From 57ad953d7bc1b0dbdf92950982cf54e3e42ac1f2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?M=C3=A9sz=C3=A1ros=20Gergely?= <maetveis@gmail.com>
Date: Wed, 19 Apr 2023 05:49:28 +0200
Subject: [PATCH 1/3] Doxysphinx docs (#3192)

* Reorganize documenation based on rocm-docs-core

* Move build, install and contributing guides to docs

* Bump readthedocs config to Ubuntu 20.04

* Add more direct links to the API modules

* Pin rocm-docs-core version, add dependabot

- Use the pip package to have rocm-docs-core pinned
- Add dependabot config to update pinned packages (including rocm-docs-core)

* fixup! Add more direct links to the API modules

---------


[ROCm/hip commit: ae5f8714f4c1c1c3350bd510b283c4f954e3b645]
---
 projects/hip/.github/dependabot.yml           |   12 +
 projects/hip/.readthedocs.yaml                |   21 +
 .../doxy.cfg => .doxygen/Doxyfile}            |  106 +-
 projects/hip/docs/.doxygen/mainpage.md        |   33 +
 projects/hip/docs/.gitignore                  |    5 +
 projects/hip/docs/.sphinx/_toc.yml.in         |   24 +
 projects/hip/docs/.sphinx/requirements.in     |    1 +
 projects/hip/docs/.sphinx/requirements.txt    |  290 +++++
 projects/hip/docs/conf.py                     |   26 +
 .../hip_build.md => developer_guide/build.md} |  133 +-
 .../developer_guide/contributing.md}          |   33 +-
 .../logging.md}                               |   90 +-
 .../hip/docs/{markdown => }/device_md_gen.py  |    0
 projects/hip/docs/doxygen-input/mainpage.txt  |   19 -
 projects/hip/docs/doxygen-input/sync.txt      |   49 -
 .../{markdown => }/gen_clang_option_doc.sh    |    0
 .../debugging.md}                             |   29 +-
 .../how_to_guides/install.md}                 |   17 +-
 projects/hip/docs/index.md                    |   37 +
 ...A_Driver_API_functions_supported_by_HIP.md |    1 -
 ..._Runtime_API_functions_supported_by_HIP.md | 1121 -----------------
 projects/hip/docs/markdown/clang_options.md   |  763 -----------
 projects/hip/docs/markdown/clang_options.txt  |  758 -----------
 .../cuComplex_API_supported_by_HIP.md         |   37 -
 projects/hip/docs/markdown/hip_bugs.md        |  172 ---
 .../docs/markdown/hip_porting_driver_api.md   |  287 -----
 .../hip/docs/markdown/hip_porting_guide.md    |  597 ---------
 .../hip/docs/markdown/modern_cpp_features.md  |  468 -------
 projects/hip/docs/markdown/obj_tooling.md     |   92 --
 .../deprecated_api_list.md}                   |    2 +-
 .../hip_terms2.md => reference/glossary.md}   |    0
 .../kernel_language.md}                       |   94 +-
 .../hip-math-api.md => reference/math_api.md} |    0
 .../hip_terms.md => reference/terms.md}       |    0
 .../hip_faq.md => user_guide/faq.md}          |  109 +-
 .../docs/{markdown => user_guide}/hip_rtc.md  |    0
 .../programming_manual.md}                    |    4 +-
 37 files changed, 704 insertions(+), 4726 deletions(-)
 create mode 100644 projects/hip/.github/dependabot.yml
 create mode 100644 projects/hip/.readthedocs.yaml
 rename projects/hip/docs/{doxygen-input/doxy.cfg => .doxygen/Doxyfile} (98%)
 create mode 100644 projects/hip/docs/.doxygen/mainpage.md
 create mode 100644 projects/hip/docs/.gitignore
 create mode 100644 projects/hip/docs/.sphinx/_toc.yml.in
 create mode 100644 projects/hip/docs/.sphinx/requirements.in
 create mode 100644 projects/hip/docs/.sphinx/requirements.txt
 create mode 100644 projects/hip/docs/conf.py
 rename projects/hip/docs/{markdown/hip_build.md => developer_guide/build.md} (64%)
 rename projects/hip/{CONTRIBUTING.md => docs/developer_guide/contributing.md} (85%)
 rename projects/hip/docs/{markdown/hip_logging.md => developer_guide/logging.md} (76%)
 rename projects/hip/docs/{markdown => }/device_md_gen.py (100%)
 delete mode 100644 projects/hip/docs/doxygen-input/mainpage.txt
 delete mode 100644 projects/hip/docs/doxygen-input/sync.txt
 rename projects/hip/docs/{markdown => }/gen_clang_option_doc.sh (100%)
 rename projects/hip/docs/{markdown/hip_debugging.md => how_to_guides/debugging.md} (95%)
 rename projects/hip/{INSTALL.md => docs/how_to_guides/install.md} (83%)
 create mode 100644 projects/hip/docs/index.md
 delete mode 100644 projects/hip/docs/markdown/CUDA_Driver_API_functions_supported_by_HIP.md
 delete mode 100644 projects/hip/docs/markdown/CUDA_Runtime_API_functions_supported_by_HIP.md
 delete mode 100644 projects/hip/docs/markdown/clang_options.md
 delete mode 100644 projects/hip/docs/markdown/clang_options.txt
 delete mode 100644 projects/hip/docs/markdown/cuComplex_API_supported_by_HIP.md
 delete mode 100644 projects/hip/docs/markdown/hip_bugs.md
 delete mode 100644 projects/hip/docs/markdown/hip_porting_driver_api.md
 delete mode 100644 projects/hip/docs/markdown/hip_porting_guide.md
 delete mode 100644 projects/hip/docs/markdown/modern_cpp_features.md
 delete mode 100644 projects/hip/docs/markdown/obj_tooling.md
 rename projects/hip/docs/{markdown/hip_deprecated_api_list.md => reference/deprecated_api_list.md} (98%)
 rename projects/hip/docs/{markdown/hip_terms2.md => reference/glossary.md} (100%)
 rename projects/hip/docs/{markdown/hip_kernel_language.md => reference/kernel_language.md} (94%)
 rename projects/hip/docs/{markdown/hip-math-api.md => reference/math_api.md} (100%)
 rename projects/hip/docs/{markdown/hip_terms.md => reference/terms.md} (100%)
 rename projects/hip/docs/{markdown/hip_faq.md => user_guide/faq.md} (76%)
 rename projects/hip/docs/{markdown => user_guide}/hip_rtc.md (100%)
 rename projects/hip/docs/{markdown/hip_programming_guide.md => user_guide/programming_manual.md} (99%)

diff --git a/projects/hip/.github/dependabot.yml b/projects/hip/.github/dependabot.yml
new file mode 100644
index 0000000000..9cdf2d670c
--- /dev/null
+++ b/projects/hip/.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"
diff --git a/projects/hip/.readthedocs.yaml b/projects/hip/.readthedocs.yaml
new file mode 100644
index 0000000000..1240c9c525
--- /dev/null
+++ b/projects/hip/.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
+
+sphinx:
+   configuration: docs/conf.py
+
+formats: [htmlzip]
+
+python:
+   install:
+   - requirements: docs/.sphinx/requirements.txt
+
+build:
+   os: ubuntu-20.04
+   tools:
+      python: "3.8"
+   apt_packages:
+     - "doxygen"
+     - "graphviz" # For dot graphs in doxygen
diff --git a/projects/hip/docs/doxygen-input/doxy.cfg b/projects/hip/docs/.doxygen/Doxyfile
similarity index 98%
rename from projects/hip/docs/doxygen-input/doxy.cfg
rename to projects/hip/docs/.doxygen/Doxyfile
index 16c2c900b6..7f89f635ed 100644
--- a/projects/hip/docs/doxygen-input/doxy.cfg
+++ b/projects/hip/docs/.doxygen/Doxyfile
@@ -32,7 +32,7 @@ DOXYFILE_ENCODING      = UTF-8
 # title of most generated pages and in a few other places.
 # The default value is: My Project.
 
-PROJECT_NAME           = "HIP: Heterogenous-computing Interface for Portability"
+PROJECT_NAME           = "HIP Runtime API Reference"
 
 # The PROJECT_NUMBER tag can be used to enter a project or revision number. This
 # could be handy for archiving the generated documentation or if some version
@@ -58,7 +58,7 @@ PROJECT_LOGO           =
 # entered, it will be relative to the location where doxygen was started. If
 # left blank the current directory will be used.
 
-OUTPUT_DIRECTORY       = RuntimeAPI
+OUTPUT_DIRECTORY       = docBin
 
 # If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub-
 # directories (in 2 levels) under the output directory of each output format and
@@ -275,7 +275,7 @@ TCL_SUBST              =
 # members will be omitted, etc.
 # The default value is: NO.
 
-OPTIMIZE_OUTPUT_FOR_C  = NO
+OPTIMIZE_OUTPUT_FOR_C  = YES
 
 # Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or
 # Python sources only. Doxygen will then generate output that is more tailored
@@ -360,7 +360,7 @@ AUTOLINK_SUPPORT       = YES
 # diagrams that involve STL classes more complete and accurate.
 # The default value is: NO.
 
-BUILTIN_STL_SUPPORT    = NO
+BUILTIN_STL_SUPPORT    =
 
 # If you use Microsoft's C++/CLI language, you should set this option to YES to
 # enable parsing support.
@@ -392,7 +392,7 @@ IDL_PROPERTY_SUPPORT   = YES
 # all members of a group must be documented explicitly.
 # The default value is: NO.
 
-DISTRIBUTE_GROUP_DOC   = NO
+DISTRIBUTE_GROUP_DOC   = YES
 
 # If one adds a struct or class to a group and this option is enabled, then also
 # any nested class or struct is added to the same group. By default this option
@@ -440,7 +440,7 @@ INLINE_SIMPLE_STRUCTS  = NO
 # types are typedef'ed and only the typedef is referenced, never the tag name.
 # The default value is: NO.
 
-TYPEDEF_HIDES_STRUCT   = NO
+TYPEDEF_HIDES_STRUCT   = YES
 
 # The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This
 # cache is used to resolve symbols given their name and scope. Since this can be
@@ -467,7 +467,7 @@ LOOKUP_CACHE_SIZE      = 0
 # normally produced when WARNINGS is set to YES.
 # The default value is: NO.
 
-EXTRACT_ALL            = NO
+EXTRACT_ALL            = YES
 
 # If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will
 # be included in the documentation.
@@ -553,7 +553,7 @@ HIDE_IN_BODY_DOCS      = NO
 # will be excluded. Set it to YES to include the internal documentation.
 # The default value is: NO.
 
-INTERNAL_DOCS          = YES
+INTERNAL_DOCS          = NO
 
 # If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file
 # names in lower-case letters. If set to YES, upper-case letters are also
@@ -562,7 +562,7 @@ INTERNAL_DOCS          = YES
 # (including Cygwin) ands Mac users are advised to set this option to NO.
 # The default value is: system dependent.
 
-CASE_SENSE_NAMES       = YES
+CASE_SENSE_NAMES       = NO
 
 # If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with
 # their full class and namespace scopes in the documentation. If set to YES, the
@@ -673,14 +673,14 @@ GENERATE_TESTLIST      = YES
 # list. This list is created by putting \bug commands in the documentation.
 # The default value is: YES.
 
-GENERATE_BUGLIST       = NO
+GENERATE_BUGLIST       = YES
 
 # The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO)
 # the deprecated list. This list is created by putting \deprecated commands in
 # the documentation.
 # The default value is: YES.
 
-GENERATE_DEPRECATEDLIST= NO
+GENERATE_DEPRECATEDLIST= YES
 
 # The ENABLED_SECTIONS tag can be used to enable conditional documentation
 # sections, marked by \if <section_label> ... \endif and \cond <section_label>
@@ -829,15 +829,8 @@ WARN_LOGFILE           =
 # spaces. See also FILE_PATTERNS and EXTENSION_MAPPING
 # Note: If this tag is empty the current directory is searched.
 
-INPUT                  = $(HIP_PATH)/docs/doxygen-input/mainpage.txt \
-                         $(HIP_PATH)/README.md \
-                         $(HIP_PATH)/CONTRIBUTING.md \
-                         $(HIP_PATH)/docs/doxygen-input/sync.txt \
-                         $(HIP_PATH)/INSTALL.md \
-                         $(HIP_PATH)/docs/markdown \
-                         $(HIP_PATH)/include/hip \
-                         $(HIP_PATH)/include/hip/amd_detail/ \
-                         $(HIP_PATH)/src/
+INPUT                  = mainpage.md       \
+                         ../../include/hip
 
 # This tag can be used to specify the character encoding of the source files
 # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
@@ -868,18 +861,47 @@ FILE_PATTERNS          = *.c \
                          *.cc \
                          *.cxx \
                          *.cpp \
+                         *.c++ \
+                         *.java \
+                         *.ii \
+                         *.ixx \
+                         *.ipp \
+                         *.i++ \
+                         *.inl \
+                         *.idl \
+                         *.ddl \
+                         *.odl \
                          *.h \
+                         *.hh \
+                         *.hxx \
                          *.hpp \
+                         *.h++ \
+                         *.cs \
+                         *.d \
+                         *.php \
+                         *.php4 \
+                         *.php5 \
+                         *.phtml \
+                         *.inc \
+                         *.m \
+                         *.markdown \
                          *.md \
+                         *.mm \
                          *.dox \
-                         *.doc \
-                         *.txt \
+                         *.py \
+                         *.tcl \
+                         *.vhd \
+                         *.vhdl \
+                         *.ucf \
+                         *.qsf \
+                         *.as \
+                         *.js
 
 # The RECURSIVE tag can be used to specify whether or not subdirectories should
 # be searched for input files as well.
 # The default value is: NO.
 
-RECURSIVE              = YES
+RECURSIVE              = NO
 
 # The EXCLUDE tag can be used to specify files and/or directories that should be
 # excluded from the INPUT source files. This way you can easily exclude a
@@ -921,7 +943,7 @@ EXCLUDE_SYMBOLS        =
 # that contain example code fragments that are included (see the \include
 # command).
 
-EXAMPLE_PATH           = ./examples
+EXAMPLE_PATH           =
 
 # If the value of the EXAMPLE_PATH tag contains directories, you can use the
 # EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and
@@ -941,7 +963,7 @@ EXAMPLE_RECURSIVE      = NO
 # that contain images that are to be included in the documentation (see the
 # \image command).
 
-IMAGE_PATH             = $(HIP_PATH)/docs/doxygen-input/images
+IMAGE_PATH             =
 
 # The INPUT_FILTER tag can be used to specify a program that doxygen should
 # invoke to filter for each input file. Doxygen will invoke the filter program
@@ -1182,7 +1204,7 @@ HTML_FILE_EXTENSION    = .html
 # of the possible markers and block names see the documentation.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-HTML_HEADER            =
+HTML_HEADER            = ../_doxygen/header.html
 
 # The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each
 # generated HTML page. If the tag is left blank doxygen will generate a standard
@@ -1192,7 +1214,7 @@ HTML_HEADER            =
 # that doxygen normally uses.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-HTML_FOOTER            =
+HTML_FOOTER            = ../_doxygen/footer.html
 
 # The HTML_STYLESHEET tag can be used to specify a user-defined cascading style
 # sheet that is used by each HTML page. It can be used to fine-tune the look of
@@ -1204,7 +1226,7 @@ HTML_FOOTER            =
 # obsolete.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-HTML_STYLESHEET        =
+HTML_STYLESHEET        = ../_doxygen/stylesheet.css
 
 # The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined
 # cascading style sheets that are included after the standard style sheets
@@ -1217,7 +1239,7 @@ HTML_STYLESHEET        =
 # list). For an example see the documentation.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-HTML_EXTRA_STYLESHEET  =
+HTML_EXTRA_STYLESHEET  = ../_doxygen/extra_stylesheet.css
 
 # The HTML_EXTRA_FILES tag can be used to specify one or more extra images or
 # other source files which should be copied to the HTML output directory. Note
@@ -1266,7 +1288,7 @@ HTML_COLORSTYLE_GAMMA  = 80
 # The default value is: NO.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-HTML_TIMESTAMP         = YES
+HTML_TIMESTAMP         = NO
 
 # If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML
 # documentation will contain a main index with vertical navigation menus that
@@ -1524,7 +1546,7 @@ GENERATE_TREEVIEW      = NO
 # Minimum value: 0, maximum value: 20, default value: 4.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-ENUM_VALUES_PER_LINE   = 4
+ENUM_VALUES_PER_LINE   = 1
 
 # If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used
 # to set the initial width (in pixels) of the frame in which the tree is shown.
@@ -1575,7 +1597,7 @@ FORMULA_MACROFILE      =
 # The default value is: NO.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-USE_MATHJAX            = NO
+USE_MATHJAX            = YES
 
 # When MathJax is enabled you can set the default output format to be used for
 # the MathJax output. See the MathJax site (see:
@@ -1598,7 +1620,7 @@ MATHJAX_FORMAT         = HTML-CSS
 # The default value is: https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/.
 # This tag requires that the tag USE_MATHJAX is set to YES.
 
-MATHJAX_RELPATH        = https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/
+MATHJAX_RELPATH        = http://cdn.mathjax.org/mathjax/latest
 
 # The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax
 # extension names that should be enabled during MathJax rendering. For example
@@ -1634,7 +1656,7 @@ MATHJAX_CODEFILE       =
 # The default value is: YES.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-SEARCHENGINE           = YES
+SEARCHENGINE           = NO
 
 # When the SERVER_BASED_SEARCH tag is enabled the search engine will be
 # implemented using a web server instead of a web client using JavaScript. There
@@ -2010,7 +2032,7 @@ MAN_LINKS              = NO
 # captures the structure of the code including all documentation.
 # The default value is: NO.
 
-GENERATE_XML           = NO
+GENERATE_XML           = YES
 
 # The XML_OUTPUT tag is used to specify where the XML pages will be put. If a
 # relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
@@ -2130,7 +2152,7 @@ ENABLE_PREPROCESSING   = YES
 # The default value is: NO.
 # This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
 
-MACRO_EXPANSION        = NO
+MACRO_EXPANSION        = YES
 
 # If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES then
 # the macro expansion is limited to the macros specified with the PREDEFINED and
@@ -2138,14 +2160,14 @@ MACRO_EXPANSION        = NO
 # The default value is: NO.
 # This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
 
-EXPAND_ONLY_PREDEF     = NO
+EXPAND_ONLY_PREDEF     = YES
 
 # If the SEARCH_INCLUDES tag is set to YES, the include files in the
 # INCLUDE_PATH will be searched if a #include is found.
 # The default value is: YES.
 # This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
 
-SEARCH_INCLUDES        = YES
+SEARCH_INCLUDES        = NO
 
 # The INCLUDE_PATH tag can be used to specify one or more directories that
 # contain include files that are not input files but should be processed by the
@@ -2214,7 +2236,7 @@ TAGFILES               =
 # tag file that is based on the input files it reads. See section "Linking to
 # external documentation" for more information about the usage of tag files.
 
-GENERATE_TAGFILE       =
+GENERATE_TAGFILE       = docBin/html/tagfile.xml
 
 # If the ALLEXTERNALS tag is set to YES, all external class will be listed in
 # the class index. If set to NO, only the inherited external classes will be
@@ -2248,7 +2270,7 @@ EXTERNAL_PAGES         = YES
 # powerful graphs.
 # The default value is: YES.
 
-CLASS_DIAGRAMS         = YES
+CLASS_DIAGRAMS         = NO
 
 # You can include diagrams made with dia in doxygen documentation. Doxygen will
 # then run dia to produce the diagram and insert it in the documentation. The
@@ -2432,7 +2454,7 @@ DIRECTORY_GRAPH        = YES
 # The default value is: png.
 # This tag requires that the tag HAVE_DOT is set to YES.
 
-DOT_IMAGE_FORMAT       = png
+DOT_IMAGE_FORMAT       = svg
 
 # If DOT_IMAGE_FORMAT is set to svg, then this option can be set to YES to
 # enable generation of interactive SVG images that allow zooming and panning.
@@ -2444,7 +2466,7 @@ DOT_IMAGE_FORMAT       = png
 # The default value is: NO.
 # This tag requires that the tag HAVE_DOT is set to YES.
 
-INTERACTIVE_SVG        = NO
+INTERACTIVE_SVG        = YES
 
 # The DOT_PATH tag can be used to specify the path where the dot tool can be
 # found. If left blank, it is assumed the dot tool can be found in the path.
diff --git a/projects/hip/docs/.doxygen/mainpage.md b/projects/hip/docs/.doxygen/mainpage.md
new file mode 100644
index 0000000000..44e41c67d0
--- /dev/null
+++ b/projects/hip/docs/.doxygen/mainpage.md
@@ -0,0 +1,33 @@
+# HIP Runtime API Reference {#mainpage}
+
+This is the full HIP Runtime API reference. The API is organized into
+[modules](modules.html) based on functionality.
+
+## List of Modules
+- @ref GlobalDefs
+- @ref Driver
+- @ref Device
+- @ref Execution
+- @ref Error
+- @ref Stream
+- @ref StreamM
+- @ref Memory
+  - @ref External
+  - @ref MemoryM
+  - @ref StreamO
+- @ref PeerToPeer
+- @ref Context
+  - @ref ContextD
+- @ref Module
+- @ref Occupancy
+- @ref Profiler
+- @ref Clang
+- @ref Texture
+  - @ref TextureD
+  - @ref TextureU
+- @ref Runtime
+- @ref Callback
+- @ref Graph
+- @ref Virtual
+- @ref GL
+- [Surface Object](#Surface)
diff --git a/projects/hip/docs/.gitignore b/projects/hip/docs/.gitignore
new file mode 100644
index 0000000000..8f68c925a3
--- /dev/null
+++ b/projects/hip/docs/.gitignore
@@ -0,0 +1,5 @@
+/_build
+/_doxygen
+/_images
+/_static
+/_templates
\ No newline at end of file
diff --git a/projects/hip/docs/.sphinx/_toc.yml.in b/projects/hip/docs/.sphinx/_toc.yml.in
new file mode 100644
index 0000000000..d44d7e721e
--- /dev/null
+++ b/projects/hip/docs/.sphinx/_toc.yml.in
@@ -0,0 +1,24 @@
+root: index
+subtrees:
+- caption: User Guide
+  entries:
+    - file: user_guide/programming_manual
+    - file: user_guide/hip_rtc
+    - file: user_guide/faq
+- caption: How to Guides
+  entries:
+  - file: how_to_guides/install.md
+  - file: how_to_guides/debugging.md
+- caption: Reference
+  entries:
+  - file: .doxygen/docBin/html/index
+  - file: reference/kernel_language
+  - file: reference/math_api
+  - file: reference/terms
+  - file: reference/glossary
+  - file: reference/deprecated_api_list
+- caption: Developer Guide
+  entries:
+  - file: developer_guide/build
+  - file: developer_guide/logging
+  - file: developer_guide/contributing.md
\ No newline at end of file
diff --git a/projects/hip/docs/.sphinx/requirements.in b/projects/hip/docs/.sphinx/requirements.in
new file mode 100644
index 0000000000..2e15625db8
--- /dev/null
+++ b/projects/hip/docs/.sphinx/requirements.in
@@ -0,0 +1 @@
+rocm-docs-core[api_reference]
\ No newline at end of file
diff --git a/projects/hip/docs/.sphinx/requirements.txt b/projects/hip/docs/.sphinx/requirements.txt
new file mode 100644
index 0000000000..6f21017824
--- /dev/null
+++ b/projects/hip/docs/.sphinx/requirements.txt
@@ -0,0 +1,290 @@
+#
+# This file is autogenerated by pip-compile with Python 3.8
+# by the following command:
+#
+#    pip-compile requirements.in
+#
+accessible-pygments==0.0.3
+    # via pydata-sphinx-theme
+alabaster==0.7.12
+    # via sphinx
+asttokens==2.2.0
+    # via stack-data
+attrs==22.1.0
+    # via
+    #   jsonschema
+    #   jupyter-cache
+babel==2.10.3
+    # via
+    #   pydata-sphinx-theme
+    #   sphinx
+backcall==0.2.0
+    # via ipython
+beautifulsoup4==4.11.1
+    # via pydata-sphinx-theme
+breathe==4.34.0
+    # via rocm-docs-core
+certifi==2022.6.15
+    # via requests
+cffi==1.15.1
+    # via pynacl
+charset-normalizer==2.1.0
+    # via requests
+click==8.1.3
+    # via
+    #   click-log
+    #   doxysphinx
+    #   jupyter-cache
+    #   sphinx-external-toc
+click-log==0.4.0
+    # via doxysphinx
+debugpy==1.6.4
+    # via ipykernel
+decorator==5.1.1
+    # via ipython
+deprecated==1.2.13
+    # via pygithub
+docutils==0.16
+    # via
+    #   breathe
+    #   myst-parser
+    #   pydata-sphinx-theme
+    #   rocm-docs-core
+    #   sphinx
+doxysphinx==3.2.1
+    # via rocm-docs-core
+entrypoints==0.4
+    # via jupyter-client
+executing==1.2.0
+    # via stack-data
+fastjsonschema==2.16.2
+    # via nbformat
+gitdb==4.0.10
+    # via gitpython
+gitpython==3.1.31
+    # via rocm-docs-core
+greenlet==2.0.1
+    # via sqlalchemy
+idna==3.3
+    # via requests
+imagesize==1.4.1
+    # via sphinx
+importlib-metadata==5.1.0
+    # via
+    #   jupyter-cache
+    #   myst-nb
+importlib-resources==5.10.4
+    # via
+    #   jsonschema
+    #   rocm-docs-core
+ipykernel==6.17.1
+    # via myst-nb
+ipython==8.7.0
+    # via
+    #   ipykernel
+    #   myst-nb
+jedi==0.18.2
+    # via ipython
+jinja2==3.1.2
+    # via
+    #   myst-parser
+    #   sphinx
+json5==0.9.11
+    # via doxysphinx
+jsonschema==4.17.3
+    # via nbformat
+jupyter-cache==0.5.0
+    # via myst-nb
+jupyter-client==7.4.7
+    # via
+    #   ipykernel
+    #   nbclient
+jupyter-core==5.1.0
+    # via
+    #   jupyter-client
+    #   nbformat
+linkify-it-py==1.0.3
+    # via myst-parser
+lxml==4.9.2
+    # via doxysphinx
+markdown-it-py==2.1.0
+    # via
+    #   mdit-py-plugins
+    #   myst-parser
+markupsafe==2.1.1
+    # via jinja2
+matplotlib-inline==0.1.6
+    # via
+    #   ipykernel
+    #   ipython
+mdit-py-plugins==0.3.1
+    # via myst-parser
+mdurl==0.1.2
+    # via markdown-it-py
+myst-nb==0.17.1
+    # via rocm-docs-core
+myst-parser[linkify]==0.18.1
+    # via
+    #   myst-nb
+    #   rocm-docs-core
+nbclient==0.5.13
+    # via
+    #   jupyter-cache
+    #   myst-nb
+nbformat==5.7.0
+    # via
+    #   jupyter-cache
+    #   myst-nb
+    #   nbclient
+nest-asyncio==1.5.6
+    # via
+    #   ipykernel
+    #   jupyter-client
+    #   nbclient
+packaging==21.3
+    # via
+    #   ipykernel
+    #   pydata-sphinx-theme
+    #   sphinx
+parso==0.8.3
+    # via jedi
+pexpect==4.8.0
+    # via ipython
+pickleshare==0.7.5
+    # via ipython
+pkgutil-resolve-name==1.3.10
+    # via jsonschema
+platformdirs==2.5.4
+    # via jupyter-core
+prompt-toolkit==3.0.33
+    # via ipython
+psutil==5.9.4
+    # via ipykernel
+ptyprocess==0.7.0
+    # via pexpect
+pure-eval==0.2.2
+    # via stack-data
+pycparser==2.21
+    # via cffi
+pydata-sphinx-theme==0.13.1
+    # via sphinx-book-theme
+pygithub==1.57
+    # via rocm-docs-core
+pygments==2.12.0
+    # via
+    #   accessible-pygments
+    #   ipython
+    #   pydata-sphinx-theme
+    #   sphinx
+pyjwt==2.6.0
+    # via pygithub
+pynacl==1.5.0
+    # via pygithub
+pyparsing==3.0.9
+    # via
+    #   doxysphinx
+    #   packaging
+pyrsistent==0.19.2
+    # via jsonschema
+python-dateutil==2.8.2
+    # via jupyter-client
+pytz==2022.1
+    # via babel
+pyyaml==6.0
+    # via
+    #   jupyter-cache
+    #   myst-nb
+    #   myst-parser
+    #   sphinx-external-toc
+pyzmq==24.0.1
+    # via
+    #   ipykernel
+    #   jupyter-client
+requests==2.28.1
+    # via
+    #   pygithub
+    #   sphinx
+rocm-docs-core[api_reference]==0.2.0
+    # via -r requirements.in
+six==1.16.0
+    # via
+    #   asttokens
+    #   python-dateutil
+smmap==5.0.0
+    # via gitdb
+snowballstemmer==2.2.0
+    # via sphinx
+soupsieve==2.3.2.post1
+    # via beautifulsoup4
+sphinx==4.3.1
+    # via
+    #   breathe
+    #   myst-nb
+    #   myst-parser
+    #   pydata-sphinx-theme
+    #   rocm-docs-core
+    #   sphinx-book-theme
+    #   sphinx-copybutton
+    #   sphinx-design
+    #   sphinx-external-toc
+    #   sphinx-notfound-page
+sphinx-book-theme==1.0.0rc2
+    # via rocm-docs-core
+sphinx-copybutton==0.5.1
+    # via rocm-docs-core
+sphinx-design==0.3.0
+    # via rocm-docs-core
+sphinx-external-toc==0.3.1
+    # via rocm-docs-core
+sphinx-notfound-page==0.8.3
+    # via rocm-docs-core
+sphinxcontrib-applehelp==1.0.2
+    # via sphinx
+sphinxcontrib-devhelp==1.0.2
+    # via sphinx
+sphinxcontrib-htmlhelp==2.0.0
+    # via sphinx
+sphinxcontrib-jsmath==1.0.1
+    # via sphinx
+sphinxcontrib-qthelp==1.0.3
+    # via sphinx
+sphinxcontrib-serializinghtml==1.1.5
+    # via sphinx
+sqlalchemy==1.4.44
+    # via jupyter-cache
+stack-data==0.6.2
+    # via ipython
+tabulate==0.9.0
+    # via jupyter-cache
+tornado==6.2
+    # via
+    #   ipykernel
+    #   jupyter-client
+traitlets==5.6.0
+    # via
+    #   ipykernel
+    #   ipython
+    #   jupyter-client
+    #   jupyter-core
+    #   matplotlib-inline
+    #   nbclient
+    #   nbformat
+typing-extensions==4.4.0
+    # via
+    #   myst-nb
+    #   myst-parser
+uc-micro-py==1.0.1
+    # via linkify-it-py
+urllib3==1.26.11
+    # via requests
+wcwidth==0.2.5
+    # via prompt-toolkit
+wrapt==1.15.0
+    # via deprecated
+zipp==3.11.0
+    # via
+    #   importlib-metadata
+    #   importlib-resources
+
+# The following packages are considered to be unsafe in a requirements file:
+# setuptools
diff --git a/projects/hip/docs/conf.py b/projects/hip/docs/conf.py
new file mode 100644
index 0000000000..62b6736eba
--- /dev/null
+++ b/projects/hip/docs/conf.py
@@ -0,0 +1,26 @@
+# 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
+
+from rocm_docs import ROCmDocs
+from typing import Any, Dict, List
+
+docs_core = ROCmDocs("HIP Documentation")
+docs_core.run_doxygen()
+docs_core.enable_api_reference()
+docs_core.setup()
+
+for sphinx_var in ROCmDocs.SPHINX_VARS:
+    globals()[sphinx_var] = getattr(docs_core, sphinx_var)
+
+# rocm-docs-core might or might not have changed these yet (depending on version),
+# and we don't want to wipe their settings if they did
+if not "html_theme_options" in globals():
+    html_theme_options: Dict[str, Any] = {}
+if not "exclude_patterns" in globals():
+    exclude_patterns: List[str] = []
+
+html_theme_options["show_navbar_depth"] = 2
+exclude_patterns.append(".doxygen/mainpage.md")
diff --git a/projects/hip/docs/markdown/hip_build.md b/projects/hip/docs/developer_guide/build.md
similarity index 64%
rename from projects/hip/docs/markdown/hip_build.md
rename to projects/hip/docs/developer_guide/build.md
index 5fc7daa9b3..51117be207 100755
--- a/projects/hip/docs/markdown/hip_build.md
+++ b/projects/hip/docs/developer_guide/build.md
@@ -1,73 +1,56 @@
-## Table of Contents
+# Building HIP from Source
 
-<!-- toc -->
-
-- [Prerequisites](#Prerequisites)
-- [Build HIP on AMD platform](#build-hip-on-amd-platform)
-  * [Get HIP source code](#get-hip-source-code)
-  * [Set the environment variables](#set-the-environment-variables)
-  * [Build HIP](#build-hip)
-  * [Default paths and environment variables](#default-paths-and-environment-variables)
-  * [Build HIP Tests](#build-hip-tests)
-- [Build HIP on NVIDIA platform](#build-hip-on-NVIDIA-platform)
-  * [Get HIP source code](#get-hip-source-code)
-  * [Set the environment variables](#set-the-environment-variables)
-  * [Build HIP](#build-hip)
-  * [Build HIP tests](#build-hip-tests)
-- [Run HIP](#run-hip)
-<!-- tocstop -->
-
-# Prerequisites
+## Prerequisites
 
 HIP code can be developed either on AMD ROCm platform using HIP-Clang compiler, or a CUDA platform with nvcc installed.
 Before build and run HIP, make sure drivers and pre-build packages are installed properly on the platform.
 
-## AMD platform
+### AMD platform
 Install ROCm packages (see ROCm Installation Guide on AMD public documentation site (https://docs.amd.com/)) or install pre-built binary packages using the package manager,
 
-```
+```shell
 sudo apt install mesa-common-dev
 sudo apt install clang
 sudo apt install comgr
 sudo apt-get -y install rocm-dkms
 ```
 
-## NVIDIA platform
+### NVIDIA platform
 
 Install Nvidia driver and pre-build packages (see HIP Installation Guide at https://docs.amd.com/ for the release)
 
-## Branch of repository
+### Branch of repository
 
-Before get HIP source code, set the expected branch of repository at the variable ROCM_BRANCH.
+Before get HIP source code, set the expected branch of repository at the variable `ROCM_BRANCH`.
 For example, for ROCm5.0 release branch, set
-```
+```shell
 export ROCM_BRANCH=rocm-5.0.x
 ```
 
 ROCm5.4 release branch, set
-```
+```shell
 export ROCM_BRANCH=rocm-5.4.x
 ```
 Similiar format for future branches.
 
-ROCM_PATH is path where ROCM is installed. BY default ROCM_PATH is at /opt/rocm.
+`ROCM_PATH` is path where ROCM is installed. BY default `ROCM_PATH` is at `/opt/rocm`.
 
 
-# Build HIP on AMD platform
+## Build HIP on AMD platform
 
 
-## Get HIP source code
+### Get HIP source code
 
-```
+```shell
 git clone -b "$ROCM_BRANCH" https://github.com/ROCm-Developer-Tools/hipamd.git
 git clone -b "$ROCM_BRANCH" https://github.com/ROCm-Developer-Tools/hip.git
 git clone -b "$ROCM_BRANCH" https://github.com/ROCm-Developer-Tools/ROCclr.git
 git clone -b "$ROCM_BRANCH" https://github.com/RadeonOpenCompute/ROCm-OpenCL-Runtime.git
 ```
 
-## Set the environment variables
+### Set the environment variables
 
-```
+```shell
 export HIPAMD_DIR="$(readlink -f hipamd)"
 export HIP_DIR="$(readlink -f hip)"
 ```
@@ -78,31 +61,32 @@ See https://github.com/ROCm-Developer-Tools/ROCclr
 HIPAMD repository provides implementation specifically for AMD platform.
 See https://github.com/ROCm-Developer-Tools/hipamd
 
-## Build HIP
+### Build HIP
 
-```
+```shell
 cd "$HIPAMD_DIR"
 mkdir -p build; cd build
 cmake -DHIP_COMMON_DIR=$HIP_DIR -DCMAKE_PREFIX_PATH="<ROCM_PATH>/" -DCMAKE_INSTALL_PREFIX=$PWD/install ..
 make -j$(nproc)
 sudo make install
 ```
-
-Note: If you don't specify CMAKE_INSTALL_PREFIX, hip runtime will be installed to "<ROCM_PATH>/hip".
+::::{note}
+If you don't specify `CMAKE_INSTALL_PREFIX`, hip runtime will be installed to `<ROCM_PATH>/hip`.
 By default, release version of AMDHIP is built.
+::::
 
-## Default paths and environment variables
+### Default paths and environment variables
 
-   * By default HIP looks for HSA in <ROCM_PATH>/hsa (can be overridden by setting HSA_PATH environment variable).
-   * By default HIP is installed into <ROCM_PATH>/hip (can be overridden by setting HIP_PATH environment variable).
-   * By default HIP looks for clang in <ROCM_PATH>/llvm/bin (can be overridden by setting HIP_CLANG_PATH environment variable)
-   * By default HIP looks for device library in <ROCM_PATH>/lib (can be overridden by setting DEVICE_LIB_PATH environment variable).
-   * Optionally, consider adding <ROCM_PATH>/bin to your PATH to make it easier to use the tools.
-   * Optionally, set HIPCC_VERBOSE=7 to output the command line for compilation.
+   * By default HIP looks for HSA in `<ROCM_PATH>/hsa` (can be overridden by setting `HSA_PATH` environment variable).
+   * By default HIP is installed into `<ROCM_PATH>/hip` (can be overridden by setting HIP_PATH environment variable).
+   * By default HIP looks for clang in `<ROCM_PATH>/llvm/bin` (can be overridden by setting `HIP_CLANG_PATH` environment variable)
+   * By default HIP looks for device library in `<ROCM_PATH>/lib` (can be overridden by setting `DEVICE_LIB_PATH` environment variable).
+   * Optionally, consider adding `<ROCM_PATH>/bin` to your `PATH` to make it easier to use the tools.
+   * Optionally, set `HIPCC_VERBOSE=7` to output the command line for compilation.
 
-After make install command, make sure HIP_PATH is pointed to $PWD/install/hip.
+After make install command, make sure `HIP_PATH` is pointed to `$PWD/install/hip`.
 
-## Generating profiling header after adding/changing a HIP API
+### Generating profiling header after adding/changing a HIP API
 
 When you add or change a HIP API, you might need to generate a new `hip_prof_str.h` header. This header is used by rocm tools to track HIP APIs like rocprofiler/roctracer etc.
 To generate the header after your change, use the tool `hip_prof_gen.py` present in `hipamd/src`.
@@ -120,34 +104,39 @@ Flags:
   * -e - on error exit mode
   * -p - HIP_INIT_API macro patching mode
 
-Example Usage: `hip_prof_gen.py -v -p -t --priv <hip>/include/hip/hip_runtime_api.h <hipamd>/src <hipamd>/include/hip/amd_detail/hip_prof_str.h <hipamd>/include/hip/amd_detail/hip_prof_str.h.new`
+Example Usage:
+```shell
+hip_prof_gen.py -v -p -t --priv <hip>/include/hip/hip_runtime_api.h \
+<hipamd>/src <hipamd>/include/hip/amd_detail/hip_prof_str.h         \
+<hipamd>/include/hip/amd_detail/hip_prof_str.h.new
+```
 
-## Build HIP tests
+### Build HIP tests
 
-### Build HIP directed tests
+#### Build HIP directed tests
 Developers can build HIP directed tests right after build HIP commands,
 
-```
+```shell
 sudo make install
 make -j$(nproc) build_tests
 ```
-By default, all HIP directed tests will be built and generated under the folder $HIPAMD_DIR/build/directed_tests.
+By default, all HIP directed tests will be built and generated under the folder `$HIPAMD_DIR/build/`directed_tests.
 Take HIP directed device APIs tests, as an example, all available test applications will have executable files generated under,
-$HIPAMD_DIR/build/directed_tests/runtimeApi/device.
+`$HIPAMD_DIR/build/directed_tests/runtimeApi/device`.
 
 Run all HIP directed_tests, use the command,
 
-```
+```shell
 ctest
 ```
 Or
-```
+```shell
 make test
 ```
 
 Build and run a single directed test, use the follow command as an example,
 
-```
+```shell
 make directed_tests.texture.hipTexObjPitch
 cd $HIPAMD_DIR/build/directed_tests/texcture
 ./hipTexObjPitch
@@ -155,18 +144,18 @@ cd $HIPAMD_DIR/build/directed_tests/texcture
 Please note, the integrated HIP directed tests, will be deprecated in future release.
 
 
-### Build HIP catch tests
+##### Build HIP catch tests
 
 HIP catch tests, with new architectured Catch2, are official seperated from HIP project, exist in HIP tests repository, can be built via the following instructions.
 
-#### Get HIP tests source code
+##### Get HIP tests source code
 
-```
+```shell
 git clone -b "$ROCM_BRANCH" https://github.com/ROCm-Developer-Tools/hip-tests.git
 ```
-#### Build HIP tests from source
+##### Build HIP tests from source
 
-```
+```shell
 export HIP_TESTS_DIR="$(readlink -f hip-tests)"
 cd "$HIP_TESTS_DIR"
 mkdir -p build; cd build
@@ -179,16 +168,16 @@ HIP catch tests are built under the folder $HIP_TESTS_DIR/build.
 
 To run any single catch test, the following is an example,
 
-```
+```shell
 cd $HIP_TESTS_DIR/build/catch_tests/unit/texture
 ./TextureTest
 ```
 
-#### Build HIP Catch2 standalone test
+##### Build HIP Catch2 standalone test
 
 HIP Catch2 supports build a standalone test, for example,
 
-```
+```shell
 cd "$HIP_TESTS_DIR"
 hipcc $HIP_TESTS_DIR/catch/unit/memory/hipPointerGetAttributes.cc -I ./catch/include ./catch/hipTestMain/standalone_main.cc -I ./catch/external/Catch2 -o hipPointerGetAttributes
 ./hipPointerGetAttributes
@@ -197,26 +186,26 @@ hipcc $HIP_TESTS_DIR/catch/unit/memory/hipPointerGetAttributes.cc -I ./catch/inc
 All tests passed
 ```
 
-# Build HIP on NVIDIA platform
+## Build HIP on NVIDIA platform
 
 
-## Get HIP source code
+### Get HIP source code
 
-```
+```shell
 git clone -b "$ROCM_BRANCH" https://github.com/ROCm-Developer-Tools/hip.git
 git clone -b "$ROCM_BRANCH" https://github.com/ROCm-Developer-Tools/hipamd.git
 ```
 
-## Set the environment variables
+### Set the environment variables
 
-```
+```shell
 export HIP_DIR="$(readlink -f hip)"
 export HIPAMD_DIR="$(readlink -f hipamd)"
 ```
 
-## Build HIP
+### Build HIP
 
-```
+```shell
 cd "$HIPAMD_DIR"
 mkdir -p build; cd build
 cmake -DHIP_COMMON_DIR=$HIP_DIR -DHIP_PLATFORM=nvidia -DCMAKE_INSTALL_PREFIX=$PWD/install ..
@@ -224,10 +213,10 @@ make -j$(nproc)
 sudo make install
 ```
 
-## Build HIP tests
-Build HIP tests commands on NVIDIA platform are basically the same as AMD, except set -DHIP_PLATFORM=nvidia.
+### Build HIP tests
+Build HIP tests commands on NVIDIA platform are basically the same as AMD, except set `-DHIP_PLATFORM=nvidia`.
 
-# Run HIP
+## Run HIP
 
 Compile and run the [square sample](https://github.com/ROCm-Developer-Tools/HIP/tree/rocm-5.0.x/samples/0_Intro/square).
 
diff --git a/projects/hip/CONTRIBUTING.md b/projects/hip/docs/developer_guide/contributing.md
similarity index 85%
rename from projects/hip/CONTRIBUTING.md
rename to projects/hip/docs/developer_guide/contributing.md
index e5fd36e9d4..1d9288fbb1 100644
--- a/projects/hip/CONTRIBUTING.md
+++ b/projects/hip/docs/developer_guide/contributing.md
@@ -1,12 +1,12 @@
 # Contributor Guidelines
 
 ## Make Tips
-ROCM_PATH is path where ROCM is installed. BY default ROCM_PATH is /opt/rocm.
-When building HIP, you will likely want to build and install to a local user-accessible directory (rather than <ROCM_PATH>).
-This can be easily be done by setting the -DCMAKE_INSTALL_PREFIX variable when running cmake.  Typical use case is to
-set CMAKE_INSTALL_PREFIX to your HIP git root, and then ensure HIP_PATH points to this directory.   For example
+`ROCM_PATH` is path where ROCM is installed. BY default `ROCM_PATH` is `/opt/rocm`.
+When building HIP, you will likely want to build and install to a local user-accessible directory (rather than `<ROCM_PATH>`).
+This can be easily be done by setting the `-DCMAKE_INSTALL_PREFIX` variable when running cmake.  Typical use case is to
+set `CMAKE_INSTALL_PREFIX` to your HIP git root, and then ensure `HIP_PATH` points to this directory. For example
 
-```
+```shell
 cmake .. -DCMAKE_INSTALL_PREFIX=..
 make install
 
@@ -18,20 +18,19 @@ After making HIP, don't forget the "make install" step !
 
 
 ## Adding a new HIP API
-
-    - Add a translation to the hipify-clang tool ; many examples abound.
-       - For stat tracking purposes, place the API into an appropriate stat category ("dev", "mem", "stream", etc).
-    - Add a inlined NVIDIA implementation for the function in include/hip/nvidia_detail/hip_runtime_api.h.
-       - These are typically headers
-    - Add an HIP_ROCclr definition and Doxygen comments for the function in include/amd_detail/hip_runtime_api.h
-       - Source implementation typically go in hip/rocclr/hip_*.cpp. The implementation involve calls to HIP runtime (ie for hipStream_t).
+- Add a translation to the hipify-clang tool ; many examples abound.
+    - For stat tracking purposes, place the API into an appropriate stat category ("dev", "mem", "stream", etc).
+- Add a inlined NVIDIA implementation for the function in include/hip/nvidia_detail/hip_runtime_api.h.
+    - These are typically headers
+- Add an HIP_ROCclr definition and Doxygen comments for the function in include/amd_detail/hip_runtime_api.h
+    - Source implementation typically go in hip/rocclr/hip_*.cpp. The implementation involve calls to HIP runtime (ie for hipStream_t).
 
 ## Check HIP-Clang version
 In some cases new HIP-Clang features are tied to specified releases, and it can be useful to check the current version is sufficiently new enough to support the desired feature.
 
 HIP runtime version
 
-```
+```console
 > cat <ROCM_PATH>/hip/bin/.hipVersion
 # Auto-generated by cmake
 HIP_VERSION_MAJOR=3
@@ -41,7 +40,7 @@ HIP_VERSION_PATCH=20345-519ef3f2
 
 HIP-Clang compiler version
 
-```
+```console
 $ <ROCM_PATH>/llvm/bin/clang -v
 clang version 11.0.0 (/src/external/llvm-project/clang 075fedd3fd2f4d9d8cca79d0cd51f64c5ef21432)
 Target: x86_64-unknown-linux-gnu
@@ -128,9 +127,9 @@ Differences or limitations of HIP APIs as compared to CUDA APIs should be clearl
 Before checking in or submitting a pull request, run all directed tests (see tests/README.md) and all Rodinia tests.
 Ensure pass results match starting point:
 
-```shell
-       > cd examples/
-       > ./run_all.sh
+```console
+> cd examples/
+> ./run_all.sh
 ```
 
 
diff --git a/projects/hip/docs/markdown/hip_logging.md b/projects/hip/docs/developer_guide/logging.md
similarity index 76%
rename from projects/hip/docs/markdown/hip_logging.md
rename to projects/hip/docs/developer_guide/logging.md
index 94858167f2..b712a40d7c 100644
--- a/projects/hip/docs/markdown/hip_logging.md
+++ b/projects/hip/docs/developer_guide/logging.md
@@ -1,32 +1,37 @@
-## What is HIP logging for? ###
+# Logging Mechanisms
 
-HIP provides a logging mechanism, which is a convinient way of printing important information so as to trace HIP API and runtime codes during the execution of HIP application.
-It assists HIP development team in the development of HIP runtime, and is useful for HIP application developers as well.
-Depending on the setting of logging level and logging mask, HIP logging will print different kinds of information, for different types of functionalities such as HIP APIs, executed kernels, queue commands and queue contents, etc.
+HIP provides a logging mechanism, which is a convenient way of printing
+important information so as to trace HIP API and runtime codes during the
+execution of HIP application.
+It assists HIP development team in the development of HIP runtime, and is useful
+for HIP application developers as well.
+Depending on the setting of logging level and logging mask, HIP logging will
+print different kinds of information, for different types of functionalities
+such as HIP APIs, executed kernels, queue commands and queue contents, etc.
 
 ## HIP Logging Level:
 
-By Default, HIP logging is disabled, it can be enabled via environment setting,
-  - AMD_LOG_LEVEL
+By default, HIP logging is disabled, it can be enabled via the `AMD_LOG_LEVEL`
+environment variable.
+The value controls the logging level. The levels are defined as:
 
-The value of the setting controls different logging level,
-
-```
+```cpp
 enum LogLevel {
-LOG_NONE = 0,
-LOG_ERROR = 1,
-LOG_WARNING = 2,
-LOG_INFO = 3,
-LOG_DEBUG = 4
+  LOG_NONE    = 0,
+  LOG_ERROR   = 1,
+  LOG_WARNING = 2,
+  LOG_INFO    = 3,
+  LOG_DEBUG   = 4
 };
 ```
 
 ## HIP Logging Mask:
 
-Logging mask is designed to print types of functionalities during the execution of HIP application.
+Logging mask is designed to print types of functionalities during the execution
+of HIP application.
 It can be set as one of the following values,
 
-```
+```cpp
 enum LogMask {
   LOG_API       = 0x00000001, //!< API call
   LOG_CMD       = 0x00000002, //!< Kernel and Copy Commands and Barriers
@@ -49,39 +54,41 @@ enum LogMask {
 };
 ```
 
-Once AMD_LOG_LEVEL is set, logging mask is set as default with the value 0x7FFFFFFF.
-However, for different pupose of logging functionalities, logging mask can be defined as well via environment variable,
-
-  - AMD_LOG_MASK
+Once `AMD_LOG_LEVEL` is set, logging mask is set as default with the value
+`0x7FFFFFFF`.
+However, for different purpose of logging functionalities, logging mask can be
+defined as well via environment variable `AMD_LOG_MASK`
 
 ## HIP Logging command:
 
 To pring HIP logging information, the function is defined as
-```
-#define ClPrint(level, mask, format, ...)
-  do {
-    if (AMD_LOG_LEVEL >= level) {
-      if (AMD_LOG_MASK & mask || mask == amd::LOG_ALWAYS) {
-        if (AMD_LOG_MASK & amd::LOG_LOCATION) {
-          amd::log_printf(level, __FILENAME__, __LINE__, format, ##__VA_ARGS__);
-        } else {
-          amd::log_printf(level, "", 0, format, ##__VA_ARGS__);
-        }
-      }
-    }
+```cpp
+#define ClPrint(level, mask, format, ...)                                       \
+  do {                                                                          \
+    if (AMD_LOG_LEVEL >= level) {                                               \
+      if (AMD_LOG_MASK & mask || mask == amd::LOG_ALWAYS) {                     \
+        if (AMD_LOG_MASK & amd::LOG_LOCATION) {                                 \
+          amd::log_printf(level, __FILENAME__, __LINE__, format, ##__VA_ARGS__);\
+        } else {                                                                \
+          amd::log_printf(level, "", 0, format, ##__VA_ARGS__);                 \
+        }                                                                       \
+      }                                                                         \
+    }                                                                           \
   } while (false)
 ```
 
-So in HIP code, call ClPrint() function with proper input varibles as needed, for example,
-```
+So in HIP code, call `ClPrint()` function with proper input varibles as needed,
+for example,
+```cpp
 ClPrint(amd::LOG_INFO, amd::LOG_INIT, "Initializing HSA stack.");
 ```
 
 ## HIP Logging Example:
 
-Below is an example to enable HIP logging and get logging information during execution of hipinfo,
+Below is an example to enable HIP logging and get logging information during
+execution of hipinfo,
 
-```
+```console
 user@user-test:~/hip/bin$ export AMD_LOG_LEVEL=4
 user@user-test:~/hip/bin$ ./hipinfo
 
@@ -174,14 +181,13 @@ memInfo.free:                     7.98 GB (100%)
 ## HIP Logging Tips:
 
 - HIP logging works for both release and debug version of HIP application.
-
-- Logging function with different logging level can be called in the code as needed.
-
+- Logging function with different logging level can be called in the code as
+  needed.
 - Information with logging level less than AMD_LOG_LEVEL will be printed.
+- If need to save the HIP logging output information in a file, just define the
+  file at the command when run the application at the terminal, for example,
 
