Update documentation requirements

* update SLES 15.4 prerequisites

* update wordlist from develop

* fix spelling errors

* more spelling fixes

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @saadrahim @Rmalavally @amd-aakash @zhang2amd @jlgreathouse @samjwu @MathiasMagnus

.github/dependabot.yml

@@ -0,0 +1,12 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+
+version: 2
+updates:
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/docs/sphinx" # Location of package manifests
+    open-pull-requests-limit: 10
+    schedule:
+      interval: "daily"

.github/workflows/linting.yml

@@ -0,0 +1,60 @@
+name: Linting
+
+on:
+  push:
+    branches: 
+    - develop
+    - main
+    - 'docs/*'
+    - 'roc**'    
+  pull_request:
+    branches: 
+    - develop
+    - main
+    - 'docs/*'
+    - 'roc**'
+
+concurrency:
+  group: ${{ github.ref }}-${{ github.workflow }}
+  cancel-in-progress: true
+
+jobs:
+  lint-rest:
+    name: "RestructuredText"
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+    - name: Install rst-lint
+      run: pip install restructuredtext-lint
+    - name: Lint ResT files
+      run: rst-lint ${{ join(github.workspace, '/docs') }}
+
+  lint-md:
+    name: "Markdown"
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+    - name: Use markdownlint-cli2
+      uses: DavidAnson/markdownlint-cli2-action@v10.0.1
+      with:
+        globs: '**/*.md'
+
+  spelling:
+    name: "Spelling"
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+    - name: Fetch config
+      shell: sh
+      run: |
+        curl --silent --show-error --fail --location https://raw.github.com/RadeonOpenCompute/rocm-docs-core/develop/.spellcheck.yaml -O
+        curl --silent --show-error --fail --location https://raw.github.com/RadeonOpenCompute/rocm-docs-core/develop/.wordlist.txt >> .wordlist.txt
+    - name: Run spellcheck
+      uses: rojopolis/spellcheck-github-actions@0.30.0
+    - name: On fail
+      if: failure()
+      run: |
+        echo "Please check for spelling mistakes or add them to '.wordlist.txt' in either the root of this project or in rocm-docs-core."

.gitignore

@@ -0,0 +1,18 @@
+.venv
+.vscode
+build
+
+# documentation artifacts
+_build/
+_images/
+_static/
+_templates/
+_toc.yml
+docBin/
+_doxygen/
+_readthedocs/
+
+# avoid duplicating contributing.md due to conf.py
+docs/contributing.md
+docs/release.md
+docs/CHANGELOG.md

.markdownlint-cli2.yaml

@@ -0,0 +1,14 @@
+config:
+  default: true
+  MD013: false
+  MD026:
+    punctuation: '.,;:!'
+  MD029:
+    style: ordered
+  MD033: false
+  MD034: false
+  MD041: false
+ignores:
+  - CHANGELOG.md
+  - "{,docs/}{RELEASE,release}.md"
+  - tools/autotag/templates/**/*.md

.readthedocs.yaml

@@ -0,0 +1,21 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+version: 2
+
+build:
+   os: ubuntu-22.04
+   tools:
+      python: "3.10"
+   apt_packages:
+     - "doxygen"
+     - "graphviz" # For dot graphs in doxygen
+
+python:
+   install:
+   - requirements: docs/sphinx/requirements.txt
+
+sphinx:
+   configuration: docs/conf.py
+
+formats: []

.wordlist.txt

@@ -0,0 +1,686 @@
+AAC
+ABI
+ACE
+ACEs
+AccVGPR
+AccVGPRs
+ALU
+AMD
+AMDGPU
+AMDGPUs
+AMDMIGraphX
+AMI
+AOCC
+AOMP
+APIC
+APIs
+APU
+ASIC
+ASICs
+ASan
+ASm
+ATI
+AddressSanitizer
+AlexNet
+Arb
+BLAS
+BMC
+BitCode
+Blit
+Bluefield
+CCD
+CDNA
+CIFAR
+CLI
+CLion
+CMake
+CMakeLists
+CMakePackage
+CP
+CPC
+CPF
+CPP
+CPU
+CPUs
+CSC
+CSE
+CSV
+CSn
+CTests
+CU
+CUDA
+CUs
+CXX
+Cavium
+CentOS
+ChatGPT
+CoRR
+Codespaces
+Commitizen
+CommonMark
+Concretized
+Conda
+ConnectX
+DGEMM
+DKMS
+DL
+DMA
+DNN
+DNNL
+DPM
+DRI
+DW
+DWORD
+Dask
+DataFrame
+DataLoader
+DataParallel
+DeepSpeed
+Dependabot
+DevCap
+Dockerfile
+Doxygen
+ELMo
+ENDPGM
+EPYC
+ESXi
+FFT
+FFTs
+FFmpeg
+FHS
+FMA
+FP
+Filesystem
+Flang
+Fortran
+Fuyu
+GALB
+GCD
+GCDs
+GCN
+GDB
+GDDR
+GDR
+GDS
+GEMM
+GEMMs
+GFortran
+GiB
+GIM
+GL
+GLXT
+GMI
+GPG
+GPR
+GPT
+GPU
+GPU's
+GPUs
+GRBM
+GenAI
+GenZ
+GitHub
+Gitpod
+HBM
+HCA
+HIPCC
+HIPExtension
+HIPIFY
+HPC
+HPCG
+HPE
+HPL
+HSA
+HWE
+Haswell
+Higgs
+Hyperparameters
+ICV
+IDE
+IDEs
+IMDb
+IOMMU
+IOP
+IOPM
+IOV
+IRQ
+ISA
+ISV
+ISVs
+ImageNet
+InfiniBand
+Inlines
+IntelliSense
+Intersphinx
+Intra
+Ioffe
+JSON
+Jupyter
+KFD
+KiB
+KVM
+Keras
+Khronos
+LAPACK
+LCLK
+LDS
+LLM
+LLMs
+LLVM
+LM
+LSAN
+LTS
+LoRA
+MEM
+MERCHANTABILITY
+MFMA
+MiB
+MIGraphX
+MIOpen
+MIOpenGEMM
+MIVisionX
+MLM
+MMA
+MMIO
+MMIOH
+MNIST
+MPI
+MSVC
+MVAPICH
+MVFFR
+Makefile
+Makefiles
+Matplotlib
+Megatron
+Mellanox
+Mellanox's
+Meta's
+MirroredStrategy
+Multicore
+Multithreaded
+MyEnvironment
+MyST
+NBIO
+NBIOs
+NIC
+NICs
+NLI
+NLP
+NPS
+NSP
+NUMA
+NVCC
+NVIDIA
+NVPTX
+NaN
+Nano
+Navi
+Noncoherently
+NousResearch's
+NumPy
+OAM
+OAMs
+OCP
+OEM
+OFED
+OMP
+OMPI
+OMPT
+OMPX
+ONNX
+OSS
+OSU
+OpenCL
+OpenCV
+OpenFabrics
+OpenGL
+OpenMP
+OpenSSL
+OpenVX
+PCI
+PCIe
+PEFT
+PIL
+PILImage
+PRNG
+PRs
+PaLM
+Pageable
+PeerDirect
+Perfetto
+PipelineParallel
+PnP
+PowerShell
+PyPi
+PyTorch
+Qcycles
+RAII
+RCCL
+RDC
+RDMA
+RDNA
+RHEL
+ROC
+ROCProfiler
+ROCTracer
+ROCclr
+ROCdbgapi
+ROCgdb
+ROCk
+ROCm
+ROCmCC
+ROCmSoftwarePlatform
+ROCmValidationSuite
+ROCr
+RST
+RW
+Radeon
+RelWithDebInfo
+Req
+Rickle
+RoCE
+Ryzen
+SALU
+SBIOS
+SCA
+SDK
+SDMA
+SDRAM
+SENDMSG
+SGPR
+SGPRs
+SHA
+SIGQUIT
+SIMD
+SIMDs
+SKU
+SKUs
+SLES
+SMEM
+SMI
+SMT
+SPI
+SQs
+SRAM
+SRAMECC
+SVD
+SWE
+SerDes
+Shlens
+Skylake
+Softmax
+Spack
+Supermicro
+Szegedy
+TCA
+TCC
+TCI
+TCIU
+TCP
+TCR
+TF
+TFLOPS
+TPU
+TPUs
+TensorBoard
+TensorFlow
+TensorParallel
+ToC
+TorchAudio
+TorchMIGraphX
+TorchScript
+TorchServe
+TorchVision
+TransferBench
+TrapStatus
+UAC
+UC
+UCC
+UCX
+UIF
+USM
+UTCL
+UTIL
+Uncached
+Unhandled
+VALU
+VBIOS
+VGPR
+VGPRs
+VM
+VMEM
+VMWare
+VRAM
+VSIX
+VSkipped
+Vanhoucke
+Vulkan
+WGP
+WGPs
+WX
+WikiText
+Wojna
+Workgroups
+Writebacks
+XCD
+XCDs
+XGBoost
+XGBoost's
+XGMI
+XT
+XTX
+Xeon
+Xilinx
+Xnack
+Xteam
+YAML
+YML
+YModel
+ZeRO
+ZenDNN
+accuracies
+activations
+addr
+alloc
+allocator
+allocators
+amdgpu
+api
+atmi
+atomics
+autogenerated
+avx
+awk
+backend
+backends
+benchmarking
+bfloat
+bilinear
+bitsandbytes
+blit
+boson
+bosons
+buildable
+bursty
+bzip
+cacheable
+cd
+centos
+centric
+changelog
+chiplet
+cmake
+cmd
+coalescable
+codename
+collater
+comgr
+completers
+composable
+concretization
+config
+conformant
+convolutional
+convolves
+cpp
+csn
+cuBLAS
+cuFFT
+cuLIB
+cuRAND
+cuSOLVER
+cuSPARSE
+dataset
+datasets
+dataspace
+datatype
+datatypes
+dbgapi
+de
+deallocation
+denoise
+denoised
+denoises
+denormalize
+deserializers
+detections
+dev
+devicelibs
+devsel
+dimensionality
+disambiguates
+distro
+el
+embeddings
+enablement
+endpgm
+encodings
+env
+epilog
+etcetera
+ethernet
+exascale
+executables
+ffmpeg
+filesystem
+fortran
+galb
+gcc
+gdb
+gfortran
+gfx
+githooks
+github
+gnupg
+grayscale
+gzip
+heterogenous
+hipBLAS
+hipBLASLt
+hipCUB
+hipFFT
+hipLIB
+hipRAND
+hipSOLVER
+hipSPARSE
+hipSPARSELt
+hipTensor
+hipamd
+hipblas
+hipcub
+hipfft
+hipfort
+hipify
+hipsolver
+hipsparse
+hpp
+hsa
+hsakmt
+hyperparameter
+ib_core
+inband
+incrementing
+inferencing
+inflight
+init
+initializer
+inlining
+installable
+interprocedural
+intra
+invariants
+invocating
+ipo
+kdb
+latencies
+libfabric
+libjpeg
+libs
+linearized
+linter
+linux
+llvm
+localscratch
+logits
+lossy
+macOS
+matchers
+microarchitecture
+migraphx
+miopen
+miopengemm
+mivisionx
+mkdir
+mlirmiopen
+mtypes
+mvffr
+namespace
+namespaces
+numref
+ocl
+opencl
+opencv
+openmp
+openssl
+optimizers
+os
+pageable
+parallelization
+parameterization
+passthrough
+perfcounter
+performant
+perl
+pragma
+pre
+prebuilt
+precompiled
+prefetch
+prefetchable
+preprocess
+preprocessed
+preprocessing
+prequantized
+prerequisites
+profiler
+protobuf
+pseudorandom
+py
+quasirandom
+queueing
+rccl
+rdc
+reStructuredText
+reformats
+repos
+representativeness
+req
+resampling
+rescaling
+reusability
+roadmap
+roc
+rocAL
+rocALUTION
+rocBLAS
+rocFFT
+rocLIB
+rocMLIR
+rocPRIM
+rocRAND
+rocSOLVER
+rocSPARSE
+rocThrust
+rocWMMA
+rocalution
+rocblas
+rocclr
+rocfft
+rocm
+rocminfo
+rocprim
+rocprof
+rocprofiler
+rocr
+rocrand
+rocsolver
+rocsparse
+rocthrust
+roctracer
+runtime
+runtimes
+sL
+scalability
+scalable
+sendmsg
+serializers
+shader
+sharding
+sigmoid
+sm
+smi
+softmax
+spack
+src
+stochastically
+strided
+subdirectory
+subexpression
+subfolder
+subfolders
+supercomputing
+tensorfloat
+th
+tokenization
+tokenize
+tokenized
+tokenizer
+tokenizes
+toolchain
+toolchains
+toolset
+toolsets
+torchvision
+tqdm
+tracebacks
+txt
+uarch
+uncached
+uncorrectable
+uninstallation
+unsqueeze
+unstacking
+unswitching
+untrusted
+untuned
+upvote
+USM
+UTCL
+UTIL
+utils
+vL
+variational
+vdi
+vectorizable
+vectorization
+vectorize
+vectorized
+vectorizer
+vectorizes
+vjxb
+walkthrough
+walkthroughs
+wavefront
+wavefronts
+whitespaces
+workgroup
+workgroups
+writeback
+writebacks
+wrreq
+wzo
+xargs
+xz
+yaml
+ysvmadyb
+zypper

