merge amd-staging into amd-mainline

Change-Id: Ife1ef0ece8b2e4ab27f62be157b855fa9fe4e9bc

CMakeLists.txt

@@ -292,6 +292,7 @@ if(HIPIFY_CLANG_TESTS OR HIPIFY_CLANG_TESTS_ONLY)
   set(CUDA_TOOLKIT_ROOT_DIR "" CACHE PATH "Path to CUDA Toolkit to use in hipify-clang unit testing")
   set(CUDA_SDK_ROOT_DIR     "" CACHE PATH "Path to CUDA Toolkit Samples")
   set(CUDA_DNN_ROOT_DIR     "" CACHE PATH "Path to cuDNN")
+  set(CUDA_TENSOR_ROOT_DIR  "" CACHE PATH "Path to cuTENSOR")
   set(CUDA_CUB_ROOT_DIR     "" CACHE PATH "Path to CUB")
 
   if(NOT CUDA_TOOLKIT_ROOT_DIR STREQUAL "" AND NOT CUDA_TOOLKIT_ROOT_DIR MATCHES "OFF")
@@ -308,6 +309,7 @@ if(HIPIFY_CLANG_TESTS OR HIPIFY_CLANG_TESTS_ONLY)
   message(STATUS "   - CUDA Toolkit path     : ${CUDA_TOOLKIT_ROOT_DIR}")
   message(STATUS "   - CUDA Samples path     : ${CUDA_SDK_ROOT_DIR}")
   message(STATUS "   - cuDNN path            : ${CUDA_DNN_ROOT_DIR}")
+  message(STATUS "   - cuTENSOR path         : ${CUDA_TENSOR_ROOT_DIR}")
   message(STATUS "   - CUB path              : ${CUDA_CUB_ROOT_DIR}")
 
   if(${CMAKE_VERSION} VERSION_LESS "3.27.0")
@@ -346,6 +348,10 @@ if(HIPIFY_CLANG_TESTS OR HIPIFY_CLANG_TESTS_ONLY)
     set(CUDA_DNN_ROOT_DIR OFF)
   endif()
 
+  if(CUDA_TENSOR_ROOT_DIR STREQUAL "")
+    set(CUDA_TENSOR_ROOT_DIR OFF)
+  endif()
+
   if(CUDA_CUB_ROOT_DIR STREQUAL "")
     if(CUDA_VERSION VERSION_GREATER_EQUAL "11.0")
       if(WIN32 OR (UNIX AND CUDA_VERSION VERSION_LESS "11.4" OR CUDA_VERSION VERSION_GREATER_EQUAL "11.6"))
@@ -362,6 +368,7 @@ if(HIPIFY_CLANG_TESTS OR HIPIFY_CLANG_TESTS_ONLY)
   message(STATUS "   - CUDA Toolkit path     : ${CUDA_TOOLKIT_ROOT_DIR}")
   message(STATUS "   - CUDA Samples path     : ${CUDA_SDK_ROOT_DIR}")
   message(STATUS "   - cuDNN path            : ${CUDA_DNN_ROOT_DIR}")
+  message(STATUS "   - cuTENSOR path         : ${CUDA_TENSOR_ROOT_DIR}")
   message(STATUS "   - CUB path              : ${CUDA_CUB_ROOT_DIR}")
 
   if((CUDA_VERSION VERSION_LESS "7.0") OR (LLVM_PACKAGE_VERSION VERSION_LESS "3.8") OR

README.md

@@ -5,8 +5,7 @@ HIPIFY is a set of tools that you can use to automatically translate CUDA source
 
 ## Documentation
 
-Documentation for HIPIFY is available at
-[https://rocmdocs.amd.com/projects/HIPIFY/en/latest/](https://rocmdocs.amd.com/projects/HIPIFY/en/latest/).
+The published documentation is available at [HIPIFY](https://rocm.docs.amd.com/projects/HIPIFY/en/latest/index.html) in an organized, easy-to-read format, with search and a table of contents. The documentation source files reside in the `HIPIFY/docs` folder of this GitHub repository. As with all ROCm projects, the documentation is open source. For more information on contributing to the documentation, see [Contribute to ROCm documentation](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).
 
