Merge pull request #3259 from ROCm/develop

Merge develop into roc-6.1.x

.azuredevops/ci-builds/aomp.yml

@@ -17,11 +17,7 @@ resources:
   pipelines:
   - pipeline: rocr-runtime_pipeline
     source: \ROCR-Runtime
-    trigger:
-      branches:
-        include:
-        - master
-
+    trigger: true
 # this job will only be triggered after successful build sequence of llvm-project and ROCR-Runtime
 
 trigger: none

.azuredevops/components/rccl.yml

@@ -61,6 +61,7 @@ jobs:
       parameters:
         dependencyList: ${{ parameters.rocmDependencies }}
         dependencySource: tag-builds
+  - script: chmod +x $(Agent.BuildDirectory)/rocm/bin/hipify-perl
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
       extraBuildFlags: >-

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

@@ -17,7 +17,7 @@ steps:
   displayName: 'sudo apt-get upgrade'
   inputs:
     targetType: inline
-    script: sudo apt-get update
+    script: sudo apt-get upgrade
 - task: Bash@3
   displayName: 'sudo apt-get fix'
   inputs:

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=6.1.0   # or 6.1.1
+export ROCM_VERSION=6.1.0   # or 6.1.1 6.1.2
 ~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.1.x -m rocm-build/rocm-${ROCM_VERSION}.xml
 ~/bin/repo sync
 

docs/compatibility/compatibility-matrix.rst

@@ -36,9 +36,9 @@ Use this matrix to view the ROCm compatibility across successive major and minor
       ,,
       ECOSYSTEM SUPPORT:,,
       :doc:`PyTorch <rocm-install-on-linux:how-to/3rd-party/pytorch-install>`,"2.1, 2.0, 1.13","2.1, 2.0, 1.13"
-      :doc:`Tensorflow <rocm-install-on-linux:how-to/3rd-party/tensorflow-install>`,"2.15, 2.14, 2.13","2.14, 2.13, 2.12"
+      :doc:`TensorFlow <rocm-install-on-linux:how-to/3rd-party/tensorflow-install>`,"2.15, 2.14, 2.13","2.14, 2.13, 2.12"
       :doc:`JAX <rocm-install-on-linux:how-to/3rd-party/jax-install>`,0.4.26,0.4.26
-      `ONNX-RT <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.14.1
+      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.14.1
       ,,
       3RD PARTY COMMUNICATION LIBS:,,
       `UCC <https://github.com/ROCm/ucc>`_,>=1.2.0,>=1.2.0
@@ -52,12 +52,12 @@ Use this matrix to view the ROCm compatibility across successive major and minor
       :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0
       :doc:`MIGraphX <amdmigraphx:index>`,2.9.0,2.8.0
       :doc:`MIOpen <miopen:index>`,3.1.0,3.0.0
-      :doc:`MIVisionX <mivisionx:doxygen/html/index>`,2.5.0,2.5.0
+      :doc:`MIVisionX <mivisionx:index>`,2.5.0,2.5.0
       :doc:`rocDecode <rocdecode:index>`,0.5.0,N/A
-      :doc:`RPP <rpp:index>`,1.5.0,1.4.0
+      :doc:`ROCm Performance Primitives (RPP) <rpp:index>`,1.5.0,1.4.0
       ,,
       COMMUNICATION:,,
-      :doc:`rccl <rccl:index>`,2.18.6,2.18.3
+      :doc:`RCCL <rccl:index>`,2.18.6,2.18.3
       ,,
       MATH LIBS:,,
       `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0
@@ -86,7 +86,7 @@ Use this matrix to view the ROCm compatibility across successive major and minor
       ,,
       SUPPORT LIBS:,,
       `hipother <https://github.com/ROCm/hipother>`_,6.1.40091,6.0.32830
-      `rocm-cmake <https://github.com/ROCm/rocm-cmake>`_,0.12.0,0.11.0
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.12.0,0.11.0
       `rocm-core <https://github.com/ROCm/rocm-core>`_,6.1.0,6.0.0
       `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240125.3.30,20231016.2.245
       ,,
@@ -94,15 +94,15 @@ Use this matrix to view the ROCm compatibility across successive major and minor
       :doc:`AMD SMI <amdsmi:index>`,24.4.1,23.4.2
       :doc:`HIPIFY <hipify:index>`,17.0.0,17.0.0
       :doc:`ROCdbgapi <rocdbgapi:index>`,0.71.0,0.71.0
-      `ROCdebug-Agent <https://github.com/ROCm/rocr_debug_agent>`_,2.0.3,2.0.3
-      :doc:`rocGDB <rocgdb:index>`,14.1.0,13.2.0
-      :doc:`rocProfiler <rocprofiler:profiler_home_page>`,2.0.60100,2.0.0
+      `ROCm Debug Agent (ROCdebug-agent) <https://github.com/ROCm/rocr_debug_agent>`_,2.0.3,2.0.3
+      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60100,2.0.0
       `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.3.0,N/A
-      :doc:`rocTracer <roctracer:index>`,4.1.60100,4.1.0
-      `rocm_bandwidth_test <https://github.com/ROCm/rocm_bandwidth_test>`_,1.4.0,1.4.0
+      :doc:`ROCTracer <roctracer:index>`,4.1.60100,4.1.0
+      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0
       :doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0
-      `rocminfo <https://github.com/ROCm/rocminfo>`_,1.0.0,1.0.0
-      :doc:`ROCm SMI Lib <rocm_smi_lib:index>`,7.0.0,6.0.0
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.1.0,13.2.0
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.0.0,6.0.0
       :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.1.0,rocm-6.0.0
       :doc:`TransferBench <transferbench:index>`,1.48,1.46
       ,,
@@ -116,7 +116,7 @@ Use this matrix to view the ROCm compatibility across successive major and minor
       RUNTIMES:,,
       :doc:`HIP <hip:index>`,6.1.40091,6.0.32830
       `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0
-      `ROCR Runtime <https://github.com/ROCm/ROCR-Runtime>`_,1.13.0,1.12.0
+      :doc:`ROCR-Runtime <rocr-runtime:index>`,1.13.0,1.12.0
 