CONTRIBUTING.md

@@ -0,0 +1,246 @@
+# Contributing to ROCm Docs
+
+AMD values and encourages the ROCm community to contribute to our code and
+documentation. This repository is focused on ROCm documentation and this
+contribution guide describes the recommend method for creating and modifying our
+documentation.
+
+While interacting with ROCm Documentation, we encourage you to be polite and
+respectful in your contributions, content or otherwise. Authors, maintainers of
+these docs act on good intentions and to the best of their knowledge.
+Keep that in mind while you engage. Should you have issues with contributing
+itself, refer to
+[discussions](https://github.com/RadeonOpenCompute/ROCm/discussions) on the
+GitHub repository.
+
+## Supported Formats
+
+Our documentation includes both markdown and rst files. Markdown is encouraged
+over rst due to the lower barrier to participation. GitHub flavored markdown is preferred
+for all submissions as it will render accurately on our GitHub repositories. For existing documentation,
+[MyST](https://myst-parser.readthedocs.io/en/latest/intro.html) markdown
+is used to implement certain features unsupported in GitHub markdown. This is
+not encouraged for new documentation. AMD will transition
+to stricter use of GitHub flavored markdown with a few caveats. ROCm documentation
+also uses [sphinx-design](https://sphinx-design.readthedocs.io/en/latest/index.html)
+in our markdown and rst files. We also will use breathe syntax for doxygen documentation
+in our markdown files. Other design elements for effective HTML rendering of the documents
+may be added to our markdown files. Please see
+[GitHub](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github)'s
+guide on writing and formatting on GitHub as a starting point.
+
+ROCm documentation adds additional requirements to markdown and rst based files
+as follows:
+
+- Level one headers are only used for page titles. There must be only one level
+  1 header per file for both Markdown and Restructured Text.
+- Pass [markdownlint](https://github.com/markdownlint/markdownlint) check via
+  our automated github action on a Pull Request (PR).
+
+## Filenames and folder structure
+
+Please use snake case for file names. Our documentation follows pitchfork for
+folder structure. All documentation is in /docs except for special files like
+the contributing guide in the / folder. All images used in the documentation are
+place in the /docs/data folder.
+
+## How to provide feedback for for ROCm documentation
+
+There are three standard ways to provide feedback for this repository.
+
+### Pull Request
+
+All contributions to ROCm documentation should arrive via the
+[GitHub Flow](https://docs.github.com/en/get-started/quickstart/github-flow)
+targetting the develop branch of the repository. If you are unable to contribute
+via the GitHub Flow, feel free to email us. TODO, confirm email address.
+
+### GitHub Issue
+
+Issues on existing or absent docs can be filed as [GitHub issues
+](https://github.com/RadeonOpenCompute/ROCm/issues).
+
+### Email Feedback
+
+## Language and Style
+
+Adopting Microsoft CPP-Docs guidelines for [Voice and Tone
+](https://github.com/MicrosoftDocs/cpp-docs/blob/main/styleguide/voice-tone.md).
+
+ROCm documentation templates to be made public shortly. ROCm templates dictate
+the recommended structure and flow of the documentation. Guidelines on how to
+integrate figures, equations, and tables are all based off
+[MyST](https://myst-parser.readthedocs.io/en/latest/intro.html).
+
+Font size and selection, page layout, white space control, and other formatting
+details are controlled via rocm-docs-core, sphinx extention. Please raise issues
+in rocm-docs-core for any formatting concerns and changes requested.
+
+## Building Documentation
+
+While contributing, one may build the documentation locally on the command-line
+or rely on Continuous Integration for previewing the resulting HTML pages in a
+browser.
+
+### Command line documentation builds
+
+Python versions known to build documentation:
+
+- 3.8
+
+To build the docs locally using Python Virtual Environment (`venv`), execute the
+following commands from the project root:
+
+```sh
+python3 -mvenv .venv
+# Windows
+.venv/Scripts/python -m pip install -r docs/sphinx/requirements.txt
+.venv/Scripts/python -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
+# Linux
+.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
+```
+
+Then open up `_build/html/index.html` in your favorite browser.
+
+### Pull Requests documentation builds
+
+When opening a PR to the `develop` branch on GitHub, the page corresponding to
+the PR (`https://github.com/RadeonOpenCompute/ROCm/pull/<pr_number>`) will have
+a summary at the bottom. This requires the user be logged in to GitHub.
+
+- There, click `Show all checks` and `Details` of the Read the Docs pipeline. It
+  will take you to `https://readthedocs.com/projects/advanced-micro-devices-rocm/
+  builds/<some_build_num>/`
+  - The list of commands shown are the exact ones used by CI to produce a render
+    of the documentation.
+- There, click on the small blue link `View docs` (which is not the same as the
+  bigger button with the same text). It will take you to the built HTML site with
+  a URL of the form `https://
+  advanced-micro-devices-demo--<pr_number>.com.readthedocs.build/projects/alpha/en
+  /<pr_number>/`.
+
+### Build the docs using VS Code
+
+One can put together a productive environment to author documentation and also
+test it locally using VS Code with only a handful of extensions. Even though the
+extension landscape of VS Code is ever changing, here is one example setup that
+proved useful at the time of writing. In it, one can change/add content, build a
+new version of the docs using a single VS Code Task (or hotkey), see all errors/
+warnings emitted by Sphinx in the Problems pane and immediately see the
+resulting website show up on a locally serving web server.
+
+#### Configuring VS Code
+
+1. Install the following extensions:
+
+    - Python (ms-python.python)
+    - Live Server (ritwickdey.LiveServer)
+
+2. Add the following entries in `.vscode/settings.json`
+
+    ```json
+    {
+      "liveServer.settings.root": "/.vscode/build/html",
+      "liveServer.settings.wait": 1000,
+      "python.terminal.activateEnvInCurrentTerminal": true
+    }
+    ```
+
+    The settings in order are set for the following reasons:
+    - Sets the root of the output website for live previews. Must be changed
+      alongside the `tasks.json` command.
+    - Tells live server to wait with the update to give time for Sphinx to
+      regenerate site contents and not refresh before all is don. (Empirical value)
+    - Automatic virtual env activation is a nice touch, should you want to build
+      the site from the integrated terminal.
+
+3. Add the following tasks in `.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 Python virtual environment (venv)
+
+    - From the Command Palette, run `Python: Create Environment`
+      - Select `venv` environment and the `docs/sphinx/requirements.txt` file.
+      _(Simply pressing enter while hovering over the file from the dropdown is
+      insufficient, one has to select the radio button with the 'Space' key if
+      using the keyboard.)_
+
+5. Build the docs
+
+    - Launch the default build Task using either:
+      - a hotkey _(default is 'Ctrl+Shift+B')_ or
+      - by issuing the `Tasks: Run Build Task` from the Command Palette.
+
+6. Open the live preview
+
+    - Navigate to the output of the site 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.
+
+<!-- markdownlint-restore -->

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Advanced Micro Devices, Inc. All rights reserved.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,653 +1,54 @@
-# AMD ROCm™ v4.1 Release Notes 
-This document describes the features, fixed issues, and information about downloading and installing the AMD ROCm™ software. It also covers known issues and deprecations in the AMD ROCm v4.1 release.
+# AMD ROCm™ Platform
 
-- [Supported Operating Systems and Documentation Updates](#Supported-Operating-Systems-and-Documentation-Updates)
-  * [Supported Operating Systems](#Supported-Operating-Systems)
-  * [ROCm Installation Updates](#ROCm-Installation-Updates)
-  * [AMD ROCm Documentation Updates](#AMD-ROCm-Documentation-Updates)
+ROCm™ is an open-source stack for GPU computation. ROCm is primarily Open-Source
+Software (OSS) that allows developers the freedom to customize and tailor their
+GPU software for their own needs while collaborating with a community of other
+developers, and helping each other find solutions in an agile, flexible, rapid
+and secure manner.
 
-- [Driver Compatibility Issue in This Release](#Driver-Compatibility-Issue-in-This-Release)
-   
-- [What\'s New in This Release](#Whats-New-in-This-Release)
-  * [TargetID for Multiple Configurations](#TargetID-for-Multiple-Configurations)
-  * [ROCm Data Center Tool](#ROCm-Data-Center-Tool)
-  * [ROCm Math and Communication Libraries](#ROCm-Math-and-Communication-Libraries)
-  * [HIP Enhancements](#HIP-Enhancements)
-  * [OpenMP Enhancements and Fixes](#OpenMP-Enhancements-and-Fixes)
-  * [MIOpen Tensile Integration](#MIOpen-Tensile-Integration)
+ROCm is a collection of drivers, development tools and APIs enabling GPU
+programming from the low-level kernel to end-user applications. ROCm is powered
+by AMD’s Heterogeneous-computing Interface for Portability (HIP), an OSS C++ GPU
+programming environment and its corresponding runtime. HIP allows ROCm
+developers to create portable applications on different platforms by deploying
+code on a range of platforms, from dedicated gaming GPUs to exascale HPC
+clusters. ROCm supports programming models such as OpenMP and OpenCL, and
+includes all the necessary OSS compilers, debuggers and libraries. ROCm is fully
+integrated into ML frameworks such as PyTorch and TensorFlow. ROCm can be
+deployed in many ways, including through the use of containers such as Docker,
+Spack, and your own build from source.
 
-    
-- [Known Issues](#Known-Issues)
+ROCm’s goal is to allow our users to maximize their GPU hardware investment.
+ROCm is designed to help develop, test and deploy GPU accelerated HPC, AI,
+scientific computing, CAD, and other applications in a free, open-source,
+integrated and secure software ecosystem.
 