 To build our documentation locally, run the following code.
 

docs/hipify-clang.rst

@@ -37,11 +37,11 @@ Dependencies
 
 * `LLVM+Clang <http://releases.llvm.org>`_ of at least version
   `4.0.0 <http://releases.llvm.org/download.html#4.0.0>`_; the latest stable and recommended release:
-  `19.1.3 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.3>`_.
+  `19.1.5 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.5>`_.
 
 * `CUDA <https://developer.nvidia.com/cuda-downloads>`_ of at least version
   `7.0 <https://developer.nvidia.com/cuda-toolkit-70>`_, the latest supported version is
-  `12.6.2 <https://developer.nvidia.com/cuda-downloads>`_.
+  `12.6.3 <https://developer.nvidia.com/cuda-downloads>`_.
 
 .. list-table::
 
@@ -187,8 +187,10 @@ Dependencies
   * - `19.1.0 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.0>`_,
       `19.1.1 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.1>`_,
       `19.1.2 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.2>`_,
-      `19.1.3 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.3>`_:sup:`4`
-    - `12.6.2 <https://developer.nvidia.com/cuda-downloads>`_:sup:`4`
+      `19.1.3 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.3>`_,
+      `19.1.4 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.4>`_,
+      `19.1.5 <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.5>`_:sup:`4`
+    - `12.6.3 <https://developer.nvidia.com/cuda-downloads>`_:sup:`4`
     - **Latest stable config**
     - **Latest stable config**
 
@@ -230,7 +232,7 @@ Dependencies
 In most cases, you can get a suitable version of ``LLVM+Clang`` with your package manager. However, you can also
 `download a release archive <http://releases.llvm.org/>`_ and build or install it. In case of multiple versions of ``LLVM`` installed, set
 `CMAKE_PREFIX_PATH <https://cmake.org/cmake/help/latest/variable/CMAKE_PREFIX_PATH.html>`_ so that
-``CMake`` can find the desired version of ``LLVM``. For example, ``-DCMAKE_PREFIX_PATH=D:\LLVM\19.1.3\dist``.
+``CMake`` can find the desired version of ``LLVM``. For example, ``-DCMAKE_PREFIX_PATH=D:\LLVM\19.1.5\dist``.
 
 Usage
 ============================================================
@@ -263,7 +265,7 @@ header files used during the hipification process:
 
 .. code:: shell
 
-  ./hipify-clang square.cu --cuda-path=/usr/local/cuda-12.6 --clang-resource-directory=/usr/llvm/19.1.3/dist/lib/clang/19
+  ./hipify-clang square.cu --cuda-path=/usr/local/cuda-12.6 --clang-resource-directory=/usr/llvm/19.1.5/dist/lib/clang/19
 
 For more information, refer to the `Clang manual for compiling CUDA <https://llvm.org/docs/CompileCudaWithLLVM.html#compiling-cuda-code>`_.
 
@@ -400,7 +402,7 @@ To ensure LLVM being found or in case of multiple LLVM instances, specify the pa
 
 .. code-block:: bash
 
-  -DCMAKE_PREFIX_PATH=/usr/llvm/19.1.3/dist
+  -DCMAKE_PREFIX_PATH=/usr/llvm/19.1.5/dist
 
 On Windows, specify the following option for CMake in the first place:
 ``-G "Visual Studio 17 2022"``. 
@@ -474,7 +476,7 @@ LLVM <= 9.0.1
 LLVM >= 10.0.0
 -----------------
 
-1. Download `LLVM project <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.3>`_ sources.
+1. Download `LLVM project <https://github.com/llvm/llvm-project/releases/tag/llvmorg-19.1.5>`_ sources.
 
