin/python3",
+            "args": [
+              "-m",
+              "sphinx",
+              "-j",
+              "auto",
+              "-T",
+              "-b",
+              "html",
+              "-d",
+              "${workspaceFolder}/.vscode/build/doctrees",
+              "-D",
+              "language=en",
+              "${workspaceFolder}/docs",
+              "${workspaceFolder}/.vscode/build/html"
+            ],
+            "problemMatcher": [
+              {
+                "owner": "sphinx",
+                "fileLocation": "absolute",
+                "pattern": {
+                  "regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):(\\d+):\\s+(WARNING|ERROR):\\s+(.*)$",
+                  "file": 1,
+                  "line": 2,
+                  "severity": 3,
+                  "message": 4
+                }
+              },
+              {
+              "owner": "sphinx",
+                "fileLocation": "absolute",
+                "pattern": {
+                  "regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):{1,2}\\s+(WARNING|ERROR):\\s+(.*)$",
+                  "file": 1,
+                  "severity": 2,
+                  "message": 3
+                }
+              }
+            ],
+            "group": {
+              "kind": "build",
+              "isDefault": true
+            }
+          }
+        ]
+      }
+    ```
+
+    > Implementation detail: two problem matchers were needed to be defined,
+    > because VS Code doesn't tolerate some problem information being potentially
+    > absent. While a single regex could match all types of errors, if a capture
+    > group remains empty (the line number doesn't show up in all warning/error
+    > messages) but the `pattern` references said empty capture group, VS Code
+    > discards the message completely.
+
+4. Configure the Python virtual environment (`venv`).
+
+    From the Command Palette, run `Python: Create Environment`. Select `venv` environment and
+    `docs/sphinx/requirements.txt`.
+
+5. Build the docs.
+
+    Launch the default build task using one of the following options:
+
+    * A hotkey (the default is `Ctrl+Shift+B`)
+    * Issuing the `Tasks: Run Build Task` from the Command Palette
+
+6. Open the live preview.
+
+    Navigate to the site output within VS Code: right-click on `.vscode/build/html/index.html` and
+    select `Open with Live Server`. The contents should update on every rebuild without having to
+    refresh the browser.

docs/how-to/llm-fine-tuning-optimization/llm-inference-frameworks.rst

@@ -16,7 +16,7 @@ This section discusses how to implement `vLLM <https://docs.vllm.ai/en/latest>`_
 vLLM inference
 ==============
 
-vLLM is renowned for its paged attention algorithm that can reduce memory consumption and increase throughput thanks to
+vLLM is renowned for its PagedAttention algorithm that can reduce memory consumption and increase throughput thanks to
 its paging scheme. Instead of allocating GPU high-bandwidth memory (HBM) for the maximum output token lengths of the
 models, the paged attention of vLLM allocates GPU HBM dynamically for its actual decoding lengths. This paged attention
 is also effective when multiple requests share the same key and value contents for a large value of beam search or
@@ -139,9 +139,7 @@ Refer to :ref:`mi300x-vllm-optimization` for performance optimization tips.
 
 ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM 
 on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV 
-format. For more information, see the guide to 
-`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_ 
-on the ROCm GitHub repository.
+format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
 
 .. _fine-tuning-llms-tgi:
 

docs/how-to/llm-fine-tuning-optimization/model-quantization.rst

@@ -181,7 +181,7 @@ Installing bitsandbytes
       # Clone the github repo
       git clone --recurse https://github.com/ROCm/bitsandbytes.git
       cd bitsandbytes
-      git checkout rocm_enabled
+      git checkout rocm_enabled_multi_backend
 
       # Install dependencies 
       pip install -r requirements-dev.txt

docs/how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference.rst

@@ -91,7 +91,7 @@ Setting up the base implementation environment
       # Use -DBNB_ROCM_ARCH to target a specific GPU architecture.
       git clone --recurse https://github.com/ROCm/bitsandbytes.git
       cd bitsandbytes
-      git checkout rocm_enabled
+      git checkout rocm_enabled_multi_backend
       pip install -r requirements-dev.txt
       cmake -DBNB_ROCM_ARCH="gfx942" -DCOMPUTE_BACKEND=hip -S .
       python setup.py install

docs/how-to/performance-validation/mi300x/vllm-benchmark.rst

@@ -0,0 +1,407 @@
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
+                 ROCm Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+***********************************************************
+LLM inference performance validation on AMD Instinct MI300X
+***********************************************************
+
+.. _vllm-benchmark-unified-docker:
+
+The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
+a prebuilt, optimized environment designed 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:
+
+* `ROCm 6.2.1 <https://github.com/ROCm/ROCm>`_
+
+* `vLLM 0.6.4 <https://docs.vllm.ai/en/latest>`_
+
+* `PyTorch 2.5.0 <https://github.com/pytorch/pytorch>`_
+
+* Tuning files (in CSV format)
+
+With this Docker image, you can quickly validate the expected inference
+performance numbers on the MI300X accelerator. This topic also provides tips on
+optimizing performance with popular AI models.
+
+.. hlist::
+   :columns: 6
+
+   * Llama 3.1 8B
+
+   * Llama 3.1 70B
+
+   * Llama 3.1 405B
+
+   * Llama 2 7B
+
+   * Llama 2 70B
+
+   * Mixtral 8x7B
+
+   * Mixtral 8x22B
+
+   * Mixtral 7B
+
+   * Qwen2 7B
+
+   * Qwen2 72B
+
+   * JAIS 13B
+
+   * JAIS 30B
+
+.. _vllm-benchmark-vllm:
+
+.. note::
+
+   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.
+
+Getting started
+===============
+
+Use the following procedures to reproduce the benchmark results on an
+MI300X accelerator with the prebuilt vLLM Docker image.
+
+.. _vllm-benchmark-get-started:
+
+1. Disable NUMA auto-balancing.
+
+   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
+
+      # 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
+
+2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
+
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+
+Once setup is complete, you can choose between two options to reproduce the
+benchmark results:
+
+-  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
+
+-  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
+
+.. _vllm-benchmark-mad:
+
+MAD-integrated benchmarking
+===========================
+
+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.
+
+.. code-block:: shell
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD
+   pip install -r requirements.txt
+
+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.
+
+.. code-block:: shell
+
+   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
+
+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/``.
+
+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.
+
+Available models
+----------------
+
+.. hlist::
+   :columns: 3
+
+   * ``pyt_vllm_llama-3.1-8b``
+
+   * ``pyt_vllm_llama-3.1-70b``
+
+   * ``pyt_vllm_llama-3.1-405b``
+
+   * ``pyt_vllm_llama-2-7b``
+
+   * ``pyt_vllm_llama-2-70b``
+
+   * ``pyt_vllm_mixtral-8x7b``
+
+   * ``pyt_vllm_mixtral-8x22b``
+
+   * ``pyt_vllm_mistral-7b``
+
+   * ``pyt_vllm_qwen2-7b``
+
+   * ``pyt_vllm_qwen2-72b``
+
+   * ``pyt_vllm_jais-13b``
+
+   * ``pyt_vllm_jais-30b``
+
+   * ``pyt_vllm_llama-3.1-8b_fp8``
+
+   * ``pyt_vllm_llama-3.1-70b_fp8``
+
+   * ``pyt_vllm_llama-3.1-405b_fp8``
+
+   * ``pyt_vllm_mixtral-8x7b_fp8``
+
+   * ``pyt_vllm_mixtral-8x22b_fp8``
+
+.. _vllm-benchmark-standalone:
+
+Standalone benchmarking
+=======================
+
+You can run the vLLM benchmark tool independently by starting the
+:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
+snippet.
+
+.. code-block::
+
+   docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.4 rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+
+In the Docker container, clone the ROCm MAD repository and navigate to the
+benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+.. code-block::
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD/scripts/vllm
+
+Command
+-------
+
+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.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
+
+See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
+
+.. note::
+
+   The input sequence length, output sequence length, and tensor parallel (TP) are
+   already configured. You don't need to specify them with this script.
+
+.. note::
+
+   If you encounter the following error, pass your access-authorized Hugging
+   Face token to the gated models.
+
+   .. code-block:: shell
+
+      OSError: You are trying to access a gated repo.
+
+      # pass your HF_TOKEN
+      export HF_TOKEN=$your_personal_hf_token
+
+.. _vllm-benchmark-standalone-options:
+
+Options
+-------
+
+.. list-table::
+   :header-rows: 1
+   :align: center
+
+   * - Name
+     - Options
+     - Description
+
+   * - ``$test_option``
+     - latency
+     - Measure decoding token latency
+
+   * -
+     - throughput
+     - Measure token generation throughput
+
+   * -
+     - all
+     - Measure both throughput and latency
+
+   * - ``$model_repo``
+     - ``meta-llama/Meta-Llama-3.1-8B-Instruct``
+     - Llama 3.1 8B
+
+   * - (``float16``)
+     - ``meta-llama/Meta-Llama-3.1-70B-Instruct``
+     - Llama 3.1 70B
+
+   * -
+     - ``meta-llama/Meta-Llama-3.1-405B-Instruct``
+     - Llama 3.1 405B
+
+   * -
+     - ``meta-llama/Llama-2-7b-chat-hf``
+     - Llama 2 7B
+
+   * -
+     - ``meta-llama/Llama-2-70b-chat-hf``
+     - Llama 2 70B
+
+   * -
+     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
+     - Mixtral 8x7B
+
+   * -
+     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
+     - Mixtral 8x22B
+
+   * -
+     - ``mistralai/Mistral-7B-Instruct-v0.3``
+     - Mixtral 7B
+
+   * -
+     - ``Qwen/Qwen2-7B-Instruct``
+     - Qwen2 7B
+
+   * -
+     - ``Qwen/Qwen2-72B-Instruct``
+     - Qwen2 72B
+
+   * -
+     - ``core42/jais-13b-chat``
+     - JAIS 13B
+
+   * -
+     - ``core42/jais-30b-chat-v3``
+     - JAIS 30B
+
+   * - ``$model_repo``
+     - ``amd/Meta-Llama-3.1-8B-Instruct-FP8-KV``
+     - Llama 3.1 8B
+
+   * - (``float8``)
+     - ``amd/Meta-Llama-3.1-70B-Instruct-FP8-KV``
+     - Llama 3.1 70B
+
+   * -
+     - ``amd/Meta-Llama-3.1-405B-Instruct-FP8-KV``
+     - Llama 3.1 405B
+
+   * -
+     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
+     - Mixtral 8x7B
+
+   * -
+     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
+     - Mixtral 8x22B
+
+   * - ``$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 8B model on one GPU with the ``float16`` and ``float8`` data types.
+
+.. code-block::
+
+   ./vllm_benchmark_report.sh -s latency -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+   ./vllm_benchmark_report.sh -s latency -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+
+Find the latency reports at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
+
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_latency_report.csv``
+
+Example 2: throughput benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+   ./vllm_benchmark_report.sh -s throughput -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+
+Find the throughput reports at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
+
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-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
+===============
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/tuning-guides/mi300x/workload`.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see :doc:`/how-to/system-optimization/mi300x`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Using ROCm for AI </how-to/rocm-for-ai/index>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Fine-tuning LLMs and inference optimization </how-to/llm-fine-tuning-optimization/index>`.
+
+- For a list of other ready-made Docker images for ROCm, see the
+  :doc:`Docker image support matrix <rocm-install-on-linux:reference/docker-image-support-matrix>`.
+
+- To compare with the previous version of the ROCm vLLM Docker image for performance validation, refer to
+  `LLM inference performance validation on AMD Instinct MI300X (ROCm 6.2.0) <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_.
+

docs/how-to/rocm-for-ai/deploy-your-model.rst

@@ -46,9 +46,7 @@ Validating vLLM performance
 
 ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM 
 on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV 
-format. For more information, see the guide to 
-`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_ 
-on the ROCm GitHub repository.
+format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
 
 .. _rocm-for-ai-serve-hugging-face-tgi:
 

docs/how-to/system-optimization/mi100.md

@@ -342,8 +342,8 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
 (logical) cores of the system:
 
 * In the server BIOS, set IOMMU to "Enabled".
-* When configuring the Grub boot loader, add the following arguments for the
-  Linux kernel: `amd_iommu=on iommu=pt`
+* When configuring the Grub boot loader, add the following argument for the
+  Linux kernel: `iommu=pt`
 * Update Grub to use the modified configuration:
 
   ```shell
@@ -355,7 +355,7 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
 
   ```none
   [...]
-  [   0.000000] Kernel command line: [...] amd_iommu=on iommu=pt
+  [   0.000000] Kernel command line: [...] iommu=pt
      [...]
   ```
 

docs/how-to/system-optimization/mi200.md

@@ -327,8 +327,8 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
 (logical) cores of the system:
 
 * In the server BIOS, set IOMMU to "Enabled".
-* When configuring the Grub boot loader, add the following arguments for the
-  Linux kernel: `amd_iommu=on iommu=pt`
+* When configuring the Grub boot loader, add the following argument for the
+  Linux kernel: `iommu=pt`
 * Update Grub to use the modified configuration:
 
   ```shell
@@ -340,7 +340,7 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
 
   ```none
   [...]
-  [   0.000000] Kernel command line: [...] amd_iommu=on iommu=pt
+  [   0.000000] Kernel command line: [...] iommu=pt
      [...]
   ```
 

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

@@ -299,7 +299,7 @@ For a system that has AMD host CPUs add this to ``GRUB_CMDLINE_LINUX``:
 
 .. code-block:: text
 
-   amd_iommu=on iommu=pt
+   iommu=pt
 
 Otherwise, if the system has Intel host CPUs add this instead to
 ``GRUB_CMDLINE_LINUX``:
@@ -500,7 +500,7 @@ If SMT is enabled by setting ``CCD/Core/Thread Enablement > SMT Control`` to
 
 #. In the server BIOS, set IOMMU to ``Enabled``.
 
-#. When configuring the GRUB boot loader, add the following arguments for the Linux kernel: ``amd_iommu=on iommu=pt``.
+#. When configuring the GRUB boot loader, add the following argument for the Linux kernel: ``iommu=pt``.
 
 #. Update GRUB.
 
@@ -515,7 +515,7 @@ If SMT is enabled by setting ``CCD/Core/Thread Enablement > SMT Control`` to
 .. code-block:: shell
 
    [...]
-   [   0.000000] Kernel command line: [...] amd_iommu=on iommu=pt
+   [   0.000000] Kernel command line: [...] iommu=pt
    [...]
 
 Once the system is properly configured, ROCm software can be

docs/how-to/system-optimization/w6000-v620.md

@@ -111,7 +111,7 @@ sudo virsh net-start default /*to enable Virtual network by default
 Enable input-output memory management unit (IOMMU) in GRUB settings by adding the following line to `/etc/default/grub`:
 
 ```none
-GRUB_CMDLINE_LINUX_DEFAULT="quiet splash amd_iommu=on" for AMD CPU
+GRUB_CMDLINE_LINUX_DEFAULT="quiet splash" for AMD CPU
 ```
 
 Update grub and reboot

docs/how-to/tuning-guides/mi300x/index.rst

@@ -8,6 +8,8 @@ accelerators. They include detailed instructions on system settings and
 application tuning suggestions to help you fully leverage the capabilities of
 these accelerators, thereby achieving optimal performance.
 
+* :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`
+
 * :doc:`/how-to/tuning-guides/mi300x/system`
 
 * :doc:`/how-to/tuning-guides/mi300x/workload`

docs/how-to/tuning-guides/mi300x/workload.rst

@@ -152,9 +152,7 @@ address any new bottlenecks that may emerge.
 
 ROCm provides a prebuilt optimized Docker image that has everything required to implement
 the tips in this section. It includes ROCm, vLLM, PyTorch, and tuning files in the CSV 
-format. For more information, see the guide to 
-`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_ 
-on the ROCm GitHub repository.
+format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
 
 .. _mi300x-profiling-tools:
 
@@ -378,11 +376,10 @@ Refer to `vLLM documentation <https://docs.vllm.ai/en/latest/models/performance.
 for additional performance tips. :ref:`fine-tuning-llms-vllm` describes vLLM
 usage with ROCm.
 
-ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM 
-on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV 
-format. For more information, see the guide to 
-`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_ 
-on the ROCm GitHub repository.
+ROCm provides a prebuilt optimized Docker image for validating the performance
+of LLM inference with vLLM on the MI300X accelerator. The Docker image includes
+ROCm, vLLM, PyTorch, and tuning files in the CSV format. For more information,
+see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
 
 Maximize throughput
 -------------------

docs/index.md

@@ -11,7 +11,7 @@ ROCm is an open-source software platform optimized to extract HPC and AI workloa
 performance from AMD Instinct accelerators and AMD Radeon GPUs while maintaining
 compatibility with industry software frameworks. For more information, see [What is ROCm?](./what-is-rocm.rst)
 
-If you're using Radeon GPUs, consider reviewing {doc}`Radeon-specific ROCm documentation<radeon:index>`.