-- If need to save the HIP logging output information in a file, just define the file at the command when run the application at the terminal, for example,
-
-```
+```console
 user@user-test:~/hip/bin$ ./hipinfo > ~/hip_log.txt
 ```
 
diff --git a/projects/hip/docs/markdown/device_md_gen.py b/projects/hip/docs/device_md_gen.py
similarity index 100%
rename from projects/hip/docs/markdown/device_md_gen.py
rename to projects/hip/docs/device_md_gen.py
diff --git a/projects/hip/docs/doxygen-input/mainpage.txt b/projects/hip/docs/doxygen-input/mainpage.txt
deleted file mode 100644
index b1e6119a63..0000000000
--- a/projects/hip/docs/doxygen-input/mainpage.txt
+++ /dev/null
@@ -1,19 +0,0 @@
-/**
- * @file mainpage.cpp
- * @brief : DoxyGen Main Page.
- * @mainpage Heterogeneous-computing Interface for Portability (HIP)
- * @tableofcontents
- *
- * The HIP interface makes it very easy to port existing CUDA apps to run on AMD GPUs,
- * or to develop new apps that can run on either CUDA or AMD GPUs from a common source base.
- *
- *  - HIP is very thin and has little or no performance impact over coding directly in CUDA NVCC mode.
- *  - HIP allows developers to use the "best" development environment and tools on each target platform.
- *  - HIP allows coding in a single-source C++ programming language including features such as templates, C++11 lambdas,and more.
- *  - HIPIFY tools automatically convert CUDA sources to HIP.
- *  - Developers can specialize for CUDA or HIP to tune for performance or handle tricky cases with #ifdef.
-
- *  - See the @ref API.
-
-
-*/
diff --git a/projects/hip/docs/doxygen-input/sync.txt b/projects/hip/docs/doxygen-input/sync.txt
deleted file mode 100644
index 4341418358..0000000000
--- a/projects/hip/docs/doxygen-input/sync.txt
+++ /dev/null
@@ -1,49 +0,0 @@
-/** @page Synchonization
- * @tableofcontents
-
- * # Host-synchronous behavior:
-   The following commands are "host-asynchronous" - meaning they do not wait for any preceding commands to complete, and may return control to the host thread before the requested operation completes:
-
-    - Kernel launches (hipLaunchKernel() )
-    - Asynchronous memory copies - any memory copy API which contains "Async", such as hipMemcpyAsync())
-    - Any memory set (for example, hipMemset());
-    - TODO
-
-   "Host-synchronous" commands have the following properties:
-    - wait for all previous commands to complete.
-    - will not return control back to host until the command completes.
-
-
-   The following commands are "host-synchronous". 
-
-    - hipMemcpy waits for preceding work in the same stream to complete.
-
-
- * # Stream synchronization
-
-
-### Blocking
-
-The term "blocking" has two meanings in HIP.
-
-The first refers to synchronization commands (ie hipStreamSynchronize, hipEventSynchronize) that cause the host CPU to wait for GPU activity to complete.  
-These can either use an active where the host CPU spin-waits on the synchronization variable, or can use an interrupt-based scheme where the core is interrupted 
-when the wait completes.  The second technique is referred to as "blocking" (ie hipDeviceBlockingSync, hipEventBlockingSync) while the first is referred 
-to as "active".  Active can be appropriate for short tasks where latency is critical, but comes at the expense of a CPU core dedicated to monitoring the event.
-
- ### HIP_LAUNCH_BLOCKING (also can use CUDA_LAUNCH_BLOCKING)
-
-    - The following commands become host-synchronous and will not return until the requested command has completed:
-
-      - Kernel launches (hipKernelLaunch).
-      - Memory set commands (hipMemset, hipMemsetAsync).
-      - Memory copy commands (hipMemcpy, hipMemsetAsync).
-
-    Note CUDA_LAUNCH_BLOCKING does add any pre-serialization to the commands and does not affect the concurrent stream behavior.  For example, 
-    even when CUDA_LAUNCH_BLOCKING is set, kernels or data copy commands launched to separate streams can execute concurrently.   Use the NULL
-    stream if additional stream synchronization is desired.
-
-
-
- 
-*/
diff --git a/projects/hip/docs/markdown/gen_clang_option_doc.sh b/projects/hip/docs/gen_clang_option_doc.sh
similarity index 100%
rename from projects/hip/docs/markdown/gen_clang_option_doc.sh
rename to projects/hip/docs/gen_clang_option_doc.sh
diff --git a/projects/hip/docs/markdown/hip_debugging.md b/projects/hip/docs/how_to_guides/debugging.md
similarity index 95%
rename from projects/hip/docs/markdown/hip_debugging.md
rename to projects/hip/docs/how_to_guides/debugging.md
index c6e857a90f..556a51c106 100644
--- a/projects/hip/docs/markdown/hip_debugging.md
+++ b/projects/hip/docs/how_to_guides/debugging.md
@@ -1,21 +1,6 @@
 # HIP Debugging
 There are some techniques provided in HIP for developers to trace and debug codes during execution, this section describes some details and practical suggestions on debugging.
 
-Table of Contents
-=================
-
-  * [ Debugging Tools](#debugging-tools)
-      * [Using ltrace](#using-ltrace)
-      * [Using ROCgdb](#using-rocgdb)
-      * [Other Debugging Tools](#Other-debugging-tools)
-  * [ Debugging HIP Application](#debugging-hip-application)
-  * [ Useful Environment Variables](#useful-environment-variables)
-      * [Kernel Enqueue Serialization](#kernel-enqueue-serialization)
-      * [Making Device visible](#making-device-visible)
-      * [Dump code object](#dump-code-object)
-      * [HSA related environment variables](#HSA-related-environment-variables)
-  * [ General Debugging Tips](#general-debugging-tips)
-
 ## Debugging tools
 
 ### Using ltrace
@@ -27,7 +12,7 @@ The trace can also show performance issues related to accidental calls to expens
 
 Here's a simple sample with command-line to trace hip APIs and output:
 
-```
+```console
 $ ltrace -C -e "hip*" ./hipGetChanDesc
 hipGetChanDesc->hipCreateChannelDesc(0x7ffdc4b66860, 32, 0, 0) = 0x7ffdc4b66860
 hipGetChanDesc->hipMallocArray(0x7ffdc4b66840, 0x7ffdc4b66860, 8, 8) = 0
@@ -39,7 +24,7 @@ PASSED!
 
 Another sample below with command-line only trace hsa APIs and output:
 
-```
+```console
 $ ltrace -C -e "hsa*" ./hipGetChanDesc
 libamdhip64.so.4->hsa_init(0, 0x7fff325a69d0, 0x9c80e0, 0 <unfinished ...>
 libhsa-runtime64.so.1->hsaKmtOpenKFD(0x7fff325a6590, 0x9c38c0, 0, 1) = 0
@@ -98,7 +83,7 @@ For details, see (https://github.com/ROCm-Developer-Tools/ROCgdb).
 
 Below is a sample how to use ROCgdb run and debug HIP application, rocgdb is installed with ROCM package in the folder /opt/rocm/bin.
 
-```
+```console
 $ export PATH=$PATH:/opt/rocm/bin
 $ rocgdb ./hipTexObjPitch
 GNU gdb (rocm-dkms-no-npi-hipclang-6549) 10.1
@@ -133,7 +118,7 @@ There are also other debugging tools available online developers can google and
 
 Below is an example to show how to get useful information from the debugger while running a simple memory copy test, which caused an issue of segmentation fault.
 
-```
+```console
 test: simpleTest2<?> numElements=4194304 sizeElements=4194304 bytes
 Segmentation fault (core dumped)
 
@@ -219,12 +204,12 @@ For system with multiple devices, it's possible to make only certain device(s) v
 HIP_VISIBLE_DEVICES, only devices whose index is present in the sequence are visible to HIP.
 
 For example,
-```
+```console
 $ HIP_VISIBLE_DEVICES=0,1
 ```
 