 
 .. rubric:: Footnotes

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

@@ -65,4 +65,4 @@ through the following guides.
 
 * :doc:`rocm-for-ai/index`
 
-* :doc:`fine-tuning-llms/index`
+* :doc:`llm-fine-tuning-optimization/index`

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

@@ -77,7 +77,7 @@ Installing vLLM
 
          The following log message is displayed in your command line indicates that the server is listening for requests.
 
-         .. image:: ../../data/how-to/fine-tuning-llms/vllm-single-gpu-log.png
+         .. image:: ../../data/how-to/llm-fine-tuning-optimization/vllm-single-gpu-log.png
             :alt: vLLM API server log message
             :align: center
 

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

@@ -18,7 +18,7 @@ Attention (GQA), and Multi-Query Attention (MQA). This reduction in memory movem
 time-to-first-token (TTFT) latency for large batch sizes and long prompt sequences, thereby enhancing overall
 performance.
 
-.. image:: ../../data/how-to/fine-tuning-llms/attention-module.png
+.. image:: ../../data/how-to/llm-fine-tuning-optimization/attention-module.png
    :alt: Attention module of a large language module utilizing tiling
    :align: center
 
@@ -243,7 +243,7 @@ page describes the options.
    Validator,ROCBLAS_VERSION,4.1.0-cefa4a9b-dirty
    GemmTunableOp_float_TN,tn_200_100_20,Gemm_Rocblas_32323,0.00669595
 
-.. image:: ../../data/how-to/fine-tuning-llms/tunableop.png
+.. image:: ../../data/how-to/llm-fine-tuning-optimization/tunableop.png
    :alt: GEMM and TunableOp
    :align: center
 

docs/how-to/llm-fine-tuning-optimization/optimizing-triton-kernel.rst

@@ -31,7 +31,7 @@ Each accelerator or GPU has multiple Compute Units (CUs) and various CUs do comp
 can a compute kernel can allocate its task to? For the :doc:`AMD MI300X accelerator <../../reference/gpu-arch-specs>`, the
 grid should have at least 1024 thread blocks or workgroups.
 
-.. figure:: ../../data/how-to/fine-tuning-llms/compute-unit.png
+.. figure:: ../../data/how-to/llm-fine-tuning-optimization/compute-unit.png
 
    Schematic representation of a CU in the CDNA2 or CDNA3 architecture.
 