+If you're using AMD Radeon™ PRO or Radeon GPUs in a workstation setting with a display connected, review {doc}`Radeon-specific ROCm documentation<radeon:index>`.
 
 Installation instructions are available from:
 
@@ -45,8 +45,8 @@ ROCm documentation is organized into the following categories:
 * [Using ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
 * [Fine-tuning LLMs and inference optimization](./how-to/llm-fine-tuning-optimization/index.rst)
 * [System optimization](./how-to/system-optimization/index.rst)
-* [AMD Instinct MI300X tuning guides](./how-to/tuning-guides/mi300x/index.rst)
-* [GPU cluster networking](https://rocm.docs.amd.com/projects/gpu-cluster-networking/en/latest/index.html)
+* [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)
+* [GPU cluster networking](https://dcgpu.docs.amd.com/projects/gpu-cluster-networking/en/latest/index.html)
 * [System debugging](./how-to/system-debugging.md)
 * [Using MPI](./how-to/gpu-enabled-mpi.rst)
 * [Using advanced compiler features](./conceptual/compiler-topics.md)
@@ -64,7 +64,7 @@ ROCm documentation is organized into the following categories:
 * [Using CMake](./conceptual/cmake-packages.rst)
 * [ROCm & PCIe atomics](./conceptual/More-about-how-ROCm-uses-PCIe-Atomics.rst)
 * [Inception v3 with PyTorch](./conceptual/ai-pytorch-inception.md)
-* [Inference optimization with MIGraphX](./conceptual/ai-migraphx-optimization.md)
+* [Oversubscription of hardware resources](./conceptual/oversubscription.rst)
 :::
 
 <!-- markdownlint-disable MD051 -->

docs/sphinx/_toc.yml.in

@@ -70,15 +70,15 @@ subtrees:
       - file: how-to/system-optimization/w6000-v620.md
         title: AMD RDNA 2
   - file: how-to/tuning-guides/mi300x/index.rst
-    title: AMD MI300X tuning guides
+    title: AMD MI300X performance validation and tuning
     subtrees:
     - entries:
+      - file: how-to/performance-validation/mi300x/vllm-benchmark.rst
+        title: Performance validation
       - file: how-to/tuning-guides/mi300x/system.rst
         title: System tuning
       - file: how-to/tuning-guides/mi300x/workload.rst
         title: Workload tuning
-  - url: https://rocm.docs.amd.com/projects/gpu-cluster-networking/en/${branch}/index.html
-    title: GPU cluster networking
   - file: how-to/gpu-enabled-mpi.rst
     title: Using MPI
   - file: how-to/system-debugging.md
@@ -158,8 +158,8 @@ subtrees:
     title: ROCm & PCIe atomics
   - file: conceptual/ai-pytorch-inception.md
     title: Inception v3 with PyTorch
-  - file: conceptual/ai-migraphx-optimization.md
-    title: Inference optimization with MIGraphX
+  - file: conceptual/oversubscription.rst
+    title: Oversubscription of hardware resources
 
 - caption: Reference
   entries:
@@ -180,6 +180,7 @@ subtrees:
     - entries:
       - file: contribute/toolchain.md
         title: ROCm documentation toolchain
+      - file: contribute/building.md
   - file: contribute/feedback.md
     title: Providing feedback about the ROCm documentation
   - file: about/license.md

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-6.2.2"
+    <default revision="refs/tags/rocm-6.1.1"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />

tools/autotag/templates/highlights/5.3.0.md

@@ -184,5 +184,5 @@ clinfo, and HelloWord.cl and cause a system crash.
 * IRQ remapping does not support X2APIC mode
 * NMI error
 
-Workaround: To avoid the system crash, add `amd_iommu=on iommu=pt` as the kernel bootparam, as
+Workaround: To avoid the system crash, add `iommu=pt` as the kernel bootparam, as
 indicated in the warning message.

tools/rocm-build/ROCm.mk

@@ -67,16 +67,18 @@ endef
 
 $(call adddep,amd_smi_lib,${ASAN_DEP})
 $(call adddep,aqlprofile,${ASAN_DEP} hsa)
-$(call adddep,clang-ocl,lightning rocm-cmake)
 $(call adddep,comgr,lightning devicelibs)
 $(call adddep,dbgapi,hsa comgr)
 $(call adddep,devicelibs,lightning)
-$(call adddep,hip_on_rocclr,${ASAN_DEP} rocclr rocprofiler-register)
+$(call adddep,hip_on_rocclr,${ASAN_DEP} hsa comgr hipcc rocprofiler-register)
 $(call adddep,hipcc,)
 $(call adddep,hipify_clang,hip_on_rocclr lightning)
 $(call adddep,hsa,${ASAN_DEP} thunk lightning devicelibs rocprofiler-register)
 $(call adddep,lightning,)
-$(call adddep,opencl_on_rocclr,${ASAN_DEP} rocclr)
+$(call adddep,omniperf,${ASAN_DEP})
+$(call adddep,omnitrace,hipcc hsa hip_on_rocclr rocm_smi_lib rocprofiler roctracer)
+$(call adddep,opencl_icd_loader,)
+$(call adddep,opencl_on_rocclr,${ASAN_DEP} hsa comgr opencl_icd_loader)
 $(call adddep,openmp_extras,thunk lightning devicelibs hsa)
 $(call adddep,rdc,${ASAN_DEP} rocm_smi_lib hsa rocprofiler)
 $(call adddep,rocclr,${ASAN_DEP} hsa comgr hipcc rocprofiler-register)
@@ -87,14 +89,15 @@ $(call adddep,rocm-core,${ASAN_DEP})
 $(call adddep,rocm-gdb,dbgapi)
 $(call adddep,rocminfo,${ASAN_DEP} hsa)
 $(call adddep,rocprofiler-register,${ASAN_DEP})
-$(call adddep,rocprofiler,${ASAN_DEP} hsa roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr dbgapi rocm_smi_lib)
+$(call adddep,rocprofiler-sdk,${ASAN_DEP} hsa aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
+$(call adddep,rocprofiler,${ASAN_DEP} hsa roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
 $(call adddep,rocr_debug_agent,${ASAN_DEP} hip_on_rocclr hsa dbgapi)
 $(call adddep,roctracer,${ASAN_DEP} hsa hip_on_rocclr)
 $(call adddep,thunk,${ASAN_DEP})
 
 # rocm-dev points to all possible last finish components of Stage1 build.
 rocm-dev-components :=rdc hipify_clang openmp_extras \
-	rocm-core amd_smi_lib hipcc clang-ocl \
+	omniperf omnitrace rocm-core amd_smi_lib hipcc \
 	rocm_bandwidth_test rocr_debug_agent rocm-gdb
 $(call adddep,rocm-dev,$(filter-out ${NOBUILD},${rocm-dev-components}))
 
@@ -117,6 +120,7 @@ $(call adddep,mivisionx,amdmigraphx miopen-hip rpp lightning hipcc)
 $(call adddep,rccl,hip_on_rocclr hsa lightning hipcc rocm_smi_lib hipify_clang)
 $(call adddep,rocalution,rocblas rocsparse rocrand lightning hipcc)
 $(call adddep,rocblas,hip_on_rocclr openmp_extras lightning hipcc)
+$(call adddep,rocal,mivisionx)
 $(call adddep,rocdecode,hip_on_rocclr lightning hipcc)
 $(call adddep,rocfft,hip_on_rocclr rocrand hiprand lightning hipcc openmp_extras)
 $(call adddep,rocmvalidationsuite,hip_on_rocclr hsa rocblas rocm-core lightning hipcc rocm_smi_lib)
@@ -221,7 +225,7 @@ rocm-dev: T_rocm-dev
 
 ${OUT_DIR}/logs:
 	sudo mkdir -p -m 775 "${ROCM_INSTALL_PATH}" && \
-	sudo chown -R "$(shell id -u):$(shell id -g)" "${ROCM_INSTALL_PATH}"
+	sudo chown -R "$(shell id -u):$(shell id -g)" "/opt"
 	sudo chown -R "$(shell id -u):$(shell id -g)" "/home/$(shell id -un)"
 	mkdir -p "${@}"
 	mkdir -p ${HOME}/.ccache

tools/rocm-build/build_amdmigraphx.sh

@@ -22,12 +22,13 @@ build_amdmigraphx() {
     else
         GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
     fi
+    init_rocm_common_cmake_params
 
     mkdir -p ${BUILD_DIR} && rm -rf ${BUILD_DIR}/* && mkdir -p ${HOME}/amdmigraphx && rm -rf ${HOME}/amdmigraphx/*
     rbuild package -d "${HOME}/amdmigraphx" -B "${BUILD_DIR}" \
         --cxx="${ROCM_PATH}/llvm/bin/clang++" \
         --cc="${ROCM_PATH}/llvm/bin/clang" \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DCMAKE_MODULE_LINKER_FLAGS="-Wl,--enable-new-dtags -Wl,--rpath,$ROCM_LIB_RPATH" \
 	    -DGPU_TARGETS="${GPU_TARGETS}" \
         -DCMAKE_INSTALL_RPATH=""

tools/rocm-build/build_composable_kernel.sh

@@ -17,9 +17,7 @@ build_miopen_ck() {
     mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
 
     if [ -n "$GPU_ARCHS" ]; then
-        GPU_TARGETS="$GPU_ARCHS"
-    else
-        GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
+        GPU_TARGETS="-DAMDGPU_TARGETS=${GPU_ARCHS}"
     fi
 
     if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
@@ -43,7 +41,7 @@ build_miopen_ck() {
             ${LAUNCHER_FLAGS} \
             -DINSTANCES_ONLY=ON \
             -DENABLE_ASAN_PACKAGING=true \
-            -DAMDGPU_TARGETS=${GPU_TARGETS} \
+            "${GPU_TARGETS}" \
             "$COMPONENT_SRC"
     else
         cmake -DBUILD_DEV=OFF \
@@ -63,9 +61,11 @@ build_miopen_ck() {
             -DROCM_DISABLE_LDCONFIG=ON \
             -DROCM_PATH=${ROCM_PATH} \
             -DCPACK_GENERATOR="${PKGTYPE^^}" \
+            -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
+            -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
             ${LAUNCHER_FLAGS} \
             -DINSTANCES_ONLY=ON \
-            -DAMDGPU_TARGETS=${GPU_TARGETS} \
+            "${GPU_TARGETS}" \
             "$COMPONENT_SRC"
     fi
 
@@ -106,8 +106,6 @@ build_miopen_ckProf() {
     architectures='gfx10 gfx11 gfx90 gfx94'
     if [ -n "$GPU_ARCHS" ]; then
         architectures=$(echo ${GPU_ARCHS} | awk -F';' '{for(i=1;i<=NF;i++) a[substr($i,1,5)]} END{for(i in a) printf i" "}')
-    else
-        architectures='gfx10 gfx11 gfx90 gfx94'
     fi
 
     for arch in ${architectures}

tools/rocm-build/build_hipblas.sh

@@ -28,9 +28,10 @@ build_hipblas() {
        rebuild_lapack
     fi
 
+    init_rocm_common_cmake_params
     cmake \
         ${LAUNCHER_FLAGS} \
-	$(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DUSE_CUDA=OFF \
         -DBUILD_CLIENTS_TESTS=ON \
         -DBUILD_CLIENTS_BENCHMARKS=ON \

tools/rocm-build/build_hipblaslt.sh

@@ -27,11 +27,12 @@ build_hipblaslt() {
         GPU_TARGETS=all
     fi
 
+    init_rocm_common_cmake_params
     CXX=$(set_build_variables CXX)\
     cmake \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         ${LAUNCHER_FLAGS} \
-         $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DTensile_LOGIC= \
         -DTensile_CODE_OBJECT_VERSION=default \
         -DTensile_CPU_THREADS= \

tools/rocm-build/build_hipcub.sh

@@ -17,6 +17,7 @@ build_hipcub() {
     fi
 
     mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
 
     if [ -n "$GPU_ARCHS" ]; then
         GPU_TARGETS="$GPU_ARCHS"
@@ -27,7 +28,7 @@ build_hipcub() {
     CXX=$(set_build_variables CXX)\
     cmake \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
         -Drocprim_DIR="${ROCM_PATH}/rocprim"  \
         -DBUILD_TEST=ON \

tools/rocm-build/build_hipfft.sh

@@ -16,6 +16,7 @@ build_hipfft() {
 
     cd $COMPONENT_SRC
     mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
 
     if [ -n "$GPU_ARCHS" ]; then
         GPU_TARGETS="$GPU_ARCHS"
@@ -26,7 +27,7 @@ build_hipfft() {
     cmake \
         -DCMAKE_CXX_COMPILER=$(set_build_variables CXX) \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip" \
         -DCMAKE_SKIP_BUILD_RPATH=TRUE \

tools/rocm-build/build_hiprand.sh

@@ -61,7 +61,6 @@ build_hiprand() {
     rm -rf _CPack_Packages/  && find -name '*.o' -delete
     mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
 
-    $SCCACHE_BIN -s || echo "Unable to display sccache stats"
 }
 
 clean_hiprand() {

tools/rocm-build/build_hipsolver.sh

@@ -27,10 +27,11 @@ build_hipsolver() {
        rebuild_lapack
     fi
 
+    init_rocm_common_cmake_params
     cmake \
         -DUSE_CUDA=OFF \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DBUILD_CLIENTS_TESTS=ON \
         -DBUILD_CLIENTS_BENCHMARKS=ON \
         -DBUILD_CLIENTS_SAMPLES=ON \

tools/rocm-build/build_hipsparse.sh

@@ -22,11 +22,12 @@ build_hipsparse() {
     echo "CXX compiler: $CXX"
 
     mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
 
     cmake \
         -DCPACK_SET_DESTDIR=OFF \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DUSE_CUDA=OFF  \
         -DBUILD_CLIENTS_SAMPLES=ON \
         -DBUILD_CLIENTS_TESTS=ON \

tools/rocm-build/build_hipsparselt.sh

@@ -28,6 +28,7 @@ build_hipsparselt() {
 
     cd $COMPONENT_SRC
     mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
 
     if [ -n "$GPU_ARCHS" ]; then
         GPU_TARGETS="$GPU_ARCHS"
@@ -41,7 +42,7 @@ build_hipsparselt() {
     cmake \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         ${LAUNCHER_FLAGS} \
-         $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DTensile_LOGIC= \
         -DTensile_CODE_OBJECT_VERSION=default \
         -DTensile_CPU_THREADS= \

tools/rocm-build/build_hiptensor.sh

@@ -16,6 +16,8 @@ build_hiptensor() {
 
     cd "$COMPONENT_SRC"
     mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
+
 
     if [ -n "$GPU_ARCHS" ]; then
         GPU_TARGETS="$GPU_ARCHS"
@@ -25,7 +27,7 @@ build_hiptensor() {
 
     cmake \
         -B "${BUILD_DIR}" \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         $(set_build_variables CMAKE_C_CXX) \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         ${LAUNCHER_FLAGS} \

tools/rocm-build/build_lightning.sh

@@ -17,7 +17,8 @@ printUsage() {
     echo "  -r,  --release               Build a release version of the package"
     echo "  -a,  --address_sanitizer     Enable address sanitizer (enabled by default)"
     echo "  -A   --no_address_sanitizer  Disable address sanitizer"
-    echo "  -s,  --static                Supports static CI by accepting this param & not bailing out. No effect of the param though"
+    echo "  -s,  --static                Build static lib (.a).  build instead of dynamic/shared(.so) "
+    echo "  -w,  --wheel                 Creates python wheel package of rocm-llvm. It needs to be used along with -r option"
     echo "  -l,  --build_llvm_static     Build LLVM libraries statically linked.  Default is to build dynamic linked libs"
     echo "  -o,  --outdir <pkg_type>     Print path of output directory containing packages of
                             type referred to by pkg_type"
@@ -42,6 +43,7 @@ DEB_PATH="$(getDebPath lightning)"
 RPM_PATH="$(getRpmPath lightning)"
 INSTALL_PATH="${ROCM_INSTALL_PATH}/lib/llvm"
 LLVM_ROOT_LCL="${LLVM_ROOT}"
+ROCM_WHEEL_DIR="${BUILD_PATH}/_wheel"
 
 TARGET="all"
 MAKEOPTS="$DASH_JAY"
@@ -69,14 +71,29 @@ ASSERT_LLVM_VERSION_MINOR=""
 
 SKIP_LIT_TESTS=0
 BUILD_MANPAGES="ON"
+STATIC_FLAG=
 
 SANITIZER_AMDGPU=1
 HSA_INC_PATH="$WORK_ROOT/ROCR-Runtime/src/inc"
 COMGR_INC_PATH="$WORK_ROOT/llvm-project/amd/comgr/include"
 
-VALID_STR=`getopt -o htcV:v:draAslo:BPNM --long help,alt,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
+VALID_STR=`getopt -o htcV:v:draAswlo:BPNM --long help,alt,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,wheel,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
 eval set -- "$VALID_STR"
 
+set_dwarf_version(){
+  case "$DISTRO_ID" in
+    (sles*|rhel*)
+       SET_DWARF_VERSION_4="-gdwarf-4"
+       ;;
+    (*)
+       SET_DWARF_VERSION_4=""
+       ;;
+  esac
+  export CFLAGS="$CFLAGS $SET_DWARF_VERSION_4  "
+  export CXXFLAGS="$CXXFLAGS $SET_DWARF_VERSION_4 "
+  export ASMFLAGS="$ASMFLAGS $SET_DWARF_VERSION_4 "
+}
+
 while true ;
 do
     case "$1" in
@@ -95,6 +112,7 @@ do