 or in the application,
-```
+```cpp
 if (totalDeviceNum > 2) {
   setenv("HIP_VISIBLE_DEVICES", "0,1,2", 1);
   assert(getDeviceNumber(false) == 3);
@@ -272,7 +257,7 @@ The following is the summary of the most useful environment variables in HIP.
 (gdb) set env AMD_SERIALIZE_KERNEL 3
 ```
 - The fault will be caught by the runtime but was actually generated by an asynchronous command running on the GPU. So, the GDB backtrace will show a path in the runtime.
-- To determine the true location of the fault, force the kernels to execute synchronously by seeing the environment variables AMD_SERIALIZE_KERNEL=3 AMD_SERIALIZE_COPY=3.  This will force HIP runtime to wait for the kernel to finish executing before retuning.  If the fault occurs during the execution of a kernel, you can see the code which launched the kernel inside the backtrace.  A bit of guesswork is required to determine which thread is actually causing the issue - typically it will the thread which is waiting inside the libhsa-runtime64.so.
+- To determine the true location of the fault, force the kernels to execute synchronously by seeing the environment variables AMD_SERIALIZE_KERNEL=3 AMD_SERIALIZE_COPY=3.  This will force HIP runtime to wait for the kernel to finish executing before retuning.  If the fault occurs during the execution of a kernel, you can see the code which launched the kernel inside the backtrace.  A bit of guesswork is required to determine which thread is actually causing the issue - typically it will the thread which is waiting inside the `libhsa-runtime64.so`.
 - VM faults inside kernels can be caused by:
    - incorrect code (ie a for loop which extends past array boundaries),
    - memory issues  - kernel arguments which are invalid (null pointers, unregistered host pointers, bad pointers),
diff --git a/projects/hip/INSTALL.md b/projects/hip/docs/how_to_guides/install.md
similarity index 83%
rename from projects/hip/INSTALL.md
rename to projects/hip/docs/how_to_guides/install.md
index 6d40178cc8..b8b38a0199 100644
--- a/projects/hip/INSTALL.md
+++ b/projects/hip/docs/how_to_guides/install.md
@@ -1,16 +1,4 @@
-## Table of Contents
-
-<!-- toc -->
-
-- [Install HIP](#installing-hip)
-  * [Prerequisites](#prerequisites)
-  * [AMD Platform](#amd-platform)
-  * [NVIDIA Platform](#nvidia-platform)
-- [Verify your installation](#verify-your-installation)
-- [How to build HIP from source](#how-to-build-hip-from-source)
-<!-- tocstop -->
-
-# Install HIP
+# Installing HIP
 
 HIP can be installed either on AMD ROCm platform with HIP-Clang compiler, or a CUDA platform with nvcc installed.
 
@@ -59,6 +47,7 @@ Run hipconfig (instructions below assume default installation path) :
 
 # How to build HIP from source
 
-Developers can build HIP from source on either AMD or NVIDIA platforms, see detail instructions at [building HIP] (docs/markdown/hip_build.md).
+Developers can build HIP from source on either AMD or NVIDIA platforms, see
+detailed instructions at {doc}`/developer_guide/build` 
 
 
diff --git a/projects/hip/docs/index.md b/projects/hip/docs/index.md
new file mode 100644
index 0000000000..a2a7c89f20
--- /dev/null
+++ b/projects/hip/docs/index.md
@@ -0,0 +1,37 @@
+# HIP Documentation
+
+HIP is a C++ runtime API and kernel language that allows developers to create
+portable applications for AMD and NVIDIA GPUs from single source code.
+
+## Overview
+
+::::{grid} 1 1 2 2
+:gutter: 1
+
+:::{grid-item-card} User Guide
+- {doc}`/user_guide/programming_manual`
+- {doc}`/user_guide/hip_rtc`
+- {doc}`/user_guide/faq`
+:::
+
+:::{grid-item-card} How to Guides
+- {doc}`/how_to_guides/install`
+- {doc}`/how_to_guides/debugging`
+:::
+
+:::{grid-item-card} Reference
+- {doc}`/.doxygen/docBin/html/index`
+  - {doc}`/.doxygen/docBin/html/modules`
+- {doc}`/reference/kernel_language`
+- {doc}`/reference/math_api`
+- {doc}`/reference/terms`
+- {doc}`/reference/deprecated_api_list`
+:::
+
+:::{grid-item-card} Developer Guide
+- {doc}`/developer_guide/build`
+- {doc}`/developer_guide/logging`
+- {doc}`/developer_guide/contributing`
+:::
+
+::::
\ No newline at end of file
diff --git a/projects/hip/docs/markdown/CUDA_Driver_API_functions_supported_by_HIP.md b/projects/hip/docs/markdown/CUDA_Driver_API_functions_supported_by_HIP.md
deleted file mode 100644
index c5649e36d6..0000000000
--- a/projects/hip/docs/markdown/CUDA_Driver_API_functions_supported_by_HIP.md
+++ /dev/null
@@ -1 +0,0 @@
-Document has been moved to https://github.com/ROCm-Developer-Tools/HIPIFY/blob/master/doc/markdown/CUDA_Driver_API_functions_supported_by_HIP.md
diff --git a/projects/hip/docs/markdown/CUDA_Runtime_API_functions_supported_by_HIP.md b/projects/hip/docs/markdown/CUDA_Runtime_API_functions_supported_by_HIP.md
deleted file mode 100644
index da4e226c11..0000000000
--- a/projects/hip/docs/markdown/CUDA_Runtime_API_functions_supported_by_HIP.md
+++ /dev/null
@@ -1,1121 +0,0 @@
-# CUDA Runtime API functions supported by HIP
-
-## **1. Device Management**
-
-|   **CUDA**                                                |   **HIP**                         |**CUDA version\***|
-|-----------------------------------------------------------|-----------------------------------|:----------------:|
-| `cudaChooseDevice`                                        | `hipChooseDevice`                 |
-| `cudaDeviceGetAttribute`                                  | `hipDeviceGetAttribute`           |
-| `cudaDeviceGetByPCIBusId`                                 | `hipDeviceGetByPCIBusId`          |
-| `cudaDeviceGetCacheConfig`                                | `hipDeviceGetCacheConfig`         |
-| `cudaDeviceGetLimit`                                      | `hipDeviceGetLimit`               |
-| `cudaDeviceGetNvSciSyncAttributes`                        |                                   | 10.2             |
-| `cudaDeviceGetPCIBusId`                                   | `hipDeviceGetPCIBusId`            |
-| `cudaDeviceGetSharedMemConfig`                            | `hipDeviceGetSharedMemConfig`     |
-| `cudaDeviceGetStreamPriorityRange`                        | `hipDeviceGetStreamPriorityRange` |
-| `cudaDeviceReset`                                         | `hipDeviceReset`                  |
-| `cudaDeviceSetCacheConfig`                                | `hipDeviceSetCacheConfig`         |
-| `cudaDeviceSetLimit`                                      | `hipDeviceSetLimit`               |
-| `cudaDeviceSetSharedMemConfig`                            | `hipDeviceSetSharedMemConfig`     |
-| `cudaDeviceSynchronize`                                   | `hipDeviceSynchronize`            |
-| `cudaGetDevice`                                           | `hipGetDevice`                    |
-| `cudaGetDeviceCount`                                      | `hipGetDeviceCount`               |
-| `cudaGetDeviceFlags`                                      | `hipCtxGetFlags`                  |
-| `cudaGetDeviceProperties`                                 | `hipGetDeviceProperties`          |
-| `cudaIpcCloseMemHandle`                                   | `hipIpcCloseMemHandle`            |
-| `cudaIpcGetEventHandle`                                   | `hipIpcGetEventHandle`            |
-| `cudaIpcGetMemHandle`                                     | `hipIpcGetMemHandle`              |
-| `cudaIpcOpenEventHandle`                                  | `hipIpcOpenEventHandle`           |
-| `cudaIpcOpenMemHandle`                                    | `hipIpcOpenMemHandle`             |
-| `cudaSetDevice`                                           | `hipSetDevice`                    |
-| `cudaSetDeviceFlags`                                      | `hipSetDeviceFlags`               |
-| `cudaSetValidDevices`                                     |                                   |
-| `cudaDeviceGetP2PAttribute`                               |                                   | 8.0              |
-
-## **2. Thread Management [DEPRECATED]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaThreadExit`                                          | `hipDeviceReset`              |
-| `cudaThreadGetCacheConfig`                                | `hipDeviceGetCacheConfig`     |
-| `cudaThreadGetLimit`                                      |                               |
-| `cudaThreadSetCacheConfig`                                | `hipDeviceSetCacheConfig`     |
-| `cudaThreadSetLimit`                                      |                               |
-| `cudaThreadSynchronize`                                   | `hipDeviceSynchronize`        |
-
-## **3. Error Handling**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaGetErrorName`                                        | `hipGetErrorName`             |
-| `cudaGetErrorString`                                      | `hipGetErrorString`           |
-| `cudaGetLastError`                                        | `hipGetLastError`             |
-| `cudaPeekAtLastError`                                     | `hipPeekAtLastError`          |
-
-## **4. Stream Management**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaStreamAddCallback`                                   | `hipStreamAddCallback`        |
-| `cudaStreamAttachMemAsync`                                |                               |
-| `cudaStreamBeginCapture`                                  |                               | 10.0             |
-| `cudaStreamEndCapture`                                    |                               | 10.0             |
-| `cudaStreamIsCapturing`                                   |                               | 10.0             |
-| `cudaStreamGetCaptureInfo`                                |                               | 10.1             |
-| `cudaStreamCreate`                                        | `hipStreamCreate`             |
-| `cudaStreamCreateWithFlags`                               | `hipStreamCreateWithFlags`    |
-| `cudaStreamCreateWithPriority`                            | `hipStreamCreateWithPriority` |
-| `cudaStreamDestroy`                                       | `hipStreamDestroy`            |
-| `cudaStreamGetFlags`                                      | `hipStreamGetFlags`           |
-| `cudaStreamGetPriority`                                   | `hipStreamGetPriority`        |
-| `cudaStreamQuery`                                         | `hipStreamQuery`              |
-| `cudaStreamSynchronize`                                   | `hipStreamSynchronize`        |
-| `cudaStreamWaitEvent`                                     | `hipStreamWaitEvent`          |
-| `cudaThreadExchangeStreamCaptureMode`                     |                               | 10.1             |
-
-## **5. Event Management**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaEventCreate`                                         | `hipEventCreate`              |
-| `cudaEventCreateWithFlags`                                | `hipEventCreateWithFlags`     |
-| `cudaEventDestroy`                                        | `hipEventDestroy`             |
-| `cudaEventElapsedTime`                                    | `hipEventElapsedTime`         |
-| `cudaEventQuery`                                          | `hipEventQuery`               |
-| `cudaEventRecord`                                         | `hipEventRecord`              |
-| `cudaEventSynchronize`                                    | `hipEventSynchronize`         |
-
-## **6. External Resource Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaSignalExternalSemaphoresAsync`                       |                               | 10.0             |
-| `cudaWaitExternalSemaphoresAsync`                         |                               | 10.0             |
-| `cudaImportExternalMemory`                                |                               | 10.0             |
-| `cudaExternalMemoryGetMappedBuffer`                       |                               | 10.0             |
-| `cudaExternalMemoryGetMappedMipmappedArray`               |                               | 10.0             |
-| `cudaDestroyExternalMemory`                               |                               | 10.0             |
-| `cudaImportExternalSemaphore`                             |                               | 10.0             |
-| `cudaDestroyExternalSemaphore`                            |                               | 10.0             |
-
-## **7. Execution Control**
-
-|   **CUDA**                                                |   **HIP**                             |**CUDA version\***|
-|-----------------------------------------------------------|---------------------------------------|:----------------:|
-| `cudaFuncGetAttributes`                                   |`hipFuncGetAttributes`                 |
-| `cudaFuncSetAttribute`                                    |`hipFuncSetAttribute`                  | 9.0              |
-| `cudaFuncSetCacheConfig`                                  |`hipFuncSetCacheConfig`                |
-| `cudaFuncSetSharedMemConfig`                              |`hipFuncSetSharedMemConfig`            |
-| `cudaGetParameterBuffer`                                  |                                       |
-| `cudaGetParameterBufferV2`                                |                                       |
-| `cudaLaunchKernel`                                        |`hipLaunchKernel`                      |
-| `cudaSetDoubleForDevice`                                  |                                       |
-| `cudaSetDoubleForHost`                                    |                                       |
-| `cudaLaunchCooperativeKernel`                             |`hipLaunchCooperativeKernel`           | 9.0              |
-| `cudaLaunchCooperativeKernelMultiDevice`                  |`hipLaunchCooperativeKernelMultiDevice`| 9.0              |
-| `cudaLaunchHostFunc`                                      |                                       | 10.0             |
-
-## **8. Occupancy**
-
-|   **CUDA**                                                |   **HIP**                                             |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------------------------------|:----------------:|
-| `cudaOccupancyMaxActiveBlocksPerMultiprocessor`           |`hipOccupancyMaxActiveBlocksPerMultiprocessor`         |
-| `cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags`  |`hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags`|
-
-## **Former 9. Execution Control [DEPRECATED since 7.0, REMOVED since 10.1]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaConfigureCall`                                       | `hipConfigureCall`            |
-| `cudaLaunch`                                              | `hipLaunchByPtr`              |
-| `cudaSetupArgument`                                       | `hipSetupArgument`            |
-
-## **9. Memory Management**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaArrayGetInfo`                                        | `hipArrayGetInfo`             |
-| `cudaFree`                                                | `hipFree`                     |
-| `cudaFreeArray`                                           | `hipFreeArray`                |
-| `cudaFreeHost`                                            | `hipHostFree`                 |
-| `cudaFreeMipmappedArray`                                  |                               |
-| `cudaGetMipmappedArrayLevel`                              |                               |
-| `cudaGetSymbolAddress`                                    | `hipGetSymbolAddress`         |
-| `cudaGetSymbolSize`                                       | `hipGetSymbolSize`            |
-| `cudaHostAlloc`                                           | `hipHostMalloc`               |
-| `cudaHostGetDevicePointer`                                | `hipHostGetDevicePointer`     |
-| `cudaHostGetFlags`                                        | `hipHostGetFlags`             |
-| `cudaHostRegister`                                        | `hipHostRegister`             |
-| `cudaHostUnregister`                                      | `hipHostUnregister`           |
-| `cudaMalloc`                                              | `hipMalloc`                   |
-| `cudaMalloc3D`                                            | `hipMalloc3D`                 |
-| `cudaMalloc3DArray`                                       | `hipMalloc3DArray`            |
-| `cudaMallocArray`                                         | `hipMallocArray`              |
-| `cudaMallocHost`                                          | `hipHostMalloc`               |
-| `cudaMallocManaged`                                       | `hipMallocManaged`            |
-| `cudaMallocMipmappedArray`                                |                               |
-| `cudaMallocPitch`                                         |                               |
-| `cudaMemGetInfo`                                          | `hipMemGetInfo`               |
-| `cudaMemPrefetchAsync`                                    |                               | 8.0              |
-| `cudaMemcpy`                                              | `hipMemcpy`                   |
-| `cudaMemcpy2D`                                            | `hipMemcpy2D`                 |
-| `cudaMemcpy2DArrayToArray`                                |                               |
-| `cudaMemcpy2DAsync`                                       | `hipMemcpy2DAsync`            |
-| `cudaMemcpy2DFromArray`                                   | `hipMemcpy2DFromArray`        |
-| `cudaMemcpy2DFromArrayAsync`                              | `hipMemcpy2DFromArrayAsync`   |
-| `cudaMemcpy2DToArray`                                     | `hipMemcpy2DToArray`          |
-| `cudaMemcpy2DToArrayAsync`                                |                               |
-| `cudaMemcpy3D`                                            | `hipMemcpy3D`                 |
-| `cudaMemcpy3DAsync`                                       | `hipMemcpy3DAsync`            |
-| `cudaMemcpy3DPeer`                                        |                               |
-| `cudaMemcpy3DPeerAsync`                                   |                               |
-| `cudaMemcpyAsync`                                         | `hipMemcpyAsync`              |
-| `cudaMemcpyFromSymbol`                                    | `hipMemcpyFromSymbol`         |
-| `cudaMemcpyFromSymbolAsync`                               | `hipMemcpyFromSymbolAsync`    |
-| `cudaMemcpyPeer`                                          | `hipMemcpyPeer`               |
-| `cudaMemcpyPeerAsync`                                     | `hipMemcpyPeerAsync`          |
-| `cudaMemcpyToSymbol`                                      | `hipMemcpyToSymbol`           |
-| `cudaMemcpyToSymbolAsync`                                 | `hipMemcpyToSymbolAsync`      |
-| `cudaMemset`                                              | `hipMemset`                   |
-| `cudaMemset2D`                                            | `hipMemset2D`                 |
-| `cudaMemset2DAsync`                                       | `hipMemset2DAsync`            |
-| `cudaMemset3D`                                            | `hipMemset3D`                 |
-| `cudaMemset3DAsync`                                       | `hipMemset3DAsync`            |
-| `cudaMemsetAsync`                                         | `hipMemsetAsync`              |
-| `make_cudaExtent`                                         | `make_hipExtent`              |
-| `make_cudaPitchedPtr`                                     | `make_hipPitchedPtr`          |
-| `make_cudaPos`                                            | `make_hipPos`                 |
-
-## **10. Memory Management [DEPRECATED since 10.1]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaMemcpyArrayToArray`                                  |                               |
-| `cudaMemcpyFromArray`                                     | `hipMemcpyFromArray`          |
-| `cudaMemcpyFromArrayAsync`                                |                               |
-| `cudaMemcpyToArray`                                       | `hipMemcpyToArray`            |
-| `cudaMemcpyToArrayAsync`                                  |                               |
-
-## **11. Unified Addressing**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaPointerGetAttributes`                                | `hipPointerGetAttributes`     |
-
-## **12. Peer Device Memory Access**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaDeviceCanAccessPeer`                                 | `hipDeviceCanAccessPeer`      |
-| `cudaDeviceDisablePeerAccess`                             | `hipDeviceDisablePeerAccess`  |
-| `cudaDeviceEnablePeerAccess`                              | `hipDeviceEnablePeerAccess`   |
-
-## **13. OpenGL Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaGLGetDevices`                                        |                               |
-| `cudaGraphicsGLRegisterBuffer`                            |                               |
-| `cudaGraphicsGLRegisterImage`                             |                               |
-| `cudaWGLGetDevice`                                        |                               |
-
-## **14. OpenGL Interoperability [DEPRECATED]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaGLMapBufferObject`                                   |                               |
-| `cudaGLMapBufferObjectAsync`                              |                               |
-| `cudaGLRegisterBufferObject`                              |                               |
-| `cudaGLSetBufferObjectMapFlags`                           |                               |
-| `cudaGLSetGLDevice`                                       |                               |
-| `cudaGLUnmapBufferObject`                                 |                               |
-| `cudaGLUnmapBufferObjectAsync`                            |                               |
-| `cudaGLUnregisterBufferObject`                            |                               |
-
-## **15. Direct3D 9 Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaD3D9GetDevice`                                       |                               |
-| `cudaD3D9GetDevices`                                      |                               |
-| `cudaD3D9GetDirect3DDevice`                               |                               |
-| `cudaD3D9SetDirect3DDevice`                               |                               |
-| `cudaGraphicsD3D9RegisterResource`                        |                               |
-
-## **16. Direct3D 9 Interoperability [DEPRECATED]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaD3D9MapResources`                                    |                               |
-| `cudaD3D9RegisterResource`                                |                               |
-| `cudaD3D9ResourceGetMappedArray`                          |                               |
-| `cudaD3D9ResourceGetMappedPitch`                          |                               |
-| `cudaD3D9ResourceGetMappedPointer`                        |                               |
-| `cudaD3D9ResourceGetMappedSize`                           |                               |
-| `cudaD3D9ResourceGetSurfaceDimensions`                    |                               |
-| `cudaD3D9ResourceSetMapFlags`                             |                               |
-| `cudaD3D9UnmapResources`                                  |                               |
-| `cudaD3D9UnregisterResource`                              |                               |
-
-## **17. Direct3D 10 Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaD3D10GetDevice`                                      |                               |
-| `cudaD3D10GetDevices`                                     |                               |
-| `cudaGraphicsD3D10RegisterResource`                       |                               |
-
-## **18. Direct3D 10 Interoperability [DEPRECATED]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaD3D10GetDirect3DDevice`                              |                               |
-| `cudaD3D10MapResources`                                   |                               |
-| `cudaD3D10RegisterResource`                               |                               |
-| `cudaD3D10ResourceGetMappedArray`                         |                               |
-| `cudaD3D10ResourceGetMappedPitch`                         |                               |
-| `cudaD3D10ResourceGetMappedPointer`                       |                               |
-| `cudaD3D10ResourceGetMappedSize`                          |                               |
-| `cudaD3D10ResourceGetSurfaceDimensions`                   |                               |
-| `cudaD3D10ResourceSetMapFlags`                            |                               |
-| `cudaD3D10SetDirect3DDevice`                              |                               |
-| `cudaD3D10UnmapResources`                                 |                               |
-| `cudaD3D10UnregisterResource`                             |                               |
-
-## **19. Direct3D 11 Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaD3D11GetDevice`                                      |                               |
-| `cudaD3D11GetDevices`                                     |                               |
-| `cudaGraphicsD3D11RegisterResource`                       |                               |
-
-## **20. Direct3D 11 Interoperability [DEPRECATED]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaD3D11GetDirect3DDevice`                              |                               |
-| `cudaD3D11SetDirect3DDevice`                              |                               |
-
-## **21. VDPAU Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaGraphicsVDPAURegisterOutputSurface`                  |                               |
-| `cudaGraphicsVDPAURegisterVideoSurface`                   |                               |
-| `cudaVDPAUGetDevice`                                      |                               |
-| `cudaVDPAUSetVDPAUDevice`                                 |                               |
-
-## **22. EGL Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaEGLStreamConsumerAcquireFrame`                       |                               | 8.0              |
-| `cudaEGLStreamConsumerConnect`                            |                               | 8.0              |
-| `cudaEGLStreamConsumerConnectWithFlags`                   |                               | 8.0              |
-| `cudaEGLStreamConsumerDisconnect`                         |                               | 8.0              |
-| `cudaEGLStreamConsumerReleaseFrame`                       |                               | 8.0              |
-| `cudaEGLStreamProducerConnect`                            |                               | 8.0              |
-| `cudaEGLStreamProducerDisconnect`                         |                               | 8.0              |
-| `cudaEGLStreamProducerPresentFrame`                       |                               | 8.0              |
-| `cudaEGLStreamProducerReturnFrame`                        |                               | 8.0              |
-| `cudaEventCreateFromEGLSync`                              |                               | 9.0              |
-| `cudaGraphicsEGLRegisterImage`                            |                               | 8.0              |
-| `cudaGraphicsResourceGetMappedEglFrame`                   |                               | 8.0              |
-
-## **23. Graphics Interoperability**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaGraphicsMapResources`                                |                               |
-| `cudaGraphicsResourceGetMappedMipmappedArray`             |                               |
-| `cudaGraphicsResourceGetMappedPointer`                    |                               |
-| `cudaGraphicsResourceSetMapFlags`                         |                               |
-| `cudaGraphicsSubResourceGetMappedArray`                   |                               |
-| `cudaGraphicsUnmapResources`                              |                               |
-| `cudaGraphicsUnregisterResource`                          |                               |
-
-## **24. Texture Reference Management [DEPRECATED]**
-
-|   **CUDA**                                                |   **HIP**                        |**CUDA version\***|
-|-----------------------------------------------------------|----------------------------------|:----------------:|
-| `cudaBindTexture`                                         | `hipBindTexture`                 |
-| `cudaBindTexture2D`                                       | `hipBindTexture2D`               |
-| `cudaBindTextureToArray`                                  | `hipBindTextureToArray`          |
-| `cudaBindTextureToMipmappedArray`                         | `hipBindTextureToMipmappedArray` |
-| `cudaCreateChannelDesc`                                   | `hipCreateChannelDesc`           |
-| `cudaGetChannelDesc`                                      | `hipGetChannelDesc`              |
-| `cudaGetTextureAlignmentOffset`                           | `hipGetTextureAlignmentOffset`   |
-| `cudaGetTextureReference`                                 | `hipGetTextureReference`         |
-| `cudaUnbindTexture`                                       | `hipUnbindTexture`               |
-
-## **25. Surface Reference Management [DEPRECATED]**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaBindSurfaceToArray`                                  |                               |
-| `cudaGetSurfaceReference`                                 |                               |
-
-## **26. Texture Object Management**
-
-|   **CUDA**                                                |   **HIP**                            |**CUDA version\***|
-|-----------------------------------------------------------|--------------------------------------|:----------------:|
-| `cudaCreateTextureObject`                                 |`hipCreateTextureObject`              |
-| `cudaDestroyTextureObject`                                |`hipDestroyTextureObject`             |
-| `cudaGetTextureObjectResourceDesc`                        |`hipGetTextureObjectResourceDesc`     |
-| `cudaGetTextureObjectResourceViewDesc`                    |`hipGetTextureObjectResourceViewDesc` |
-| `cudaGetTextureObjectTextureDesc`                         |`hipGetTextureObjectTextureDesc`      |
-
-## **27. Surface Object Management**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaCreateSurfaceObject`                                 | `hipCreateSurfaceObject`      |
-| `cudaDestroySurfaceObject`                                | `hipDestroySurfaceObject`     |
-| `cudaGetSurfaceObjectResourceDesc`                        |                               |
-
-## **28. Version Management**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaDriverGetVersion`                                    | `hipDriverGetVersion`         |
-| `cudaRuntimeGetVersion`                                   | `hipRuntimeGetVersion`        |
-
-## **29. Graph Management**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaGraphAddChildGraphNode`                              |                               | 10.0             |
-| `cudaGraphAddDependencies`                                |                               | 10.0             |
-| `cudaGraphAddEmptyNode`                                   |                               | 10.0             |
-| `cudaGraphAddHostNode`                                    |                               | 10.0             |
-| `cudaGraphAddKernelNode`                                  |                               | 10.0             |
-| `cudaGraphAddMemcpyNode`                                  |                               | 10.0             |
-| `cudaGraphAddMemsetNode`                                  |                               | 10.0             |
-| `cudaGraphChildGraphNodeGetGraph`                         |                               | 10.0             |
-| `cudaGraphClone`                                          |                               | 10.0             |
-| `cudaGraphCreate`                                         |                               | 10.0             |
-| `cudaGraphDestroy`                                        |                               | 10.0             |
-| `cudaGraphDestroyNode`                                    |                               | 10.0             |
-| `cudaGraphExecDestroy`                                    |                               | 10.0             |
-| `cudaGraphGetEdges`                                       |                               | 10.0             |
-| `cudaGraphGetNodes`                                       |                               | 10.0             |
-| `cudaGraphGetRootNodes`                                   |                               | 10.0             |
-| `cudaGraphHostNodeGetParams`                              |                               | 10.0             |
-| `cudaGraphHostNodeSetParams`                              |                               | 10.0             |
-| `cudaGraphInstantiate`                                    |                               | 10.0             |
-| `cudaGraphExecKernelNodeSetParams`                        |                               | 10.1             |
-| `cudaGraphExecMemcpyNodeSetParams`                        |                               | 10.2             |
-| `cudaGraphExecMemsetNodeSetParams`                        |                               | 10.2             |
-| `cudaGraphExecHostNodeSetParams`                          |                               | 10.2             |
-| `cudaGraphExecUpdate`                                     |                               | 10.2             |
-| `cudaGraphKernelNodeGetParams`                            |                               | 10.0             |
-| `cudaGraphKernelNodeSetParams`                            |                               | 10.0             |
-| `cudaGraphLaunch`                                         |                               | 10.0             |
-| `cudaGraphMemcpyNodeGetParams`                            |                               | 10.0             |
-| `cudaGraphMemcpyNodeSetParams`                            |                               | 10.0             |
-| `cudaGraphMemsetNodeGetParams`                            |                               | 10.0             |
-| `cudaGraphMemsetNodeSetParams`                            |                               | 10.0             |
-| `cudaGraphNodeFindInClone`                                |                               | 10.0             |
-| `cudaGraphNodeGetDependencies`                            |                               | 10.0             |
-| `cudaGraphNodeGetDependentNodes`                          |                               | 10.0             |
-| `cudaGraphNodeGetType`                                    |                               | 10.0             |
-| `cudaGraphRemoveDependencies`                             |                               | 10.0             |
-
-## **30. C++ API Routines [DEPRECATED since 7.5]**
-
-|   **CUDA**                                                |   **HIP**                                             |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------------------------------|:----------------:|
-| `cudaBindSurfaceToArray`                                  |                                                       |
-| `cudaBindTexture`                                         |`hipBindTexture`                                       |
-| `cudaBindTexture2D`                                       |                                                       |
-| `cudaBindTextureToArray`                                  |                                                       |
-| `cudaBindTextureToMipmappedArray`                         |                                                       |
-| `cudaCreateChannelDesc`                                   |`hipCreateChannelDesc`                                 |
-| `cudaEventCreate`                                         |                                                       |
-| `cudaFuncGetAttributes`                                   |                                                       |
-| `cudaFuncSetAttribute`                                    |                                                       |
-| `cudaFuncSetCacheConfig`                                  |                                                       |
-| `cudaGetSymbolAddress`                                    |`hipGetSymbolAddress`                                  |
-| `cudaGetSymbolSize`                                       |`hipGetSymbolSize`                                     |
-| `cudaGetTextureAlignmentOffset`                           |                                                       |
-| `cudaLaunch`                                              |                                                       |
-| `cudaLaunchCooperativeKernel`                             |`hipLaunchCooperativeKernel`                           |
-| `cudaLaunchCooperativeKernelMultiDevice`                  |`hipLaunchCooperativeKernelMultiDevice`                |
-| `cudaLaunchKernel`                                        |                                                       |
-| `cudaMallocHost`                                          |                                                       |
-| `cudaMallocManaged`                                       |                                                       |
-| `cudaMemcpyFromSymbol`                                    |                                                       |
-| `cudaMemcpyFromSymbolAsync`                               |                                                       |
-| `cudaMemcpyToSymbol`                                      |                                                       |
-| `cudaMemcpyToSymbolAsync`                                 |                                                       |
-| `cudaOccupancyMaxPotentialBlockSize`                      |`hipOccupancyMaxPotentialBlockSize`                    |
-| `cudaOccupancyMaxPotentialBlockSizeWithFlags`             |                                                       |
-| `cudaOccupancyMaxPotentialBlockSizeVariableSMem`          |                                                       |
-| `cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags` |                                                       |
-| `cudaSetupArgument`                                       |                                                       |
-| `cudaStreamAttachMemAsync`                                |                                                       |
-| `cudaUnbindTexture`                                       |`hipUnbindTexture`                                     |
-
-## **32. Profiler Control**
-
-|   **CUDA**                                                |   **HIP**                     |**CUDA version\***|
-|-----------------------------------------------------------|-------------------------------|:----------------:|
-| `cudaProfilerInitialize`                                  |                               |
-| `cudaProfilerStart`                                       | `hipProfilerStart`            |
-| `cudaProfilerStop`                                        | `hipProfilerStop`             |
-
-# Data types used by CUDA Runtime API and supported by HIP
-
-## **33. Data types**
-
-| **type**     |   **CUDA**                                          |**CUDA version\***|   **HIP**                                                  |**HIP value** (if differs) |
-|-------------:|-----------------------------------------------------|:----------------:|------------------------------------------------------------|---------------------------|
-| struct       |`cudaChannelFormatDesc`                              |                  |`hipChannelFormatDesc`                                      |
-| struct       |`cudaDeviceProp`                                     |                  |`hipDeviceProp_t`                                           |
-| struct       |`cudaEglFrame`                                       | 9.1              |                                                            |
-| typedef      |`cudaEglFrame_st`                                    | 9.1              |                                                            |
-| struct       |`cudaEglPlaneDesc`                                   | 9.1              |                                                            |
-| typedef      |`cudaEglPlaneDesc_st`                                | 9.1              |                                                            |
-| struct       |`cudaExtent`                                         |                  |`hipExtent`                                                 |
-| struct       |`cudaFuncAttributes`                                 |                  |`hipFuncAttributes`                                         |
-| struct       |`cudaIpcEventHandle_t`                               |                  |`hipIpcEventHandle_t`                                       |
-| struct       |`cudaIpcMemHandle_t`                                 |                  |`hipIpcMemHandle_t`                                         |
-| struct       |`cudaMemcpy3DParms`                                  |                  |`hipMemcpy3DParms`                                          |
-| struct       |`cudaMemcpy3DPeerParms`                              |                  |                                                            |
-| struct       |`cudaPitchedPtr`                                     |                  |`hipPitchedPtr`                                             |
-| struct       |`cudaPointerAttributes`                              |                  |`hipPointerAttribute_t`                                     |
-| struct       |`cudaPos`                                            |                  |`hipPos`                                                    |
-| struct       |`cudaResourceDesc`                                   |                  |`hipResourceDesc`                                           |
-| struct       |`cudaResourceViewDesc`                               |                  |`hipResourceViewDesc`                                       |
-| struct       |`cudaTextureDesc`                                    |                  |`hipTextureDesc`                                            |
-| struct       |`textureReference`                                   |                  |`textureReference`                                          |
-| struct       |`surfaceReference`                                   |                  |                                                            |
-| enum         |***`cudaCGScope`***                                  | 9.0              |                                                            |
-|            0 |*`cudaCGScopeInvalid`*                               | 9.0              |                                                            |
-|            1 |*`cudaCGScopeGrid`*                                  | 9.0              |                                                            |
-|            2 |*`cudaCGScopeMultiGrid`*                             | 9.0              |                                                            |
-| enum         |***`cudaChannelFormatKind`***                        |                  |***`hipChannelFormatKind`***                                |
-|            0 |*`cudaChannelFormatKindSigned`*                      |                  |*`hipChannelFormatKindSigned`*                              |
-|            1 |*`cudaChannelFormatKindUnsigned`*                    |                  |*`hipChannelFormatKindUnsigned`*                            |
-|            2 |*`cudaChannelFormatKindFloat`*                       |                  |*`hipChannelFormatKindFloat`*                               |
-|            3 |*`cudaChannelFormatKindNone`*                        |                  |*`hipChannelFormatKindNone`*                                |
-| enum         |***`cudaComputeMode`***                              |                  |***`hipComputeMode`***                                      |
-|            0 |*`cudaComputeModeDefault`*                           |                  |*`hipComputeModeDefault`*                                   |
-|            1 |*`cudaComputeModeExclusive`*                         |                  |*`hipComputeModeExclusive`*                                 |
-|            2 |*`cudaComputeModeProhibited`*                        |                  |*`hipComputeModeProhibited`*                                |
-|            3 |*`cudaComputeModeExclusiveProcess`*                  |                  |*`hipComputeModeExclusiveProcess`*                          |
-| enum         |***`cudaDeviceAttr`***                               |                  |***`hipDeviceAttribute_t`***                                |
-|            1 |*`cudaDevAttrMaxThreadsPerBlock`*                    |                  |*`hipDeviceAttributeMaxThreadsPerBlock`*                    |
-|            2 |*`cudaDevAttrMaxBlockDimX`*                          |                  |*`hipDeviceAttributeMaxBlockDimX`*                          |
-|            3 |*`cudaDevAttrMaxBlockDimY`*                          |                  |*`hipDeviceAttributeMaxBlockDimY`*                          |
-|            4 |*`cudaDevAttrMaxBlockDimZ`*                          |                  |*`hipDeviceAttributeMaxBlockDimZ`*                          |
-|            5 |*`cudaDevAttrMaxGridDimX`*                           |                  |*`hipDeviceAttributeMaxGridDimX`*                           |
-|            6 |*`cudaDevAttrMaxGridDimY`*                           |                  |*`hipDeviceAttributeMaxGridDimY`*                           |
-|            7 |*`cudaDevAttrMaxGridDimZ`*                           |                  |*`hipDeviceAttributeMaxGridDimZ`*                           |
-|            8 |*`cudaDevAttrMaxSharedMemoryPerBlock`*               |                  |*`hipDeviceAttributeMaxSharedMemoryPerBlock`*               |
-|            9 |*`cudaDevAttrTotalConstantMemory`*                   |                  |*`hipDeviceAttributeTotalConstantMemory`*                   |
-|           10 |*`cudaDevAttrWarpSize`*                              |                  |*`hipDeviceAttributeWarpSize`*                              |
-|           11 |*`cudaDevAttrMaxPitch`*                              |                  |*`hipDeviceAttributeMaxPitch`*                              |
-|           12 |*`cudaDevAttrMaxRegistersPerBlock`*                  |                  |*`hipDeviceAttributeMaxRegistersPerBlock`*                  |
-|           13 |*`cudaDevAttrClockRate`*                             |                  |*`hipDeviceAttributeClockRate`*                             |
-|           14 |*`cudaDevAttrTextureAlignment`*                      |                  |*`hipDeviceAttributeTextureAlignment`*                      |
-|           15 |*`cudaDevAttrGpuOverlap`*                            |                  |                                                            |
-|           16 |*`cudaDevAttrMultiProcessorCount`*                   |                  |*`hipDeviceAttributeMultiprocessorCount`*                   |
-|           17 |*`cudaDevAttrKernelExecTimeout`*                     |                  |*`hipDeviceAttributeKernelExecTimeout`*                     |
-|           18 |*`cudaDevAttrIntegrated`*                            |                  |*`hipDeviceAttributeIntegrated`*                            |
-|           19 |*`cudaDevAttrCanMapHostMemory`*                      |                  |*`hipDeviceAttributeCanMapHostMemory`*                      |
-|           20 |*`cudaDevAttrComputeMode`*                           |                  |*`hipDeviceAttributeComputeMode`*                           |
-|           21 |*`cudaDevAttrMaxTexture1DWidth`*                     |                  |*`hipDeviceAttributeMaxTexture1DWidth`*                     |
-|           22 |*`cudaDevAttrMaxTexture2DWidth`*                     |                  |*`hipDeviceAttributeMaxTexture2DWidth`*                     |
-|           23 |*`cudaDevAttrMaxTexture2DHeight`*                    |                  |*`hipDeviceAttributeMaxTexture2DHeight`*                    |
-|           24 |*`cudaDevAttrMaxTexture3DWidth`*                     |                  |*`hipDeviceAttributeMaxTexture3DWidth`*                     |
-|           25 |*`cudaDevAttrMaxTexture3DHeight`*                    |                  |*`hipDeviceAttributeMaxTexture3DHeight`*                    |
-|           26 |*`cudaDevAttrMaxTexture3DDepth`*                     |                  |*`hipDeviceAttributeMaxTexture3DDepth`*                     |
-|           27 |*`cudaDevAttrMaxTexture2DLayeredWidth`*              |                  |                                                            |
-|           28 |*`cudaDevAttrMaxTexture2DLayeredHeight`*             |                  |                                                            |
-|           29 |*`cudaDevAttrMaxTexture2DLayeredLayers`*             |                  |                                                            |
-|           30 |*`cudaDevAttrSurfaceAlignment`*                      |                  |                                                            |
-|           31 |*`cudaDevAttrConcurrentKernels`*                     |                  |*`hipDeviceAttributeConcurrentKernels`*                     |
-|           32 |*`cudaDevAttrEccEnabled`*                            |                  |*`hipDeviceAttributeEccEnabled`*                            |
-|           33 |*`cudaDevAttrPciBusId`*                              |                  |*`hipDeviceAttributePciBusId`*                              |
-|           34 |*`cudaDevAttrPciDeviceId`*                           |                  |*`hipDeviceAttributePciDeviceId`*                           |
-|           35 |*`cudaDevAttrTccDriver`*                             |                  |                                                            |
-|           36 |*`cudaDevAttrMemoryClockRate`*                       |                  |*`hipDeviceAttributeMemoryClockRate`*                       |
-|           37 |*`cudaDevAttrGlobalMemoryBusWidth`*                  |                  |*`hipDeviceAttributeMemoryBusWidth`*                        |
-|           38 |*`cudaDevAttrL2CacheSize`*                           |                  |*`hipDeviceAttributeL2CacheSize`*                           |
-|           39 |*`cudaDevAttrMaxThreadsPerMultiProcessor`*           |                  |*`hipDeviceAttributeMaxThreadsPerMultiProcessor`*           |
-|           40 |*`cudaDevAttrAsyncEngineCount`*                      |                  |                                                            |
-|           41 |*`cudaDevAttrUnifiedAddressing`*                     |                  |                                                            |
-|           42 |*`cudaDevAttrMaxTexture1DLayeredWidth`*              |                  |                                                            |
-|           43 |*`cudaDevAttrMaxTexture1DLayeredLayers`*             |                  |                                                            |
-|           44 |                                                     |                  |                                                            |
-|           45 |*`cudaDevAttrMaxTexture2DGatherWidth`*               |                  |                                                            |
-|           46 |*`cudaDevAttrMaxTexture2DGatherHeight`*              |                  |                                                            |
-|           47 |*`cudaDevAttrMaxTexture3DWidthAlt`*                  |                  |                                                            |
-|           48 |*`cudaDevAttrMaxTexture3DHeightAlt`*                 |                  |                                                            |
-|           49 |*`cudaDevAttrMaxTexture3DDepthAlt`*                  |                  |                                                            |
-|           50 |*`cudaDevAttrPciDomainId`*                           |                  |                                                            |
-|           51 |*`cudaDevAttrTexturePitchAlignment`*                 |                  |                                                            |
-|           52 |*`cudaDevAttrMaxTextureCubemapWidth`*                |                  |                                                            |
-|           53 |*`cudaDevAttrMaxTextureCubemapLayeredWidth`*         |                  |                                                            |
-|           54 |*`cudaDevAttrMaxTextureCubemapLayeredLayers`*        |                  |                                                            |
-|           55 |*`cudaDevAttrMaxSurface1DWidth`*                     |                  |                                                            |
-|           56 |*`cudaDevAttrMaxSurface2DWidth`*                     |                  |                                                            |
-|           57 |*`cudaDevAttrMaxSurface2DHeight`*                    |                  |                                                            |
-|           58 |*`cudaDevAttrMaxSurface3DWidth`*                     |                  |                                                            |
-|           59 |*`cudaDevAttrMaxSurface3DHeight`*                    |                  |                                                            |
-|           60 |*`cudaDevAttrMaxSurface3DDepth`*                     |                  |                                                            |
-|           61 |*`cudaDevAttrMaxSurface1DLayeredWidth`*              |                  |                                                            |
-|           62 |*`cudaDevAttrMaxSurface1DLayeredLayers`*             |                  |                                                            |
-|           63 |*`cudaDevAttrMaxSurface2DLayeredWidth`*              |                  |                                                            |
-|           64 |*`cudaDevAttrMaxSurface2DLayeredHeight`*             |                  |                                                            |
-|           65 |*`cudaDevAttrMaxSurface2DLayeredLayers`*             |                  |                                                            |
-|           66 |*`cudaDevAttrMaxSurfaceCubemapWidth`*                |                  |                                                            |
-|           67 |*`cudaDevAttrMaxSurfaceCubemapLayeredWidth`*         |                  |                                                            |
-|           68 |*`cudaDevAttrMaxSurfaceCubemapLayeredLayers`*        |                  |                                                            |
-|           69 |*`cudaDevAttrMaxTexture1DLinearWidth`*               |                  |                                                            |
-|           70 |*`cudaDevAttrMaxTexture2DLinearWidth`*               |                  |                                                            |
-|           71 |*`cudaDevAttrMaxTexture2DLinearHeight`*              |                  |                                                            |
-|           72 |*`cudaDevAttrMaxTexture2DLinearPitch`*               |                  |                                                            |
-|           73 |*`cudaDevAttrMaxTexture2DMipmappedWidth*             |                  |                                                            |
-|           74 |*`cudaDevAttrMaxTexture2DMipmappedHeight`*           |                  |                                                            |
-|           75 |*`cudaDevAttrComputeCapabilityMajor`*                |                  |*`hipDeviceAttributeComputeCapabilityMajor`*                |
-|           76 |*`cudaDevAttrComputeCapabilityMinor`*                |                  |*`hipDeviceAttributeComputeCapabilityMinor`*                |
-|           77 |*`cudaDevAttrMaxTexture1DMipmappedWidth`*            |                  |                                                            |
-|           78 |*`cudaDevAttrStreamPrioritiesSupported`*             |                  |                                                            |
-|           79 |*`cudaDevAttrGlobalL1CacheSupported`*                |                  |                                                            |
-|           80 |*`cudaDevAttrLocalL1CacheSupported`*                 |                  |                                                            |
-|           81 |*`cudaDevAttrMaxSharedMemoryPerMultiprocessor`*      |                  |*`hipDeviceAttributeMaxSharedMemoryPerMultiprocessor`*      |
-|           82 |*`cudaDevAttrMaxRegistersPerMultiprocessor`*         |                  |                                                            |
-|           83 |*`cudaDevAttrManagedMemory`*                         |                  |                                                            |
-|           84 |*`cudaDevAttrIsMultiGpuBoard`*                       |                  |*`hipDeviceAttributeIsMultiGpuBoard`*                       |
-|           85 |*`cudaDevAttrMultiGpuBoardGroupID`*                  |                  |                                                            |
-|           86 |*`cudaDevAttrHostNativeAtomicSupported`*             | 8.0              |                                                            |
-|           87 |*`cudaDevAttrSingleToDoublePrecisionPerfRatio`*      | 8.0              |                                                            |
-|           88 |*`cudaDevAttrPageableMemoryAccess`*                  | 8.0              |                                                            |
-|           89 |*`cudaDevAttrConcurrentManagedAccess`*               | 8.0              |                                                            |
-|           90 |*`cudaDevAttrComputePreemptionSupported`*            | 8.0              |                                                            |
-|           91 |*`cudaDevAttrCanUseHostPointerForRegisteredMem`*     | 8.0              |                                                            |
-|           92 |*`cudaDevAttrReserved92`*                            | 9.0              |                                                            |
-|           93 |*`cudaDevAttrReserved93`*                            | 9.0              |                                                            |
-|           94 |*`cudaDevAttrReserved94`*                            | 9.0              |                                                            |
-|           95 |*`cudaDevAttrCooperativeLaunch`*                     | 9.0              |*`hipDeviceAttributeCooperativeLaunch`*                     |
-|           96 |*`cudaDevAttrCooperativeMultiDeviceLaunch`*          | 9.0              |*`hipDeviceAttributeCooperativeMultiDeviceLaunch`*          |
-|           97 |*`cudaDevAttrMaxSharedMemoryPerBlockOptin`*          | 9.0              |                                                            |
-|           98 |*`cudaDevAttrCanFlushRemoteWrites`*                  | 9.2              |                                                            |
-|           99 |*`cudaDevAttrHostRegisterSupported`*                 | 9.2              |                                                            |
-|          100 |*`cudaDevAttrPageableMemoryAccessUsesHostPageTables`*| 9.2              |                                                            |
-|          101 |*`cudaDevAttrDirectManagedMemAccessFromHost`*        | 9.2              |                                                            |
-| enum         |***`cudaDeviceP2PAttr`***                            | 8.0              |                                                            |
-|            1 |*`cudaDevP2PAttrPerformanceRank`*                    | 8.0              |                                                            |
-|            2 |*`cudaDevP2PAttrAccessSupported`*                    | 8.0              |                                                            |
-|            3 |*`cudaDevP2PAttrNativeAtomicSupported`*              | 8.0              |                                                            |
-|            4 |*`cudaDevP2PAttrCudaArrayAccessSupported`*           | 9.2              |                                                            |
-| enum         |***`cudaEglColorFormat`***                           | 9.1              |                                                            |
-|            0 |*`cudaEglColorFormatYUV420Planar`*                   | 9.1              |                                                            |
-|            1 |*`cudaEglColorFormatYUV420SemiPlanar`*               | 9.1              |                                                            |
-|            2 |*`cudaEglColorFormatYUV422Planar`*                   | 9.1              |                                                            |
-|            3 |*`cudaEglColorFormatYUV422SemiPlanar`*               | 9.1              |                                                            |
-|            4 |*`cudaEglColorFormatRGB`*                            | 9.1              |                                                            |
-|            5 |*`cudaEglColorFormatBGR`*                            | 9.1              |                                                            |
-|            6 |*`cudaEglColorFormatARGB`*                           | 9.1              |                                                            |
-|            7 |*`cudaEglColorFormatRGBA`*                           | 9.1              |                                                            |
-|            8 |*`cudaEglColorFormatL`*                              | 9.1              |                                                            |
-|            9 |*`cudaEglColorFormatR`*                              | 9.1              |                                                            |
-|           10 |*`cudaEglColorFormatYUV444Planar`*                   | 9.1              |                                                            |
-|           11 |*`cudaEglColorFormatYUV444SemiPlanar`*               | 9.1              |                                                            |
-|           12 |*`cudaEglColorFormatYUYV422`*                        | 9.1              |                                                            |
-|           13 |*`cudaEglColorFormatUYVY422`*                        | 9.1              |                                                            |
-|           14 |*`cudaEglColorFormatABGR`*                           | 9.1              |                                                            |
-|           15 |*`cudaEglColorFormatBGRA`*                           | 9.1              |                                                            |
-|           16 |*`cudaEglColorFormatA`*                              | 9.1              |                                                            |
-|           17 |*`cudaEglColorFormatRG`*                             | 9.1              |                                                            |
-|           18 |*`cudaEglColorFormatAYUV`*                           | 9.1              |                                                            |
-|           19 |*`cudaEglColorFormatYVU444SemiPlanar`*               | 9.1              |                                                            |
-|           20 |*`cudaEglColorFormatYVU422SemiPlanar`*               | 9.1              |                                                            |
-|           21 |*`cudaEglColorFormatYVU420SemiPlanar`*               | 9.1              |                                                            |
-|           22 |*`cudaEglColorFormatY10V10U10_444SemiPlanar`*        | 9.1              |                                                            |
-|           23 |*`cudaEglColorFormatY10V10U10_420SemiPlanar`*        | 9.1              |                                                            |
-|           24 |*`cudaEglColorFormatY12V12U12_444SemiPlanar`*        | 9.1              |                                                            |
-|           25 |*`cudaEglColorFormatY12V12U12_420SemiPlanar`*        | 9.1              |                                                            |
-|           26 |*`cudaEglColorFormatVYUY_ER`*                        | 9.1              |                                                            |
-|           27 |*`cudaEglColorFormatUYVY_ER`*                        | 9.1              |                                                            |
-|           28 |*`cudaEglColorFormatYUYV_ER`*                        | 9.1              |                                                            |
-|           29 |*`cudaEglColorFormatYVYU_ER`*                        | 9.1              |                                                            |
-|           30 |*`cudaEglColorFormatYUV_ER`*                         | 9.1              |                                                            |
-|           31 |*`cudaEglColorFormatYUVA_ER`*                        | 9.1              |                                                            |
-|           32 |*`cudaEglColorFormatAYUV_ER`*                        | 9.1              |                                                            |
-|           33 |*`cudaEglColorFormatYUV444Planar_ER`*                | 9.1              |                                                            |
-|           34 |*`cudaEglColorFormatYUV422Planar_ER`*                | 9.1              |                                                            |
-|           35 |*`cudaEglColorFormatYUV420Planar_ER`*                | 9.1              |                                                            |
-|           36 |*`cudaEglColorFormatYUV444SemiPlanar_ER`*            | 9.1              |                                                            |
-|           37 |*`cudaEglColorFormatYUV422SemiPlanar_ER`*            | 9.1              |                                                            |
-|           38 |*`cudaEglColorFormatYUV420SemiPlanar_ER`*            | 9.1              |                                                            |
-|           39 |*`cudaEglColorFormatYVU444Planar_ER`*                | 9.1              |                                                            |
-|           40 |*`cudaEglColorFormatYVU422Planar_ER`*                | 9.1              |                                                            |
-|           41 |*`cudaEglColorFormatYVU420Planar_ER`*                | 9.1              |                                                            |
-|           42 |*`cudaEglColorFormatYVU444SemiPlanar_ER`*            | 9.1              |                                                            |
-|           43 |*`cudaEglColorFormatYVU422SemiPlanar_ER`*            | 9.1              |                                                            |
-|           44 |*`cudaEglColorFormatYVU420SemiPlanar_ER`*            | 9.1              |                                                            |
-|           45 |*`cudaEglColorFormatBayerRGGB`*                      | 9.1              |                                                            |
-|           46 |*`cudaEglColorFormatBayerBGGR`*                      | 9.1              |                                                            |
-|           47 |*`cudaEglColorFormatBayerGRBG`*                      | 9.1              |                                                            |
-|           48 |*`cudaEglColorFormatBayerGBRG`*                      | 9.1              |                                                            |
-|           49 |*`cudaEglColorFormatBayer10RGGB`*                    | 9.1              |                                                            |
-|           50 |*`cudaEglColorFormatBayer10BGGR`*                    | 9.1              |                                                            |
-|           51 |*`cudaEglColorFormatBayer10GRBG`*                    | 9.1              |                                                            |
-|           52 |*`cudaEglColorFormatBayer10GBRG`*                    | 9.1              |                                                            |
-|           53 |*`cudaEglColorFormatBayer12RGGB`*                    | 9.1              |                                                            |
-|           54 |*`cudaEglColorFormatBayer12BGGR`*                    | 9.1              |                                                            |
-|           55 |*`cudaEglColorFormatBayer12GRBG`*                    | 9.1              |                                                            |
-|           56 |*`cudaEglColorFormatBayer12GBRG`*                    | 9.1              |                                                            |
-|           57 |*`cudaEglColorFormatBayer14RGGB`*                    | 9.1              |                                                            |
-|           58 |*`cudaEglColorFormatBayer14BGGR`*                    | 9.1              |                                                            |
-|           59 |*`cudaEglColorFormatBayer14GRBG`*                    | 9.1              |                                                            |
-|           60 |*`cudaEglColorFormatBayer14GBRG`*                    | 9.1              |                                                            |
-|           61 |*`cudaEglColorFormatBayer20RGGB`*                    | 9.1              |                                                            |
-|           62 |*`cudaEglColorFormatBayer20BGGR`*                    | 9.1              |                                                            |
-|           63 |*`cudaEglColorFormatBayer20GRBG`*                    | 9.1              |                                                            |
-|           64 |*`cudaEglColorFormatBayer20GBRG`*                    | 9.1              |                                                            |
-|           65 |*`cudaEglColorFormatYVU444Planar`*                   | 9.1              |                                                            |
-|           66 |*`cudaEglColorFormatYVU422Planar`*                   | 9.1              |                                                            |
-|           67 |*`cudaEglColorFormatYVU420Planar`*                   | 9.1              |                                                            |
-|           68 |*`cudaEglColorFormatBayerIspRGGB`*                   | 9.2              |                                                            |
-|           69 |*`cudaEglColorFormatBayerIspBGGR`*                   | 9.2              |                                                            |
-|           70 |*`cudaEglColorFormatBayerIspGRBG`*                   | 9.2              |                                                            |
-|           71 |*`cudaEglColorFormatBayerIspGBRG`*                   | 9.2              |                                                            |
-| enum         |***`cudaEglFrameType`***                             | 9.1              |                                                            |
-|            0 |*`cudaEglFrameTypeArray`*                            | 9.1              |                                                            |
-|            1 |*`cudaEglFrameTypePitch`*                            | 9.1              |                                                            |
-| enum         |***`cudaExternalMemoryHandleType`***                 | 10.0             |                                                            |
-|            1 |*`cudaExternalMemoryHandleTypeOpaqueFd`*             | 10.0             |                                                            |
-|            2 |*`cudaExternalMemoryHandleTypeOpaqueWin32`*          | 10.0             |                                                            |
-|            3 |*`cudaExternalMemoryHandleTypeOpaqueWin32Kmt`*       | 10.0             |                                                            |
-|            4 |*`cudaExternalMemoryHandleTypeD3D12Heap`*            | 10.0             |                                                            |
-|            5 |*`cudaExternalMemoryHandleTypeD3D12Resource`*        | 10.0             |                                                            |
-|            6 |*`cudaExternalMemoryHandleTypeD3D11Resource`*        | 10.2             |                                                            |
-|            7 |*`cudaExternalMemoryHandleTypeD3D11ResourceKmt`*     | 10.2             |                                                            |
-|            8 |*`cudaExternalMemoryHandleTypeNvSciBuf`*             | 10.2             |                                                            |
-| enum         |***`cudaExternalSemaphoreHandleType`***              | 10.0             |                                                            |
-|            1 |*`cudaExternalSemaphoreHandleTypeOpaqueFd`*          | 10.0             |                                                            |
-|            2 |*`cudaExternalSemaphoreHandleTypeOpaqueWin32`*       | 10.0             |                                                            |
-|            3 |*`cudaExternalSemaphoreHandleTypeOpaqueWin32Kmt`*    | 10.0             |                                                            |
-|            4 |*`cudaExternalSemaphoreHandleTypeD3D12Fence`*        | 10.0             |                                                            |
-|            5 |*`cudaExternalSemaphoreHandleTypeD3D11Fence`*        | 10.2             |                                                            |
-|            6 |*`cudaExternalSemaphoreHandleTypeNvSciSync`*         | 10.2             |                                                            |
-|            7 |*`cudaExternalSemaphoreHandleTypeKeyedMutex`*        | 10.2             |                                                            |
-|            8 |*`cudaExternalSemaphoreHandleTypeKeyedMutexKmt`*     | 10.2             |                                                            |
-| enum         |***`cudaFuncAttribute`***                            | 9.0              |                                                            |
-|            8 |*`cudaFuncAttributeMaxDynamicSharedMemorySize`*      | 9.0              |                                                            |
-|            9 |*`cudaFuncAttributePreferredSharedMemoryCarveout`*   | 9.0              |                                                            |
-|           10 |*`cudaFuncAttributeMax`*                             | 9.0              |                                                            |
-| enum         |***`cudaEglResourceLocationFlags`***                 | 9.1              |                                                            |
-|         0x00 |*`cudaEglResourceLocationSysmem`*                    | 9.1              |                                                            |
-|         0x01 |*`cudaEglResourceLocationVidmem`*                    | 9.1              |                                                            |
-| enum         |***`cudaError`***                                    |                  |***`hipError_t`***                                          |
-| typedef      |***`cudaError_t`***                                  |                  |***`hipError_t`***                                          |
-|            0 |*`cudaSuccess`*                                      |                  |*`hipSuccess`*                                              |
-|            1 |*`cudaErrorInvalidValue`*                            |                  |*`hipErrorInvalidValue`*                                    |
-|            2 |*`cudaErrorMemoryAllocation`*                        |                  |*`hipErrorOutOfMemory`*                                     |
-|            3 |*`cudaErrorInitializationError`*                     |                  |*`hipErrorNotInitialized`*                                  |
-|            4 |*`cudaErrorCudartUnloading`*                         |                  |*`hipErrorDeinitialized`*                                   |
-|            5 |*`cudaErrorProfilerDisabled`*                        |                  |*`hipErrorProfilerDisabled`*                                |
-|            6 |*`cudaErrorProfilerNotInitialized`*                  |                  |*`hipErrorProfilerNotInitialized`*                          |
-|            7 |*`cudaErrorProfilerAlreadyStarted`*                  |                  |*`hipErrorProfilerAlreadyStarted`*                          |
-|            8 |*`cudaErrorProfilerAlreadyStopped`*                  |                  |*`hipErrorProfilerAlreadyStopped`*                          |
-|            9 |*`cudaErrorInvalidConfiguration`*                    |                  |*`hipErrorInvalidConfiguration`*                            |
-|           12 |*`cudaErrorInvalidPitchValue`*                       |                  |                                                            |
-|           13 |*`cudaErrorInvalidSymbol`*                           |                  |*`hipErrorInvalidSymbol`*                                   |
-|           16 |*`cudaErrorInvalidHostPointer`*                      |                  |                                                            |
-|           17 |*`cudaErrorInvalidDevicePointer`*                    |                  |*`hipErrorInvalidDevicePointer`*                            |
-|           18 |*`cudaErrorInvalidTexture`*                          |                  |                                                            |
-|           19 |*`cudaErrorInvalidTextureBinding`*                   |                  |                                                            |
-|           20 |*`cudaErrorInvalidChannelDescriptor`*                |                  |                                                            |
-|           21 |*`cudaErrorInvalidMemcpyDirection`*                  |                  |*`hipErrorInvalidMemcpyDirection`*                          |
-|           22 |*`cudaErrorAddressOfConstant`*                       |                  |                                                            |
-|           23 |*`cudaErrorTextureFetchFailed`*                      |                  |                                                            |
-|           24 |*`cudaErrorTextureNotBound`*                         |                  |                                                            |
-|           25 |*`cudaErrorSynchronizationError`*                    |                  |                                                            |
-|           26 |*`cudaErrorInvalidFilterSetting`*                    |                  |                                                            |
-|           27 |*`cudaErrorInvalidNormSetting`*                      |                  |                                                            |
-|           28 |*`cudaErrorMixedDeviceExecution`*                    |                  |                                                            |
-|           31 |*`cudaErrorNotYetImplemented`*                       |                  |                                                            |
-|           32 |*`cudaErrorMemoryValueTooLarge`*                     |                  |                                                            |
-|           35 |*`cudaErrorInsufficientDriver`*                      |                  |*`hipErrorInsufficientDriver`*                              |
-|           37 |*`cudaErrorInvalidSurface`*                          |                  |                                                            |
-|           43 |*`cudaErrorDuplicateVariableName`*                   |                  |                                                            |
-|           44 |*`cudaErrorDuplicateTextureName`*                    |                  |                                                            |
-|           45 |*`cudaErrorDuplicateSurfaceName`*                    |                  |                                                            |
-|           46 |*`cudaErrorDevicesUnavailable`*                      |                  |                                                            |
-|           49 |*`cudaErrorIncompatibleDriverContext`*               |                  |                                                            |
-|           52 |*`cudaErrorMissingConfiguration`*                    |                  |*`hipErrorMissingConfiguration`*                            |
-|           53 |*`cudaErrorPriorLaunchFailure`*                      |                  |*`hipErrorPriorLaunchFailure`*                              |
-|           65 |*`cudaErrorLaunchMaxDepthExceeded`*                  |                  |                                                            |
-|           66 |*`cudaErrorLaunchFileScopedTex`*                     |                  |                                                            |
-|           67 |*`cudaErrorLaunchFileScopedSurf`*                    |                  |                                                            |
-|           68 |*`cudaErrorSyncDepthExceeded`*                       |                  |                                                            |
-|           69 |*`cudaErrorLaunchPendingCountExceeded`*              |                  |                                                            |
-|           98 |*`cudaErrorInvalidDeviceFunction`*                   |                  |*`hipErrorInvalidDeviceFunction`*                           |
-|          100 |*`cudaErrorNoDevice`*                                |                  |*`hipErrorNoDevice`*                                        |
-|          101 |*`cudaErrorInvalidDevice`*                           |                  |*`hipErrorInvalidDevice`*                                   |
-|          127 |*`cudaErrorStartupFailure`*                          | 10.0             |                                                            |
-|          200 |*`cudaErrorInvalidKernelImage`*                      |                  |*`hipErrorInvalidImage`*                                    |
-|          201 |*`cudaErrorDeviceUninitilialized`*                   |                  |*`hipErrorInvalidContext`*                                  |
-|          205 |*`cudaErrorMapBufferObjectFailed`*                   |                  |*`hipErrorMapFailed`*                                       |
-|          206 |*`cudaErrorUnmapBufferObjectFailed`*                 |                  |*`hipErrorUnmapFailed`*                                     |
-|          209 |*`cudaErrorNoKernelImageForDevice`*                  |                  |*`hipErrorNoBinaryForGpu`*                                  |
-|          214 |*`cudaErrorECCUncorrectable`*                        |                  |*`hipErrorECCNotCorrectable`*                               |
-|          215 |*`cudaErrorUnsupportedLimit`*                        |                  |*`hipErrorUnsupportedLimit`*                                |
-|          216 |*`cudaErrorDeviceAlreadyInUse`*                      |                  |                                                            |
-|          217 |*`cudaErrorPeerAccessUnsupported`*                   |                  |*`hipErrorPeerAccessUnsupported`*                           |
-|          218 |*`cudaErrorInvalidPtx`*                              |                  |*`hipErrorInvalidKernelFile`*                               |
-|          219 |*`cudaErrorInvalidGraphicsContext`*                  |                  |*`hipErrorInvalidGraphicsContext`*                          |
-|          220 |*`cudaErrorNvlinkUncorrectable`*                     | 8.0              |                                                            |
-|          221 |*`cudaErrorJitCompilerNotFound`*                     | 9.0              |                                                            |
-|          300 |*`cudaErrorInvalidSource`*                           | 10.1             |*`hipErrorInvalidSource`*                                   |
-|          301 |*`cudaErrorFileNotFound`*                            | 10.1             |*`hipErrorFileNotFound`*                                    |
-|          302 |*`cudaErrorSharedObjectSymbolNotFound`*              |                  |*`hipErrorSharedObjectSymbolNotFound`*                      |
-|          303 |*`cudaErrorSharedObjectInitFailed`*                  |                  |*`hipErrorSharedObjectInitFailed`*                          |
-|          304 |*`cudaErrorOperatingSystem`*                         |                  |*`hipErrorOperatingSystem`*                                 |
-|          400 |*`cudaErrorInvalidResourceHandle`*                   |                  |*`hipErrorInvalidHandle`*                                   |
-|          401 |*`cudaErrorIllegalState`*                            | 10.0             |                                                            |
-|          500 |*`cudaErrorSymbolNotFound`*                          | 10.1             |*`hipErrorNotFound`*                                        |
-|          600 |*`cudaErrorNotReady`*                                |                  |*`hipErrorNotReady`*                                        |
-|          700 |*`cudaErrorIllegalAddress`*                          |                  |*`hipErrorIllegalAddress`*                                  |
-|          701 |*`cudaErrorLaunchOutOfResources`*                    |                  |*`hipErrorLaunchOutOfResources`*                            |
-|          702 |*`cudaErrorLaunchTimeout`*                           |                  |*`hipErrorLaunchTimeOut`*                                   |
-|          703 |*`cudaErrorLaunchIncompatibleTexturing`*             |                  |                                                            |
-|          704 |*`cudaErrorPeerAccessAlreadyEnabled`*                |                  |*`hipErrorPeerAccessAlreadyEnabled`*                        |
-|          705 |*`cudaErrorPeerAccessNotEnabled`*                    |                  |*`hipErrorPeerAccessNotEnabled`*                            |
-|          708 |*`cudaErrorSetOnActiveProcess`*                      |                  |*`hipErrorSetOnActiveProcess`*                              |
-|          709 |*`cudaErrorContextIsDestroyed`*                      |                  |                                                            |
-|          710 |*`cudaErrorAssert`*                                  |                  |*`hipErrorAssert`*                                          |
-|          711 |*`cudaErrorTooManyPeers`*                            |                  |                                                            |
-|          712 |*`cudaErrorHostMemoryAlreadyRegistered`*             |                  |*`hipErrorHostMemoryAlreadyRegistered`*                     |
-|          713 |*`cudaErrorHostMemoryNotRegistered`*                 |                  |*`hipErrorHostMemoryNotRegistered`*                         |
-|          714 |*`cudaErrorHardwareStackError`*                      |                  |                                                            |
-|          715 |*`cudaErrorIllegalInstruction`*                      |                  |                                                            |
-|          716 |*`cudaErrorMisalignedAddress`*                       |                  |                                                            |
-|          717 |*`cudaErrorInvalidAddressSpace`*                     |                  |                                                            |
-|          718 |*`cudaErrorInvalidPc`*                               |                  |                                                            |
-|          719 |*`cudaErrorLaunchFailure`*                           |                  |*`hipErrorLaunchFailure`*                                   |
-|          720 |*`cudaErrorCooperativeLaunchTooLarge`*               | 9.0              |*`hipErrorCooperativeLaunchTooLarge`*                       |
-|          800 |*`cudaErrorNotPermitted`*                            |                  |                                                            |
-|          801 |*`cudaErrorNotSupported`*                            |                  |*`hipErrorNotSupported`*                                    |
-|          802 |*`cudaErrorSystemNotReady`*                          | 10.0             |                                                            |
-|          803 |*`cudaErrorSystemDriverMismatch`*                    | 10.0             |                                                            |
-|          804 |*`cudaErrorCompatNotSupportedOnDevice`*              | 10.0             |                                                            |
-|          900 |*`cudaErrorStreamCaptureUnsupported`*                | 10.0             |                                                            |
-|          901 |*`cudaErrorStreamCaptureInvalidated`*                | 10.0             |                                                            |
-|          902 |*`cudaErrorStreamCaptureMerge`*                      | 10.0             |                                                            |
-|          903 |*`cudaErrorStreamCaptureUnmatched`*                  | 10.0             |                                                            |
-|          904 |*`cudaErrorStreamCaptureUnjoined`*                   | 10.0             |                                                            |
-|          905 |*`cudaErrorStreamCaptureIsolation`*                  | 10.0             |                                                            |
-|          906 |*`cudaErrorStreamCaptureImplicit`*                   | 10.0             |                                                            |
-|          907 |*`cudaErrorCapturedEvent`*                           | 10.0             |                                                            |
-|          908 |*`cudaErrorStreamCaptureWrongThread`*                | 10.1             |                                                            |
-|          909 |*`cudaErrorTimeout`*                                 | 10.2             |                                                            |
-|          910 |*`cudaErrorGraphExecUpdateFailure`*                  | 10.2             |                                                            |
-|          999 |*`cudaErrorUnknown`*                                 |                  |*`hipErrorUnknown`*                                         |
-|        10000 |*`cudaErrorApiFailureBase`*                          |                  |                                                            |
-| enum         |***`cudaFuncCache`***                                |                  |***`hipFuncCache_t`***                                      |
-|            0 |*`cudaFuncCachePreferNone`*                          |                  |*`hipFuncCachePreferNone`*                                  |
-|            1 |*`cudaFuncCachePreferShared`*                        |                  |*`hipFuncCachePreferShared`*                                |
-|            2 |*`cudaFuncCachePreferL1`*                            |                  |*`hipFuncCachePreferL1`*                                    |
-|            3 |*`cudaFuncCachePreferEqual`*                         |                  |*`hipFuncCachePreferEqual`*                                 |
-| enum         |***`cudaGraphicsCubeFace`***                         |                  |                                                            |
-|         0x00 |*`cudaGraphicsCubeFacePositiveX`*                    |                  |                                                            |
-|         0x01 |*`cudaGraphicsCubeFaceNegativeX`*                    |                  |                                                            |
-|         0x02 |*`cudaGraphicsCubeFacePositiveY`*                    |                  |                                                            |
-|         0x03 |*`cudaGraphicsCubeFaceNegativeY`*                    |                  |                                                            |
-|         0x04 |*`cudaGraphicsCubeFacePositiveZ`*                    |                  |                                                            |
-|         0x05 |*`cudaGraphicsCubeFaceNegativeZ`*                    |                  |                                                            |
-| enum         |***`cudaGraphicsMapFlags`***                         |                  |                                                            |
-|            0 |*`cudaGraphicsMapFlagsNone`*                         |                  |                                                            |
-|            1 |*`cudaGraphicsMapFlagsReadOnly`*                     |                  |                                                            |
-|            2 |*`cudaGraphicsMapFlagsWriteDiscard`*                 |                  |                                                            |
-| enum         |***`cudaGraphicsRegisterFlags`***                    |                  |                                                            |
-|            0 |*`cudaGraphicsRegisterFlagsNone`*                    |                  |                                                            |
-|            1 |*`cudaGraphicsRegisterFlagsReadOnly`*                |                  |                                                            |
-|            2 |*`cudaGraphicsRegisterFlagsWriteDiscard`*            |                  |                                                            |
-|            4 |*`cudaGraphicsRegisterFlagsSurfaceLoadStore`*        |                  |                                                            |
-|            8 |*`cudaGraphicsRegisterFlagsTextureGather`*           |                  |                                                            |
-| enum         |***`cudaGraphNodeType`***                            | 10.0             |                                                            |
-|         0x00 |*`cudaGraphNodeTypeKernel`*                          | 10.0             |                                                            |
-|         0x01 |*`cudaGraphNodeTypeMemcpy`*                          | 10.0             |                                                            |
-|         0x02 |*`cudaGraphNodeTypeMemset`*                          | 10.0             |                                                            |
-|         0x03 |*`cudaGraphNodeTypeHost`*                            | 10.0             |                                                            |
-|         0x04 |*`cudaGraphNodeTypeGraph`*                           | 10.0             |                                                            |
-|         0x05 |*`cudaGraphNodeTypeEmpty`*                           | 10.0             |                                                            |
-|              |*`cudaGraphNodeTypeCount`*                           | 10.0             |                                                            |
-| enum         |***`cudaLimit`***                                    |                  |***`hipLimit_t`***                                          |
-|         0x00 |*`cudaLimitStackSize`*                               |                  |                                                            |
-|         0x01 |*`cudaLimitPrintfFifoSize`*                          |                  |*`hipLimitPrintfFifoSize`*                                  |
-|         0x02 |*`cudaLimitMallocHeapSize`*                          |                  |*`hipLimitMallocHeapSize`*                                  |
-|         0x03 |*`cudaLimitDevRuntimeSyncDepth`*                     |                  |                                                            |
-|         0x04 |*`cudaLimitDevRuntimePendingLaunchCount`*            |                  |                                                            |
-|         0x05 |*`cudaLimitMaxL2FetchGranularity`*                   | 10.0             |                                                            |
-| enum         |***`cudaMemcpyKind`***                               |                  |***`hipMemcpyKind`***                                       |
-|            0 |*`cudaMemcpyHostToHost`*                             |                  |*`hipMemcpyHostToHost`*                                     |
-|            1 |*`cudaMemcpyHostToDevice`*                           |                  |*`hipMemcpyHostToDevice`*                                   |
-|            2 |*`cudaMemcpyDeviceToHost`*                           |                  |*`hipMemcpyDeviceToHost`*                                   |
-|            3 |*`cudaMemcpyDeviceToDevice`*                         |                  |*`hipMemcpyDeviceToDevice`*                                 |
-|            4 |*`cudaMemcpyDefault`*                                |                  |*`hipMemcpyDefault`*                                        |
-| enum         |***`cudaMemoryAdvise`***                             | 8.0              |                                                            |
-|            1 |*`cudaMemAdviseSetReadMostly`*                       | 8.0              |                                                            |
-|            2 |*`cudaMemAdviseUnsetReadMostly`*                     | 8.0              |                                                            |
-|            3 |*`cudaMemAdviseSetPreferredLocation`*                | 8.0              |                                                            |
-|            4 |*`cudaMemAdviseUnsetPreferredLocation`*              | 8.0              |                                                            |
-|            5 |*`cudaMemAdviseSetAccessedBy`*                       | 8.0              |                                                            |
-|            6 |*`cudaMemAdviseUnsetAccessedBy`*                     | 8.0              |                                                            |
-| enum         |***`cudaMemoryType`***                               |                  |                                                            |
-|            0 |*`cudaMemoryTypeUnregistered`*                       |                  |                                                            |
-|            1 |*`cudaMemoryTypeHost`*                               |                  |                                                            |
-|            2 |*`cudaMemoryTypeDevice`*                             |                  |                                                            |
-|            3 |*`cudaMemoryTypeManaged`*                            | 10.0             |                                                            |
-| enum         |***`cudaMemRangeAttribute`***                        | 8.0              |                                                            |
-|            1 |*`cudaMemRangeAttributeReadMostly`*                  | 8.0              |                                                            |
-|            2 |*`cudaMemRangeAttributePreferredLocation`*           | 8.0              |                                                            |
-|            3 |*`cudaMemRangeAttributeAccessedBy`*                  | 8.0              |                                                            |
-|            4 |*`cudaMemRangeAttributeLastPrefetchLocation`*        | 8.0              |                                                            |