-- [Deprecations](#Deprecations)
+This repository contains the manifest file for ROCm™ releases, changelogs, and
+release information. The file default.xml contains information for all
+repositories and the associated commit used to build the current ROCm release.
 
-  * [Compiler Generated Code Object Version 2 Deprecation ](#Compiler-Generated-Code-Object-Version-2-Deprecation)
+The default.xml file uses the repo Manifest format.
 
-- [Deploying ROCm](#Deploying-ROCm)
- 
-- [Hardware and Software Support](#Hardware-and-Software-Support)
+The develop branch of this repository contains content for the next
+ROCm release.
 
-- [Machine Learning and High Performance Computing Software Stack for AMD GPU](#Machine-Learning-and-High-Performance-Computing-Software-Stack-for-AMD-GPU)
-  * [ROCm Binary Package Structure](#ROCm-Binary-Package-Structure)
-  * [ROCm Platform Packages](#ROCm-Platform-Packages)
-  
+## ROCm Documentation
 
+ROCm Documentation is available online at
+[rocm.docs.amd.com](https://rocm.docs.amd.com). Source code for the documenation
+is located in the docs folder of most repositories that are part of ROCm.
 
+### How to build documentation via Sphinx
 
-## ROCm Installation Updates 
+```bash
+cd docs
 
-### List of Supported Operating Systems
+pip3 install -r sphinx/requirements.txt
 