         (-r | --release)
                 BUILD_TYPE="Release" ; shift ;;
         (-a | --address_sanitizer)
+                set_dwarf_version
                 SANITIZER_AMDGPU=1 ;
                 HSA_INC_PATH="$WORK_ROOT/hsa/runtime/opensrc/hsa-runtime/inc" ;
                 COMGR_INC_PATH="$WORK_ROOT/external/llvm-project/amd/comgr/include" ; shift ;;
@@ -103,9 +121,12 @@ do
                 unset HSA_INC_PATH ;
                 unset COMGR_INC_PATH ; shift ;;
         (-s | --static)
-                SHARED_LIBS="OFF" ; shift ;;
+                SHARED_LIBS="OFF" ;
+                STATIC_FLAG="-DBUILD_SHARED_LIBS=$SHARED_LIBS" ; shift ;;
         (-l | --build_llvm_static)
                 BUILD_LLVM_DYLIB="OFF"; shift ;;
+        (-w | --wheel)
+                WHEEL_PACKAGE=true ; shift ;;
         (-o | --outdir)
                 TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
         (-B | --build)
@@ -151,6 +172,7 @@ else
 fi
 
 clean_lightning() {
+    rm -rf "$ROCM_WHEEL_DIR"
     rm -rf "$BUILD_PATH"
     rm -rf "$DEB_PATH"
     rm -rf "$RPM_PATH"
@@ -196,7 +218,10 @@ LLVM_VERSION_MINOR=""
 LLVM_VERSION_PATCH=""
 LLVM_VERSION_SUFFIX=""
 get_llvm_version() {
-    local LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/CMakeLists.txt))
+    local LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/../cmake/Modules/LLVMVersion.cmake))
+    if [ ${#LLVM_VERSIONS[@]} -eq 0 ]; then
+        LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/CMakeLists.txt))
+    fi
     LLVM_VERSION_MAJOR=${LLVM_VERSIONS[0]}
     LLVM_VERSION_MINOR=${LLVM_VERSIONS[1]}
     LLVM_VERSION_PATCH=${LLVM_VERSIONS[2]}
@@ -260,15 +285,22 @@ build_lightning() {
 
     if [ ! -e Makefile ]; then
         echo "Building LLVM CMake environment"
-	if [ -e "$LLVM_ROOT_LCL/../flang/docs/AssumedRank.md" ]; then
-          FLANG_NEW=1
-	  LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
-	else
-	  echo "NOT building project flang"
-	fi
+        if [ -e "$LLVM_ROOT_LCL/../flang/AFARrelease" ]; then
+            FLANG_NEW=1
+            LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
+            ENABLE_RUNTIMES="$ENABLE_RUNTIMES;openmp";
+        else
 
+          if [[ "${JOB_NAME}" != *afar* ]] && [ -e "$LLVM_ROOT_LCL/../flang/DoROCmRelease" ]; then
+            FLANG_NEW=1
+            LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
+          else
+            echo "NOT building project flang"
+          fi
+        fi
         set -x
         cmake $(rocm_cmake_params) ${GEN_NINJA} \
+              ${STATIC_FLAG} \
               -DCMAKE_INSTALL_PREFIX="$INSTALL_PATH" \
               -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" \
               -DLLVM_ENABLE_PROJECTS="$LLVM_PROJECTS" \
@@ -307,9 +339,9 @@ build_lightning() {
               -DCMAKE_SHARED_LINKER_FLAGS=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_LLVM_LIB_RPATH \
               -DROCM_LLVM_BACKWARD_COMPAT_LINK="$ROCM_INSTALL_PATH/llvm" \
               -DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET="./lib/llvm" \
-	      -DCLANG_LINK_FLANG_LEGACY=ON \
-	      -DCMAKE_CXX_STANDARD=17 \
-	      -DFLANG_INCLUDE_DOCS=OFF \
+              -DCLANG_LINK_FLANG_LEGACY=ON \
+              -DCMAKE_CXX_STANDARD=17 \
+              -DFLANG_INCLUDE_DOCS=OFF \
               "$LLVM_ROOT_LCL"
         set +x
         echo "CMake complete"
@@ -326,8 +358,23 @@ build_lightning() {
     echo "End Workaround for race condition"
     cmake --build . -- $MAKEOPTS
 
+    case "$DISTRO_ID" in
+    (rhel*|centos*)
+       RHEL_BUILD=1
+       ;;
+    (*)
+       RHEL_BUILD=0
+       ;;
+     esac
+
     if [ $SKIP_LIT_TESTS -eq 0 ]; then
-        if [ "$DISTRO_NAME" != "sles" ] && [ $BUILD_ALT != 1 ]; then
+        if [ $RHEL_BUILD -eq 1 ] && [ $BUILD_ALT != 1 ]; then
+            if [ $FLANG_NEW -eq 1 ]; then
+                cmake --build . -- $MAKEOPTS check-lld check-mlir
+            else
+                cmake --build . -- $MAKEOPTS check-lld
+            fi
+        elif [ "$DISTRO_NAME" != "sles" ] && [ $BUILD_ALT != 1 ]; then
             if [ $FLANG_NEW -eq 1 ]; then
                 cmake --build . -- $MAKEOPTS check-llvm check-clang check-lld check-mlir
             else
@@ -733,7 +780,7 @@ package_lightning_static() {
     local amd_compiler_commands=("amdclang" "amdclang++" "amdclang-cl" "amdclang-cpp" "amdflang" "amdlld" "offload-arch")
     local amd_man_pages=("amdclang.1.gz" "flang.1.gz" "amdflang.1.gz")
     local core_bin=("amdgpu-arch" "amdgpu-offload-arch" "amdlld" "amdllvm" "clang" "clang++" "clang-${LLVM_VERSION_MAJOR}" "clang-cl"
-                    "clang-cpp" "clang-build-select-link" "clang-offload-bundler" "clang-offload-packager" "clang-offload-wrapper" "flang" "flang-new"
+                    "clang-cpp" "clang-build-select-link" "clang-offload-bundler" "clang-offload-packager" "clang-offload-wrapper" "clang-linker-wrapper" "clang-nvlink-wrapper" "flang" "flang-new"
                     "ld64.lld" "ld.lld" "llc" "lld" "lld-link" "llvm-ar" "llvm-bitcode-strip" "llvm-dwarfdump" "llvm-install-name-tool"
                     "llvm-link" "llvm-mc" "llvm-objcopy" "llvm-objdump" "llvm-otool" "llvm-ranlib" "llvm-readelf" "llvm-readobj" "llvm-strip"
                     "nvidia-arch" "nvptx-arch" "offload-arch" "opt" "wasm-ld" "amdclang" "amdclang++" "amdclang-${LLVM_VERSION_MAJOR}" "amdclang-cl"
@@ -934,7 +981,7 @@ package_lightning_static() {
 
         if [ $BUILD_ALT -eq 0 ]; then
             echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
-			echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
+            echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
         else
             echo "cp -R $LLVM_PROJECT_ALT_ROOT/EULA \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
             echo "cp -R $LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
@@ -948,7 +995,6 @@ package_lightning_static() {
 
         echo "cp -d \"$distBin/flang\" \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
 
-        # Copy the config files
         if [ $BUILD_ALT -eq 0 ]; then
             echo "cp -d \"$distBin\"/*.cfg \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
         fi
@@ -970,14 +1016,12 @@ package_lightning_static() {
         if [ "$BUILD_MANPAGES" == "ON" ]; then
             if [ $BUILD_ALT -eq 0 ]; then
                 echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFile
-
                 for i in "${core_man_pages[@]}"; do
                     if [ -f "$distMan/man1/$i" ]; then
                         echo "gzip -f $distMan/man1/$i" >> $specFile
                         echo "cp -d $distMan/man1/${i}.gz \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFile
                     fi
                 done
-
                 if [ -f "$distMan/man1/clang.1.gz" ]; then
                     for i in "${amd_man_pages[@]}"; do
                         echo "ln -sf clang.1.gz \"$distMan/man1/$i\"" >> $specFile
@@ -1064,7 +1108,6 @@ package_lightning_static() {
             contains "$bin" "${core_bin[@]}" "${amd_compiler_commands[@]}" && continue
             echo "cp -d \"$i\" \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFileExtra
         done
-
         for i in "$distLib"/*; do
             lib=$(basename "$i")
             contains "$lib" "${core_lib[@]}" && continue
@@ -1072,18 +1115,15 @@ package_lightning_static() {
         done
 
         echo "cp -R $distInc \$RPM_BUILD_ROOT/$installPath" >> $specFileExtra
-
         echo "rm -rf \$RPM_BUILD_ROOT/$installPath/lib/clang" >> $specFileExtra
 
         if [ $FLANG_NEW -eq 1 ]; then
-
           echo "rm -rf \$RPM_BUILD_ROOT/$installPath/include/flang" >> $specFileExtra
         fi
 
         if [ "$BUILD_MANPAGES" == "ON" ]; then
             if [ $BUILD_ALT -eq 0 ]; then
                 echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFileExtra
-
                 for i in "${extra_man_pages[@]}"; do
                     if [ -f "$distMan/man1/$i" ]; then
                         echo "gzip -f $distMan/man1/$i" >> $specFileExtra
@@ -1125,34 +1165,34 @@ package_docs() {
     local packageName="rocm-llvm-docs"
     local packageSummary="ROCm LLVM compiler documentation"
     local packageSummaryLong="Documenation for LLVM $llvmParsedVersion"
-    local installPath="$ROCM_INSTALL_PATH/lib/llvm/share"
 
     local packageArch="amd64"
     local packageVersion="${llvmParsedVersion}.${LLVM_COMMIT_GITDATE}"
     local packageMaintainer="ROCm Compiler Support <rocm.compiler.support@amd.com>"
-    local distDoc="$INSTALL_PATH/share/doc"
+    local distDoc="$INSTALL_PATH/share/doc/LLVM"
 
     local licenseDir="$ROCM_INSTALL_PATH/share/doc/$packageName"
     local packageDir="$BUILD_PATH/package"
 
     local packageDeb="$packageDir/deb"
     local controlFile="$packageDeb/DEBIAN/control"
+    local debDependencies="rocm-core"
 
     local packageRpm="$packageDir/rpm"
     local specFile="$packageDir/$packageName.spec"
+    local rpmRequires="rocm-core"
 
     rm -rf "$packageDir"
     echo "rm -rf $packageDir"
 
     if [ "$PACKAGEEXT" = "deb" ]; then
 
-        mkdir -p "$packageDeb/$installPath"
-        mkdir "${controlFile%/*}"
         mkdir -p "$packageDeb/$licenseDir"
+        mkdir "${controlFile%/*}"
 
         cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDir"
 
-        cp -r "$distDoc" "$packageDeb/$installPath/doc"
+        cp -r "$distDoc" "$packageDeb/$licenseDir"
 
         {
             echo "Package: $packageName"
@@ -1162,6 +1202,7 @@ package_docs() {
             echo "Maintainer: $packageMaintainer"
             echo "Version: ${packageVersion}.${ROCM_LIBPATCH_VERSION}-${JOB_DESIGNATOR}${BUILD_ID}~${DISTRO_RELEASE}"
             echo "Release:    ${JOB_DESIGNATOR}${BUILD_ID}~${DISTRO_RELEASE}"
+            echo "Depends: $debDependencies"
             echo "Recommends: $debRecommends"
             echo "Description: $packageSummary"
             echo "  $packageSummaryLong"
@@ -1182,6 +1223,7 @@ package_docs() {
         echo "Summary:    $packageSummary" >> $specFile
         echo "Group:      System Environment/Libraries" >> $specFile
         echo "License:    ASL 2.0 with exceptions" >> $specFile
+        echo "Requires:   $rpmRequires" >> $specFile
 
         echo "%description" >> $specFile
         echo "$packageSummaryLong" >> $specFile
@@ -1190,16 +1232,13 @@ package_docs() {
         echo "%setup -T -D -c -n $packageName" >> $specFile
 
         echo "%install" >> $specFile
-        echo "rm -rf \$RPM_BUILD_ROOT/$installPath" >> $specFile
-        echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/doc" >> $specFile
         echo "mkdir -p  \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
 
         echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
 
-        echo "cp -R \"$distDoc\" \$RPM_BUILD_ROOT/$installPath" >> $specFile
+        echo "cp -R \"$distDoc\" \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
 
         echo "%clean" >> $specFile
-        echo "rm -rf \$RPM_BUILD_ROOT/$installPath" >> $specFile
         echo "%files " >> $specFile
         echo "%defattr(-,root,root,-)" >> $specFile
 
@@ -1232,6 +1271,18 @@ build() {
     fi
 }
 
+create_wheel_package() {
+    echo "Creating rocm-llvm wheel package"
+    mkdir -p "$ROCM_WHEEL_DIR"
+    cp -f $SCRIPT_ROOT/generate_setup_py.py $ROCM_WHEEL_DIR
+    cp -f $SCRIPT_ROOT/repackage_wheel.sh $ROCM_WHEEL_DIR
+    cd $ROCM_WHEEL_DIR
+    # Currently only supports python3.6
+    ./repackage_wheel.sh $RPM_PATH/rocm-llvm*.rpm python3.6
+    # Copy the wheel created to RPM folder which will be uploaded to artifactory
+    mv "$ROCM_WHEEL_DIR"/dist/*.whl "$RPM_PATH"
+}
+
 case $TARGET in
     (clean) clean_lightning ;;
     (all)
@@ -1250,4 +1301,9 @@ case $TARGET in
     (*) die "Invalid target $TARGET" ;;
 esac
 
+if [[ $WHEEL_PACKAGE == true ]]; then
+    echo "Wheel Package build started !!!!"
+    create_wheel_package
+fi
+
 echo "Operation complete"

tools/rocm-build/build_miopen-deps.sh

@@ -44,7 +44,7 @@ build_miopen_deps() {
     cd "$COMPONENT_SRC"
 
     # Commenting the rocMLIR & composable_kernel from requirements.txt
-    sed -i '/ROCmSoftwarePlatform\/rocMLIR@\|ROCmSoftwarePlatform\/composable_kernel@/s/^/#/' requirements.txt
+    sed -i '/ROCm\/rocMLIR@\|ROCm\/composable_kernel@/s/^/#/' requirements.txt
     # Extract MLIR commit from requirements.txt
     MLIR_COMMIT="$(awk '/rocMLIR/ {split($1, s, "@"); print s[2]}' requirements.txt)"
 

tools/rocm-build/build_miopen-hip.sh

@@ -13,7 +13,7 @@ build_miopen_hip() {
     echo "Start build"
 
     cd $COMPONENT_SRC
-
+    git config --global --add safe.directory "$COMPONENT_SRC"
     checkout_lfs
 
     if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
@@ -22,8 +22,9 @@ build_miopen_hip() {
    fi
 
     mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
     cmake \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DMIOPEN_BACKEND=HIP \
         -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
         -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \

tools/rocm-build/build_mivisionx.sh

@@ -16,6 +16,8 @@ build_mivisionx() {
        BUILD_DEV=OFF
     fi
 
+    init_rocm_common_cmake_params
+
     if [ -n "$GPU_ARCHS" ]; then
         GPU_TARGETS="$GPU_ARCHS"
     else
@@ -23,7 +25,7 @@ build_mivisionx() {
     fi
 
     cmake \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DROCM_PATH="$ROCM_PATH" \
         -DBUILD_DEV=$BUILD_DEV \
         -DCMAKE_INSTALL_LIBDIR=$(getInstallLibDir) \
@@ -34,6 +36,7 @@ build_mivisionx() {
         "$COMPONENT_SRC"
 
     cmake --build "$BUILD_DIR" -- -j${PROC}
+    cmake --build "$BUILD_DIR" -- install
     cpack -G ${PKGTYPE^^}
 
     rm -rf _CPack_Packages/ && find -name '*.o' -delete

tools/rocm-build/build_omniperf.sh

@@ -0,0 +1,171 @@
+#!/bin/bash
+
+source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
+
+printUsage() {
+    echo
+    echo "Usage: ${BASH_SOURCE##*/} [options ...]"
+    echo
+    echo "Options:"
+    echo "  -c,  --clean              Clean output and delete all intermediate work"
+    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
+    echo "  -p,  --package <type>     Specify packaging format"
+    echo "  -r,  --release            Make a release build instead of a debug build"
+    echo "  -a,  --address_sanitizer  Enable address sanitizer"
+    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
+                                      type referred to by pkg_type"
+    echo "  -w,  --wheel              Creates python wheel package of omniperf.