-| enum         |***`cudaResourceType`***                             |                  |***`hipResourceType`***                                     |
-|         0x00 |*`cudaResourceTypeArray`*                            |                  |*`hipResourceTypeArray`*                                    |
-|         0x01 |*`cudaResourceTypeMipmappedArray`*                   |                  |*`hipResourceTypeMipmappedArray`*                           |
-|         0x02 |*`cudaResourceTypeLinear`*                           |                  |*`hipResourceTypeLinear`*                                   |
-|         0x03 |*`cudaResourceTypePitch2D`*                          |                  |*`hipResourceTypePitch2D`*                                  |
-| enum         |***`cudaResourceViewFormat`***                       |                  |***`hipResourceViewFormat`***                               |
-|         0x00 |*`cudaResViewFormatNone`*                            |                  |*`hipResViewFormatNone`*                                    |
-|         0x01 |*`cudaResViewFormatUnsignedChar1`*                   |                  |*`hipResViewFormatUnsignedChar1`*                           |
-|         0x02 |*`cudaResViewFormatUnsignedChar2`*                   |                  |*`hipResViewFormatUnsignedChar2`*                           |
-|         0x03 |*`cudaResViewFormatUnsignedChar4`*                   |                  |*`hipResViewFormatUnsignedChar4`*                           |
-|         0x04 |*`cudaResViewFormatSignedChar1`*                     |                  |*`hipResViewFormatSignedChar1`*                             |
-|         0x05 |*`cudaResViewFormatSignedChar2`*                     |                  |*`hipResViewFormatSignedChar2`*                             |
-|         0x06 |*`cudaResViewFormatSignedChar4`*                     |                  |*`hipResViewFormatSignedChar4`*                             |
-|         0x07 |*`cudaResViewFormatUnsignedShort1`*                  |                  |*`hipResViewFormatUnsignedShort1`*                          |
-|         0x08 |*`cudaResViewFormatUnsignedShort2`*                  |                  |*`hipResViewFormatUnsignedShort2`*                          |
-|         0x09 |*`cudaResViewFormatUnsignedShort4`*                  |                  |*`hipResViewFormatUnsignedShort4`*                          |
-|         0x0a |*`cudaResViewFormatSignedShort1`*                    |                  |*`hipResViewFormatSignedShort1`*                            |
-|         0x0b |*`cudaResViewFormatSignedShort2`*                    |                  |*`hipResViewFormatSignedShort2`*                            |
-|         0x0c |*`cudaResViewFormatSignedShort4`*                    |                  |*`hipResViewFormatSignedShort4`*                            |
-|         0x0d |*`cudaResViewFormatUnsignedInt1`*                    |                  |*`hipResViewFormatUnsignedInt1`*                            |
-|         0x0e |*`cudaResViewFormatUnsignedInt2`*                    |                  |*`hipResViewFormatUnsignedInt2`*                            |
-|         0x0f |*`cudaResViewFormatUnsignedInt4`*                    |                  |*`hipResViewFormatUnsignedInt4`*                            |
-|         0x10 |*`cudaResViewFormatSignedInt1`*                      |                  |*`hipResViewFormatSignedInt1`*                              |
-|         0x11 |*`cudaResViewFormatSignedInt2`*                      |                  |*`hipResViewFormatSignedInt2`*                              |
-|         0x12 |*`cudaResViewFormatSignedInt4`*                      |                  |*`hipResViewFormatSignedInt4`*                              |
-|         0x13 |*`cudaResViewFormatHalf1`*                           |                  |*`hipResViewFormatHalf1`*                                   |
-|         0x14 |*`cudaResViewFormatHalf2`*                           |                  |*`hipResViewFormatHalf2`*                                   |
-|         0x15 |*`cudaResViewFormatHalf4`*                           |                  |*`hipResViewFormatHalf4`*                                   |
-|         0x16 |*`cudaResViewFormatFloat1`*                          |                  |*`hipResViewFormatFloat1`*                                  |
-|         0x17 |*`cudaResViewFormatFloat2`*                          |                  |*`hipResViewFormatFloat2`*                                  |
-|         0x18 |*`cudaResViewFormatFloat4`*                          |                  |*`hipResViewFormatFloat4`*                                  |
-|         0x19 |*`cudaResViewFormatUnsignedBlockCompressed1`*        |                  |*`hipResViewFormatUnsignedBlockCompressed1`*                |
-|         0x1a |*`cudaResViewFormatUnsignedBlockCompressed2`*        |                  |*`hipResViewFormatUnsignedBlockCompressed2`*                |
-|         0x1b |*`cudaResViewFormatUnsignedBlockCompressed3`*        |                  |*`hipResViewFormatUnsignedBlockCompressed3`*                |
-|         0x1c |*`cudaResViewFormatUnsignedBlockCompressed4`*        |                  |*`hipResViewFormatUnsignedBlockCompressed4`*                |
-|         0x1d |*`cudaResViewFormatSignedBlockCompressed4`*          |                  |*`hipResViewFormatSignedBlockCompressed4`*                  |
-|         0x1e |*`cudaResViewFormatUnsignedBlockCompressed5`*        |                  |*`hipResViewFormatUnsignedBlockCompressed5`*                |
-|         0x1f |*`cudaResViewFormatSignedBlockCompressed5`*          |                  |*`hipResViewFormatSignedBlockCompressed5`*                  |
-|         0x20 |*`cudaResViewFormatUnsignedBlockCompressed6H`*       |                  |*`hipResViewFormatUnsignedBlockCompressed6H`*               |
-|         0x21 |*`cudaResViewFormatSignedBlockCompressed6H`*         |                  |*`hipResViewFormatSignedBlockCompressed6H`*                 |
-|         0x22 |*`cudaResViewFormatUnsignedBlockCompressed7`*        |                  |*`hipResViewFormatUnsignedBlockCompressed7`*                |
-| enum         |***`cudaSharedMemConfig`***                          |                  |***`hipSharedMemConfig`***                                  |
-|            0 |*`cudaSharedMemBankSizeDefault`*                     |                  |*`hipSharedMemBankSizeDefault`*                             |
-|            1 |*`cudaSharedMemBankSizeFourByte`*                    |                  |*`hipSharedMemBankSizeFourByte`*                            |
-|            2 |*`cudaSharedMemBankSizeEightByte`*                   |                  |*`hipSharedMemBankSizeEightByte`*                           |
-| enum         |***`cudaSharedCarveout`***                           | 9.0              |                                                            |
-|           -1 |*`cudaSharedmemCarveoutDefault`*                     | 9.0              |                                                            |
-|          100 |*`cudaSharedmemCarveoutMaxShared`*                   | 9.0              |                                                            |
-|            0 |*`cudaSharedmemCarveoutMaxL1`*                       | 9.0              |                                                            |
-| enum         |***`cudaStreamCaptureStatus`***                      | 10.0             |                                                            |
-|            0 |*`cudaStreamCaptureStatusNone`*                      | 10.0             |                                                            |
-|            1 |*`cudaStreamCaptureStatusActive`*                    | 10.0             |                                                            |
-|            2 |*`cudaStreamCaptureStatusInvalidated`*               | 10.0             |                                                            |
-| enum         |***`cudaStreamCaptureMode`***                        | 10.1             |                                                            |
-|            0 |*`cudaStreamCaptureModeGlobal`*                      | 10.1             |                                                            |
-|            1 |*`cudaStreamCaptureModeThreadLocal`*                 | 10.1             |                                                            |
-|            2 |*`cudaStreamCaptureModeRelaxed`*                     | 10.1             |                                                            |
-| enum         |***`cudaSurfaceBoundaryMode`***                      |                  |***`hipSurfaceBoundaryMode`***                              |
-|            0 |*`cudaBoundaryModeZero`*                             |                  |*`hipBoundaryModeZero`*                                     |
-|            1 |*`cudaBoundaryModeClamp`*                            |                  |*`hipBoundaryModeClamp`*                                    |
-|            2 |*`cudaBoundaryModeTrap`*                             |                  |*`hipBoundaryModeTrap`*                                     |
-| enum         |***`cudaSurfaceFormatMode`***                        |                  |                                                            |
-|            0 |*`cudaFormatModeForced`*                             |                  |                                                            |
-|            1 |*`cudaFormatModeAuto`*                               |                  |                                                            |
-| enum         |***`cudaTextureAddressMode`***                       |                  |***`hipTextureAddressMode`***                               |
-|            0 |*`cudaAddressModeWrap`*                              |                  |*`hipAddressModeWrap`*                                      |
-|            1 |*`cudaAddressModeClamp`*                             |                  |*`hipAddressModeClamp`*                                     |
-|            2 |*`cudaAddressModeMirror`*                            |                  |*`hipAddressModeMirror`*                                    |
-|            3 |*`cudaAddressModeBorder`*                            |                  |*`hipAddressModeBorder`*                                    |
-| enum         |***`cudaTextureFilterMode`***                        |                  |***`hipTextureFilterMode`***                                |
-|            0 |*`cudaFilterModePoint`*                              |                  |*`hipFilterModePoint`*                                      |
-|            1 |*`cudaFilterModeLinear`*                             |                  |*`hipFilterModeLinear`*                                     |
-| enum         |***`cudaTextureReadMode`***                          |                  |***`hipTextureReadMode`***                                  |
-|            0 |*`cudaReadModeElementType`*                          |                  |*`hipReadModeElementType`*                                  |
-|            1 |*`cudaReadModeNormalizedFloat`*                      |                  |*`hipReadModeNormalizedFloat`*                              |
-| enum         |***`cudaGLDeviceList`***                             |                  |                                                            |
-|            1 |*`cudaGLDeviceListAll`*                              |                  |                                                            |
-|            2 |*`cudaGLDeviceListCurrentFrame`*                     |                  |                                                            |
-|            3 |*`cudaGLDeviceListNextFrame`*                        |                  |                                                            |
-| enum         |***`cudaGLMapFlags`***                               |                  |                                                            |
-|            0 |*`cudaGLMapFlagsNone`*                               |                  |                                                            |
-|            1 |*`cudaGLMapFlagsReadOnly`*                           |                  |                                                            |
-|            2 |*`cudaGLMapFlagsWriteDiscard`*                       |                  |                                                            |
-| enum         |***`cudaD3D9DeviceList`***                           |                  |                                                            |
-|            1 |*`cudaD3D9DeviceListAll`*                            |                  |                                                            |
-|            2 |*`cudaD3D9DeviceListCurrentFrame`*                   |                  |                                                            |
-|            3 |*`cudaD3D9DeviceListNextFrame`*                      |                  |                                                            |
-| enum         |***`cudaD3D9MapFlags`***                             |                  |                                                            |
-|            0 |*`cudaD3D9MapFlagsNone`*                             |                  |                                                            |
-|            1 |*`cudaD3D9MapFlagsReadOnly`*                         |                  |                                                            |
-|            2 |*`cudaD3D9MapFlagsWriteDiscard`*                     |                  |                                                            |
-| enum         |***`cudaD3D9RegisterFlags`***                        |                  |                                                            |
-|            0 |*`cudaD3D9RegisterFlagsNone`*                        |                  |                                                            |
-|            1 |*`cudaD3D9RegisterFlagsArray`*                       |                  |                                                            |
-| enum         |***`cudaD3D10DeviceList`***                          |                  |                                                            |
-|            1 |*`cudaD3D10DeviceListAll`*                           |                  |                                                            |
-|            2 |*`cudaD3D10DeviceListCurrentFrame`*                  |                  |                                                            |
-|            3 |*`cudaD3D10DeviceListNextFrame`*                     |                  |                                                            |
-| enum         |***`cudaD3D10MapFlags`***                            |                  |                                                            |
-|            0 |*`cudaD3D10MapFlagsNone`*                            |                  |                                                            |
-|            1 |*`cudaD3D10MapFlagsReadOnly`*                        |                  |                                                            |
-|            2 |*`cudaD3D10MapFlagsWriteDiscard`*                    |                  |                                                            |
-| enum         |***`cudaD3D10RegisterFlags`***                       |                  |                                                            |
-|            0 |*`cudaD3D10RegisterFlagsNone`*                       |                  |                                                            |
-|            1 |*`cudaD3D10RegisterFlagsArray`*                      |                  |                                                            |
-| enum         |***`cudaD3D11DeviceList`***                          |                  |                                                            |
-|            1 |*`cudaD3D11DeviceListAll`*                           |                  |                                                            |
-|            2 |*`cudaD3D11DeviceListCurrentFrame`*                  |                  |                                                            |
-|            3 |*`cudaD3D11DeviceListNextFrame`*                     |                  |                                                            |
-| struct       |`cudaArray`                                          |                  |`hipArray`                                                  |
-| typedef      |`cudaArray_t`                                        |                  |`hipArray_t`                                                |
-| typedef      |`cudaArray_const_t`                                  |                  |`hipArray_const_t`                                          |
-| typedef      |`cudaEvent_t`                                        |                  |`hipEvent_t`                                                |
-| struct       |`CUevent_st`                                         |                  |`ihipEvent_t`                                               |
-| struct       |`cudaMipmappedArray`                                 |                  |`hipMipmappedArray`                                         |
-| typedef      |`cudaMipmappedArray_t`                               |                  |`hipMipmappedArray_t`                                       |
-| typedef      |`cudaMipmappedArray_const_t`                         |                  |`hipMipmappedArray_const_t`                                 |
-| enum         |***`cudaOutputMode`***                               |                  |                                                            |
-| typedef      |***`cudaOutputMode_t`***                             |                  |                                                            |
-|         0x00 |*`cudaKeyValuePair`*                                 |                  |                                                            |
-|         0x01 |*`cudaCSV`*                                          |                  |                                                            |
-| typedef      |`cudaStream_t`                                       |                  |`hipStream_t`                                               |
-| struct       |`CUstream_st`                                        |                  |`ihipStream_t`                                              |
-| typedef      |`cudaStreamCallback_t`                               |                  |`hipStreamCallback_t`                                       |
-| typedef      |`cudaSurfaceObject_t`                                |                  |`hipSurfaceObject_t`                                        |
-| typedef      |`cudaTextureObject_t`                                |                  |`hipTextureObject_t`                                        |
-| struct       |`CUuuid_st`                                          |                  |                                                            |
-| typedef      |`cudaUUID_t`                                         |                  |                                                            |
-| define       |`CUDA_EGL_MAX_PLANES`                                | 9.1              |                                                            |
-| define       |`CUDA_IPC_HANDLE_SIZE`                               |                  |                                                            |
-| define       |`cudaArrayColorAttachment`                           | 10.0             |                                                            |
-| define       |`cudaArrayCubemap`                                   |                  |`hipArrayCubemap`                                           |
-| define       |`cudaArrayDefault`                                   |                  |`hipArrayDefault`                                           |
-| define       |`cudaArrayLayered`                                   |                  |`hipArrayLayered`                                           |
-| define       |`cudaArraySurfaceLoadStore`                          |                  |`hipArraySurfaceLoadStore`                                  |
-| define       |`cudaArrayTextureGather`                             |                  |`hipArrayTextureGather`                                     |
-| define       |`cudaCooperativeLaunchMultiDeviceNoPreSync`          | 9.0              |                                                            |
-| define       |`cudaCooperativeLaunchMultiDeviceNoPostSync`         | 9.0              |                                                            |
-| define       |`cudaCpuDeviceId`                                    | 8.0              |                                                            |
-| define       |`cudaInvalidDeviceId`                                | 8.0              |                                                            |
-| define       |`cudaDeviceBlockingSync`                             |                  |`hipDeviceScheduleBlockingSync`                             |
-| define       |`cudaDeviceLmemResizeToMax`                          |                  |`hipDeviceLmemResizeToMax`                                  | 0x16                      |
-| define       |`cudaDeviceMapHost`                                  |                  |`hipDeviceMapHost`                                          |
-| define       |`cudaDeviceMask`                                     |                  |                                                            |
-| define       |`cudaDevicePropDontCare`                             |                  |                                                            |
-| define       |`cudaDeviceScheduleAuto`                             |                  |`hipDeviceScheduleAuto`                                     |
-| define       |`cudaDeviceScheduleBlockingSync`                     |                  |`hipDeviceScheduleBlockingSync`                             |
-| define       |`cudaDeviceScheduleMask`                             |                  |`hipDeviceScheduleMask`                                     |
-| define       |`cudaDeviceScheduleSpin`                             |                  |`hipDeviceScheduleSpin`                                     |
-| define       |`cudaDeviceScheduleYield`                            |                  |`hipDeviceScheduleYield`                                    |
-| define       |`cudaEventDefault`                                   |                  |`hipEventDefault`                                           |
-| define       |`cudaEventBlockingSync`                              |                  |`hipEventBlockingSync`                                      |
-| define       |`cudaEventDisableTiming`                             |                  |`hipEventDisableTiming`                                     |
-| define       |`cudaEventInterprocess`                              |                  |`hipEventInterprocess`                                      |
-| define       |`cudaHostAllocDefault`                               |                  |`hipHostMallocDefault`                                      |
-| define       |`cudaHostAllocMapped`                                |                  |`hipHostMallocMapped`                                       |
-| define       |`cudaHostAllocPortable`                              |                  |`hipHostMallocPortable`                                     |
-| define       |`cudaHostAllocWriteCombined`                         |                  |`hipHostMallocWriteCombined`                                |
-| define       |`cudaHostRegisterDefault`                            |                  |`hipHostRegisterDefault`                                    |
-| define       |`cudaHostRegisterIoMemory`                           | 7.5              |`hipHostRegisterIoMemory`                                   |
-| define       |`cudaHostRegisterMapped`                             |                  |`hipHostRegisterMapped`                                     |
-| define       |`cudaHostRegisterPortable`                           |                  |`hipHostRegisterPortable`                                   |
-| define       |`cudaIpcMemLazyEnablePeerAccess`                     |                  |`hipIpcMemLazyEnablePeerAccess`                             | 0                         |
-| define       |`cudaMemAttachGlobal`                                |                  |`hipMemAttachGlobal`                                        |
-| define       |`cudaMemAttachHost`                                  |                  |`hipMemAttachHost`                                          |
-| define       |`cudaMemAttachSingle`                                |                  |                                                            |
-| define       |`cudaOccupancyDefault`                               |                  |`hipOccupancyDefault`                                    |
-| define       |`cudaOccupancyDisableCachingOverride`                |                  |                                                            |
-| define       |`cudaPeerAccessDefault`                              |                  |                                                            |
-| define       |`cudaStreamDefault`                                  |                  |`hipStreamDefault`                                          |
-| define       |`cudaStreamNonBlocking`                              |                  |`hipStreamNonBlocking`                                      |
-| define       |`cudaStreamLegacy`                                   |                  |                                                            |
-| define       |`cudaStreamPerThread`                                |                  |                                                            |
-| define       |`cudaTextureType1D`                                  |                  |`hipTextureType1D`                                          |
-| define       |`cudaTextureType2D`                                  |                  |`hipTextureType2D`                                          |
-| define       |`cudaTextureType3D`                                  |                  |`hipTextureType3D`                                          |
-| define       |`cudaTextureTypeCubemap`                             |                  |`hipTextureTypeCubemap`                                     |
-| define       |`cudaTextureType1DLayered`                           |                  |`hipTextureType1DLayered`                                   |
-| define       |`cudaTextureType2DLayered`                           |                  |`hipTextureType2DLayered`                                   |
-| define       |`cudaTextureTypeCubemapLayered`                      |                  |`hipTextureTypeCubemapLayered`                              |
-| enum         |***`cudaDataType_t`***                               | 8.0              |***`hipblasDatatype_t`***                                   |
-| enum         |***`cudaDataType`***                                 | 8.0              |***`hipblasDatatype_t`***                                   |
-|            2 |*`CUDA_R_16F`*                                       | 8.0              |*`HIPBLAS_R_16F`*                                           | 150                       |
-|            6 |*`CUDA_C_16F`*                                       | 8.0              |*`HIPBLAS_C_16F`*                                           | 153                       |
-|            0 |*`CUDA_R_32F`*                                       | 8.0              |*`HIPBLAS_R_32F`*                                           | 151                       |
-|            4 |*`CUDA_C_32F`*                                       | 8.0              |*`HIPBLAS_C_32F`*                                           | 154                       |
-|            1 |*`CUDA_R_64F`*                                       | 8.0              |*`HIPBLAS_R_64F`*                                           | 152                       |
-|            5 |*`CUDA_C_64F`*                                       | 8.0              |*`HIPBLAS_C_64F`*                                           | 155                       |
-|            3 |*`CUDA_R_8I`*                                        | 8.0              |*`HIPBLAS_R_8I`*                                            | 160                       |
-|            7 |*`CUDA_C_8I`*                                        | 8.0              |*`HIPBLAS_C_8I`*                                            | 164                       |
-|            8 |*`CUDA_R_8U`*                                        | 8.0              |*`HIPBLAS_R_8U`*                                            | 161                       |
-|            9 |*`CUDA_C_8U`*                                        | 8.0              |*`HIPBLAS_C_8U`*                                            | 165                       |
-|           10 |*`CUDA_R_32I`*                                       | 8.0              |*`HIPBLAS_R_32I`*                                           | 162                       |
-|           11 |*`CUDA_C_32I`*                                       | 8.0              |*`HIPBLAS_C_32I`*                                           | 166                       |
-|           12 |*`CUDA_R_32U`*                                       | 8.0              |*`HIPBLAS_R_32U`*                                           | 163                       |
-|           13 |*`CUDA_C_32U`*                                       | 8.0              |*`HIPBLAS_C_32U`*                                           | 167                       |
-| struct       |`cudaExternalMemoryBufferDesc`                       | 10.0             |                                                            |
-| struct       |`cudaExternalMemoryHandleDesc`                       | 10.0             |                                                            |
-| struct       |`cudaExternalMemoryMipmappedArrayDesc`               | 10.0             |                                                            |
-| struct       |`cudaExternalSemaphoreHandleDesc`                    | 10.0             |                                                            |
-| struct       |`cudaExternalSemaphoreSignalParams`                  | 10.0             |                                                            |
-| struct       |`cudaExternalSemaphoreWaitParams`                    | 10.0             |                                                            |
-| struct       |`cudaHostNodeParams`                                 | 10.0             |                                                            |
-| struct       |`cudaLaunchParams`                                   | 9.0              |`hipLaunchParams`                                           |
-| struct       |`cudaMemsetParams`                                   | 10.0             |                                                            |
-| struct       |`CUeglStreamConnection_st`                           | 9.1              |                                                            |
-| typedef      |`cudaEglStreamConnection`                            | 9.1              |                                                            |
-| define       |`cudaExternalMemoryDedicated`                        | 10.0             |                                                            |
-| define       |`cudaExternalSemaphoreSignalSkipNvSciBufMemSync`     | 10.2             |                                                            |
-| define       |`cudaExternalSemaphoreWaitSkipNvSciBufMemSync`       | 10.2             |                                                            |
-| define       |`cudaNvSciSyncAttrSignal`                            | 10.2             |                                                            |
-| define       |`cudaNvSciSyncAttrWait`                              | 10.2             |                                                            |
-| typedef      |`cudaExternalMemory_t`                               | 10.0             |                                                            |
-| struct       |`CUexternalMemory_st`                                | 10.0             |                                                            |
-| typedef      |`cudaExternalSemaphore_t`                            | 10.0             |                                                            |
-| struct       |`CUexternalSemaphore_st`                             | 10.0             |                                                            |
-| typedef      |`cudaGraph_t`                                        | 10.0             |                                                            |
-| struct       |`CUgraph_st`                                         | 10.0             |                                                            |
-| typedef      |`cudaGraphNode_t`                                    | 10.0             |                                                            |
-| struct       |`CUgraphNode_st`                                     | 10.0             |                                                            |
-| typedef      |`cudaGraphExec_t`                                    | 10.0             |                                                            |
-| struct       |`CUgraphExec_st`                                     | 10.0             |                                                            |
-| typedef      |`cudaGraphicsResource_t`                             |                  |                                                            |
-| struct       |`cudaGraphicsResource`                               |                  |                                                            |
-| typedef      |`cudaHostFn_t`                                       | 10.0             |                                                            |
-| enum         |***`libraryPropertyType`***                          | 8.0              |                                                            |
-| typedef      |***`libraryPropertyType_t`***                        | 8.0              |                                                            |
-|            0 |*`MAJOR_VERSION`*                                    | 8.0              |                                                            |
-|            1 |*`MINOR_VERSION`*                                    | 8.0              |                                                            |
-|            2 |*`PATCH_LEVEL`*                                      | 8.0              |                                                            |
-| enum         |***`cudaGraphExecUpdateResult`***                    | 10.2             |                                                            |
-|          0x0 |*`cudaGraphExecUpdateSuccess`*                       | 10.2             |                                                            |
-|          0x1 |*`cudaGraphExecUpdateError`*                         | 10.2             |                                                            |
-|          0x2 |*`cudaGraphExecUpdateErrorTopologyChanged`*          | 10.2             |                                                            |
-|          0x3 |*`cudaGraphExecUpdateErrorNodeTypeChanged`*          | 10.2             |                                                            |
-|          0x4 |*`cudaGraphExecUpdateErrorFunctionChanged`*          | 10.2             |                                                            |
-|          0x5 |*`cudaGraphExecUpdateErrorParametersChanged`*        | 10.2             |                                                            |
-|          0x6 |*`cudaGraphExecUpdateErrorNotSupported`*             | 10.2             |                                                            |
-
-\* CUDA version, in which API has appeared and (optional) last version before abandoning it; no value in case of earlier versions < 7.5.
diff --git a/projects/hip/docs/markdown/clang_options.md b/projects/hip/docs/markdown/clang_options.md
deleted file mode 100644
index 01b7fa78ee..0000000000
--- a/projects/hip/docs/markdown/clang_options.md
+++ /dev/null
@@ -1,763 +0,0 @@
-# Support of Clang options
- Clang version: clang version 12.0.0 927e2776dc0e4bb0119efbc5ea405b7425d7f4ac
-
-|Option|Support|Description|
-|-------|------|-------|
-|`-###`|Supported|`Print (but do not run) the commands to run for this compilation`|
-|`--analyzer-output <value>`|Supported|`Static analyzer report output format (html\|plist\|plist-multi-file\|plist-html\|sarif\|text).`|
-|`--analyze`|Supported|`Run the static analyzer`|
-|`-arcmt-migrate-emit-errors`|Unsupported|`Emit ARC errors even if the migrator can fix them`|
-|`-arcmt-migrate-report-output <value>`|Unsupported|`Output path for the plist report`|
-|`-byteswapio`|Supported|`Swap byte-order for unformatted input/output`|
-|`-B <dir>`|Supported|`Add <dir> to search path for binaries and object files used implicitly`|
-|`-CC`|Supported|`Include comments from within macros in preprocessed output`|
-|`-cl-denorms-are-zero`|Supported|`OpenCL only. Allow denormals to be flushed to zero.`|
-|`-cl-fast-relaxed-math`|Supported|`OpenCL only. Sets -cl-finite-math-only and -cl-unsafe-math-optimizations, and defines __FAST_RELAXED_MATH__.`|
-|`-cl-finite-math-only`|Supported|`OpenCL only. Allow floating-point optimizations that assume arguments and results are not NaNs or +-Inf.`|
-|`-cl-fp32-correctly-rounded-divide-sqrt`|Supported|`OpenCL only. Specify that single precision floating-point divide and sqrt used in the program source are correctly rounded.`|
-|`-cl-kernel-arg-info`|Supported|`OpenCL only. Generate kernel argument metadata.`|
-|`-cl-mad-enable`|Supported|`OpenCL only. Allow use of less precise MAD computations in the generated binary.`|
-|`-cl-no-signed-zeros`|Supported|`OpenCL only. Allow use of less precise no signed zeros computations in the generated binary.`|
-|`-cl-opt-disable`|Supported|`OpenCL only. This option disables all optimizations. By default optimizations are enabled.`|
-|`-cl-single-precision-constant`|Supported|`OpenCL only. Treat double precision floating-point constant as single precision constant.`|
-|`-cl-std=<value>`|Supported|`OpenCL language standard to compile for.`|
-|`-cl-strict-aliasing`|Supported|`OpenCL only. This option is added for compatibility with OpenCL 1.0.`|
-|`-cl-uniform-work-group-size`|Supported|`OpenCL only. Defines that the global work-size be a multiple of the work-group size specified to clEnqueueNDRangeKernel`|
-|`-cl-unsafe-math-optimizations`|Supported|`OpenCL only. Allow unsafe floating-point optimizations. Also implies -cl-no-signed-zeros and -cl-mad-enable.`|
-|`--config <value>`|Supported|`Specifies configuration file`|
-|`--cuda-compile-host-device`|Supported|`Compile CUDA code for both host and device (default). Has no effect on non-CUDA compilations.`|
-|`--cuda-device-only`|Supported|`Compile CUDA code for device only`|
-|`--cuda-host-only`|Supported|`Compile CUDA code for host only. Has no effect on non-CUDA compilations.`|
-|`--cuda-include-ptx=<value>`|Unsupported|`Include PTX for the following GPU architecture (e.g. sm_35) or 'all'. May be specified more than once.`|
-|`--cuda-noopt-device-debug`|Unsupported|`Enable device-side debug info generation. Disables ptxas optimizations.`|
-|`--cuda-path-ignore-env`|Unsupported|`Ignore environment variables to detect CUDA installation`|
-|`--cuda-path=<value>`|Unsupported|`CUDA installation path`|
-|`-cxx-isystem <directory>`|Supported|`Add directory to the C++ SYSTEM include search path`|
-|`-C`|Supported|`Include comments in preprocessed output`|
-|`-c`|Supported|`Only run preprocess, compile, and assemble steps`|
-|`-dD`|Supported|`Print macro definitions in -E mode in addition to normal output`|
-|`-dependency-dot <value>`|Supported|`Filename to write DOT-formatted header dependencies to`|
-|`-dependency-file <value>`|Supported|`Filename (or -) to write dependency output to`|
-|`-dI`|Supported|`Print include directives in -E mode in addition to normal output`|
-|`-dM`|Supported|`Print macro definitions in -E mode instead of normal output`|
-|`-dsym-dir <dir>`|Unsupported|`Directory to output dSYM's (if any) to`|
-|`-D <macro>`|Supported|`=<value> Define <macro> to <value> (or 1 if <value> omitted)`|
-|`-emit-ast`|Supported|`Emit Clang AST files for source inputs`|
-|`-emit-interface-stubs`|Supported|`Generate Interface Stub Files.`|
-|`-emit-llvm`|Supported|`Use the LLVM representation for assembler and object files`|
-|`-emit-merged-ifs`|Supported|`Generate Interface Stub Files, emit merged text not binary.`|
-|`--emit-static-lib`|Supported|`Enable linker job to emit a static library.`|
-|`-enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang`|Supported|`Trivial automatic variable initialization to zero is only here for benchmarks, it'll eventually be removed, and I'm OK with that because I'm only using it to benchmark`|
-|`-E`|Supported|`Only run the preprocessor`|
-|`-fAAPCSBitfieldLoad`|Unsupported|`Follows the AAPCS standard that all volatile bit-field write generates at least one load. (ARM only).`|
-|`-faddrsig`|Supported|`Emit an address-significance table`|
-|`-faligned-allocation`|Supported|`Enable C++17 aligned allocation functions`|
-|`-fallow-editor-placeholders`|Supported|`Treat editor placeholders as valid source code`|
-|`-fallow-fortran-gnu-ext`|Supported|`Allow Fortran GNU extensions`|
-|`-fansi-escape-codes`|Supported|`Use ANSI escape codes for diagnostics`|
-|`-fapple-kext`|Unsupported|`Use Apple's kernel extensions ABI`|
-|`-fapple-link-rtlib`|Unsupported|`Force linking the clang builtins runtime library`|
-|`-fapple-pragma-pack`|Unsupported|`Enable Apple gcc-compatible #pragma pack handling`|
-|`-fapplication-extension`|Unsupported|`Restrict code to those available for App Extensions`|
-|`-fbackslash`|Supported|`Treat backslash as C-style escape character`|
-|`-fbasic-block-sections=<value>`|Supported|`Place each function's basic blocks in unique sections (ELF Only) : all \| labels \| none \| list=<file>`|
-|`-fblocks`|Supported|`Enable the 'blocks' language feature`|
-|`-fborland-extensions`|Unsupported|`Accept non-standard constructs supported by the Borland compiler`|
-|`-fbuild-session-file=<file>`|Supported|`Use the last modification time of <file> as the build session timestamp`|
-|`-fbuild-session-timestamp=<time since Epoch in seconds>`|Supported|`Time when the current build session started`|
-|`-fbuiltin-module-map`|Unsupported|`Load the clang builtins module map file.`|
-|`-fcall-saved-x10`|Unsupported|`Make the x10 register call-saved (AArch64 only)`|
-|`-fcall-saved-x11`|Unsupported|`Make the x11 register call-saved (AArch64 only)`|
-|`-fcall-saved-x12`|Unsupported|`Make the x12 register call-saved (AArch64 only)`|
-|`-fcall-saved-x13`|Unsupported|`Make the x13 register call-saved (AArch64 only)`|
-|`-fcall-saved-x14`|Unsupported|`Make the x14 register call-saved (AArch64 only)`|
-|`-fcall-saved-x15`|Unsupported|`Make the x15 register call-saved (AArch64 only)`|
-|`-fcall-saved-x18`|Unsupported|`Make the x18 register call-saved (AArch64 only)`|
-|`-fcall-saved-x8`|Unsupported|`Make the x8 register call-saved (AArch64 only)`|
-|`-fcall-saved-x9`|Unsupported|`Make the x9 register call-saved (AArch64 only)`|
-|`-fcf-protection=<value>`|Unsupported|`Instrument control-flow architecture protection. Options: return, branch, full, none.`|
-|`-fcf-protection`|Unsupported|`Enable cf-protection in 'full' mode`|
-|`-fchar8_t`|Supported|`Enable C++ builtin type char8_t`|
-|`-fclang-abi-compat=<version>`|Supported|`Attempt to match the ABI of Clang <version>`|
-|`-fcolor-diagnostics`|Supported|`Enable colors in diagnostics`|
-|`-fcomment-block-commands=<arg>`|Supported|`Treat each comma separated argument in <arg> as a documentation comment block command`|
-|`-fcommon`|Supported|`Place uninitialized global variables in a common block`|
-|`-fcomplete-member-pointers`|Supported|`Require member pointer base types to be complete if they would be significant under the Microsoft ABI`|
-|`-fconvergent-functions`|Supported|`Assume functions may be convergent`|
-|`-fcoroutines-ts`|Supported|`Enable support for the C++ Coroutines TS`|
-|`-fcoverage-mapping`|Unsupported|`Generate coverage mapping to enable code coverage analysis`|
-|`-fcs-profile-generate=<directory>`|Unsupported|`Generate instrumented code to collect context sensitive execution counts into <directory>/default.profraw (overridden by LLVM_PROFILE_FILE env var)`|
-|`-fcs-profile-generate`|Unsupported|`Generate instrumented code to collect context sensitive execution counts into default.profraw (overridden by LLVM_PROFILE_FILE env var)`|
-|`-fcuda-approx-transcendentals`|Unsupported|`Use approximate transcendental functions`|
-|`-fcuda-flush-denormals-to-zero`|Supported|`Flush denormal floating point values to zero in CUDA device mode.`|
-|`-fcuda-short-ptr`|Unsupported|`Use 32-bit pointers for accessing const/local/shared address spaces`|
-|`-fcxx-exceptions`|Supported|`Enable C++ exceptions`|
-|`-fdata-sections`|Supported|`Place each data in its own section`|
-|`-fdebug-compilation-dir <value>`|Supported|`The compilation directory to embed in the debug info.`|
-|`-fdebug-default-version=<value>`|Supported|`Default DWARF version to use, if a -g option caused DWARF debug info to be produced`|
-|`-fdebug-info-for-profiling`|Supported|`Emit extra debug info to make sample profile more accurate`|
-|`-fdebug-macro`|Supported|`Emit macro debug information`|
-|`-fdebug-prefix-map=<value>`|Supported|`remap file source paths in debug info`|
-|`-fdebug-ranges-base-address`|Supported|`Use DWARF base address selection entries in .debug_ranges`|
-|`-fdebug-types-section`|Supported|`Place debug types in their own section (ELF Only)`|
-|`-fdeclspec`|Supported|`Allow __declspec as a keyword`|
-|`-fdelayed-template-parsing`|Supported|`Parse templated function definitions at the end of the translation unit`|
-|`-fdelete-null-pointer-checks`|Supported|`Treat usage of null pointers as undefined behavior (default)`|
-|`-fdiagnostics-absolute-paths`|Supported|`Print absolute paths in diagnostics`|
-|`-fdiagnostics-hotness-threshold=<number>`|Unsupported|`Prevent optimization remarks from being output if they do not have at least this profile count`|
-|`-fdiagnostics-parseable-fixits`|Supported|`Print fix-its in machine parseable form`|
-|`-fdiagnostics-print-source-range-info`|Supported|`Print source range spans in numeric form`|
-|`-fdiagnostics-show-hotness`|Unsupported|`Enable profile hotness information in diagnostic line`|
-|`-fdiagnostics-show-note-include-stack`|Supported|`Display include stacks for diagnostic notes`|
-|`-fdiagnostics-show-option`|Supported|`Print option name with mappable diagnostics`|
-|`-fdiagnostics-show-template-tree`|Supported|`Print a template comparison tree for differing templates`|
-|`-fdigraphs`|Supported|`Enable alternative token representations '<:', ':>', '<%', '%>', '%:', '%:%:' (default)`|
-|`-fdiscard-value-names`|Supported|`Discard value names in LLVM IR`|
-|`-fdollars-in-identifiers`|Supported|`Allow '$' in identifiers`|
-|`-fdouble-square-bracket-attributes`|Supported|`Enable '[[]]' attributes in all C and C++ language modes`|
-|`-fdwarf-exceptions`|Unsupported|`Use DWARF style exceptions`|
-|`-feliminate-unused-debug-types`|Supported|`Do not emit debug info for defined but unused types`|
-|`-fembed-bitcode-marker`|Supported|`Embed placeholder LLVM IR data as a marker`|
-|`-fembed-bitcode=<option>`|Supported|`Embed LLVM bitcode (option: off, all, bitcode, marker)`|
-|`-fembed-bitcode`|Supported|`Embed LLVM IR bitcode as data`|
-|`-femit-all-decls`|Supported|`Emit all declarations, even if unused`|
-|`-femulated-tls`|Supported|`Use emutls functions to access thread_local variables`|
-|`-fenable-matrix`|Supported|`Enable matrix data type and related builtin functions`|
-|`-fexceptions`|Supported|`Enable support for exception handling`|
-|`-fexperimental-new-constant-interpreter`|Supported|`Enable the experimental new constant interpreter`|
-|`-fexperimental-new-pass-manager`|Supported|`Enables an experimental new pass manager in LLVM.`|
-|`-fexperimental-relative-c++-abi-vtables`|Supported|`Use the experimental C++ class ABI for classes with virtual tables`|
-|`-fexperimental-strict-floating-point`|Supported|`Enables experimental strict floating point in LLVM.`|
-|`-ffast-math`|Supported|`Allow aggressive, lossy floating-point optimizations`|
-|`-ffile-prefix-map=<value>`|Supported|`remap file source paths in debug info and predefined preprocessor macros`|
-|`-ffine-grained-bitfield-accesses`|Supported|`Use separate accesses for consecutive bitfield runs with legal widths and alignments.`|
-|`-ffixed-form`|Supported|`Enable fixed-form format for Fortran`|
-|`-ffixed-point`|Supported|`Enable fixed point types`|
-|`-ffixed-r19`|Unsupported|`Reserve register r19 (Hexagon only)`|
-|`-ffixed-r9`|Unsupported|`Reserve the r9 register (ARM only)`|
-|`-ffixed-x10`|Unsupported|`Reserve the x10 register (AArch64/RISC-V only)`|
-|`-ffixed-x11`|Unsupported|`Reserve the x11 register (AArch64/RISC-V only)`|
-|`-ffixed-x12`|Unsupported|`Reserve the x12 register (AArch64/RISC-V only)`|
-|`-ffixed-x13`|Unsupported|`Reserve the x13 register (AArch64/RISC-V only)`|
-|`-ffixed-x14`|Unsupported|`Reserve the x14 register (AArch64/RISC-V only)`|
-|`-ffixed-x15`|Unsupported|`Reserve the x15 register (AArch64/RISC-V only)`|
-|`-ffixed-x16`|Unsupported|`Reserve the x16 register (AArch64/RISC-V only)`|
-|`-ffixed-x17`|Unsupported|`Reserve the x17 register (AArch64/RISC-V only)`|
-|`-ffixed-x18`|Unsupported|`Reserve the x18 register (AArch64/RISC-V only)`|
-|`-ffixed-x19`|Unsupported|`Reserve the x19 register (AArch64/RISC-V only)`|
-|`-ffixed-x1`|Unsupported|`Reserve the x1 register (AArch64/RISC-V only)`|
-|`-ffixed-x20`|Unsupported|`Reserve the x20 register (AArch64/RISC-V only)`|
-|`-ffixed-x21`|Unsupported|`Reserve the x21 register (AArch64/RISC-V only)`|
-|`-ffixed-x22`|Unsupported|`Reserve the x22 register (AArch64/RISC-V only)`|
-|`-ffixed-x23`|Unsupported|`Reserve the x23 register (AArch64/RISC-V only)`|
-|`-ffixed-x24`|Unsupported|`Reserve the x24 register (AArch64/RISC-V only)`|
-|`-ffixed-x25`|Unsupported|`Reserve the x25 register (AArch64/RISC-V only)`|
-|`-ffixed-x26`|Unsupported|`Reserve the x26 register (AArch64/RISC-V only)`|
-|`-ffixed-x27`|Unsupported|`Reserve the x27 register (AArch64/RISC-V only)`|
-|`-ffixed-x28`|Unsupported|`Reserve the x28 register (AArch64/RISC-V only)`|
-|`-ffixed-x29`|Unsupported|`Reserve the x29 register (AArch64/RISC-V only)`|
-|`-ffixed-x2`|Unsupported|`Reserve the x2 register (AArch64/RISC-V only)`|
-|`-ffixed-x30`|Unsupported|`Reserve the x30 register (AArch64/RISC-V only)`|
-|`-ffixed-x31`|Unsupported|`Reserve the x31 register (AArch64/RISC-V only)`|
-|`-ffixed-x3`|Unsupported|`Reserve the x3 register (AArch64/RISC-V only)`|
-|`-ffixed-x4`|Unsupported|`Reserve the x4 register (AArch64/RISC-V only)`|
-|`-ffixed-x5`|Unsupported|`Reserve the x5 register (AArch64/RISC-V only)`|
-|`-ffixed-x6`|Unsupported|`Reserve the x6 register (AArch64/RISC-V only)`|
-|`-ffixed-x7`|Unsupported|`Reserve the x7 register (AArch64/RISC-V only)`|
-|`-ffixed-x8`|Unsupported|`Reserve the x8 register (AArch64/RISC-V only)`|
-|`-ffixed-x9`|Unsupported|`Reserve the x9 register (AArch64/RISC-V only)`|
-|`-fforce-dwarf-frame`|Supported|`Always emit a debug frame section`|
-|`-fforce-emit-vtables`|Supported|`Emits more virtual tables to improve devirtualization`|
-|`-fforce-enable-int128`|Supported|`Enable support for int128_t type`|
-|`-ffp-contract=<value>`|Supported|`Form fused FP ops (e.g. FMAs): fast (everywhere) \| on (according to FP_CONTRACT pragma) \| off (never fuse). Default is 'fast' for CUDA/HIP and 'on' otherwise.`|
-|`-ffp-exception-behavior=<value>`|Supported|`Specifies the exception behavior of floating-point operations.`|
-|`-ffp-model=<value>`|Supported|`Controls the semantics of floating-point calculations.`|
-|`-ffree-form`|Supported|`Enable free-form format for Fortran`|
-|`-ffreestanding`|Supported|`Assert that the compilation takes place in a freestanding environment`|
-|`-ffunc-args-alias`|Supported|`Function argument may alias (equivalent to ansi alias)`|
-|`-ffunction-sections`|Supported|`Place each function in its own section`|
-|`-fglobal-isel`|Supported|`Enables the global instruction selector`|
-|`-fgnu-keywords`|Supported|`Allow GNU-extension keywords regardless of language standard`|
-|`-fgnu-runtime`|Unsupported|`Generate output compatible with the standard GNU Objective-C runtime`|
-|`-fgnu89-inline`|Unsupported|`Use the gnu89 inline semantics`|
-|`-fgnuc-version=<value>`|Supported|`Sets various macros to claim compatibility with the given GCC version (default is 4.2.1)`|
-|`-fgpu-allow-device-init`|Supported|`Allow device side init function in HIP`|
-|`-fgpu-rdc`|Supported|`Generate relocatable device code, also known as separate compilation mode`|
-|`-fhip-new-launch-api`|Supported|`Use new kernel launching API for HIP`|
-|`-fignore-exceptions`|Supported|`Enable support for ignoring exception handling constructs`|
-|`-fimplicit-module-maps`|Unsupported|`Implicitly search the file system for module map files.`|
-|`-finline-functions`|Supported|`Inline suitable functions`|
-|`-finline-hint-functions`|Supported|`Inline functions which are (explicitly or implicitly) marked inline`|
-|`-finstrument-function-entry-bare`|Unsupported|`Instrument function entry only, after inlining, without arguments to the instrumentation call`|
-|`-finstrument-functions-after-inlining`|Unsupported|`Like -finstrument-functions, but insert the calls after inlining`|
-|`-finstrument-functions`|Unsupported|`Generate calls to instrument function entry and exit`|
-|`-fintegrated-as`|Supported|`Enable the integrated assembler`|
-|`-fintegrated-cc1`|Supported|`Run cc1 in-process`|
-|`-fjump-tables`|Supported|`Use jump tables for lowering switches`|
-|`-fkeep-static-consts`|Supported|`Keep static const variables if unused`|
-|`-flax-vector-conversions=<value>`|Supported|`Enable implicit vector bit-casts`|
-|`-flto-jobs=<value>`|Unsupported|`Controls the backend parallelism of -flto=thin (default of 0 means the number of threads will be derived from the number of CPUs detected)`|
-|`-flto=<value>`|Unsupported|`Set LTO mode to either 'full' or 'thin'`|
-|`-flto`|Unsupported|`Enable LTO in 'full' mode`|
-|`-fmacro-prefix-map=<value>`|Supported|`remap file source paths in predefined preprocessor macros`|
-|`-fmath-errno`|Supported|`Require math functions to indicate errors by setting errno`|
-|`-fmax-tokens=<value>`|Supported|`Max total number of preprocessed tokens for -Wmax-tokens.`|
-|`-fmax-type-align=<value>`|Supported|`Specify the maximum alignment to enforce on pointers lacking an explicit alignment`|
-|`-fmemory-profile`|Supported|`Enable heap memory profiling`|
-|`-fmerge-all-constants`|Supported|`Allow merging of constants`|
-|`-fmessage-length=<value>`|Supported|`Format message diagnostics so that they fit within N columns`|
-|`-fmodule-file=[<name>=]<file>`|Unsupported|`Specify the mapping of module name to precompiled module file, or load a module file if name is omitted.`|
-|`-fmodule-map-file=<file>`|Unsupported|`Load this module map file`|
-|`-fmodule-name=<name>`|Unsupported|`Specify the name of the module to build`|
-|`-fmodules-cache-path=<directory>`|Unsupported|`Specify the module cache path`|
-|`-fmodules-decluse`|Unsupported|`Require declaration of modules used within a module`|
-|`-fmodules-disable-diagnostic-validation`|Unsupported|`Disable validation of the diagnostic options when loading the module`|
-|`-fmodules-ignore-macro=<value>`|Unsupported|`Ignore the definition of the given macro when building and loading modules`|
-|`-fmodules-prune-after=<seconds>`|Unsupported|`Specify the interval (in seconds) after which a module file will be considered unused`|
-|`-fmodules-prune-interval=<seconds>`|Unsupported|`Specify the interval (in seconds) between attempts to prune the module cache`|
-|`-fmodules-search-all`|Unsupported|`Search even non-imported modules to resolve references`|
-|`-fmodules-strict-decluse`|Unsupported|`Like -fmodules-decluse but requires all headers to be in modules`|
-|`-fmodules-ts`|Unsupported|`Enable support for the C++ Modules TS`|
-|`-fmodules-user-build-path <directory>`|Unsupported|`Specify the module user build path`|
-|`-fmodules-validate-input-files-content`|Supported|`Validate PCM input files based on content if mtime differs`|
-|`-fmodules-validate-once-per-build-session`|Unsupported|`Don't verify input files for the modules if the module has been successfully validated or loaded during this build session`|
-|`-fmodules-validate-system-headers`|Supported|`Validate the system headers that a module depends on when loading the module`|
-|`-fmodules`|Unsupported|`Enable the 'modules' language feature`|
-|`-fms-compatibility-version=<value>`|Supported|`Dot-separated value representing the Microsoft compiler version number to report in _MSC_VER (0 = don't define it (default))`|
-|`-fms-compatibility`|Supported|`Enable full Microsoft Visual C++ compatibility`|
-|`-fms-extensions`|Supported|`Accept some non-standard constructs supported by the Microsoft compiler`|
-|`-fmsc-version=<value>`|Supported|`Microsoft compiler version number to report in _MSC_VER (0 = don't define it (default))`|
-|`-fnew-alignment=<align>`|Supported|`Specifies the largest alignment guaranteed by '::operator new(size_t)'`|
-|`-fno-addrsig`|Supported|`Don't emit an address-significance table`|
-|`-fno-allow-fortran-gnu-ext`|Supported|`Allow Fortran GNU extensions`|
-|`-fno-assume-sane-operator-new`|Supported|`Don't assume that C++'s global operator new can't alias any pointer`|
-|`-fno-autolink`|Supported|`Disable generation of linker directives for automatic library linking`|
-|`-fno-backslash`|Supported|`Treat backslash like any other character in character strings`|
-|`-fno-builtin-<value>`|Supported|`Disable implicit builtin knowledge of a specific function`|
-|`-fno-builtin`|Supported|`Disable implicit builtin knowledge of functions`|
-|`-fno-c++-static-destructors`|Supported|`Disable C++ static destructor registration`|
-|`-fno-char8_t`|Supported|`Disable C++ builtin type char8_t`|
-|`-fno-color-diagnostics`|Supported|`Disable colors in diagnostics`|
-|`-fno-common`|Supported|`Compile common globals like normal definitions`|
-|`-fno-complete-member-pointers`|Supported|`Do not require member pointer base types to be complete if they would be significant under the Microsoft ABI`|
-|`-fno-constant-cfstrings`|Supported|`Disable creation of CodeFoundation-type constant strings`|
-|`-fno-coverage-mapping`|Supported|`Disable code coverage analysis`|
-|`-fno-crash-diagnostics`|Supported|`Disable auto-generation of preprocessed source files and a script for reproduction during a clang crash`|
-|`-fno-cuda-approx-transcendentals`|Unsupported|`Don't use approximate transcendental functions`|
-|`-fno-debug-macro`|Supported|`Do not emit macro debug information`|
-|`-fno-declspec`|Unsupported|`Disallow __declspec as a keyword`|
-|`-fno-delayed-template-parsing`|Supported|`Disable delayed template parsing`|
-|`-fno-delete-null-pointer-checks`|Supported|`Do not treat usage of null pointers as undefined behavior`|
-|`-fno-diagnostics-fixit-info`|Supported|`Do not include fixit information in diagnostics`|
-|`-fno-digraphs`|Supported|`Disallow alternative token representations '<:', ':>', '<%', '%>', '%:', '%:%:'`|
-|`-fno-discard-value-names`|Supported|`Do not discard value names in LLVM IR`|
-|`-fno-dollars-in-identifiers`|Supported|`Disallow '$' in identifiers`|
-|`-fno-double-square-bracket-attributes`|Supported|`Disable '[[]]' attributes in all C and C++ language modes`|
-|`-fno-elide-constructors`|Supported|`Disable C++ copy constructor elision`|
-|`-fno-elide-type`|Supported|`Do not elide types when printing diagnostics`|
-|`-fno-eliminate-unused-debug-types`|Supported|`Emit debug info for defined but unused types`|
-|`-fno-exceptions`|Supported|`Disable support for exception handling`|
-|`-fno-experimental-new-pass-manager`|Supported|`Disables an experimental new pass manager in LLVM.`|
-|`-fno-experimental-relative-c++-abi-vtables`|Supported|`Do not use the experimental C++ class ABI for classes with virtual tables`|
-|`-fno-fine-grained-bitfield-accesses`|Supported|`Use large-integer access for consecutive bitfield runs.`|
-|`-fno-fixed-form`|Supported|`Disable fixed-form format for Fortran`|
-|`-fno-fixed-point`|Supported|`Disable fixed point types`|
-|`-fno-force-enable-int128`|Supported|`Disable support for int128_t type`|
-|`-fno-fortran-main`|Supported|`Don't link in Fortran main`|
-|`-fno-free-form`|Supported|`Disable free-form format for Fortran`|
-|`-fno-func-args-alias`|Supported|`Function argument may alias (equivalent to ansi alias)`|
-|`-fno-global-isel`|Supported|`Disables the global instruction selector`|
-|`-fno-gnu-inline-asm`|Supported|`Disable GNU style inline asm`|
-|`-fno-gpu-allow-device-init`|Supported|`Don't allow device side init function in HIP`|
-|`-fno-hip-new-launch-api`|Supported|`Don't use new kernel launching API for HIP`|
-|`-fno-integrated-as`|Supported|`Disable the integrated assembler`|
-|`-fno-integrated-cc1`|Supported|`Spawn a separate process for each cc1`|
-|`-fno-jump-tables`|Supported|`Do not use jump tables for lowering switches`|
-|`-fno-keep-static-consts`|Supported|`Don't keep static const variables if unused`|
-|`-fno-lto`|Supported|`Disable LTO mode (default)`|
-|`-fno-memory-profile`|Supported|`Disable heap memory profiling`|
-|`-fno-merge-all-constants`|Supported|`Disallow merging of constants`|
-|`-fno-no-access-control`|Supported|`Disable C++ access control`|
-|`-fno-objc-infer-related-result-type`|Supported|`do not infer Objective-C related result type based on method family`|
-|`-fno-operator-names`|Supported|`Do not treat C++ operator name keywords as synonyms for operators`|
-|`-fno-pch-codegen`|Supported|`Do not generate code for uses of this PCH that assumes an explicit object file will be built for the PCH`|
-|`-fno-pch-debuginfo`|Supported|`Do not generate debug info for types in an object file built from this PCH and do not generate them elsewhere`|
-|`-fno-plt`|Supported|`Use GOT indirection instead of PLT to make external function calls (x86 only)`|
-|`-fno-preserve-as-comments`|Supported|`Do not preserve comments in inline assembly`|
-|`-fno-profile-generate`|Supported|`Disable generation of profile instrumentation.`|
-|`-fno-profile-instr-generate`|Supported|`Disable generation of profile instrumentation.`|
-|`-fno-profile-instr-use`|Supported|`Disable using instrumentation data for profile-guided optimization`|
-|`-fno-register-global-dtors-with-atexit`|Supported|`Don't use atexit or __cxa_atexit to register global destructors`|
-|`-fno-rtlib-add-rpath`|Supported|`Do not add -rpath with architecture-specific resource directory to the linker flags`|
-|`-fno-rtti-data`|Supported|`Disable generation of RTTI data`|
-|`-fno-rtti`|Supported|`Disable generation of rtti information`|
-|`-fno-sanitize-address-poison-custom-array-cookie`|Supported on Host only|`Disable poisoning array cookies when using custom operator new[] in AddressSanitizer`|
-|`-fno-sanitize-address-use-after-scope`|Supported on Host only|`Disable use-after-scope detection in AddressSanitizer`|
-|`-fno-sanitize-address-use-odr-indicator`|Supported on Host only|`Disable ODR indicator globals`|
-|`-fno-sanitize-blacklist`|Supported on Host only|`Don't use blacklist file for sanitizers`|
-|`-fno-sanitize-cfi-canonical-jump-tables`|Supported on Host only|`Do not make the jump table addresses canonical in the symbol table`|
-|`-fno-sanitize-cfi-cross-dso`|Supported on Host only|`Disable control flow integrity (CFI) checks for cross-DSO calls.`|
-|`-fno-sanitize-coverage=<value>`|Supported on Host only|`Disable specified features of coverage instrumentation for Sanitizers`|
-|`-fno-sanitize-memory-track-origins`|Supported on Host only|`Disable origins tracking in MemorySanitizer`|
-|`-fno-sanitize-memory-use-after-dtor`|Supported on Host only|`Disable use-after-destroy detection in MemorySanitizer`|
-|`-fno-sanitize-recover=<value>`|Supported on Host only|`Disable recovery for specified sanitizers`|
-|`-fno-sanitize-stats`|Supported on Host only|`Disable sanitizer statistics gathering.`|
-|`-fno-sanitize-thread-atomics`|Supported on Host only|`Disable atomic operations instrumentation in ThreadSanitizer`|
-|`-fno-sanitize-thread-func-entry-exit`|Supported on Host only|`Disable function entry/exit instrumentation in ThreadSanitizer`|
-|`-fno-sanitize-thread-memory-access`|Supported on Host only|`Disable memory access instrumentation in ThreadSanitizer`|
-|`-fno-sanitize-trap=<value>`|Supported on Host only|`Disable trapping for specified sanitizers`|
-|`-fno-sanitize-trap`|Supported on Host only|`Disable trapping for all sanitizers`|
-|`-fno-short-wchar`|Supported|`Force wchar_t to be an unsigned int`|
-|`-fno-show-column`|Supported|`Do not include column number on diagnostics`|
-|`-fno-show-source-location`|Supported|`Do not include source location information with diagnostics`|
-|`-fno-signed-char`|Supported|`char is unsigned`|
-|`-fno-signed-zeros`|Supported|`Allow optimizations that ignore the sign of floating point zeros`|
-|`-fno-spell-checking`|Supported|`Disable spell-checking`|
-|`-fno-split-machine-functions`|Supported|`Disable late function splitting using profile information (x86 ELF)`|
-|`-fno-stack-clash-protection`|Supported|`Disable stack clash protection`|
-|`-fno-stack-protector`|Supported|`Disable the use of stack protectors`|
-|`-fno-standalone-debug`|Supported|`Limit debug information produced to reduce size of debug binary`|
-|`-fno-strict-float-cast-overflow`|Supported|`Relax language rules and try to match the behavior of the target's native float-to-int conversion instructions`|
-|`-fno-strict-return`|Supported|`Don't treat control flow paths that fall off the end of a non-void function as unreachable`|
-|`-fno-sycl`|Unsupported|`Disable SYCL kernels compilation for device`|
-|`-fno-temp-file`|Supported|`Directly create compilation output files. This may lead to incorrect incremental builds if the compiler crashes`|
-|`-fno-threadsafe-statics`|Supported|`Do not emit code to make initialization of local statics thread safe`|
-|`-fno-trigraphs`|Supported|`Do not process trigraph sequences`|
-|`-fno-unique-section-names`|Supported|`Don't use unique names for text and data sections`|
-|`-fno-unroll-loops`|Supported|`Turn off loop unroller`|
-|`-fno-use-cxa-atexit`|Supported|`Don't use __cxa_atexit for calling destructors`|
-|`-fno-use-flang-math-libs`|Supported|`Use Flang internal runtime math library instead of LLVM math intrinsics.`|
-|`-fno-use-init-array`|Supported|`Use .ctors/.dtors instead of .init_array/.fini_array`|
-|`-fno-visibility-inlines-hidden-static-local-var`|Supported|`Disables -fvisibility-inlines-hidden-static-local-var (this is the default on non-darwin targets)`|
-|`-fno-xray-function-index`|Unsupported|`Omit function index section at the expense of single-function patching performance`|
-|`-fno-zero-initialized-in-bss`|Supported|`Don't place zero initialized data in BSS`|
-|`-fobjc-arc-exceptions`|Unsupported|`Use EH-safe code when synthesizing retains and releases in -fobjc-arc`|
-|`-fobjc-arc`|Unsupported|`Synthesize retain and release calls for Objective-C pointers`|
-|`-fobjc-exceptions`|Unsupported|`Enable Objective-C exceptions`|
-|`-fobjc-runtime=<value>`|Unsupported|`Specify the target Objective-C runtime kind and version`|
-|`-fobjc-weak`|Unsupported|`Enable ARC-style weak references in Objective-C`|
-|`-fopenmp-simd`|Unsupported|`Emit OpenMP code only for SIMD-based constructs.`|
-|`-fopenmp-targets=<value>`|Unsupported|`Specify comma-separated list of triples OpenMP offloading targets to be supported`|
-|`-fopenmp`|Unsupported|`Parse OpenMP pragmas and generate parallel code.`|
-|`-foptimization-record-file=<file>`|Supported|`Specify the output name of the file containing the optimization remarks. Implies -fsave-optimization-record. On Darwin platforms, this cannot be used with multiple -arch <arch> options.`|
-|`-foptimization-record-passes=<regex>`|Supported|`Only include passes which match a specified regular expression in the generated optimization record (by default, include all passes)`|
-|`-forder-file-instrumentation`|Supported|`Generate instrumented code to collect order file into default.profraw file (overridden by '=' form of option or LLVM_PROFILE_FILE env var)`|
-|`-fpack-struct=<value>`|Unsupported|`Specify the default maximum struct packing alignment`|
-|`-fpascal-strings`|Supported|`Recognize and construct Pascal-style string literals`|
-|`-fpass-plugin=<dsopath>`|Supported|`Load pass plugin from a dynamic shared object file (only with new pass manager).`|
-|`-fpatchable-function-entry=<N,M>`|Supported|`Generate M NOPs before function entry and N-M NOPs after function entry`|
-|`-fpcc-struct-return`|Unsupported|`Override the default ABI to return all structs on the stack`|
-|`-fpch-codegen`|Supported|`Generate code for uses of this PCH that assumes an explicit object file will be built for the PCH`|
-|`-fpch-debuginfo`|Supported|`Generate debug info for types in an object file built from this PCH and do not generate them elsewhere`|
-|`-fpch-instantiate-templates`|Supported|`Instantiate templates already while building a PCH`|
-|`-fpch-validate-input-files-content`|Supported|`Validate PCH input files based on content if mtime differs`|
-|`-fplugin=<dsopath>`|Supported|`Load the named plugin (dynamic shared object)`|
-|`-fprebuilt-module-path=<directory>`|Unsupported|`Specify the prebuilt module path`|
-|`-fprofile-exclude-files=<value>`|Unsupported|`Instrument only functions from files where names don't match all the regexes separated by a semi-colon`|
-|`-fprofile-filter-files=<value>`|Unsupported|`Instrument only functions from files where names match any regex separated by a semi-colon`|
-|`-fprofile-generate=<directory>`|Unsupported|`Generate instrumented code to collect execution counts into <directory>/default.profraw (overridden by LLVM_PROFILE_FILE env var)`|
-|`-fprofile-generate`|Unsupported|`Generate instrumented code to collect execution counts into default.profraw (overridden by LLVM_PROFILE_FILE env var)`|
-|`-fprofile-instr-generate=<file>`|Unsupported|`Generate instrumented code to collect execution counts into <file> (overridden by LLVM_PROFILE_FILE env var)`|
-|`-fprofile-instr-generate`|Unsupported|`Generate instrumented code to collect execution counts into default.profraw file (overridden by '=' form of option or LLVM_PROFILE_FILE env var)`|
-|`-fprofile-instr-use=<value>`|Unsupported|`Use instrumentation data for profile-guided optimization`|
-|`-fprofile-remapping-file=<file>`|Unsupported|`Use the remappings described in <file> to match the profile data against names in the program`|
-|`-fprofile-sample-accurate`|Unsupported|`Specifies that the sample profile is accurate`|
-|`-fprofile-sample-use=<value>`|Unsupported|`Enable sample-based profile guided optimizations`|
-|`-fprofile-use=<pathname>`|Unsupported|`Use instrumentation data for profile-guided optimization. If pathname is a directory, it reads from <pathname>/default.profdata. Otherwise, it reads from file <pathname>.`|
-|`-freciprocal-math`|Supported|`Allow division operations to be reassociated`|
-|`-freg-struct-return`|Unsupported|`Override the default ABI to return small structs in registers`|
-|`-fregister-global-dtors-with-atexit`|Supported|`Use atexit or __cxa_atexit to register global destructors`|
-|`-frelaxed-template-template-args`|Supported|`Enable C++17 relaxed template template argument matching`|
-|`-freroll-loops`|Supported|`Turn on loop reroller`|
-|`-fropi`|Unsupported|`Generate read-only position independent code (ARM only)`|
-|`-frtlib-add-rpath`|Supported|`Add -rpath with architecture-specific resource directory to the linker flags`|
-|`-frwpi`|Unsupported|`Generate read-write position independent code (ARM only)`|
-|`-fsanitize-address-field-padding=<value>`|Supported on Host only|`Level of field padding for AddressSanitizer`|
-|`-fsanitize-address-globals-dead-stripping`|Supported on Host only|`Enable linker dead stripping of globals in AddressSanitizer`|
-|`-fsanitize-address-poison-custom-array-cookie`|Supported on Host only|`Enable poisoning array cookies when using custom operator new[] in AddressSanitizer`|
-|`-fsanitize-address-use-after-scope`|Supported on Host only|`Enable use-after-scope detection in AddressSanitizer`|
-|`-fsanitize-address-use-odr-indicator`|Supported on Host only|`Enable ODR indicator globals to avoid false ODR violation reports in partially sanitized programs at the cost of an increase in binary size`|
-|`-fsanitize-blacklist=<value>`|Supported on Host only|`Path to blacklist file for sanitizers`|
-|`-fsanitize-cfi-canonical-jump-tables`|Supported on Host only|`Make the jump table addresses canonical in the symbol table`|
-|`-fsanitize-cfi-cross-dso`|Supported on Host only|`Enable control flow integrity (CFI) checks for cross-DSO calls.`|
-|`-fsanitize-cfi-icall-generalize-pointers`|Supported on Host only|`Generalize pointers in CFI indirect call type signature checks`|
-|`-fsanitize-coverage-allowlist=<value>`|Supported on Host only|`Restrict sanitizer coverage instrumentation exclusively to modules and functions that match the provided special case list, except the blocked ones`|
-|`-fsanitize-coverage-blacklist=<value>`|Supported on Host only|`Deprecated, use -fsanitize-coverage-blocklist= instead`|
-|`-fsanitize-coverage-blocklist=<value>`|Supported on Host only|`Disable sanitizer coverage instrumentation for modules and functions that match the provided special case list, even the allowed ones`|
-|`-fsanitize-coverage-whitelist=<value>`|Supported on Host only|`Deprecated, use -fsanitize-coverage-allowlist= instead`|
-|`-fsanitize-coverage=<value>`|Supported on Host only|`Specify the type of coverage instrumentation for Sanitizers`|
-|`-fsanitize-hwaddress-abi=<value>`|Supported on Host only|`Select the HWAddressSanitizer ABI to target (interceptor or platform, default interceptor). This option is currently unused.`|
-|`-fsanitize-memory-track-origins=<value>`|Supported on Host only|`Enable origins tracking in MemorySanitizer`|
-|`-fsanitize-memory-track-origins`|Supported on Host only|`Enable origins tracking in MemorySanitizer`|
-|`-fsanitize-memory-use-after-dtor`|Supported on Host only|`Enable use-after-destroy detection in MemorySanitizer`|
-|`-fsanitize-recover=<value>`|Supported on Host only|`Enable recovery for specified sanitizers`|
-|`-fsanitize-stats`|Supported on Host only|`Enable sanitizer statistics gathering.`|
-|`-fsanitize-system-blacklist=<value>`|Supported on Host only|`Path to system blacklist file for sanitizers`|
-|`-fsanitize-thread-atomics`|Supported on Host only|`Enable atomic operations instrumentation in ThreadSanitizer (default)`|
-|`-fsanitize-thread-func-entry-exit`|Supported on Host only|`Enable function entry/exit instrumentation in ThreadSanitizer (default)`|
-|`-fsanitize-thread-memory-access`|Supported on Host only|`Enable memory access instrumentation in ThreadSanitizer (default)`|
-|`-fsanitize-trap=<value>`|Supported on Host only|`Enable trapping for specified sanitizers`|
-|`-fsanitize-trap`|Supported on Host only|`Enable trapping for all sanitizers`|
-|`-fsanitize-undefined-strip-path-components=<number>`|Supported on Host only|`Strip (or keep only, if negative) a given number of path components when emitting check metadata.`|
-|`-fsanitize=<check>`|Supported on Host only|`Turn on runtime checks for various forms of undefined or suspicious behavior. See user manual for available checks`|
-|`-fsave-optimization-record=<format>`|Supported|`Generate an optimization record file in a specific format`|
-|`-fsave-optimization-record`|Supported|`Generate a YAML optimization record file`|
-|`-fseh-exceptions`|Supported|`Use SEH style exceptions`|
-|`-fshort-enums`|Supported|`Allocate to an enum type only as many bytes as it needs for the declared range of possible values`|
-|`-fshort-wchar`|Unsupported|`Force wchar_t to be a short unsigned int`|
-|`-fshow-overloads=<value>`|Supported|`Which overload candidates to show when overload resolution fails: best\|all; defaults to all`|
-|`-fsigned-char`|Supported|`char is signed`|
-|`-fsized-deallocation`|Supported|`Enable C++14 sized global deallocation functions`|
-|`-fsjlj-exceptions`|Supported|`Use SjLj style exceptions`|
-|`-fslp-vectorize`|Supported|`Enable the superword-level parallelism vectorization passes`|
-|`-fsplit-dwarf-inlining`|Unsupported|`Provide minimal debug info in the object/executable to facilitate online symbolication/stack traces in the absence of .dwo/.dwp files when using Split DWARF`|
-|`-fsplit-lto-unit`|Unsupported|`Enables splitting of the LTO unit`|
-|`-fsplit-machine-functions`|Supported|`Enable late function splitting using profile information (x86 ELF)`|
-|`-fstack-clash-protection`|Supported|`Enable stack clash protection`|
-|`-fstack-protector-all`|Unsupported|`Enable stack protectors for all functions`|
-|`-fstack-protector-strong`|Unsupported|`Enable stack protectors for some functions vulnerable to stack smashing. Compared to -fstack-protector, this uses a stronger heuristic that includes functions containing arrays of any size (and any type), as well as any calls to alloca or the taking of an address from a local variable`|
-|`-fstack-protector`|Unsupported|`Enable stack protectors for some functions vulnerable to stack smashing. This uses a loose heuristic which considers functions vulnerable if they contain a char (or 8bit integer) array or constant sized calls to alloca , which are of greater size than ssp-buffer-size (default: 8 bytes). All variable sized calls to alloca are considered vulnerable. A function with a stack protector has a guard value added to the stack frame that is checked on function exit. The guard value must be positioned in the stack frame such that a buffer overflow from a vulnerable variable will overwrite the guard value before overwriting the function's return address. The reference stack guard value is stored in a global variable.`|
-|`-fstack-size-section`|Supported|`Emit section containing metadata on function stack sizes`|
-|`-fstandalone-debug`|Supported|`Emit full debug info for all types used by the program`|
-|`-fstrict-enums`|Supported|`Enable optimizations based on the strict definition of an enum's value range`|
-|`-fstrict-float-cast-overflow`|Supported|`Assume that overflowing float-to-int casts are undefined (default)`|
-|`-fstrict-vtable-pointers`|Supported|`Enable optimizations based on the strict rules for overwriting polymorphic C++ objects`|
-|`-fsycl`|Unsupported|`Enable SYCL kernels compilation for device`|
-|`-fsystem-module`|u|`Build this module as a system module. Only used with -emit-module`|
-|`-fthin-link-bitcode=<value>`|Supported|`Write minimized bitcode to <file> for the ThinLTO thin link only`|
-|`-fthinlto-index=<value>`|Unsupported|`Perform ThinLTO importing using provided function summary index`|
-|`-ftime-trace-granularity=<value>`|Supported|`Minimum time granularity (in microseconds) traced by time profiler`|
-|`-ftime-trace`|Supported|`Turn on time profiler. Generates JSON file based on output filename.`|
-|`-ftrap-function=<value>`|Unsupported|`Issue call to specified function rather than a trap instruction`|
-|`-ftrapv-handler=<function name>`|Unsupported|`Specify the function to be called on overflow`|
-|`-ftrapv`|Unsupported|`Trap on integer overflow`|
-|`-ftrigraphs`|Supported|`Process trigraph sequences`|
-|`-ftrivial-auto-var-init-stop-after=<value>`|Supported|`Stop initializing trivial automatic stack variables after the specified number of instances`|
-|`-ftrivial-auto-var-init=<value>`|Supported|`Initialize trivial automatic stack variables: uninitialized (default) \| pattern`|
-|`-funique-basic-block-section-names`|Supported|`Use unique names for basic block sections (ELF Only)`|
-|`-funique-internal-linkage-names`|Supported|`Uniqueify Internal Linkage Symbol Names by appending the MD5 hash of the module path`|
-|`-funroll-loops`|Supported|`Turn on loop unroller`|
-|`-fuse-flang-math-libs`|Supported|`Use Flang internal runtime math library instead of LLVM math intrinsics.`|
-|`-fuse-line-directives`|Supported|`Use #line in preprocessed output`|
-|`-fvalidate-ast-input-files-content`|Supported|`Compute and store the hash of input files used to build an AST. Files with mismatching mtime's are considered valid if both contents is identical`|
-|`-fveclib=<value>`|Unsupported|`Use the given vector functions library`|
-|`-fvectorize`|Unsupported|`Enable the loop vectorization passes`|
-|`-fverbose-asm`|Supported|`Generate verbose assembly output`|
-|`-fvirtual-function-elimination`|Supported|`Enables dead virtual function elimination optimization. Requires -flto=full`|
-|`-fvisibility-global-new-delete-hidden`|Supported|`Give global C++ operator new and delete declarations hidden visibility`|
-|`-fvisibility-inlines-hidden-static-local-var`|Supported|`When -fvisibility-inlines-hidden is enabled, static variables in inline C++ member functions will also be given hidden visibility by default`|
-|`-fvisibility-inlines-hidden`|Supported|`Give inline C++ member functions hidden visibility by default`|
-|`-fvisibility-ms-compat`|Supported|`Give global types 'default' visibility and global functions and variables 'hidden' visibility by default`|
-|`-fvisibility=<value>`|Supported|`Set the default symbol visibility for all global declarations`|
-|`-fwasm-exceptions`|Unsupported|`Use WebAssembly style exceptions`|
-|`-fwhole-program-vtables`|Unsupported|`Enables whole-program vtable optimization. Requires -flto`|
-|`-fwrapv`|Supported|`Treat signed integer overflow as two's complement`|
-|`-fwritable-strings`|Supported|`Store string literals as writable data`|
-|`-fxray-always-emit-customevents`|Unsupported|`Always emit __xray_customevent(...) calls even if the containing function is not always instrumented`|
-|`-fxray-always-emit-typedevents`|Unsupported|`Always emit __xray_typedevent(...) calls even if the containing function is not always instrumented`|
-|`-fxray-always-instrument= <value>`|Unsupported|`DEPRECATED: Filename defining the whitelist for imbuing the 'always instrument' XRay attribute.`|
-|`-fxray-attr-list= <value>`|Unsupported|`Filename defining the list of functions/types for imbuing XRay attributes.`|
-|`-fxray-ignore-loops`|Unsupported|`Don't instrument functions with loops unless they also meet the minimum function size`|
-|`-fxray-instruction-threshold= <value>`|Unsupported|`Sets the minimum function size to instrument with XRay`|
-|`-fxray-instrumentation-bundle= <value>`|Unsupported|`Select which XRay instrumentation points to emit. Options: all, none, function-entry, function-exit, function, custom. Default is 'all'. 'function' includes both 'function-entry' and 'function-exit'.`|
-|`-fxray-instrument`|Unsupported|`Generate XRay instrumentation sleds on function entry and exit`|
-|`-fxray-link-deps`|Unsupported|`Tells clang to add the link dependencies for XRay.`|
-|`-fxray-modes= <value>`|Unsupported|`List of modes to link in by default into XRay instrumented binaries.`|
-|`-fxray-never-instrument= <value>`|Unsupported|`DEPRECATED: Filename defining the whitelist for imbuing the 'never instrument' XRay attribute.`|
-|`-fzvector`|Supported|`Enable System z vector language extension`|
-|`-F <value>`|Unsupported|`Add directory to framework include search path`|
-|`--gcc-toolchain=<value>`|Supported|`Use the gcc toolchain at the given directory`|
-|`-gcodeview-ghash`|Supported|`Emit type record hashes in a .debug$H section`|
-|`-gcodeview`|Supported|`Generate CodeView debug information`|
-|`-gdwarf-2`|Supported|`Generate source-level debug information with dwarf version 2`|
-|`-gdwarf-3`|Supported|`Generate source-level debug information with dwarf version 3`|
-|`-gdwarf-4`|Supported|`Generate source-level debug information with dwarf version 4`|
-|`-gdwarf-5`|Supported|`Generate source-level debug information with dwarf version 5`|
-|`-gdwarf`|Supported|`Generate source-level debug information with the default dwarf version`|
-|`-gembed-source`|Supported|`Embed source text in DWARF debug sections`|
-|`-gline-directives-only`|Supported|`Emit debug line info directives only`|
-|`-gline-tables-only`|Supported|`Emit debug line number tables only`|
-|`-gmodules`|Supported|`Generate debug info with external references to clang modules or precompiled headers`|
-|`-gno-embed-source`|Supported|`Restore the default behavior of not embedding source text in DWARF debug sections`|
-|`-gno-inline-line-tables`|Supported|`Don't emit inline line tables`|
-|`--gpu-max-threads-per-block=<value>`|Supported|`Default max threads per block for kernel launch bounds for HIP`|
-|`-gsplit-dwarf=<value>`|Supported|`Set DWARF fission mode to either 'split' or 'single'`|
-|`-gz=<value>`|Supported|`DWARF debug sections compression type`|
-|`-gz`|Supported|`DWARF debug sections compression type`|
-|`-G <size>`|Unsupported|`Put objects of at most <size> bytes into small data section (MIPS / Hexagon)`|
-|`-g`|Supported|`Generate source-level debug information`|
-|`--help-hidden`|Supported|`Display help for hidden options`|
-|`-help`|Supported|`Display available options`|
-|`--hip-device-lib=<value>`|Supported|`HIP device library`|
-|`--hip-link`|Supported|`Link clang-offload-bundler bundles for HIP`|
-|`--hip-version=<value>`|Supported|`HIP version in the format of major.minor.patch`|
-|`-H`|Supported|`Show header includes and nesting depth`|
-|`-I-`|Supported|`Restrict all prior -I flags to double-quoted inclusion and remove current directory from include path`|
-|`-ibuiltininc`|Supported|`Enable builtin #include directories even when -nostdinc is used before or after -ibuiltininc. Using -nobuiltininc after the option disables it`|
-|`-idirafter <value>`|Supported|`Add directory to AFTER include search path`|
-|`-iframeworkwithsysroot <directory>`|Unsupported|`Add directory to SYSTEM framework search path, absolute paths are relative to -isysroot`|
-|`-iframework <value>`|Unsupported|`Add directory to SYSTEM framework search path`|
-|`-imacros <file>`|Supported|`Include macros from file before parsing`|
-|`-include-pch <file>`|Supported|`Include precompiled header file`|
-|`-include <file>`|Supported|`Include file before parsing`|
-|`-index-header-map`|Supported|`Make the next included directory (-I or -F) an indexer header map`|
-|`-iprefix <dir>`|Supported|`Set the -iwithprefix/-iwithprefixbefore prefix`|
-|`-iquote <directory>`|Supported|`Add directory to QUOTE include search path`|
-|`-isysroot <dir>`|Supported|`Set the system root directory (usually /)`|
-|`-isystem-after <directory>`|Supported|`Add directory to end of the SYSTEM include search path`|
-|`-isystem <directory>`|Supported|`Add directory to SYSTEM include search path`|
-|`-ivfsoverlay <value>`|Supported|`Overlay the virtual filesystem described by file over the real file system`|
-|`-iwithprefixbefore <dir>`|Supported|`Set directory to include search path with prefix`|
-|`-iwithprefix <dir>`|Supported|`Set directory to SYSTEM include search path with prefix`|
-|`-iwithsysroot <directory>`|Supported|`Add directory to SYSTEM include search path, absolute paths are relative to -isysroot`|
-|`-I <dir>`|Supported|`Add directory to include search path. If there are multiple -I options, these directories are searched in the order they are given before the standard system directories are searched. If the same directory is in the SYSTEM include search paths, for example if also specified with -isystem, the -I option will be ignored`|
-|`--libomptarget-nvptx-path=<value>`|Unsupported|`Path to libomptarget-nvptx libraries`|
-|`-L <dir>`|Supported|`Add directory to library search path`|
-|`-mabicalls`|Unsupported|`Enable SVR4-style position-independent code (Mips only)`|
-|`-maix-struct-return`|Unsupported|`Return all structs in memory (PPC32 only)`|
-|`-malign-branch-boundary=<value>`|Supported|`Specify the boundary's size to align branches`|
-|`-malign-branch=<value>`|Supported|`Specify types of branches to align`|
-|`-malign-double`|Supported|`Align doubles to two words in structs (x86 only)`|
-|`-Mallocatable=<value>`|Unsupported|`Select semantics for assignments to allocatables (F03 or F95)`|
-|`-mbackchain`|Unsupported|`Link stack frames through backchain on System Z`|
-|`-mbranch-protection=<value>`|Unsupported|`Enforce targets of indirect branches and function returns`|
-|`-mbranches-within-32B-boundaries`|Supported|`Align selected branches (fused, jcc, jmp) within 32-byte boundary`|
-|`-mcmodel=medany`|Unsupported|`Equivalent to -mcmodel=medium, compatible with RISC-V gcc.`|
-|`-mcmodel=medlow`|Unsupported|`Equivalent to -mcmodel=small, compatible with RISC-V gcc.`|
-|`-mcmse`|Unsupported|`Allow use of CMSE (Armv8-M Security Extensions)`|
-|`-mcode-object-v3`|Supported|`Legacy option to specify code object ABI V2 (-mnocode-object-v3) or V3 (-mcode-object-v3) (AMDGPU only)`|
-|`-mcode-object-version=<version>`|Supported|`Specify code object ABI version. Defaults to 4. (AMDGPU only)`|
-|`-mcrc`|Unsupported|`Allow use of CRC instructions (ARM/Mips only)`|
-|`-mcumode`|Supported|`Specify CU (-mcumode) or WGP (-mno-cumode) wavefront execution mode (AMDGPU only)`|
-|`-mdouble=<value>`|Supported|`Force double to be 32 bits or 64 bits`|
-|`-MD`|Supported|`Write a depfile containing user and system headers`|
-|`-meabi <value>`|Supported|`Set EABI type, e.g. 4, 5 or gnu (default depends on triple)`|
-|`-membedded-data`|Unsupported|`Place constants in the .rodata section instead of the .sdata section even if they meet the -G <size> threshold (MIPS)`|
-|`-menable-experimental-extensions`|Unsupported|`Enable use of experimental RISC-V extensions.`|
-|`-mexec-model=<value>`|Unsupported|`Execution model (WebAssembly only)`|
-|`-mexecute-only`|Unsupported|`Disallow generation of data access to code sections (ARM only)`|
-|`-mextern-sdata`|Unsupported|`Assume that externally defined data is in the small data if it meets the -G <size> threshold (MIPS)`|
-|`-mfentry`|Unsupported|`Insert calls to fentry at function entry (x86/SystemZ only)`|
-|`-mfix-cortex-a53-835769`|Unsupported|`Workaround Cortex-A53 erratum 835769 (AArch64 only)`|
-|`-mfp32`|Unsupported|`Use 32-bit floating point registers (MIPS only)`|
-|`-mfp64`|Unsupported|`Use 64-bit floating point registers (MIPS only)`|
-|`-MF <file>`|Supported|`Write depfile output from -MMD, -MD, -MM, or -M to <file>`|
-|`-mgeneral-regs-only`|Unsupported|`Generate code which only uses the general purpose registers (AArch64 only)`|
-|`-mglobal-merge`|Supported|`Enable merging of globals`|
-|`-mgpopt`|Unsupported|`Use GP relative accesses for symbols known to be in a small data section (MIPS)`|
-|`-MG`|Supported|`Add missing headers to depfile`|
-|`-mharden-sls=<value>`|Unsupported|`Select straight-line speculation hardening scope`|
-|`-mhvx-length=<value>`|Unsupported|`Set Hexagon Vector Length`|
-|`-mhvx=<value>`|Unsupported|`Enable Hexagon Vector eXtensions`|
-|`-mhvx`|Unsupported|`Enable Hexagon Vector eXtensions`|
-|`-miamcu`|Unsupported|`Use Intel MCU ABI`|
-|`--migrate`|Unsupported|`Run the migrator`|
-|`-mincremental-linker-compatible`|Supported|`(integrated-as) Emit an object file which can be used with an incremental linker`|
-|`-mindirect-jump=<value>`|Unsupported|`Change indirect jump instructions to inhibit speculation`|
-|`-Minform=<value>`|Supported|`Set error level of messages to display`|
-|`-mios-version-min=<value>`|Unsupported|`Set iOS deployment target`|
-|`-MJ <value>`|Unsupported|`Write a compilation database entry per input`|
-|`-mllvm <value>`|Supported|`Additional arguments to forward to LLVM's option processing`|
-|`-mlocal-sdata`|Unsupported|`Extend the -G behaviour to object local data (MIPS)`|
-|`-mlong-calls`|Supported|`Generate branches with extended addressability, usually via indirect jumps.`|
-|`-mlong-double-128`|Supported on Host only|`Force long double to be 128 bits`|
-|`-mlong-double-64`|Supported|`Force long double to be 64 bits`|
-|`-mlong-double-80`|Supported on Host only|`Force long double to be 80 bits, padded to 128 bits for storage`|
-|`-mlvi-cfi`|Supported on Host only|`Enable only control-flow mitigations for Load Value Injection (LVI)`|
-|`-mlvi-hardening`|Supported on Host only|`Enable all mitigations for Load Value Injection (LVI)`|
-|`-mmacosx-version-min=<value>`|Unsupported|`Set Mac OS X deployment target`|
-|`-mmadd4`|Supported|`Enable the generation of 4-operand madd.s, madd.d and related instructions.`|
-|`-mmark-bti-property`|Unsupported|`Add .note.gnu.property with BTI to assembly files (AArch64 only)`|
-|`-MMD`|Supported|`Write a depfile containing user headers`|
-|`-mmemops`|Supported|`Enable generation of memop instructions`|
-|`-mms-bitfields`|Unsupported|`Set the default structure layout to be compatible with the Microsoft compiler standard`|
-|`-mmsa`|Unsupported|`Enable MSA ASE (MIPS only)`|
-|`-mmt`|Unsupported|`Enable MT ASE (MIPS only)`|
-|`-MM`|Supported|`Like -MMD, but also implies -E and writes to stdout by default`|
-|`-mno-abicalls`|Unsupported|`Disable SVR4-style position-independent code (Mips only)`|
-|`-mno-crc`|Unsupported|`Disallow use of CRC instructions (Mips only)`|
-|`-mno-embedded-data`|Unsupported|`Do not place constants in the .rodata section instead of the .sdata if they meet the -G <size> threshold (MIPS)`|
-|`-mno-execute-only`|Unsupported|`Allow generation of data access to code sections (ARM only)`|
-|`-mno-extern-sdata`|Unsupported|`Do not assume that externally defined data is in the small data if it meets the -G <size> threshold (MIPS)`|
-|`-mno-fix-cortex-a53-835769`|Unsupported|`Don't workaround Cortex-A53 erratum 835769 (AArch64 only)`|
-|`-mno-global-merge`|Supported|`Disable merging of globals`|
-|`-mno-gpopt`|Unsupported|`Do not use GP relative accesses for symbols known to be in a small data section (MIPS)`|
-|`-mno-hvx`|Unsupported|`Disable Hexagon Vector eXtensions`|
-|`-mno-implicit-float`|Supported|`Don't generate implicit floating point instructions`|
-|`-mno-incremental-linker-compatible`|Supported|`(integrated-as) Emit an object file which cannot be used with an incremental linker`|
-|`-mno-local-sdata`|Unsupported|`Do not extend the -G behaviour to object local data (MIPS)`|
-|`-mno-long-calls`|Supported|`Restore the default behaviour of not generating long calls`|
-|`-mno-lvi-cfi`|Supported on Host only|`Disable control-flow mitigations for Load Value Injection (LVI)`|
-|`-mno-lvi-hardening`|Supported on Host only|`Disable mitigations for Load Value Injection (LVI)`|
-|`-mno-madd4`|Supported|`Disable the generation of 4-operand madd.s, madd.d and related instructions.`|
-|`-mno-memops`|Supported|`Disable generation of memop instructions`|
-|`-mno-movt`|Supported|`Disallow use of movt/movw pairs (ARM only)`|
-|`-mno-ms-bitfields`|Supported|`Do not set the default structure layout to be compatible with the Microsoft compiler standard`|
-|`-mno-msa`|Unsupported|`Disable MSA ASE (MIPS only)`|
-|`-mno-mt`|Unsupported|`Disable MT ASE (MIPS only)`|
-|`-mno-neg-immediates`|Supported|`Disallow converting instructions with negative immediates to their negation or inversion.`|
-|`-mno-nvj`|Supported|`Disable generation of new-value jumps`|
-|`-mno-nvs`|Supported|`Disable generation of new-value stores`|
-|`-mno-outline`|Unsupported|`Disable function outlining (AArch64 only)`|
-|`-mno-packets`|Supported|`Disable generation of instruction packets`|
-|`-mno-relax`|Supported|`Disable linker relaxation`|
-|`-mno-restrict-it`|Unsupported|`Allow generation of deprecated IT blocks for ARMv8. It is off by default for ARMv8 Thumb mode`|
-|`-mno-save-restore`|Unsupported|`Disable using library calls for save and restore`|
-|`-mno-seses`|Unsupported|`Disable speculative execution side effect suppression (SESES)`|
-|`-mno-stack-arg-probe`|Supported|`Disable stack probes which are enabled by default`|
-|`-mno-tls-direct-seg-refs`|Supported|`Disable direct TLS access through segment registers`|
-|`-mno-unaligned-access`|Unsupported|`Force all memory accesses to be aligned (AArch32/AArch64 only)`|
-|`-mno-wavefrontsize64`|Supported|`Specify wavefront size 32 mode (AMDGPU only)`|
-|`-mnocrc`|Unsupported|`Disallow use of CRC instructions (ARM only)`|
-|`-mnop-mcount`|Supported|`Generate mcount/__fentry__ calls as nops. To activate they need to be patched in.`|
-|`-mnvj`|Supported|`Enable generation of new-value jumps`|
-|`-mnvs`|Supported|`Enable generation of new-value stores`|
-|`-module-dependency-dir <value>`|Unsupported|`Directory to dump module dependencies to`|
-|`-module-file-info`|Unsupported|`Provide information about a particular module file`|
-|`-momit-leaf-frame-pointer`|Supported|`Omit frame pointer setup for leaf functions`|
-|`-moutline`|Unsupported|`Enable function outlining (AArch64 only)`|
-|`-mpacked-stack`|Unsupported|`Use packed stack layout (SystemZ only).`|
-|`-mpackets`|Supported|`Enable generation of instruction packets`|
-|`-mpad-max-prefix-size=<value>`|Supported|`Specify maximum number of prefixes to use for padding`|
-|`-mpie-copy-relocations`|Supported|`Use copy relocations support for PIE builds`|
-|`-mprefer-vector-width=<value>`|Unsupported|`Specifies preferred vector width for auto-vectorization. Defaults to 'none' which allows target specific decisions.`|
-|`-MP`|Supported|`Create phony target for each dependency (other than main file)`|
-|`-mqdsp6-compat`|Unsupported|`Enable hexagon-qdsp6 backward compatibility`|
-|`-MQ <value>`|Supported|`Specify name of main file output to quote in depfile`|
-|`-mrecord-mcount`|Supported|`Generate a __mcount_loc section entry for each __fentry__ call.`|
-|`-mrelax-all`|Supported|`(integrated-as) Relax all machine instructions`|
-|`-mrelax`|Supported|`Enable linker relaxation`|
-|`-mrestrict-it`|Unsupported|`Disallow generation of deprecated IT blocks for ARMv8. It is on by default for ARMv8 Thumb mode.`|
-|`-mrtd`|Unsupported|`Make StdCall calling convention the default`|
-|`-msave-restore`|Unsupported|`Enable using library calls for save and restore`|
-|`-mseses`|Unsupported|`Enable speculative execution side effect suppression (SESES). Includes LVI control flow integrity mitigations`|
-|`-msign-return-address=<value>`|Unsupported|`Select return address signing scope`|
-|`-msmall-data-limit=<value>`|Supported|`Put global and static data smaller than the limit into a special section`|
-|`-msoft-float`|Supported|`Use software floating point`|
-|`-msram-ecc`|Supported|`Legacy option to specify SRAM ECC mode (AMDGPU only). Should use --offload-arch with :sramecc+ instead`|
-|`-mstack-alignment=<value>`|Unsupported|`Set the stack alignment`|
-|`-mstack-arg-probe`|Unsupported|`Enable stack probes`|
-|`-mstack-probe-size=<value>`|Unsupported|`Set the stack probe size`|
-|`-mstackrealign`|Unsupported|`Force realign the stack at entry to every function`|
-|`-msve-vector-bits=<value>`|Unsupported|`Specify the size in bits of an SVE vector register. Defaults to the vector length agnostic value of "scalable". (AArch64 only)`|
-|`-msvr4-struct-return`|Unsupported|`Return small structs in registers (PPC32 only)`|
-|`-mthread-model <value>`|Supported|`The thread model to use, e.g. posix, single (posix by default)`|
-|`-mtls-direct-seg-refs`|Supported|`Enable direct TLS access through segment registers (default)`|
-|`-mtls-size=<value>`|Unsupported|`Specify bit size of immediate TLS offsets (AArch64 ELF only): 12 (for 4KB) \| 24 (for 16MB, default) \| 32 (for 4GB) \| 48 (for 256TB, needs -mcmodel=large)`|
-|`-mtp=<value>`|Unsupported|`Thread pointer access method (AArch32/AArch64 only)`|
-|`-mtune=<value>`|Supported on Host only|`Only supported on X86. Otherwise accepted for compatibility with GCC.`|
-|`-MT <value>`|Unsupported|`Specify name of main file output in depfile`|
-|`-munaligned-access`|Unsupported|`Allow memory accesses to be unaligned (AArch32/AArch64 only)`|
-|`-MV`|Supported|`Use NMake/Jom format for the depfile`|
-|`-mwavefrontsize64`|Supported|`Specify wavefront size 64 mode (AMDGPU only)`|
-|`-mxnack`|Supported|`Legacy option to specify XNACK mode (AMDGPU only). Should use --offload-arch with :xnack+ instead`|
-|`-M`|Supported|`Like -MD, but also implies -E and writes to stdout by default`|
-|`--no-cuda-include-ptx=<value>`|Supported|`Do not include PTX for the following GPU architecture (e.g. sm_35) or 'all'. May be specified more than once.`|
-|`--no-cuda-version-check`|Supported|`Don't error out if the detected version of the CUDA install is too low for the requested CUDA gpu architecture.`|
-|`-no-flang-libs`|Supported|`Do not link against Flang libraries`|
-|`--no-offload-arch=<value>`|Supported|`Remove CUDA/HIP offloading device architecture (e.g. sm_35, gfx906) from the list of devices to compile for. 'all' resets the list to its default value.`|
-|`--no-system-header-prefix=<prefix>`|Supported|`Treat all #include paths starting with <prefix> as not including a system header.`|
-|`-nobuiltininc`|Supported|`Disable builtin #include directories`|
-|`-nogpuinc`|Supported|`Do not add CUDA/HIP include paths and include default CUDA/HIP wrapper header files`|
-|`-nogpulib`|Supported|`Do not link device library for CUDA/HIP device compilation`|