 2. Build `LLVM project <http://llvm.org/docs/CMake.html>`_:
 
@@ -548,7 +550,7 @@ LLVM >= 10.0.0
 
      .. code-block:: shell
       
-      -DCUDA_DNN_ROOT_DIR=D:/CUDA/cuDNN/9.5.1
+      -DCUDA_DNN_ROOT_DIR=D:/CUDA/cuDNN/9.6.0
 
 5. [Optional] Install `CUB 1.9.8 <https://github.com/NVIDIA/cub/releases/tag/1.9.8>`_ for ``CUDA < 11.0`` only;
    for ``CUDA >= 11.0``, the CUB shipped with CUDA will be used for testing.
@@ -577,13 +579,13 @@ LLVM >= 10.0.0
 
      .. code-block:: bash
 
-      python /usr/llvm/19.1.3/llvm-project/llvm/utils/lit/setup.py install
+      python /usr/llvm/19.1.5/llvm-project/llvm/utils/lit/setup.py install
       
      **Windows**:
 
      .. code-block:: shell
 
-      python D:/LLVM/19.1.3/llvm-project/llvm/utils/lit/setup.py install
+      python D:/LLVM/19.1.5/llvm-project/llvm/utils/lit/setup.py install
 
      In case of errors similar to ``ModuleNotFoundError: No module named 'setuptools'``, upgrade the ``setuptools`` package:
 
@@ -597,23 +599,23 @@ LLVM >= 10.0.0
 
      .. code-block:: bash
 
-      -DLLVM_EXTERNAL_LIT=/usr/llvm/19.1.3/build/bin/llvm-lit
+      -DLLVM_EXTERNAL_LIT=/usr/llvm/19.1.5/build/bin/llvm-lit
 
      **Windows**:
 
      .. code-block:: shell
 
-      -DLLVM_EXTERNAL_LIT=D:/LLVM/19.1.3/build/Release/bin/llvm-lit.py
+      -DLLVM_EXTERNAL_LIT=D:/LLVM/19.1.5/build/Release/bin/llvm-lit.py
 
    * ``FileCheck``:
 
      **Linux**:
 
-     Copy from ``/usr/llvm/19.1.3/build/bin/`` to ``CMAKE_INSTALL_PREFIX/dist/bin``.
+     Copy from ``/usr/llvm/19.1.5/build/bin/`` to ``CMAKE_INSTALL_PREFIX/dist/bin``.
 
      **Windows**:
 
-     Copy from ``D:/LLVM/19.1.3/build/Release/bin`` to ``CMAKE_INSTALL_PREFIX/dist/bin``.
+     Copy from ``D:/LLVM/19.1.5/build/Release/bin`` to ``CMAKE_INSTALL_PREFIX/dist/bin``.
 
      Alternatively, specify the path to ``FileCheck`` in the ``CMAKE_INSTALL_PREFIX`` option.
 
@@ -640,16 +642,16 @@ On Linux, the following configurations are tested:
 
 * Ubuntu 14: LLVM 4.0.0 - 7.1.0, CUDA 7.0 - 9.0, cuDNN 5.0.5 - 7.6.5
 * Ubuntu 16-19: LLVM 8.0.0 - 14.0.6, CUDA 7.0 - 10.2, cuDNN 5.1.10 - 8.0.5
-* Ubuntu 20-21: LLVM 9.0.0 - 19.1.3, CUDA 7.0 - 12.6.2, cuDNN 5.1.10 - 9.5.1
-* Ubuntu 22-23: LLVM 13.0.0 - 19.1.3, CUDA 7.0 - 12.6.2, cuDNN 8.0.5 - 9.5.1
+* Ubuntu 20-21: LLVM 9.0.0 - 19.1.5, CUDA 7.0 - 12.6.3, cuDNN 5.1.10 - 9.6.0
+* Ubuntu 22-23: LLVM 13.0.0 - 19.1.5, CUDA 7.0 - 12.6.3, cuDNN 8.0.5 - 9.6.0
 
 Minimum build system requirements for the above configurations:
 
 * CMake 3.16.8, GNU C/C++ 9.2, Python 3.0.
 