+                                      It needs to be used along with -r option"
+    echo "  -h,  --help               Prints this help"
+    echo
+    echo "Possible values for <type>:"
+    echo "  deb -> Debian format (default)"
+    echo "  rpm -> RPM format"
+    echo
+
+    return 0
+}
+
+API_NAME="omniperf"
+PROJ_NAME="$API_NAME"
+LIB_NAME="lib${API_NAME}"
+TARGET="build"
+MAKETARGET="deb"
+PACKAGE_ROOT="$(getPackageRoot)"
+PACKAGE_LIB="$(getLibPath)"
+BUILD_DIR="$(getBuildPath $API_NAME)"
+PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
+PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
+ROCM_WHEEL_DIR="${BUILD_DIR}/_wheel"
+BUILD_TYPE="Debug"
+MAKE_OPTS="$DASH_JAY -C $BUILD_DIR"
+SHARED_LIBS="ON"
+CLEAN_OR_OUT=0;
+MAKETARGET="deb"
+PKGTYPE="deb"
+WHEEL_PACKAGE=false
+
+
+#parse the arguments
+VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,static,address_sanitizer,outdir:,package:,wheel -- "$@")
+eval set -- "$VALID_STR"
+
+while true ;
+do
+    case "$1" in
+        -h | --help)
+                printUsage ; exit 0;;
+        -c | --clean)
+                TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
+        -r | --release)
+                BUILD_TYPE="Release" ; shift ;;
+        -a | --address_sanitizer)
+                set_asan_env_vars
+                set_address_sanitizer_on ; shift ;;
+        -s | --static)
+                SHARED_LIBS="OFF" ; shift ;;
+        -o | --outdir)
+                TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
+        -p | --package)
+                MAKETARGET="$2" ; shift 2 ;;
+        -w | --wheel)
+                WHEEL_PACKAGE=true ; shift ;;
+        --)     shift; break;; # end delimiter
+        *)
+                echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
+    esac
+
+done
+
+RET_CONFLICT=1
+check_conflicting_options "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
+if [ $RET_CONFLICT -ge 30 ]; then
+   print_vars "$API_NAME" "$TARGET" "$BUILD_TYPE" "$SHARED_LIBS" "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
+   exit $RET_CONFLICT
+fi
+
+clean() {
+    echo "Cleaning $PROJ_NAME"
+    rm -rf "$ROCM_WHEEL_DIR"
+    rm -rf "$BUILD_DIR"
+    rm -rf "$PACKAGE_DEB"
+    rm -rf "$PACKAGE_RPM"
+    rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
+    rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
+}
+
+build() {
+    echo "Building $PROJ_NAME"
+    if [ "$DISTRO_ID" = centos-7 ]; then
+        echo "Skip make and uploading packages for Omniperf on Centos7 distro, due to python dependency"
+        exit 0
+    fi
+
+    if [ ! -d "$BUILD_DIR" ]; then
+        mkdir -p "$BUILD_DIR"
+        pushd "$BUILD_DIR" || exit
+
+        echo "ROCm CMake Params: $(rocm_cmake_params)"
+        echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
+
+        print_lib_type $SHARED_LIBS
+        cmake \
+            $(rocm_cmake_params) \
+            $(rocm_common_cmake_params) \
+            -DCHECK_PYTHON_DEPS=NO \
+            -DPYTHON_DEPS=${BUILD_DIR}/python-libs \
+            -DMOD_INSTALL_PATH=${BUILD_DIR}/modulefiles \
+            "$OMNIPERF_ROOT"
+    fi
+
+    make $MAKE_OPTS
+    make $MAKE_OPTS install
+    make $MAKE_OPTS package
+
+    copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
+    copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
+}
+
+create_wheel_package() {
+    echo "Creating Omniperf wheel package"
+
+    # Copy the setup.py generator to build folder
+    mkdir -p "$ROCM_WHEEL_DIR"
+    cp -f "$SCRIPT_ROOT"/generate_setup_py.py "$ROCM_WHEEL_DIR"
+    cp -f "$SCRIPT_ROOT"/repackage_wheel.sh "$ROCM_WHEEL_DIR"
+    cd "$ROCM_WHEEL_DIR" || exit
+
+    # Currently only supports python3.6
+    ./repackage_wheel.sh "$BUILD_DIR"/*.rpm python3.6
+
+    # Copy the wheel created to RPM folder which will be uploaded to artifactory
+    copy_if WHL "WHL" "$PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
+}
+
+print_output_directory() {
+    case ${PKGTYPE} in
+        ("deb")
+            echo "${PACKAGE_DEB}";;
+        ("rpm")
+            echo "${PACKAGE_RPM}";;
+        (*)
+            echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
+    esac
+    exit
+}
+
+verifyEnvSetup
+
+case "$TARGET" in
+    (clean) clean ;;
+    (build) build ;;
+    (outdir) print_output_directory ;;
+    (*) die "Invalid target $TARGET" ;;
+esac
+
+if [[ $WHEEL_PACKAGE == true ]]; then
+    echo "Wheel Package build started !!!!"
+    create_wheel_package
+fi
+
+echo "Operation complete"

tools/rocm-build/build_omnitrace.sh

@@ -0,0 +1,191 @@
+#!/bin/bash
+
+source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
+
+printUsage() {
+    echo
+    echo "Usage: ${BASH_SOURCE##*/} [options ...]"
+    echo
+    echo "Options:"
+    echo "  -c,  --clean              Clean output and delete all intermediate work"
+    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
+    echo "  -p,  --package <type>     Specify packaging format"
+    echo "  -r,  --release            Make a release build instead of a debug build"
+    echo "  -a,  --address_sanitizer  Enable address sanitizer"
+    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
+                                      type referred to by pkg_type"
+    echo "  -w,  --wheel              Creates python wheel package of omnitrace.
+                                      It needs to be used along with -r option"
+    echo "  -h,  --help               Prints this help"
+    echo
+    echo "Possible values for <type>:"
+    echo "  deb -> Debian format (default)"
+    echo "  rpm -> RPM format"
+    echo
+
+    return 0
+}
+
+API_NAME="omnitrace"
+PROJ_NAME="$API_NAME"
+LIB_NAME="lib${API_NAME}"
+TARGET="build"
+MAKETARGET="deb"
+PACKAGE_ROOT="$(getPackageRoot)"
+PACKAGE_LIB="$(getLibPath)"
+BUILD_DIR="$(getBuildPath $API_NAME)"
+PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
+PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
+BUILD_TYPE="Debug"
+MAKE_OPTS="-j 8"
+SHARED_LIBS="ON"
+CLEAN_OR_OUT=0
+MAKETARGET="deb"
+PKGTYPE="deb"
+ASAN=0
+
+#parse the arguments
+VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,address_sanitizer,static,outdir:,package:,wheel -- "$@")
+eval set -- "$VALID_STR"
+
+while true; do
+    case "$1" in
+    -h | --help)
+        printUsage
+        exit 0
+        ;;
+    -c | --clean)
+        TARGET="clean"
+        ((CLEAN_OR_OUT |= 1))
+        shift
+        ;;
+    -r | --release)
+        BUILD_TYPE="RelWithDebInfo"
+        shift
+        ;;
+    -a | --address_sanitizer)
+        ack_and_ignore_asan
+
+        ASAN=1
+        shift
+        ;;
+    -s | --static)
+        SHARED_LIBS="OFF"
+        shift
+        ;;
+    -o | --outdir)
+        TARGET="outdir"
+        PKGTYPE=$2
+        ((CLEAN_OR_OUT |= 2))
+        shift 2
+        ;;
+    -p | --package)
+        MAKETARGET="$2"
+        shift 2
+        ;;
+    -w | --wheel)
+	   echo "omnitrace: wheel build option accepted and ignored"
+       shift
+       ;;
+    --)
+        shift
+        break
+        ;;
+    *)
+        echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
+        exit 20
+        ;;
+    esac
+
+done
+
+RET_CONFLICT=1
+check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+if [ $RET_CONFLICT -ge 30 ]; then
+    print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+    exit $RET_CONFLICT
+fi
+
+clean() {
+    echo "Cleaning $PROJ_NAME"
+    rm -rf "$BUILD_DIR"
+    rm -rf "$PACKAGE_DEB"
+    rm -rf "$PACKAGE_RPM"
+    rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
+    rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
+}
+
+build_omnitrace() {
+    echo "Building $PROJ_NAME"
+    if [ "$DISTRO_ID" = "mariner-2.0" ] || [ "$DISTRO_ID" = "ubuntu-24.04" ] || [ "$DISTRO_ID" = "azurelinux-3.0" ]; then
+        echo "Skip make and uploading packages for Omnitrace on \"${DISTRO_ID}\" distro"
+        exit 0
+    fi
+
+    if [ $ASAN == 1 ]; then
+        echo "Skip make and uploading packages for Omnitrace on ASAN build"
+        exit 0
+    fi
+    if [ ! -d "$BUILD_DIR" ]; then
+        mkdir -p "$BUILD_DIR"
+        echo "Created build directory: $BUILD_DIR"
+    fi
+
+    echo "Build directory: $BUILD_DIR"
+    pushd "$BUILD_DIR" || exit
+    print_lib_type $SHARED_LIBS
+
+    echo "ROCm CMake Params: $(rocm_cmake_params)"
+    echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
+
+
+    if [ $ASAN == 1 ]; then
+        echo "Address Sanitizer path"
+
+    else
+        cmake \
+            $(rocm_cmake_params) \
+            $(rocm_common_cmake_params) \
+            -DOMNITRACE_BUILD_{LIBUNWIND,DYNINST}=ON \
+            -DDYNINST_BUILD_{TBB,BOOST,ELFUTILS,LIBIBERTY}=ON \
+            "$OMNITRACE_ROOT"
+    fi
+
+
+    popd || exit
+
+    echo "Make Options: $MAKE_OPTS"
+    cmake --build "$BUILD_DIR" --target all -- $MAKE_OPTS
+    cmake --build "$BUILD_DIR" --target install -- $MAKE_OPTS
+    cmake --build "$BUILD_DIR" --target package -- $MAKE_OPTS
+
+    copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
+    copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
+}
+
+print_output_directory() {
+    case ${PKGTYPE} in
+    "deb")
+        echo "${PACKAGE_DEB}"
+        ;;
+    "rpm")
+        echo "${PACKAGE_RPM}"
+        ;;
+    *)
+        echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
+        exit 1
+        ;;
+    esac
+    exit
+}
+
+verifyEnvSetup
+
+case "$TARGET" in
+clean) clean ;;
+build) build_omnitrace ;;
+outdir) print_output_directory ;;
+*) die "Invalid target $TARGET" ;;
+esac
+
+echo "Operation complete"

tools/rocm-build/build_opencl_icd_loader.sh

@@ -0,0 +1,141 @@
+#!/bin/bash
+
+source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
+PROJ_NAME=OpenCL-ICD-Loader
+TARGET="build"
+MAKEOPTS="$DASH_JAY"
+BUILD_TYPE="Debug"
+PACKAGE_ROOT="$(getPackageRoot)"
+PACKAGE_DEB="$PACKAGE_ROOT/deb/${PROJ_NAME,,}"
+PACKAGE_RPM="$PACKAGE_ROOT/rpm/${PROJ_NAME,,}"
+CLEAN_OR_OUT=0;
+PKGTYPE="deb"
+MAKETARGET="deb"
+API_NAME="rocm-opencl-icd-loader"
+
+printUsage() {
+    echo
+    echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
+    echo
+    echo "Options:"
+    echo "  -c,  --clean              Clean output and delete all intermediate work"
+    echo "  -p,  --package <type>     Specify packaging format"
+    echo "  -r,  --release            Make a release build instead of a debug build"
+    echo "  -h,  --help               Prints this help"
+    echo "  -o,  --outdir             Print path of output directory containing packages"
+    echo "  -s,  --static             Component/Build does not support static builds just accepting this param & ignore. No effect of the param on this build"
+    echo
+    echo "Possible values for <type>:"
+    echo "  deb -> Debian format (default)"
+    echo "  rpm -> RPM format"
+    echo
+    return 0
+}
+
+RET_CONFLICT=1
+check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+if [ $RET_CONFLICT -ge 30 ]; then
+   print_vars $TARGET $BUILD_TYPE $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+   exit $RET_CONFLICT
+fi
+
+clean_opencl_icd_loader() {
+    echo "Cleaning $PROJ_NAME"
+    rm -rf "$PACKAGE_DEB"
+    rm -rf "$PACKAGE_RPM"
+    rm -rf "$PACKAGE_ROOT/${PROJ_NAME,,}"
+}
+
+copy_pkg_files_to_rocm() {
+    local comp_folder=$1
+    local comp_pkg_name=$2
+
+    cd "${OUT_DIR}/${PKGTYPE}/${comp_folder}"|| exit 2
+    if [ "${PKGTYPE}" = 'deb' ]; then
+        dpkg-deb -x ${comp_pkg_name}_*.deb pkg/
+    else
+        mkdir pkg && pushd pkg/ || exit 2
+        if [[ "${comp_pkg_name}" != *-dev* ]]; then
+            rpm2cpio ../${comp_pkg_name}-*.rpm | cpio -idmv
+        else
+            rpm2cpio ../${comp_pkg_name}el-*.rpm | cpio -idmv
+        fi
+        popd || exit 2
+    fi
+    ls ./pkg -alt
+    cp -r ./pkg/*/rocm*/* "${ROCM_PATH}" || exit 2
+    rm -rf pkg/
+}
+
+build_opencl_icd_loader() {
+    echo "Downloading $PROJ_NAME" package
+    if [ "$DISTRO_NAME" = ubuntu ]; then
+        mkdir -p "$PACKAGE_DEB"
+        local rocm_ver=${ROCM_VERSION}
+        if [ ${ROCM_VERSION##*.} = 0 ]; then
+            rocm_ver=${ROCM_VERSION%.*}
+        fi
+        local url="https://repo.radeon.com/rocm/apt/${rocm_ver}/pool/main/r/${API_NAME}/"
+        local package
+        package=$(curl -s "$url" | grep -Po 'href="\K[^"]*' | grep "${DISTRO_RELEASE}" | head -n 1)
+
+        if [ -z "$package" ]; then
+            echo "No package found for Ubuntu version $DISTRO_RELEASE"
+            exit 1
+        fi
+
+        wget -t3 -P "$PACKAGE_DEB" "${url}${package}"
+        copy_pkg_files_to_rocm ${PROJ_NAME,,} ${API_NAME}
+    else
+        echo "$DISTRO_ID is not supported..."
+        exit 2
+    fi
+
+    echo "Installing $PROJ_NAME" package
+}
+
+print_output_directory() {
+    case ${PKGTYPE} in
+        ("deb")
+            echo ${PACKAGE_DEB};;
+        ("rpm")
+            echo ${PACKAGE_RPM};;
+        (*)
+            echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
+    esac
+    exit
+}
+
+VALID_STR=`getopt -o hcraswlo:p: --long help,clean,release,outdir:,package: -- "$@"`
+eval set -- "$VALID_STR"
+while true ;
+do
+    case "$1" in
+        (-c  | --clean )
+            TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
+        (-r  | --release )
+            BUILD_TYPE="RelWithDebInfo" ; shift ;;
+        (-h  | --help )
+            printUsage ; exit 0 ;;
+        (-a  | --address_sanitizer)
+            ack_and_ignore_asan ; shift ;;
+        (-o  | --outdir)
+            TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
+        (-p | --package)
+            MAKETARGET="$2" ; shift 2;;
+	(-s | --static)
+            echo "-s parameter accepted but ignored" ; shift ;;
+        --)     shift; break;;
+        (*)
+            echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
+    esac
+done
+
+case $TARGET in
+    (clean) clean_opencl_icd_loader ;;
+    (build) build_opencl_icd_loader ;;
+    (outdir) print_output_directory ;;
+    (*) die "Invalid target $TARGET" ;;
+esac
+
+echo "Operation complete"

tools/rocm-build/build_rccl.sh

@@ -26,14 +26,16 @@ build_rccl() {
         GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
     fi
 
+    init_rocm_common_cmake_params
 
     CC=${ROCM_PATH}/bin/amdclang \
     CXX=$(set_build_variables CXX) \
     cmake \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DHIP_COMPILER=clang \
         -DCMAKE_PREFIX_PATH="${ROCM_PATH};${ROCM_PATH}/share/rocm/cmake/" \
+        ${LAUNCHER_FLAGS} \
         -DCPACK_GENERATOR="${PKGTYPE^^}" \
         -DROCM_PATCH_VERSION=$ROCM_LIBPATCH_VERSION \
         -DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \

tools/rocm-build/build_rocal.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+
+set -ex
+source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
+
+set_component_src rocAL
+
+build_rocal() {
+
+    if [ "$DISTRO_ID" = "mariner-2.0" ] ; then
+     echo "Not building rocal for ${DISTRO_ID}. Exiting..."