@@ -187,7 +187,7 @@ Kernel occupancy
 
 .. _fine-tuning-llms-occupancy-vgpr-table:
 
-.. figure:: ../../data/how-to/fine-tuning-llms/occupancy-vgpr.png
+.. figure:: ../../data/how-to/llm-fine-tuning-optimization/occupancy-vgpr.png
    :alt: Occupancy related to VGPR usage in an Instinct MI300X accelerator.
    :align: center
 

docs/how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel.md

@@ -32,7 +32,7 @@ The template parameters of the instance are grouped into four parameter types:
 ================
  ### Figure 2
 ================ -->
-```{figure} ../../data/how-to/fine-tuning-llms/ck-template_parameters.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-template_parameters.jpg
 The template parameters of the selected GEMM kernel are classified into four groups. These template parameter groups should be defined properly before running the instance.
 ```
 
@@ -126,7 +126,7 @@ The row and column, and stride information of input matrices are also passed to
 ================
  ### Figure 3
 ================ -->
-```{figure} ../../data/how-to/fine-tuning-llms/ck-kernel_launch.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-kernel_launch.jpg
 Templated kernel launching consists of kernel instantiation, making arguments by passing in actual application parameters, creating an invoker, and running the instance through the invoker.
 ```
 
@@ -155,7 +155,7 @@ The first operation in the process is to perform the multiplication of input mat
 ================
  ### Figure 4
 ================ -->
-```{figure} ../../data/how-to/fine-tuning-llms/ck-operation_flow.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-operation_flow.jpg
 Operation flow.
 ```
 
@@ -171,7 +171,7 @@ Here, we use [DeviceBatchedGemmMultiD_Xdl](https://github.com/ROCm/composable_ke
 ================
  ### Figure 5
 ================ -->
-```{figure} ../../data/how-to/fine-tuning-llms/ck-root_instance.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-root_instance.jpg
 Use the ‘DeviceBatchedGemmMultiD_Xdl’ instance as a root.
 ```
 
@@ -421,7 +421,7 @@ Run `python setup.py install` to build and install the extension. It should look
 ================
  ### Figure 6
 ================ -->
-```{figure} ../../data/how-to/fine-tuning-llms/ck-compilation.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-compilation.jpg
 Compilation and installation of the INT8 kernels.
 ```
 
@@ -433,7 +433,7 @@ The implementation architecture of running SmoothQuant models on MI300X GPUs is
 ================
  ### Figure 7
 ================ -->
-```{figure} ../../data/how-to/fine-tuning-llms/ck-inference_flow.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-inference_flow.jpg
 The implementation architecture of running SmoothQuant models on AMD MI300X accelerators.
 ```
 