 Recommended build system requirements:
 
-* CMake 3.31.0, GNU C/C++ 13.2, Python 3.13.0.
+* CMake 3.31.2, GNU C/C++ 13.2, Python 3.13.1.
 
 Here's how to build ``hipify-clang`` with testing support on ``Ubuntu 23.10.01``:
 
@@ -659,10 +661,10 @@ Here's how to build ``hipify-clang`` with testing support on ``Ubuntu 23.10.01``
   -DHIPIFY_CLANG_TESTS=ON \
   -DCMAKE_BUILD_TYPE=Release \
   -DCMAKE_INSTALL_PREFIX=../dist \
-  -DCMAKE_PREFIX_PATH=/usr/llvm/19.1.3/dist \
-  -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda-12.6.2 \
-  -DCUDA_DNN_ROOT_DIR=/usr/local/cudnn-9.5.1 \
-  -DLLVM_EXTERNAL_LIT=/usr/llvm/19.1.3/build/bin/llvm-lit \
+  -DCMAKE_PREFIX_PATH=/usr/llvm/19.1.5/dist \
+  -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda-12.6.3 \
+  -DCUDA_DNN_ROOT_DIR=/usr/local/cudnn-9.6.0 \
+  -DLLVM_EXTERNAL_LIT=/usr/llvm/19.1.5/build/bin/llvm-lit \
   ../hipify
 
 The corresponding successful output is:
@@ -686,30 +688,30 @@ The corresponding successful output is:
   --    - Test  hipify-clang : ON
   --    - Is part of HIP SDK : OFF
   -- Found ZLIB: /usr/lib/x86_64-linux-gnu/libz.so (found version "1.2.13")
-  -- Found LLVM 19.1.3:
-  --    - CMake module path  : /usr/llvm/19.1.3/dist/lib/cmake/llvm
-  --    - Clang include path : /usr/llvm/19.1.3/dist/include
-  --    - LLVM Include path  : /usr/llvm/19.1.3/dist/include
-  --    - Binary path        : /usr/llvm/19.1.3/dist/bin
+  -- Found LLVM 19.1.5:
+  --    - CMake module path  : /usr/llvm/19.1.5/dist/lib/cmake/llvm
+  --    - Clang include path : /usr/llvm/19.1.5/dist/include
+  --    - LLVM Include path  : /usr/llvm/19.1.5/dist/include
+  --    - Binary path        : /usr/llvm/19.1.5/dist/bin
   -- Linker detection: GNU ld
   -- ---- The below configuring for hipify-clang testing only ----
-  -- Found Python: /usr/bin/python3.13 (found version "3.13.0") found components: Interpreter 
+  -- Found Python: /usr/bin/python3.13 (found suitable version "3.13.1", required range is "3.0...3.14") found components: Interpreter
   -- Found lit: /usr/local/bin/lit
   -- Found FileCheck: /GIT/LLVM/trunk/dist/FileCheck
   -- Initial CUDA to configure:
-  --    - CUDA Toolkit path  : /usr/local/cuda-12.6.2
+  --    - CUDA Toolkit path  : /usr/local/cuda-12.6.3
   --    - CUDA Samples path  :
-  --    - cuDNN path         : /usr/local/cudnn-9.5.1
+  --    - cuDNN path         : /usr/local/cudnn-9.6.0
   --    - CUB path           :
-  -- Found CUDAToolkit: /usr/local/cuda-12.6.2/targets/x86_64-linux/include (found version "12.6.68")
+  -- Found CUDAToolkit: /usr/local/cuda-12.6.3/targets/x86_64-linux/include (found version "12.6.85")
   -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
   -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
   -- Found Threads: TRUE
   -- Found CUDA config:
-  --    - CUDA Toolkit path  : /usr/local/cuda-12.6.2
+  --    - CUDA Toolkit path  : /usr/local/cuda-12.6.3
   --    - CUDA Samples path  : OFF
-  --    - cuDNN path         : /usr/local/cudnn-9.5.1
-  --    - CUB path           : /usr/local/cuda-12.6.2/include/cub
+  --    - cuDNN path         : /usr/local/cudnn-9.6.0
+  --    - CUB path           : /usr/local/cuda-12.6.3/include/cub
   -- Configuring done (0.5s)
   -- Generating done (0.0s)
   -- Build files have been written to: /usr/hipify/build
@@ -724,12 +726,12 @@ The corresponding successful output is:
 