+     return 0
+    fi
+
+    echo "Start build"
+
+    # Enable ASAN
+    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
+        set_asan_env_vars
+        set_address_sanitizer_on
+    fi
+
+#    python3 ${COMPONENT_SRC}/rocAL-setup.py
+    pushd /tmp
+    # PyBind11
+    git clone -b v2.11.1  https://github.com/pybind/pybind11
+    cd pybind11 && mkdir build && cd build
+    cmake -DDOWNLOAD_CATCH=ON -DDOWNLOAD_EIGEN=ON ../
+    make -j$(nproc) && sudo make install
+    cd ../..
+    # Turbo JPEG
+    git clone -b 3.0.2 https://github.com/libjpeg-turbo/libjpeg-turbo.git
+    cd libjpeg-turbo && mkdir build && cd build
+    cmake -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_BUILD_TYPE=RELEASE -DENABLE_STATIC=FALSE -DCMAKE_INSTALL_DEFAULT_LIBDIR=lib -DWITH_JPEG8=TRUE ..
+    make -j$(nproc) && sudo make install
+    cd ../..
+    # RapidJSON
+    git clone https://github.com/Tencent/rapidjson.git
+    cd rapidjson && mkdir build && cd build
+    cmake .. && make -j$(nproc) && sudo make install
+    popd
+
+    mkdir -p $BUILD_DIR && cd $BUILD_DIR
+
+    cmake -DAMDRPP_PATH=$ROCM_PATH ${COMPONENT_SRC}
+    make -j${PROC}
+    cmake --build . --target PyPackageInstall
+    sudo make install
+    sudo make package
+    sudo chown -R $(id -u):$(id -g) ${BUILD_DIR}
+
+    rm -rf _CPack_Packages/ && find -name '*.o' -delete
+    mkdir -p $PACKAGE_DIR
+    cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
+    show_build_cache_stats
+}
+
+clean_rocal() {
+    echo "Cleaning rocAL build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
+    rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
+    echo "Done!"
+}
+
+stage2_command_args "$@"
+
+case $TARGET in
+    build) build_rocal ;;
+    outdir) print_output_directory ;;
+    clean) clean_rocal ;;
+    *) die "Invalid target $TARGET" ;;
+esac

tools/rocm-build/build_rocalution.sh

@@ -22,6 +22,7 @@ build_rocalution() {
     echo "CXX compiler: $CXX"
 
     mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
 
     if [ -n "$GPU_ARCHS" ]; then
         GPU_TARGETS="$GPU_ARCHS"
@@ -32,7 +33,7 @@ build_rocalution() {
     cmake \
         -DSUPPORT_HIP=ON \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DCPACK_SET_DESTDIR=OFF \
         -DBUILD_CLIENTS_SAMPLES=ON \

tools/rocm-build/build_rocblas.sh

@@ -28,11 +28,12 @@ build_rocblas() {
     else
         GPU_TARGETS="gfx908:xnack-;gfx90a:xnack+;gfx90a:xnack-;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
     fi
+    init_rocm_common_cmake_params
 
     cmake \
         -DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake \
         -DBUILD_DIR="${BUILD_DIR}" \
-        $(rocm_common_cmake_params) \
+	"${rocm_math_common_cmake_params[@]}" \
         -DROCM_DIR="${ROCM_PATH}" \
         ${LAUNCHER_FLAGS} \
         -DCMAKE_PREFIX_PATH="${DEPS_DIR};${ROCM_PATH}" \

tools/rocm-build/build_rocdecode.sh

@@ -4,15 +4,16 @@ source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
 set_component_src rocDecode
 BUILD_DEV=ON
 build_rocdecode() {
-    if [ "$DISTRO_ID" = "centos-7" ] ; then
+    if [ "$DISTRO_ID" = "centos-7" ] || [ "$DISTRO_ID" = "sles-15.4" ] ; then
      echo "Not building rocDecode for ${DISTRO_ID}. Exiting..." 
      return 0
     fi
 
     echo "Start build"
     mkdir -p $BUILD_DIR && cd $BUILD_DIR
+    python3 ${COMPONENT_SRC}/rocDecode-setup.py --developer OFF
     
-    cmake ${COMPONENT_SRC}
+    cmake -DROCM_DEP_ROCMCORE=ON ${COMPONENT_SRC}
     make -j8
     make install
     make package

tools/rocm-build/build_rocfft.sh

@@ -16,6 +16,7 @@ build_rocfft() {
          set_address_sanitizer_on
     fi
     mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
+    init_rocm_common_cmake_params
 
     if [ -n "$GPU_ARCHS" ]; then
         GPU_TARGETS="$GPU_ARCHS"
@@ -26,7 +27,7 @@ build_rocfft() {
     CXX="${ROCM_PATH}/bin/hipcc" \
     cmake \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DUSE_HIP_CLANG=ON \
         -DHIP_COMPILER=clang  \

tools/rocm-build/build_rocm-cmake.sh

@@ -10,11 +10,13 @@ printUsage() {
     echo "  -c,  --clean              Clean output and delete all intermediate work"
     echo "  -r,  --release            Build a release version of the package"
     echo "  -a,  --address_sanitizer  Enable address sanitizer"
-    echo "  -s,  --static             Supports static CI by accepting this param & not bailing out. No effect of the param though"
+    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
+    echo "  -w,  --wheel              Creates python wheel package of rocm-cmake. 
+                                      It needs to be used along with -r option"
     echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
     type referred to by pkg_type"
     echo "  -p,  --package <type>     Specify packaging format"
-    echo "  -h,  --help             Prints this help"
+    echo "  -h,  --help               Prints this help"
     echo
     echo
 
@@ -30,6 +32,7 @@ ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
 ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
 ROCM_CMAKE_PACKAGE_DEB="$(getPackageRoot)/deb/rocm-cmake"
 ROCM_CMAKE_PACKAGE_RPM="$(getPackageRoot)/rpm/rocm-cmake"
+ROCM_WHEEL_DIR="${ROCM_CMAKE_BUILD_DIR}/_wheel"
 ROCM_CMAKE_BUILD_TYPE="debug"
 BUILD_TYPE="Debug"
 SHARED_LIBS="ON"
@@ -37,7 +40,7 @@ CLEAN_OR_OUT=0;
 PKGTYPE="deb"
 MAKETARGET="deb"
 
-VALID_STR=`getopt -o hcraso:p: --long help,clean,release,static,address_sanitizer,outdir:,package: -- "$@"`
+VALID_STR=`getopt -o hcraswo:p: --long help,clean,release,static,wheel,address_sanitizer,outdir:,package: -- "$@"`
 eval set -- "$VALID_STR"
 
 while true ;
@@ -53,6 +56,8 @@ do
                 ack_and_ignore_asan ; shift ;;
         (-s | --static)
                 SHARED_LIBS="OFF" ; shift ;;
+        (-w | --wheel)
+            WHEEL_PACKAGE=true ; shift ;;
         (-o | --outdir)
                 TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
         (-p | --package)
@@ -73,6 +78,7 @@ fi
 
 
 clean_rocm_cmake() {
+    rm -rf "$ROCM_WHEEL_DIR"
     rm -rf $ROCM_CMAKE_BUILD_DIR
     rm -rf $ROCM_CMAKE_PACKAGE_DEB
     rm -rf $ROCM_CMAKE_PACKAGE_RPM
@@ -87,6 +93,7 @@ build_rocm_cmake() {
 
         cmake \
             $(rocm_cmake_params) \
+            -DBUILD_SHARED_LIBS=$SHARED_LIBS \
             -DCPACK_SET_DESTDIR="OFF" \
             -DROCM_DISABLE_LDCONFIG=ON \
             $ROCM_CMAKE_ROOT
@@ -99,6 +106,19 @@ build_rocm_cmake() {
     copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$ROCM_CMAKE_PACKAGE_RPM" $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm
 }
 
+create_wheel_package() {
+    echo "Creating rocm-cmake wheel package"
+    # Copy the setup.py generator to build folder
+    mkdir -p $ROCM_WHEEL_DIR
+    cp -f $SCRIPT_ROOT/generate_setup_py.py $ROCM_WHEEL_DIR
+    cp -f $SCRIPT_ROOT/repackage_wheel.sh $ROCM_WHEEL_DIR
+    cd $ROCM_WHEEL_DIR
+    # Currently only supports python3.6
+    ./repackage_wheel.sh $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm python3.6
+    # Copy the wheel created to RPM folder which will be uploaded to artifactory
+    copy_if WHL "WHL" "$ROCM_CMAKE_PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
+}
+
 print_output_directory() {
     case ${PKGTYPE} in
         ("deb")
@@ -118,4 +138,9 @@ case $TARGET in
     (*) die "Invalid target $TARGET" ;;
 esac
 
+if [[ $WHEEL_PACKAGE == true ]]; then
+    echo "Wheel Package build started !!!!"
+    create_wheel_package
+fi
+
 echo "Operation complete"

tools/rocm-build/build_rocprim.sh

@@ -24,13 +24,14 @@ build_rocprim() {
         GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
     fi
 
+    init_rocm_common_cmake_params
     CXX="${ROCM_PATH}/bin/hipcc" \
     cmake \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DBUILD_BENCHMARK=OFF \
-        -DBUILD_BENCHMARK=OFF \
+	-DBUILD_SHARED_LIBS=ON \
         -DBUILD_TEST=ON \
         -DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
         "$COMPONENT_SRC"

tools/rocm-build/build_rocprofiler-sdk.sh

@@ -0,0 +1,222 @@
+#!/bin/bash
+
+source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
+
+printUsage() {
+    echo
+    echo "Usage: ${BASH_SOURCE##*/} [options ...]"
+    echo
+    echo "Options:"
+    echo "  -c,  --clean              Clean output and delete all intermediate work"
+    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
+    echo "  -w,  --wheel              Creates python wheel package of rocprofiler-sdk. 
+                                      It needs to be used along with -r option"
+    echo "  -p,  --package <type>     Specify packaging format"
+    echo "  -r,  --release            Make a release build instead of a debug build"
+    echo "  -a,  --address_sanitizer  Enable address sanitizer"
+    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
+    type referred to by pkg_type"
+    echo "  -h,  --help               Prints this help"
+    echo
+    echo "Possible values for <type>:"
+    echo "  deb -> Debian format (default)"
+    echo "  rpm -> RPM format"
+    echo
+
+    return 0
+}
+
+API_NAME="rocprofiler-sdk"
+PROJ_NAME="$API_NAME"
+LIB_NAME="lib${API_NAME}"
+TARGET="build"
+MAKETARGET="deb"
+PACKAGE_ROOT="$(getPackageRoot)"
+PACKAGE_LIB="$(getLibPath)"
+PACKAGE_INCLUDE="$(getIncludePath)"
+BUILD_DIR="$(getBuildPath $API_NAME)"
+PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
+PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
+ROCM_WHEEL_DIR="${BUILD_DIR}/_wheel"
+PACKAGE_PREFIX="$ROCM_INSTALL_PATH"
+BUILD_TYPE="Debug"
+MAKE_OPTS="$DASH_JAY"
+SHARED_LIBS="ON"
+CLEAN_OR_OUT=0
+MAKETARGET="deb"
+PKGTYPE="deb"
+
+GPU_LIST="gfx900;gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1031;gfx1100;gfx1101;gfx1102"
+ASAN=0
+
+VALID_STR=$(getopt -o hcrawso:p: --long help,clean,release,static,address_sanitizer,wheel,outdir:,package: -- "$@")
+eval set -- "$VALID_STR"
+
+while true; do
+    case "$1" in
+        -h | --help)
+            printUsage
+            exit 0
+        ;;
+        -c | --clean)
+            TARGET="clean"
+            ((CLEAN_OR_OUT |= 1))
+            shift
+        ;;
+        -r | --release)
+            BUILD_TYPE="RelWithDebInfo"
+            shift
+        ;;
+        -a | --address_sanitizer)
+            set_address_sanitizer_on
+	        set_asan_env_vars
+            ASAN=1
+            shift
+        ;;
+        -s | --static)
+            SHARED_LIBS="OFF"
+            shift
+        ;;
+        -w | --wheel)
+            WHEEL_PACKAGE=true
+            shift
+        ;;
+        -o | --outdir)
+            TARGET="outdir"
+            PKGTYPE=$2
+            OUT_DIR_SPECIFIED=1
+            ((CLEAN_OR_OUT |= 2))
+            shift 2
+        ;;
+        -p | --package)
+            MAKETARGET="$2"
+            shift 2
+        ;;
+        --)
+            shift
+            break
+        ;; # end delimiter
+        *)
+            echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
+            exit 20
+        ;;
+    esac
+
+done
+
+RET_CONFLICT=1
+check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+if [ $RET_CONFLICT -ge 30 ]; then
+    print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+    exit $RET_CONFLICT
+fi
+
+clean() {
+    echo "Cleaning $PROJ_NAME"
+    rm -rf "$ROCM_WHEEL_DIR"
+    rm -rf "$BUILD_DIR"
+    rm -rf "$PACKAGE_DEB"
+    rm -rf "$PACKAGE_RPM"
+    rm -rf "$PACKAGE_ROOT/${PROJ_NAME}"
+    rm -rf "$PACKAGE_ROOT/libexec/${PROJ_NAME}"
+    rm -rf "$PACKAGE_INCLUDE/${PROJ_NAME}"
+    rm -rf "$PACKAGE_LIB/${LIB_NAME}"*
+    rm -rf "$PACKAGE_LIB/${PROJ_NAME}"
+}
+
+build_rocprofiler-sdk() {
+    if [ ! -f "${ROCPROFILER_SDK_ROOT}/CMakeLists.txt" ]; then
+        echo "Warning: $ROCPROFILER_SDK_ROOT not found"
+    else
+        echo "Building $PROJ_NAME"
+        PACKAGE_CMAKE="$(getCmakePath)"
+        if [ ! -d "$BUILD_DIR" ]; then
+            mkdir -p "$BUILD_DIR"
+            pushd "$BUILD_DIR"
+            print_lib_type $SHARED_LIBS
+
+            if [ $ASAN == 1 ]; then
+                cmake \
+                $(rocm_cmake_params) \
+                $(rocm_common_cmake_params) \
+                -DAMDDeviceLibs_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/AMDDeviceLibs" \
+                -Dhip_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hip" \
+                -Dhip-lang_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hip-lang" \
+                -Damd_comgr_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/amd_comgr" \
+                -Dhsa-runtime64_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hsa-runtime64" \
+                -Dhsakmt_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hsakmt" \
+                -DCMAKE_HIP_COMPILER_ROCM_ROOT="${ROCM_INSTALL_PATH}" \
+                -DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH};${ROCM_INSTALL_PATH}/lib/asan" \
+                -DBUILD_SHARED_LIBS=$SHARED_LIBS \
+                -DGPU_TARGETS="$GPU_LIST" \
+                -DCPACK_DEBIAN_PACKAGE_SHLIBDEPS=OFF \
+                -DPython3_EXECUTABLE=$(which python3) \
+                "$ROCPROFILER_SDK_ROOT"
+            else
+                cmake \
+                $(rocm_cmake_params) \
+                $(rocm_common_cmake_params) \
+                -DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH}" \
+                -DBUILD_SHARED_LIBS=$SHARED_LIBS \
+                -DGPU_TARGETS="$GPU_LIST" \
+                -DROCPROFILER_BUILD_SAMPLES=ON \
+                -DROCPROFILER_BUILD_TESTS=ON \
+                -DCPACK_DEBIAN_PACKAGE_SHLIBDEPS=OFF \
+                -DPython3_EXECUTABLE=$(which python3) \
+                "$ROCPROFILER_SDK_ROOT"
+            fi
+
+            popd
+        fi
+        cmake --build "$BUILD_DIR" --target all -- $MAKE_OPTS
+        cmake --build "$BUILD_DIR" --target install -- $MAKE_OPTS
+        cmake --build "$BUILD_DIR" --target package -- $MAKE_OPTS
+
+        copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
+        copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
+    fi
+}
+
+create_wheel_package() {
+    echo "Creating rocprofiler sdk wheel package"
+    mkdir -p "$ROCM_WHEEL_DIR"
+    cp -f "$SCRIPT_ROOT"/generate_setup_py.py "$ROCM_WHEEL_DIR"
+    cp -f "$SCRIPT_ROOT"/repackage_wheel.sh "$ROCM_WHEEL_DIR"
+    cd "$ROCM_WHEEL_DIR"
+    # Currently only supports python3.6
+    ./repackage_wheel.sh "$BUILD_DIR"/*.rpm python3.6
+    # Copy the wheel created to RPM folder which will be uploaded to artifactory
+    copy_if WHL "WHL" "$PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
+}
+
+print_output_directory() {
+    case ${PKGTYPE} in
+        "deb")
+            echo ${PACKAGE_DEB}
+        ;;
+        "rpm")
+            echo ${PACKAGE_RPM}
+        ;;
+        *)
+            echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
+            exit 1
+        ;;
+    esac
+    exit
+}
+
+verifyEnvSetup
+
+case "$TARGET" in
+    clean) clean ;;
+    build) build_rocprofiler-sdk ;;
+    outdir) print_output_directory ;;
+    *) die "Invalid target $TARGET" ;;
+esac
+
+if [[ $WHEEL_PACKAGE == true ]]; then
+    echo "Wheel Package build started !!!!"