-The AMD ROCm platform is designed to support the following operating systems:
-
-* Ubuntu 20.04.1 (5.4 and 5.6-oem) and 18.04.5 (Kernel 5.4)	
-* CentOS 7.9 (3.10.0-1127) & RHEL 7.9 (3.10.0-1160.6.1.el7) (Using devtoolset-7 runtime support)
-* CentOS 8.3 (4.18.0-193.el8) and RHEL 8.3 (4.18.0-193.1.1.el8) (devtoolset is not required)
-* SLES 15 SP2
-
-### FRESH INSTALLATION OF AMD ROCM V4.1 RECOMMENDED
-
-A complete uninstallation of previous ROCm versions is required before installing a new version of ROCm. An upgrade from previous releases to AMD ROCm v4.1 is not supported. For more information, refer to the AMD ROCm Installation Guide at
-
-https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
-
-**Note**: AMD ROCm release v3.3 or prior releases are not fully compatible with AMD ROCm v3.5 and higher versions. You must perform a fresh ROCm installation if you want to upgrade from AMD ROCm v3.3 or older to 3.5 or higher versions and vice-versa.
-
-**Note**: *render* group is required only for Ubuntu v20.04. For all other ROCm supported operating systems, continue to use video group. 
-
-* For ROCm v3.5 and releases thereafter, the clinfo path is changed to /opt/rocm/opencl/bin/clinfo. 
-
-* For ROCm v3.3 and older releases, the clinfo path remains /opt/rocm/opencl/bin/x86_64/clinfo. 
- 
-### ROCM MULTI-VERSION INSTALLATION UPDATE
-
-With the AMD ROCm v4.1 release, the following ROCm multi-version installation changes apply:
-
-The meta packages rocm-dkms<version> are now deprecated for multi-version ROCm installs.  For example, rocm-dkms3.7.0, rocm-dkms3.8.0.
- 
-* Multi-version installation of ROCm should be performed by installing rocm-dev<version> using each of the desired ROCm versions. For example, rocm-dev3.7.0, rocm-dev3.8.0, rocm-dev3.9.0.   
-
-* Version files must be created for each multi-version rocm <= 4.1.0
-
- * Command: echo <version> | sudo tee /opt/rocm-<version>/.info/version
-
- * Example: echo 4.1.0 | sudo tee /opt/rocm-4.1.0/.info/version
-
-* The rock-dkms loadable kernel modules should be installed using a single rock-dkms package. 
-
-* ROCm v3.9 and above will not set any ldconfig entries for ROCm libraries for multi-version installation.  Users must set LD_LIBRARY_PATH to load the ROCm library version of choice.
-
-**NOTE**: The single version installation of the ROCm stack remains the same. The rocm-dkms package can be used for single version installs and is not deprecated at this time.
-
-
-
-# Driver Compatibility Issue in This Release
-
-In certain scenarios, the ROCm 4.1 run-time and userspace environment are not compatible with ROCm v4.0 and older driver implementations for 7nm-based (Vega 20) hardware (MI50 and MI60). 
-
-To mitigate issues, the ROCm v4.1 or newer userspace prevents running older drivers for these GPUs.
-
-Users are notified in the following scenarios:
-
-* Bare Metal 
-* Containers
- 
-## Bare Metal
-
-In the bare-metal environment, the following error message displays in the console: 
-
-*“HSA Error: Incompatible kernel and userspace, Vega 20 disabled. Upgrade amdgpu.”*
-
-To test the compatibility, run the ROCm v4.1 version of rocminfo using the following instruction: 
-
-*/opt/rocm-4.1.0/bin/rocminfo 2>&1 | less*
-
-## Containers
-
-A container (built with error detection for this issue) using a ROCm v4.1 or newer run-time is initiated to execute on an older kernel. The container fails to start and the following warning appears:
-
-*Error: Incompatible ROCm environment. The Docker container requires the latest kernel driver to operate correctly.
-Upgrade the ROCm kernel to v4.1 or newer, or use a container tagged for v4.0.1 or older.*
-
-To inspect the version of the installed kernel driver,  run either: 
-
-* dpkg --status rock-dkms [Debian-based]
-
-or
-
-* rpm -ql rock-dkms [RHEL, SUSE, and others]
-
-To install or update the driver, follow the installation instructions at:
-
-https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
-
-
-# AMD ROCm Documentation Updates
-
-## AMD ROCm Installation Guide 
-
-The AMD ROCm Installation Guide in this release includes:
-
-* Supported Environments
-
-* Installation Instructions for v4.1
-
-* HIP Installation Instructions 
-
-For more information, refer to the ROCm documentation website at:
-
-https://rocmdocs.amd.com/en/latest/
-
-
-## AMD ROCm - HIP Documentation Updates
-
-* HIP Programming Guide v4.1 
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Programming_Guide_v4.1.pdf
-
-* HIP API Guide v4.1
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_API_Guide_v4.1.pdf
-  
-
-* HIP-Supported CUDA API Reference Guide v4.1
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/HIP_Supported_CUDA_API_Reference_Guide_v4.1.pdf
-
-* HIP FAQ  
-
-  For more information, refer to
-
-  https://rocmdocs.amd.com/en/latest/Programming_Guides/HIP-FAQ.html#hip-faq
-
-
-## ROCm Data Center User and API Guide
-
-* ROCm Data Center Tool User Guide
-
-   - Grafana Plugin Integration
-
-  For more information, refer to the ROCm Data Center User Guide at,
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_ROCm_DataCenter_Tool_User_Guide_v4.1.pdf
-  
-
-* ROCm Data Center Tool API Guide
-
-  For more information, refer to the ROCm Data Center API Guide at,
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCm_Data_Center_Tool_API_Manual_4.1.pdf
-
-
-## ROCm SMI API Documentation Updates 
-
-* ROCm SMI API Guide 
-
-  For more information, refer to the ROCm SMI API Guide at,
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCm_SMI_API_GUIDE_v4.1.pdf
-  
-## ROC Debugger User and API Guide 
-
-* ROC Debugger User Guide 
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/Debugging%20with%20ROCGDB%20User%20Guide%20v4.1.pdf
-  
-
-* Debugger API Guide 
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD-Debugger%20API%20Guide%20v4.1.pdf
-
-
-## General AMD ROCm Documentation Links
-
-Access the following links for more information:
-
-* For AMD ROCm documentation, see 
-
-  https://rocmdocs.amd.com/en/latest/
-
-* For installation instructions on supped platforms, see
-
-  https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
-
-* For AMD ROCm binary structure, see
-
-  https://rocmdocs.amd.com/en/latest/Installation_Guide/Software-Stack-for-AMD-GPU.html
-  
-
-* For AMD ROCm Release History, see
-
- https://rocmdocs.amd.com/en/latest/Current_Release_Notes/ROCm-Version-History.html
-
-
-
-# What\'s New in This Release
-
-## TARGETID FOR MULTIPLE CONFIGURATIONS
-
-The new TargetID functionality allows compilations to specify various configurations of the supported hardware. 
-
-Previously, ROCm supported only a single configuration per target. 
-
-With the TargetID enhancement, ROCm supports configurations for Linux, PAL and associated configurations such as XNACK. This feature addresses configurations for the same target in different modes and allows applications to build executables that specify the supported configurations, including the option to be agnostic for the desired setting.
-
-
-### New Code Object Format Version for TargetID
-
-* A new clang option -mcode-object-version can be used to request the legacy code object version 3 or code object version 2. For more information, refer to
-
-  https://llvm.org/docs/AMDGPUUsage.html#elf-code-object
-
-* A new clang --offload-arch= option is introduced to specify the offload target architecture(s) for the HIP language.
-
-* The clang --offload-arch= and -mcpu options accept a new Target ID syntax. This allows both the processor and target feature settings to be specified. For more details, refer to
-
-  https://llvm.org/docs/AMDGPUUsage.html#amdgpu-target-id
-
-    - If a target feature is not specified, it defaults to a new concept of "any". The compiler, then, produces code, 
-      which executes on a target configured for either value of the setting impacting the overall performance. 
-      
-      It is recommended to explicitly specify the setting for more efficient performance. 
-
-    - In particular, the setting for XNACK now defaults to produce less performant code than previous ROCm releases.
-
-    - The legacy clang -mxnack, -mno-xnack, -msram-ecc, and -mno-sram-ecc options are deprecated. They are still 
-      supported, however, they will be removed in a future release. 
-
-    - The new Target ID syntax renames the SRAM ECC feature from sram-ecc to sramecc.
-
-* The clang offload bundler uses the new offload hipv4 for HIP code object version 4. For more information, see 
-https://clang.llvm.org/docs/ClangOffloadBundler.html
-
-* ROCm v4.1 corrects code object loading to enforce target feature settings of the code object to match the setting of the agent. It also corrects the recording of target feature settings in the code object. As a consequence, the legacy code objects may no longer load due to mismatches.
-
-* gfx802, gfx803, and gfx805 do not support the XNACK target feature in the ROCm v4.1 release.
-
-
-### New Code Object Tools
-
-AMD ROCm v4.1 provides new code object tools *roc-obj-ls* and *roc-obj-extract*. These tools allow for the listing and extraction of AMD GPU ROCm code objects that are embedded in HIP executables and shared objects. Each tool supports a --help option that provides more information. 
-
-Refer to the HIP Programming Guide v4.1 for additional information and examples.
-
-https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Programming_Guide_v4.1.pdf
-
-**Note**
-
-The extractkernel tool in previous AMD ROCm releases has been removed from the AMD ROCm v4.1 release 
-and will no longer be  supported.
-
-**Note**
- 
- The roc-obj-ls and roc-obj-extract tools may generate an error about the following missing Perl modules: 
-
-* File::Which
-* File::BaseDir
-* File::Copy
-* URI::Encode
-
-This error is due to the missing dependencies in the hip-base installer package.  As a workaround, you may use the 
-following instructions to install the Perl modules:  
-
-*Ubuntu*
-     
-     apt-get install libfile-which-perl libfile-basedir-perl libfile-copy-recursive-perl liburi-encode-perl
-   
-*CentOS*
-            
-      yum install “ perl(File::Which) perl(File::BaseDir) perl(File::Copy) perl(URI::Encode)
-
-
-
-## ROCm Data Center Tool 
-
-### Grafana Integration
-
-The ROCm Data Center (RDC) Tool is enhanced with the Grafana plugin. Grafana is a common monitoring stack used for storing and visualizing time series data. Prometheus acts as the storage backend, and Grafana is used as the interface for analysis and visualization. Grafana has a plethora of visualization options and can be integrated with Prometheus for the ROCm Data Center (RDC) dashboard. 
-
-For more information about Grafana integration and installation, refer to the ROCm Data Center Tool User guide at:
-
-https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_ROCm_DataCenter_Tool_User_Guide_v4.1.pdf
-
-
-
-## ROCm Math and Communication Libraries 
-
-### rocSPARSE
-
-rocSPARSE extends support for:
-
-* gebsrmm
-* gebsrmv
-* gebsrsv
-* coo2dense and dense2coo
-* generic API including axpby, gather, scatter, rot, spvv, spmv, spgemm, sparsetodense, densetosparse
-* mixed indexing types in matrix formats
-
-For more information, see 
-
-https://rocsparse.readthedocs.io/en/latest/
-
-
-### rocSOLVER
-
-rocSOLVER extends support for:
-
-* Eigensolver routines for symmetric/hermitian matrices:
-  - STERF, STEQR
-  
-* Linear solvers for general non-square systems:
-  - GELS (API added with batched and strided_batched versions. Only the overdetermined non-transpose case is implemented in 
-    this release. Other cases will return rocblas_status_not_implemented status for now.)
-    
-* Extended test coverage for functions returning information
-
-* Changelog file
-
-* Tridiagonalization routines for symmetric and hermitian matrices:
-  - LATRD
-  - SYTD2, SYTRD (with batched and strided_batched versions)
-  - HETD2, HETRD (with batched and strided_batched versions)
-  
-* Sample code and unit test for unified memory model/Heterogeneous Memory Management (HMM)
-
-For more information, see
-
-https://rocsolver.readthedocs.io/en/latest/
-
-### hipCUB
-
-The new iterator DiscardOutputIterator in hipCUB represents a special kind of pointer that ignores values written to it upon dereference.  It is useful for ignoring the output of certain algorithms without wasting memory capacity or bandwidth.  DiscardOutputIterator may also be used to count the size of an algorithm's output, which was not known previously.
-
-For more information, see
-
-https://hipcub.readthedocs.io/en/latest/
-
-
-## HIP Enhancements
-
-### Support for hipEventDisableTiming Flag
-
-HIP now supports the hipEventDisableTiming flag for hipEventCreateWithFlags. Note, events created with this flag do not record profiling data and provide optimal performance when used for synchronization.
-
-### Cooperative Group Functions
-
-Cooperative Groups defines, synchronizes, and communicates between groups of threads and blocks for efficiency and ease of management. HIP now supports the following kernel language Cooperative Groups types and functions:
-
-![Screenshot](https://github.com/Rmalavally/ROCm/blob/master/images/CG1.PNG)
-![Screenshot](https://github.com/Rmalavally/ROCm/blob/master/images/CG2.PNG)
-![Screenshot](https://github.com/Rmalavally/ROCm/blob/master/images/CG3.PNG)
-
-
-###  Support for Extern Shared Declarations
-
-Previously, it was required to declare dynamic shared memory using the HIP_DYNAMIC_SHARED macro for accuracy as using static shared memory in the same kernel could result in overlapping memory ranges and data-races.
-Now, the HIP-Clang compiler provides support for extern shared declarations, and the HIP_DYNAMIC_SHARED option is no longer required. 
-
-You may use the standard extern definition:
-
-    extern __shared__ type var[];
-
-
-## OpenMP Enhancements and Fixes
-
-This release includes the following OpenMP changes:
-
-* Usability Enhancements
-* Fixes to Internal Clang Math Headers
-* OpenMP Defect Fixes
-
-### Usability Enhancements
-
-* OMPD updates for flang
-* To support OpenMP debugging, the selected OpenMP runtime sources are included in lib-debug/src/openmp. The ROCgdb debugger 
-  will find these automatically.
-* Threadsafe hsa plugin for libomptarget
-* Support multiple devices with malloc and hostrpc
-* Improve hostrpc version check
-* Add max reduction offload feature to flang
-* Integration of changes to support HPC Toolkit
-* Support for fprintf
-* Initial support for GPU malloc and Free. The internal (device rtl) is required for GPU malloc and Free for nested parallelism.  
-  GPU malloc and Free are now replaced, which improves the device memory footprint.
-* Increase detail of debug printing controlled by LIBOMPTARGET_KERNEL_TRACE environment variable
-* Add support for -gpubnames in Flang Driver
-* Increase detail of debug printing controlled by LIBOMPTARGET_KERNEL_TRACE environment variable
-* Add support for -gpubnames in Flang Driver
-
-###  Fixes to Internal Clang Math Headers
-
-This release includes a set of changes applied to Clang internal headers to support OpenMP C, C++, FORTRAN, and HIP C. This establishes consistency between NVPTX and AMDGCN offloading, and OpenMP, HIP, and CUDA. OpenMP uses function variants and header overlays to define device versions of functions. This causes Clang LLVM IR codegen to mangle names of variants in both the definition and callsites of functions defined in the internal Clang headers. The changes apply to headers found in the installation subdirectory lib/clang/11.0.0/include.
-
-The changes also temporarily eliminate the use of the libm bitcode libraries for C and C++. Although math functions are now defined with internal clang headers, a bitcode library of the C functions defined in the headers is still built for the FORTRAN toolchain linking. This is because FORTRAN cannot use C math headers. This bitcode library is installed in lib/libdevice/libm-.bc. The source build of the bitcode library is implemented with the aomp-extras repository and the component-built script build_extras.sh. 
-
-### OpenMP Defect Fixes
-
-The following OpenMP defects are fixed in this release:
-
-* Openmpi configuration issue with real16. 
-* [flang] The AOMP 11.7-1 Fortran compiler claims to support the -isystem flag, but ignores it.
-* [flang] producing internal compiler error when the character is used with KIND.
-* [flang] openmp map clause on complex allocatable expressions !$omp target data map( chunk%tiles(1)%field%density0).
-* Add a fatal error if missing -Xopenmp-target or -march options when -fopenmp-targets is specified. However, this requirement is not 
-  applicable for offloading to the host when there is only a single target and that target is the host.
-* Openmp error message output for no_rocm_device_lib was asserting.
-* Linkage on constant per-kernel symbols from external to weaklinkageonly to prevent duplicate symbols when building kokkos.
-* Add environment variables ROCM_LLD_ARGS ROCM_LINK_ARGS ROCM_SELECT_ARGS to test driver options without compiler rebuild.  
-* Fix problems with device math functions being ambiguous, especially the pow function.ix aompcc to accept file type cxx. 
-* Fix a latent race between host runtime and devicertl.
-
-## MIOPEN TENSILE INTEGRATION
-
-MIOpenTensile provides host-callable interfaces to the Tensile library and supports the HIP programming model. You may use the Tensile feature in the HIP backend by setting the building environment variable value to ON.
-
-    MIOPEN_USE_MIOPENTENSILE=ON
-
-MIOpenTensile is an open-source collaboration tool where external entities can submit source pull requests (PRs) for updates. MIOpenTensile maintainers review and approve the PRs using standard open-source practices. 
-
-For more information about the sources and the build system, see
-
-https://github.com/ROCmSoftwarePlatform/MIOpenTensile
-
-
-# Known Issues 
-
-The following are the known issues in this release.
-
-## Upgrade to AMD ROCm v4.1 Not Supported
-
-An upgrade from previous releases to AMD ROCm v4.1 is not supported. A complete uninstallation of previous ROCm versions is required before installing a new version of ROCm.
-
-## Performance Impact for Kernel Launch Bound Attribute
-
-Kernels without the *__launch_bounds__* attribute assume the default maximum threads per block value. In the previous ROCm release, this value was 256. In the ROCm v4.1 release, it is changed to 1024. The objective of this change ensures the actual threads per block value used to launch a kernel, by default, are always within the launch bounds, thus, establishing the correctness of HIP programs. 
-
-**NOTE**: Using the above-mentioned approach may incur performance degradation in certain cases. Users must add a minimum launch bound to each kernel, which covers all possible threads per block values used to launch that kernel for correctness and performance. 
-
-The recommended workaround to recover the performance is to add *--gpu-max-threads-per-block=256* to the compilation options for HIP programs.
-
-## Issue with Passing a Subset of GPUs in a Multi-GPU System
-
-ROCm support for passing individual GPUs via the docker --device flag in a Docker run command has a known issue when passing a subset of GPUs in a multi-GPU system. The command runs without any warning or error notification. However, all GPU executable run outputs are randomly corrupted. 
-
-Using GPU targeting via the Docker command is not recommended for users of ROCm 4.1. There is no workaround for this issue currently. 
-
-## Performance Impact for LDS-Bound Kernels
-
-The compiler in ROCm v4.1 generates LDS load and stores instructions that incorrectly assume equal performance between aligned and misaligned accesses. While this does not impact code correctness, it may result in sub-optimal performance.
-
-This issue is under investigation, and there is no known workaround at this time.
-
-
-# Deprecations
-
-This section describes deprecations and removals in AMD ROCm.
-
-## Compiler Generated Code Object Version 2 Deprecation 
-
-Compiler-generated code object version 2 is no longer supported and has been completely removed. Support for loading code object version 2 is also deprecated with no announced removal release.
-
-
-# Deploying ROCm
-
-AMD hosts both Debian and RPM repositories for the ROCm packages. 
-
-For more information on ROCM installation on all platforms, see
-
-https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
-
-
-# Machine Learning and High Performance Computing Software Stack for AMD GPU
-
-For an updated version of the software stack for AMD GPU, see
-
-https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html#software-stack-for-amd-gpu
-
-
-
-# Hardware and Software Support
-ROCm is focused on using AMD GPUs to accelerate computational tasks such as machine learning, engineering workloads, and scientific computing.
-In order to focus our development efforts on these domains of interest, ROCm supports a targeted set of hardware configurations which are detailed further in this section.
-
-**Note:** The AMD ROCm™ open software platform is a compute stack for headless system deployments. GUI-based software applications are currently not supported.
-
-#### Supported GPUs
-Because the ROCm Platform has a focus on particular computational domains, we offer official support for a selection of AMD GPUs that are designed to offer good performance and price in these domains.
-
-**Note:** The integrated GPUs of Ryzen are not officially supported targets for ROCm.
-
-ROCm officially supports AMD GPUs that use following chips:
-
-* GFX9 GPUs
-
-  - "Vega 10" chips, such as on the AMD Radeon RX Vega 64 and Radeon Instinct MI25
-  
-  - "Vega 7nm" chips, such as on the Radeon Instinct MI50, Radeon Instinct MI60 or AMD Radeon VII, Radeon Pro VII
-
-* CDNA GPUs
-
-  - MI100 chips such as on the AMD Instinct™ MI100
-
-
-ROCm is a collection of software ranging from drivers and runtimes to libraries and developer tools.
-Some of this software may work with more GPUs than the "officially supported" list above, though AMD does not make any official claims of support for these devices on the ROCm software platform.
-
-The following list of GPUs are enabled in the ROCm software, though full support is not guaranteed:
-
-  * GFX8 GPUs
-    * "Polaris 11" chips, such as on the AMD Radeon RX 570 and Radeon Pro WX 4100
-    * "Polaris 12" chips, such as on the AMD Radeon RX 550 and Radeon RX 540
-  * GFX7 GPUs
-    * "Hawaii" chips, such as the AMD Radeon R9 390X and FirePro W9100
-
-As described in the next section, GFX8 GPUs require PCI Express 3.0 (PCIe 3.0) with support for PCIe atomics. This requires both CPU and motherboard support. GFX9 GPUs require PCIe 3.0 with support for PCIe atomics by default, but they can operate in most cases without this capability.
-
-The integrated GPUs in AMD APUs are not officially supported targets for ROCm.
-As described [below](#limited-support), "Carrizo", "Bristol Ridge", and "Raven Ridge" APUs are enabled in our upstream drivers and the ROCm OpenCL runtime.
-However, they are not enabled in the HIP runtime, and may not work due to motherboard or OEM hardware limitations.
-As such, they are not yet officially supported targets for ROCm.
-
-For a more detailed list of hardware support, please see [the following documentation](https://en.wikipedia.org/wiki/List_of_AMD_graphics_processing_units).
-
-#### Supported CPUs
-As described above, GFX8 GPUs require PCIe 3.0 with PCIe atomics in order to run ROCm.
-In particular, the CPU and every active PCIe point between the CPU and GPU require support for PCIe 3.0 and PCIe atomics.
-The CPU root must indicate PCIe AtomicOp Completion capabilities and any intermediate switch must indicate PCIe AtomicOp Routing capabilities.
-
-Current CPUs which support PCIe Gen3 + PCIe Atomics are:
-
-  * AMD Ryzen CPUs
-  * The CPUs in AMD Ryzen APUs
-  * AMD Ryzen Threadripper CPUs
-  * AMD EPYC CPUs
-  * Intel Xeon E7 v3 or newer CPUs
-  * Intel Xeon E5 v3 or newer CPUs
-  * Intel Xeon E3 v3 or newer CPUs
-  * Intel Core i7 v4, Core i5 v4, Core i3 v4 or newer CPUs (i.e. Haswell family or newer)
-  * Some Ivy Bridge-E systems
-
-Beginning with ROCm 1.8, GFX9 GPUs (such as Vega 10) no longer require PCIe atomics.
-We have similarly opened up more options for number of PCIe lanes.
-GFX9 GPUs can now be run on CPUs without PCIe atomics and on older PCIe generations, such as PCIe 2.0.
-This is not supported on GPUs below GFX9, e.g. GFX8 cards in the Fiji and Polaris families.
-
-If you are using any PCIe switches in your system, please note that PCIe Atomics are only supported on some switches, such as Broadcom PLX.
-When you install your GPUs, make sure you install them in a PCIe 3.1.0 x16, x8, x4, or x1 slot attached either directly to the CPU's Root I/O controller or via a PCIe switch directly attached to the CPU's Root I/O controller.
-
-In our experience, many issues stem from trying to use consumer motherboards which provide physical x16 connectors that are electrically connected as e.g. PCIe 2.0 x4, PCIe slots connected via the Southbridge PCIe I/O controller, or PCIe slots connected through a PCIe switch that does
-not support PCIe atomics.
-
-If you attempt to run ROCm on a system without proper PCIe atomic support, you may see an error in the kernel log (`dmesg`):
-```
-kfd: skipped device 1002:7300, PCI rejects atomics
+python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html
 ```
 
-Experimental support for our Hawaii (GFX7) GPUs (Radeon R9 290, R9 390, FirePro W9100, S9150, S9170)
-does not require or take advantage of PCIe Atomics. However, we still recommend that you use a CPU
-from the list provided above for compatibility purposes.
-
-#### Not supported or limited support under ROCm
-
-##### Limited support
-