-|`-nostdinc++`|Unsupported|`Disable standard #include directories for the C++ standard library`|
-|`-ObjC++`|Unsupported|`Treat source input files as Objective-C++ inputs`|
-|`-objcmt-atomic-property`|Unsupported|`Make migration to 'atomic' properties`|
-|`-objcmt-migrate-all`|Unsupported|`Enable migration to modern ObjC`|
-|`-objcmt-migrate-annotation`|Unsupported|`Enable migration to property and method annotations`|
-|`-objcmt-migrate-designated-init`|Unsupported|`Enable migration to infer NS_DESIGNATED_INITIALIZER for initializer methods`|
-|`-objcmt-migrate-instancetype`|Unsupported|`Enable migration to infer instancetype for method result type`|
-|`-objcmt-migrate-literals`|Unsupported|`Enable migration to modern ObjC literals`|
-|`-objcmt-migrate-ns-macros`|Unsupported|`Enable migration to NS_ENUM/NS_OPTIONS macros`|
-|`-objcmt-migrate-property-dot-syntax`|Unsupported|`Enable migration of setter/getter messages to property-dot syntax`|
-|`-objcmt-migrate-property`|Unsupported|`Enable migration to modern ObjC property`|
-|`-objcmt-migrate-protocol-conformance`|Unsupported|`Enable migration to add protocol conformance on classes`|
-|`-objcmt-migrate-readonly-property`|Unsupported|`Enable migration to modern ObjC readonly property`|
-|`-objcmt-migrate-readwrite-property`|Unsupported|`Enable migration to modern ObjC readwrite property`|
-|`-objcmt-migrate-subscripting`|Unsupported|`Enable migration to modern ObjC subscripting`|
-|`-objcmt-ns-nonatomic-iosonly`|Unsupported|`Enable migration to use NS_NONATOMIC_IOSONLY macro for setting property's 'atomic' attribute`|
-|`-objcmt-returns-innerpointer-property`|Unsupported|`Enable migration to annotate property with NS_RETURNS_INNER_POINTER`|
-|`-objcmt-whitelist-dir-path=<value>`|Unsupported|`Only modify files with a filename contained in the provided directory path`|
-|`-ObjC`|Unsupported|`Treat source input files as Objective-C inputs`|
-|`--offload-arch=<value>`|Supported|`CUDA offloading device architecture (e.g. sm_35), or HIP offloading target ID in the form of a device architecture followed by target ID features delimited by a colon. Each target ID feature is a pre-defined string followed by a plus or minus sign (e.g. gfx908:xnack+:sramecc-). May be specified more than once.`|
-|`-o <file>`|Supported|`Write output to <file>`|
-|`-parallel-jobs=<value>`|Supported|`Number of parallel jobs`|
-|`-pg`|Supported|`Enable mcount instrumentation`|
-|`-pipe`|Supported|`Use pipes between commands, when possible`|
-|`--precompile`|Supported|`Only precompile the input`|
-|`-print-effective-triple`|Supported|`Print the effective target triple`|
-|`-print-file-name=<file>`|Supported|`Print the full library path of <file>`|
-|`-print-ivar-layout`|Unsupported|`Enable Objective-C Ivar layout bitmap print trace`|
-|`-print-libgcc-file-name`|Supported|`Print the library path for the currently used compiler runtime library ("libgcc.a" or "libclang_rt.builtins.*.a")`|
-|`-print-prog-name=<name>`|Supported|`Print the full program path of <name>`|
-|`-print-resource-dir`|Supported|`Print the resource directory pathname`|
-|`-print-search-dirs`|Supported|`Print the paths used for finding libraries and programs`|
-|`-print-supported-cpus`|Supported|`Print supported cpu models for the given target (if target is not specified, it will print the supported cpus for the default target)`|
-|`-print-target-triple`|Supported|`Print the normalized target triple`|
-|`-print-targets`|Supported|`Print the registered targets`|
-|`-pthread`|Supported|`Support POSIX threads in generated code`|
-|`--ptxas-path=<value>`|Unsupported|`Path to ptxas (used for compiling CUDA code)`|
-|`-P`|Supported|`Disable linemarker output in -E mode`|
-|`-Qn`|Supported|`Do not emit metadata containing compiler name and version`|
-|`-Qunused-arguments`|Supported|`Don't emit warning for unused driver arguments`|
-|`-Qy`|Supported|`Emit metadata containing compiler name and version`|
-|`-relocatable-pch`|Supported|`Whether to build a relocatable precompiled header`|
-|`-rewrite-legacy-objc`|Unsupported|`Rewrite Legacy Objective-C source to C++`|
-|`-rewrite-objc`|Unsupported|`Rewrite Objective-C source to C++`|
-|`--rocm-device-lib-path=<value>`|Supported|`ROCm device library path. Alternative to rocm-path.`|
-|`--rocm-path=<value>`|Supported|`ROCm installation path, used for finding and automatically linking required bitcode libraries.`|
-|`-Rpass-analysis=<value>`|Supported|`Report transformation analysis from optimization passes whose name matches the given POSIX regular expression`|
-|`-Rpass-missed=<value>`|Supported|`Report missed transformations by optimization passes whose name matches the given POSIX regular expression`|
-|`-Rpass=<value>`|Supported|`Report transformations performed by optimization passes whose name matches the given POSIX regular expression`|
-|`-rtlib=<value>`|Unsupported|`Compiler runtime library to use`|
-|`-R<remark>`|Unsupported|`Enable the specified remark`|
-|`-save-stats=<value>`|Supported|`Save llvm statistics.`|
-|`-save-stats`|Supported|`Save llvm statistics.`|
-|`-save-temps=<value>`|Supported|`Save intermediate compilation results.`|
-|`-save-temps`|Supported|`Save intermediate compilation results`|
-|`-serialize-diagnostics <value>`|Supported|`Serialize compiler diagnostics to a file`|
-|`-shared-libsan`|Unsupported|`Dynamically link the sanitizer runtime`|
-|`-static-flang-libs`|Supported|`Link using static Flang libraries`|
-|`-static-libsan`|Unsupported|`Statically link the sanitizer runtime`|
-|`-static-openmp`|Supported|`Use the static host OpenMP runtime while linking.`|
-|`-std=<value>`|Supported|`Language standard to compile for`|
-|`-stdlib++-isystem <directory>`|Supported|`Use directory as the C++ standard library include path`|
-|`-stdlib=<value>`|Supported|`C++ standard library to use`|
-|`-sycl-std=<value>`|Unsupported|`SYCL language standard to compile for.`|
-|`--system-header-prefix=<prefix>`|Supported|`Treat all #include paths starting with <prefix> as including a system header.`|
-|`-S`|Supported|`Only run preprocess and compilation steps`|
-|`--target=<value>`|Supported|`Generate code for the given target`|
-|`-Tbss <addr>`|Supported|`Set starting address of BSS to <addr>`|
-|`-Tdata <addr>`|Supported|`Set starting address of DATA to <addr>`|
-|`-time`|Supported|`Time individual commands`|
-|`-traditional-cpp`|Unsupported|`Enable some traditional CPP emulation`|
-|`-trigraphs`|Supported|`Process trigraph sequences`|
-|`-Ttext <addr>`|Supported|`Set starting address of TEXT to <addr>`|
-|`-T <script>`|Unsupported|`Specify <script> as linker script`|
-|`-undef`|Supported|`undef all system defines`|
-|`-unwindlib=<value>`|Supported|`Unwind library to use`|
-|`-U <macro>`|Supported|`Undefine macro <macro>`|
-|`--verify-debug-info`|Supported|`Verify the binary representation of debug output`|
-|`-verify-pch`|Unsupported|`Load and verify that a pre-compiled header file is not stale`|
-|`--version`|Supported|`Print version information`|
-|`-v`|Supported|`Show commands to run and use verbose output`|
-|`-Wa,<arg>`|Supported|`Pass the comma separated arguments in <arg> to the assembler`|
-|`-Wdeprecated`|Supported|`Enable warnings for deprecated constructs and define __DEPRECATED`|
-|`-Wl,<arg>`|Supported|`Pass the comma separated arguments in <arg> to the linker`|
-|`-working-directory <value>`|Supported|`Resolve file paths relative to the specified directory`|
-|`-Wp,<arg>`|Supported|`Pass the comma separated arguments in <arg> to the preprocessor`|
-|`-W<warning>`|Supported|`Enable the specified warning`|
-|`-w`|Supported|`Suppress all warnings`|
-|`-Xanalyzer <arg>`|Supported|`Pass <arg> to the static analyzer`|
-|`-Xarch_device <arg>`|Supported|`Pass <arg> to the CUDA/HIP device compilation`|
-|`-Xarch_host <arg>`|Supported|`Pass <arg> to the CUDA/HIP host compilation`|
-|`-Xassembler <arg>`|Supported|`Pass <arg> to the assembler`|
-|`-Xclang <arg>`|Supported|`Pass <arg> to the clang compiler`|
-|`-Xcuda-fatbinary <arg>`|Supported|`Pass <arg> to fatbinary invocation`|
-|`-Xcuda-ptxas <arg>`|Supported|`Pass <arg> to the ptxas assembler`|
-|`-Xlinker <arg>`|Supported|`Pass <arg> to the linker`|
-|`-Xopenmp-target=<triple> <arg>`|Supported|`Pass <arg> to the target offloading toolchain identified by <triple>.`|
-|`-Xopenmp-target <arg>`|Supported|`Pass <arg> to the target offloading toolchain.`|
-|`-Xpreprocessor <arg>`|Supported|`Pass <arg> to the preprocessor`|
-|`-x <language>`|Supported|`Treat subsequent input files as having type <language>`|
-|`-z <arg>`|Supported|`Pass -z <arg> to the linker`|
diff --git a/projects/hip/docs/markdown/clang_options.txt b/projects/hip/docs/markdown/clang_options.txt
deleted file mode 100644
index 654fda238b..0000000000
--- a/projects/hip/docs/markdown/clang_options.txt
+++ /dev/null
@@ -1,758 +0,0 @@
--### s
---analyzer-output s
---analyze s
--arcmt-migrate-emit-errors n
--arcmt-migrate-report-output n
--byteswapio s
--B s
--CC s
--cl-denorms-are-zero s
--cl-fast-relaxed-math s
--cl-finite-math-only s
--cl-fp32-correctly-rounded-divide-sqrt s
--cl-kernel-arg-info s
--cl-mad-enable s
--cl-no-signed-zeros s
--cl-opt-disable s
--cl-single-precision-constant s
--cl-std s
--cl-strict-aliasing s
--cl-uniform-work-group-size s
--cl-unsafe-math-optimizations s
---config s
---cuda-compile-host-device s
---cuda-device-only s
---cuda-host-only s
---cuda-include-ptx n
---cuda-noopt-device-debug n
---cuda-path-ignore-env n
---cuda-path n
--cxx-isystem s
--C s
--c s
--dD s
--dependency-dot s
--dependency-file s
--dI s
--dM s
--dsym-dir n
--D s
--emit-ast s
--emit-interface-stubs s
--emit-llvm s
--emit-merged-ifs s
---emit-static-lib s
--enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang s
--E s
--fAAPCSBitfieldLoad n
--faddrsig s
--faligned-allocation s
--fallow-editor-placeholders s
--fallow-fortran-gnu-ext s
--fansi-escape-codes s
--fapple-kext n
--fapple-link-rtlib n
--fapple-pragma-pack n
--fapplication-extension n
--fbackslash s
--fbasic-block-sections s
--fblocks s
--fborland-extensions n
--fbuild-session-file s
--fbuild-session-timestamp s
--fbuiltin-module-map n
--fcall-saved-x10 n
--fcall-saved-x11 n
--fcall-saved-x12 n
--fcall-saved-x13 n
--fcall-saved-x14 n
--fcall-saved-x15 n
--fcall-saved-x18 n
--fcall-saved-x8 n
--fcall-saved-x9 n
--fcf-protection n
--fcf-protection n
--fchar8_t s
--fclang-abi-compat s
--fcolor-diagnostics s
--fcomment-block-commands s
--fcommon s
--fcomplete-member-pointers s
--fconvergent-functions s
--fcoroutines-ts s
--fcoverage-mapping n
--fcs-profile-generate n
--fcs-profile-generate n
--fcuda-approx-transcendentals n
--fcuda-flush-denormals-to-zero s
--fcuda-short-ptr n
--fcxx-exceptions s
--fdata-sections s
--fdebug-compilation-dir s
--fdebug-default-version s
--fdebug-info-for-profiling s
--fdebug-macro s
--fdebug-prefix-map s
--fdebug-ranges-base-address s
--fdebug-types-section s
--fdeclspec s
--fdelayed-template-parsing s
--fdelete-null-pointer-checks s
--fdiagnostics-absolute-paths s
--fdiagnostics-hotness-threshold n
--fdiagnostics-parseable-fixits s
--fdiagnostics-print-source-range-info s
--fdiagnostics-show-hotness n
--fdiagnostics-show-note-include-stack s
--fdiagnostics-show-option s
--fdiagnostics-show-template-tree s
--fdigraphs s
--fdiscard-value-names s
--fdollars-in-identifiers s
--fdouble-square-bracket-attributes s
--fdwarf-exceptions n
--feliminate-unused-debug-types s
--fembed-bitcode-marker s
--fembed-bitcode s
--fembed-bitcode s
--femit-all-decls s
--femulated-tls s
--fenable-matrix s
--fexceptions s
--fexperimental-new-constant-interpreter s
--fexperimental-new-pass-manager s
--fexperimental-relative-c++-abi-vtables s
--fexperimental-strict-floating-point s
--ffast-math s
--ffile-prefix-map s
--ffine-grained-bitfield-accesses s
--ffixed-form s
--ffixed-point s
--ffixed-r19 n
--ffixed-r9 n
--ffixed-x10 n
--ffixed-x11 n
--ffixed-x12 n
--ffixed-x13 n
--ffixed-x14 n
--ffixed-x15 n
--ffixed-x16 n
--ffixed-x17 n
--ffixed-x18 n
--ffixed-x19 n
--ffixed-x1 n
--ffixed-x20 n
--ffixed-x21 n
--ffixed-x22 n
--ffixed-x23 n
--ffixed-x24 n
--ffixed-x25 n
--ffixed-x26 n
--ffixed-x27 n
--ffixed-x28 n
--ffixed-x29 n
--ffixed-x2 n
--ffixed-x30 n
--ffixed-x31 n
--ffixed-x3 n
--ffixed-x4 n
--ffixed-x5 n
--ffixed-x6 n
--ffixed-x7 n
--ffixed-x8 n
--ffixed-x9 n
--fforce-dwarf-frame s
--fforce-emit-vtables s
--fforce-enable-int128 s
--ffp-contract s
--ffp-exception-behavior s
--ffp-model s
--ffree-form s
--ffreestanding s
--ffunc-args-alias s
--ffunction-sections s
--fglobal-isel s
--fgnu-keywords s
--fgnu-runtime n
--fgnu89-inline n
--fgnuc-version s
--fgpu-allow-device-init s
--fgpu-rdc s
--fhip-new-launch-api s
--fignore-exceptions s
--fimplicit-module-maps n
--finline-functions s
--finline-hint-functions s
--finstrument-function-entry-bare n
--finstrument-functions-after-inlining n
--finstrument-functions n
--fintegrated-as s
--fintegrated-cc1 s
--fjump-tables s
--fkeep-static-consts s
--flax-vector-conversions s
--flto-jobs n
--flto n
--flto n
--fmacro-prefix-map s
--fmath-errno s
--fmax-tokens s
--fmax-type-align s
--fmemory-profile s
--fmerge-all-constants s
--fmessage-length s
--fmodule-file n
--fmodule-map-file n
--fmodule-name n
--fmodules-cache-path n
--fmodules-decluse n
--fmodules-disable-diagnostic-validation n
--fmodules-ignore-macro n
--fmodules-prune-after n
--fmodules-prune-interval n
--fmodules-search-all n
--fmodules-strict-decluse n
--fmodules-ts n
--fmodules-user-build-path n
--fmodules-validate-input-files-content s
--fmodules-validate-once-per-build-session n
--fmodules-validate-system-headers s
--fmodules n
--fms-compatibility-version s
--fms-compatibility s
--fms-extensions s
--fmsc-version s
--fnew-alignment s
--fno-addrsig s
--fno-allow-fortran-gnu-ext s
--fno-assume-sane-operator-new s
--fno-autolink s
--fno-backslash s
--fno-builtin- s
--fno-builtin s
--fno-c++-static-destructors s
--fno-char8_t s
--fno-color-diagnostics s
--fno-common s
--fno-complete-member-pointers s
--fno-constant-cfstrings s
--fno-coverage-mapping s
--fno-crash-diagnostics s
--fno-cuda-approx-transcendentals n
--fno-debug-macro s
--fno-declspec n
--fno-delayed-template-parsing s
--fno-delete-null-pointer-checks s
--fno-diagnostics-fixit-info s
--fno-digraphs s
--fno-discard-value-names s
--fno-dollars-in-identifiers s
--fno-double-square-bracket-attributes s
--fno-elide-constructors s
--fno-elide-type s
--fno-eliminate-unused-debug-types s
--fno-exceptions s
--fno-experimental-new-pass-manager s
--fno-experimental-relative-c++-abi-vtables s
--fno-fine-grained-bitfield-accesses s
--fno-fixed-form s
--fno-fixed-point s
--fno-force-enable-int128 s
--fno-fortran-main s
--fno-free-form s
--fno-func-args-alias s
--fno-global-isel s
--fno-gnu-inline-asm s
--fno-gpu-allow-device-init s
--fno-hip-new-launch-api s
--fno-integrated-as s
--fno-integrated-cc1 s
--fno-jump-tables s
--fno-keep-static-consts s
--fno-lto s
--fno-memory-profile s
--fno-merge-all-constants s
--fno-no-access-control s
--fno-objc-infer-related-result-type s
--fno-operator-names s
--fno-pch-codegen s
--fno-pch-debuginfo s
--fno-plt s
--fno-preserve-as-comments s
--fno-profile-generate s
--fno-profile-instr-generate s
--fno-profile-instr-use s
--fno-register-global-dtors-with-atexit s
--fno-rtlib-add-rpath s
--fno-rtti-data s
--fno-rtti s
--fno-sanitize-address-poison-custom-array-cookie h
--fno-sanitize-address-use-after-scope h
--fno-sanitize-address-use-odr-indicator h
--fno-sanitize-blacklist h
--fno-sanitize-cfi-canonical-jump-tables h
--fno-sanitize-cfi-cross-dso h
--fno-sanitize-coverage h
--fno-sanitize-memory-track-origins h
--fno-sanitize-memory-use-after-dtor h
--fno-sanitize-recover h
--fno-sanitize-stats h
--fno-sanitize-thread-atomics h
--fno-sanitize-thread-func-entry-exit h
--fno-sanitize-thread-memory-access h
--fno-sanitize-trap h
--fno-sanitize-trap h
--fno-short-wchar s
--fno-show-column s
--fno-show-source-location s
--fno-signed-char s
--fno-signed-zeros s
--fno-spell-checking s
--fno-split-machine-functions s
--fno-stack-clash-protection s
--fno-stack-protector s
--fno-standalone-debug s
--fno-strict-float-cast-overflow s
--fno-strict-return s
--fno-sycl n
--fno-temp-file s
--fno-threadsafe-statics s
--fno-trigraphs s
--fno-unique-section-names s
--fno-unroll-loops s
--fno-use-cxa-atexit s
--fno-use-flang-math-libs s
--fno-use-init-array s
--fno-visibility-inlines-hidden-static-local-var s
--fno-xray-function-index n
--fno-zero-initialized-in-bss s
--fobjc-arc-exceptions n
--fobjc-arc n
--fobjc-exceptions n
--fobjc-runtime n
--fobjc-weak n
--fopenmp-simd n
--fopenmp-targets n
--fopenmp n
--foptimization-record-file s
--foptimization-record-passes s
--forder-file-instrumentation s
--fpack-struct n
--fpascal-strings s
--fpass-plugin s
--fpatchable-function-entry s
--fpcc-struct-return n
--fpch-codegen s
--fpch-debuginfo s
--fpch-instantiate-templates s
--fpch-validate-input-files-content s
--fplugin s
--fprebuilt-module-path n
--fprofile-exclude-files n
--fprofile-filter-files n
--fprofile-generate n
--fprofile-generate n
--fprofile-instr-generate n
--fprofile-instr-generate n
--fprofile-instr-use n
--fprofile-remapping-file n
--fprofile-sample-accurate n
--fprofile-sample-use n
--fprofile-use n
--freciprocal-math s
--freg-struct-return n
--fregister-global-dtors-with-atexit s
--frelaxed-template-template-args s
--freroll-loops s
--fropi n
--frtlib-add-rpath s
--frwpi n
--fsanitize-address-field-padding h
--fsanitize-address-globals-dead-stripping h
--fsanitize-address-poison-custom-array-cookie h
--fsanitize-address-use-after-scope h
--fsanitize-address-use-odr-indicator h
--fsanitize-blacklist h
--fsanitize-cfi-canonical-jump-tables h
--fsanitize-cfi-cross-dso h
--fsanitize-cfi-icall-generalize-pointers h
--fsanitize-coverage-allowlist h
--fsanitize-coverage-blacklist h
--fsanitize-coverage-blocklist h
--fsanitize-coverage-whitelist h
--fsanitize-coverage h
--fsanitize-hwaddress-abi h
--fsanitize-memory-track-origins h
--fsanitize-memory-track-origins h
--fsanitize-memory-use-after-dtor h
--fsanitize-recover h
--fsanitize-stats h
--fsanitize-system-blacklist h
--fsanitize-thread-atomics h
--fsanitize-thread-func-entry-exit h
--fsanitize-thread-memory-access h
--fsanitize-trap h
--fsanitize-trap h
--fsanitize-undefined-strip-path-components h
--fsanitize h
--fsave-optimization-record s
--fsave-optimization-record s
--fseh-exceptions s
--fshort-enums s
--fshort-wchar n
--fshow-overloads s
--fsigned-char s
--fsized-deallocation s
--fsjlj-exceptions s
--fslp-vectorize s
--fsplit-dwarf-inlining n
--fsplit-lto-unit n
--fsplit-machine-functions s
--fstack-clash-protection s
--fstack-protector-all n
--fstack-protector-strong n
--fstack-protector n
--fstack-size-section s
--fstandalone-debug s
--fstrict-enums s
--fstrict-float-cast-overflow s
--fstrict-vtable-pointers s
--fsycl n
--fsystem-module u
--fthin-link-bitcode s
--fthinlto-index n
--ftime-trace-granularity s
--ftime-trace s
--ftrap-function n
--ftrapv-handler n
--ftrapv n
--ftrigraphs s
--ftrivial-auto-var-init-stop-after s
--ftrivial-auto-var-init s
--funique-basic-block-section-names s
--funique-internal-linkage-names s
--funroll-loops s
--fuse-flang-math-libs s
--fuse-line-directives s
--fvalidate-ast-input-files-content s
--fveclib n
--fvectorize n
--fverbose-asm s
--fvirtual-function-elimination s
--fvisibility-global-new-delete-hidden s
--fvisibility-inlines-hidden-static-local-var s
--fvisibility-inlines-hidden s
--fvisibility-ms-compat s
--fvisibility s
--fwasm-exceptions n
--fwhole-program-vtables n
--fwrapv s
--fwritable-strings s
--fxray-always-emit-customevents n
--fxray-always-emit-typedevents n
--fxray-always-instrument n
--fxray-attr-list n
--fxray-ignore-loops n
--fxray-instruction-threshold n
--fxray-instrumentation-bundle n
--fxray-instrument n
--fxray-link-deps n
--fxray-modes n
--fxray-never-instrument n
--fzvector s
--F n
---gcc-toolchain s
--gcodeview-ghash s
--gcodeview s
--gdwarf-2 s
--gdwarf-3 s
--gdwarf-4 s
--gdwarf-5 s
--gdwarf s
--gembed-source s
--gline-directives-only s
--gline-tables-only s
--gmodules s
--gno-embed-source s
--gno-inline-line-tables s
---gpu-max-threads-per-block s
--gsplit-dwarf s
--gz s
--gz s
--G n
--g s
---help-hidden s
--help s
---hip-device-lib s
---hip-link s
---hip-version s
--H s
--I- s
--ibuiltininc s
--idirafter s
--iframeworkwithsysroot n
--iframework n
--imacros s
--include-pch s
--include s
--index-header-map s
--iprefix s
--iquote s
--isysroot s
--isystem-after s
--isystem s
--ivfsoverlay s
--iwithprefixbefore s
--iwithprefix s
--iwithsysroot s
--I s
---libomptarget-nvptx-path n
--L s
--mabicalls n
--maix-struct-return n
--malign-branch-boundary s
--malign-branch s
--malign-double s
--Mallocatable n
--mbackchain n
--mbranch-protection n
--mbranches-within-32B-boundaries s
--mcmodel n
--mcmodel n
--mcmse n
--mcode-object-v3 s
--mcode-object-version s
--mcrc n
--mcumode s
--mdouble s
--MD s
--meabi s
--membedded-data n
--menable-experimental-extensions n
--mexec-model n
--mexecute-only n
--mextern-sdata n
--mfentry n
--mfix-cortex-a53-835769 n
--mfp32 n
--mfp64 n
--MF s
--mgeneral-regs-only n
--mglobal-merge s
--mgpopt n
--MG s
--mharden-sls n
--mhvx-length n
--mhvx n
--mhvx n
--miamcu n
---migrate n
--mincremental-linker-compatible s
--mindirect-jump n
--Minform s
--mios-version-min n
--MJ n
--mllvm s
--mlocal-sdata n
--mlong-calls s
--mlong-double-128 h
--mlong-double-64 s
--mlong-double-80 h
--mlvi-cfi h
--mlvi-hardening h
--mmacosx-version-min n
--mmadd4 s
--mmark-bti-property n
--MMD s
--mmemops s
--mms-bitfields n
--mmsa n
--mmt n
--MM s
--mno-abicalls n
--mno-crc n
--mno-embedded-data n
--mno-execute-only n
--mno-extern-sdata n
--mno-fix-cortex-a53-835769 n
--mno-global-merge s
--mno-gpopt n
--mno-hvx n
--mno-implicit-float s
--mno-incremental-linker-compatible s
--mno-local-sdata n
--mno-long-calls s
--mno-lvi-cfi h
--mno-lvi-hardening h
--mno-madd4 s
--mno-memops s
--mno-movt s
--mno-ms-bitfields s
--mno-msa n
--mno-mt n
--mno-neg-immediates s
--mno-nvj s
--mno-nvs s
--mno-outline n
--mno-packets s
--mno-relax s
--mno-restrict-it n
--mno-save-restore n
--mno-seses n
--mno-stack-arg-probe s
--mno-tls-direct-seg-refs s
--mno-unaligned-access n
--mno-wavefrontsize64 s
--mnocrc n
--mnop-mcount s
--mnvj s
--mnvs s
--module-dependency-dir n
--module-file-info n
--momit-leaf-frame-pointer s
--moutline n
--mpacked-stack n
--mpackets s
--mpad-max-prefix-size s
--mpie-copy-relocations s
--mprefer-vector-width n
--MP s
--mqdsp6-compat n
--MQ s
--mrecord-mcount s
--mrelax-all s
--mrelax s
--mrestrict-it n
--mrtd n
--msave-restore n
--mseses n
--msign-return-address n
--msmall-data-limit s
--msoft-float s
--msram-ecc s
--mstack-alignment n
--mstack-arg-probe n
--mstack-probe-size n
--mstackrealign n
--msve-vector-bits n
--msvr4-struct-return n
--mthread-model s
--mtls-direct-seg-refs s
--mtls-size n
--mtp n
--mtune h
--MT n
--munaligned-access n
--MV s
--mwavefrontsize64 s
--mxnack s
--M s
---no-cuda-include-ptx s
---no-cuda-version-check s
--no-flang-libs s
---no-offload-arch s
---no-system-header-prefix s
--nobuiltininc s
--nogpuinc s
--nogpulib s
--nostdinc++ n
--ObjC++ n
--objcmt-atomic-property n
--objcmt-migrate-all n
--objcmt-migrate-annotation n
--objcmt-migrate-designated-init n
--objcmt-migrate-instancetype n
--objcmt-migrate-literals n
--objcmt-migrate-ns-macros n
--objcmt-migrate-property-dot-syntax n
--objcmt-migrate-property n
--objcmt-migrate-protocol-conformance n
--objcmt-migrate-readonly-property n
--objcmt-migrate-readwrite-property n
--objcmt-migrate-subscripting n
--objcmt-ns-nonatomic-iosonly n
--objcmt-returns-innerpointer-property n
--objcmt-whitelist-dir-path n
--ObjC n
---offload-arch s
--o s
--parallel-jobs s
--pg s
--pipe s
---precompile s
--print-effective-triple s
--print-file-name s
--print-ivar-layout n
--print-libgcc-file-name s
--print-prog-name s
--print-resource-dir s
--print-search-dirs s
--print-supported-cpus s
--print-target-triple s
--print-targets s
--pthread s
---ptxas-path n
--P s
--Qn s
--Qunused-arguments s
--Qy s
--relocatable-pch s
--rewrite-legacy-objc n
--rewrite-objc n
---rocm-device-lib-path s
---rocm-path s
--Rpass-analysis s
--Rpass-missed s
--Rpass s
--rtlib n
--R n
--save-stats s
--save-stats s
--save-temps s
--save-temps s
--serialize-diagnostics s
--shared-libsan n
--static-flang-libs s
--static-libsan n
--static-openmp s
--std s
--stdlib++-isystem s
--stdlib s
--sycl-std n
---system-header-prefix s
--S s
---target s
--Tbss s
--Tdata s
--time s
--traditional-cpp n
--trigraphs s
--Ttext s
--T n
--undef s
--unwindlib s
--U s
---verify-debug-info s
--verify-pch n
---version s
--v s
--Wa, s
--Wdeprecated s
--Wl, s
--working-directory s
--Wp, s
--W s
--w s
--Xanalyzer s
--Xarch_device s
--Xarch_host s
--Xassembler s
--Xclang s
--Xcuda-fatbinary s
--Xcuda-ptxas s
--Xlinker s
--Xopenmp-target s
--Xopenmp-target s
--Xpreprocessor s
--x s
--z s
diff --git a/projects/hip/docs/markdown/cuComplex_API_supported_by_HIP.md b/projects/hip/docs/markdown/cuComplex_API_supported_by_HIP.md
deleted file mode 100644
index 621973ba61..0000000000
--- a/projects/hip/docs/markdown/cuComplex_API_supported_by_HIP.md
+++ /dev/null
@@ -1,37 +0,0 @@
-# cuComplex API supported by HIP
-
-## **1. cuComplex Data types**
-
-| **type**     |   **CUDA**                                                    |   **HIP**                                                  |**HIP value** (if differs) |
-|-------------:|---------------------------------------------------------------|------------------------------------------------------------|---------------------------|
-| float2       |***`cuFloatComplex`***                                         |***`hipFloatComplex`***                                     | struct                    |
-| double2      |***`cuDoubleComplex`***                                        |***`hipDoubleComplex`***                                    | struct                    |
-| float2       |***`cuComplex`***                                              |***`hipComplex`***                                          | struct                    |
-
-## **2. cuComplex API functions**
-
-|   **CUDA**                                                |   **HIP**                                       |
-|-----------------------------------------------------------|-------------------------------------------------|
-|`cuCrealf`                                                 |`hipCrealf`                                      |
-|`cuCimagf`                                                 |`hipCimagf`                                      |
-|`make_cuFloatComplex`                                      |`make_hipFloatComplex`                           |
-|`cuConjf`                                                  |`hipConjf`                                       |
-|`cuCaddf`                                                  |`hipCaddf`                                       |
-|`cuCsubf`                                                  |`hipCsubf`                                       |
-|`cuCmulf`                                                  |`hipCmulf`                                       |
-|`cuCdivf`                                                  |`hipCdivf`                                       |
-|`cuCabsf`                                                  |`hipCabsf`                                       |
-|`cuCreal`                                                  |`hipCreal`                                       |
-|`cuCimag`                                                  |`hipCimag`                                       |
-|`make_cuDoubleComplex`                                     |`make_hipDoubleComplex`                          |
-|`cuConj`                                                   |`hipConj`                                        |
-|`cuCadd`                                                   |`hipCadd`                                        |
-|`cuCsub`                                                   |`hipCsub`                                        |
-|`cuCmul`                                                   |`hipCmul`                                        |
-|`cuCdiv`                                                   |`hipCdiv`                                        |
-|`cuCabs`                                                   |`hipCabs`                                        |
-|`make_cuComplex`                                           |`make_hipComplex`                                |
-|`cuComplexFloatToDouble`                                   |`hipComplexFloatToDouble`                        |
-|`cuComplexDoubleToFloat`                                   |`hipComplexDoubleToFloat`                        |
-|`cuCfmaf`                                                  |`hipCfmaf`                                       |
-|`cuCfma`                                                   |`hipCfma`                                        |
diff --git a/projects/hip/docs/markdown/hip_bugs.md b/projects/hip/docs/markdown/hip_bugs.md
deleted file mode 100644
index 6f872ff89e..0000000000
--- a/projects/hip/docs/markdown/hip_bugs.md
+++ /dev/null
@@ -1,172 +0,0 @@
-# HIP Bugs
-
-<!-- toc -->
-- [HIP is more restrictive in enforcing restrictions](#hip-is-more-restrictive-in-enforcing-restrictions)
-
-<!-- tocstop -->
-
-
-
-### HIP is more restrictive in enforcing restrictions
-The language specification for HIP and CUDA forbid calling a
-`__device__` function in a `__host__` context. In practice, you may observe
-differences in the strictness of this restriction, with HIP exhibiting a tighter
-adherence to the specification and thus less tolerant of infringing code. The
-solution is to ensure that all functions which are called in a
-`__device__` context are correctly annotated to reflect it.
-
-The following is an example of codes using the specification,
-```
-#include <hip/hip_runtime.h>
-#include <type_traits>
-#include <random>
-#include "test_common.h"
-
-static std::random_device dev;
-static std::mt19937 rng(dev());
-
-template <typename T, typename M>
-__host__ __device__ inline constexpr int count() {
-    return sizeof(T) / sizeof(M);
-}
-
-inline float getRandomFloat(float min = 10, float max = 100) {
-    std::uniform_real_distribution<float> gen(min, max);
-    return gen(rng);
-}
-
-template <typename T, typename B>
-void fillMatrix(T* a, int size) {
-    for (int i = 0; i < size; i++) {
-        T t;
-        t.x = getRandomFloat();
-        if constexpr (count<T, B>() >= 2) t.y = getRandomFloat();
-        if constexpr (count<T, B>() >= 3) t.z = getRandomFloat();
-        if constexpr (count<T, B>() >= 4) t.w = getRandomFloat();
-
-        a[i] = t;
-    }
-}
-
-// Test operations
-template <typename T, typename B>
-__host__ __device__ void testOperations(T& a, T& b) {
-    a.x += b.x;
-    a.x++;
-    b.x++;
-    if constexpr (count<T, B>() >= 2) {
-        a.y = b.x;
-        a.x = b.y;
-    }
-    if constexpr (count<T, B>() >= 3) {
-        if (a.x > 0) b.x /= a.x;
-        a.x *= b.z;
-        a.y--;
-    }
-    if constexpr (count<T, B>() >= 4) {
-        b.w = a.x;
-        a.w += (-b.y);
-    }
-}
-
-template <typename T, typename B>
-__global__ void testOperationsGPU(T* d_a, T* d_b, int size) {
-    int id = threadIdx.x;
-    if (id > size) return;
-    T &a = d_a[id];
-    T &b = d_b[id];
-
-    testOperations<T, B>(a, b);
-}
-
-
-template <typename T>
-void dcopy(T* a, T* b, int size) {
-    for (int i = 0; i < size; i++) {
-        a[i] = b[i];
-    }
-}
-
-template <typename T>
-bool isEqual(T* a, T* b, int size) {
-    for (int i = 0; i < size; i++) {
-        if (a[i] != b[i]) {
-            return false;
-        }
-    }
-    return true;
-}
-
-// Main function that tests type
-// T = what you want to test
-// D = pack of 1 i.e. float1 int1
-template <typename T, typename D>
-void testType(int msize) {
-    T *fa, *fb, *fc, *h_fa, *h_fb;
-    fa = new T[msize];
-    fb = new T[msize];
-    fc = new T[msize];
-    h_fa = new T[msize];
-    h_fb = new T[msize];
-
-    T *d_fa, *d_fb;
-
-    constexpr int c = count<T, D>();
-
-    if (c <= 0 || c >= 5) {
-        failed("Invalid Size\n");
-    }
-
-    fillMatrix<T, D>(fa, msize);
-    dcopy(fb, fa, msize);
-    dcopy(h_fa, fa, msize);
-    dcopy(h_fb, fa, msize);
-    for (int i = 0; i < msize; i++) testOperations<T, D>(h_fa[i], h_fb[i]);
-
-    hipMalloc(&d_fa, sizeof(T) * msize);
-    hipMalloc(&d_fb, sizeof(T) * msize);
-
-    hipMemcpy(d_fa, fa, sizeof(T) * msize, hipMemcpyHostToDevice);
-    hipMemcpy(d_fb, fb, sizeof(T) * msize, hipMemcpyHostToDevice);
-
-    auto kernel = testOperationsGPU<T, D>;
-    hipLaunchKernelGGL(kernel, 1, msize, 0, 0, d_fa, d_fb, msize);
-
-    hipMemcpy(fc, d_fa, sizeof(T) * msize, hipMemcpyDeviceToHost);
-
-    bool pass = true;
-    if (!isEqual<T>(h_fa, fc, msize)) {
-        pass = false;
-    }
-
-    delete[] fa;
-    delete[] fb;
-    delete[] fc;
-    delete[] h_fa;
-    delete[] h_fb;
-    hipFree(d_fa);
-    hipFree(d_fb);
-
-    if (!pass) {
-        failed("Failed");
-    }
-}
-
-int main() {
-    const int msize = 100;
-    // double
-    testType<double1, double1>(msize);
-    testType<double2, double1>(msize);
-    testType<double3, double1>(msize);
-    testType<double4, double1>(msize);
-
-    // floats
-    testType<float1, float1>(msize);
-    testType<float2, float1>(msize);
-    testType<float3, float1>(msize);
-    testType<float4, float1>(msize);
-    ...
-    passed();
-}
-```
-For more details for the complete program, please refer to HIP test application at the link, https://github.com/ROCm-Developer-Tools/HIP/blob/main/tests/src/deviceLib/hip_floatnTM.cpp
diff --git a/projects/hip/docs/markdown/hip_porting_driver_api.md b/projects/hip/docs/markdown/hip_porting_driver_api.md
deleted file mode 100644
index 08df9aaa8a..0000000000
--- a/projects/hip/docs/markdown/hip_porting_driver_api.md
+++ /dev/null
@@ -1,287 +0,0 @@
-# Porting CUDA Driver API
-
-## Introduction to the CUDA Driver and Runtime APIs
-CUDA provides a separate CUDA Driver and Runtime APIs. The two APIs have significant overlap in functionality:
-- Both APIs support events, streams, memory management, memory copy, and error handling.
-- Both APIs deliver similar performance.
-- Driver APIs calls begin with the prefix `cu` while Runtime APIs begin with the prefix `cuda`. For example, the Driver API API contains `cuEventCreate` while the Runtime API contains `cudaEventCreate`, with similar functionality.
-- The Driver API defines a different but largely overlapping error code space than the Runtime API, and uses a different coding convention. For example, Driver API defines `CUDA_ERROR_INVALID_VALUE` while the Runtime API defines `cudaErrorInvalidValue`
-
-
-The Driver API offers two additional pieces of functionality not provided by the Runtime API: cuModule and cuCtx APIs.
-
-### cuModule API
-The Module section of the Driver API provides additional control over how and when accelerator code objects are loaded.
-For example, the driver API allows code objects to be loaded from files or memory pointers.
-Symbols for kernels or global data can be extracted from the loaded code objects.
-In contrast, the Runtime API automatically loads and (if necessary) compiles all of the kernels from an executable binary when run.
-In this mode, NVCC must be used to compile kernel code so the automatic loading can function correctly.
-
-Both Driver and Runtime APIs define a function for launching kernels (called `cuLaunchKernel` or `cudaLaunchKernel`.
-The kernel arguments and the execution configuration (grid dimensions, group dimensions, dynamic shared memory, and stream) are passed as arguments to the launch function.
-The Runtime additionally provides the `<<< >>>` syntax for launching kernels, which resembles a special function call and is easier to use than explicit launch API (in particular with respect to handling of kernel arguments).
-However, this syntax is not standard C++ and is available only when NVCC is used to compile the host code.
-
-The Module features are useful in an environment which generates the code objects directly, such as a new accelerator language front-end.
-Here, NVCC is not used. Instead, the environment may have a different kernel language or different compilation flow.
-Other environments have many kernels and do not want them to be all loaded automatically.
-The Module functions can be used to load the generated code objects and launch kernels.
-As we will see below, HIP defines a Module API which provides similar explicit control over code object management.
-
-### cuCtx API
-The Driver API defines "Context" and "Devices" as separate entities.
-Contexts contain a single device, and a device can theoretically have multiple contexts.
-Each context contains a set of streams and events specific to the context.
-Historically contexts also defined a unique address space for the GPU, though this may no longer be the case in Unified Memory platforms (since the CPU and all the devices in the same process share a single unified address space).
-The Context APIs also provide a mechanism to switch between devices, which allowed a single CPU thread to send commands to different GPUs.
-HIP as well as a recent versions of CUDA Runtime provide other mechanisms to accomplish this feat - for example using streams or `cudaSetDevice`.
-
-The CUDA Runtime API unifies the Context API with the Device API. This simplifies the APIs and has little loss of functionality since each Context can contain a single device, and the benefits of multiple contexts has been replaced with other interfaces.
-HIP provides a context API to facilitate easy porting from existing Driver codes.
-In HIP, the Ctx functions largely provide an alternate syntax for changing the active device.
-
-Most new applications will prefer to use `hipSetDevice` or the stream APIs , therefore HIP has marked hipCtx APIs as **deprecated**. Support for these APIs may not be available in future releases. For more details on deprecated APIs please refer [HIP deprecated APIs](https://github.com/ROCm-Developer-Tools/HIP/tree/master/docs/markdown/hip_deprecated_api_list.md).
-
-## HIP Module and Ctx APIs
-
-Rather than present two separate APIs, HIP extends the HIP API with new APIs for Modules and Ctx control.
-
-### hipModule API
-
-Like the CUDA Driver API, the Module API provides additional control over how code is loaded, including options to load code from files or from in-memory pointers.
-NVCC and HIP-Clang target different architectures and use different code object formats: NVCC is `cubin` or `ptx` files, while the HIP-Clang path is the `hsaco` format.
-The external compilers which generate these code objects are responsible for generating and loading the correct code object for each platform.
-Notably, there is not a fat binary format that can contain code for both NVCC and HIP-Clang platforms. The following table summarizes the formats used on each platform:
-
-| Format        | APIs                             | NVCC               | HIP-CLANG    |
-| ---           | ---                              | ---                | ---          |
-| Code Object   | hipModuleLoad, hipModuleLoadData | .cubin or PTX text | .hsaco       |
-| Fat Binary    | hipModuleLoadFatBin              | .fatbin            | .hip_fatbin  |
-
-`hipcc` uses HIP-Clang or NVCC to compile host codes. Both of these may embed code objects into the final executable, and these code objects will be automatically loaded when the application starts.
-The hipModule API can be used to load additional code objects, and in this way provides an extended capability to the automatically loaded code objects.
-HIP-Clang allows both of these capabilities to be used together, if desired. Of course it is possible to create a program with no kernels and thus no automatic loading.
-
-
-### hipCtx API
-HIP provides a `Ctx` API as a thin layer over the existing Device functions. This Ctx API can be used to set the current context, or to query properties of the device associated with the context.
-The current context is implicitly used by other APIs such as `hipStreamCreate`.
-
-### hipify translation of CUDA Driver API
-The HIPIFY tools convert CUDA Driver APIs for streams, events, modules, devices, memory management, context, profiler to the equivalent HIP driver calls. For example, `cuEventCreate` will be translated to `hipEventCreate`.
-HIPIFY tools also convert error codes from the Driver namespace and coding convention to the equivalent HIP error code. Thus, HIP unifies the APIs for these common functions.
-
-The memory copy API requires additional explanation. The CUDA driver includes the memory direction in the name of the API (ie `cuMemcpyH2D`) while the CUDA driver API provides a single memory copy API with a parameter that specifies the direction and additionally supports a "default" direction where the runtime determines the direction automatically.
-HIP provides APIs with both styles: for example, `hipMemcpyH2D` as well as `hipMemcpy`.
-The first flavor may be faster in some cases since they avoid host overhead to detect the different memory directions.
-
-HIP defines a single error space, and uses camel-case for all errors (i.e. `hipErrorInvalidValue`).
-
-#### Address Spaces
-HIP-Clang defines a process-wide address space where the CPU and all devices allocate addresses from a single unified pool.
-Thus addresses may be shared between contexts, and unlike the original CUDA definition a new context does not create a new address space for the device.
-
-#### Using hipModuleLaunchKernel
-`hipModuleLaunchKernel` is `cuLaunchKernel` in HIP world. It takes the same arguments as `cuLaunchKernel`.
-
-#### Additional Information
-- HIP-Clang creates a primary context when the HIP API is called. So in a pure driver API code, HIP-Clang will create a primary context while HIP/NVCC will have empty context stack.
-HIP-Clang will push primary context to context stack when it is empty. This can have subtle differences on applications which mix the runtime and driver APIs.
-
-### hip-clang Implementation Notes
-#### .hip_fatbin
-hip-clang links device code from different translation units together. For each device target, a code object is generated. Code objects for different device targets are bundled by clang-offload-bundler as one fatbinary, which is embeded as a global symbol `__hip_fatbin` in the .hip_fatbin section of the ELF file of the executable or shared object.
-
-#### Initialization and Termination Functions
-hip-clang generates initializatiion and termination functions for each translation unit for host code compilation. The initialization functions call `__hipRegisterFatBinary` to register the fatbinary embeded in the ELF file. They also call `__hipRegisterFunction` and `__hipRegisterVar` to register kernel functions and device side global variables. The termination functions call `__hipUnregisterFatBinary`.
-hip-clang emits a global variable `__hip_gpubin_handle` of void** type with linkonce linkage and inital value 0 for each host translation unit. Each initialization function checks `__hip_gpubin_handle` and register the fatbinary only if `__hip_gpubin_handle` is 0 and saves the return value of `__hip_gpubin_handle` to `__hip_gpubin_handle`. This is to guarantee that the fatbinary is only registered once. Similar check is done in the termination functions.
-
-#### Kernel Launching
-hip-clang supports kernel launching by CUDA `<<<>>>` syntax, hipLaunchKernelGGL. The latter one is macro which expand to CUDA `<<<>>>` syntax.
-
-When the executable or shared library is loaded by the dynamic linker, the initilization functions are called. In the initialization functions, when `__hipRegisterFatBinary` is called, the code objects containing all kernels are loaded; when `__hipRegisterFunction` is called, the stub functions are associated with the corresponding kernels in code objects.
-
-hip-clang implements two sets of kernel launching APIs.
-
-By default, in the host code, for the `<<<>>>` statement, hip-clang first emits call of hipConfigureCall to set up the threads and grids, then emits call of the stub function with the given arguments. In the stub function, hipSetupArgument is called for each kernel argument, then hipLaunchByPtr is called with a function pointer to the stub function. In hipLaunchByPtr, the real kernel associated with the stub function is launched.
-
-### NVCC Implementation Notes
-
-#### Interoperation between HIP and CUDA Driver
-CUDA applications may want to mix CUDA driver code with HIP code (see example below). This table shows the type equivalence to enable this interaction.
-
-|**HIP Type**   |**CU Driver Type**|**CUDA Runtime Type**|
-| ----          | ----             | ----                |
-| hipModule_t   |  CUmodule        |                     |
-| hipFunction_t |  CUfunction      |                     |
-| hipCtx_t      |  CUcontext       |                     |
-| hipDevice_t   |  CUdevice        |                     |
-| hipStream_t   |  CUstream        | cudaStream_t        |
-| hipEvent_t    |  CUevent         | cudaEvent_t         |
-| hipArray      |  CUarray         | cudaArray           |
-
-#### Compilation Options
-The `hipModule_t` interface does not support `cuModuleLoadDataEx` function, which is used to control PTX compilation options.
-HIP-Clang does not use PTX and does not support these compilation options.
-In fact, HIP-Clang code objects always contain fully compiled ISA and do not require additional compilation as a part of the load step.
-The corresponding HIP function `hipModuleLoadDataEx` behaves as `hipModuleLoadData` on HIP-Clang path (compilation options are not used) and as `cuModuleLoadDataEx` on NVCC path.
-For example (CUDA):
-```
-CUmodule module;
-void *imagePtr = ...;  // Somehow populate data pointer with code object
-
-const int numOptions = 1;
-CUJit_option options[numOptions];
-void * optionValues[numOptions];
-
-options[0] = CU_JIT_MAX_REGISTERS;
-unsigned maxRegs = 15;
-optionValues[0] = (void*)(&maxRegs);
-
-cuModuleLoadDataEx(module, imagePtr, numOptions, options, optionValues);
-
-CUfunction k;
-cuModuleGetFunction(&k, module, "myKernel");
-```
-HIP:
-```
-hipModule_t module;
-void *imagePtr = ...;  // Somehow populate data pointer with code object
-
-const int numOptions = 1;
-hipJitOption options[numOptions];
-void * optionValues[numOptions];
-
-options[0] = hipJitOptionMaxRegisters;
-unsigned maxRegs = 15;
-optionValues[0] = (void*)(&maxRegs);
-
-// hipModuleLoadData(module, imagePtr) will be called on HIP-Clang path, JIT options will not be used, and
-// cupModuleLoadDataEx(module, imagePtr, numOptions, options, optionValues) will be called on NVCC path
-hipModuleLoadDataEx(module, imagePtr, numOptions, options, optionValues);
-
-hipFunction_t k;
-hipModuleGetFunction(&k, module, "myKernel");
-```
-
-The below sample shows how to use `hipModuleGetFunction`.
-
-```
-#include<hip_runtime.h>
-#include<hip_runtime_api.h>
-#include<iostream>
-#include<fstream>
-#include<vector>
-
-#define LEN 64
-#define SIZE LEN<<2
-
-#ifdef __HIP_PLATFORM_AMD__
-#define fileName "vcpy_isa.co"
-#endif
-
-#ifdef __HIP_PLATFORM_NVIDIA__
-#define fileName "vcpy_isa.ptx"
-#endif
-
-#define kernel_name "hello_world"
-
-int main(){
-    float *A, *B;
-    hipDeviceptr_t Ad, Bd;
-    A = new float[LEN];
-    B = new float[LEN];
-
-    for(uint32_t i=0;i<LEN;i++){
-        A[i] = i*1.0f;
-        B[i] = 0.0f;
-        std::cout<<A[i] << " "<<B[i]<<std::endl;
-    }
-
-
-#ifdef __HIP_PLATFORM_NVIDIA__
-          hipInit(0);
-          hipDevice_t device;
-          hipCtx_t context;
-          hipDeviceGet(&device, 0);
-          hipCtxCreate(&context, 0, device);
-#endif
-
-    hipMalloc((void**)&Ad, SIZE);
-    hipMalloc((void**)&Bd, SIZE);
-
-    hipMemcpyHtoD(Ad, A, SIZE);
-    hipMemcpyHtoD(Bd, B, SIZE);
-    hipModule_t Module;
-    hipFunction_t Function;
-    hipModuleLoad(&Module, fileName);
-    hipModuleGetFunction(&Function, Module, kernel_name);
-
-    std::vector<void*>argBuffer(2);
-    memcpy(&argBuffer[0], &Ad, sizeof(void*));
-    memcpy(&argBuffer[1], &Bd, sizeof(void*));
-
-    size_t size = argBuffer.size()*sizeof(void*);
-
-    void *config[] = {
-      HIP_LAUNCH_PARAM_BUFFER_POINTER, &argBuffer[0],
-      HIP_LAUNCH_PARAM_BUFFER_SIZE, &size,
-      HIP_LAUNCH_PARAM_END
-    };
-
-    hipModuleLaunchKernel(Function, 1, 1, 1, LEN, 1, 1, 0, 0, NULL, (void**)&config);
-
-    hipMemcpyDtoH(B, Bd, SIZE);
-    for(uint32_t i=0;i<LEN;i++){
-        std::cout<<A[i]<<" - "<<B[i]<<std::endl;
-    }
-
-#ifdef __HIP_PLATFORM_NVIDIA__
-          hipCtxDetach(context);
-#endif
-
-    return 0;
-}
-```
-
-## HIP Module and Texture Driver API
-
-HIP supports texture driver APIs however texture reference should be declared in host scope. Following code explains the use of texture reference for __HIP_PLATFORM_AMD__ platform.
-
-```
-// Code to generate code object
-
-#include "hip/hip_runtime.h"
-extern texture<float, 2, hipReadModeElementType> tex;
-
-__global__ void tex2dKernel(hipLaunchParm lp, float* outputData,
-                             int width,
-                             int height)
-{
-    int x = blockIdx.x*blockDim.x + threadIdx.x;
-    int y = blockIdx.y*blockDim.y + threadIdx.y;
-    outputData[y*width + x] = tex2D(tex, x, y);
-}
-
-```
-```
-// Host code:
-
-texture<float, 2, hipReadModeElementType> tex;
-
-void myFunc ()
-{
-    // ...
-
-    textureReference* texref;
-    hipModuleGetTexRef(&texref, Module1, "tex");
-    hipTexRefSetAddressMode(texref, 0, hipAddressModeWrap);
-    hipTexRefSetAddressMode(texref, 1, hipAddressModeWrap);
-    hipTexRefSetFilterMode(texref, hipFilterModePoint);
-    hipTexRefSetFlags(texref, 0);
-    hipTexRefSetFormat(texref, HIP_AD_FORMAT_FLOAT, 1);
-    hipTexRefSetArray(texref, array, HIP_TRSA_OVERRIDE_FORMAT);
-
-   // ...
-}
-```
diff --git a/projects/hip/docs/markdown/hip_porting_guide.md b/projects/hip/docs/markdown/hip_porting_guide.md
deleted file mode 100644
index fe1972e3b3..0000000000
--- a/projects/hip/docs/markdown/hip_porting_guide.md
+++ /dev/null
@@ -1,597 +0,0 @@
-# HIP Porting Guide
-In addition to providing a portable C++ programming environment for GPUs, HIP is designed to ease
-the porting of existing CUDA code into the HIP environment.  This section describes the available tools
-and provides practical suggestions on how to port CUDA code and work through common issues.
-
-## Table of Contents
-
-<!-- toc -->
-
-- [Porting a New CUDA Project](#porting-a-new-cuda-project)
-  * [General Tips](#general-tips)
-  * [Scanning existing CUDA code to scope the porting effort](#scanning-existing-cuda-code-to-scope-the-porting-effort)
-  * [Converting a project "in-place"](#converting-a-project-in-place)
-  * [CUDA to HIP Math Library Equivalents](#library-equivalents)
-- [Distinguishing Compiler Modes](#distinguishing-compiler-modes)
-  * [Identifying HIP Target Platform](#identifying-hip-target-platform)
-  * [Identifying the Compiler: hip-clang, or nvcc](#identifying-the-compiler-hip-clang-or-nvcc)
-  * [Identifying Current Compilation Pass: Host or Device](#identifying-current-compilation-pass-host-or-device)
-  * [Compiler Defines: Summary](#compiler-defines-summary)
-- [Identifying Architecture Features](#identifying-architecture-features)
-  * [HIP_ARCH Defines](#hip_arch-defines)
-  * [Device-Architecture Properties](#device-architecture-properties)
-  * [Table of Architecture Properties](#table-of-architecture-properties)
-- [Finding HIP](#finding-hip)
-- [Identifying HIP Runtime](#identifying-hip-runtime)
-- [hipLaunchKernelGGL](#hiplaunchkernelGGL)
-- [Compiler Options](#compiler-options)
-- [Linking Issues](#linking-issues)
-  * [Linking With hipcc](#linking-with-hipcc)
-  * [-lm Option](#-lm-option)
-- [Linking Code With Other Compilers](#linking-code-with-other-compilers)
-  * [libc++ and libstdc++](#libc-and-libstdc)
-  * [HIP Headers (hip_runtime.h, hip_runtime_api.h)](#hip-headers-hip_runtimeh-hip_runtime_apih)
-  * [Using a Standard C++ Compiler](#using-a-standard-c-compiler)
-    + [cuda.h](#cudah)
-  * [Choosing HIP File Extensions](#choosing-hip-file-extensions)
-- [Workarounds](#workarounds)
-  * [warpSize](#warpsize)
-  * [Kernel launch with group size > 256](#kernel-launch-with-group-size--256)
-- [memcpyToSymbol](#memcpytosymbol)
-- [threadfence_system](#threadfence_system)
-  * [Textures and Cache Control](#textures-and-cache-control)
-- [More Tips](#more-tips)
-  * [HIP Logging](#hip-logging)
-  * [Debugging hipcc](#debugging-hipcc)
-  * [What Does This Error Mean?](#what-does-this-error-mean)
-    + [/usr/include/c++/v1/memory:5172:15: error: call to implicitly deleted default constructor of 'std::__1::bad_weak_ptr' throw bad_weak_ptr();](#usrincludecv1memory517215-error-call-to-implicitly-deleted-default-constructor-of-std__1bad_weak_ptr-throw-bad_weak_ptr)
-  * [Editor Highlighting](#editor-highlighting)
-
-
-<!-- tocstop -->
-
-## Porting a New CUDA Project
-
-### General Tips
-- Starting the port on a CUDA machine is often the easiest approach, since you can incrementally port pieces of the code to HIP while leaving the rest in CUDA. (Recall that on CUDA machines HIP is just a thin layer over CUDA, so the two code types can interoperate on nvcc platforms.) Also, the HIP port can be compared with the original CUDA code for function and performance.
-- Once the CUDA code is ported to HIP and is running on the CUDA machine, compile the HIP code using the HIP compiler on an AMD machine.
-- HIP ports can replace CUDA versions: HIP can deliver the same performance as a native CUDA implementation, with the benefit of portability to both Nvidia and AMD architectures as well as a path to future C++ standard support. You can handle platform-specific features through conditional compilation or by adding them to the open-source HIP infrastructure.
-- Use **[hipconvertinplace-perl.sh](https://github.com/ROCm-Developer-Tools/HIPIFY/blob/master/bin/hipconvertinplace-perl.sh)** to hipify all code files in the CUDA source directory.
-
-### Scanning existing CUDA code to scope the porting effort
-The **[hipexamine-perl.sh](https://github.com/ROCm-Developer-Tools/HIPIFY/blob/master/bin/hipexamine-perl.sh)** tool will scan a source directory to determine which files contain CUDA code and how much of that code can be automatically hipified.
-```
-> cd examples/rodinia_3.0/cuda/kmeans
-> $HIP_DIR/bin/hipexamine-perl.sh.
-info: hipify ./kmeans.h =====>
-info: hipify ./unistd.h =====>
-info: hipify ./kmeans.c =====>
-info: hipify ./kmeans_cuda_kernel.cu =====>
-  info: converted 40 CUDA->HIP refs( dev:0 mem:0 kern:0 builtin:37 math:0 stream:0 event:0 err:0 def:0 tex:3 other:0 ) warn:0 LOC:185
-info: hipify ./getopt.h =====>
-info: hipify ./kmeans_cuda.cu =====>
-  info: converted 49 CUDA->HIP refs( dev:3 mem:32 kern:2 builtin:0 math:0 stream:0 event:0 err:0 def:0 tex:12 other:0 ) warn:0 LOC:311
-info: hipify ./rmse.c =====>
-info: hipify ./cluster.c =====>
-info: hipify ./getopt.c =====>
-info: hipify ./kmeans_clustering.c =====>
-info: TOTAL-converted 89 CUDA->HIP refs( dev:3 mem:32 kern:2 builtin:37 math:0 stream:0 event:0 err:0 def:0 tex:15 other:0 ) warn:0 LOC:3607
-  kernels (1 total) :   kmeansPoint(1)
-```
-
-hipexamine-perl scans each code file (cpp, c, h, hpp, etc.) found in the specified directory:
-
-   * Files with no CUDA code (ie kmeans.h) print one line summary just listing the source file name.
-   * Files with CUDA code print a summary of what was found - for example the kmeans_cuda_kernel.cu file:
-```
-info: hipify ./kmeans_cuda_kernel.cu =====>
-  info: converted 40 CUDA->HIP refs( dev:0 mem:0 kern:0 builtin:37 math:0 stream:0 event:0
-```
-* Interesting information in kmeans_cuda_kernel.cu :
-  * How many CUDA calls were converted to HIP (40)
-  * Breakdown of the CUDA functionality used (dev:0 mem:0 etc). This file uses many CUDA builtins (37) and texture functions (3).
-   * Warning for code that looks like CUDA API but was not converted (0 in this file).
-   * Count Lines-of-Code (LOC) - 185 for this file.
-
-* hipexamine-perl also presents a summary at the end of the process for the statistics collected across all files. This has similar format to the per-file reporting, and also includes a list of all kernels which have been called.  An example from above:
-
-```shell
-info: TOTAL-converted 89 CUDA->HIP refs( dev:3 mem:32 kern:2 builtin:37 math:0 stream:0 event:0 err:0 def:0 tex:15 other:0 ) warn:0 LOC:3607
-  kernels (1 total) :   kmeansPoint(1)
-```
-
-### Converting a project "in-place"
-
-```shell
-> hipify-perl --inplace
-```
-
-For each input file FILE, this script will:
-  - If "FILE.prehip file does not exist, copy the original code to a new file with extension ".prehip". Then hipify the code file.
-  - If "FILE.prehip" file exists, hipify FILE.prehip and save to FILE.
-
-This is useful for testing improvements to the hipify toolset.
-
-
-The [hipconvertinplace-perl.sh](https://github.com/ROCm-Developer-Tools/HIPIFY/blob/master/bin/hipconvertinplace-perl.sh) script will perform inplace conversion for all code files in the specified directory.
-This can be quite handy when dealing with an existing CUDA code base since the script preserves the existing directory structure
-and filenames - and includes work.  After converting in-place, you can review the code to add additional parameters to
-directory names.
-
-
-```shell
-> hipconvertinplace-perl.sh MY_SRC_DIR
-```
-
-### Library Equivalents
-
-| CUDA Library | ROCm Library | Comment |
-|------- | ---------   | -----   |
-| cuBLAS        |    rocBLAS     | Basic Linear Algebra Subroutines
-| cuFFT        |    rocFFT     | Fast Fourier Transfer Library
-| cuSPARSE     |    rocSPARSE   | Sparse BLAS  + SPMV
-| cuSolver     |    rocSOLVER   | Lapack library
-| AMG-X    |    rocALUTION   | Sparse iterative solvers and preconditioners with Geometric and Algebraic MultiGrid
-| Thrust    |    rocThrust | C++ parallel algorithms library
-| CUB     |    rocPRIM | Low Level Optimized Parallel Primitives
-| cuDNN    |    MIOpen | Deep learning Solver Library
-| cuRAND    |    rocRAND | Random Number Generator Library
-| EIGEN    |    EIGEN – HIP port | C++ template library for linear algebra: matrices, vectors, numerical solvers,
-| NCCL    |    RCCL  | Communications Primitives Library based on the MPI equivalents
-
-
-
-## Distinguishing Compiler Modes
-
-
-### Identifying HIP Target Platform
-All HIP projects target either AMD or NVIDIA platform. The platform affects which headers are included and which libraries are used for linking.
-
-- `HIP_PLATFORM_AMD` is defined if the HIP platform targets AMD.
-Note, `HIP_PLATFORM_HCC` was previously defined if the HIP platform targeted AMD, it is deprecated.
-
-- `HIP_PLATFORM_NVDIA` is defined if the HIP platform targets NVIDIA.
-Note, `HIP_PLATFORM_NVCC` was previously defined if the HIP platform targeted NVIDIA, it is deprecated.
-
-### Identifying the Compiler: hip-clang or nvcc
-Often, it's useful to know whether the underlying compiler is HIP-Clang or nvcc. This knowledge can guard platform-specific code or aid in platform-specific performance tuning.
-
-```
-#ifdef __HIP_PLATFORM_AMD__
-// Compiled with HIP-Clang
-#endif
-```
-
-```
-#ifdef __HIP_PLATFORM_NVIDIA__
-// Compiled with nvcc
-//  Could be compiling with CUDA language extensions enabled (for example, a ".cu file)
-//  Could be in pass-through mode to an underlying host compile OR (for example, a .cpp file)
-
-```
-
-```
-#ifdef __CUDACC__
-// Compiled with nvcc (CUDA language extensions enabled)
-```
-
-Compiler directly generates the host code (using the Clang x86 target) and passes the code to another host compiler. Thus, they have no equivalent of the \__CUDA_ACC define.
-
-
-### Identifying Current Compilation Pass: Host or Device
-
-nvcc makes two passes over the code: one for host code and one for device code.
-HIP-Clang will have multiple passes over the code: one for the host code, and one for each architecture on the device code.
-`__HIP_DEVICE_COMPILE__` is set to a nonzero value when the compiler (HIP-Clang or nvcc) is compiling code for a device inside a `__global__` kernel or for a device function. `__HIP_DEVICE_COMPILE__` can replace #ifdef checks on the `__CUDA_ARCH__` define.
-
-```
-// #ifdef __CUDA_ARCH__
-#if __HIP_DEVICE_COMPILE__
-```
-
-Unlike `__CUDA_ARCH__`, the `__HIP_DEVICE_COMPILE__` value is 1 or undefined, and it doesn't represent the feature capability of the target device.
-
-### Compiler Defines: Summary
-|Define  		|   HIP-Clang  | nvcc 		|  Other (GCC, ICC, Clang, etc.)
-|--- | --- | --- |---|
-|HIP-related defines:|
-|`__HIP_PLATFORM_AMD__`| Defined | Undefined |  Defined if targeting AMD platform; undefined otherwise |
-|`__HIP_PLATFORM_NVIDIA__`| Undefined  | Defined |  Defined if targeting NVIDIA platform; undefined otherwise |
-|`__HIP_DEVICE_COMPILE__`     | 1 if compiling for device; undefined if compiling for host  |1 if compiling for device; undefined if compiling for host  | Undefined
-|`__HIPCC__`		|  Defined | Defined 		|  Undefined
-|`__HIP_ARCH_*` |0 or 1 depending on feature support (see below) | 0 or 1 depending on feature support (see below) | 0
-|nvcc-related defines:|
-|`__CUDACC__` 		 | Defined if source code is compiled by nvcc; undefined otherwise 		|  Undefined
-|`__NVCC__` 		 | Undefined | Defined 		|  Undefined
-|`__CUDA_ARCH__`		 | Undefined | Unsigned representing compute capability (e.g., "130") if in device code; 0 if in host code  | Undefined
-|hip-clang-related defines:|
-|`__HIP__`  		 | Defined   | Undefined   	|  Undefined
-|HIP-Clang common defines:|
-|`__clang__`		| Defined   | Defined | Undefined 	|  Defined if using Clang; otherwise undefined
-
-## Identifying Architecture Features
-
-### HIP_ARCH Defines
-
-Some CUDA code tests `__CUDA_ARCH__` for a specific value to determine whether the machine supports a certain architectural feature. For instance,
-
-```
-#if (__CUDA_ARCH__ >= 130)
-// doubles are supported
-```
-This type of code requires special attention, since AMD and CUDA devices have different architectural capabilities. Moreover, you can't determine the presence of a feature using a simple comparison against an architecture's version number. HIP provides a set of defines and device properties to query whether a specific architectural feature is supported.
-
-The `__HIP_ARCH_*` defines can replace comparisons of `__CUDA_ARCH__` values:
-```
-//#if (__CUDA_ARCH__ >= 130)   // non-portable
-if __HIP_ARCH_HAS_DOUBLES__ {  // portable HIP feature query
-   // doubles are supported
-}
-```
-
-For host code, the `__HIP_ARCH__*` defines are set to 0. You should only use the __HIP_ARCH__ fields in device code.
-
-### Device-Architecture Properties
-
-Host code should query the architecture feature flags in the device properties that hipGetDeviceProperties returns, rather than testing the "major" and "minor" fields directly:
-
-```
-hipGetDeviceProperties(&deviceProp, device);
-//if ((deviceProp.major == 1 && deviceProp.minor < 2))  // non-portable
-if (deviceProp.arch.hasSharedInt32Atomics) {            // portable HIP feature query
-    // has shared int32 atomic operations ...
-}
-```
-
-### Table of Architecture Properties
-The table below shows the full set of architectural properties that HIP supports.
-
-|Define (use only in device code) | Device Property (run-time query) | Comment |
-|------- | ---------   | -----   |
-|32-bit atomics:||
-|`__HIP_ARCH_HAS_GLOBAL_INT32_ATOMICS__`        |    hasGlobalInt32Atomics      |32-bit integer atomics for global memory
-|`__HIP_ARCH_HAS_GLOBAL_FLOAT_ATOMIC_EXCH__`    |    hasGlobalFloatAtomicExch   |32-bit float atomic exchange for global memory
-|`__HIP_ARCH_HAS_SHARED_INT32_ATOMICS__`        |    hasSharedInt32Atomics      |32-bit integer atomics for shared memory
-|`__HIP_ARCH_HAS_SHARED_FLOAT_ATOMIC_EXCH__`    |    hasSharedFloatAtomicExch   |32-bit float atomic exchange for shared memory
-|`__HIP_ARCH_HAS_FLOAT_ATOMIC_ADD__`            |     hasFloatAtomicAdd         |32-bit float atomic add in global and shared memory
-|64-bit atomics:                           |                                     |
-|`__HIP_ARCH_HAS_GLOBAL_INT64_ATOMICS__`        |    hasGlobalInt64Atomics      |64-bit integer atomics for global memory
-|`__HIP_ARCH_HAS_SHARED_INT64_ATOMICS__`        |    hasSharedInt64Atomics      |64-bit integer atomics for shared memory
-|Doubles:                                  |                                     |
-|`__HIP_ARCH_HAS_DOUBLES__`                    |     hasDoubles                 |Double-precision floating point
-|Warp cross-lane operations:              |                                      |
-|`__HIP_ARCH_HAS_WARP_VOTE__`                  |     hasWarpVote                |Warp vote instructions (any, all)
-|`__HIP_ARCH_HAS_WARP_BALLOT__`                |     hasWarpBallot              |Warp ballot instructions
-|`__HIP_ARCH_HAS_WARP_SHUFFLE__`               |     hasWarpShuffle             |Warp shuffle operations (shfl\_\*)
-|`__HIP_ARCH_HAS_WARP_FUNNEL_SHIFT__`          |     hasFunnelShift             |Funnel shift two input words into one
-|Sync:                                    |                                      |
-|`__HIP_ARCH_HAS_THREAD_FENCE_SYSTEM__`        |     hasThreadFenceSystem       |threadfence\_system
-|`__HIP_ARCH_HAS_SYNC_THREAD_EXT__`            |     hasSyncThreadsExt         |syncthreads\_count, syncthreads\_and, syncthreads\_or
-|Miscellaneous:                                |                                |
-|`__HIP_ARCH_HAS_SURFACE_FUNCS__`              |   hasSurfaceFuncs              |
-|`__HIP_ARCH_HAS_3DGRID__`                     |   has3dGrid                    | Grids and groups are 3D
-|`__HIP_ARCH_HAS_DYNAMIC_PARALLEL__`           |   hasDynamicParallelism        |
-
-
-## Finding HIP
-
-Makefiles can use the following syntax to conditionally provide a default HIP_PATH if one does not exist:
-
-```
-HIP_PATH ?= $(shell hipconfig --path)
-```
-
-## Identifying HIP Runtime
-
-HIP can depend on rocclr, or cuda as runtime
-
-- AMD platform
-On AMD platform, HIP uses Radeon Open Compute Common Language Runtime, called ROCclr.
-ROCclr is a virtual device interface that HIP runtimes interact with different backends which allows runtimes to work on Linux , as well as Windows without much efforts.
-
-- NVIDIA platform
-On Nvidia platform, HIP is just a thin layer on top of CUDA.
-On non-AMD platform, HIP runtime determines if cuda is available and can be used. If available, HIP_PLATFORM is set to nvidia and underneath CUDA path is used.
-
-
-## hipLaunchKernelGGL
-
-hipLaunchKernelGGL is a macro that can serve as an alternative way to launch kernel, which accepts parameters of launch configurations (grid dims, group dims, stream, dynamic shared size) followed by a variable number of kernel arguments.
-It can replace <<< >>>, if the user so desires.
-
-## Compiler Options
-
-hipcc is a portable compiler driver that will call nvcc or HIP-Clang (depending on the target system) and attach all required include and library options. It passes options through to the target compiler. Tools that call hipcc must ensure the compiler options are appropriate for the target compiler.
-The `hipconfig` script may helpful in identifying the target platform, compiler and runtime. It can also help set options appropriately.
-
-### Compiler options supported on AMD platforms
-
-Here are the main compiler options supported on AMD platforms by HIP-Clang.
-
-| Option                            | Description |
-| ------                            | ----------- |
-| --amdgpu-target=<gpu_arch>        | [DEPRECATED] This option is being replaced by `--offload-arch=<target>`. Generate code for the given GPU target.  Supported targets are gfx701, gfx801, gfx802, gfx803, gfx900, gfx906, gfx908, gfx1010, gfx1011, gfx1012, gfx1030, gfx1031.  This option could appear multiple times on the same command line to generate a fat binary for multiple targets. |
-| --fgpu-rdc                        | Generate relocatable device code, which allows kernels or device functions calling device functions in different translation units. |
-| -ggdb                             | Equivalent to `-g` plus tuning for GDB.  This is recommended when using ROCm's GDB to debug GPU code. |
-| --gpu-max-threads-per-block=<num> | Generate code to support up to the specified number of threads per block.  |
-| -O<n>                             | Specify the optimization level. |
-| -offload-arch=<target>            | Specify the AMD GPU [target ID](https://clang.llvm.org/docs/ClangOffloadBundlerFileFormat.html#target-id). |
-| -save-temps                       | Save the compiler generated intermediate files. |
-| -v                                | Show the compilation steps. |
-
-## Linking Issues
-
-### Linking With hipcc
-
-hipcc adds the necessary libraries for HIP as well as for the accelerator compiler (nvcc or AMD compiler). We recommend linking with hipcc since it automatically links the binary to the necessary HIP runtime libraries.  It also has knowledge on how to link and to manage the GPU objects.
-
-### -lm Option
-
-hipcc adds -lm by default to the link command.
-
-
-## Linking Code With Other Compilers
-
-CUDA code often uses nvcc for accelerator code (defining and launching kernels, typically defined in .cu or .cuh files).
-It also uses a standard compiler (g++) for the rest of the application. nvcc is a preprocessor that employs a standard host compiler (gcc) to generate the host code.
-Code compiled using this tool can employ only the intersection of language features supported by both nvcc and the host compiler.
-In some cases, you must take care to ensure the data types and alignment of the host compiler are identical to those of the device compiler. Only some host compilers are supported---for example, recent nvcc versions lack Clang host-compiler capability.
-
-HIP-Clang generates both device and host code using the same Clang-based compiler. The code uses the same API as gcc, which allows code generated by different gcc-compatible compilers to be linked together. For example, code compiled using HIP-Clang can link with code compiled using "standard" compilers (such as gcc, ICC and Clang). Take care to ensure all compilers use the same standard C++ header and library formats.
-
-
-### libc++ and libstdc++
-
-hipcc links to libstdc++ by default. This provides better compatibility between g++ and HIP.
-
-If you pass "--stdlib=libc++" to hipcc, hipcc will use the libc++ library.  Generally, libc++ provides a broader set of C++ features while libstdc++ is the standard for more compilers (notably including g++).
-
-When cross-linking C++ code, any C++ functions that use types from the C++ standard library (including std::string, std::vector and other containers) must use the same standard-library implementation. They include the following:
-
-- Functions or kernels defined in HIP-Clang that are called from a standard compiler
-- Functions defined in a standard compiler that are called from HIP-Clanng.
-
-Applications with these interfaces should use the default libstdc++ linking.
-
-Applications which are compiled entirely with hipcc, and which benefit from advanced C++ features not supported in libstdc++, and which do not require portability to nvcc, may choose to use libc++.
-
-
-### HIP Headers (hip_runtime.h, hip_runtime_api.h)
-
-The hip_runtime.h and hip_runtime_api.h files define the types, functions and enumerations needed to compile a HIP program:
-
-- hip_runtime_api.h: defines all the HIP runtime APIs (e.g., hipMalloc) and the types required to call them. A source file that is only calling HIP APIs but neither defines nor launches any kernels can include hip_runtime_api.h. hip_runtime_api.h uses no custom hc language features and can be compiled using a standard C++ compiler.
-- hip_runtime.h: included in hip_runtime_api.h. It additionally provides the types and defines required to create and launch kernels. hip_runtime.h can be compiled using a standard C++ compiler but will expose a subset of the available functions.
-
-CUDA has slightly different contents for these two files. In some cases you may need to convert hipified code to include the richer hip_runtime.h instead of hip_runtime_api.h.
-
-### Using a Standard C++ Compiler
-You can compile hip\_runtime\_api.h using a standard C or C++ compiler (e.g., gcc or ICC). The HIP include paths and defines (`__HIP_PLATFORM_AMD__` or `__HIP_PLATFORM_NVIDIA__`) must pass to the standard compiler; hipconfig then returns the necessary options:
-```
-> hipconfig --cxx_config
- -D__HIP_PLATFORM_AMD__ -I/home/user1/hip/include
-```
-
-You can capture the hipconfig output and passed it to the standard compiler; below is a sample makefile syntax:
-
-```
-CPPFLAGS += $(shell $(HIP_PATH)/bin/hipconfig --cpp_config)
-```
-
-nvcc includes some headers by default.  However, HIP does not include default headers, and instead all required files must be explicitly included.
-Specifically, files that call HIP run-time APIs or define HIP kernels must explicitly include the appropriate HIP headers.
-If the compilation process reports that it cannot find necessary APIs (for example, "error: identifier ‘hipSetDevice’ is undefined"),
-ensure that the file includes hip_runtime.h (or hip_runtime_api.h, if appropriate).
-The hipify-perl script automatically converts "cuda_runtime.h" to "hip_runtime.h," and it converts "cuda_runtime_api.h" to "hip_runtime_api.h", but it may miss nested headers or macros.
-
-#### cuda.h
-
-The HIP-Clang path provides an empty cuda.h file. Some existing CUDA programs include this file but don't require any of the functions.
-
-### Choosing HIP File Extensions
-
-Many existing CUDA projects use the ".cu" and ".cuh" file extensions to indicate code that should be run through the nvcc compiler.
-For quick HIP ports, leaving these file extensions unchanged is often easier, as it minimizes the work required to change file names in the directory and #include statements in the files.
-
-For new projects or ports which can be re-factored, we recommend the use of the extension ".hip.cpp" for source files, and
-".hip.h" or ".hip.hpp" for header files.
-This indicates that the code is standard C++ code, but also provides a unique indication for make tools to
-run hipcc when appropriate.
-
-## Workarounds
-
-### warpSize
-Code should not assume a warp size of 32 or 64.  See [Warp Cross-Lane Functions](hip_kernel_language.md#warp-cross-lane-functions) for information on how to write portable wave-aware code.
-
-### Kernel launch with group size > 256
-Kernel code should use ``` __attribute__((amdgpu_flat_work_group_size(<min>,<max>)))```.
-
-For example:
-```
-__global__ void dot(double *a,double *b,const int n) __attribute__((amdgpu_flat_work_group_size(1, 512)))
-```
-
-## memcpyToSymbol
-
-HIP support for hipMemcpyToSymbol is complete.  This feature allows a kernel
-to define a device-side data symbol which can be accessed on the host side.  The symbol
-can be in __constant or device space.
-
-Note that the symbol name needs to be encased in the HIP_SYMBOL macro, as shown in the code example below. This also applies to hipMemcpyFromSymbol, hipGetSymbolAddress, and hipGetSymbolSize.
-
-For example:
-
-Device Code:
-```
-#include<hip/hip_runtime.h>
-#include<hip/hip_runtime_api.h>
-#include<iostream>
-
-#define HIP_ASSERT(status) \
-    assert(status == hipSuccess)
-
-#define LEN 512
-#define SIZE 2048
-
-__constant__ int Value[LEN];
-
-__global__ void Get(hipLaunchParm lp, int *Ad)
-{
-    int tid = threadIdx.x + blockIdx.x * blockDim.x;
-    Ad[tid] = Value[tid];
-}
-
-int main()
-{
-    int *A, *B, *Ad;
-    A = new int[LEN];
-    B = new int[LEN];
-    for(unsigned i=0;i<LEN;i++)
-    {
-        A[i] = -1*i;
-        B[i] = 0;
-    }
-
-    HIP_ASSERT(hipMalloc((void**)&Ad, SIZE));
-
-    HIP_ASSERT(hipMemcpyToSymbol(HIP_SYMBOL(Value), A, SIZE, 0, hipMemcpyHostToDevice));
-    hipLaunchKernelGGL(Get, dim3(1,1,1), dim3(LEN,1,1), 0, 0, Ad);
-    HIP_ASSERT(hipMemcpy(B, Ad, SIZE, hipMemcpyDeviceToHost));
-
-    for(unsigned i=0;i<LEN;i++)
-    {
-        assert(A[i] == B[i]);
-    }
-    std::cout<<"Passed"<<std::endl;
-}
-```
-
-## CU_POINTER_ATTRIBUTE_MEMORY_TYPE
-
-To get pointer's memory type in HIP/HIP-Clang, developers should use hipPointerGetAttributes API. First parameter of the API is hipPointerAttribute_t which has 'type' as member variable. 'type' indicates input pointer is allocated on device or host.
-
-For example:
-```
-double * ptr;
-hipMalloc(reinterpret_cast<void**>(&ptr), sizeof(double));
-hipPointerAttribute_t attr;
-hipPointerGetAttributes(&attr, ptr); /*attr.type will have value as hipMemoryTypeDevice*/
-
-double* ptrHost;
-hipHostMalloc(&ptrHost, sizeof(double));
-hipPointerAttribute_t attr;
-hipPointerGetAttributes(&attr, ptrHost); /*attr.type will have value as hipMemoryTypeHost*/
-```
-Please note, hipMemoryType enum values are different from cudaMemoryType enum values.
-
-For example, on AMD platform, hipMemoryType is defined in hip_runtime_api.h,
-```
-typedef enum hipMemoryType {
-    hipMemoryTypeHost = 0,    ///< Memory is physically located on host
-    hipMemoryTypeDevice = 1,  ///< Memory is physically located on device. (see deviceId for specific device)
-    hipMemoryTypeArray = 2,   ///< Array memory, physically located on device. (see deviceId for specific device)
-    hipMemoryTypeUnified = 3, ///< Not used currently
-    hipMemoryTypeManaged = 4  ///< Managed memory, automaticallly managed by the unified memory system
-} hipMemoryType;
-```
-Looking into CUDA toolkit, it defines cudaMemoryType as following,
-```
-enum cudaMemoryType
-{
-  cudaMemoryTypeUnregistered = 0, // Unregistered memory.
-  cudaMemoryTypeHost = 1, // Host memory.
-  cudaMemoryTypeDevice = 2, // Device memory.
-  cudaMemoryTypeManaged = 3, // Managed memory
-}
-```
-In this case, memory type translation for hipPointerGetAttributes needs to be handled properly on nvidia platform to get the correct memory type in CUDA, which is done in the file nvidia_hip_runtime_api.h.
-
-So in any HIP applications which use HIP APIs involving memory types, developers should use #ifdef in order to assign the correct enum values depending on Nvidia or AMD platform.
-
-As an example, please see the code from the link,
-github.com/ROCm-Developer-Tools/HIP/blob/develop/tests/catch/unit/memory/hipMemcpyParam2D.cc#L77-L96.
-
-With the #ifdef condition, HIP APIs work as expected on both AMD and NVIDIA platforms.
-
-## threadfence_system
-Threadfence_system makes all device memory writes, all writes to mapped host memory, and all writes to peer memory visible to CPU and other GPU devices.
-Some implementations can provide this behavior by flushing the GPU L2 cache.
-HIP/HIP-Clang does not provide this functionality.  As a workaround, users can set the environment variable `HSA_DISABLE_CACHE=1` to disable the GPU L2 cache. This will affect all accesses and for all kernels and so may have a performance impact.
-
-### Textures and Cache Control
-
-Compute programs sometimes use textures either to access dedicated texture caches or to use the texture-sampling hardware for interpolation and clamping. The former approach uses simple point samplers with linear interpolation, essentially only reading a single point. The latter approach uses the sampler hardware to interpolate and combine multiple samples. AMD hardware, as well as recent competing hardware, has a unified texture/L1 cache, so it no longer has a dedicated texture cache. But the nvcc path often caches global loads in the L2 cache, and some programs may benefit from explicit control of the L1 cache contents.  We recommend the __ldg instruction for this purpose.
-
-AMD compilers currently load all data into both the L1 and L2 caches, so __ldg is treated as a no-op.
-
-We recommend the following for functional portability:
-
-- For programs that use textures only to benefit from improved caching, use the __ldg instruction
-- Programs that use texture object and reference APIs, work well on HIP
-
-
-## More Tips
-
-### HIP Logging
-
-On an AMD platform, set the AMD_LOG_LEVEL environment variable to log HIP application execution information.
-
-The value of the setting controls different logging level,
-
-```
-enum LogLevel {
-LOG_NONE = 0,
-LOG_ERROR = 1,
-LOG_WARNING = 2,
-LOG_INFO = 3,
-LOG_DEBUG = 4
-};
-```
-
-Logging mask is used to print types of functionalities during the execution of HIP application.
-It can be set as one of the following values,
-
-```
-enum LogMask {
-  LOG_API       = 0x00000001, //!< API call
-  LOG_CMD       = 0x00000002, //!< Kernel and Copy Commands and Barriers
-  LOG_WAIT      = 0x00000004, //!< Synchronization and waiting for commands to finish
-  LOG_AQL       = 0x00000008, //!< Decode and display AQL packets
-  LOG_QUEUE     = 0x00000010, //!< Queue commands and queue contents
-  LOG_SIG       = 0x00000020, //!< Signal creation, allocation, pool
-  LOG_LOCK      = 0x00000040, //!< Locks and thread-safety code.
-  LOG_KERN      = 0x00000080, //!< kernel creations and arguments, etc.
-  LOG_COPY      = 0x00000100, //!< Copy debug
-  LOG_COPY2     = 0x00000200, //!< Detailed copy debug
-  LOG_RESOURCE  = 0x00000400, //!< Resource allocation, performance-impacting events.
-  LOG_INIT      = 0x00000800, //!< Initialization and shutdown
-  LOG_MISC      = 0x00001000, //!< misc debug, not yet classified
-  LOG_AQL2      = 0x00002000, //!< Show raw bytes of AQL packet
-  LOG_CODE      = 0x00004000, //!< Show code creation debug
-  LOG_CMD2      = 0x00008000, //!< More detailed command info, including barrier commands
-  LOG_LOCATION  = 0x00010000, //!< Log message location
-  LOG_ALWAYS    = 0xFFFFFFFF, //!< Log always even mask flag is zero
-};
-```
-
-### Debugging hipcc
-To see the detailed commands that hipcc issues, set the environment variable HIPCC_VERBOSE to 1. Doing so will print to stderr the HIP-clang (or nvcc) commands that hipcc generates.
-
-```
-export HIPCC_VERBOSE=1
-make
-...
-hipcc-cmd: /opt/hcc/bin/hcc  -hc -I/opt/hcc/include -stdlib=libc++ -I../../../../hc/include -I../../../../include/amd_detail/cuda -I../../../../include -x c++ -I../../common -O3 -c backprop_cuda.cu
-```
-
-### What Does This Error Mean?
-
-#### /usr/include/c++/v1/memory:5172:15: error: call to implicitly deleted default constructor of 'std::__1::bad_weak_ptr' throw bad_weak_ptr();
-
-If you pass a ".cu" file, hcc will attempt to compile it as a CUDA language file. You must tell hcc that it's in fact a C++ file: use the "-x c++" option.
-
-
-### Editor Highlighting
-See the utils/vim or utils/gedit directories to add handy highlighting to hip files.
-
-
diff --git a/projects/hip/docs/markdown/modern_cpp_features.md b/projects/hip/docs/markdown/modern_cpp_features.md
deleted file mode 100644
index 1bd0fcf79c..0000000000
--- a/projects/hip/docs/markdown/modern_cpp_features.md
+++ /dev/null
@@ -1,468 +0,0 @@
-# HIP C++ Feature
-
-## C++ 11
-
-### Rvalue References
-
-```cpp
-struct Y {
-  int x;
-};
-
-__device__ void do_something(Y &&val) { val.x += 1; }
-
-__global__ void kernel() {
-  Y y{10};
-  // do_something(y); // does not compile since the argument is an lvalue
-  do_something(std::move(y));
-}
-
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Rvalue References for `*this`
-
-```cpp
-struct Sample {
-  __host__ __device__ void callMe() & { printf("Lval Func\n"); }
-  __host__ __device__ void callMe() && { printf("Rval Func\n"); }
-};
-
-__global__ void kernel() {
-  Sample s;
-  s.callMe();        // prints Lval Func
-  Sample().callMe(); // prints Rval Func
-}
-
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Variadic templates, Static Assertions, `auto` Variables
-
-```cpp
-template <typename T> __host__ __device__ T add(T val) { return val; }
-
-template <typename T, typename... Targs>
-__host__ __device__ T add(T val, Targs... pVal) {
-  static_assert(std::is_arithmetic<T>::value, "Not a valid type");
-  return val + add(pVal...);
-}
-
-template <typename T, typename... Targs>
-__global__ void kernel(T *ptr, Targs... args) {
-  auto &&sum = add(args...);
-  *ptr = sum;
-}
-
-// Or something like
-
-__device__ int &getX(int &x) { return ++x; }
-__device__ int getY(int &x) { return x + 10; }
-
-__global__ void kernel() {
-  int X = 0;
-  auto &&x = getX(X);
-  auto &&y = getY(X);
-
-  // Init with value or initializer list
-  auto val{10};
-  auto list = {10};
-}
-
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Non-static Data Member Initialization
-
-```cpp
-struct S {
-  int a = 1;
-  int b = 2;
-};
-
-__global__ void kernel() {
-  S s; // s.a == 1 and s.b == 2
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Lambda Device Functions
-
-```cpp
-template <typename T> __global__ void kernel(T f) { f(); }
-
-int main() {
-  auto func = [=] __device__() { printf("In Kernel\n"); };
-  kernel<<<1, 1>>>(func);
-  hipDeviceSynchronize();
-}
-```
-
-### `decltype` Usage
-
-```cpp
-template <typename T> __device__ T ret() {
-  T x{0};
-  return x;
-}
-
-template <typename T> __global__ void kernel() {
-  decltype(ret<T>()) a;
-  int i = 0;
-  decltype(i) j = i + 1;
-}
-int main() { kernel<float><<<1, 1>>>(); }
-```
-
-### Default Template Arguments
-
-```cpp
-template <int N = 5> __global__ void kernel(int x) { x += N; }
-int main() {
-  kernel<<<1, 1>>>(1);
-  kernel<-2><<<1, 1>>>(1);
-}
-```
-
-### Template Alias
-
-```cpp
-template <typename T> struct Alloc {};
-
-template <typename T, typename U> struct Vector {};
-
-template <typename T> using V = Vector<T, Alloc<T>>;
-
-template <typename T> __global__ void kernel(T x) { V<T> v; }
-
-int main() { kernel<<<1, 1>>>(5); }
-```
-
-### Extern Template
-
-```cpp
-template <typename T> __global__ void kernel(T x) {}
-
-extern template __global__ void kernel(long x);
-
-int main() {
-  kernel<<<1, 1, 0, 0>>>(10); // will create a template specialization
-  // kernel<<<1,1,0,0>>>(10l);  // looks for existing kernel<long>, causing
-  // linking to fail
-}
-```
-
-### `nullptr` as a Keyword in Device Compiler
-
-```cpp
-__global__ void kernel() {
-  int *ptr = nullptr;
-  //...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Strongly Typed Enums
-
-```cpp
-enum class EnumVals { Red, Blue, Green };
-__global__ void kernel() {
-  auto val = EnumVals::Red;
-  //...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Standardized Attribute Syntax
-
-```cpp
-[[deprecated]] __global__ void kernel() {
-  //...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### `constexpr`
-
-```cpp
-struct S {
-  constexpr __device__ S(double v) : val(v) {}
-  constexpr __device__ double value() const { return val; }
-
-private:
-  double val;
-};
-
-constexpr __device__ int factorial(int n) {
-  return n <= 1 ? 1 : (n * factorial(n - 1));
-}
-
-__global__ void kernel() {
-  constexpr S s(factorial(5));
-  constexpr double d = s.value();
-  // ...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### `alignas` with Struct
-
-```cpp
-struct alignas(alignof(int)) S {
-  //...
-};
-
-__global__ void kernel() {
-  S s;
-  static_assert(alignof(S) == alignof(int), "they have the same alignment");
-  // check the alignment
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Delegating Constructors
-
-```cpp
-struct S {
-private:
-  int val;
-
-public:
-  __device__ S(int v) : val(v) {}
-  __device__ S() : S(42) {}
-};
-__global__ void kernel() { S s{}; }
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Explicit Conversion Functions
-
-```cpp
-struct S {
-private:
-  int val;
-
-public:
-  __device__ S(int val) : val(val) {}
-  __device__ explicit operator int *() { return &val; }
-};
-
-__global__ void kernel() {
-  S s{0};
-  // if (s) { // compile error
-  // without the explicit function specifier then s would be converted to the
-  // pointer to s.val, which would be non-zero so always true.
-  //}
-  if ((int *)(s)) {
-    // this compiles but is likely not what the user intended
-  }
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Unicode Character Types, Unicode String, Universal Character Literal
-
-```cpp
-__global__ void kernel() {
-  // cant print it since printf(gpu) doesnot support unicode char arguments
-  char16_t a = u'y';
-  char32_t l = U'猫';
-  auto *string = U"इस अनुवाद को करने से आपको क्या मिला?";
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### User Defined Literals
-
-```cpp
-__device__ long double operator"" _w(long double a) { return a; }
-__device__ unsigned operator"" _w(char const *c) { return *c - '0'; }
-
-__global__ void kernel() {
-  auto ld = 1.2_w; // calls operator "" _w(1.2L)
-  auto val = 2_w;  // calls operator "" _w("2")
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### `default`/`delete` Functions
-
-```cpp
-struct S {
-  __device__ S() = default;
-  __device__ S &operator=(const S &) = delete;
-};
-__global__ void kernel() {
-  S s, other; // fine
-  // other = s; // compile error, function deleted
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Friend Declaration
-
-```cpp
-struct Y {};
-
-struct A {
-  __device__ A() = default;
-  friend Y;
-  // friend Z; // compile error since class or struct Z doesn't exist
-  friend class Z;        // this is fine
-  friend void asdf(int); // functions can be declared without a definition
-};
-__global__ void kernel() { A a; }
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Extended `sizeof`
-
-```cpp
-template <typename... Ts> __global__ void kernel(Ts... ts) {
-  auto size = sizeof...(ts);
-  // ...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Unrestricted Unions
-
-```cpp
-struct Point {
-  __device__ Point() {}
-  __device__ Point(int x, int y) : x_(x), y_(y) {}
-  int x_, y_;
-};
-
-union U {
-  int z;
-  double w;
-  Point p;
-  __device__ U() {}
-  __device__ U(const Point &pt) : p(pt) {}
-  __device__ U &operator=(const Point &pt) {
-    new (&p) Point(pt);
-    return *this;
-  }
-};
-
-__global__ void kernel() {
-  U u;
-  //...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Inline Namespaces
-
-```cpp
-namespace XX {
-inline namespace YY {
-struct Y {
-  int x;
-};
-} // namespace YY
-struct X {
-  int a;
-};
-} // namespace XX
-
-__global__ void kernel() {
-  XX::X x{};
-  XX::Y y{};
-}
-
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Range Based For-loop
-
-```cpp
-__global__ void kernel() {
-  for (auto &x : {1, 2, 3, 4, 5}) {
-    // ...
-  }
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### `override` Specifier
-
-```cpp
-struct Base {
-  int n;
-  __device__ Base(int v) : n(v + 1) {}
-  __device__ Base() : Base(10) {}
-  __device__ virtual ~Base() {}
-  __device__ virtual int get() { return n; }
-};
-
-struct Derived : public Base {
-  int n;
-  __device__ Derived(int v) : n(v) {}
-  __device__ int get() override { return n; }
-  __device__ ~Derived() {}
-};
-
-__global__ void kernel() {
-  Derived d(10);
-  //...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### `noexcept` Keyword
-
-```cpp
-__global__ void kernel() noexcept {
-  int n;
-  //...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Consecutive Right Angle Brackets in Templates
-
-```cpp
-template <typename T> struct A { T a; };
-
-template <typename T> struct B { T b; };
-
-__global__ void kernel() {
-  A<B<int>> ab;
-  //...
-}
-int main() { kernel<<<1, 1>>>(); }
-```
-
-### Not Yet Documented 
-
-* Right Angled Brackets : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2005/n1757.html
-* Initializer List :  http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2672.htm
-* Solving SFINAE problem for expression :  http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2634.html
-* Forward Declaration of Enum : http://www.open-std.org/jtc1/sc22/wg21/docs/cwg_defects.html#1206 http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2764.pdf
-* Conditionally supported behavior : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2004/n1627.pdf
-* Inheriting Constructors : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2540.htm
-* Standard layout types : https://en.cppreference.com/w/cpp/named_req/StandardLayoutType
-* Local and unnamed types as template arguments : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2657.htm
-* Minimal support for Garbage Collection : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2670.htm
-* Move special functions : https://en.cppreference.com/w/cpp/language/rule_of_three
-* long long int
-
-
-## C++14
-
-### Not Yet Documented
-
-* Tweak C++ contextual conversions : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2012/n3323.pdf
-* Binary literals : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2012/n3472.pdf
-* Functions to deduce return type : https://isocpp.org/files/papers/N3638.html
-* Lambda capture changes : https://isocpp.org/files/papers/N3648.html
-* Polymorphic lambda : https://isocpp.org/files/papers/N3649.html
-* Variable template : https://en.cppreference.com/w/cpp/language/variable_template
-* constexpr changes : https://isocpp.org/files/papers/N3652.html
-* struct member initializer : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2013/n3653.html
-* clarifying mem allocation : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2013/n3664.html
-* sized dealloc : https://isocpp.org/files/papers/n3778.html
-* deprecated attribute : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2013/n3760.html
-* digit separator : http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2013/n3781.pdf
\ No newline at end of file
diff --git a/projects/hip/docs/markdown/obj_tooling.md b/projects/hip/docs/markdown/obj_tooling.md
deleted file mode 100644
index a4e0d253f5..0000000000
--- a/projects/hip/docs/markdown/obj_tooling.md
+++ /dev/null
@@ -1,92 +0,0 @@
-# ROCm Code Object tooling
-
-ROCm compiler generated code objects (executables, object files, and shared
-object libraries) can be examined and code objects extracted with the following
-tools.
-
-## roc-obj
-
-High-level wrapper around low-level tooling described below. For a more
-detailed overview, see the help text available with `roc-obj --help`.
-
-### Examples:
-
-#### Extract all ROCm code objects from a list of executables
-    roc-obj <executable>...
-
-#### Extract all ROCm code objects from a list of executables, and disassemble them
-    roc-obj --disassemble <executable>...
-    # or
-    roc-obj -d <executable>...
-
-#### Extract all ROCm code objects from a list of executables into dir/
-    roc-obj --outdir dir/ <executable>...
-    # or
-    roc-obj -o dir/ <executable>...
-
-#### Extract only ROCm code objects matching regex over Target ID
-    roc-obj --target-id gfx9 <executable>...
-    # or
-    roc-obj -t gfx9 <executable>...
-
-## Low-Level Tooling
-
-### URI syntax:
-
-  ROCm Code Objects can be listed/accessed using the following URI syntax:
-```
-	code_object_uri ::== file_uri | memory_uri
-	file_uri        ::== file:// extract_file [ range_specifier ]
-	memory_uri      ::== memory:// process_id range_specifier
-	range_specifier ::== [ # | ? ] offset= number & size= number
-	extract_file    ::== URI_ENCODED_OS_FILE_PATH
-	process_id      ::== DECIMAL_NUMBER
-	number          ::== HEX_NUMBER | DECIMAL_NUMBER | OCTAL_NUMBER
-```
-  Example: file://dir1/dir2/hello_world#offset=133&size=14472
-           memory://1234#offset=0x20000&size=3000
-
-### List available ROCm Code Objects: rocm-obj-ls
-
-  Use this tool to list available ROCm code objects.  Code objects are listed by bundle number, entry ID, and URI syntax.
-
-  Usage: roc-obj-ls [-v|h] executable...
-  List the URIs of the code objects embedded in the specfied host executables.
-    -v Verbose output.  Adds column headers for more human readable format
-    -h Show this help message
-
-
-### Extract ROCm Code Objects: roc-obj-extract
-
-  Extracts available ROCm code objects from specified URI.
-
-  Usage: roc-obj-extract [-o|v|h] URI...
-    - URIs can be read from STDIN, one per line.
-    - From the URIs specified, extracts code objects into files named: <executable_name>-[pid<number>]-offset<number>-size<number>.co
-
-  Options:
-    -o <path> Path for output. If "-" specified, code object is printed to STDOUT.
-    -v        Verbose output (includes Entry ID).
-    -h        Show this help message
-
-  Note, when specifying a URI argument to roc-obj-extract, if cut and pasting the output from roc-obj-ls you need to escape the '&' character or your shell will interpret it as the option to run the command as a background process.
-  As an example, if roc-obj-ls generates a URI like this ```file://my_exe#offset=24576&size=46816xxi```, you need to use the following argument to roc-obj-extract: ```file://my_exe#offset=24576\&size=46816```
-
-### Examples:
-
-#### Dump the ISA for gfx906:
-    roc-obj-ls -v <exe> | awk '/gfx906/{print $3}' | roc-obj-extract -o - | llvm-objdump -d - > <exe>.gfx906.isa
-
-#### Check the e_flags of the gfx908 code object:
-    roc-obj-ls -v <exe> | awk '/gfx908/{print $3}' | roc-obj-extract -o - | llvm-readelf -h - | grep Flags
-
-#### Disassemble the fourth code object:
-    roc-obj-ls <exe> | sed -n 4p | roc-obj-extract -o - | llvm-objdump -d -
-
-#### Sort embedded code objects by size:
-    for uri in $(roc-obj-ls <exe>); do printf "%d: %s\n" "$(roc-obj-extract -o - "$uri" | wc -c)" "$uri"; done | sort -n
-
-#### Compare disassembly of gfx803 and gfx900 code objects:
-    dis() { roc-obj-ls -v <exe> | grep "$1" | awk '{print $3}' | roc-obj-extract -o - | llvm-objdump -d -; }
-    diff <(dis gfx803) <(dis gfx900)
-
diff --git a/projects/hip/docs/markdown/hip_deprecated_api_list.md b/projects/hip/docs/reference/deprecated_api_list.md
similarity index 98%
rename from projects/hip/docs/markdown/hip_deprecated_api_list.md
rename to projects/hip/docs/reference/deprecated_api_list.md
index 22f3b2a4c9..e9e32ec1ba 100644
--- a/projects/hip/docs/markdown/hip_deprecated_api_list.md
+++ b/projects/hip/docs/reference/deprecated_api_list.md
@@ -1,4 +1,4 @@
-# HIP Deprecated APIs
+# HIP Deprecated Runtime Functions
 
 
 ## HIP Context Management APIs
diff --git a/projects/hip/docs/markdown/hip_terms2.md b/projects/hip/docs/reference/glossary.md
similarity index 100%
rename from projects/hip/docs/markdown/hip_terms2.md
rename to projects/hip/docs/reference/glossary.md
diff --git a/projects/hip/docs/markdown/hip_kernel_language.md b/projects/hip/docs/reference/kernel_language.md
similarity index 94%
rename from projects/hip/docs/markdown/hip_kernel_language.md
rename to projects/hip/docs/reference/kernel_language.md
index 5f8e9f8f95..3cd4d55007 100644
--- a/projects/hip/docs/markdown/hip_kernel_language.md
+++ b/projects/hip/docs/reference/kernel_language.md
@@ -1,60 +1,4 @@
-## Table of Contents
-
-<!-- toc -->
-
-- [Introduction](#introduction)
-- [Function-Type Qualifiers](#function-type-qualifiers)
-  * [`__device__`](#__device__)
-  * [`__global__`](#__global__)
-  * [`__host__`](#__host__)
-- [Calling `__global__` Functions](#calling-__global__-functions)
-- [Kernel-Launch Example](#kernel-launch-example)
-- [Variable-Type Qualifiers](#variable-type-qualifiers)
-  * [`__constant__`](#__constant__)
-  * [`__shared__`](#__shared__)
-  * [`__managed__`](#__managed__)
-  * [`__restrict__`](#__restrict__)
-- [Built-In Variables](#built-in-variables)
-  * [Coordinate Built-Ins](#coordinate-built-ins)
-  * [warpSize](#warpsize)
-- [Vector Types](#vector-types)
-  * [Short Vector Types](#short-vector-types)
-  * [dim3](#dim3)
-- [Memory-Fence Instructions](#memory-fence-instructions)
-- [Synchronization Functions](#synchronization-functions)
-- [Math Functions](#math-functions)
-  * [Single Precision Mathematical Functions](#single-precision-mathematical-functions)
-  * [Double Precision Mathematical Functions](#double-precision-mathematical-functions)
-  * [Integer Intrinsics](#integer-intrinsics)
-  * [Floating-point Intrinsics](#floating-point-intrinsics)
-- [Texture Functions](#texture-functions)
-- [Surface Functions](#surface-functions)
-- [Timer Functions](#timer-functions)
-- [Atomic Functions](#atomic-functions)
-- [Warp Cross-Lane Functions](#warp-cross-lane-functions)
-  * [Warp Vote and Ballot Functions](#warp-vote-and-ballot-functions)
-  * [Warp Shuffle Functions](#warp-shuffle-functions)
-- [Cooperative Groups Functions](#cooperative-groups-functions)
-- [Warp Matrix Functions](#warp-matrix-functions)
-- [Independent Thread Scheduling](#independent-thread-scheduling)
-- [Profiler Counter Function](#profiler-counter-function)
-- [Assert](#assert)
-- [Printf](#printf)
-- [Device-Side Dynamic Global Memory Allocation](#device-side-dynamic-global-memory-allocation)
-- [`__launch_bounds__`](#__launch_bounds__)
-  * [Compiler Impact](#compiler-impact)
-  * [CU and EU Definitions](#cu-and-eu-definitions)
-  * [Porting from CUDA __launch_bounds](#porting-from-cuda-__launch_bounds)
-  * [maxregcount](#maxregcount)
-- [Register Keyword](#register-keyword)
-- [Pragma Unroll](#pragma-unroll)
-- [In-Line Assembly](#in-line-assembly)
-- [C++ Support](#c-support)
-- [Kernel Compilation](#kernel-compilation)
-- [GFX Arch specific kernel](#gfx-arch-specific-kernel)
-<!-- tocstop -->
-
-## Introduction
+# Kernel Language Syntax
 
 HIP provides a C++ syntax that is suitable for compiling most code that commonly appears in compute kernels, including classes, namespaces, operator overloading, templates and more. Additionally, it defines other language features designed specifically to target accelerators, such as the following:
 - A kernel-launch syntax that uses standard C++, resembles a function call and is portable to all HIP targets
@@ -75,7 +19,7 @@ Supported  `__device__` functions are
   - Executed on the device
   - Called from the device only
 
-The `__device__` keyword can combine with the host keyword (see [__host__](#host)).
+The `__device__` keyword can combine with the host keyword (see {ref}`host_attr`).
 
 ### `__global__`
 Supported `__global__` functions are
@@ -86,6 +30,7 @@ HIP `__global__` functions must have a `void` return type, and the first paramet
 
 HIP lacks dynamic-parallelism support, so `__global__ ` functions cannot be called from the device.
 
+(host_attr)=
 ### `__host__`
 Supported `__host__` functions are
   - Executed on the host
@@ -123,7 +68,7 @@ MyKernel<<<dim3(gridDim), dim3(groupDim), 0, 0>>> (a,b,c,n);
 