   Running HIPify regression tests
   ===============================================================
-  CUDA 12.6.68 - will be used for testing
-  LLVM 19.1.3 - will be used for testing
+  CUDA 12.6.85 - will be used for testing
+  LLVM 19.1.5 - will be used for testing
   x86_64 - Platform architecture
   Linux 6.5.0-15-generic - Platform OS
   64 - hipify-clang binary bitness
-  64 - python 3.13.0 binary bitness
+  64 - python 3.13.1 binary bitness
   ===============================================================
   -- Testing: 106 tests, 12 threads --
   Testing Time: 6.91s
@@ -821,16 +823,16 @@ Tested configurations:
     - ``3.11.4``
   * - ``17.0.1`` :sup:`6` - ``18.1.8`` :sup:`7`
     - ``7.0 - 12.3.2``
-    - ``8.0.5  - 9.5.1``
-    - ``2019.16.11.42, 2022.17.11.6``
-    - ``3.31.0``
-    - ``3.13.0``
-  * - ``19.1.0 - 19.1.3``
-    - ``7.0 - 12.6.2``
-    - ``8.0.5  - 9.5.1``
-    - ``2019.16.11.42, 2022.17.11.6``
-    - ``3.31.0``
-    - ``3.13.0``
+    - ``8.0.5  - 9.6.0``
+    - ``2019.16.11.42, 2022.17.12.3``
+    - ``3.31.2``
+    - ``3.13.1``
+  * - ``19.1.0 - 19.1.5``
+    - ``7.0 - 12.6.3``
+    - ``8.0.5  - 9.6.0``
+    - ``2019.16.11.42, 2022.17.12.3``
+    - ``3.31.2``
+    - ``3.13.1``
 
 :sup:`5` LLVM 14.x.x is the latest major release supporting Visual Studio 2017.
 
@@ -855,11 +857,11 @@ Building with testing support using ``Visual Studio 17 2022`` on ``Windows 11``:
   -DHIPIFY_CLANG_TESTS=ON \
   -DCMAKE_BUILD_TYPE=Release \
   -DCMAKE_INSTALL_PREFIX=../dist \
-  -DCMAKE_PREFIX_PATH=D:/LLVM/19.1.3/dist \
+  -DCMAKE_PREFIX_PATH=D:/LLVM/19.1.5/dist \
   -DCUDA_TOOLKIT_ROOT_DIR="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6" \
   -DCUDA_SDK_ROOT_DIR="C:/ProgramData/NVIDIA Corporation/CUDA Samples/v12.5" \
-  -DCUDA_DNN_ROOT_DIR=D:/CUDA/cuDNN/9.5.1 \
-  -DLLVM_EXTERNAL_LIT=D:/LLVM/19.1.3/build/Release/bin/llvm-lit.py \
+  -DCUDA_DNN_ROOT_DIR=D:/CUDA/cuDNN/9.6.0 \
+  -DLLVM_EXTERNAL_LIT=D:/LLVM/19.1.5/build/Release/bin/llvm-lit.py \
   ../hipify
 