+    create_wheel_package
+fi
+
+echo "Operation complete"

tools/rocm-build/build_rocrand.sh

@@ -25,10 +25,12 @@ build_rocrand() {
         GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
     fi
 
+    init_rocm_common_cmake_params
+
     CXX=$(set_build_variables CXX)\
     cmake \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DBUILD_TEST=ON \
         -DBUILD_BENCHMARK=ON \

tools/rocm-build/build_rocsolver.sh

@@ -28,11 +28,13 @@ build_rocsolver() {
         GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
     fi
 
+    init_rocm_common_cmake_params
+
     CXX="${ROCM_PATH}/bin/hipcc" \
     cmake \
         -DCPACK_SET_DESTDIR=OFF \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -Drocblas_DIR="${ROCM_PATH}/rocblas/lib/cmake/rocblas" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DBUILD_CLIENTS_TESTS=ON \

tools/rocm-build/build_rocsparse.sh

@@ -27,12 +27,14 @@ build_rocsparse() {
     fi
 
     ROCSPARSE_TEST_MIRROR=$MIRROR \
-    CXX=$(set_build_variables CXX)\
-    CC=$(set_build_variables CC)\
+    export CXX=$(set_build_variables CXX)\
+    export CC=$(set_build_variables CC)\
+
+    init_rocm_common_cmake_params
     cmake \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}"\
         -DBUILD_CLIENTS_SAMPLES=ON \
         -DBUILD_CLIENTS_TESTS=ON \
         -DBUILD_CLIENTS_BENCHMARKS=ON \

tools/rocm-build/build_rocthrust.sh

@@ -27,10 +27,12 @@ build_rocthrust() {
         GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
     fi
 
+    init_rocm_common_cmake_params
+
     CXX=$(set_build_variables CXX)\
     cmake \
         ${LAUNCHER_FLAGS} \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
         -DROCPRIM_ROOT="${ROCM_PATH}/rocprim" \

tools/rocm-build/build_rocwmma.sh

@@ -27,9 +27,11 @@ build_rocwmma() {
         GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1100;gfx1101"
     fi
 
+    init_rocm_common_cmake_params
+
     CXX=$(set_build_variables CXX)\
     cmake \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         ${LAUNCHER_FLAGS} \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
         -DROCWMMA_BUILD_VALIDATION_TESTS=ON \

tools/rocm-build/build_rpp.sh

@@ -12,7 +12,7 @@ ROCM_LLVM_LIB_RPATH="\$ORIGIN/llvm/lib"
 rpp_specific_cmake_params() {
     local rpp_cmake_params
     if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
-        rpp_cmake_params="-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH:$LLVM_LIBDIR"
+        rpp_cmake_params="-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_ASAN_EXE_RPATH:$LLVM_LIBDIR"
     else
         rpp_cmake_params=""
     fi
@@ -41,14 +41,16 @@ build_rpp() {
         GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100"
     fi
 
+    init_rocm_common_cmake_params
+
     cmake \
-        $(rocm_common_cmake_params) \
+        "${rocm_math_common_cmake_params[@]}" \
         ${LAUNCHER_FLAGS} \
         -DBACKEND=HIP \
         -DCMAKE_INSTALL_LIBDIR=$(getInstallLibDir) \
         $(rpp_specific_cmake_params) \
         -DAMDGPU_TARGETS=${GPU_TARGETS} \
-        -DCMAKE_SHARED_LINKER_FLAGS_INIT="-fno-openmp-implicit-rpath -Wl,--enable-new-dtags,--rpath,${ROCM_LIB_RPATH}:${DEPS_DIR}/lib:${ROCM_LLVM_LIB_RPATH}" \
+        -DCMAKE_SHARED_LINKER_FLAGS_INIT="-fno-openmp-implicit-rpath -Wl,--enable-new-dtags,--build-id=sha1,--rpath,${ROCM_LIB_RPATH}:${DEPS_DIR}/lib:${ROCM_LLVM_LIB_RPATH}" \
         -DCMAKE_PREFIX_PATH="${DEPS_DIR};${ROCM_PATH}" \
         "$COMPONENT_SRC"
 

tools/rocm-build/compute_helper.sh

@@ -189,6 +189,65 @@ echo " PKGTYPE= $6 "
 echo " MAKETARGET = $7 "
 }
 
+rocm_math_common_cmake_params=()
+init_rocm_common_cmake_params(){
+  local retCmakeParams=${1:-rocm_math_common_cmake_params}
+  local SET_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'}
+  local ASAN_LIBDIR="lib/asan"
+  local CMAKE_PATH=$(getCmakePath)
+# Common cmake parameters can be set
+# component build scripts can use this function
+  local cmake_params
+  if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
+    cmake_params=(
+        "-DCMAKE_PREFIX_PATH=$CMAKE_PATH;${ROCM_PATH}/$ASAN_LIBDIR;$ROCM_PATH/llvm;$ROCM_PATH"
+        "-DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_ASAN_LIB_RPATH"
+        "-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_ASAN_EXE_RPATH"
+        "-DENABLE_ASAN_PACKAGING=true"
+    )
+  else
+    cmake_params=(
+        "-DCMAKE_PREFIX_PATH=${ROCM_PATH}/llvm;${ROCM_PATH}"
+        "-DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_LIB_RPATH"
+        "-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_EXE_RPATH"
+    )
+  fi
+
+  cmake_params+=(
+      "-DCMAKE_VERBOSE_MAKEFILE=1"
+      "-DCMAKE_BUILD_TYPE=${SET_BUILD_TYPE}"
+      "-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE"
+      "-DCMAKE_INSTALL_PREFIX=${ROCM_PATH}"
+      "-DCMAKE_PACKAGING_INSTALL_PREFIX=${ROCM_PATH}"
+      "-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF"
+      "-DROCM_SYMLINK_LIBS=OFF"
+      "-DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH}"
+      "-DROCM_DISABLE_LDCONFIG=ON"
+      "-DROCM_PATH=${ROCM_PATH}"
+  )
+
+  #TODO :remove if clause once debug related issues are fixed
+  if [ "${DISABLE_DEBUG_PACKAGE}" == "true" ] ; then
+    SET_BUILD_TYPE=${BUILD_TYPE:-'Release'}
+    cmake_params+=(
+        "-DCPACK_DEBIAN_DEBUGINFO_PACKAGE=FALSE"
+        "-DCPACK_RPM_DEBUGINFO_PACKAGE=FALSE"
+        "-DCPACK_RPM_INSTALL_WITH_EXEC=FALSE"
+        "-DCMAKE_BUILD_TYPE=${SET_BUILD_TYPE}"
+    )
+  elif [ "$SET_BUILD_TYPE" == "RelWithDebInfo" ] || [ "$SET_BUILD_TYPE" == "Debug" ]; then
+    # RelWithDebinfo optimization level -O2 is having performance impact
+    # So overriding the same to -O3
+    cmake_params+=(
+        "-DCPACK_DEBIAN_DEBUGINFO_PACKAGE=TRUE"
+        "-DCPACK_RPM_DEBUGINFO_PACKAGE=TRUE"
+        "-DCPACK_RPM_INSTALL_WITH_EXEC=TRUE"
+        "-DCMAKE_CXX_FLAGS_RELWITHDEBINFO=-O3 -g -DNDEBUG"
+    )
+  fi
+    eval "${retCmakeParams}=( \"\${cmake_params[@]}\" ) "
+}
+
 # Common cmake parameters can be set
 # component build scripts can use this function
 rocm_common_cmake_params() {

tools/rocm-build/docker/ubuntu20/install-prerequisites.sh

@@ -2,7 +2,6 @@
 
 set -ex
 
-
 apt-get update 
 DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true apt-get install --no-install-recommends -y $(grep -v '^#' /tmp/packages)
 apt-get clean 
@@ -105,7 +104,7 @@ git clone --recurse-submodules -b v1.61.0 https://github.com/grpc/grpc
 cd grpc
 mkdir -p cmake/build
 cd cmake/build
-cmake -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF  -DCMAKE_INSTALL_PREFIX=/usr/grpc   -DCMAKE_CXX_STANDARD=14  ../.. 
+cmake -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF  -DCMAKE_INSTALL_PREFIX=/usr/grpc   -DCMAKE_CXX_STANDARD=14  -DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,'$ORIGIN' ../.. 
 make -j$(nproc)
 make install 
 cd  / 
@@ -120,11 +119,11 @@ mv amd-blis-mt /usr/blis
 cd / 
 rm -rf /tmp/blis
 
-## Download aocl-linux-aocc-4.0_1_amd64.deb
+## Download aocl-linux-gcc-4.2.0_1_amd64.deb
 mkdir -p /tmp/aocl 
 cd /tmp/aocl 
-wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-0/aocl-linux-aocc-4.0_1_amd64.deb 
-apt install ./aocl-linux-aocc-4.0_1_amd64.deb
+wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb 
+apt install ./aocl-linux-gcc-4.2.0_1_amd64.deb
 rm -rf /tmp/aocl
 
 ## lapack(3.9.1v)
@@ -180,8 +179,7 @@ cd ninja-1.11.1.g95dee.kitware.jobserver-1
 cp ninja /usr/local/bin/ 
 rm -rf /tmp/ninja
 
-# Install pre-built FFmpeg and dependencies
-# See docker/build-deps for instructions on how to build these packages
+# Install FFmpeg from source
 wget -qO- https://www.ffmpeg.org/releases/ffmpeg-4.4.2.tar.gz | tar -xzv -C /usr/local
 
 command -v lbzip2 

tools/rocm-build/docker/ubuntu20/packages

@@ -8,6 +8,7 @@ bison
 bridge-utils
 build-essential
 bzip2
+ccache
 check
 chrpath
 cifs-utils
@@ -97,6 +98,7 @@ libva-dev
 libvirt-clients
 libvirt-daemon-system
 libyaml-cpp-dev
+libzstd-dev
 llvm
 llvm-6.0-dev
 llvm-dev
@@ -119,9 +121,11 @@ python3-yaml
 python3.8-dev
 re2c
 redis-tools
+# Eventually we should be able to remove rpm for debian builds.
 rpm
 rsync
 ssh
+# This makes life more pleasent inside the container
 strace
 sudo
 systemtap-sdt-dev

tools/rocm-build/docker/ubuntu22/install-prerequisities.sh

@@ -1,6 +1,6 @@
 #! /usr/bin/bash
 
-set -ex
+set -x
 
 apt-get -y update 
 DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true apt-get install --no-install-recommends -y $(sed 's/#.*//' /tmp/packages)
@@ -60,7 +60,6 @@ apt install -y sharp
 apt clean
 rm -rf /var/cache/apt/ /var/lib/apt/lists/* mlnx /etc/apt/sources.list.d/sharp.list
 
-
 apt update
 apt -y install libunwind-dev
 apt -y install libgoogle-glog-dev
@@ -118,12 +117,12 @@ git clone --recurse-submodules -b v1.61.0 https://github.com/grpc/grpc
 cd grpc
 mkdir -p build 
 cd build
-cmake  -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_STANDARD=14 .. 
+cmake  -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_STANDARD=14 -DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,'$ORIGIN' .. 
 make -j $(nproc) install 
 rm -rf /tmp/grpc
 
 ## rocBLAS Pre-requisites
-## Download prebuilt AMD multithreaded   (2.0)
+## Download prebuilt AMD multithreaded blis (2.0)
 ## Reference : https://github.com/ROCmSoftwarePlatform/rocBLAS/blob/develop/install.sh#L403
 mkdir -p /tmp/blis 
 cd /tmp/blis
@@ -131,12 +130,13 @@ wget -O - https://github.com/amd/blis/releases/download/2.0/aocl-blis-mt-ubuntu-
 mv amd-blis-mt /usr/blis 
 cd / 
 rm -rf /tmp/blis
+
 ## rocBLAS Pre-requisites(SWDEV-404612)
-## Download aocl-linux-aocc-4.0_1_amd64
+## Download aocl-linux-gcc-4.2.0_1_amd64.deb
 mkdir -p /tmp/aocl 
 cd /tmp/aocl 
-wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-0/aocl-linux-aocc-4.0_1_amd64.deb 
-apt install ./aocl-linux-aocc-4.0_1_amd64.deb 
+wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb 
+apt install ./aocl-linux-gcc-4.2.0_1_amd64.deb 
 rm -rf /tmp/aocl
 
 ## hipBLAS Pre-requisites
@@ -194,9 +194,62 @@ cd ninja-1.11.1.g95dee.kitware.jobserver-1
 cp ninja /usr/local/bin/ 
 rm -rf /tmp/ninja
 
-# Install pre-built FFmpeg and dependencies
-# See docker/build-deps for instructions on how to build these packages
-wget -qO- https://www.ffmpeg.org/releases/ffmpeg-4.4.2.tar.gz  | tar -xzv -C /usr/local
+# Install  FFmpeg and dependencies
+# Build NASM
+mkdir -p /tmp/nasm-2.15.05 
+cd /tmp
+wget -qO- "https://distfiles.macports.org/nasm/nasm-2.15.05.tar.bz2" | tar -xvj 
+cd nasm-2.15.05
+./autogen.sh
+./configure --prefix="/usr/local"
+make -j$(nproc) install
+rm -rf /tmp/nasm-2.15.05
+
+# Build YASM
+mkdir -p /tmp/yasm-1.3.0 
+cd /tmp
+wget -qO- "http://www.tortall.net/projects/yasm/releases/yasm-1.3.0.tar.gz" | tar -xvz 
+cd yasm-1.3.0
+./configure --prefix="/usr/local"
+make -j$(nproc) install
+rm -rf /tmp/yasm-1.3.0
+
+# Build x264
+mkdir -p /tmp/x264-snapshot-20191217-2245-stable
+cd /tmp
+wget -qO-  "https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-20191217-2245-stable.tar.bz2" | tar -xvj
+cd /tmp/x264-snapshot-20191217-2245-stable
+PKG_CONFIG_PATH="/usr/local/lib/pkgconfig" ./configure --prefix="/usr/local" --enable-shared
+make -j$(nproc) install
+rm -rf /tmp/x264-snapshot-20191217-2245-stable
+
+# Build x265
+mkdir -p /tmp/x265_2.7
+cd /tmp
+wget -qO- "https://get.videolan.org/x265/x265_2.7.tar.gz" | tar -xvz
+cd  /tmp/x265_2.7/build/linux
+cmake -G "Unix Makefiles" -DCMAKE_INSTALL_PREFIX="/usr/local" -DENABLE_SHARED:bool=on ../../source
+make -j$(nproc) install
+rm -rf /tmp/x265_2.7
+
+# Build fdk-aac
+mkdir -p /tmp/fdk-aac-2.0.2
+cd /tmp
+wget -qO- "https://sourceforge.net/projects/opencore-amr/files/fdk-aac/fdk-aac-2.0.2.tar.gz" | tar -xvz
+cd /tmp/fdk-aac-2.0.2
+autoreconf -fiv
+./configure --prefix="/usr/local" --enable-shared --disable-static
+make -j$(nproc) install
+rm -rf /tmp/fdk-aac-2.0.2
+
+# Build FFmpeg
+cd /tmp
+git clone -b release/4.4 https://git.ffmpeg.org/ffmpeg.git ffmpeg
+cd ffmpeg
+PKG_CONFIG_PATH="/usr/local/lib/pkgconfig"
+./configure  --prefix="/usr/local" --extra-cflags="-I/usr/local/include"   --extra-ldflags="-L/usr/local/lib"  --extra-libs=-lpthread  --extra-libs=-lm  --enable-shared   --disable-static   --enable-libx264  --enable-libx265  --enable-libfdk-aac  --enable-gpl --enable-nonfree
+make -j$(nproc) install
+rm -rf /tmp/ffmpeg
 
 cp /tmp/local-pin-600 /etc/apt/preferences.d
 
@@ -212,21 +265,21 @@ make -j -C build
 cd /tmp/Gbenchmark/build
 make install
 
-# Build boost-1.82.0 from source for RPP
+# Build boost-1.85.0 from source for RPP
 # Installing in a non-standard location since the test packages of hipFFT and rocFFT pick up the version of
 # the installed Boost library and declare a package dependency on that specific version of Boost.
-# For example, if this was installed in the standard location it would declare a dependency on libboost-dev(el)1.82.0
+# For example, if this was installed in the standard location it would declare a dependency on libboost-dev(el)1.85.0