-* ROCm 4.x should support PCIe 2.0 enabled CPUs such as the AMD Opteron, Phenom, Phenom II, Athlon, Athlon X2, Athlon II and older Intel Xeon and Intel Core Architecture and Pentium CPUs. However, we have done very limited testing on these configurations, since our test farm has been catering to CPUs listed above. This is where we need community support. _If you find problems on such setups, please report these issues_.
-* Thunderbolt 1, 2, and 3 enabled breakout boxes should now be able to work with ROCm. Thunderbolt 1 and 2 are PCIe 2.0 based, and thus are only supported with GPUs that do not require PCIe 3.1.0 atomics (e.g. Vega 10). However, we have done no testing on this configuration and would need community support due to limited access to this type of equipment.
-* AMD "Carrizo" and "Bristol Ridge" APUs are enabled to run OpenCL, but do not yet support HIP or our libraries built on top of these compilers and runtimes.
-  * As of ROCm 2.1, "Carrizo" and "Bristol Ridge" require the use of upstream kernel drivers.
-  * In addition, various "Carrizo" and "Bristol Ridge" platforms may not work due to OEM and ODM choices when it comes to key configurations parameters such as inclusion of the required CRAT tables and IOMMU configuration parameters in the system BIOS.
-  * Before purchasing such a system for ROCm, please verify that the BIOS provides an option for enabling IOMMUv2 and that the system BIOS properly exposes the correct CRAT table. Inquire with your vendor about the latter.
-* AMD "Raven Ridge" APUs are enabled to run OpenCL, but do not yet support HIP or our libraries built on top of these compilers and runtimes.
-  * As of ROCm 2.1, "Raven Ridge" requires the use of upstream kernel drivers.
-  * In addition, various "Raven Ridge" platforms may not work due to OEM and ODM choices when it comes to key configurations parameters such as inclusion of the required CRAT tables and IOMMU configuration parameters in the system BIOS.
-  * Before purchasing such a system for ROCm, please verify that the BIOS provides an option for enabling IOMMUv2 and that the system BIOS properly exposes the correct CRAT table. Inquire with your vendor about the latter.
-
-##### Not supported
-
-* "Tonga", "Iceland", "Vega M", and "Vega 12" GPUs are not supported.
-* We do not support GFX8-class GPUs (Fiji, Polaris, etc.) on CPUs that do not have PCIe 3.0 with PCIe atomics.
-  * As such, we do not support AMD Carrizo and Kaveri APUs as hosts for such GPUs.
-  * Thunderbolt 1 and 2 enabled GPUs are not supported by GFX8 GPUs on ROCm. Thunderbolt 1 & 2 are based on PCIe 2.0.
-
-In the default ROCm configuration, GFX8 and GFX9 GPUs require PCI Express 3.0 with PCIe atomics. The ROCm platform leverages these advanced capabilities to allow features such as user-level submission of work from the host to the GPU. This includes PCIe atomic Fetch and Add, Compare and Swap, Unconditional Swap, and AtomicOp Completion.
-
-#### ROCm support in upstream Linux kernels
-
-As of ROCm 1.9.0, the ROCm user-level software is compatible with the AMD drivers in certain upstream Linux kernels.
-As such, users have the option of either using the ROCK kernel driver that are part of AMD's ROCm repositories or using the upstream driver and only installing ROCm user-level utilities from AMD's ROCm repositories.
-
-These releases of the upstream Linux kernel support the following GPUs in ROCm:
- * 4.17: Fiji, Polaris 10, Polaris 11
- * 4.18: Fiji, Polaris 10, Polaris 11, Vega10
- * 4.20: Fiji, Polaris 10, Polaris 11, Vega10, Vega 7nm
-
-The upstream driver may be useful for running ROCm software on systems that are not compatible with the kernel driver available in AMD's repositories.
-For users that have the option of using either AMD's or the upstreamed driver, there are various tradeoffs to take into consideration:
-
-|   | Using AMD's `rock-dkms` package | Using the upstream kernel driver |
-| ---- | ------------------------------------------------------------| ----- |
-| Pros | More GPU features, and they are enabled earlier | Includes the latest Linux kernel features |
-|      | Tested by AMD on supported distributions | May work on other distributions and with custom kernels |
-|      | Supported GPUs enabled regardless of kernel version | |
-|      | Includes the latest GPU firmware | |
-| Cons | May not work on all Linux distributions or versions | Features and hardware support varies depending on kernel version |
-|      | Not currently supported on kernels newer than 5.4 | Limits GPU's usage of system memory to 3/8 of system memory (before 5.6). For 5.6 and beyond, both DKMS and upstream kernels allow use of 15/16 of system memory. |
-|      |   | IPC and RDMA capabilities are not yet enabled |
-|      |   | Not tested by AMD to the same level as `rock-dkms` package |
-|      |   | Does not include most up-to-date firmware |
-
-
-# Disclaimer
-
-AMD®, the AMD Arrow logo, AMD Instinct™, Radeon™, ROCm® and combinations thereof are trademarks of Advanced Micro Devices, Inc.
-
-Linux® is the registered trademark of Linus Torvalds in the U.S. and other countries.
-
-PCIe® is a registered trademark of PCI-SIG Corporation. Other product names used in this publication are for identification purposes only and may be trademarks of their respective companies.  
-
-Google®  is a registered trademark of Google LLC.
-
-Ubuntu and the Ubuntu logo are registered trademarks of Canonical Ltd.
-
-Other product names used in this publication are for identification purposes only and may be trademarks of their respective companies.
+## Older ROCm™ Releases
 
+For release information for older ROCm™ releases, refer to
+[CHANGELOG](./CHANGELOG.md).

RELEASE.md

@@ -0,0 +1,582 @@
+# Release Notes
+<!-- Do not edit this file! This file is autogenerated with -->
+<!--   tools/autotag/tag_script.py                          -->
+
+<!-- Disable lints since this is an auto-generated file.    -->
+<!-- markdownlint-disable blanks-around-headers             -->
+<!-- markdownlint-disable no-duplicate-header               -->
+<!-- markdownlint-disable no-blanks-blockquote              -->
+<!-- markdownlint-disable ul-indent                         -->
+<!-- markdownlint-disable no-trailing-spaces                -->
+
+<!-- spellcheck-disable -->
+
+The release notes for the ROCm platform.
+
+-------------------
+
+## ROCm 5.6.0
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable no-duplicate-header -->
+<!-- markdownlint-disable header-increment -->
+#### Release Highlights
+
+ROCm 5.6 consists of several AI software ecosystem improvements to our fast-growing user base. A few examples include:
+
+- New documentation portal at https://rocm.docs.amd.com
+- Ongoing software enhancements for LLMs, ensuring full compliance with the HuggingFace unit test suite
+- OpenAI Triton, CuPy, HIP Graph support, and many other library performance enhancements
+- Improved ROCm deployment and development tools, including CPU-GPU (rocGDB) debugger, profiler, and docker containers
+- New pseudorandom generators are available in rocRAND.  Added support for half-precision transforms in hipFFT/rocFFT.  Added LU refactorization and linear system solver for sparse matrices in rocSOLVER.  
+
+#### OS and GPU Support Changes
+
+- SLES15 SP5 support was added this release. SLES15 SP3 support was dropped.
+- AMD Instinct MI50, Radeon Pro VII, and Radeon VII products (collectively referred to as gfx906 GPUs) will be entering the maintenance mode starting Q3 2023. This will be aligned with ROCm 5.7 GA release date.
+  - No new features and performance optimizations will be supported for the gfx906 GPUs beyond ROCm 5.7
+  - Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (End of Maintenance [EOM])(will be aligned with the closest ROCm release)
+  - Bug fixes during the maintenance will be made to the next ROCm point release
+  - Bug fixes will not be back ported to older ROCm releases for this SKU
+  - Distro / Operating system updates will continue as per the ROCm release cadence for gfx906 GPUs till EOM.
+
+#### AMDSMI CLI 23.0.0.4
+
+##### Added
+
+- AMDSMI CLI tool enabled for Linux Bare Metal & Guest
+
+- Package: amd-smi-lib
+ 
+##### Known Issues
+
+- not all Error Correction Code (ECC) fields are currently supported
+
+- RHEL 8 & SLES 15 have extra install steps
+
+#### Kernel Modules (DKMS)
+
+##### Fixes
+
+- Stability fix for multi GPU system reproducilble via ROCm_Bandwidth_Test as reported in [Issue 2198](https://github.com/RadeonOpenCompute/ROCm/issues/2198).
+
+#### HIP 5.6 (For ROCm 5.6)
+
+##### Optimizations
+
+- Consolidation of hipamd, rocclr and OpenCL projects in clr
+- Optimized lock for graph global capture mode
+
+##### Added
+
+- Added hipRTC support for amd_hip_fp16
+- Added hipStreamGetDevice implementation to get the device associated with the stream
+- Added HIP_AD_FORMAT_SIGNED_INT16 in hipArray formats
+- hipArrayGetInfo for getting information about the specified array
+- hipArrayGetDescriptor for getting 1D or 2D array descriptor
+- hipArray3DGetDescriptor to get 3D array descriptor
+
+##### Changed
+
+- hipMallocAsync to return success for zero size allocation to match hipMalloc
+- Separation of hipcc perl binaries from HIP project to hipcc project. hip-devel package depends on newly added hipcc package
+- Consolidation of hipamd, ROCclr, and OpenCL repositories into a single repository called clr. Instructions are updated to build HIP from sources in the HIP Installation guide
+- Removed hipBusBandwidth and hipCommander samples from hip-tests
+
+##### Fixed
+
+- Fixed regression in hipMemCpyParam3D when offset is applied
+
+##### Known Issues
+
+- Limited testing on xnack+ configuration
+  - Multiple HIP tests failures (gpuvm fault or hangs)
+- hipSetDevice and hipSetDeviceFlags APIs return hipErrorInvalidDevice instead of hipErrorNoDevice, on a system without GPU
+- Known memory leak when code object files are loaded/unloaded via hipModuleLoad/hipModuleUnload APIs. Issue will be fixed in a future ROCm release
+
+##### Upcoming changes in future release
+
+- Removal of gcnarch from hipDeviceProp_t structure
+- Addition of new fields in hipDeviceProp_t structure
+  - maxTexture1D
+  - maxTexture2D
+  - maxTexture1DLayered
+  - maxTexture2DLayered
+  - sharedMemPerMultiprocessor
+  - deviceOverlap
+  - asyncEngineCount
+  - surfaceAlignment
+  - unifiedAddressing
+  - computePreemptionSupported
+  - uuid
+- Removal of deprecated code
+  - hip-hcc codes from hip code tree
+- Correct hipArray usage in HIP APIs such as hipMemcpyAtoH and hipMemcpyHtoA
+- HIPMEMCPY_3D fields correction (unsigned int -> size_t)
+- Renaming of 'memoryType' in hipPointerAttribute_t structure to 'type'
+
+#### ROCgdb-13 (For ROCm 5.6.0)
+
+##### Optimized
+
+- Improved performances when handling the end of a process with a large number of threads.
+
+Known Issues
+
+- On certain configurations, ROCgdb can show the following warning message:
+
+  `warning: Probes-based dynamic linker interface failed. Reverting to original interface.`
+
+  This does not affect ROCgdb's functionalities.
+
+#### ROCprofiler (For ROCm 5.6.0)
+
+In ROCm 5.6 the `rocprofilerv1` and `rocprofilerv2` include and library files of
+ROCm 5.5 are split into separate files. The `rocmtools` files that were
+deprecated in ROCm 5.5 have been removed.
+
+  | ROCm 5.6        | rocprofilerv1                       | rocprofilerv2                          |
+  |-----------------|-------------------------------------|----------------------------------------|
+  | **Tool script** | `bin/rocprof`                       | `bin/rocprofv2`                        |
+  | **API include** | `include/rocprofiler/rocprofiler.h` | `include/rocprofiler/v2/rocprofiler.h` |
+  | **API library** | `lib/librocprofiler.so.1`           | `lib/librocprofiler.so.2`              |
+
+The ROCm Profiler Tool that uses `rocprofilerV1` can be invoked using the
+following command:
+
+```sh
+$ rocprof …
+```
+
+To write a custom tool based on the `rocprofilerV1` API do the following:
+
+```C
+main.c:
+#include <rocprofiler/rocprofiler.h> // Use the rocprofilerV1 API
+int main() {
+  // Use the rocprofilerV1 API
+  return 0;
+}
+```
+
+This can be built in the following manner:
+
+```sh
+$ gcc main.c -I/opt/rocm-5.6.0/include -L/opt/rocm-5.6.0/lib -lrocprofiler64
+```
+
+The resulting `a.out` will depend on
+`/opt/rocm-5.6.0/lib/librocprofiler64.so.1`.
+
+The ROCm Profiler that uses `rocprofilerV2` API can be invoked using the
+following command:
+
+```sh
+$ rocprofv2 …
+```
+
+To write a custom tool based on the `rocprofilerV2` API do the following:
+
+```C
+main.c:
+#include <rocprofiler/v2/rocprofiler.h> // Use the rocprofilerV2 API
+int main() {
+  // Use the rocprofilerV2 API
+  return 0;
+}
+```
+
+This can be built in the following manner:
+
+```sh
+$ gcc main.c -I/opt/rocm-5.6.0/include -L/opt/rocm-5.6.0/lib -lrocprofiler64-v2
+```
+
+The resulting `a.out` will depend on
+`/opt/rocm-5.6.0/lib/librocprofiler64.so.2`.
+
+##### Optimized
+
+- Improved Test Suite
+
+##### Added
+
+- 'end_time' need to be disabled in roctx_trace.txt
+
+##### Fixed
+
