yaxunl created this revision.
yaxunl added reviewers: tra, scchan, b-sumner, arsenm.
Herald added a project: All.
yaxunl requested review of this revision.
Herald added a subscriber: wdng.
start with example usage, predefined macros and env vars.
https://reviews.llvm.org/D154123
Files:
clang/docs/HIPSupport.rst
Index: clang/docs/HIPSupport.rst
===================================================================
--- /dev/null
+++ clang/docs/HIPSupport.rst
@@ -0,0 +1,104 @@
+.. raw:: html
+
+ <style type="text/css">
+ .none { background-color: #FFCCCC }
+ .part { background-color: #FFFF99 }
+ .good { background-color: #CCFF99 }
+ </style>
+
+.. role:: none
+.. role:: part
+.. role:: good
+
+.. contents::
+ :local:
+
+===========
+HIP Support
+===========
+
+`HIP (Heterogeneous-Compute Interface for Portability) <https://github.com/ROCm-Developer-Tools/HIP>`_
+is a C++ Runtime API and Kernel Language that allows developers to create portable applications for
+GPUs from single source code.
+
+Clang supports HIP on `ROCm platform <https://rocm.docs.amd.com/en/latest/#>`_.
+
+Example Usage
+=============
+
+To compile a HIP program, you can use the following command:
+
+.. code-block:: shell
+
+ clang -c --offload-arch=gfx906 test.hip -o test.o
+
+To link a HIP program, you can use this command:
+
+.. code-block:: shell
+
+ clang --hip-link --offload-arch=gfx906 test.o -o test
+
+In the above commands, ``gfx906`` is the GPU architecture that the code is being compiled for.
+The supported GPU architectures can be found in the `AMDGPU Processor Table <https://llvm.org/docs/AMDGPUUsage.html#processors>`_.
+Alternatively, you can run the ``amdgpu-arch`` tool that comes with Clang to list the GPU architecture on your sytem:
+
+.. code-block:: shell
+
+ amdgpu-arch
+
+You can also use ``--offload-arch=native`` to let ``amdgpu-arch`` automatically detect the GPU architecture on your system:
+
+.. code-block:: shell
+
+ clang -c --offload-arch=native test.hip -o test.o
+
+Environment Variables
+=====================
+
+.. list-table::
+ :header-rows: 1
+
+ * - Variable
+ - Description
+ - Default Value
+ * - ``ROCM_PATH``
+ - ROCm installation path.
+ - Empty
+ * - ``HIP_PATH``
+ - HIP runtime installation path.
+ - Empty
+ * - ``HIP_DEVICE_LIB_PATH``
+ - HIP device library installation path.
+ - Empty
+
+Predefined Macros
+=================
+
+.. list-table::
+ :header-rows: 1
+
+ * - Macro
+ - Description
+ * - ``__CLANG_RDC__``
+ - This macro indicates that Clang is used for relocatable device code compilation (RDC).
+ * - ``__HIP__``
+ - This macro is defined when the HIP language option is enabled. It is used to indicate that the code is being compiled for the HIP environment.
+ * - ``__HIPCC__``
+ - This macro indicates that the code is being compiled using the HIP compiler.
+ * - ``__HIP_MEMORY_SCOPE_SINGLETHREAD``
+ - This macro is set to 1 and represents the memory scope that is limited to a single thread in HIP.
+ * - ``__HIP_MEMORY_SCOPE_WAVEFRONT``
+ - This macro is set to 2 and represents the memory scope that is limited to a wavefront in HIP.
+ * - ``__HIP_MEMORY_SCOPE_WORKGROUP``
+ - This macro is set to 3 and represents the memory scope that is limited to a workgroup in HIP.
+ * - ``__HIP_MEMORY_SCOPE_AGENT``
+ - This macro is set to 4 and represents the memory scope that is limited to an agent in HIP.
+ * - ``__HIP_MEMORY_SCOPE_SYSTEM``
+ - This macro is set to 5 and represents the memory scope that is limited to the system in HIP.
+ * - ``__HIP_DEVICE_COMPILE__``
+ - This macro is defined when the code is being compiled for a HIP device.
+ * - ``__HIP_NO_IMAGE_SUPPORT``
+ - This macro is set to 1 when the target device does not support HIP image functions.
+ * - ``HIP_API_PER_THREAD_DEFAULT_STREAM``
+ - This macro is defined when the GPU default stream kind is set to per-thread.
+
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