 # which is not available as a package in any distro.
 # Once this is fixed, we can remove the Boost package from the requirements list and install this
 # in the standard location
-mkdir -p /tmp/boost-1.82.0 
-cd /tmp/boost-1.82.0 
-wget -nv https://sourceforge.net/projects/boost/files/boost/1.82.0/boost_1_82_0.tar.bz2 -O ./boost_1_82_0.tar.bz2 
-tar -xf boost_1_82_0.tar.bz2 --use-compress-program="/usr/local/bin/compressor" 
-cd boost_1_82_0 
+mkdir -p /tmp/boost-1.85.0 
+cd /tmp/boost-1.85.0 
+wget -nv https://sourceforge.net/projects/boost/files/boost/1.85.0/boost_1_85_0.tar.bz2 -O ./boost_1_85_0.tar.bz2 
+tar -xf boost_1_85_0.tar.bz2 --use-compress-program="/usr/local/bin/compressor" 
+cd boost_1_85_0 
 ./bootstrap.sh --prefix=${RPP_DEPS_LOCATION} --with-python=python3 
 ./b2 stage -j$(nproc) threading=multi link=shared cxxflags="-std=c++11" 
 ./b2 install threading=multi link=shared --with-system --with-filesystem 
 ./b2 stage -j$(nproc) threading=multi link=static cxxflags="-std=c++11 -fpic" cflags="-fpic"
 ./b2 install threading=multi link=static --with-system --with-filesystem 
-rm -rf /tmp/boost-1.82.0
+rm -rf /tmp/boost-1.85.0

tools/rocm-build/docker/ubuntu22/packages

@@ -8,6 +8,7 @@ bison
 bridge-utils
 build-essential
 bzip2
+ccache
 check
 chrpath
 cifs-utils
@@ -99,6 +100,7 @@ libva-dev
 libvirt-clients
 libvirt-daemon-system
 libyaml-cpp-dev
+libzstd-dev
 llvm
 llvm-dev
 llvm-runtime
@@ -137,3 +139,4 @@ unzip
 vim
 wget
 xsltproc
+zlib1g-dev

tools/rocm-build/docker/ubuntu24/Dockerfile

@@ -0,0 +1,11 @@
+FROM ubuntu:noble as builder	
+COPY packages /tmp/packages
+COPY local-pin-600 /tmp/local-pin-600
+COPY install-prerequisities.sh /tmp/install-prerequisities.sh
+RUN chmod +x /tmp/install-prerequisities.sh
+ENV KBUILD_PKG_ROOTCMD=
+ENV RPP_DEPS_LOCATION=/usr/local/rpp-deps
+ENV PATH="/opt/venv/bin:$PATH"
+ENV PATH=$PATH:"/usr/local/bin"
+RUN  /tmp/install-prerequisities.sh
+WORKDIR /src

tools/rocm-build/docker/ubuntu24/README.md

@@ -0,0 +1,27 @@
+## Steps to build the Docker Image
+
+1. Clone this repositry
+
+   ```bash
+   git clone https://github.com/ROCm/rocm-build.git
+   ```
+
+2. Go into the OS specific docker directory in build-infra
+
+    ```bash
+    cd rocm-build/build/docker/ubuntu24
+    ```
+
+3. Build the docker image
+
+    ```bash
+    docker build -t <docker Image Name> .
+    ```
+
+    replace the `<docker Image Name>` with the new Docker image Name of your choice,
+
+4. After successful build, verify your \<docker Image Name\> in the list all available docker images.
+
+    ```bash
+    docker images
+    ```

tools/rocm-build/docker/ubuntu24/install-prerequisites.sh

@@ -0,0 +1,237 @@
+
+#! /usr/bin/bash
+set -ex
+
+# The following assumes that you have a cache, e.g.
+# https://docs.docker.com/engine/examples/apt-cacher-ng/
+# Comment out if it breaks things
+echo 'Acquire::http { Proxy "http://rocm-ci-services.amd.com:3142";  };' > /etc/apt/apt.conf.d/01proxy
+
+apt-get update 
+DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true apt-get install --no-install-recommends -y $(sed 's/#.*//' /tmp/packages)
+update-ccache-symlinks
+apt-get upgrade
+apt-get clean 
+rm -rf /var/cache/apt/ /var/lib/apt/lists/* /etc/apt/apt.conf.d/01proxy
+
+#Install  2.17.1 version of git as we are seeing issues with 2.25 , where it was not allowing to add git submodules if the user is different for parent git directory
+curl -o git.tar.gz https://cdn.kernel.org/pub/software/scm/git/git-2.17.1.tar.gz 
+tar -zxf git.tar.gz 
+cd git-* 
+make prefix=/usr/local all    
+make prefix=/usr/local install
+git --version
+
+# venv for python to be able to run pip3 without --break-system-packages
+python3 -m venv /opt/venv
+
+pip3 install --no-cache-dir setuptools wheel tox
+pip3 install --no-cache-dir --pre CppHeaderParser argparse requests lxml barectf recommonmark jinja2==3.0.0 websockets matplotlib numpy scipy minimal msgpack pytest sphinx joblib PyYAML==5.3.1 rocm-docs-core cmake==3.25.2 pandas myst-parser
+
+# Allow sudo for everyone user
+echo 'ALL ALL=(ALL) NOPASSWD:ALL' > /etc/sudoers.d/everyone
+
+# Install OCaml packages to build LLVM's OCaml bindings to be used in lightning compiler test pipeline
+wget -nv https://sourceforge.net/projects/opam.mirror/files/2.1.4/opam-2.1.4-x86_64-linux -O /usr/local/bin/opam 
+chmod +x /usr/local/bin/opam
+opam init --yes --disable-sandboxing
+opam install ctypes --yes
+
+# Install and modify git-repo (#!/usr/bin/env python -> #!/usr/bin/env python3)
+curl https://storage.googleapis.com/git-repo-downloads/repo > /usr/bin/repo
+chmod a+x /usr/bin/repo
+
+# Build ccache from the source
+cd /tmp 
+git clone https://github.com/ccache/ccache -b v4.7.5 
+cd ccache 
+mkdir build 
+cd build 
+cmake -DCMAKE_BUILD_TYPE=Release .. 
+make 
+make install 
+cd /tmp 
+rm -rf ccache
+
+#Install older version of hwloc-devel package for rocrtst
+curl -lO https://download.open-mpi.org/release/hwloc/v1.11/hwloc-1.11.13.tar.bz2
+tar -xvf hwloc-1.11.13.tar.bz2
+cd hwloc-1.11.13
+./configure
+make
+make install
+cp /usr/local/lib/libhwloc.so.5 /usr/lib
+hwloc-info --version
+
+# Install gtest
+mkdir -p /tmp/gtest
+cd /tmp/gtest
+wget https://github.com/google/googletest/archive/refs/tags/v1.14.0.zip -O googletest.zip
+unzip googletest.zip
+cd googletest-1.14.0/ 
+mkdir build
+cd build
+cmake .. 
+make -j$(nproc) 
+make install
+rm -rf /tmp/gtest
+
+## Install gRPC from source
+## RDC Pre-requisites
+GRPC_ARCHIVE=grpc-1.61.0.tar.gz
+mkdir /tmp/grpc
+mkdir /usr/grpc 
+cd /tmp 
+git clone --recurse-submodules -b v1.61.0 https://github.com/grpc/grpc
+cd grpc
+mkdir -p build 
+cd build
+cmake  -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_STANDARD=14 -DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,'$ORIGIN' .. 
+make -j $(nproc) install 
+rm -rf /tmp/grpc
+
+## rocBLAS Pre-requisites(ROCMOPS-3856)
+## Download prebuilt AMD multithreaded blis (2.0)
+## Reference : https://github.com/ROCmSoftwarePlatform/rocBLAS/blob/develop/install.sh#L403
+mkdir -p /tmp/blis 
+cd /tmp/blis
+wget -O - https://github.com/amd/blis/releases/download/2.0/aocl-blis-mt-ubuntu-2.0.tar.gz | tar xfz - 
+mv amd-blis-mt /usr/blis 
+cd / 
+rm -rf /tmp/blis
+
+## rocBLAS Pre-requisites(SWDEV-404612)
+## Download aocl-linux-gcc-4.2.0_1_amd64.deb
+mkdir -p /tmp/aocl 
+cd /tmp/aocl 
+wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb 
+apt install ./aocl-linux-gcc-4.2.0_1_amd64.deb 
+rm -rf /tmp/aocl
+
+## hipBLAS Pre-requisites
+## lapack(3.9.1v)
+## Reference https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/install.sh#L174
+lapack_version=3.9.1
+lapack_srcdir=lapack-$lapack_version
+lapack_blddir=lapack-$lapack_version-bld
+mkdir -p /tmp/lapack
+cd /tmp/lapack
+rm -rf "$lapack_srcdir" "$lapack_blddir" 
+wget -O - https://github.com/Reference-LAPACK/lapack/archive/refs/tags/v3.9.1.tar.gz | tar xzf - 
+cmake -H$lapack_srcdir -B$lapack_blddir -DCMAKE_BUILD_TYPE=Release -DCMAKE_Fortran_FLAGS=-fno-optimize-sibling-calls -DBUILD_TESTING=OFF -DCBLAS=ON -DLAPACKE=OFF
+make -j$(nproc) -C "$lapack_blddir"
+make -C "$lapack_blddir" install
+cd $lapack_blddir
+cp -r ./include/* /usr/local/include/ 
+cp -r ./lib/* /usr/local/lib 
+cd / 
+rm -rf /tmp/lapack
+
+## rocSOLVER Pre-requisites
+## FMT(7.1.3v)
+## Reference https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/install.sh#L152
+fmt_version=7.1.3
+fmt_srcdir=fmt-$fmt_version
+fmt_blddir=fmt-$fmt_version-bld
+mkdir -p /tmp/fmt
+cd /tmp/fmt
+rm -rf "$fmt_srcdir" "$fmt_blddir"
+wget -O - https://github.com/fmtlib/fmt/archive/refs/tags/7.1.3.tar.gz | tar xzf -
+cmake -H$fmt_srcdir -B$fmt_blddir -DCMAKE_BUILD_TYPE=Release -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DCMAKE_CXX_STANDARD=17 -DCMAKE_CXX_EXTENSIONS=OFF -DCMAKE_CXX_STANDARD_REQUIRED=ON -DFMT_DOC=OFF -DFMT_TEST=OFF
+make -j$(nproc) -C "$fmt_blddir"
+make -C "$fmt_blddir" install
+
+# Build and install libjpeg-turbo
+mkdir -p /tmp/libjpeg-turbo 
+cd /tmp/libjpeg-turbo 
+wget -nv https://github.com/rrawther/libjpeg-turbo/archive/refs/heads/2.0.6.2.zip -O libjpeg-turbo-2.0.6.2.zip
+unzip libjpeg-turbo-2.0.6.2.zip 
+cd libjpeg-turbo-2.0.6.2
+mkdir build
+cd build
+cmake -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_BUILD_TYPE=RELEASE -DENABLE_STATIC=FALSE -DCMAKE_INSTALL_DEFAULT_LIBDIR=lib .. 
+make -j$(nproc) install 
+rm -rf /tmp/libjpeg-turbo
+
+# Get released ninja from source
+mkdir -p /tmp/ninja 
+cd /tmp/ninja 
+wget -nv https://codeload.github.com/Kitware/ninja/zip/refs/tags/v1.11.1.g95dee.kitware.jobserver-1 -O ninja.zip
+unzip ninja.zip
+cd ninja-1.11.1.g95dee.kitware.jobserver-1
+./configure.py --bootstrap 
+cp ninja /usr/local/bin/ 
+rm -rf /tmp/ninja
+
+# Install  FFmpeg and dependencies
+# Build NASM
+mkdir -p /tmp/nasm-2.15.05 
+cd /tmp
+wget -qO- "https://distfiles.macports.org/nasm/nasm-2.15.05.tar.bz2" | tar -xvj 
+cd nasm-2.15.05
+./autogen.sh
+./configure --prefix="/usr/local"
+make -j$(nproc) install
+rm -rf /tmp/nasm-2.15.05
+
+# Build YASM
+mkdir -p /tmp/yasm-1.3.0 
+cd /tmp
+wget -qO- "http://www.tortall.net/projects/yasm/releases/yasm-1.3.0.tar.gz" | tar -xvz 
+cd yasm-1.3.0
+./configure --prefix="/usr/local"
+make -j$(nproc) install
+rm -rf /tmp/yasm-1.3.0
+
+# Build x264
+mkdir -p /tmp/x264-snapshot-20191217-2245-stable
+cd /tmp
+wget -qO-  "https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-20191217-2245-stable.tar.bz2" | tar -xvj
+cd /tmp/x264-snapshot-20191217-2245-stable
+PKG_CONFIG_PATH="/usr/local/lib/pkgconfig" ./configure --prefix="/usr/local" --enable-shared
+make -j$(nproc) install
+rm -rf /tmp/x264-snapshot-20191217-2245-stable
+
+# Build x265
+mkdir -p /tmp/x265_2.7
+cd /tmp
+wget -qO- "https://get.videolan.org/x265/x265_2.7.tar.gz" | tar -xvz
+cd  /tmp/x265_2.7/build/linux
+cmake -G "Unix Makefiles" -DCMAKE_INSTALL_PREFIX="/usr/local" -DENABLE_SHARED:bool=on ../../source
+make -j$(nproc) install
+rm -rf /tmp/x265_2.7
+
+
+# Build fdk-aac
+mkdir -p /tmp/fdk-aac-2.0.2
+cd /tmp
+wget -qO- "https://sourceforge.net/projects/opencore-amr/files/fdk-aac/fdk-aac-2.0.2.tar.gz" | tar -xvz
+cd /tmp/fdk-aac-2.0.2
+autoreconf -fiv
+./configure --prefix="/usr/local" --enable-shared --disable-static
+make -j$(nproc) install
+rm -rf /tmp/fdk-aac-2.0.2
+
+# Build FFmpeg
+cd /tmp
+rm -rf ffmpeg
+git clone -b release/4.4 https://git.ffmpeg.org/ffmpeg.git ffmpeg
+cd ffmpeg
+PKG_CONFIG_PATH="/usr/local/lib/pkgconfig"
+./configure  --prefix="/usr/local" --extra-cflags="-I/usr/local/include"   --extra-ldflags="-L/usr/local/lib"  --extra-libs=-lpthread  --extra-libs=-lm  --enable-shared   --disable-static   --enable-libx264  --enable-libx265  --enable-libfdk-aac  --enable-gpl --enable-nonfree
+make -j$(nproc) install
+rm -rf /tmp/ffmpeg
+
+cp /tmp/local-pin-600 /etc/apt/preferences.d
+
+command -v lbzip2 
+ln -sf $(command -v lbzip2) /usr/local/bin/compressor || ln -sf $(command -v bzip2) /usr/local/bin/compressor
+
+# Install Google Benchmark (ROCMOPS-5283)
+mkdir -p /tmp/Gbenchmark 
+cd /tmp/Gbenchmark 
+wget -qO- https://github.com/google/benchmark/archive/refs/tags/v1.6.1.tar.gz | tar xz 
+cmake -Sbenchmark-1.6.1 -Bbuild -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=OFF -DBENCHMARK_ENABLE_TESTING=OFF -DCMAKE_CXX_STANDARD=14 
+make -j -C build 
+cd /tmp/Gbenchmark/build
+make install

tools/rocm-build/docker/ubuntu24/local-pin-60

@@ -0,0 +1,3 @@
+Package: *
+Pin: origin ""
+Pin-Priority: 600

tools/rocm-build/docker/ubuntu24/packages

@@ -0,0 +1,140 @@
+# List of packages needed for stage1 build
+apt-utils
+aria2
+autoconf
+automake
+bc
+bison
+bridge-utils
+build-essential
+bzip2
+ccache
+check
+chrpath
+cifs-utils
+cmake
+cpio
+curl
+devscripts
+dos2unix
+doxygen
+fakeroot
+flex
+freeglut3-dev
+g++
+g++-multilib
+# gawk is needed for aomp
+gawk
+gcc
+gcc-multilib
+gfortran
+git-lfs
+gnupg
+googletest
+graphviz
+kernel-wedge
+# kmod for kernel build
+kmod
+lbzip2
+# less is needed by repo
+less
+libass-dev
+libatlas-base-dev
+libbabeltrace-dev
+libboost-all-dev
+libboost-dev
+libboost-filesystem-dev
+libboost-program-options-dev
+libboost-system-dev
+libbz2-dev
+libc++-dev
+libc++1
+libc++abi-dev
+libc++abi1
+libc6-dev-i386
+libcap-dev
+libcurl4-openssl-dev
+libdrm-dev
+libdw-dev
+libdw1
+libdwarf-dev
+libelf-dev
+libelf1
+libexpat1-dev
+libfftw3-dev
+libfile-find-rule-perl
+libgflags-dev
+libglew-dev
+libgmp-dev
+libgoogle-glog-dev
+libgtk2.0-dev
+libhdf5-dev
+libjpeg-dev
+libleveldb-dev
+liblmdb-dev
+liblzma-dev
+libmpfr-dev
+libmpich-dev
+libmsgpack-dev
+libncurses-dev
+libnuma-dev
+libomp-dev
+libopenblas-dev
+libpci-dev
+libpci3
+libpciaccess-dev
+libpciaccess0
+libprotobuf-dev
+libpython3-dev
+libreadline-dev
+libsnappy-dev
+libssl-dev
+libsuitesparse-dev
+libsystemd-dev
+libtool
+liburi-encode-perl
+libva-dev
+libvirt-clients
+libvirt-daemon-system
+libyaml-cpp-dev
+llvm
+llvm-dev
+llvm-runtime
+mesa-common-dev
+mpich
+ocaml
+ocaml-findlib
+patchelf
+pigz
+pkg-config
+protobuf-compiler
+python-is-python3
+python3-barectf
+python3-dev
+python3-pip
+python3-pip-whl
+python3-requests
+python3-venv
+python3-yaml
+python3-yaml
+re2c
+redis-tools
+# hipclang needs rpm
+rpm
+rsync
+ssh
+# This makes life more pleasent inside the container
+strace
+sudo
+systemtap-sdt-dev
+texinfo
+texlive
+texlive-extra-utils
+texlive-plain-generic
+texlive-xetex
+unzip
+vim
+wget
+xsltproc
+xxd
+zlib1g-dev

tools/rocm-build/envsetup.sh

@@ -123,9 +123,12 @@ if [ -d "$HSA_OPENSOURCE_ROOT/ROCT-Thunk-Interface" ]; then
 	export THUNK_ROOT=$HSA_OPENSOURCE_ROOT/ROCT-Thunk-Interface
 fi