+- rocprof in ROcm/5.4.0 gpu selector broken.
+- rocprof in ROCm/5.4.1 fails to generate kernel info.
+- rocprof clobbers LD_PRELOAD.
+
+### Library Changes in ROCM 5.6.0
+
+| Library | Version |
+|---------|---------|
+| hipBLAS |  ⇒ [1.0.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.6.0) |
+| hipCUB |  ⇒ [2.13.1](https://github.com/ROCmSoftwarePlatform/hipCUB/releases/tag/rocm-5.6.0) |
+| hipFFT |  ⇒ [1.0.12](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.6.0) |
+| hipSOLVER |  ⇒ [1.8.0](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.6.0) |
+| hipSPARSE |  ⇒ [2.3.6](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.6.0) |
+| MIOpen |  ⇒ [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.6.0) |
+| rccl |  ⇒ [2.15.5](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.6.0) |
+| rocALUTION |  ⇒ [2.1.9](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.6.0) |
+| rocBLAS |  ⇒ [3.0.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.6.0) |
+| rocFFT |  ⇒ [1.0.23](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.6.0) |
+| rocm-cmake |  ⇒ [0.9.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.6.0) |
+| rocPRIM |  ⇒ [2.13.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.6.0) |
+| rocRAND |  ⇒ [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.6.0) |
+| rocSOLVER |  ⇒ [3.22.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.6.0) |
+| rocSPARSE |  ⇒ [2.5.2](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.6.0) |
+| rocThrust |  ⇒ [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.6.0) |
+| rocWMMA |  ⇒ [1.1.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.6.0) |
+| Tensile |  ⇒ [4.37.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.6.0) |
+
+#### hipBLAS 1.0.0
+
+hipBLAS 1.0.0 for ROCm 5.6.0
+
+##### Changed
+
+- added const qualifier to hipBLAS functions (swap, sbmv, spmv, symv, trsm) where missing
+
+##### Removed
+
+- removed support for deprecated hipblasInt8Datatype_t enum
+- removed support for deprecated hipblasSetInt8Datatype and hipblasGetInt8Datatype functions
+
+##### Deprecated
+
+- in-place trmm is deprecated. It will be replaced by trmm which includes both in-place and
+  out-of-place functionality
+
+#### hipCUB 2.13.1
+
+hipCUB 2.13.1 for ROCm 5.6.0
+
+##### Added
+
+- Benchmarks for `BlockShuffle`, `BlockLoad`, and `BlockStore`.
+
+##### Changed
+
+- CUB backend references CUB and Thrust version 1.17.2.
+- Improved benchmark coverage of `BlockScan` by adding `ExclusiveScan`, benchmark coverage of `BlockRadixSort` by adding `SortBlockedToStriped`, and benchmark coverage of `WarpScan` by adding `Broadcast`.
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core).
+
+##### Known Issues
+
+- `BlockRadixRankMatch` is currently broken under the rocPRIM backend.
+- `BlockRadixRankMatch` with a warp size that does not exactly divide the block size is broken under the CUB backend.
+
+#### hipFFT 1.0.12
+
+hipFFT 1.0.12 for ROCm 5.6.0
+
+##### Added
+
+- Implemented the hipfftXtMakePlanMany, hipfftXtGetSizeMany, hipfftXtExec APIs, to allow requesting half-precision transforms.
+
+##### Changed
+
+- Added --precision argument to benchmark/test clients.  --double is still accepted but is deprecated as a method to request a double-precision transform.
+
+#### hipSOLVER 1.8.0
+
+hipSOLVER 1.8.0 for ROCm 5.6.0
+
+##### Added
+
+- Added compatibility API with hipsolverRf prefix
+
+#### hipSPARSE 2.3.6
+
+hipSPARSE 2.3.6 for ROCm 5.6.0
+
+##### Added
+
+- Added SpGEMM algorithms
+
+##### Changed
+
+- For hipsparseXbsr2csr and hipsparseXcsr2bsr, blockDim == 0 now returns HIPSPARSE_STATUS_INVALID_SIZE
+
+#### MIOpen 2.19.0
+
+MIOpen 2.19.0 for ROCm 5.6.0
+
+##### Added
+
+- ROCm 5.5 support for gfx1101 (Navi32)
+
+##### Changed
+
+- Tuning results for MLIR on ROCm 5.5
+- Bumping MLIR commit to 5.5.0 release tag
+
+##### Fixed
+
+- Fix 3d convolution Host API bug
+- [HOTFIX][MI200][FP16] Disabled ConvHipImplicitGemmBwdXdlops when FP16_ALT is required.
+
+#### rccl 2.15.5
+
+RCCL 2.15.5 for ROCm 5.6.0
+
+##### Changed
+
+- Compatibility with NCCL 2.15.5
+- Unit test executable renamed to rccl-UnitTests
+
+##### Added
+
+- HW-topology aware binary tree implementation
+- Experimental support for MSCCL
+- New unit tests for hipGraph support
+- NPKit integration
+
+##### Fixed
+
+- rocm-smi ID conversion
+- Support for HIP_VISIBLE_DEVICES for unit tests
+- Support for p2p transfers to non (HIP) visible devices
+
+##### Removed
+
+- Removed TransferBench from tools.  Exists in standalone repo: https://github.com/ROCmSoftwarePlatform/TransferBench
+
+#### rocALUTION 2.1.9
+
+rocALUTION 2.1.9 for ROCm 5.6.0
+
+##### Improved
+
+- Fixed synchronization issues in level 1 routines
+
+#### rocBLAS 3.0.0
+
+rocBLAS 3.0.0 for ROCm 5.6.0
+
+##### Optimizations
+
+- Improved performance of Level 2 rocBLAS GEMV on gfx90a GPU for non-transposed problems having small matrices and larger batch counts. Performance enhanced for problem sizes when m and n &lt;= 32 and batch_count &gt;= 256.
+- Improved performance of rocBLAS syr2k for single, double, and double-complex precision, and her2k for double-complex precision. Slightly improved performance for general sizes on gfx90a.
+
+##### Added
+
+- Added bf16 inputs and f32 compute support to Level 1 rocBLAS Extension functions axpy_ex, scal_ex and nrm2_ex.
+
+##### Deprecated
+
+- trmm inplace is deprecated. It will be replaced by trmm that has both inplace and out-of-place functionality
+- rocblas_query_int8_layout_flag() is deprecated and will be removed in a future release
+- rocblas_gemm_flags_pack_int8x4 enum is deprecated and will be removed in a future release
+- rocblas_set_device_memory_size() is deprecated and will be replaced by a future function rocblas_increase_device_memory_size()
+- rocblas_is_user_managing_device_memory() is deprecated and will be removed in a future release
+
+##### Removed
+
+- is_complex helper was deprecated and now removed.  Use rocblas_is_complex instead.
+- The enum truncate_t and the value truncate was deprecated and now removed from. It was replaced by rocblas_truncate_t and rocblas_truncate, respectively.
+- rocblas_set_int8_type_for_hipblas was deprecated and is now removed.
+- rocblas_get_int8_type_for_hipblas was deprecated and is now removed.
+
+##### Dependencies
+
+- build only dependency on python joblib added as used by Tensile build
+- fix for cmake install on some OS when performed by install.sh -d --cmake_install
+
+##### Fixed
+
+- make trsm offset calculations 64 bit safe
+
+##### Changed
+
+- refactor rotg test code
+
+#### rocFFT 1.0.23
+
+rocFFT 1.0.23 for ROCm 5.6.0
+
+##### Added
+
+- Implemented half-precision transforms, which can be requested by passing rocfft_precision_half to rocfft_plan_create.
+- Implemented a hierarchical solution map which saves how to decompose a problem and the kernels to be used.
+- Implemented a first version of offline-tuner to support tuning kernels for C2C/Z2Z problems.
+
+##### Changed
+
+- Replaced std::complex with hipComplex data types for data generator.
+- FFT plan dimensions are now sorted to be row-major internally where possible, which produces better plans if the dimensions were accidentally specified in a different order (column-major, for example).
+- Added --precision argument to benchmark/test clients.  --double is still accepted but is deprecated as a method to request a double-precision transform.
+
+##### Fixed
+
+- Fixed over-allocation of LDS in some real-complex kernels, which was resulting in kernel launch failure.
+
+#### rocm-cmake 0.9.0
+
+rocm-cmake 0.9.0 for ROCm 5.6.0
+
+##### Added
+
+- Added the option ROCM_HEADER_WRAPPER_WERROR
+    - Compile-time C macro in the wrapper headers causes errors to be emitted instead of warnings.
+    - Configure-time CMake option sets the default for the C macro.
+
+#### rocPRIM 2.13.0
+
+rocPRIM 2.13.0 for ROCm 5.6.0
+
+##### Added
+
+- New block level `radix_rank` primitive.
+- New block level `radix_rank_match` primitive.
+- Added a stable block sorting implementation. This be used with `block_sort` by using the `block_sort_algorithm::stable_merge_sort` algorithm.
+
+##### Changed
+
+- Improved the performance of `block_radix_sort` and `device_radix_sort`.
+- Improved the performance of `device_merge_sort`.
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core). Contributed by: [v01dXYZ](https://github.com/v01dXYZ).
+
+##### Known Issues
+
+- Disabled GPU error messages relating to incorrect warp operation usage with Navi GPUs on Windows, due to GPU printf performance issues on Windows.
+- When `ROCPRIM_DISABLE_LOOKBACK_SCAN` is set, `device_scan` fails for input sizes bigger than `scan_config::size_limit`, which defaults to `std::numeric_limits&lt;unsigned int&gt;::max()`.
+
+#### rocRAND 2.10.17
+
+rocRAND 2.10.17 for ROCm 5.6.0
+
+##### Added
+
+- MT19937 pseudo random number generator based on M. Matsumoto and T. Nishimura, 1998, Mersenne Twister: A 623-dimensionally equidistributed uniform pseudorandom number generator.
+- New benchmark for the device API using Google Benchmark, `benchmark_rocrand_device_api`, replacing `benchmark_rocrand_kernel`. `benchmark_rocrand_kernel` is deprecated and will be removed in a future version. Likewise, `benchmark_curand_host_api` is added to replace `benchmark_curand_generate` and `benchmark_curand_device_api` is added to replace `benchmark_curand_kernel`.
+- experimental HIP-CPU feature
+- ThreeFry pseudorandom number generator based on Salmon et al., 2011, &#34;Parallel random numbers: as easy as 1, 2, 3&#34;.
+
+##### Changed
+
+- Python 2.7 is no longer officially supported.
+
+#### rocSOLVER 3.22.0
+
+rocSOLVER 3.22.0 for ROCm 5.6.0
+
+##### Added
+
+- LU refactorization for sparse matrices
+    - CSRRF_ANALYSIS
+    - CSRRF_SUMLU
+    - CSRRF_SPLITLU
+    - CSRRF_REFACTLU
+- Linear system solver for sparse matrices
+    - CSRRF_SOLVE
+- Added type `rocsolver_rfinfo` for use with sparse matrix routines
+
+##### Optimized
+
+- Improved the performance of BDSQR and GESVD when singular vectors are requested
+
+##### Fixed
+
+- BDSQR and GESVD should no longer hang when the input contains `NaN` or `Inf`
+
+#### rocSPARSE 2.5.2
+
+rocSPARSE 2.5.2 for ROCm 5.6.0
+
+##### Improved
+
+- Fixed a memory leak in csritsv
+- Fixed a bug in csrsm and bsrsm
+
+#### rocThrust 2.18.0
+
+rocThrust 2.18.0 for ROCm 5.6.0
+
+##### Fixed 
+
+- `lower_bound`, `upper_bound`, and `binary_search` failed to compile for certain types.
+
+##### Changed
+
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core).
+
+#### rocWMMA 1.1.0
+
+rocWMMA 1.1.0 for ROCm 5.6.0
+
+##### Added
+
+- Added cross-lane operation backends (Blend, Permute, Swizzle and Dpp)
+- Added GPU kernels for rocWMMA unit test pre-process and post-process operations (fill, validation)
+- Added performance gemm samples for half, single and double precision
+- Added rocWMMA cmake versioning
+- Added vectorized support in coordinate transforms
+- Included ROCm smi for runtime clock rate detection
+- Added fragment transforms for transpose and change data layout
+
+##### Changed
+
+- Default to GPU rocBLAS validation against rocWMMA
+- Re-enabled int8 gemm tests on gfx9
+- Upgraded to C++17
+- Restructured unit test folder for consistency
+- Consolidated rocWMMA samples common code
+
+#### Tensile 4.37.0
+
+Tensile 4.37.0 for ROCm 5.6.0
+
+##### Added
+
+- Added user driven tuning API
+- Added decision tree fallback feature
+- Added SingleBuffer + AtomicAdd option for GlobalSplitU
+- DirectToVgpr support for fp16 and Int8 with TN orientation
+- Added new test cases for various functions
+- Added SingleBuffer algorithm for ZGEMM/CGEMM
+- Added joblib for parallel map calls
+- Added support for MFMA + LocalSplitU + DirectToVgprA+B
+- Added asmcap check for MIArchVgpr
+- Added support for MFMA + LocalSplitU
+- Added frequency, power, and temperature data to the output
+
+##### Optimizations
+
+- Improved the performance of GlobalSplitU with SingleBuffer algorithm
+- Reduced the running time of the extended and pre_checkin tests
+- Optimized the Tailloop section of the assembly kernel
+- Optimized complex GEMM (fixed vgpr allocation, unified CGEMM and ZGEMM code in MulMIoutAlphaToArch)
+- Improved the performance of the second kernel of MultipleBuffer algorithm
+
+##### Changed
+
+- Updated custom kernels with 64-bit offsets
+- Adapted 64-bit offset arguments for assembly kernels
+- Improved temporary register re-use to reduce max sgpr usage
+- Removed some restrictions on VectorWidth and DirectToVgpr
+- Updated the dependency requirements for Tensile
+- Changed the range of AssertSummationElementMultiple
+- Modified the error messages for more clarity
+- Changed DivideAndReminder to vectorStaticRemainder in case quotient is not used
+- Removed dummy vgpr for vectorStaticRemainder
+- Removed tmpVgpr parameter from vectorStaticRemainder/Divide/DivideAndReminder
+- Removed qReg parameter from vectorStaticRemainder
+
+##### Fixed
+
