[PATCH] D84822: Add documentation for target ID and ClangOffloadBundlerFormat

[Tony Tye via Phabricator via llvm-commits]

t-tye added inline comments.


================
Comment at: clang/docs/ClangOffloadBundlerFileFormat.rst:25
+  binary is compiled. If target ID is supported by the target, this is the target ID for which the
+  device binary is compiled (see `Target ID Definition <https://llvm.org/docs/AMDGPUUsage.html#target-ids>`_).
+
----------------
for AMD GPU see


================
Comment at: clang/docs/ClangOffloadBundlerFileFormat.rst:87-89
+If target ID is supported, the rules of compatible offload targets in a single bundled device binary is defined
+in `AMDGPU Embedding Bundled Code Objects
+  <https://llvm.org/docs/AMDGPUUsage.html#embedding-bundled-objects>`_.
----------------
defined by the target (for AMD GPU see `AMDGPU Embedding Bundled Code Objects
  <https://llvm.org/docs/AMDGPUUsage.html#embedding-bundled-objects>`_).


================
Comment at: llvm/docs/AMDGPUUsage.rst:90
 
 Processors
 ----------
----------------
We should move the code object V3 into a separate page so we continue to define that ABI since old code objects still exist. Then these changes can define the code object V4, with a reference to the pages for previous vesions.


================
Comment at: llvm/docs/AMDGPUUsage.rst:264
+                                                                                    .. TODO
+                                                                                       Add product
+                                                                                       names.
----------------
```
*TBA*

.. TODO::
  Add product
  names.
```


================
Comment at: llvm/docs/AMDGPUUsage.rst:7679
+.amdgcn_target <target_triple> "-" <target_id>
 +++++++++++++++++++++++
 
----------------
Make +'s match length of above title.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D84822/new/

https://reviews.llvm.org/D84822