 export AQLPROFILE_ROOT=$WORK_ROOT/hsa/aqlprofile
+export OMNIPERF_ROOT=$WORK_ROOT/omniperf
 export ROCPROFILER_ROOT=$WORK_ROOT/rocprofiler
 export ROCTRACER_ROOT=$WORK_ROOT/roctracer
 export ROCPROFILER_REGISTER_ROOT=$WORK_ROOT/rocprofiler-register
+export ROCPROFILER_SDK_ROOT=$WORK_ROOT/rocprofiler-sdk
+export OMNITRACE_ROOT=$WORK_ROOT/omnitrace
 export RDC_ROOT=$WORK_ROOT/rdc
 export RDCTST_ROOT=$RDC_ROOT/tests/rdc_tests
 export UTILS_ROOT=$WORK_ROOT/rocm-utils
@@ -147,7 +150,6 @@ export ROCM_CORE_ROOT=$WORK_ROOT/rocm-core
 export ROCM_CMAKE_ROOT=$WORK_ROOT/rocm-cmake
 export ROCM_BANDWIDTH_TEST_ROOT=$WORK_ROOT/rocm_bandwidth_test
 export ROCMINFO_ROOT=$WORK_ROOT/rocminfo
-export CLANG_OCL_ROOT=$WORK_ROOT/clang-ocl
 export ROCR_DEBUG_AGENT_ROOT=$WORK_ROOT/rocr_debug_agent
 export COMGR_ROOT=$LLVM_PROJECT_ROOT/amd/comgr
 export COMGR_LIB_PATH=$OUT_DIR/build/amd_comgr
@@ -179,7 +181,7 @@ export BUILD_ARTIFACTS=$OUT_DIR/$PACKAGEEXT
 export HIPCC_COMPILE_FLAGS_APPEND="-O3 -Wno-format-nonliteral -parallel-jobs=4"
 export HIPCC_LINK_FLAGS_APPEND="-O3 -parallel-jobs=4"
 
-export PATH="${ROCM_PATH}/lib/llvm/bin:${PATH}"
+export PATH="${ROCM_PATH}/bin:${ROCM_PATH}/lib/llvm/bin:${PATH}"
 
 export LC_ALL=C.UTF-8
 export LANG=C.UTF-8

tools/rocm-build/rocm-6.1.1.xml

@@ -1,71 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<manifest>
-    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.1.1"
-     remote="rocm-org"
-     sync-c="true"
-     sync-j="4" />
-<!--list of projects for ROCm-->
-    <project name="ROCm" revision="roc-6.1.x" />
-    <project name="ROCK-Kernel-Driver" />
-    <project name="ROCT-Thunk-Interface" />
-    <project name="ROCR-Runtime" />
-    <project name="amdsmi" />
-    <project name="rocm_smi_lib" />
-    <project name="rocm-core" />
-    <project name="rocm-cmake" />
-    <project name="rocminfo" />
-    <project name="rocm_bandwidth_test" />
-    <project name="rocprofiler" />
-    <project name="rocprofiler-register" />
-    <project name="roctracer" />
-    <project name="clang-ocl" />
-    <project name="rdc" />
-<!--HIP Projects-->
-    <project name="HIP" />
-    <project name="hip-tests" />
-    <project name="HIP-Examples" />
-    <project name="clr" />
-    <project name="hipother" />
-    <project name="HIPIFY" />
-<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
-    <project name="llvm-project" />
-    <project name="half" />
-<!-- gdb projects -->
-    <project name="ROCgdb" />
-    <project name="ROCdbgapi" />
-    <project name="rocr_debug_agent" />
-<!-- ROCm Libraries -->
-    <project groups="mathlibs" name="rocBLAS" />
-    <project groups="mathlibs" name="Tensile" />
-    <project groups="mathlibs" name="hipTensor" />
-    <project groups="mathlibs" name="hipBLAS" />
-    <project groups="mathlibs" name="hipBLASLt" />
-    <project groups="mathlibs" name="rocFFT" />
-    <project groups="mathlibs" name="hipFFT" />
-    <project groups="mathlibs" name="rocRAND" />
-    <project groups="mathlibs" name="hipRAND" />
-    <project groups="mathlibs" name="rocSPARSE" />
-    <project groups="mathlibs" name="hipSPARSELt" />
-    <project groups="mathlibs" name="rocSOLVER" />
-    <project groups="mathlibs" name="hipSOLVER" />
-    <project groups="mathlibs" name="hipSPARSE" />
-    <project groups="mathlibs" name="rocALUTION" />
-    <project groups="mathlibs" name="rocThrust" />
-    <project groups="mathlibs" name="hipCUB" />
-    <project groups="mathlibs" name="rocPRIM" />
-    <project groups="mathlibs" name="rocWMMA" />
-    <project groups="mathlibs" name="rccl" />
-    <project groups="mathlibs" name="MIOpen" />
-    <project groups="mathlibs" name="MIVisionX" />
-    <project groups="mathlibs" name="ROCmValidationSuite" />
-    <project groups="mathlibs" name="composable_kernel" />
-    <project groups="mathlibs" name="hipfort" />
-    <project groups="mathlibs" name="rocDecode" />
-    <project groups="mathlibs" name="AMDMIGraphX" />
-    <project groups="mathlibs" name="rpp" />
-<!-- Projects for OpenMP-Extras -->
-    <project name="aomp" path="openmp-extras/aomp" />
-    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
-    <project name="flang" path="openmp-extras/flang" />
-</manifest>

tools/rocm-build/rocm-6.1.2.xml

@@ -1,71 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<manifest>
-    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.1.2"
-     remote="rocm-org"
-     sync-c="true"
-     sync-j="4" />
-<!--list of projects for ROCm-->
-    <project name="ROCm" revision="roc-6.1.x" />
-    <project name="ROCK-Kernel-Driver" />
-    <project name="ROCT-Thunk-Interface" />
-    <project name="ROCR-Runtime" />
-    <project name="amdsmi" />
-    <project name="rocm_smi_lib" />
-    <project name="rocm-core" />
-    <project name="rocm-cmake" />
-    <project name="rocminfo" />
-    <project name="rocm_bandwidth_test" />
-    <project name="rocprofiler" />
-    <project name="rocprofiler-register" />
-    <project name="roctracer" />
-    <project name="clang-ocl" />
-    <project name="rdc" />
-<!--HIP Projects-->
-    <project name="HIP" />
-    <project name="hip-tests" />
-    <project name="HIP-Examples" />
-    <project name="clr" />
-    <project name="hipother" />
-    <project name="HIPIFY" />
-<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
-    <project name="llvm-project" />
-    <project name="half" />
-<!-- gdb projects -->
-    <project name="ROCgdb" />
-    <project name="ROCdbgapi" />
-    <project name="rocr_debug_agent" />
-<!-- ROCm Libraries -->
-    <project groups="mathlibs" name="rocBLAS" />
-    <project groups="mathlibs" name="Tensile" />
-    <project groups="mathlibs" name="hipTensor" />
-    <project groups="mathlibs" name="hipBLAS" />
-    <project groups="mathlibs" name="hipBLASLt" />
-    <project groups="mathlibs" name="rocFFT" />
-    <project groups="mathlibs" name="hipFFT" />
-    <project groups="mathlibs" name="rocRAND" />
-    <project groups="mathlibs" name="hipRAND" />
-    <project groups="mathlibs" name="rocSPARSE" />
-    <project groups="mathlibs" name="hipSPARSELt" />
-    <project groups="mathlibs" name="rocSOLVER" />
-    <project groups="mathlibs" name="hipSOLVER" />
-    <project groups="mathlibs" name="hipSPARSE" />
-    <project groups="mathlibs" name="rocALUTION" />
-    <project groups="mathlibs" name="rocThrust" />
-    <project groups="mathlibs" name="hipCUB" />
-    <project groups="mathlibs" name="rocPRIM" />
-    <project groups="mathlibs" name="rocWMMA" />
-    <project groups="mathlibs" name="rccl" />
-    <project groups="mathlibs" name="MIOpen" />
-    <project groups="mathlibs" name="MIVisionX" />
-    <project groups="mathlibs" name="ROCmValidationSuite" />
-    <project groups="mathlibs" name="composable_kernel" />
-    <project groups="mathlibs" name="hipfort" />
-    <project groups="mathlibs" name="rocDecode" />
-    <project groups="mathlibs" name="AMDMIGraphX" />
-    <project groups="mathlibs" name="rpp" />
-<!-- Projects for OpenMP-Extras -->
-    <project name="aomp" path="openmp-extras/aomp" />
-    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
-    <project name="flang" path="openmp-extras/flang" />
-</manifest>

tools/rocm-build/rocm-6.2.0.xml

@@ -6,30 +6,29 @@
      sync-c="true"
      sync-j="4" />
 <!--list of projects for ROCm-->
+    <project name="ROCm" revision="roc-6.2.x" />
+    <project name="ROCK-Kernel-Driver" />
+    <project name="ROCR-Runtime" />
+    <project name="ROCT-Thunk-Interface" />
     <project name="amdsmi" />
     <project name="omniperf" />
     <project name="omnitrace" />
     <project name="rdc" />
-    <project name="roc-core" />
     <project name="rocm_bandwidth_test" />
     <project name="rocm_smi_lib" />
+    <project name="rocm-core" />
     <project name="rocminfo" />
-    <project name="rocm-examples" />
-    <project name="rocm-prof" />
-    <project name="rocm-prof-register" />
-    <project name="rocm-prof-sdk" />
-    <project name="rocm-tracer" />
-    <project name="ROCK-Kernel-Driver" />
-    <project name="ROCR-Runtime" />
-    <project name="ROCT-Thunk-Interface" />
-    <project name="ROCm" revision="roc-6.2.x" />
+    <project name="rocprofiler" />
+    <project name="rocprofiler-register" />
+    <project name="rocprofiler-sdk" />
+    <project name="roctracer" />
 <!--HIP Projects-->
-    <project name="clr" />
-    <project name="HIPIFY" />
     <project name="HIP" />
-    <project name="hip-other" />
     <project name="hip-tests" />
     <project name="HIP-Examples" />
+    <project name="HIPIFY" />
+    <project name="clr" />
+    <project name="hipother" />
 <!-- The following projects are all associated with the AMDGPU LLVM compiler -->
     <project name="half" />
     <project name="llvm-project" />
@@ -72,5 +71,4 @@
     <project name="aomp" path="openmp-extras/aomp" />
     <project name="aomp-extras" path="openmp-extras/aomp-extras" />
     <project name="flang" path="openmp-extras/flang" />
-</manifest>
-
+</manifest>

tools/rocm-build/rocm-6.2.1.xml

@@ -1,71 +1,74 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.1.0"
+    <default revision="refs/tags/rocm-6.2.1"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />
 <!--list of projects for ROCm-->
-    <project name="ROCm" revision="roc-6.1.x" />
+    <project name="ROCm" revision="roc-6.2.x" />
     <project name="ROCK-Kernel-Driver" />
-    <project name="ROCT-Thunk-Interface" />
     <project name="ROCR-Runtime" />
+    <project name="ROCT-Thunk-Interface" />
     <project name="amdsmi" />
+    <project name="omniperf" />
+    <project name="omnitrace" />
+    <project name="rdc" />
+    <project name="rocm_bandwidth_test" />
     <project name="rocm_smi_lib" />
     <project name="rocm-core" />
-    <project name="rocm-cmake" />
     <project name="rocminfo" />
-    <project name="rocm_bandwidth_test" />
     <project name="rocprofiler" />
     <project name="rocprofiler-register" />
+    <project name="rocprofiler-sdk" />
     <project name="roctracer" />
-    <project name="clang-ocl" />
-    <project name="rdc" />
 <!--HIP Projects-->
     <project name="HIP" />
     <project name="hip-tests" />
     <project name="HIP-Examples" />
+    <project name="HIPIFY" />
     <project name="clr" />
     <project name="hipother" />
-    <project name="HIPIFY" />
 <!-- The following projects are all associated with the AMDGPU LLVM compiler -->
-    <project name="llvm-project" />
     <project name="half" />
+    <project name="llvm-project" />
 <!-- gdb projects -->
-    <project name="ROCgdb" />
     <project name="ROCdbgapi" />
+    <project name="ROCgdb" />
     <project name="rocr_debug_agent" />
 <!-- ROCm Libraries -->
-    <project groups="mathlibs" name="rocBLAS" />
-    <project groups="mathlibs" name="Tensile" />
-    <project groups="mathlibs" name="hipTensor" />
-    <project groups="mathlibs" name="hipBLAS" />
-    <project groups="mathlibs" name="hipBLASLt" />
-    <project groups="mathlibs" name="rocFFT" />
-    <project groups="mathlibs" name="hipFFT" />
-    <project groups="mathlibs" name="rocRAND" />
-    <project groups="mathlibs" name="hipRAND" />
-    <project groups="mathlibs" name="rocSPARSE" />
-    <project groups="mathlibs" name="hipSPARSELt" />
-    <project groups="mathlibs" name="rocSOLVER" />
-    <project groups="mathlibs" name="hipSOLVER" />
-    <project groups="mathlibs" name="hipSPARSE" />
-    <project groups="mathlibs" name="rocALUTION" />
-    <project groups="mathlibs" name="rocThrust" />
-    <project groups="mathlibs" name="hipCUB" />
-    <project groups="mathlibs" name="rocPRIM" />
-    <project groups="mathlibs" name="rocWMMA" />
-    <project groups="mathlibs" name="rccl" />
+    <project groups="mathlibs" name="AMDMIGraphX" />
     <project groups="mathlibs" name="MIOpen" />
     <project groups="mathlibs" name="MIVisionX" />
     <project groups="mathlibs" name="ROCmValidationSuite" />
+    <project groups="mathlibs" name="Tensile" />
     <project groups="mathlibs" name="composable_kernel" />
+    <project groups="mathlibs" name="hipBLAS" />
+    <project groups="mathlibs" name="hipBLASLt" />
+    <project groups="mathlibs" name="hipCUB" />
+    <project groups="mathlibs" name="hipFFT" />
+    <project groups="mathlibs" name="hipRAND" />
+    <project groups="mathlibs" name="hipSOLVER" />
+    <project groups="mathlibs" name="hipSPARSE" />
+    <project groups="mathlibs" name="hipSPARSELt" />
+    <project groups="mathlibs" name="hipTensor" />
     <project groups="mathlibs" name="hipfort" />
+    <project groups="mathlibs" name="rccl" />
+    <project groups="mathlibs" name="rocAL" />
+    <project groups="mathlibs" name="rocALUTION" />
+    <project groups="mathlibs" name="rocBLAS" />
     <project groups="mathlibs" name="rocDecode" />
-    <project groups="mathlibs" name="AMDMIGraphX" />
+    <project groups="mathlibs" name="rocFFT" />
+    <project groups="mathlibs" name="rocPRIM" />
+    <project groups="mathlibs" name="rocRAND" />
+    <project groups="mathlibs" name="rocSOLVER" />
+    <project groups="mathlibs" name="rocSPARSE" />
+    <project groups="mathlibs" name="rocThrust" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
     <project groups="mathlibs" name="rpp" />
 <!-- Projects for OpenMP-Extras -->
     <project name="aomp" path="openmp-extras/aomp" />
     <project name="aomp-extras" path="openmp-extras/aomp-extras" />
     <project name="flang" path="openmp-extras/flang" />
-</manifest>
+</manifest>