 ```
 
-The hipLaunchKernelGGL macro always starts with the five parameters specified above, followed by the kernel arguments. HIPIFY tools optionally convert Cuda launch syntax to hipLaunchKernelGGL, including conversion of optional arguments in <<< >>> to the five required hipLaunchKernelGGL parameters. The dim3 constructor accepts zero to three arguments and will by default initialize unspecified dimensions to 1. See [dim3](#dim3). The kernel uses the coordinate built-ins (thread*, block*, grid*) to determine coordinate index and coordinate bounds of the work item that’s currently executing. See [Coordinate Built-Ins](#coordinate-builtins).
+The hipLaunchKernelGGL macro always starts with the five parameters specified above, followed by the kernel arguments. HIPIFY tools optionally convert Cuda launch syntax to hipLaunchKernelGGL, including conversion of optional arguments in <<< >>> to the five required hipLaunchKernelGGL parameters. The dim3 constructor accepts zero to three arguments and will by default initialize unspecified dimensions to 1. See [dim3](#dim3). The kernel uses the coordinate built-ins (thread*, block*, grid*) to determine coordinate index and coordinate bounds of the work item that’s currently executing. See {ref}`coordinate_builtins`.
 
 Please note, HIP does not support kernel launch with total work items defined in dimension with size gridDim x blockDim >= 2^32.
 
@@ -181,6 +126,7 @@ The `__restrict__` keyword tells the compiler that the associated memory pointer
 
 ## Built-In Variables
 
+(coordinate_builtins)=
 ### Coordinate Built-Ins
 Built-ins determine the coordinate of the active work item in the execution grid. They are defined in amd_hip_runtime.h (rather than being implicitly defined by the compiler).
 In HIP, built-ins coordinate variable definitions are the same as in Cuda, for instance:
@@ -277,9 +223,9 @@ Following is the list of supported single precision mathematical functions.
 | float frexpf ( float  x, int* nptr ) <br><sub>Extract mantissa and exponent of a floating-point value.</sub> | ✓ | ✗ |
 | float hypotf ( float  x, float  y ) <br><sub>Calculate the square root of the sum of squares of two arguments.</sub> | ✓ | ✓ |
 | int ilogbf ( float  x ) <br><sub>Compute the unbiased integer exponent of the argument.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup id="a1">[1](#f1)</sup> isfinite ( float  a ) <br><sub>Determine whether argument is finite.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup>[1](#f1)</sup> isinf ( float  a ) <br><sub>Determine whether argument is infinite.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup>[1](#f1)</sup> isnan ( float  a ) <br><sub>Determine whether argument is a NaN.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1] isfinite ( float  a ) <br><sub>Determine whether argument is finite.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1]</sup> isinf ( float  a ) <br><sub>Determine whether argument is infinite.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1]</sup> isnan ( float  a ) <br><sub>Determine whether argument is a NaN.</sub> | ✓ | ✓ |
 | float ldexpf ( float  x, int  exp ) <br><sub>Calculate the value of x ⋅ 2<sup>exp</sup>.</sub> | ✓ | ✓ |
 | float log10f ( float  x ) <br><sub>Calculate the base 10 logarithm of the input argument.</sub> | ✓ | ✓ |
 | float log1pf ( float  x ) <br><sub>Calculate the value of log<sub>e</sub>( 1 + x ).</sub> | ✓ | ✓ |
@@ -294,7 +240,7 @@ Following is the list of supported single precision mathematical functions.
 | float remquof ( float  x, float  y, int* quo ) <br><sub>Compute single-precision floating-point remainder and part of quotient.</sub> | ✓ | ✗ |
 | float roundf ( float  x ) <br><sub>Round to nearest integer value in floating-point.</sub> | ✓ | ✓ |
 | float scalbnf ( float  x, int  n ) <br><sub>Scale floating-point input by integer power of two.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup>[1](#f1)</sup> signbit ( float  a ) <br><sub>Return the sign bit of the input.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1]</sup> signbit ( float  a ) <br><sub>Return the sign bit of the input.</sub> | ✓ | ✓ |
 | void sincosf ( float  x, float* sptr, float* cptr ) <br><sub>Calculate the sine and cosine of the first input argument.</sub> | ✓ | ✗ |
 | float sinf ( float  x ) <br><sub>Calculate the sine of the input argument.</sub> | ✓ | ✓ |
 | float sinhf ( float  x ) <br><sub>Calculate the hyperbolic sine of the input argument.</sub> | ✓ | ✓ |
@@ -338,8 +284,7 @@ Following is the list of supported single precision mathematical functions.
 | float ynf ( int n, float  x ) <br><sub>Calculate the value of the Bessel function of the second kind of order n for the input argument.</sub> | ✓ | ✓ |
 
 
-
-<sub><b id="f1"><sup>[1]</sup></b> __RETURN_TYPE is dependent on compiler. It is usually 'int' for C compilers and 'bool' for C++ compilers.</sub> [↩](#a1)
+[^f1]: __RETURN_TYPE is dependent on compiler. It is usually 'int' for C compilers and 'bool' for C++ compilers.
 
 ### Double Precision Mathematical Functions
 Following is the list of supported double precision mathematical functions.
@@ -374,9 +319,9 @@ Following is the list of supported double precision mathematical functions.
 | double frexp ( double  x, int* nptr ) <br><sub>Extract mantissa and exponent of a floating-point value.</sub> | ✓ | ✗ |
 | double hypot ( double  x, double  y ) <br><sub>Calculate the square root of the sum of squares of two arguments.</sub> | ✓ | ✓ |
 | int ilogb ( double  x ) <br><sub>Compute the unbiased integer exponent of the argument.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup id="a2">[1](#f2)</sup> isfinite ( double  a ) <br><sub>Determine whether argument is finite.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup>[1](#f2)</sup> isinf ( double  a ) <br><sub>Determine whether argument is infinite.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup>[1](#f2)</sup> isnan ( double  a ) <br><sub>Determine whether argument is a NaN.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1] isfinite ( double  a ) <br><sub>Determine whether argument is finite.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1]</sup> isinf ( double  a ) <br><sub>Determine whether argument is infinite.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1]</sup> isnan ( double  a ) <br><sub>Determine whether argument is a NaN.</sub> | ✓ | ✓ |
 | double ldexp ( double  x, int  exp ) <br><sub>Calculate the value of x ⋅ 2<sup>exp</sup>.</sub> | ✓ | ✓ |
 | double log ( double  x ) <br><sub>Calculate the base e logarithm of the input argument.</sub> | ✓ | ✓ |
 | double log10 ( double  x ) <br><sub>Calculate the base 10 logarithm of the input argument.</sub> | ✓ | ✓ |
@@ -391,7 +336,7 @@ Following is the list of supported double precision mathematical functions.
 | double remquo ( double  x, double  y, int* quo ) <br><sub>Compute double-precision floating-point remainder and part of quotient.</sub> | ✓ | ✗ |
 | double round ( double  x ) <br><sub>Round to nearest integer value in floating-point.</sub> | ✓ | ✓ |
 | double scalbn ( double  x, int  n ) <br><sub>Scale floating-point input by integer power of two.</sub> | ✓ | ✓ |
-| __RETURN_TYPE<sup>[1](#f2)</sup> signbit ( double  a ) <br><sub>Return the sign bit of the input.</sub> | ✓ | ✓ |
+| __RETURN_TYPE[^f1] signbit ( double  a ) <br><sub>Return the sign bit of the input.</sub> | ✓ | ✓ |
 | double sin ( double  x ) <br><sub>Calculate the sine of the input argument.</sub> | ✓ | ✓ |
 | void sincos ( double  x, double* sptr, double* cptr ) <br><sub>Calculate the sine and cosine of the first input argument.</sub> | ✓ | ✗ |
 | double sinh ( double  x ) <br><sub>Calculate the hyperbolic sine of the input argument.</sub> | ✓ | ✓ |
@@ -432,10 +377,6 @@ Following is the list of supported double precision mathematical functions.
 | double y1 ( double  x ) <br><sub>Calculate the value of the Bessel function of the second kind of order 1 for the input argument.</sub> | ✓ | ✓ |
 | double yn ( int n, double  x ) <br><sub>Calculate the value of the Bessel function of the second kind of order n for the input argument.</sub> | ✓ | ✓ |
 
-
-
-<sub><b id="f2"><sup>[1]</sup></b> __RETURN_TYPE is dependent on compiler. It is usually 'int' for C compilers and 'bool' for C++ compilers.</sub> [↩](#a2)
-
 ### Integer Intrinsics
 Following is the list of supported integer intrinsics. Note that intrinsics are supported on device only.
 
@@ -447,15 +388,15 @@ Following is the list of supported integer intrinsics. Note that intrinsics are
 | unsigned int __clz(unsigned int x) <br><sub>Return the number of consecutive high-order zero bits in 32 bit unsigned integer.</sub> |
 | int __clzll ( long long int x ) <br><sub>Count the number of consecutive high-order zero bits in a 64 bit integer.</sub> |
 | unsigned int __clzll(long long int x) <br><sub>Return the number of consecutive high-order zero bits in 64 bit signed integer.</sub> |
-| unsigned int __ffs(unsigned int x) <br><sub>Find the position of least signigicant bit set to 1 in a 32 bit unsigned integer.<sup id="a3">[1](#f3)</sup></sub> |
+| unsigned int __ffs(unsigned int x) <br><sub>Find the position of least signigicant bit set to 1 in a 32 bit unsigned integer.[^f3]</sub> |
 | unsigned int __ffs(int x) <br><sub>Find the position of least signigicant bit set to 1 in a 32 bit signed integer.</sub> |
-| unsigned int __ffsll(unsigned long long int x) <br><sub>Find the position of least signigicant bit set to 1 in a 64 bit unsigned integer.<sup>[1](#f3)</sup></sub> |
+| unsigned int __ffsll(unsigned long long int x) <br><sub>Find the position of least signigicant bit set to 1 in a 64 bit unsigned integer.[^f3]</sup></sub> |
 | unsigned int __ffsll(long long int x) <br><sub>Find the position of least signigicant bit set to 1 in a 64 bit signed integer.</sub> |
 | unsigned int __popc ( unsigned int x ) <br><sub>Count the number of bits that are set to 1 in a 32 bit integer.</sub> |
 | unsigned int __popcll ( unsigned long long int x )<br><sub>Count the number of bits that are set to 1 in a 64 bit integer.</sub> |
 | int __mul24 ( int x, int y )<br><sub>Multiply two 24bit integers.</sub> |
 | unsigned int __umul24 ( unsigned int x, unsigned int y )<br><sub>Multiply two 24bit unsigned integers.</sub> |
-<sub><b id="f3"><sup>[1]</sup></b>
+<sub>[^f3]
 The HIP-Clang implementation of __ffs() and __ffsll() contains code to add a constant +1 to produce the ffs result format.
 For the cases where this overhead is not acceptable and programmer is willing to specialize for the platform,
 HIP-Clang provides __lastbit_u32_u32(unsigned int input) and __lastbit_u32_u64(unsigned long long int input).
@@ -612,6 +553,7 @@ Towards this end, HIP has four extra functions to help developers more precisely
 - `double safeAtomicAdd(double* address, double val)`
    - These functions will always produce safe atomic RMW operations, even when `-munsafe-fp-atomics` is set
 
+(warp_cross_lane_functions)=
 ## Warp Cross-Lane Functions
 
 Warp cross-lane functions operate across all lanes in a warp. The hardware guarantees that all warp lanes will execute in lockstep, so additional synchronization is unnecessary, and the instructions use no shared memory.
diff --git a/projects/hip/docs/markdown/hip-math-api.md b/projects/hip/docs/reference/math_api.md
similarity index 100%
rename from projects/hip/docs/markdown/hip-math-api.md
rename to projects/hip/docs/reference/math_api.md
diff --git a/projects/hip/docs/markdown/hip_terms.md b/projects/hip/docs/reference/terms.md
similarity index 100%
rename from projects/hip/docs/markdown/hip_terms.md
rename to projects/hip/docs/reference/terms.md
diff --git a/projects/hip/docs/markdown/hip_faq.md b/projects/hip/docs/user_guide/faq.md
similarity index 76%
rename from projects/hip/docs/markdown/hip_faq.md
rename to projects/hip/docs/user_guide/faq.md
index e4725190c0..ab67cc745f 100644
--- a/projects/hip/docs/markdown/hip_faq.md
+++ b/projects/hip/docs/user_guide/faq.md
@@ -1,43 +1,6 @@
-# FAQ
+# Frequently asked questions
 
-<!-- toc -->
-
-- [What APIs and features does HIP support?](#what-apis-and-features-does-hip-support)
-- [What is not supported?](#what-is-not-supported)
-  * [Runtime/Driver API features](#runtimedriver-api-features)
-  * [Kernel language features](#kernel-language-features)
-- [Is HIP a drop-in replacement for CUDA?](#is-hip-a-drop-in-replacement-for-cuda)
-- [What specific version of CUDA does HIP support?](#what-specific-version-of-cuda-does-hip-support)
-- [What libraries does HIP support?](#what-libraries-does-hip-support)
-- [How does HIP compare with OpenCL?](#how-does-hip-compare-with-opencl)
-- [How does porting CUDA to HIP compare to porting CUDA to OpenCL?](#how-does-porting-cuda-to-hip-compare-to-porting-cuda-to-opencl)
-- [What hardware does HIP support?](#what-hardware-does-hip-support)
-- [Do HIPIFY tools automatically convert all source code?](#do-hipify-tools-automatically-convert-all-source-code)
-- [What is NVCC?](#what-is-nvcc)
-- [What is HIP-Clang?](#what-is-hip-clang)
-- [Why use HIP rather than supporting CUDA directly?](#why-use-hip-rather-than-supporting-cuda-directly)
-- [Can I develop HIP code on an Nvidia CUDA platform?](#can-i-develop-hip-code-on-an-nvidia-cuda-platform)
-- [Can I develop HIP code on an AMD HIP-Clang platform?](#can-i-develop-hip-code-on-an-amd-hip-clang-platform)
-- [What is ROCclr?](#what-is-rocclr)
-- [What is hipamd?](#what-is-hipamd)
-- [Can a HIP binary run on both AMD and Nvidia platforms?](#can-a-hip-binary-run-on-both-amd-and-nvidia-platforms)
-- [On HIP-Clang, can I link HIP code with host code compiled with another compiler such as gcc, icc, or clang?](#on-HIP-Clang-can-i-link-hip-code-with-host-code-compiled-with-another-compiler-such-as-gcc-icc-or-clang-)
-- [HIP detected my platform (hip-clang vs nvcc) incorrectly - what should I do?](#hip-detected-my-platform-hip-clang-vs-nvcc-incorrectly---what-should-i-do)
-- [Can I install both CUDA SDK and HIP-clang on same machine?](#can-i-install-both-cuda-sdk-and-hip-clang-on-same-machine)
-- [On CUDA, can I mix CUDA code with HIP code?](#on-cuda-can-i-mix-cuda-code-with-hip-code)
-- [How do I trace HIP application flow?](#how-do-i-trace-hip-application-flow)
-- [What if HIP generates an error of "symbol multiply defined!" only on AMD machine?](#what-if-hip-generates-error-of-symbol-multiply-defined-only-on-amd-machine)
-- [What is maximum limit of Generic kernel launching parameter?](#what-is-maximum-limit-of-generic-kernel-launching-parameter)
-- [Are _shfl_*_sync functions supported on HIP platform?](#are-_shfl_*_sync-functions-supported-on-hip-platform)
-- [How to create a guard for code that is specific to the host or the GPU?](#how-to-create-a-guard-for-code-that-is-specific-to-the-host-or-the-gpu)
-- [Why _OpenMP is undefined when compiling with -fopenmp?](#why-_openmp-is-undefined-when-compiling-with--fopenmp)
-- [Does the HIP-Clang compiler support extern shared declarations?](#does-the-hip-clang-compiler-support-extern-shared-declarations)
-- [I have multiple HIP enabled devices and I am getting an error message hipErrorNoBinaryForGpu: Unable to find code object for all current devices?](#i-have-multiple-hip-enabled-devices-and-i-am-getting-an-error-message-hipErrorNoBinaryForGpu-unable-to-find-code-object-for-all-current-devices)
-- [How to use per-thread default stream in HIP?](#how-to-use-per-thread-default-stream-in-hip)
-- [How can I know the version of HIP?](#how-can-I-know-the-version-of-hip)
-<!-- tocstop -->
-
-### What APIs and features does HIP support?
+## What APIs and features does HIP support?
 HIP provides the following:
 - Devices (hipSetDevice(), hipGetDeviceProperties(), etc.)
 - Memory management (hipMalloc(), hipMemcpy(), hipFree(), etc.)
@@ -52,9 +15,9 @@ HIP provides the following:
 
 The HIP API documentation describes each API and its limitations, if any, compared with the equivalent CUDA API.
 