@@ -459,7 +459,7 @@ Figure 8 shows the performance comparisons between the original FP16 and the Smo
 ================
  ### Figure 8
 ================ -->
-```{figure} ../../data/how-to/fine-tuning-llms/ck-comparisons.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-comparisons.jpg
 Performance comparisons between the original FP16 and the SmoothQuant-quantized INT8 models on a single MI300X accelerator.
 ```
 

docs/how-to/llm-fine-tuning-optimization/overview.rst

@@ -41,7 +41,7 @@ The weight update is as follows: :math:`W_{updated} = W + ΔW`.
 If the weight matrix :math:`W` contains 7B parameters, then the weight update matrix :math:`ΔW` should also
 contain 7B parameters. Therefore, the :math:`ΔW` calculation is computationally and memory intensive.
 
-.. figure:: ../../data/how-to/fine-tuning-llms/weight-update.png
+.. figure:: ../../data/how-to/llm-fine-tuning-optimization/weight-update.png
    :alt: Weight update diagram
 
    (a) Weight update in regular fine-tuning. (b) Weight update in LoRA where the product of matrix A (:math:`M\times K`)

docs/how-to/llm-fine-tuning-optimization/profiling-and-debugging.rst

@@ -38,7 +38,7 @@ You can then visualize and view these metrics using an open-source profile visua
    shows transactions denoting the CPU activities that launch GPU kernels while the lower section shows the actual GPU
    activities where it processes the ``resnet18`` inferences layer by layer. 
 
-   .. figure:: ../../data/how-to/fine-tuning-llms/perfetto-trace.svg
+   .. figure:: ../../data/how-to/llm-fine-tuning-optimization/perfetto-trace.svg
       
       Perfetto trace visualization example.
 
@@ -100,7 +100,7 @@ analyze bottlenecks and stressors for their computational workloads on AMD Insti
    Omniperf collects hardware counters in multiple passes, and will therefore re-run the application during each pass
    to collect different sets of metrics.
 
-.. figure:: ../../data/how-to/fine-tuning-llms/omniperf-analysis.png
+.. figure:: ../../data/how-to/llm-fine-tuning-optimization/omniperf-analysis.png
 
    Omniperf memory chat analysis panel.
 
@@ -130,7 +130,7 @@ hardware counters are also included.
    have the greatest impact on the end-to-end execution of the application and to discover what else is happening on the
    system during a performance bottleneck.
 
-.. figure:: ../../data/how-to/fine-tuning-llms/omnitrace-timeline.png
+.. figure:: ../../data/how-to/llm-fine-tuning-optimization/omnitrace-timeline.png
 
    Omnitrace timeline trace example.
 

docs/how-to/rocm-for-ai/train-a-model.rst

@@ -110,7 +110,7 @@ Fine-tuning your model
 ROCm supports multiple techniques for :ref:`optimizing fine-tuning <fine-tuning-llms-concept-optimizations>`, for
 example, LoRA, QLoRA, PEFT, and FSDP.
 
-Learn more about challenges and solutions for model fine-tuning in :doc:`../fine-tuning-llms/index`.
+Learn more about challenges and solutions for model fine-tuning in :doc:`../llm-fine-tuning-optimization/index`.
 
 The following developer blogs showcase examples of how to fine-tune a model on an AMD accelerator or GPU.
 

docs/index.md

@@ -34,16 +34,16 @@ Our documentation is organized into the following categories:
   * {doc}`Quick start guide<rocm-install-on-linux:tutorial/quick-start>`
   * {doc}`Linux install guide<rocm-install-on-linux:how-to/native-install/index>`
   * {doc}`Package manager integration<rocm-install-on-linux:how-to/native-install/package-manager-integration>`
+  * {doc}`Install Docker containers<rocm-install-on-linux:how-to/docker>`
+  * {doc}`ROCm & Spack<rocm-install-on-linux:how-to/spack>`
 * Windows
   * {doc}`Windows install guide<rocm-install-on-windows:how-to/install>`
   * {doc}`Application deployment guidelines<rocm-install-on-windows:conceptual/deployment-guidelines>`
 * [Deep learning frameworks](./how-to/deep-learning-rocm.rst)
-  * {doc}`Install Docker containers<rocm-install-on-linux:how-to/docker>`
   * {doc}`PyTorch for ROCm<rocm-install-on-linux:how-to/3rd-party/pytorch-install>`
   * {doc}`TensorFlow for ROCm<rocm-install-on-linux:how-to/3rd-party/tensorflow-install>`
   * {doc}`JAX for ROCm<rocm-install-on-linux:how-to/3rd-party/jax-install>`
   * {doc}`MAGMA for ROCm<rocm-install-on-linux:how-to/3rd-party/magma-install>`
-  * {doc}`ROCm & Spack<rocm-install-on-linux:how-to/spack>`
 :::
 
 :::{grid-item-card}
@@ -92,7 +92,7 @@ Our documentation is organized into the following categories:
 :padding: 2
 
 * [Using ROCm for AI](./how-to/rocm-for-ai/index.rst)
-* [Fine-tuning LLMs and inference optimization](./how-to/fine-tuning-llms/index.rst)
+* [Fine-tuning LLMs and inference optimization](./how-to/llm-fine-tuning-optimization/index.rst)
 * [System tuning for various architectures](./how-to/tuning-guides.md)
   * [MI100](./how-to/tuning-guides/mi100.md)
   * [MI200](./how-to/tuning-guides/mi200.md)

docs/reference/api-libraries.md

@@ -22,7 +22,7 @@
 * {doc}`Composable Kernel <composable_kernel:index>`
 * {doc}`MIGraphX <amdmigraphx:index>`
 * {doc}`MIOpen <miopen:index>`
-* {doc}`MIVisionX <mivisionx:doxygen/html/index>`
+* {doc}`MIVisionX <mivisionx:index>`
 * {doc}`rocAL <rocal:index>`
 * {doc}`rocDecode <rocdecode:index>`
 * {doc}`ROCm Performance Primitives (RPP) <rpp:index>`

docs/release/versions.md

@@ -8,6 +8,7 @@
 
 | Version | Release date |
 | ------- | ------------ |
+| [6.1.2](https://rocm.docs.amd.com/en/docs-6.1.2/) | June 4, 2024 |
 | [6.1.1](https://rocm.docs.amd.com/en/docs-6.1.1/) | May 8, 2024 |
 | [6.1.0](https://rocm.docs.amd.com/en/docs-6.1.0/) | Apr 16, 2024 |
 | [6.0.2](https://rocm.docs.amd.com/en/docs-6.0.2/) | Jan 31, 2024 |

docs/sphinx/_toc.yml.in

@@ -58,27 +58,27 @@ subtrees:
       - file: how-to/rocm-for-ai/train-a-model.rst
       - file: how-to/rocm-for-ai/hugging-face-models.rst
       - file: how-to/rocm-for-ai/deploy-your-model.rst
-  - file: how-to/fine-tuning-llms/index.rst
+  - file: how-to/llm-fine-tuning-optimization/index.rst
     title: Fine-tuning LLMs and inference optimization
     subtrees:
     - entries:
-      - file: how-to/fine-tuning-llms/overview.rst
+      - file: how-to/llm-fine-tuning-optimization/overview.rst
         title: Conceptual overview
-      - file: how-to/fine-tuning-llms/fine-tuning-and-inference.rst
+      - file: how-to/llm-fine-tuning-optimization/fine-tuning-and-inference.rst
         subtrees:
         - entries:
-          - file: how-to/fine-tuning-llms/single-gpu-fine-tuning-and-inference.rst
+          - file: how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference.rst
             title: Using a single accelerator
-          - file: how-to/fine-tuning-llms/multi-gpu-fine-tuning-and-inference.rst
+          - file: how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference.rst
             title: Using multiple accelerators
-      - file: how-to/fine-tuning-llms/model-quantization.rst
-      - file: how-to/fine-tuning-llms/model-acceleration-libraries.rst
-      - file: how-to/fine-tuning-llms/llm-inference-frameworks.rst
-      - file: how-to/fine-tuning-llms/optimizing-with-composable-kernel.md
+      - file: how-to/llm-fine-tuning-optimization/model-quantization.rst
+      - file: how-to/llm-fine-tuning-optimization/model-acceleration-libraries.rst
+      - file: how-to/llm-fine-tuning-optimization/llm-inference-frameworks.rst
+      - file: how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel.md
         title: Optimizing with Composable Kernel
-      - file: how-to/fine-tuning-llms/optimizing-triton-kernel.rst
+      - file: how-to/llm-fine-tuning-optimization/optimizing-triton-kernel.rst
         title: Optimizing Triton kernels
-      - file: how-to/fine-tuning-llms/profiling-and-debugging.rst
+      - file: how-to/llm-fine-tuning-optimization/profiling-and-debugging.rst
   - file: how-to/tuning-guides.md
     title: System optimization
     subtrees:

docs/sphinx/requirements.in

@@ -1,2 +1,2 @@
-rocm-docs-core==1.2.0
-sphinx-reredirects
+rocm-docs-core==1.4.0
+sphinx-reredirects

docs/sphinx/requirements.txt

@@ -92,7 +92,7 @@ requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.2.0
+rocm-docs-core==1.4.0
     # via -r requirements.in
 smmap==5.0.1
     # via gitdb

docs/sphinx/static/css/rocm_custom.css

@@ -1,53 +1,6 @@
 
 /* Adds container for big tables, used for Compatibility Matrix */
 
-
-/* Header row to have opaque background colour when sticky */
-.format-big-table th {
-    background-color: var(--pst-color-background);
+.format-big-table {
     white-space: nowrap;
   }
-  
-  /* Turn on borders for whole table */
-  .format-big-table th,
-  .format-big-table td {
-    border-width: 1px;
-  }
-  
-  /* .format-big-table th.head { */
-  /*   background-color: var(--pst-color-on-surface); */
-  /* } */
-  
-  /* Sticky header for table excluding the stub*/
-  .format-big-table th.head:not(.stub) {