+- Fixed tmp sgpr allocation to avoid over-writing values (alpha)
+- 64-bit offset parameters for post kernels
+- Fixed gfx908 CI test failures
+- Fixed offset calculation to prevent overflow for large offsets
+- Fixed issues when BufferLoad and BufferStore are equal to zero
+- Fixed StoreCInUnroll + DirectToVgpr + no useInitAccVgprOpt mismatch
+- Fixed DirectToVgpr + LocalSplitU + FractionalLoad mismatch
+- Fixed the memory access error related to StaggerU + large stride
+- Fixed ZGEMM 4x4 MatrixInst mismatch
+- Fixed DGEMM 4x4 MatrixInst mismatch
+- Fixed ASEM + GSU + NoTailLoop opt mismatch
+- Fixed AssertSummationElementMultiple + GlobalSplitU issues
+- Fixed ASEM + GSU + TailLoop inner unroll

default.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="roc-github"
-fetch="http://github.com/RadeonOpenCompute/" />
+fetch="https://github.com/RadeonOpenCompute/" />
     <remote name="rocm-devtools"
 fetch="https://github.com/ROCm-Developer-Tools/" />
     <remote name="rocm-swplat"
@@ -12,35 +12,34 @@ fetch="https://github.com/GPUOpen-ProfessionalCompute-Libraries/" />
 fetch="https://github.com/GPUOpen-Tools/" />
     <remote name="KhronosGroup"
 fetch="https://github.com/KhronosGroup/" />
-    <default revision="refs/tags/rocm-4.1.0"
+    <default revision="refs/tags/rocm-5.6.0"
      remote="roc-github"
      sync-c="true"
      sync-j="4" />
 <!--list of projects for ROCM-->
-    <project name="ROCK-Kernel-Driver" />
-    <project name="ROCT-Thunk-Interface" />
-    <project name="ROCR-Runtime" />
-    <project name="ROC-smi" />
-    <project name="rocm_smi_lib" />
-    <project name="rocm-cmake" />
-    <project name="rocminfo" />
+    <project name="ROCK-Kernel-Driver" remote="roc-github" />
+    <project name="ROCT-Thunk-Interface" remote="roc-github" />
+    <project name="ROCR-Runtime" remote="roc-github" />
+    <project name="rocm_smi_lib" remote="roc-github" />
+    <project name="rocm-core" remote="roc-github" />
+    <project name="rocm-cmake" remote="roc-github" />
+    <project name="rocminfo" remote="roc-github" />
     <project name="rocprofiler" remote="rocm-devtools" />
     <project name="roctracer" remote="rocm-devtools" />
-    <project name="ROCm-OpenCL-Runtime" />
     <project path="ROCm-OpenCL-Runtime/api/opencl/khronos/icd" name="OpenCL-ICD-Loader" remote="KhronosGroup" revision="6c03f8b58fafd9dd693eaac826749a5cfad515f8" />
-    <project name="clang-ocl" />
+    <project name="clang-ocl" remote="roc-github" />
 <!--HIP Projects-->
     <project name="HIP" remote="rocm-devtools" />
+    <project name="clr" remote="rocm-devtools" />
     <project name="HIP-Examples" remote="rocm-devtools" />
-    <project name="ROCclr" remote="rocm-devtools" />
     <project name="HIPIFY" remote="rocm-devtools" />
+    <project name="HIPCC" remote="rocm-devtools" />
 <!-- The following projects are all associated with the AMDGPU LLVM compiler -->
-    <project name="llvm-project" />
-    <project name="ROCm-Device-Libs" />
-    <project name="atmi" />
-    <project name="ROCm-CompilerSupport" />
+    <project name="llvm-project" remote="roc-github" />
+    <project name="ROCm-Device-Libs" remote="roc-github" />
+    <project name="ROCm-CompilerSupport" remote="roc-github" />
     <project name="rocr_debug_agent" remote="rocm-devtools" />
-    <project name="rocm_bandwidth_test" />
+    <project name="rocm_bandwidth_test" remote="roc-github" />
     <project name="half" remote="rocm-swplat" revision="37742ce15b76b44e4b271c1e66d13d2fa7bd003e" />
     <project name="RCP" remote="gpuopen-tools" revision="3a49405a1500067c49d181844ec90aea606055bb" />
 <!-- gdb projects -->
@@ -48,22 +47,24 @@ fetch="https://github.com/KhronosGroup/" />
     <project name="ROCdbgapi" remote="rocm-devtools" />
 <!-- ROCm Libraries -->
     <project name="rdc" remote="roc-github" />
-    <project name="rocBLAS" remote="rocm-swplat" />
-    <project name="Tensile" remote="rocm-swplat" />
-    <project name="hipBLAS" remote="rocm-swplat" />
-    <project name="rocFFT" remote="rocm-swplat" />
-    <project name="rocRAND" remote="rocm-swplat" />
-    <project name="rocSPARSE" remote="rocm-swplat" />
-    <project name="rocSOLVER" remote="rocm-swplat" />
-    <project name="hipSPARSE" remote="rocm-swplat" />
-    <project name="rocALUTION" remote="rocm-swplat" />
-    <project name="MIOpenGEMM" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocBLAS" remote="rocm-swplat" />
+    <project groups="mathlibs" name="Tensile" remote="rocm-swplat" />
+    <project groups="mathlibs" name="hipBLAS" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocFFT" remote="rocm-swplat" />
+    <project groups="mathlibs" name="hipFFT" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocRAND" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocSPARSE" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocSOLVER" remote="rocm-swplat" />
+    <project groups="mathlibs" name="hipSOLVER" remote="rocm-swplat" />
+    <project groups="mathlibs" name="hipSPARSE" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocALUTION" remote="rocm-swplat" />
     <project name="MIOpen" remote="rocm-swplat" />
-    <project name="rccl" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rccl" remote="rocm-swplat" />
     <project name="MIVisionX" remote="gpuopen-libs" />
-    <project name="rocThrust" remote="rocm-swplat" />
-    <project name="hipCUB" remote="rocm-swplat" />
-    <project name="rocPRIM" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocThrust" remote="rocm-swplat" />
+    <project groups="mathlibs" name="hipCUB" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocPRIM" remote="rocm-swplat" />
+    <project groups="mathlibs" name="rocWMMA" remote="rocm-swplat" />
     <project name="hipfort" remote="rocm-swplat" />
     <project name="AMDMIGraphX" remote="rocm-swplat" />
     <project name="ROCmValidationSuite" remote="rocm-devtools" />

docs/404.md

@@ -0,0 +1,6 @@
+# 404 Page Not Found
+
+Page could not be found.
+
+Return to [home](./index) or please use the links from the sidebar to find what
+you are looking for.

docs/about.md

@@ -0,0 +1,74 @@
+# About ROCm Documentation
+
+ROCm documentation is made available under open source [licenses](licensing.md).
+Documentation is built using open source toolchains. Contributions to our
+documentation is encouraged and welcome. As a contributor, please familiarize
+yourself with our documentation toolchain.
+
+## Read The Docs
+
+[Read the Docs](https://docs.readthedocs.io/en/stable/) is our front end for the
+our documentation. By front end, this is the tool that serves our HTML based
+documentation to our end users.
+
+## Doxygen
+
+[Doxygen](https://www.doxygen.nl/) is the most common inline code documentation
+standard. ROCm projects are use Doxygen for public API documentation (unless the
+upstream project is using a different tool).
+
+## Sphinx
+
+[Sphinx](https://www.sphinx-doc.org/en/master/) is a documentation generator
+originally used for python. It is now widely used in the Open Source community.
+Originally, sphinx supported RST based documentation. Markdown support is now
+available. ROCm documentation plans to default to markdown for new projects.
+Existing projects using RST are under no obligation to convert to markdown. New
+projects that believe markdown is not suitable should contact the documentation
+team prior to selecting RST.
+
+### MyST
+
+[Markedly Structured Text (MyST)](https://myst-tools.org/docs/spec) is an extended
+flavor of Markdown ([CommonMark](https://commonmark.org/)) influenced by reStructuredText (RST) and Sphinx.
+It is integrated via [`myst-parser`](https://myst-parser.readthedocs.io/en/latest/).
+A cheat sheet that showcases how to use the MyST syntax is available over at [the Jupyter
+reference](https://jupyterbook.org/en/stable/reference/cheatsheet.html).
+
+### Sphinx Theme
+
+ROCm is using the
+[Sphinx Book Theme](https://sphinx-book-theme.readthedocs.io/en/latest/). This
+theme is used by Jupyter books. ROCm documentation applies some customization
+include a header and footer on top of the Sphinx Book Theme. A future custom
+ROCm theme will be part of our documentation goals.
+
+### Sphinx Design
+
+Sphinx Design is an extension for sphinx based websites that add design
+functionality. Please see the documentation
+[here](https://sphinx-design.readthedocs.io/en/latest/index.html). ROCm
+documentation uses sphinx design for grids, cards, and synchronized tabs.
+Other features may be used in the future.
+
+### Sphinx External TOC
+
+ROCm uses the
+[sphinx-external-toc](https://sphinx-external-toc.readthedocs.io/en/latest/intro.html)
+for our navigation. This tool allows a YAML file based left navigation menu. This
+tool was selected due to its flexibility that allows scripts to operate on the
+YAML file. Please transition to this file for the project's navigation. You can
+see the `_toc.yml.in` file in this repository in the docs/sphinx folder for an
+example.
+
+### Breathe
+
+Sphinx uses [Breathe](https://www.breathe-doc.org/) to integrate Doxygen
+content.
+
+## `rocm-docs-core` pip package
+
+[rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) is an AMD
+maintained project that applies customization for our documentation. This
+project is the tool most ROCm repositories will use as part of the documentation
+build.

docs/conf.py

@@ -0,0 +1,98 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+import shutil
+
+from rocm_docs import ROCmDocs
+
+
+shutil.copy2('../CONTRIBUTING.md','./contributing.md')
+shutil.copy2('../RELEASE.md','./release.md')
+# Keep capitalization due to similar linking on GitHub's markdown preview.
+shutil.copy2('../CHANGELOG.md','./CHANGELOG.md')
+
+latex_engine = "xelatex"
+
+# configurations for PDF output by Read the Docs
+project = "ROCm Documentation"
+author = "Advanced Micro Devices, Inc."
+copyright = "Copyright (c) 2023 Advanced Micro Devices, Inc. All rights reserved."
+version = "5.6.0"
+release = "5.6.0"
+
+
+setting_all_article_info = True
+all_article_info_os = ["linux", "windows"]
+all_article_info_author = ""
+
+# pages with specific settings
+article_pages = [
+    {
+        "file":"release",
+        "os":["linux", "windows"],
+        "date":"2023-07-27"
+    },
+
+    {"file":"deploy/linux/index", "os":["linux"]},
+    {"file":"deploy/linux/install_overview", "os":["linux"]},
+    {"file":"deploy/linux/prerequisites", "os":["linux"]},
+    {"file":"deploy/linux/quick_start", "os":["linux"]},
+    {"file":"deploy/linux/install", "os":["linux"]},
+    {"file":"deploy/linux/upgrade", "os":["linux"]},
+    {"file":"deploy/linux/uninstall", "os":["linux"]},
+    {"file":"deploy/linux/package_manager_integration", "os":["linux"]},
+    {"file":"deploy/docker", "os":["linux"]},
+    
+    {"file":"deploy/windows/cli/index", "os":["windows"]},
+    {"file":"deploy/windows/cli/install", "os":["windows"]},
+    {"file":"deploy/windows/cli/uninstall", "os":["windows"]},
+    {"file":"deploy/windows/cli/upgrade", "os":["windows"]},
+    {"file":"deploy/windows/gui/index", "os":["windows"]},
+    {"file":"deploy/windows/gui/install", "os":["windows"]},
+    {"file":"deploy/windows/gui/uninstall", "os":["windows"]},
+    {"file":"deploy/windows/gui/upgrade", "os":["windows"]},
+    {"file":"deploy/windows/index", "os":["windows"]},
+    {"file":"deploy/windows/prerequisites", "os":["windows"]},
+    {"file":"deploy/windows/quick_start", "os":["windows"]},
+
+    {"file":"release/gpu_os_support", "os":["linux"]},
+    {"file":"release/windows_support", "os":["windows"]},
+    {"file":"release/docker_support_matrix", "os":["linux"]},
+    
+    {"file":"reference/gpu_libraries/communication", "os":["linux"]},
+    {"file":"reference/ai_tools", "os":["linux"]},
+    {"file":"reference/management_tools", "os":["linux"]},
+    {"file":"reference/validation_tools", "os":["linux"]},
+    {"file":"reference/framework_compatibility/framework_compatibility", "os":["linux"]},
+    {"file":"reference/computer_vision", "os":["linux"]},
+    
+    {"file":"how_to/deep_learning_rocm", "os":["linux"]},
+    {"file":"how_to/gpu_aware_mpi", "os":["linux"]},
+    {"file":"how_to/magma_install/magma_install", "os":["linux"]},
+    {"file":"how_to/pytorch_install/pytorch_install", "os":["linux"]},
+    {"file":"how_to/system_debugging", "os":["linux"]},
+    {"file":"how_to/tensorflow_install/tensorflow_install", "os":["linux"]},
+
+    {"file":"examples/machine_learning", "os":["linux"]},
+    {"file":"examples/inception_casestudy/inception_casestudy", "os":["linux"]},
+    
+    {"file":"understand/file_reorg", "os":["linux"]},
+
+    {"file":"understand/isv_deployment_win", "os":["windows"]},
+]
+
+external_toc_path = "./sphinx/_toc.yml"
+
+docs_core = ROCmDocs("ROCm 5.6.0 Documentation Home")
+docs_core.setup()
+
+external_projects_current_project = "rocm"
+
+for sphinx_var in ROCmDocs.SPHINX_VARS:
+    globals()[sphinx_var] = getattr(docs_core, sphinx_var)
+html_theme_options = {
+    "link_main_doc": False
+}