-### What is not supported?
+## What is not supported?
 
-#### Runtime/Driver API features
+### Runtime/Driver API features
 At a high-level, the following features are not supported:
 - Textures (partial support available)
 - Dynamic parallelism (CUDA 5.0)
@@ -65,20 +28,20 @@ At a high-level, the following features are not supported:
 
 See the [API Support Table](CUDA_Runtime_API_functions_supported_by_HIP.md) for more detailed information.
 
-#### Kernel language features
+### Kernel language features
 - C++-style device-side dynamic memory allocations (free, new, delete) (CUDA 4.0)
 - Virtual functions, indirect functions and try/catch (CUDA 4.0)
 - `__prof_trigger`
 - PTX assembly (CUDA 4.0).  HIP-Clang supports inline GCN assembly.
-- Several kernel features are under development.  See the [HIP Kernel Language](hip_kernel_language.md) for more information.
+- Several kernel features are under development.  See the {doc}`/reference/kernel_language` for more information.
 
 
-### Is HIP a drop-in replacement for CUDA?
+## Is HIP a drop-in replacement for CUDA?
 No. HIP provides porting tools which do most of the work to convert CUDA code into portable C++ code that uses the HIP APIs.
 Most developers will port their code from CUDA to HIP and then maintain the HIP version.
 HIP code provides the same performance as native CUDA code, plus the benefits of running on AMD platforms.
 
-### What specific version of CUDA does HIP support?
+## What specific version of CUDA does HIP support?
 HIP APIs and features do not map to a specific CUDA version. HIP provides a strong subset of the functionality provided in CUDA, and the hipify tools can scan code to identify any unsupported CUDA functions - this is useful for identifying the specific features required by a given application.
 
 However, we can provide a rough summary of the features included in each CUDA SDK and the support level in HIP. Each bullet below lists the major new language features in each CUDA release and then indicate which are supported/not supported in HIP:
@@ -104,7 +67,7 @@ However, we can provide a rough summary of the features included in each CUDA SD
 - CUDA 9.0 :
     - Cooperative Launch, Surface Object Management, Version Management
 
-### What libraries does HIP support?
+## What libraries does HIP support?
 HIP includes growing support for the four key math libraries using hipBlas, hipFFt, hipRAND and hipSPARSE, as well as MIOpen for machine intelligence applications.
 These offer pointer-based memory interfaces (as opposed to opaque buffers) and can be easily interfaced with other HIP applications.
 The hip interfaces support both ROCm and CUDA paths, with familiar library interfaces.
@@ -117,7 +80,7 @@ The hip interfaces support both ROCm and CUDA paths, with familiar library inter
 
 Additionally, some of the cublas routines are automatically converted to hipblas equivalents by the HIPIFY tools. These APIs use cublas or hcblas depending on the platform and replace the need to use conditional compilation.
 
-### How does HIP compare with OpenCL?
+## How does HIP compare with OpenCL?
 Both AMD and Nvidia support OpenCL 1.2 on their devices so that developers can write portable code.
 HIP offers several benefits over OpenCL:
 - Developers can code in C++ as well as mix host and device C++ code in their source files. HIP C++ code can use templates, lambdas, classes and so on.
@@ -128,7 +91,7 @@ HIP offers several benefits over OpenCL:
 - HIP provides device-level control over memory allocation and placement.
 - HIP offers an offline compilation model.
 
-### How does porting CUDA to HIP compare to porting CUDA to OpenCL?
+## How does porting CUDA to HIP compare to porting CUDA to OpenCL?
 Both HIP and CUDA are dialects of C++, and thus porting between them is relatively straightforward.
 Both dialects support templates, classes, lambdas, and other C++ constructs.
 As one example, the hipify-perl tool was originally a Perl script that used simple text conversions from CUDA to HIP.
@@ -139,39 +102,39 @@ There have been several tools that have attempted to convert CUDA into OpenCL, s
 As a result, the OpenCL syntax is different from CUDA, and the porting tools have to perform some heroic transformations to bridge this gap.
 The tools also struggle with more complex CUDA applications, in particular, those that use templates, classes, or other C++ features inside the kernel.
 
-### What hardware does HIP support?
+## What hardware does HIP support?
 - For AMD platforms, see the [ROCm documentation](https://github.com/RadeonOpenCompute/ROCm#supported-gpus) for the list of supported platforms.
 - For Nvidia platforms, HIP requires Unified Memory and should run on any device supporting CUDA SDK 6.0 or newer. We have tested the Nvidia Titan and Tesla K40.
 
-### Do HIPIFY tools automatically convert all source code?
+## Do HIPIFY tools automatically convert all source code?
 Typically, HIPIFY tools can automatically convert almost all run-time code.
 Most device code needs no additional conversion since HIP and CUDA have similar names for math and built-in functions.
 The hipify-clang tool will automatically modify the kernel signature as needed (automating a step that used to be done manually).
 Additional porting may be required to deal with architecture feature queries or with CUDA capabilities that HIP doesn't support.
 In general, developers should always expect to perform some platform-specific tuning and optimization.
 
-### What is NVCC?
+## What is NVCC?
 NVCC is Nvidia's compiler driver for compiling "CUDA C++" code into PTX or device code for Nvidia GPUs. It's a closed-source binary compiler that is provided by the CUDA SDK.
 
-### What is HIP-Clang?
+## What is HIP-Clang?
 HIP-Clang is a Clang/LLVM based compiler to compile HIP programs which can run on AMD platform.
 
-### Why use HIP rather than supporting CUDA directly?
+## Why use HIP rather than supporting CUDA directly?
 While HIP is a strong subset of the CUDA, it is a subset.  The HIP layer allows that subset to be clearly defined and documented.
 Developers who code to the HIP API can be assured their code will remain portable across Nvidia and AMD platforms.
 In addition, HIP defines portable mechanisms to query architectural features and supports a larger 64-bit wavesize which expands the return type for cross-lane functions like ballot and shuffle from 32-bit ints to 64-bit ints.
 
-### Can I develop HIP code on an Nvidia CUDA platform?
+## Can I develop HIP code on an Nvidia CUDA platform?
 Yes.  HIP's CUDA path only exposes the APIs and functionality that work on both NVCC and AMDGPU back-ends.
 "Extra" APIs, parameters, and features which exist in CUDA but not in HIP-Clang will typically result in compile-time or run-time errors.
 Developers need to use the HIP API for most accelerator code and bracket any CUDA-specific code with preprocessor conditionals.
 Developers concerned about portability should, of course, run on both platforms, and should expect to tune for performance.
 In some cases, CUDA has a richer set of modes for some APIs, and some C++ capabilities such as virtual functions - see the HIP @API documentation for more details.
 
-### Can I develop HIP code on an AMD HIP-Clang platform?
+## Can I develop HIP code on an AMD HIP-Clang platform?
 Yes. HIP's HIP-Clang path only exposes the APIs and functions that work on AMD runtime back ends. "Extra" APIs, parameters and features that appear in HIP-Clang but not CUDA will typically cause compile- or run-time errors. Developers must use the HIP API for most accelerator code and bracket any HIP-Clang specific code with preprocessor conditionals. Those concerned about portability should, of course, test their code on both platforms and should tune it for performance. Typically, HIP-Clang supports a more modern set of C++11/C++14/C++17 features, so HIP developers who want portability should be careful when using advanced C++ features on the HIP-Clang path.
 
-### How to use HIP-Clang to build HIP programs?
+## How to use HIP-Clang to build HIP programs?
 The environment variable can be used to set compiler path:
 - HIP_CLANG_PATH: path to hip-clang. When set, this variable let hipcc to use hip-clang for compilation/linking.
 
@@ -179,26 +142,26 @@ There is an alternative environment variable to set compiler path:
 - HIP_ROCCLR_HOME: path to root directory of the HIP-ROCclr runtime. When set, this variable let hipcc use hip-clang from the ROCclr distribution.
 NOTE: If HIP_ROCCLR_HOME is set, there is no need to set HIP_CLANG_PATH since hipcc will deduce them from HIP_ROCCLR_HOME.
 
-### What is ROCclr?
+## What is ROCclr?
 ROCclr (Radeon Open Compute Common Language Runtime) is a virtual device interface that compute runtimes interact with backends such as ROCr on Linux, as well as PAL on Windows.
 
-### What is HIPAMD?
+## What is HIPAMD?
 HIPAMD is a repository branched out from HIP, mainly the implementation for AMD GPU.
 
-### Can a HIP binary run on both AMD and Nvidia platforms?
+## Can a HIP binary run on both AMD and Nvidia platforms?
 HIP is a source-portable language that can be compiled to run on either AMD or NVIDIA platform. HIP tools don't create a "fat binary" that can run on either platform, however.
 
-### On HIP-Clang, can I link HIP code with host code compiled with another compiler such as gcc, icc, or clang ?
+## On HIP-Clang, can I link HIP code with host code compiled with another compiler such as gcc, icc, or clang ?
 Yes.  HIP generates the object code which conforms to the GCC ABI, and also links with libstdc++.  This means you can compile host code with the compiler of your choice and link the generated object code
 with GPU code compiled with HIP.  Larger projects often contain a mixture of accelerator code (initially written in CUDA with nvcc) and host code (compiled with gcc, icc, or clang).   These projects
 can convert the accelerator code to HIP, compile that code with hipcc, and link with object code from their preferred compiler.
 
 
-### Can I install both CUDA SDK and HIP-Clang on the same machine?
+## Can I install both CUDA SDK and HIP-Clang on the same machine?
 Yes. You can use HIP_PLATFORM to choose which path hipcc targets.  This configuration can be useful when using HIP to develop an application which is portable to both AMD and NVIDIA.
 