 The corresponding successful output is:
@@ -883,25 +885,25 @@ The corresponding successful output is:
   --    - Build hipify-clang : ON
   --    - Test  hipify-clang : ON
   --    - Is part of HIP SDK : OFF
-  -- Found LLVM 19.1.3:
-  --    - CMake module path  : D:/LLVM/19.1.3/dist/lib/cmake/llvm
-  --    - Clang include path : D:/LLVM/19.1.3/dist/include
-  --    - LLVM Include path  : D:/LLVM/19.1.3/dist/include
-  --    - Binary path        : D:/LLVM/19.1.3/dist/bin
+  -- Found LLVM 19.1.5:
+  --    - CMake module path  : D:/LLVM/19.1.5/dist/lib/cmake/llvm
+  --    - Clang include path : D:/LLVM/19.1.5/dist/include
+  --    - LLVM Include path  : D:/LLVM/19.1.5/dist/include
+  --    - Binary path        : D:/LLVM/19.1.5/dist/bin
   -- ---- The below configuring for hipify-clang testing only ----
-  -- Found Python: C:/Users/TT/AppData/Local/Programs/Python/Python313/python.exe (found version "3.13.0") found components: Interpreter
+  -- Found Python: C:/Users/evgen/AppData/Local/Programs/Python/Python313/python.exe (found suitable version "3.13.1", required range is "3.0...3.14") found components: Interpreter
   -- Found lit: C:/Users/TT/AppData/Local/Programs/Python/Python313/Scripts/lit.exe
-  -- Found FileCheck: D:/LLVM/19.1.3/dist/bin/FileCheck.exe
+  -- Found FileCheck: D:/LLVM/19.1.5/dist/bin/FileCheck.exe
   -- Initial CUDA to configure:
   --    - CUDA Toolkit path  : C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6
   --    - CUDA Samples path  : C:/ProgramData/NVIDIA Corporation/CUDA Samples/v12.5
-  --    - cuDNN path         : D:/CUDA/cuDNN/9.5.1
+  --    - cuDNN path         : D:/CUDA/cuDNN/9.6.0
   --    - CUB path           :
-  -- Found CUDAToolkit: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6/include (found version "12.6.68")
+  -- Found CUDAToolkit: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6/include (found version "12.6.85")
   -- Found CUDA config:
   --    - CUDA Toolkit path  : C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6
   --    - CUDA Samples path  : C:/ProgramData/NVIDIA Corporation/CUDA Samples/v12.5
-  --    - cuDNN path         : D:/CUDA/cuDNN/9.5.1
+  --    - cuDNN path         : D:/CUDA/cuDNN/9.6.0
   --    - CUB path           : C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6/include/cub
   -- Configuring done (2.1s)
   -- Generating done (0.1s)

docs/index.rst

@@ -12,7 +12,7 @@ HIPIFY documentation
 
 .. note::
 
-    `hipify_torch <https://github.com/ROCmSoftwarePlatform/hipify_torch>`_ is a related tool that also translates CUDA source code into portable HIP C++. It was initially developed as part of the PyTorch project to cater to the project's unique requirements but was found to be useful for PyTorch-related projects and thus was released as an independent utility.
+    `hipify_torch <https://github.com/ROCm/hipify_torch>`_ is a related tool that also translates CUDA source code into portable HIP C++. It was initially developed as part of the PyTorch project to cater to the project's unique requirements but was found to be useful for PyTorch-related projects and thus was released as an independent utility.
 
 You can access HIPIFY code on our `GitHub repository <https://github.com/ROCm/HIPIFY>`_.
 

docs/sphinx/requirements.in

@@ -1 +1 @@
-rocm-docs-core==1.8.3
+rocm-docs-core==1.12.0

docs/sphinx/requirements.txt

@@ -92,7 +92,7 @@ requests==2.32.2
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.8.3
+rocm-docs-core==1.12.0
     # via -r requirements.in
 smmap==5.0.1
     # via gitdb