-    position: sticky;
-    top: 3rem;
-    z-index: 1;
-  }
-
-  /* Sticky header for the head & stub: top left cell */
-  .format-big-table th.head.stub {
-    position: sticky;
-    top: 3rem;
-    z-index: 1;
-    background-color: var(--pst-color-background);
-    white-space: nowrap;
-  }
-  
-  /* Sticky for the stub column */
-  /*.format-big-table tbody th:not(:empty) {
-    position: sticky;
-    top: 3rem;
-    z-index: 2;
-  }*/
-  
-  /* Removes borders for stub column */
-  .format-big-table tbody th {
-    border-top: none;
-    border-bottom: none;
-  }
-  
-  /* For horizontal scrolling only.  Can't be combined with format-big-table container */
-  .horizontal-scrolling-container {
-    overflow-x: scroll;
-  }

docs/what-is-rocm.rst

@@ -43,7 +43,7 @@ Machine Learning & Computer Vision
   ":doc:`Composable Kernel <composable_kernel:index>`", "Provides a programming model for writing performance critical kernels for machine learning workloads across multiple architectures"
   ":doc:`MIGraphX <amdmigraphx:index>`", "Graph inference engine that accelerates machine learning model inference"
   ":doc:`MIOpen <miopen:index>`", "An open source deep-learning library"
-  ":doc:`MIVisionX <mivisionx:doxygen/html/index>`", "Set of comprehensive computer vision and machine learning libraries, utilities, and applications"
+  ":doc:`MIVisionX <mivisionx:index>`", "Set of comprehensive computer vision and machine learning libraries, utilities, and applications"
   ":doc:`rocAL <rocal:index>`", "An augmentation library designed to decode and process images and videos"
   ":doc:`rocDecode <rocdecode:index>`", "High-performance SDK for access to video decoding features on AMD GPUs"
   ":doc:`ROCm Performance Primitives (RPP) <rpp:index>`", "Comprehensive high-performance computer vision library for AMD processors with HIP/OpenCL/CPU back-ends"
@@ -99,18 +99,18 @@ Tools
 
   ":doc:`AMD SMI <amdsmi:index>`", "C library for Linux that provides a user space interface for applications to monitor and control AMD devices"
   ":doc:`HIPIFY <hipify:index>`", "Translates CUDA source code into portable HIP C++"
-  ":doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`", "Captures the performance characteristics of buffer copying and kernel read/write operations"
+  ":doc:`ROCdbgapi <rocdbgapi:index>`", "ROCm debugger API library"
   ":doc:`ROCmCC <./reference/rocmcc>`", "Clang/LLVM-based compiler"
+  ":doc:`rocminfo <rocminfo:index>`", "Reports system information"
+  ":doc:`ROCProfiler <rocprofiler:index>`", "Profiling tool for HIP applications"
+  ":doc:`ROCTracer <roctracer:index>`", "Intercepts runtime API calls and traces asynchronous activity"
+  ":doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`", "Captures the performance characteristics of buffer copying and kernel read/write operations"
   ":doc:`ROCm CMake <rocmcmakebuildtools:index>`", "Collection of CMake modules for common build and development tasks"
   ":doc:`ROCm Data Center Tool <rdc:index>`", "Simplifies administration and addresses key infrastructure challenges in AMD GPUs in cluster and data-center environments"
   "`ROCm Debug Agent (ROCdebug-agent) <https://github.com/ROCm/rocr_debug_agent/>`_ ", "Prints the state of all AMD GPU wavefronts that caused a queue error by sending a SIGQUIT signal to the process while the program is running"
   ":doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`", "Source-level debugger for Linux, based on the GNU Debugger (GDB)"
-  ":doc:`ROCdbgapi <rocdbgapi:index>`", "ROCm debugger API library"
-  ":doc:`rocminfo <rocminfo:index>`", "Reports system information"
   ":doc:`ROCm SMI <rocm_smi_lib:index>`", "C library for Linux that provides a user space interface for applications to monitor and control GPU applications"
   ":doc:`ROCm Validation Suite <rocmvalidationsuite:index>`", "Detects and troubleshoots common problems affecting AMD GPUs running in a high-performance computing environment"
-  ":doc:`ROCProfiler <rocprofiler:profiler_home_page>`", "Profiling tool for HIP applications"
-  ":doc:`ROCTracer <roctracer:index>`", "Intercepts runtime API calls and traces asynchronous activity"
   ":doc:`TransferBench <transferbench:index>`", "Utility to benchmark simultaneous transfers between user-specified devices (CPUs/GPUs)"
 
 Compilers

rocm-build/rocm-6.1.2.xml

@@ -0,0 +1,71 @@
+<?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>