 
-### HIP detected my platform (HIP-Clang vs nvcc) incorrectly - what should I do?
+## HIP detected my platform (HIP-Clang vs nvcc) incorrectly - what should I do?
 HIP will set the platform to AMD and use HIP-Clang as compiler if it sees that the AMD graphics driver is installed and has detected an AMD GPU.
 Sometimes this isn't what you want - you can force HIP to recognize the platform by setting the following,
 ```
@@ -218,7 +181,7 @@ HIP_RUNTIME=nvcc
 
 One symptom of this problem is the message "error: 'unknown error'(11) at square.hipref.cpp:56".  This can occur if you have a CUDA installation on an AMD platform, and HIP incorrectly detects the platform as nvcc.  HIP may be able to compile the application using the nvcc tool-chain but will generate this error at runtime since the platform does not have a CUDA device.
 
-### On CUDA, can I mix CUDA code with HIP code?
+## On CUDA, can I mix CUDA code with HIP code?
 Yes.  Most HIP data structures (hipStream_t, hipEvent_t) are typedefs to CUDA equivalents and can be intermixed.  Both CUDA and HIP use integer device ids.
 One notable exception is that hipError_t is a new type, and cannot be used where a cudaError_t is expected.  In these cases, refactor the code to remove the expectation.  Alternatively, hip_runtime_api.h defines functions which convert between the error code spaces:
 
@@ -228,30 +191,30 @@ hipCUResultTohipError
 
 If platform portability is important, use #ifdef __HIP_PLATFORM_NVIDIA__ to guard the CUDA-specific code.
 
-### How do I trace HIP application flow?
-See the [HIP Logging](hip_logging.md) for more information.
+## How do I trace HIP application flow?
+See {doc}`/developer_guide/logging` for more information.
 
-### What is maximum limit of kernel launching parameter?
+## What is maximum limit of kernel launching parameter?
 Product of block.x, block.y, and block.z should be less than 1024.
 Please note, HIP does not support kernel launch with total work items defined in dimension with size gridDim x blockDim >= 2^32, so gridDim.x * blockDim.x, gridDim.y * blockDim.y and gridDim.z * blockDim.z are always less than 2^32.
 
-### Are __shfl_*_sync functions supported on HIP platform?
+## Are __shfl_*_sync functions supported on HIP platform?
 __shfl_*_sync is not supported on HIP but for nvcc path CUDA 9.0 and above all shuffle calls get redirected to it's sync version.
 
-### How to create a guard for code that is specific to the host or the GPU?
+## How to create a guard for code that is specific to the host or the GPU?
 The compiler defines the `__HIP_DEVICE_COMPILE__` macro only when compiling the code for the GPU.  It could be used to guard code that is specific to the host or the GPU.
 
-### Why _OpenMP is undefined when compiling with -fopenmp?
+## Why _OpenMP is undefined when compiling with -fopenmp?
 When compiling an OpenMP source file with `hipcc -fopenmp`, the compiler may generate error if there is a reference to the `_OPENMP` macro.  This is due to a limitation in hipcc that treats any source file type (e.g., `.cpp`) as an HIP translation unit leading to some conflicts with the OpenMP language switch.  If the OpenMP source file doesn't contain any HIP language construct, you could workaround this issue by adding the `-x c++` switch to force the compiler to treat the file as regular C++.  Another approach would be to guard the OpenMP code with `#ifdef _OPENMP` so that the code block is disabled when compiling for the GPU.  The `__HIP_DEVICE_COMPILE__` macro defined by the HIP compiler when compiling GPU code could also be used for guarding code paths specific to the host or the GPU.
 
-### Does the HIP-Clang compiler support extern shared declarations?
+## Does the HIP-Clang compiler support extern shared declarations?
 
 Previously, it was essential 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[];
 
-### I have multiple HIP enabled devices and I am getting an error message hipErrorNoBinaryForGpu Unable to find code object for all current devices?
+## I have multiple HIP enabled devices and I am getting an error message hipErrorNoBinaryForGpu Unable to find code object for all current devices?
 
 This error message is seen due to the fact that you do not have valid code object for all of your devices.
 
@@ -262,7 +225,7 @@ If you have a precompiled application/library (like rocblas, tensorflow etc) whi
  - The application/library does not ship code object bundles for *all* of your device(s): in this case you need to recompile the application/library yourself with correct `--offload-arch`.
  - The application/library does not ship code object bundles for *some* of your device(s), for example you have a system with an APU + GPU and the library does not ship code objects for your APU. For this you can set the environment variable `HIP_VISIBLE_DEVICES` to only enable GPUs for which code object is available. This will limit the GPUs visible to your application and allow it to run.
 
-### How to use per-thread default stream in HIP?
+## How to use per-thread default stream in HIP?
 
 The per-thread default stream is an implicit stream local to both the thread and the current device. It does not do any implicit synchronization with other streams (like explicitly created streams), or default per-thread stream on other threads.
 
@@ -274,7 +237,7 @@ Once source is compiled with per-thread default stream enabled, all APIs will be
 
 Besides, per-thread default stream be enabled per translation unit, users can compile some files with feature enabled and some with feature disabled. Feature enabled translation unit will have default stream as per thread and there will not be any implicit synchronization done but other modules will have legacy default stream which will do implicit synchronization.
 
-### How can I know the version of HIP?
+## How can I know the version of HIP?
 
 HIP version definition has been updated since ROCm 4.2 release as the following:
 
diff --git a/projects/hip/docs/markdown/hip_rtc.md b/projects/hip/docs/user_guide/hip_rtc.md
similarity index 100%
rename from projects/hip/docs/markdown/hip_rtc.md
rename to projects/hip/docs/user_guide/hip_rtc.md
diff --git a/projects/hip/docs/markdown/hip_programming_guide.md b/projects/hip/docs/user_guide/programming_manual.md
similarity index 99%
rename from projects/hip/docs/markdown/hip_programming_guide.md
rename to projects/hip/docs/user_guide/programming_manual.md
index 80b50b96e5..012a6a24f0 100644
--- a/projects/hip/docs/markdown/hip_programming_guide.md
+++ b/projects/hip/docs/user_guide/programming_manual.md
@@ -1,4 +1,4 @@
-# HIP Programming Guide
+# HIP Programming Manual
 
 ## Host Memory
 
@@ -189,5 +189,3 @@ Here is an example to create and use static libraries:
     ```
 
 For more information, please see samples/2_Cookbook/15_static_library/host_functions and samples/2_Cookbook/15_static_library/device_functions.
-
-## [Supported Clang Options](clang_options.md)

From 802f97c971eeb99727ed5d4f0972448e5aefb876 Mon Sep 17 00:00:00 2001
From: Maneesh Gupta <maneesh.gupta@amd.com>
Date: Fri, 21 Apr 2023 15:48:03 +0530
Subject: [PATCH 2/3] Update Jenkinsfile to build tests against clr (#3205)

[ROCm/hip commit: 54d79967700cecdbe687493e5cf31e6f577fd067]
---
 projects/hip/.jenkins/Jenkinsfile | 73 ++++++++++++++-----------------
 1 file changed, 34 insertions(+), 39 deletions(-)

diff --git a/projects/hip/.jenkins/Jenkinsfile b/projects/hip/.jenkins/Jenkinsfile
index 651bffad93..ba9161c5b2 100644
--- a/projects/hip/.jenkins/Jenkinsfile
+++ b/projects/hip/.jenkins/Jenkinsfile
@@ -1,6 +1,6 @@
 def hipBuildTest(String backendLabel) {
         node(backendLabel) {
-          stage("Source sync ${backendLabel}") {
+          stage("SYNC - ${backendLabel}") {
 
             // Checkout hip repository with the PR patch
             dir("${WORKSPACE}/hip") {
@@ -8,35 +8,25 @@ def hipBuildTest(String backendLabel) {
                env.HIP_DIR = "${WORKSPACE}" + "/hip"
             }
 
-            // Clone hipamd repository
-            dir("${WORKSPACE}/hipamd") {
-              git branch: 'develop',
-              url: 'https://github.com/ROCm-Developer-Tools/hipamd'
-              env.HIPAMD_DIR = "${WORKSPACE}" + "/hipamd"
-            }
-            
+            // Clone hip-tests repository
             dir("${WORKSPACE}/hip-tests") {
               git branch: 'develop',
               url: 'https://github.com/ROCm-Developer-Tools/hip-tests'
+              env.HIP_TESTS_DIR = "${WORKSPACE}" + "/hip-tests"
             }
 
-            // Clone vdi and opencl for only amd backend server
-            if (backendLabel =~ /.*amd.*/) {  
-               dir("${WORKSPACE}/ROCm-OpenCL-Runtime") {
-                   git branch:'develop',
-                   url: 'https://github.com/RadeonOpenCompute/ROCm-OpenCL-Runtime'
-                   env.OPENCL_DIR = "${WORKSPACE}" + "/ROCm-OpenCL-Runtime"
-               }
-               dir("${WORKSPACE}/ROCclr") {
-                   git branch:'develop',
-                   url: 'https://github.com/ROCm-Developer-Tools/ROCclr'
-                   env.ROCclr_DIR = "${WORKSPACE}" + "/ROCclr"
-               }
+            // Clone clr repository
+            dir("${WORKSPACE}/clr") {
+              git branch: 'develop',
+              credentialsId: 'branch-credentials',
+              url: 'https://github.com/ROCm-Developer-Tools/clr'
+              env.CLR_DIR = "${WORKSPACE}" + "/clr"
             }
         }
-        stage("Build - HIT framework ${backendLabel}") {
-            // Running the build on hipamd workspace
-            dir("${WORKSPACE}/hipamd") {
+
+        stage("BUILD - HIT ${backendLabel}") {
+            // Running the build on clr workspace
+            dir("${WORKSPACE}/clr") {
                 sh  """#!/usr/bin/env bash
                     set -x
                     rm -rf build
@@ -44,22 +34,24 @@ def hipBuildTest(String backendLabel) {
                     cd build
                     # Check if backend label contains string "amd" or backend host is a server with amd gpu
                     if [[ $backendLabel =~ amd ]]; then
-                        cmake -DHIP_CATCH_TEST=0 -DHIP_COMMON_DIR=$HIP_DIR -DAMD_OPENCL_PATH=\$OPENCL_DIR -DROCCLR_PATH=\$ROCclr_DIR -DCMAKE_PREFIX_PATH="/opt/rocm/" -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
+                        cmake -DCLR_BUILD_HIP=ON -DHIP_CATCH_TEST=0 -DHIP_COMMON_DIR=$HIP_DIR -DCMAKE_PREFIX_PATH="/opt/rocm/" -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
                     else
-                        cmake -DHIP_CATCH_TEST=0 -DHIP_PLATFORM=nvidia -DHIP_COMMON_DIR=$HIP_DIR -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
+                        cmake -DCLR_BUILD_HIP=ON -DHIP_CATCH_TEST=0 -DHIP_PLATFORM=nvidia -DHIP_COMMON_DIR=$HIP_DIR -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
                     fi
-                    make install  -j\$(nproc)
+                    make -j\$(nproc)
+                    make install -j\$(nproc)
                     if [[ $backendLabel =~ amd ]]; then
-                        make build_tests  -j\$(nproc)
+                        make build_tests -j\$(nproc)
                     else
                         HIP_COMPILER=nvcc HIP_PLATFORM=nvidia make build_tests -j\$(nproc)
                     fi
                     """
             }
         }
+
         timeout(time: 1, unit: 'HOURS') {
-            stage("HIP Unit Tests - HIT framework ${backendLabel}") {
-                dir("${WORKSPACE}/hipamd/build") {
+            stage("TEST - HIT ${backendLabel}") {
+                dir("${WORKSPACE}/clr/build/hipamd") {
                     sh  """#!/usr/bin/env bash
                         set -x
                         # Check if backend label contains string "amd" or backend host is a server with amd gpu
@@ -73,28 +65,30 @@ def hipBuildTest(String backendLabel) {
                 }
             }
         }
-        stage("Build - Catch2 framework") {
-            // Running the build on hipamd workspace
-            dir("${WORKSPACE}/hipamd") {
+
+        stage("BUILD HIP - ${backendLabel}") {
+            // Running the build on clr workspace
+            dir("${WORKSPACE}/clr") {
                 sh  """#!/usr/bin/env bash
                     set -x
+                    rm -rf build
                     mkdir -p build
                     cd build
                     # Check if backend label contains string "amd" or backend host is a server with amd gpu
                     if [[ $backendLabel =~ amd ]]; then
-                        cmake -DHIP_PATH=\$PWD/install -DHIP_COMMON_DIR=\$HIP_DIR -DAMD_OPENCL_PATH=\$OPENCL_DIR -DROCCLR_PATH=\$ROCclr_DIR -DCMAKE_PREFIX_PATH="/opt/rocm/" -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
+                        cmake -DCLR_BUILD_HIP=ON -DHIP_PATH=\$PWD/install -DHIP_COMMON_DIR=\$HIP_DIR -DCMAKE_PREFIX_PATH="/opt/rocm/" -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
                     else
-                        cmake -DHIP_PLATFORM=nvidia -DHIP_COMMON_DIR=\$HIP_DIR -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
+                        cmake -DCLR_BUILD_HIP=ON -DHIP_PLATFORM=nvidia -DHIP_COMMON_DIR=\$HIP_DIR -DCMAKE_INSTALL_PREFIX=\$PWD/install ..
                     fi
                     make -j\$(nproc)
                     make install  -j\$(nproc)
                     """
             }
         }
-        stage("Build - HIP TESTS") {
+        stage("BUILD HIP TESTS - ${backendLabel}") {
             // Running the build on HIP TESTS workspace
             dir("${WORKSPACE}/hip-tests") {
-                env.HIP_PATH = "${HIPAMD_DIR}" + "/build/install"
+                env.HIP_PATH = "${CLR_DIR}" + "/build/install"
                 sh  """#!/usr/bin/env bash
                     set -x
                     rm -rf build
@@ -112,16 +106,17 @@ def hipBuildTest(String backendLabel) {
                     """
             }
         }
+
         timeout(time: 1, unit: 'HOURS') {
-            stage('HIP Unit Tests - Catch2 framework') {
+            stage("TEST - CATCH2 ${backendLabel}") {
                 dir("${WORKSPACE}/hip-tests") {
                     sh  """#!/usr/bin/env bash
                         set -x
                         cd build
                     if [[ $backendLabel =~ amd ]]; then
-                        ctest
+                        ctest --overwrite BuildDirectory=. --output-junit hiptest_output_catch_amd.xml
                     else
-                        ctest -E 'Unit_hipMemcpyHtoD_Positive_Synchronization_Behavior|Unit_hipMemcpy_Positive_Synchronization_Behavior|Unit_hipFreeNegativeHost'
+                        ctest --overwrite BuildDirectory=. --output-junit hiptest_output_catch_nvidia.xml -E 'Unit_hipMemcpyHtoD_Positive_Synchronization_Behavior|Unit_hipMemcpy_Positive_Synchronization_Behavior|Unit_hipFreeNegativeHost'
                     fi
                     """
                }

From fd98ca392d6f64e34001cae6cd6ac5d13634261d Mon Sep 17 00:00:00 2001
From: Saad Rahim <44449863+saadrahim@users.noreply.github.com>
Date: Tue, 2 May 2023 15:54:02 -0600
Subject: [PATCH 3/3] Restoring doxygen files (#3221)

[ROCm/hip commit: 02b84f231d463a3da3c8365ec89d4738dd313204]
---
 projects/hip/docs/doxygen-input/doxy.cfg     | 2550 ++++++++++++++++++
 projects/hip/docs/doxygen-input/mainpage.txt |   19 +
 projects/hip/docs/doxygen-input/sync.txt     |   49 +
 3 files changed, 2618 insertions(+)
 create mode 100644 projects/hip/docs/doxygen-input/doxy.cfg
 create mode 100644 projects/hip/docs/doxygen-input/mainpage.txt
 create mode 100644 projects/hip/docs/doxygen-input/sync.txt

diff --git a/projects/hip/docs/doxygen-input/doxy.cfg b/projects/hip/docs/doxygen-input/doxy.cfg
new file mode 100644
index 0000000000..16c2c900b6
--- /dev/null
+++ b/projects/hip/docs/doxygen-input/doxy.cfg
@@ -0,0 +1,2550 @@
+# Doxyfile 1.8.17
+
+# This file describes the settings to be used by the documentation system
+# doxygen (www.doxygen.org) for a project.
+#
+# All text after a double hash (##) is considered a comment and is placed in
+# front of the TAG it is preceding.
+#
+# All text after a single hash (#) is considered a comment and will be ignored.
+# The format is:
+# TAG = value [value, ...]
+# For lists, items can also be appended using:
+# TAG += value [value, ...]
+# Values that contain spaces should be placed between quotes (\" \").
+
+#---------------------------------------------------------------------------
+# Project related configuration options
+#---------------------------------------------------------------------------
+
+# This tag specifies the encoding used for all characters in the configuration
+# file that follow. The default is UTF-8 which is also the encoding used for all
+# text before the first occurrence of this tag. Doxygen uses libiconv (or the
+# iconv built into libc) for the transcoding. See
+# https://www.gnu.org/software/libiconv/ for the list of possible encodings.
+# The default value is: UTF-8.
+
+DOXYFILE_ENCODING      = UTF-8
+
+# The PROJECT_NAME tag is a single word (or a sequence of words surrounded by
+# double-quotes, unless you are using Doxywizard) that should identify the
+# project for which the documentation is generated. This name is used in the
+# title of most generated pages and in a few other places.
+# The default value is: My Project.
+
+PROJECT_NAME           = "HIP: Heterogenous-computing Interface for Portability"
+
+# The PROJECT_NUMBER tag can be used to enter a project or revision number. This
+# could be handy for archiving the generated documentation or if some version
+# control system is used.
+
+PROJECT_NUMBER         =
+
+# Using the PROJECT_BRIEF tag one can provide an optional one line description
+# for a project that appears at the top of each page and should give viewer a
+# quick idea about the purpose of the project. Keep the description short.
+
+PROJECT_BRIEF          =
+
+# With the PROJECT_LOGO tag one can specify a logo or an icon that is included
+# in the documentation. The maximum height of the logo should not exceed 55
+# pixels and the maximum width should not exceed 200 pixels. Doxygen will copy
+# the logo to the output directory.
+
+PROJECT_LOGO           =
+
+# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path
+# into which the generated documentation will be written. If a relative path is
+# entered, it will be relative to the location where doxygen was started. If
+# left blank the current directory will be used.
+
+OUTPUT_DIRECTORY       = RuntimeAPI
+
+# If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub-
+# directories (in 2 levels) under the output directory of each output format and
+# will distribute the generated files over these directories. Enabling this
+# option can be useful when feeding doxygen a huge amount of source files, where
+# putting all generated files in the same directory would otherwise causes
+# performance problems for the file system.
+# The default value is: NO.
+
+CREATE_SUBDIRS         = NO
+
+# If the ALLOW_UNICODE_NAMES tag is set to YES, doxygen will allow non-ASCII
+# characters to appear in the names of generated files. If set to NO, non-ASCII
+# characters will be escaped, for example _xE3_x81_x84 will be used for Unicode
+# U+3044.
+# The default value is: NO.
+
+ALLOW_UNICODE_NAMES    = NO
+
+# The OUTPUT_LANGUAGE tag is used to specify the language in which all
+# documentation generated by doxygen is written. Doxygen will use this
+# information to generate all constant output in the proper language.
+# Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Catalan, Chinese,
+# Chinese-Traditional, Croatian, Czech, Danish, Dutch, English (United States),
+# Esperanto, Farsi (Persian), Finnish, French, German, Greek, Hungarian,
+# Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages),
+# Korean, Korean-en (Korean with English messages), Latvian, Lithuanian,
+# Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, Romanian, Russian,
+# Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, Swedish, Turkish,
+# Ukrainian and Vietnamese.
+# The default value is: English.
+
+OUTPUT_LANGUAGE        = English
+
+# The OUTPUT_TEXT_DIRECTION tag is used to specify the direction in which all
+# documentation generated by doxygen is written. Doxygen will use this
+# information to generate all generated output in the proper direction.
+# Possible values are: None, LTR, RTL and Context.
+# The default value is: None.
+
+OUTPUT_TEXT_DIRECTION  = None
+
+# If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member
+# descriptions after the members that are listed in the file and class
+# documentation (similar to Javadoc). Set to NO to disable this.
+# The default value is: YES.
+
+BRIEF_MEMBER_DESC      = YES
+
+# If the REPEAT_BRIEF tag is set to YES, doxygen will prepend the brief
+# description of a member or function before the detailed description
+#
+# Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the
+# brief descriptions will be completely suppressed.
+# The default value is: YES.
+
+REPEAT_BRIEF           = YES
+
+# This tag implements a quasi-intelligent brief description abbreviator that is
+# used to form the text in various listings. Each string in this list, if found
+# as the leading text of the brief description, will be stripped from the text
+# and the result, after processing the whole list, is used as the annotated
+# text. Otherwise, the brief description is used as-is. If left blank, the
+# following values are used ($name is automatically replaced with the name of
+# the entity):The $name class, The $name widget, The $name file, is, provides,
+# specifies, contains, represents, a, an and the.
+
+ABBREVIATE_BRIEF       = "The $name class" \
+                         "The $name widget" \
+                         "The $name file" \
+                         is \
+                         provides \
+                         specifies \
+                         contains \
+                         represents \
+                         a \
+                         an \
+                         the
+
+# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then
+# doxygen will generate a detailed section even if there is only a brief
+# description.
+# The default value is: NO.
+
+ALWAYS_DETAILED_SEC    = NO
+
+# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all
+# inherited members of a class in the documentation of that class as if those
+# members were ordinary class members. Constructors, destructors and assignment
+# operators of the base classes will not be shown.
+# The default value is: NO.
+
+INLINE_INHERITED_MEMB  = NO
+
+# If the FULL_PATH_NAMES tag is set to YES, doxygen will prepend the full path
+# before files name in the file list and in the header files. If set to NO the
+# shortest path that makes the file name unique will be used
+# The default value is: YES.
+
+FULL_PATH_NAMES        = YES
+
+# The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path.
+# Stripping is only done if one of the specified strings matches the left-hand
+# part of the path. The tag can be used to show relative paths in the file list.
+# If left blank the directory from which doxygen is run is used as the path to
+# strip.
+#
+# Note that you can specify absolute paths here, but also relative paths, which
+# will be relative from the directory where doxygen is started.
+# This tag requires that the tag FULL_PATH_NAMES is set to YES.
+
+STRIP_FROM_PATH        =
+
+# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the
+# path mentioned in the documentation of a class, which tells the reader which
+# header file to include in order to use a class. If left blank only the name of
+# the header file containing the class definition is used. Otherwise one should
+# specify the list of include paths that are normally passed to the compiler
+# using the -I flag.
+
+STRIP_FROM_INC_PATH    =
+
+# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter (but
+# less readable) file names. This can be useful is your file systems doesn't
+# support long names like on DOS, Mac, or CD-ROM.
+# The default value is: NO.
+
+SHORT_NAMES            = NO
+
+# If the JAVADOC_AUTOBRIEF tag is set to YES then doxygen will interpret the
+# first line (until the first dot) of a Javadoc-style comment as the brief
+# description. If set to NO, the Javadoc-style will behave just like regular Qt-
+# style comments (thus requiring an explicit @brief command for a brief
+# description.)
+# The default value is: NO.
+
+JAVADOC_AUTOBRIEF      = NO
+
+# If the JAVADOC_BANNER tag is set to YES then doxygen will interpret a line
+# such as
+# /***************
+# as being the beginning of a Javadoc-style comment "banner". If set to NO, the
+# Javadoc-style will behave just like regular comments and it will not be
+# interpreted by doxygen.
+# The default value is: NO.
+
+JAVADOC_BANNER         = NO
+
+# If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first
+# line (until the first dot) of a Qt-style comment as the brief description. If
+# set to NO, the Qt-style will behave just like regular Qt-style comments (thus
+# requiring an explicit \brief command for a brief description.)
+# The default value is: NO.
+
+QT_AUTOBRIEF           = NO
+
+# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make doxygen treat a
+# multi-line C++ special comment block (i.e. a block of //! or /// comments) as
+# a brief description. This used to be the default behavior. The new default is
+# to treat a multi-line C++ comment block as a detailed description. Set this
+# tag to YES if you prefer the old behavior instead.
+#
+# Note that setting this tag to YES also means that rational rose comments are
+# not recognized any more.
+# The default value is: NO.
+
+MULTILINE_CPP_IS_BRIEF = NO
+
+# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the
+# documentation from any documented member that it re-implements.
+# The default value is: YES.
+
+INHERIT_DOCS           = YES
+
+# If the SEPARATE_MEMBER_PAGES tag is set to YES then doxygen will produce a new
+# page for each member. If set to NO, the documentation of a member will be part
+# of the file/class/namespace that contains it.
+# The default value is: NO.
+
+SEPARATE_MEMBER_PAGES  = NO
+
+# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen
+# uses this value to replace tabs by spaces in code fragments.
+# Minimum value: 1, maximum value: 16, default value: 4.
+
+TAB_SIZE               = 4
+
+# This tag can be used to specify a number of aliases that act as commands in
+# the documentation. An alias has the form:
+# name=value
+# For example adding
+# "sideeffect=@par Side Effects:\n"
+# will allow you to put the command \sideeffect (or @sideeffect) in the
+# documentation, which will result in a user-defined paragraph with heading
+# "Side Effects:". You can put \n's in the value part of an alias to insert
+# newlines (in the resulting output). You can put ^^ in the value part of an
+# alias to insert a newline as if a physical newline was in the original file.
+# When you need a literal { or } or , in the value part of an alias you have to
+# escape them by means of a backslash (\), this can lead to conflicts with the
+# commands \{ and \} for these it is advised to use the version @{ and @} or use
+# a double escape (\\{ and \\})
+
+ALIASES                =
+
+# This tag can be used to specify a number of word-keyword mappings (TCL only).
+# A mapping has the form "name=value". For example adding "class=itcl::class"
+# will allow you to use the command class in the itcl::class meaning.
+
+TCL_SUBST              =
+
+# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources
+# only. Doxygen will then generate output that is more tailored for C. For
+# instance, some of the names that are used will be different. The list of all
+# members will be omitted, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_FOR_C  = NO
+
+# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or
+# Python sources only. Doxygen will then generate output that is more tailored
+# for that language. For instance, namespaces will be presented as packages,
+# qualified scopes will look different, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_JAVA   = NO
+
+# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran
+# sources. Doxygen will then generate output that is tailored for Fortran.
+# The default value is: NO.
+
+OPTIMIZE_FOR_FORTRAN   = NO
+
+# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL
+# sources. Doxygen will then generate output that is tailored for VHDL.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_VHDL   = NO
+
+# Set the OPTIMIZE_OUTPUT_SLICE tag to YES if your project consists of Slice
+# sources only. Doxygen will then generate output that is more tailored for that
+# language. For instance, namespaces will be presented as modules, types will be
+# separated into more groups, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_SLICE  = NO
+
+# Doxygen selects the parser to use depending on the extension of the files it
+# parses. With this tag you can assign which parser to use for a given
+# extension. Doxygen has a built-in mapping, but you can override or extend it
+# using this tag. The format is ext=language, where ext is a file extension, and
+# language is one of the parsers supported by doxygen: IDL, Java, JavaScript,
+# Csharp (C#), C, C++, D, PHP, md (Markdown), Objective-C, Python, Slice,
+# Fortran (fixed format Fortran: FortranFixed, free formatted Fortran:
+# FortranFree, unknown formatted Fortran: Fortran. In the later case the parser
+# tries to guess whether the code is fixed or free formatted code, this is the
+# default for Fortran type files), VHDL, tcl. For instance to make doxygen treat
+# .inc files as Fortran files (default is PHP), and .f files as C (default is
+# Fortran), use: inc=Fortran f=C.
+#
+# Note: For files without extension you can use no_extension as a placeholder.
+#
+# Note that for custom extensions you also need to set FILE_PATTERNS otherwise
+# the files are not read by doxygen.
+
+EXTENSION_MAPPING      =
+
+# If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments
+# according to the Markdown format, which allows for more readable
+# documentation. See https://daringfireball.net/projects/markdown/ for details.
+# The output of markdown processing is further processed by doxygen, so you can
+# mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in
+# case of backward compatibilities issues.
+# The default value is: YES.
+
+MARKDOWN_SUPPORT       = YES
+
+# When the TOC_INCLUDE_HEADINGS tag is set to a non-zero value, all headings up
+# to that level are automatically included in the table of contents, even if
+# they do not have an id attribute.
+# Note: This feature currently applies only to Markdown headings.
+# Minimum value: 0, maximum value: 99, default value: 5.
+# This tag requires that the tag MARKDOWN_SUPPORT is set to YES.
+
+TOC_INCLUDE_HEADINGS   = 5
+
+# When enabled doxygen tries to link words that correspond to documented
+# classes, or namespaces to their corresponding documentation. Such a link can
+# be prevented in individual cases by putting a % sign in front of the word or
+# globally by setting AUTOLINK_SUPPORT to NO.
+# The default value is: YES.
+
+AUTOLINK_SUPPORT       = YES
+
+# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want
+# to include (a tag file for) the STL sources as input, then you should set this
+# tag to YES in order to let doxygen match functions declarations and
+# definitions whose arguments contain STL classes (e.g. func(std::string);
+# versus func(std::string) {}). This also make the inheritance and collaboration
+# diagrams that involve STL classes more complete and accurate.
+# The default value is: NO.
+
+BUILTIN_STL_SUPPORT    = NO
+
+# If you use Microsoft's C++/CLI language, you should set this option to YES to
+# enable parsing support.
+# The default value is: NO.
+
+CPP_CLI_SUPPORT        = NO
+
+# Set the SIP_SUPPORT tag to YES if your project consists of sip (see:
+# https://www.riverbankcomputing.com/software/sip/intro) sources only. Doxygen
+# will parse them like normal C++ but will assume all classes use public instead
+# of private inheritance when no explicit protection keyword is present.
+# The default value is: NO.
+
+SIP_SUPPORT            = NO
+
+# For Microsoft's IDL there are propget and propput attributes to indicate
+# getter and setter methods for a property. Setting this option to YES will make
+# doxygen to replace the get and set methods by a property in the documentation.
+# This will only work if the methods are indeed getting or setting a simple
+# type. If this is not the case, or you want to show the methods anyway, you
+# should set this option to NO.
+# The default value is: YES.
+
+IDL_PROPERTY_SUPPORT   = YES
+
+# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC
+# tag is set to YES then doxygen will reuse the documentation of the first
+# member in the group (if any) for the other members of the group. By default
+# all members of a group must be documented explicitly.
+# The default value is: NO.
+
+DISTRIBUTE_GROUP_DOC   = NO
+
+# If one adds a struct or class to a group and this option is enabled, then also
+# any nested class or struct is added to the same group. By default this option
+# is disabled and one has to add nested compounds explicitly via \ingroup.
+# The default value is: NO.
+
+GROUP_NESTED_COMPOUNDS = NO
+
+# Set the SUBGROUPING tag to YES to allow class member groups of the same type
+# (for instance a group of public functions) to be put as a subgroup of that
+# type (e.g. under the Public Functions section). Set it to NO to prevent
+# subgrouping. Alternatively, this can be done per class using the
+# \nosubgrouping command.
+# The default value is: YES.
+
+SUBGROUPING            = YES
+
+# When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions
+# are shown inside the group in which they are included (e.g. using \ingroup)
+# instead of on a separate page (for HTML and Man pages) or section (for LaTeX
+# and RTF).
+#
+# Note that this feature does not work in combination with
+# SEPARATE_MEMBER_PAGES.
+# The default value is: NO.
+
+INLINE_GROUPED_CLASSES = NO
+
+# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions
+# with only public data fields or simple typedef fields will be shown inline in
+# the documentation of the scope in which they are defined (i.e. file,
+# namespace, or group documentation), provided this scope is documented. If set
+# to NO, structs, classes, and unions are shown on a separate page (for HTML and
+# Man pages) or section (for LaTeX and RTF).
+# The default value is: NO.
+
+INLINE_SIMPLE_STRUCTS  = NO
+
+# When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or
+# enum is documented as struct, union, or enum with the name of the typedef. So
+# typedef struct TypeS {} TypeT, will appear in the documentation as a struct
+# with name TypeT. When disabled the typedef will appear as a member of a file,
+# namespace, or class. And the struct will be named TypeS. This can typically be
+# useful for C code in case the coding convention dictates that all compound
+# types are typedef'ed and only the typedef is referenced, never the tag name.
+# The default value is: NO.
+
+TYPEDEF_HIDES_STRUCT   = NO
+
+# The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This
+# cache is used to resolve symbols given their name and scope. Since this can be
+# an expensive process and often the same symbol appears multiple times in the
+# code, doxygen keeps a cache of pre-resolved symbols. If the cache is too small
+# doxygen will become slower. If the cache is too large, memory is wasted. The
+# cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range
+# is 0..9, the default is 0, corresponding to a cache size of 2^16=65536
+# symbols. At the end of a run doxygen will report the cache usage and suggest
+# the optimal cache size from a speed point of view.
+# Minimum value: 0, maximum value: 9, default value: 0.
+
+LOOKUP_CACHE_SIZE      = 0
+
+#---------------------------------------------------------------------------
+# Build related configuration options
+#---------------------------------------------------------------------------
+
+# If the EXTRACT_ALL tag is set to YES, doxygen will assume all entities in
+# documentation are documented, even if no documentation was available. Private
+# class members and static file members will be hidden unless the
+# EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES.
+# Note: This will also disable the warnings about undocumented members that are
+# normally produced when WARNINGS is set to YES.
+# The default value is: NO.
+
+EXTRACT_ALL            = NO
+
+# If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will
+# be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PRIVATE        = NO
+
+# If the EXTRACT_PRIV_VIRTUAL tag is set to YES, documented private virtual
+# methods of a class will be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PRIV_VIRTUAL   = NO
+
+# If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal
+# scope will be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PACKAGE        = NO
+
+# If the EXTRACT_STATIC tag is set to YES, all static members of a file will be
+# included in the documentation.
+# The default value is: NO.
+
+EXTRACT_STATIC         = NO
+
+# If the EXTRACT_LOCAL_CLASSES tag is set to YES, classes (and structs) defined
+# locally in source files will be included in the documentation. If set to NO,
+# only classes defined in header files are included. Does not have any effect
+# for Java sources.
+# The default value is: YES.
+
+EXTRACT_LOCAL_CLASSES  = YES
+
+# This flag is only useful for Objective-C code. If set to YES, local methods,
+# which are defined in the implementation section but not in the interface are
+# included in the documentation. If set to NO, only methods in the interface are
+# included.
+# The default value is: NO.
+
+EXTRACT_LOCAL_METHODS  = NO
+
+# If this flag is set to YES, the members of anonymous namespaces will be
+# extracted and appear in the documentation as a namespace called
+# 'anonymous_namespace{file}', where file will be replaced with the base name of
+# the file that contains the anonymous namespace. By default anonymous namespace
+# are hidden.
+# The default value is: NO.
+
+EXTRACT_ANON_NSPACES   = NO
+
+# If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all
+# undocumented members inside documented classes or files. If set to NO these
+# members will be included in the various overviews, but no documentation
+# section is generated. This option has no effect if EXTRACT_ALL is enabled.
+# The default value is: NO.
+
+HIDE_UNDOC_MEMBERS     = NO
+
+# If the HIDE_UNDOC_CLASSES tag is set to YES, doxygen will hide all
+# undocumented classes that are normally visible in the class hierarchy. If set
+# to NO, these classes will be included in the various overviews. This option
+# has no effect if EXTRACT_ALL is enabled.
+# The default value is: NO.
+
+HIDE_UNDOC_CLASSES     = NO
+
+# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend
+# declarations. If set to NO, these declarations will be included in the
+# documentation.
+# The default value is: NO.
+
+HIDE_FRIEND_COMPOUNDS  = NO
+
+# If the HIDE_IN_BODY_DOCS tag is set to YES, doxygen will hide any
+# documentation blocks found inside the body of a function. If set to NO, these
+# blocks will be appended to the function's detailed documentation block.
+# The default value is: NO.
+
+HIDE_IN_BODY_DOCS      = NO
+
+# The INTERNAL_DOCS tag determines if documentation that is typed after a
+# \internal command is included. If the tag is set to NO then the documentation
+# will be excluded. Set it to YES to include the internal documentation.
+# The default value is: NO.
+
+INTERNAL_DOCS          = YES
+
+# If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file
+# names in lower-case letters. If set to YES, upper-case letters are also
+# allowed. This is useful if you have classes or files whose names only differ
+# in case and if your file system supports case sensitive file names. Windows
+# (including Cygwin) ands Mac users are advised to set this option to NO.
+# The default value is: system dependent.
+
+CASE_SENSE_NAMES       = YES
+
+# If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with
+# their full class and namespace scopes in the documentation. If set to YES, the
+# scope will be hidden.
+# The default value is: NO.
+
+HIDE_SCOPE_NAMES       = NO
+
+# If the HIDE_COMPOUND_REFERENCE tag is set to NO (default) then doxygen will
+# append additional text to a page's title, such as Class Reference. If set to
+# YES the compound reference will be hidden.
+# The default value is: NO.
+
+HIDE_COMPOUND_REFERENCE= NO
+
+# If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of
+# the files that are included by a file in the documentation of that file.
+# The default value is: YES.
+
+SHOW_INCLUDE_FILES     = YES
+
+# If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each
+# grouped member an include statement to the documentation, telling the reader
+# which file to include in order to use the member.
+# The default value is: NO.
+
+SHOW_GROUPED_MEMB_INC  = NO
+
+# If the FORCE_LOCAL_INCLUDES tag is set to YES then doxygen will list include
+# files with double quotes in the documentation rather than with sharp brackets.
+# The default value is: NO.
+
+FORCE_LOCAL_INCLUDES   = NO
+
+# If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the
+# documentation for inline members.
+# The default value is: YES.
+
+INLINE_INFO            = YES
+
+# If the SORT_MEMBER_DOCS tag is set to YES then doxygen will sort the
+# (detailed) documentation of file and class members alphabetically by member
+# name. If set to NO, the members will appear in declaration order.
+# The default value is: YES.
+
+SORT_MEMBER_DOCS       = YES
+
+# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the brief
+# descriptions of file, namespace and class members alphabetically by member
+# name. If set to NO, the members will appear in declaration order. Note that
+# this will also influence the order of the classes in the class list.
+# The default value is: NO.
+
+SORT_BRIEF_DOCS        = NO
+
+# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the
+# (brief and detailed) documentation of class members so that constructors and
+# destructors are listed first. If set to NO the constructors will appear in the
+# respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS.
+# Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief
+# member documentation.
+# Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting
+# detailed member documentation.
+# The default value is: NO.
+
+SORT_MEMBERS_CTORS_1ST = NO
+
+# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the hierarchy
+# of group names into alphabetical order. If set to NO the group names will
+# appear in their defined order.
+# The default value is: NO.
+
+SORT_GROUP_NAMES       = NO
+
+# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by
+# fully-qualified names, including namespaces. If set to NO, the class list will
+# be sorted only by class name, not including the namespace part.
+# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES.
+# Note: This option applies only to the class list, not to the alphabetical
+# list.
+# The default value is: NO.
+
+SORT_BY_SCOPE_NAME     = NO
+
+# If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to do proper
+# type resolution of all parameters of a function it will reject a match between
+# the prototype and the implementation of a member function even if there is
+# only one candidate or it is obvious which candidate to choose by doing a
+# simple string match. By disabling STRICT_PROTO_MATCHING doxygen will still
+# accept a match between prototype and implementation in such cases.
+# The default value is: NO.
+
+STRICT_PROTO_MATCHING  = NO
+
+# The GENERATE_TODOLIST tag can be used to enable (YES) or disable (NO) the todo
+# list. This list is created by putting \todo commands in the documentation.
+# The default value is: YES.
+
+GENERATE_TODOLIST      = YES
+
+# The GENERATE_TESTLIST tag can be used to enable (YES) or disable (NO) the test
+# list. This list is created by putting \test commands in the documentation.
+# The default value is: YES.
+
+GENERATE_TESTLIST      = YES
+
+# The GENERATE_BUGLIST tag can be used to enable (YES) or disable (NO) the bug
+# list. This list is created by putting \bug commands in the documentation.
+# The default value is: YES.
+
+GENERATE_BUGLIST       = NO
+
+# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO)
+# the deprecated list. This list is created by putting \deprecated commands in
+# the documentation.
+# The default value is: YES.
+
+GENERATE_DEPRECATEDLIST= NO
+
+# The ENABLED_SECTIONS tag can be used to enable conditional documentation
+# sections, marked by \if <section_label> ... \endif and \cond <section_label>
+# ... \endcond blocks.
+
+ENABLED_SECTIONS       =
+
+# The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the
+# initial value of a variable or macro / define can have for it to appear in the
+# documentation. If the initializer consists of more lines than specified here
+# it will be hidden. Use a value of 0 to hide initializers completely. The
+# appearance of the value of individual variables and macros / defines can be
+# controlled using \showinitializer or \hideinitializer command in the
+# documentation regardless of this setting.
+# Minimum value: 0, maximum value: 10000, default value: 30.
+
+MAX_INITIALIZER_LINES  = 30
+
+# Set the SHOW_USED_FILES tag to NO to disable the list of files generated at
+# the bottom of the documentation of classes and structs. If set to YES, the
+# list will mention the files that were used to generate the documentation.
+# The default value is: YES.
+
+SHOW_USED_FILES        = YES
+
+# Set the SHOW_FILES tag to NO to disable the generation of the Files page. This
+# will remove the Files entry from the Quick Index and from the Folder Tree View
+# (if specified).
+# The default value is: YES.
+
+SHOW_FILES             = YES
+
+# Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces
+# page. This will remove the Namespaces entry from the Quick Index and from the
+# Folder Tree View (if specified).
+# The default value is: YES.
+
+SHOW_NAMESPACES        = YES
+
+# The FILE_VERSION_FILTER tag can be used to specify a program or script that
+# doxygen should invoke to get the current version for each file (typically from
+# the version control system). Doxygen will invoke the program by executing (via
+# popen()) the command command input-file, where command is the value of the
+# FILE_VERSION_FILTER tag, and input-file is the name of an input file provided
+# by doxygen. Whatever the program writes to standard output is used as the file
+# version. For an example see the documentation.
+
+FILE_VERSION_FILTER    =
+
+# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed
+# by doxygen. The layout file controls the global structure of the generated
+# output files in an output format independent way. To create the layout file
+# that represents doxygen's defaults, run doxygen with the -l option. You can
+# optionally specify a file name after the option, if omitted DoxygenLayout.xml
+# will be used as the name of the layout file.
+#
+# Note that if you run doxygen from a directory containing a file called
+# DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE
+# tag is left empty.
+
+LAYOUT_FILE            =
+
+# The CITE_BIB_FILES tag can be used to specify one or more bib files containing
+# the reference definitions. This must be a list of .bib files. The .bib
+# extension is automatically appended if omitted. This requires the bibtex tool
+# to be installed. See also https://en.wikipedia.org/wiki/BibTeX for more info.
+# For LaTeX the style of the bibliography can be controlled using
+# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the
+# search path. See also \cite for info how to create references.
+
+CITE_BIB_FILES         =
+
+#---------------------------------------------------------------------------
+# Configuration options related to warning and progress messages
+#---------------------------------------------------------------------------
+
+# The QUIET tag can be used to turn on/off the messages that are generated to
+# standard output by doxygen. If QUIET is set to YES this implies that the
+# messages are off.
+# The default value is: NO.
+
+QUIET                  = NO
+
+# The WARNINGS tag can be used to turn on/off the warning messages that are
+# generated to standard error (stderr) by doxygen. If WARNINGS is set to YES
+# this implies that the warnings are on.
+#
+# Tip: Turn warnings on while writing the documentation.
+# The default value is: YES.
+
+WARNINGS               = YES
+
+# If the WARN_IF_UNDOCUMENTED tag is set to YES then doxygen will generate
+# warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag
+# will automatically be disabled.
+# The default value is: YES.
+
+WARN_IF_UNDOCUMENTED   = YES
+
+# If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for
+# potential errors in the documentation, such as not documenting some parameters
+# in a documented function, or documenting parameters that don't exist or using
+# markup commands wrongly.
+# The default value is: YES.
+
+WARN_IF_DOC_ERROR      = YES
+
+# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that
+# are documented, but have no documentation for their parameters or return
+# value. If set to NO, doxygen will only warn about wrong or incomplete
+# parameter documentation, but not about the absence of documentation. If
+# EXTRACT_ALL is set to YES then this flag will automatically be disabled.
+# The default value is: NO.
+
+WARN_NO_PARAMDOC       = NO
+
+# If the WARN_AS_ERROR tag is set to YES then doxygen will immediately stop when
+# a warning is encountered.
+# The default value is: NO.
+
+WARN_AS_ERROR          = NO
+
+# The WARN_FORMAT tag determines the format of the warning messages that doxygen
+# can produce. The string should contain the $file, $line, and $text tags, which
+# will be replaced by the file and line number from which the warning originated
+# and the warning text. Optionally the format may contain $version, which will
+# be replaced by the version of the file (if it could be obtained via
+# FILE_VERSION_FILTER)
+# The default value is: $file:$line: $text.
+
+WARN_FORMAT            = "$file:$line: $text"
+
+# The WARN_LOGFILE tag can be used to specify a file to which warning and error
+# messages should be written. If left blank the output is written to standard
+# error (stderr).
+
+WARN_LOGFILE           =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the input files
+#---------------------------------------------------------------------------
+
+# The INPUT tag is used to specify the files and/or directories that contain
+# documented source files. You may enter file names like myfile.cpp or
+# directories like /usr/src/myproject. Separate the files or directories with
+# spaces. See also FILE_PATTERNS and EXTENSION_MAPPING
+# Note: If this tag is empty the current directory is searched.
+
+INPUT                  = $(HIP_PATH)/docs/doxygen-input/mainpage.txt \
+                         $(HIP_PATH)/README.md \
+                         $(HIP_PATH)/CONTRIBUTING.md \
+                         $(HIP_PATH)/docs/doxygen-input/sync.txt \
+                         $(HIP_PATH)/INSTALL.md \
+                         $(HIP_PATH)/docs/markdown \
+                         $(HIP_PATH)/include/hip \
+                         $(HIP_PATH)/include/hip/amd_detail/ \
+                         $(HIP_PATH)/src/
+
+# This tag can be used to specify the character encoding of the source files
+# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
+# libiconv (or the iconv built into libc) for the transcoding. See the libiconv
+# documentation (see: https://www.gnu.org/software/libiconv/) for the list of
+# possible encodings.
+# The default value is: UTF-8.
+
+INPUT_ENCODING         = UTF-8
+
+# If the value of the INPUT tag contains directories, you can use the
+# FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and
+# *.h) to filter out the source-files in the directories.
+#
+# Note that for custom extensions or not directly supported extensions you also
+# need to set EXTENSION_MAPPING for the extension otherwise the files are not
+# read by doxygen.
+#
+# If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp,
+# *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h,
+# *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc,
+# *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C comment),
+# *.doc (to be provided as doxygen C comment), *.txt (to be provided as doxygen
+# C comment), *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f, *.for, *.tcl, *.vhd,
+# *.vhdl, *.ucf, *.qsf and *.ice.
+
+FILE_PATTERNS          = *.c \
+                         *.cc \
+                         *.cxx \
+                         *.cpp \
+                         *.h \
+                         *.hpp \
+                         *.md \
+                         *.dox \
+                         *.doc \
+                         *.txt \
+
+# The RECURSIVE tag can be used to specify whether or not subdirectories should
+# be searched for input files as well.
+# The default value is: NO.
+
+RECURSIVE              = YES
+
+# The EXCLUDE tag can be used to specify files and/or directories that should be
+# excluded from the INPUT source files. This way you can easily exclude a
+# subdirectory from a directory tree whose root is specified with the INPUT tag.
+#
+# Note that relative paths are relative to the directory from which doxygen is
+# run.
+
+EXCLUDE                =
+
+# The EXCLUDE_SYMLINKS tag can be used to select whether or not files or
+# directories that are symbolic links (a Unix file system feature) are excluded
+# from the input.
+# The default value is: NO.
+
+EXCLUDE_SYMLINKS       = NO
+
+# If the value of the INPUT tag contains directories, you can use the
+# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude
+# certain files from those directories.
+#
+# Note that the wildcards are matched against the file with absolute path, so to
+# exclude all test directories for example use the pattern */test/*
+
+EXCLUDE_PATTERNS       =
+
+# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names
+# (namespaces, classes, functions, etc.) that should be excluded from the
+# output. The symbol name can be a fully qualified name, a word, or if the
+# wildcard * is used, a substring. Examples: ANamespace, AClass,
+# AClass::ANamespace, ANamespace::*Test
+#
+# Note that the wildcards are matched against the file with absolute path, so to
+# exclude all test directories use the pattern */test/*
+
+EXCLUDE_SYMBOLS        =
+
+# The EXAMPLE_PATH tag can be used to specify one or more files or directories
+# that contain example code fragments that are included (see the \include
+# command).
+
+EXAMPLE_PATH           = ./examples
+
+# If the value of the EXAMPLE_PATH tag contains directories, you can use the
+# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and
+# *.h) to filter out the source-files in the directories. If left blank all
+# files are included.
+
+EXAMPLE_PATTERNS       =
+
+# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be
+# searched for input files to be used with the \include or \dontinclude commands
+# irrespective of the value of the RECURSIVE tag.
+# The default value is: NO.
+
+EXAMPLE_RECURSIVE      = NO
+
+# The IMAGE_PATH tag can be used to specify one or more files or directories
+# that contain images that are to be included in the documentation (see the
+# \image command).
+
+IMAGE_PATH             = $(HIP_PATH)/docs/doxygen-input/images
+
+# The INPUT_FILTER tag can be used to specify a program that doxygen should
+# invoke to filter for each input file. Doxygen will invoke the filter program
+# by executing (via popen()) the command:
+#
+# <filter> <input-file>
+#
+# where <filter> is the value of the INPUT_FILTER tag, and <input-file> is the
+# name of an input file. Doxygen will then use the output that the filter
+# program writes to standard output. If FILTER_PATTERNS is specified, this tag
+# will be ignored.
+#
+# Note that the filter must not add or remove lines; it is applied before the
+# code is scanned, but not when the output code is generated. If lines are added
+# or removed, the anchors will not be placed correctly.
+#
+# Note that for custom extensions or not directly supported extensions you also
+# need to set EXTENSION_MAPPING for the extension otherwise the files are not
+# properly processed by doxygen.
+
+INPUT_FILTER           =
+
+# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern
+# basis. Doxygen will compare the file name with each pattern and apply the
+# filter if there is a match. The filters are a list of the form: pattern=filter
+# (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how
+# filters are used. If the FILTER_PATTERNS tag is empty or if none of the
+# patterns match the file name, INPUT_FILTER is applied.
+#
+# Note that for custom extensions or not directly supported extensions you also
+# need to set EXTENSION_MAPPING for the extension otherwise the files are not
+# properly processed by doxygen.
+
+FILTER_PATTERNS        =
+
+# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using
+# INPUT_FILTER) will also be used to filter the input files that are used for
+# producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES).
+# The default value is: NO.
+
+FILTER_SOURCE_FILES    = NO
+
+# The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file
+# pattern. A pattern will override the setting for FILTER_PATTERN (if any) and
+# it is also possible to disable source filtering for a specific pattern using
+# *.ext= (so without naming a filter).
+# This tag requires that the tag FILTER_SOURCE_FILES is set to YES.
+
+FILTER_SOURCE_PATTERNS =
+
+# If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that
+# is part of the input, its contents will be placed on the main page
+# (index.html). This can be useful if you have a project on for instance GitHub
+# and want to reuse the introduction page also for the doxygen output.
+
+USE_MDFILE_AS_MAINPAGE =
+
+#---------------------------------------------------------------------------
+# Configuration options related to source browsing
+#---------------------------------------------------------------------------
+
+# If the SOURCE_BROWSER tag is set to YES then a list of source files will be
+# generated. Documented entities will be cross-referenced with these sources.
+#
+# Note: To get rid of all source code in the generated output, make sure that
+# also VERBATIM_HEADERS is set to NO.
+# The default value is: NO.
+
+SOURCE_BROWSER         = NO
+
+# Setting the INLINE_SOURCES tag to YES will include the body of functions,
+# classes and enums directly into the documentation.
+# The default value is: NO.
+
+INLINE_SOURCES         = NO
+
+# Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any
+# special comment blocks from generated source code fragments. Normal C, C++ and
+# Fortran comments will always remain visible.
+# The default value is: YES.
+
+STRIP_CODE_COMMENTS    = YES
+
+# If the REFERENCED_BY_RELATION tag is set to YES then for each documented
+# entity all documented functions referencing it will be listed.
+# The default value is: NO.
+
+REFERENCED_BY_RELATION = NO
+
+# If the REFERENCES_RELATION tag is set to YES then for each documented function
+# all documented entities called/used by that function will be listed.
+# The default value is: NO.
+
+REFERENCES_RELATION    = NO
+
+# If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set
+# to YES then the hyperlinks from functions in REFERENCES_RELATION and
+# REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will
+# link to the documentation.
+# The default value is: YES.
+
+REFERENCES_LINK_SOURCE = YES
+
+# If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the
+# source code will show a tooltip with additional information such as prototype,
+# brief description and links to the definition and documentation. Since this
+# will make the HTML file larger and loading of large files a bit slower, you
+# can opt to disable this feature.
+# The default value is: YES.
+# This tag requires that the tag SOURCE_BROWSER is set to YES.
+
+SOURCE_TOOLTIPS        = YES
+
+# If the USE_HTAGS tag is set to YES then the references to source code will
+# point to the HTML generated by the htags(1) tool instead of doxygen built-in
+# source browser. The htags tool is part of GNU's global source tagging system
+# (see https://www.gnu.org/software/global/global.html). You will need version
+# 4.8.6 or higher.
+#
+# To use it do the following:
+# - Install the latest version of global
+# - Enable SOURCE_BROWSER and USE_HTAGS in the configuration file
+# - Make sure the INPUT points to the root of the source tree
+# - Run doxygen as normal
+#
+# Doxygen will invoke htags (and that will in turn invoke gtags), so these
+# tools must be available from the command line (i.e. in the search path).
+#
+# The result: instead of the source browser generated by doxygen, the links to
+# source code will now point to the output of htags.
+# The default value is: NO.
+# This tag requires that the tag SOURCE_BROWSER is set to YES.
+
+USE_HTAGS              = NO
+
+# If the VERBATIM_HEADERS tag is set the YES then doxygen will generate a
+# verbatim copy of the header file for each class for which an include is
+# specified. Set to NO to disable this.
+# See also: Section \class.
+# The default value is: YES.
+
+VERBATIM_HEADERS       = YES
+
+# If the CLANG_ASSISTED_PARSING tag is set to YES then doxygen will use the
+# clang parser (see: http://clang.llvm.org/) for more accurate parsing at the
+# cost of reduced performance. This can be particularly helpful with template
+# rich C++ code for which doxygen's built-in parser lacks the necessary type
+# information.
+# Note: The availability of this option depends on whether or not doxygen was
+# generated with the -Duse_libclang=ON option for CMake.
+# The default value is: NO.
+
+CLANG_ASSISTED_PARSING = NO
+
+# If clang assisted parsing is enabled you can provide the compiler with command
+# line options that you would normally use when invoking the compiler. Note that
+# the include paths will already be set by doxygen for the files and directories
+# specified with INPUT and INCLUDE_PATH.
+# This tag requires that the tag CLANG_ASSISTED_PARSING is set to YES.
+
+CLANG_OPTIONS          =
+
+# If clang assisted parsing is enabled you can provide the clang parser with the
+# path to the compilation database (see:
+# http://clang.llvm.org/docs/HowToSetupToolingForLLVM.html) used when the files
+# were built. This is equivalent to specifying the "-p" option to a clang tool,
+# such as clang-check. These options will then be passed to the parser.
+# Note: The availability of this option depends on whether or not doxygen was
+# generated with the -Duse_libclang=ON option for CMake.
+
+CLANG_DATABASE_PATH    =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the alphabetical class index
+#---------------------------------------------------------------------------
+
+# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all
+# compounds will be generated. Enable this if the project contains a lot of
+# classes, structs, unions or interfaces.
+# The default value is: YES.
+
+ALPHABETICAL_INDEX     = YES
+
+# The COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns in
+# which the alphabetical index list will be split.
+# Minimum value: 1, maximum value: 20, default value: 5.
+# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
+
+COLS_IN_ALPHA_INDEX    = 5
+
+# In case all classes in a project start with a common prefix, all classes will
+# be put under the same header in the alphabetical index. The IGNORE_PREFIX tag
+# can be used to specify a prefix (or a list of prefixes) that should be ignored
+# while generating the index headers.
+# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
+
+IGNORE_PREFIX          =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the HTML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_HTML tag is set to YES, doxygen will generate HTML output
+# The default value is: YES.
+
+GENERATE_HTML          = YES
+
+# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: html.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_OUTPUT            = html
+
+# The HTML_FILE_EXTENSION tag can be used to specify the file extension for each
+# generated HTML page (for example: .htm, .php, .asp).
+# The default value is: .html.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_FILE_EXTENSION    = .html
+
+# The HTML_HEADER tag can be used to specify a user-defined HTML header file for
+# each generated HTML page. If the tag is left blank doxygen will generate a
+# standard header.
+#
+# To get valid HTML the header file that includes any scripts and style sheets
+# that doxygen needs, which is dependent on the configuration options used (e.g.
+# the setting GENERATE_TREEVIEW). It is highly recommended to start with a
+# default header using
+# doxygen -w html new_header.html new_footer.html new_stylesheet.css
+# YourConfigFile
+# and then modify the file new_header.html. See also section "Doxygen usage"
+# for information on how to generate the default header that doxygen normally
+# uses.
+# Note: The header is subject to change so you typically have to regenerate the
+# default header when upgrading to a newer version of doxygen. For a description
+# of the possible markers and block names see the documentation.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_HEADER            =
+
+# The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each
+# generated HTML page. If the tag is left blank doxygen will generate a standard
+# footer. See HTML_HEADER for more information on how to generate a default
+# footer and what special commands can be used inside the footer. See also
+# section "Doxygen usage" for information on how to generate the default footer
+# that doxygen normally uses.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_FOOTER            =
+
+# The HTML_STYLESHEET tag can be used to specify a user-defined cascading style
+# sheet that is used by each HTML page. It can be used to fine-tune the look of
+# the HTML output. If left blank doxygen will generate a default style sheet.
+# See also section "Doxygen usage" for information on how to generate the style
+# sheet that doxygen normally uses.
+# Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as
+# it is more robust and this tag (HTML_STYLESHEET) will in the future become
+# obsolete.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_STYLESHEET        =
+
+# The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined
+# cascading style sheets that are included after the standard style sheets
+# created by doxygen. Using this option one can overrule certain style aspects.
+# This is preferred over using HTML_STYLESHEET since it does not replace the
+# standard style sheet and is therefore more robust against future updates.
+# Doxygen will copy the style sheet files to the output directory.
+# Note: The order of the extra style sheet files is of importance (e.g. the last
+# style sheet in the list overrules the setting of the previous ones in the
+# list). For an example see the documentation.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_EXTRA_STYLESHEET  =
+
+# The HTML_EXTRA_FILES tag can be used to specify one or more extra images or
+# other source files which should be copied to the HTML output directory. Note
+# that these files will be copied to the base HTML output directory. Use the
+# $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these
+# files. In the HTML_STYLESHEET file, use the file name only. Also note that the
+# files will be copied as-is; there are no commands or markers available.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_EXTRA_FILES       =
+
+# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen
+# will adjust the colors in the style sheet and background images according to
+# this color. Hue is specified as an angle on a colorwheel, see
+# https://en.wikipedia.org/wiki/Hue for more information. For instance the value
+# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300
+# purple, and 360 is red again.
+# Minimum value: 0, maximum value: 359, default value: 220.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_HUE    = 220
+
+# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors
+# in the HTML output. For a value of 0 the output will use grayscales only. A
+# value of 255 will produce the most vivid colors.
+# Minimum value: 0, maximum value: 255, default value: 100.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_SAT    = 100
+
+# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the
+# luminance component of the colors in the HTML output. Values below 100
+# gradually make the output lighter, whereas values above 100 make the output
+# darker. The value divided by 100 is the actual gamma applied, so 80 represents
+# a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not
+# change the gamma.
+# Minimum value: 40, maximum value: 240, default value: 80.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_GAMMA  = 80
+
+# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML
+# page will contain the date and time when the page was generated. Setting this
+# to YES can help to show when doxygen was last run and thus if the
+# documentation is up to date.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_TIMESTAMP         = YES
+
+# If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML
+# documentation will contain a main index with vertical navigation menus that
+# are dynamically created via JavaScript. If disabled, the navigation index will
+# consists of multiple levels of tabs that are statically embedded in every HTML
+# page. Disable this option to support browsers that do not have JavaScript,
+# like the Qt help browser.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_DYNAMIC_MENUS     = YES
+
+# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML
+# documentation will contain sections that can be hidden and shown after the
+# page has loaded.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_DYNAMIC_SECTIONS  = NO
+
+# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries
+# shown in the various tree structured indices initially; the user can expand
+# and collapse entries dynamically later on. Doxygen will expand the tree to
+# such a level that at most the specified number of entries are visible (unless
+# a fully collapsed tree already exceeds this amount). So setting the number of
+# entries 1 will produce a full collapsed tree by default. 0 is a special value
+# representing an infinite number of entries and will result in a full expanded
+# tree by default.
+# Minimum value: 0, maximum value: 9999, default value: 100.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_INDEX_NUM_ENTRIES = 100
+
+# If the GENERATE_DOCSET tag is set to YES, additional index files will be
+# generated that can be used as input for Apple's Xcode 3 integrated development
+# environment (see: https://developer.apple.com/xcode/), introduced with OSX
+# 10.5 (Leopard). To create a documentation set, doxygen will generate a
+# Makefile in the HTML output directory. Running make will produce the docset in
+# that directory and running make install will install the docset in
+# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at
+# startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy
+# genXcode/_index.html for more information.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_DOCSET        = NO
+
+# This tag determines the name of the docset feed. A documentation feed provides
+# an umbrella under which multiple documentation sets from a single provider
+# (such as a company or product suite) can be grouped.
+# The default value is: Doxygen generated docs.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_FEEDNAME        = "Doxygen generated docs"
+
+# This tag specifies a string that should uniquely identify the documentation
+# set bundle. This should be a reverse domain-name style string, e.g.
+# com.mycompany.MyDocSet. Doxygen will append .docset to the name.
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_BUNDLE_ID       = org.doxygen.Project
+
+# The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify
+# the documentation publisher. This should be a reverse domain-name style
+# string, e.g. com.mycompany.MyDocSet.documentation.
+# The default value is: org.doxygen.Publisher.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_PUBLISHER_ID    = org.doxygen.Publisher
+
+# The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher.
+# The default value is: Publisher.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_PUBLISHER_NAME  = Publisher
+
+# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three
+# additional HTML index files: index.hhp, index.hhc, and index.hhk. The
+# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop
+# (see: https://www.microsoft.com/en-us/download/details.aspx?id=21138) on
+# Windows.
+#
+# The HTML Help Workshop contains a compiler that can convert all HTML output
+# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML
+# files are now used as the Windows 98 help format, and will replace the old
+# Windows help format (.hlp) on all Windows platforms in the future. Compressed
+# HTML files also contain an index, a table of contents, and you can search for
+# words in the documentation. The HTML workshop also contains a viewer for
+# compressed HTML files.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_HTMLHELP      = NO
+
+# The CHM_FILE tag can be used to specify the file name of the resulting .chm
+# file. You can add a path in front of the file if the result should not be
+# written to the html output directory.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+CHM_FILE               =
+
+# The HHC_LOCATION tag can be used to specify the location (absolute path
+# including file name) of the HTML help compiler (hhc.exe). If non-empty,
+# doxygen will try to run the HTML help compiler on the generated index.hhp.
+# The file has to be specified with full path.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+HHC_LOCATION           =
+
+# The GENERATE_CHI flag controls if a separate .chi index file is generated
+# (YES) or that it should be included in the master .chm file (NO).
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+GENERATE_CHI           = NO
+
+# The CHM_INDEX_ENCODING is used to encode HtmlHelp index (hhk), content (hhc)
+# and project file content.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+CHM_INDEX_ENCODING     =
+
+# The BINARY_TOC flag controls whether a binary table of contents is generated
+# (YES) or a normal table of contents (NO) in the .chm file. Furthermore it
+# enables the Previous and Next buttons.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+BINARY_TOC             = NO
+
+# The TOC_EXPAND flag can be set to YES to add extra items for group members to
+# the table of contents of the HTML help documentation and to the tree view.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+TOC_EXPAND             = NO
+
+# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and
+# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that
+# can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help
+# (.qch) of the generated HTML documentation.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_QHP           = NO
+
+# If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify
+# the file name of the resulting .qch file. The path specified is relative to
+# the HTML output folder.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QCH_FILE               =
+
+# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help
+# Project output. For more information please see Qt Help Project / Namespace
+# (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace).
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_NAMESPACE          = org.doxygen.Project
+
+# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt
+# Help Project output. For more information please see Qt Help Project / Virtual
+# Folders (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-
+# folders).
+# The default value is: doc.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_VIRTUAL_FOLDER     = doc
+
+# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom
+# filter to add. For more information please see Qt Help Project / Custom
+# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-
+# filters).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_CUST_FILTER_NAME   =
+
+# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the
+# custom filter to add. For more information please see Qt Help Project / Custom
+# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-
+# filters).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_CUST_FILTER_ATTRS  =
+
+# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this
+# project's filter section matches. Qt Help Project / Filter Attributes (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#filter-attributes).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_SECT_FILTER_ATTRS  =
+
+# The QHG_LOCATION tag can be used to specify the location of Qt's
+# qhelpgenerator. If non-empty doxygen will try to run qhelpgenerator on the
+# generated .qhp file.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHG_LOCATION           =
+
+# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be
+# generated, together with the HTML files, they form an Eclipse help plugin. To
+# install this plugin and make it available under the help contents menu in
+# Eclipse, the contents of the directory containing the HTML and XML files needs
+# to be copied into the plugins directory of eclipse. The name of the directory
+# within the plugins directory should be the same as the ECLIPSE_DOC_ID value.
+# After copying Eclipse needs to be restarted before the help appears.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_ECLIPSEHELP   = NO
+
+# A unique identifier for the Eclipse help plugin. When installing the plugin
+# the directory name containing the HTML and XML files should also have this
+# name. Each documentation set should have its own identifier.
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES.
+
+ECLIPSE_DOC_ID         = org.doxygen.Project
+
+# If you want full control over the layout of the generated HTML pages it might
+# be necessary to disable the index and replace it with your own. The
+# DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top
+# of each HTML page. A value of NO enables the index and the value YES disables
+# it. Since the tabs in the index contain the same information as the navigation
+# tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+DISABLE_INDEX          = NO
+
+# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index
+# structure should be generated to display hierarchical information. If the tag
+# value is set to YES, a side panel will be generated containing a tree-like
+# index structure (just like the one that is generated for HTML Help). For this
+# to work a browser that supports JavaScript, DHTML, CSS and frames is required
+# (i.e. any modern browser). Windows users are probably better off using the
+# HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can
+# further fine-tune the look of the index. As an example, the default style
+# sheet generated by doxygen has an example that shows how to put an image at
+# the root of the tree instead of the PROJECT_NAME. Since the tree basically has
+# the same information as the tab index, you could consider setting
+# DISABLE_INDEX to YES when enabling this option.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_TREEVIEW      = NO
+
+# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that
+# doxygen will group on one line in the generated HTML documentation.
+#
+# Note that a value of 0 will completely suppress the enum values from appearing
+# in the overview section.
+# Minimum value: 0, maximum value: 20, default value: 4.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+ENUM_VALUES_PER_LINE   = 4
+
+# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used
+# to set the initial width (in pixels) of the frame in which the tree is shown.
+# Minimum value: 0, maximum value: 1500, default value: 250.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+TREEVIEW_WIDTH         = 250
+
+# If the EXT_LINKS_IN_WINDOW option is set to YES, doxygen will open links to
+# external symbols imported via tag files in a separate window.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+EXT_LINKS_IN_WINDOW    = NO
+
+# Use this tag to change the font size of LaTeX formulas included as images in
+# the HTML documentation. When you change the font size after a successful
+# doxygen run you need to manually remove any form_*.png images from the HTML
+# output directory to force them to be regenerated.
+# Minimum value: 8, maximum value: 50, default value: 10.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+FORMULA_FONTSIZE       = 10
+
+# Use the FORMULA_TRANSPARENT tag to determine whether or not the images
+# generated for formulas are transparent PNGs. Transparent PNGs are not
+# supported properly for IE 6.0, but are supported on all modern browsers.
+#
+# Note that when changing this option you need to delete any form_*.png files in
+# the HTML output directory before the changes have effect.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+FORMULA_TRANSPARENT    = YES
+
+# The FORMULA_MACROFILE can contain LaTeX \newcommand and \renewcommand commands
+# to create new LaTeX commands to be used in formulas as building blocks. See
+# the section "Including formulas" for details.
+
+FORMULA_MACROFILE      =
+
+# Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see
+# https://www.mathjax.org) which uses client side JavaScript for the rendering
+# instead of using pre-rendered bitmaps. Use this if you do not have LaTeX
+# installed or if you want to formulas look prettier in the HTML output. When
+# enabled you may also need to install MathJax separately and configure the path
+# to it using the MATHJAX_RELPATH option.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+USE_MATHJAX            = NO
+
+# When MathJax is enabled you can set the default output format to be used for
+# the MathJax output. See the MathJax site (see:
+# http://docs.mathjax.org/en/latest/output.html) for more details.
+# Possible values are: HTML-CSS (which is slower, but has the best
+# compatibility), NativeMML (i.e. MathML) and SVG.
+# The default value is: HTML-CSS.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_FORMAT         = HTML-CSS
+
+# When MathJax is enabled you need to specify the location relative to the HTML
+# output directory using the MATHJAX_RELPATH option. The destination directory
+# should contain the MathJax.js script. For instance, if the mathjax directory
+# is located at the same level as the HTML output directory, then
+# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax
+# Content Delivery Network so you can quickly see the result without installing
+# MathJax. However, it is strongly recommended to install a local copy of
+# MathJax from https://www.mathjax.org before deployment.
+# The default value is: https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_RELPATH        = https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/
+
+# The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax
+# extension names that should be enabled during MathJax rendering. For example
+# MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_EXTENSIONS     =
+
+# The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces
+# of code that will be used on startup of the MathJax code. See the MathJax site
+# (see: http://docs.mathjax.org/en/latest/output.html) for more details. For an
+# example see the documentation.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_CODEFILE       =
+
+# When the SEARCHENGINE tag is enabled doxygen will generate a search box for
+# the HTML output. The underlying search engine uses javascript and DHTML and
+# should work on any modern browser. Note that when using HTML help
+# (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets (GENERATE_DOCSET)
+# there is already a search function so this one should typically be disabled.
+# For large projects the javascript based search engine can be slow, then
+# enabling SERVER_BASED_SEARCH may provide a better solution. It is possible to
+# search using the keyboard; to jump to the search box use <access key> + S
+# (what the <access key> is depends on the OS and browser, but it is typically
+# <CTRL>, <ALT>/<option>, or both). Inside the search box use the <cursor down
+# key> to jump into the search results window, the results can be navigated
+# using the <cursor keys>. Press <Enter> to select an item or <escape> to cancel
+# the search. The filter options can be selected when the cursor is inside the
+# search box by pressing <Shift>+<cursor down>. Also here use the <cursor keys>
+# to select a filter and <Enter> or <escape> to activate or cancel the filter
+# option.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+SEARCHENGINE           = YES
+
+# When the SERVER_BASED_SEARCH tag is enabled the search engine will be
+# implemented using a web server instead of a web client using JavaScript. There
+# are two flavors of web server based searching depending on the EXTERNAL_SEARCH
+# setting. When disabled, doxygen will generate a PHP script for searching and
+# an index file used by the script. When EXTERNAL_SEARCH is enabled the indexing
+# and searching needs to be provided by external tools. See the section
+# "External Indexing and Searching" for details.
+# The default value is: NO.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SERVER_BASED_SEARCH    = NO
+
+# When EXTERNAL_SEARCH tag is enabled doxygen will no longer generate the PHP
+# script for searching. Instead the search results are written to an XML file
+# which needs to be processed by an external indexer. Doxygen will invoke an
+# external search engine pointed to by the SEARCHENGINE_URL option to obtain the
+# search results.
+#
+# Doxygen ships with an example indexer (doxyindexer) and search engine
+# (doxysearch.cgi) which are based on the open source search engine library
+# Xapian (see: https://xapian.org/).
+#
+# See the section "External Indexing and Searching" for details.
+# The default value is: NO.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTERNAL_SEARCH        = NO
+
+# The SEARCHENGINE_URL should point to a search engine hosted by a web server
+# which will return the search results when EXTERNAL_SEARCH is enabled.
+#
+# Doxygen ships with an example indexer (doxyindexer) and search engine
+# (doxysearch.cgi) which are based on the open source search engine library
+# Xapian (see: https://xapian.org/). See the section "External Indexing and
+# Searching" for details.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SEARCHENGINE_URL       =
+
+# When SERVER_BASED_SEARCH and EXTERNAL_SEARCH are both enabled the unindexed
+# search data is written to a file for indexing by an external tool. With the
+# SEARCHDATA_FILE tag the name of this file can be specified.
+# The default file is: searchdata.xml.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SEARCHDATA_FILE        = searchdata.xml
+
+# When SERVER_BASED_SEARCH and EXTERNAL_SEARCH are both enabled the
+# EXTERNAL_SEARCH_ID tag can be used as an identifier for the project. This is
+# useful in combination with EXTRA_SEARCH_MAPPINGS to search through multiple
+# projects and redirect the results back to the right project.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTERNAL_SEARCH_ID     =
+
+# The EXTRA_SEARCH_MAPPINGS tag can be used to enable searching through doxygen
+# projects other than the one defined by this configuration file, but that are
+# all added to the same external search index. Each project needs to have a
+# unique id set via EXTERNAL_SEARCH_ID. The search mapping then maps the id of
+# to a relative location where the documentation can be found. The format is:
+# EXTRA_SEARCH_MAPPINGS = tagname1=loc1 tagname2=loc2 ...
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTRA_SEARCH_MAPPINGS  =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the LaTeX output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_LATEX tag is set to YES, doxygen will generate LaTeX output.
+# The default value is: YES.
+
+GENERATE_LATEX         = NO
+
+# The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: latex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_OUTPUT           = latex
+
+# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be
+# invoked.
+#
+# Note that when not enabling USE_PDFLATEX the default is latex when enabling
+# USE_PDFLATEX the default is pdflatex and when in the later case latex is
+# chosen this is overwritten by pdflatex. For specific output languages the
+# default can have been set differently, this depends on the implementation of
+# the output language.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_CMD_NAME         =
+
+# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to generate
+# index for LaTeX.
+# Note: This tag is used in the Makefile / make.bat.
+# See also: LATEX_MAKEINDEX_CMD for the part in the generated output file
+# (.tex).
+# The default file is: makeindex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+MAKEINDEX_CMD_NAME     = makeindex
+
+# The LATEX_MAKEINDEX_CMD tag can be used to specify the command name to
+# generate index for LaTeX. In case there is no backslash (\) as first character
+# it will be automatically added in the LaTeX code.
+# Note: This tag is used in the generated output file (.tex).
+# See also: MAKEINDEX_CMD_NAME for the part in the Makefile / make.bat.
+# The default value is: makeindex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_MAKEINDEX_CMD    = makeindex
+
+# If the COMPACT_LATEX tag is set to YES, doxygen generates more compact LaTeX
+# documents. This may be useful for small projects and may help to save some
+# trees in general.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+COMPACT_LATEX          = NO
+
+# The PAPER_TYPE tag can be used to set the paper type that is used by the
+# printer.
+# Possible values are: a4 (210 x 297 mm), letter (8.5 x 11 inches), legal (8.5 x
+# 14 inches) and executive (7.25 x 10.5 inches).
+# The default value is: a4.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+PAPER_TYPE             = a4
+
+# The EXTRA_PACKAGES tag can be used to specify one or more LaTeX package names
+# that should be included in the LaTeX output. The package can be specified just
+# by its name or with the correct syntax as to be used with the LaTeX
+# \usepackage command. To get the times font for instance you can specify :
+# EXTRA_PACKAGES=times or EXTRA_PACKAGES={times}
+# To use the option intlimits with the amsmath package you can specify:
+# EXTRA_PACKAGES=[intlimits]{amsmath}
+# If left blank no extra packages will be included.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+EXTRA_PACKAGES         =
+
+# The LATEX_HEADER tag can be used to specify a personal LaTeX header for the
+# generated LaTeX document. The header should contain everything until the first
+# chapter. If it is left blank doxygen will generate a standard header. See
+# section "Doxygen usage" for information on how to let doxygen write the
+# default header to a separate file.
+#
+# Note: Only use a user-defined header if you know what you are doing! The
+# following commands have a special meaning inside the header: $title,
+# $datetime, $date, $doxygenversion, $projectname, $projectnumber,
+# $projectbrief, $projectlogo. Doxygen will replace $title with the empty
+# string, for the replacement values of the other commands the user is referred
+# to HTML_HEADER.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_HEADER           =
+
+# The LATEX_FOOTER tag can be used to specify a personal LaTeX footer for the
+# generated LaTeX document. The footer should contain everything after the last
+# chapter. If it is left blank doxygen will generate a standard footer. See
+# LATEX_HEADER for more information on how to generate a default footer and what
+# special commands can be used inside the footer.
+#
+# Note: Only use a user-defined footer if you know what you are doing!
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_FOOTER           =
+
+# The LATEX_EXTRA_STYLESHEET tag can be used to specify additional user-defined
+# LaTeX style sheets that are included after the standard style sheets created
+# by doxygen. Using this option one can overrule certain style aspects. Doxygen
+# will copy the style sheet files to the output directory.
+# Note: The order of the extra style sheet files is of importance (e.g. the last
+# style sheet in the list overrules the setting of the previous ones in the
+# list).
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_EXTRA_STYLESHEET =
+
+# The LATEX_EXTRA_FILES tag can be used to specify one or more extra images or
+# other source files which should be copied to the LATEX_OUTPUT output
+# directory. Note that the files will be copied as-is; there are no commands or
+# markers available.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_EXTRA_FILES      =
+
+# If the PDF_HYPERLINKS tag is set to YES, the LaTeX that is generated is
+# prepared for conversion to PDF (using ps2pdf or pdflatex). The PDF file will
+# contain links (just like the HTML output) instead of page references. This
+# makes the output suitable for online browsing using a PDF viewer.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+PDF_HYPERLINKS         = YES
+
+# If the USE_PDFLATEX tag is set to YES, doxygen will use pdflatex to generate
+# the PDF file directly from the LaTeX files. Set this option to YES, to get a
+# higher quality PDF documentation.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+USE_PDFLATEX           = YES
+
+# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \batchmode
+# command to the generated LaTeX files. This will instruct LaTeX to keep running
+# if errors occur, instead of asking the user for help. This option is also used
+# when generating formulas in HTML.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_BATCHMODE        = NO
+
+# If the LATEX_HIDE_INDICES tag is set to YES then doxygen will not include the
+# index chapters (such as File Index, Compound Index, etc.) in the output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_HIDE_INDICES     = NO
+
+# If the LATEX_SOURCE_CODE tag is set to YES then doxygen will include source
+# code with syntax highlighting in the LaTeX output.
+#
+# Note that which sources are shown also depends on other settings such as
+# SOURCE_BROWSER.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_SOURCE_CODE      = NO
+
+# The LATEX_BIB_STYLE tag can be used to specify the style to use for the
+# bibliography, e.g. plainnat, or ieeetr. See
+# https://en.wikipedia.org/wiki/BibTeX and \cite for more info.
+# The default value is: plain.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_BIB_STYLE        = plain
+
+# If the LATEX_TIMESTAMP tag is set to YES then the footer of each generated
+# page will contain the date and time when the page was generated. Setting this
+# to NO can help when comparing the output of multiple runs.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_TIMESTAMP        = NO
+
+# The LATEX_EMOJI_DIRECTORY tag is used to specify the (relative or absolute)
+# path from which the emoji images will be read. If a relative path is entered,
+# it will be relative to the LATEX_OUTPUT directory. If left blank the
+# LATEX_OUTPUT directory will be used.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_EMOJI_DIRECTORY  =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the RTF output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_RTF tag is set to YES, doxygen will generate RTF output. The
+# RTF output is optimized for Word 97 and may not look too pretty with other RTF
+# readers/editors.
+# The default value is: NO.
+
+GENERATE_RTF           = NO
+
+# The RTF_OUTPUT tag is used to specify where the RTF docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: rtf.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_OUTPUT             = rtf
+
+# If the COMPACT_RTF tag is set to YES, doxygen generates more compact RTF
+# documents. This may be useful for small projects and may help to save some
+# trees in general.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+COMPACT_RTF            = NO
+
+# If the RTF_HYPERLINKS tag is set to YES, the RTF that is generated will
+# contain hyperlink fields. The RTF file will contain links (just like the HTML
+# output) instead of page references. This makes the output suitable for online
+# browsing using Word or some other Word compatible readers that support those
+# fields.
+#
+# Note: WordPad (write) and others do not support links.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_HYPERLINKS         = NO
+
+# Load stylesheet definitions from file. Syntax is similar to doxygen's
+# configuration file, i.e. a series of assignments. You only have to provide
+# replacements, missing definitions are set to their default value.
+#
+# See also section "Doxygen usage" for information on how to generate the
+# default style sheet that doxygen normally uses.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_STYLESHEET_FILE    =
+
+# Set optional variables used in the generation of an RTF document. Syntax is
+# similar to doxygen's configuration file. A template extensions file can be
+# generated using doxygen -e rtf extensionFile.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_EXTENSIONS_FILE    =
+
+# If the RTF_SOURCE_CODE tag is set to YES then doxygen will include source code
+# with syntax highlighting in the RTF output.
+#
+# Note that which sources are shown also depends on other settings such as
+# SOURCE_BROWSER.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_SOURCE_CODE        = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the man page output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_MAN tag is set to YES, doxygen will generate man pages for
+# classes and files.
+# The default value is: NO.
+
+GENERATE_MAN           = NO
+
+# The MAN_OUTPUT tag is used to specify where the man pages will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it. A directory man3 will be created inside the directory specified by
+# MAN_OUTPUT.
+# The default directory is: man.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_OUTPUT             = man
+
+# The MAN_EXTENSION tag determines the extension that is added to the generated
+# man pages. In case the manual section does not start with a number, the number
+# 3 is prepended. The dot (.) at the beginning of the MAN_EXTENSION tag is
+# optional.
+# The default value is: .3.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_EXTENSION          = .3
+
+# The MAN_SUBDIR tag determines the name of the directory created within
+# MAN_OUTPUT in which the man pages are placed. If defaults to man followed by
+# MAN_EXTENSION with the initial . removed.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_SUBDIR             =
+
+# If the MAN_LINKS tag is set to YES and doxygen generates man output, then it
+# will generate one additional man file for each entity documented in the real
+# man page(s). These additional files only source the real man page, but without
+# them the man command would be unable to find the correct page.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_LINKS              = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the XML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_XML tag is set to YES, doxygen will generate an XML file that
+# captures the structure of the code including all documentation.
+# The default value is: NO.
+
+GENERATE_XML           = NO
+
+# The XML_OUTPUT tag is used to specify where the XML pages will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: xml.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_OUTPUT             = xml
+
+# If the XML_PROGRAMLISTING tag is set to YES, doxygen will dump the program
+# listings (including syntax highlighting and cross-referencing information) to
+# the XML output. Note that enabling this will significantly increase the size
+# of the XML output.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_PROGRAMLISTING     = YES
+
+# If the XML_NS_MEMB_FILE_SCOPE tag is set to YES, doxygen will include
+# namespace members in file scope as well, matching the HTML output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_NS_MEMB_FILE_SCOPE = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the DOCBOOK output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_DOCBOOK tag is set to YES, doxygen will generate Docbook files
+# that can be used to generate PDF.
+# The default value is: NO.
+
+GENERATE_DOCBOOK       = NO
+
+# The DOCBOOK_OUTPUT tag is used to specify where the Docbook pages will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be put in
+# front of it.
+# The default directory is: docbook.
+# This tag requires that the tag GENERATE_DOCBOOK is set to YES.
+
+DOCBOOK_OUTPUT         = docbook
+
+# If the DOCBOOK_PROGRAMLISTING tag is set to YES, doxygen will include the
+# program listings (including syntax highlighting and cross-referencing
+# information) to the DOCBOOK output. Note that enabling this will significantly
+# increase the size of the DOCBOOK output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_DOCBOOK is set to YES.
+
+DOCBOOK_PROGRAMLISTING = NO
+
+#---------------------------------------------------------------------------
+# Configuration options for the AutoGen Definitions output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_AUTOGEN_DEF tag is set to YES, doxygen will generate an
+# AutoGen Definitions (see http://autogen.sourceforge.net/) file that captures
+# the structure of the code including all documentation. Note that this feature
+# is still experimental and incomplete at the moment.
+# The default value is: NO.
+
+GENERATE_AUTOGEN_DEF   = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the Perl module output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_PERLMOD tag is set to YES, doxygen will generate a Perl module
+# file that captures the structure of the code including all documentation.
+#
+# Note that this feature is still experimental and incomplete at the moment.
+# The default value is: NO.
+
+GENERATE_PERLMOD       = NO
+
+# If the PERLMOD_LATEX tag is set to YES, doxygen will generate the necessary
+# Makefile rules, Perl scripts and LaTeX code to be able to generate PDF and DVI
+# output from the Perl module output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_LATEX          = NO
+
+# If the PERLMOD_PRETTY tag is set to YES, the Perl module output will be nicely
+# formatted so it can be parsed by a human reader. This is useful if you want to
+# understand what is going on. On the other hand, if this tag is set to NO, the
+# size of the Perl module output will be much smaller and Perl will parse it
+# just the same.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_PRETTY         = YES
+
+# The names of the make variables in the generated doxyrules.make file are
+# prefixed with the string contained in PERLMOD_MAKEVAR_PREFIX. This is useful
+# so different doxyrules.make files included by the same Makefile don't
+# overwrite each other's variables.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_MAKEVAR_PREFIX =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the preprocessor
+#---------------------------------------------------------------------------
+
+# If the ENABLE_PREPROCESSING tag is set to YES, doxygen will evaluate all
+# C-preprocessor directives found in the sources and include files.
+# The default value is: YES.
+
+ENABLE_PREPROCESSING   = YES
+
+# If the MACRO_EXPANSION tag is set to YES, doxygen will expand all macro names
+# in the source code. If set to NO, only conditional compilation will be
+# performed. Macro expansion can be done in a controlled way by setting
+# EXPAND_ONLY_PREDEF to YES.
+# The default value is: NO.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+MACRO_EXPANSION        = NO
+
+# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES then
+# the macro expansion is limited to the macros specified with the PREDEFINED and
+# EXPAND_AS_DEFINED tags.
+# The default value is: NO.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+EXPAND_ONLY_PREDEF     = NO
+
+# If the SEARCH_INCLUDES tag is set to YES, the include files in the
+# INCLUDE_PATH will be searched if a #include is found.
+# The default value is: YES.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+SEARCH_INCLUDES        = YES
+
+# The INCLUDE_PATH tag can be used to specify one or more directories that
+# contain include files that are not input files but should be processed by the
+# preprocessor.
+# This tag requires that the tag SEARCH_INCLUDES is set to YES.
+
+INCLUDE_PATH           =
+
+# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard
+# patterns (like *.h and *.hpp) to filter out the header-files in the
+# directories. If left blank, the patterns specified with FILE_PATTERNS will be
+# used.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+INCLUDE_FILE_PATTERNS  =
+
+# The PREDEFINED tag can be used to specify one or more macro names that are
+# defined before the preprocessor is started (similar to the -D option of e.g.
+# gcc). The argument of the tag is a list of macros of the form: name or
+# name=definition (no spaces). If the definition and the "=" are omitted, "=1"
+# is assumed. To prevent a macro definition from being undefined via #undef or
+# recursively expanded use the := operator instead of the = operator.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+PREDEFINED             = __HIP_PLATFORM_AMD__
+
+# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then this
+# tag can be used to specify a list of macro names that should be expanded. The
+# macro definition that is found in the sources will be used. Use the PREDEFINED
+# tag if you want to use a different macro definition that overrules the
+# definition found in the source code.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+EXPAND_AS_DEFINED      =
+
+# If the SKIP_FUNCTION_MACROS tag is set to YES then doxygen's preprocessor will
+# remove all references to function-like macros that are alone on a line, have
+# an all uppercase name, and do not end with a semicolon. Such function macros
+# are typically used for boiler-plate code, and will confuse the parser if not
+# removed.
+# The default value is: YES.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+SKIP_FUNCTION_MACROS   = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to external references
+#---------------------------------------------------------------------------
+
+# The TAGFILES tag can be used to specify one or more tag files. For each tag
+# file the location of the external documentation should be added. The format of
+# a tag file without this location is as follows:
+# TAGFILES = file1 file2 ...
+# Adding location for the tag files is done as follows:
+# TAGFILES = file1=loc1 "file2 = loc2" ...
+# where loc1 and loc2 can be relative or absolute paths or URLs. See the
+# section "Linking to external documentation" for more information about the use
+# of tag files.
+# Note: Each tag file must have a unique name (where the name does NOT include
+# the path). If a tag file is not located in the directory in which doxygen is
+# run, you must also specify the path to the tagfile here.
+
+TAGFILES               =
+
+# When a file name is specified after GENERATE_TAGFILE, doxygen will create a
+# tag file that is based on the input files it reads. See section "Linking to
+# external documentation" for more information about the usage of tag files.
+
+GENERATE_TAGFILE       =
+
+# If the ALLEXTERNALS tag is set to YES, all external class will be listed in
+# the class index. If set to NO, only the inherited external classes will be
+# listed.
+# The default value is: NO.
+
+ALLEXTERNALS           = NO
+
+# If the EXTERNAL_GROUPS tag is set to YES, all external groups will be listed
+# in the modules index. If set to NO, only the current project's groups will be
+# listed.
+# The default value is: YES.
+
+EXTERNAL_GROUPS        = YES
+
+# If the EXTERNAL_PAGES tag is set to YES, all external pages will be listed in
+# the related pages index. If set to NO, only the current project's pages will
+# be listed.
+# The default value is: YES.
+
+EXTERNAL_PAGES         = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to the dot tool
+#---------------------------------------------------------------------------
+
+# If the CLASS_DIAGRAMS tag is set to YES, doxygen will generate a class diagram
+# (in HTML and LaTeX) for classes with base or super classes. Setting the tag to
+# NO turns the diagrams off. Note that this option also works with HAVE_DOT
+# disabled, but it is recommended to install and use dot, since it yields more
+# powerful graphs.
+# The default value is: YES.
+
+CLASS_DIAGRAMS         = YES
+
+# You can include diagrams made with dia in doxygen documentation. Doxygen will
+# then run dia to produce the diagram and insert it in the documentation. The
+# DIA_PATH tag allows you to specify the directory where the dia binary resides.
+# If left empty dia is assumed to be found in the default search path.
+
+DIA_PATH               =
+
+# If set to YES the inheritance and collaboration graphs will hide inheritance
+# and usage relations if the target is undocumented or is not a class.
+# The default value is: YES.
+
+HIDE_UNDOC_RELATIONS   = YES
+
+# If you set the HAVE_DOT tag to YES then doxygen will assume the dot tool is
+# available from the path. This tool is part of Graphviz (see:
+# http://www.graphviz.org/), a graph visualization toolkit from AT&T and Lucent
+# Bell Labs. The other options in this section have no effect if this option is
+# set to NO
+# The default value is: YES.
+
+HAVE_DOT               = YES
+
+# The DOT_NUM_THREADS specifies the number of dot invocations doxygen is allowed
+# to run in parallel. When set to 0 doxygen will base this on the number of
+# processors available in the system. You can set it explicitly to a value
+# larger than 0 to get control over the balance between CPU load and processing
+# speed.
+# Minimum value: 0, maximum value: 32, default value: 0.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_NUM_THREADS        = 0
+
+# When you want a differently looking font in the dot files that doxygen
+# generates you can specify the font name using DOT_FONTNAME. You need to make
+# sure dot is able to find the font, which can be done by putting it in a
+# standard location or by setting the DOTFONTPATH environment variable or by
+# setting DOT_FONTPATH to the directory containing the font.
+# The default value is: Helvetica.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTNAME           = Helvetica
+
+# The DOT_FONTSIZE tag can be used to set the size (in points) of the font of
+# dot graphs.
+# Minimum value: 4, maximum value: 24, default value: 10.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTSIZE           = 10
+
+# By default doxygen will tell dot to use the default font as specified with
+# DOT_FONTNAME. If you specify a different font using DOT_FONTNAME you can set
+# the path where dot can find it using this tag.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTPATH           =
+
+# If the CLASS_GRAPH tag is set to YES then doxygen will generate a graph for
+# each documented class showing the direct and indirect inheritance relations.
+# Setting this tag to YES will force the CLASS_DIAGRAMS tag to NO.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CLASS_GRAPH            = YES
+
+# If the COLLABORATION_GRAPH tag is set to YES then doxygen will generate a
+# graph for each documented class showing the direct and indirect implementation
+# dependencies (inheritance, containment, and class references variables) of the
+# class with other documented classes.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+COLLABORATION_GRAPH    = YES
+
+# If the GROUP_GRAPHS tag is set to YES then doxygen will generate a graph for
+# groups, showing the direct groups dependencies.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GROUP_GRAPHS           = YES
+
+# If the UML_LOOK tag is set to YES, doxygen will generate inheritance and
+# collaboration diagrams in a style similar to the OMG's Unified Modeling
+# Language.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+UML_LOOK               = NO
+
+# If the UML_LOOK tag is enabled, the fields and methods are shown inside the
+# class node. If there are many fields or methods and many nodes the graph may
+# become too big to be useful. The UML_LIMIT_NUM_FIELDS threshold limits the
+# number of items for each type to make the size more manageable. Set this to 0
+# for no limit. Note that the threshold may be exceeded by 50% before the limit
+# is enforced. So when you set the threshold to 10, up to 15 fields may appear,
+# but if the number exceeds 15, the total amount of fields shown is limited to
+# 10.
+# Minimum value: 0, maximum value: 100, default value: 10.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+UML_LIMIT_NUM_FIELDS   = 10
+
+# If the TEMPLATE_RELATIONS tag is set to YES then the inheritance and
+# collaboration graphs will show the relations between templates and their
+# instances.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+TEMPLATE_RELATIONS     = NO
+
+# If the INCLUDE_GRAPH, ENABLE_PREPROCESSING and SEARCH_INCLUDES tags are set to
+# YES then doxygen will generate a graph for each documented file showing the
+# direct and indirect include dependencies of the file with other documented
+# files.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INCLUDE_GRAPH          = YES
+
+# If the INCLUDED_BY_GRAPH, ENABLE_PREPROCESSING and SEARCH_INCLUDES tags are
+# set to YES then doxygen will generate a graph for each documented file showing
+# the direct and indirect include dependencies of the file with other documented
+# files.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INCLUDED_BY_GRAPH      = YES
+
+# If the CALL_GRAPH tag is set to YES then doxygen will generate a call
+# dependency graph for every global function or class method.
+#
+# Note that enabling this option will significantly increase the time of a run.
+# So in most cases it will be better to enable call graphs for selected
+# functions only using the \callgraph command. Disabling a call graph can be
+# accomplished by means of the command \hidecallgraph.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CALL_GRAPH             = NO
+
+# If the CALLER_GRAPH tag is set to YES then doxygen will generate a caller
+# dependency graph for every global function or class method.
+#
+# Note that enabling this option will significantly increase the time of a run.
+# So in most cases it will be better to enable caller graphs for selected
+# functions only using the \callergraph command. Disabling a caller graph can be
+# accomplished by means of the command \hidecallergraph.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CALLER_GRAPH           = NO
+
+# If the GRAPHICAL_HIERARCHY tag is set to YES then doxygen will graphical
+# hierarchy of all classes instead of a textual one.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GRAPHICAL_HIERARCHY    = YES
+
+# If the DIRECTORY_GRAPH tag is set to YES then doxygen will show the
+# dependencies a directory has on other directories in a graphical way. The
+# dependency relations are determined by the #include relations between the
+# files in the directories.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DIRECTORY_GRAPH        = YES
+
+# The DOT_IMAGE_FORMAT tag can be used to set the image format of the images
+# generated by dot. For an explanation of the image formats see the section
+# output formats in the documentation of the dot tool (Graphviz (see:
+# http://www.graphviz.org/)).
+# Note: If you choose svg you need to set HTML_FILE_EXTENSION to xhtml in order
+# to make the SVG files visible in IE 9+ (other browsers do not have this
+# requirement).
+# Possible values are: png, png:cairo, png:cairo:cairo, png:cairo:gd, png:gd,
+# png:gd:gd, jpg, jpg:cairo, jpg:cairo:gd, jpg:gd, jpg:gd:gd, gif, gif:cairo,
+# gif:cairo:gd, gif:gd, gif:gd:gd, svg, png:gd, png:gd:gd, png:cairo,
+# png:cairo:gd, png:cairo:cairo, png:cairo:gdiplus, png:gdiplus and
+# png:gdiplus:gdiplus.
+# The default value is: png.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_IMAGE_FORMAT       = png
+
+# If DOT_IMAGE_FORMAT is set to svg, then this option can be set to YES to
+# enable generation of interactive SVG images that allow zooming and panning.
+#
+# Note that this requires a modern browser other than Internet Explorer. Tested
+# and working are Firefox, Chrome, Safari, and Opera.
+# Note: For IE 9+ you need to set HTML_FILE_EXTENSION to xhtml in order to make
+# the SVG files visible. Older versions of IE do not have SVG support.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INTERACTIVE_SVG        = NO
+
+# The DOT_PATH tag can be used to specify the path where the dot tool can be
+# found. If left blank, it is assumed the dot tool can be found in the path.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_PATH               =
+
+# The DOTFILE_DIRS tag can be used to specify one or more directories that
+# contain dot files that are included in the documentation (see the \dotfile
+# command).
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOTFILE_DIRS           =
+
+# The MSCFILE_DIRS tag can be used to specify one or more directories that
+# contain msc files that are included in the documentation (see the \mscfile
+# command).
+
+MSCFILE_DIRS           =
+
+# The DIAFILE_DIRS tag can be used to specify one or more directories that
+# contain dia files that are included in the documentation (see the \diafile
+# command).
+
+DIAFILE_DIRS           =
+
+# When using plantuml, the PLANTUML_JAR_PATH tag should be used to specify the
+# path where java can find the plantuml.jar file. If left blank, it is assumed
+# PlantUML is not used or called during a preprocessing step. Doxygen will
+# generate a warning when it encounters a \startuml command in this case and
+# will not generate output for the diagram.
+
+PLANTUML_JAR_PATH      =
+
+# When using plantuml, the PLANTUML_CFG_FILE tag can be used to specify a
+# configuration file for plantuml.
+
+PLANTUML_CFG_FILE      =
+
+# When using plantuml, the specified paths are searched for files specified by
+# the !include statement in a plantuml block.
+
+PLANTUML_INCLUDE_PATH  =
+
+# The DOT_GRAPH_MAX_NODES tag can be used to set the maximum number of nodes
+# that will be shown in the graph. If the number of nodes in a graph becomes
+# larger than this value, doxygen will truncate the graph, which is visualized
+# by representing a node as a red box. Note that doxygen if the number of direct
+# children of the root node in a graph is already larger than
+# DOT_GRAPH_MAX_NODES then the graph will not be shown at all. Also note that
+# the size of a graph can be further restricted by MAX_DOT_GRAPH_DEPTH.
+# Minimum value: 0, maximum value: 10000, default value: 50.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_GRAPH_MAX_NODES    = 50
+
+# The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the graphs
+# generated by dot. A depth value of 3 means that only nodes reachable from the
+# root by following a path via at most 3 edges will be shown. Nodes that lay
+# further from the root node will be omitted. Note that setting this option to 1
+# or 2 may greatly reduce the computation time needed for large code bases. Also
+# note that the size of a graph can be further restricted by
+# DOT_GRAPH_MAX_NODES. Using a depth of 0 means no depth restriction.
+# Minimum value: 0, maximum value: 1000, default value: 0.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+MAX_DOT_GRAPH_DEPTH    = 0
+
+# Set the DOT_TRANSPARENT tag to YES to generate images with a transparent
+# background. This is disabled by default, because dot on Windows does not seem
+# to support this out of the box.
+#
+# Warning: Depending on the platform used, enabling this option may lead to
+# badly anti-aliased labels on the edges of a graph (i.e. they become hard to
+# read).
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_TRANSPARENT        = NO
+
+# Set the DOT_MULTI_TARGETS tag to YES to allow dot to generate multiple output
+# files in one run (i.e. multiple -o and -T options on the command line). This
+# makes dot run faster, but since only newer versions of dot (>1.8.10) support
+# this, this feature is disabled by default.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_MULTI_TARGETS      = NO
+
+# If the GENERATE_LEGEND tag is set to YES doxygen will generate a legend page
+# explaining the meaning of the various boxes and arrows in the dot generated
+# graphs.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GENERATE_LEGEND        = YES
+
+# If the DOT_CLEANUP tag is set to YES, doxygen will remove the intermediate dot
+# files that are used to generate the various graphs.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_CLEANUP            = YES
diff --git a/projects/hip/docs/doxygen-input/mainpage.txt b/projects/hip/docs/doxygen-input/mainpage.txt
new file mode 100644
index 0000000000..b1e6119a63
--- /dev/null
+++ b/projects/hip/docs/doxygen-input/mainpage.txt
@@ -0,0 +1,19 @@
+/**
+ * @file mainpage.cpp
+ * @brief : DoxyGen Main Page.
+ * @mainpage Heterogeneous-computing Interface for Portability (HIP)
+ * @tableofcontents
+ *
+ * The HIP interface makes it very easy to port existing CUDA apps to run on AMD GPUs,
+ * or to develop new apps that can run on either CUDA or AMD GPUs from a common source base.
+ *
+ *  - HIP is very thin and has little or no performance impact over coding directly in CUDA NVCC mode.
+ *  - HIP allows developers to use the "best" development environment and tools on each target platform.
+ *  - HIP allows coding in a single-source C++ programming language including features such as templates, C++11 lambdas,and more.
+ *  - HIPIFY tools automatically convert CUDA sources to HIP.
+ *  - Developers can specialize for CUDA or HIP to tune for performance or handle tricky cases with #ifdef.
+
+ *  - See the @ref API.
+
+
+*/
diff --git a/projects/hip/docs/doxygen-input/sync.txt b/projects/hip/docs/doxygen-input/sync.txt
new file mode 100644
index 0000000000..4341418358
--- /dev/null
+++ b/projects/hip/docs/doxygen-input/sync.txt
@@ -0,0 +1,49 @@
+/** @page Synchonization
+ * @tableofcontents
+
+ * # Host-synchronous behavior:
+   The following commands are "host-asynchronous" - meaning they do not wait for any preceding commands to complete, and may return control to the host thread before the requested operation completes:
+
+    - Kernel launches (hipLaunchKernel() )
+    - Asynchronous memory copies - any memory copy API which contains "Async", such as hipMemcpyAsync())
+    - Any memory set (for example, hipMemset());
+    - TODO
+
+   "Host-synchronous" commands have the following properties:
+    - wait for all previous commands to complete.
+    - will not return control back to host until the command completes.
+
+
+   The following commands are "host-synchronous". 
+
+    - hipMemcpy waits for preceding work in the same stream to complete.
+
+
+ * # Stream synchronization
+
+
+### Blocking
+
+The term "blocking" has two meanings in HIP.
+
+The first refers to synchronization commands (ie hipStreamSynchronize, hipEventSynchronize) that cause the host CPU to wait for GPU activity to complete.  
+These can either use an active where the host CPU spin-waits on the synchronization variable, or can use an interrupt-based scheme where the core is interrupted 
+when the wait completes.  The second technique is referred to as "blocking" (ie hipDeviceBlockingSync, hipEventBlockingSync) while the first is referred 
+to as "active".  Active can be appropriate for short tasks where latency is critical, but comes at the expense of a CPU core dedicated to monitoring the event.
+
+ ### HIP_LAUNCH_BLOCKING (also can use CUDA_LAUNCH_BLOCKING)
+
+    - The following commands become host-synchronous and will not return until the requested command has completed:
+
+      - Kernel launches (hipKernelLaunch).
+      - Memory set commands (hipMemset, hipMemsetAsync).
+      - Memory copy commands (hipMemcpy, hipMemsetAsync).
+
+    Note CUDA_LAUNCH_BLOCKING does add any pre-serialization to the commands and does not affect the concurrent stream behavior.  For example, 
+    even when CUDA_LAUNCH_BLOCKING is set, kernels or data copy commands launched to separate streams can execute concurrently.   Use the NULL
+    stream if additional stream synchronization is desired.
+
+
+
+ 
+*/