[llvm] [docs][amdgpu] Update kernarg documentation for gfx90a (PR #109690)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Jakub Kuderski (kuhar)

<details>
<summary>Changes</summary>

Update the docs to mention that kernel argument preloading is not supported on MI210.

---
Full diff: https://github.com/llvm/llvm-project/pull/109690.diff


1 Files Affected:

- (modified) llvm/docs/AMDGPUUsage.rst (+1-1) 


``````````diff
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index ba62a68c4a509e..5526d2b8fa9eb9 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -361,7 +361,7 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
                                                     - tgsplit           flat          - *rocm-amdhsa* - AMD Instinct MI250 Accelerator
                                                     - xnack             scratch       - *rocm-amdhsa* - AMD Instinct MI250X Accelerator
                                                     - kernarg preload - Packed
-                                                                        work-item
+                                                      (except MI210)    work-item
                                                                         IDs
 
      ``gfx90c``                  ``amdgcn``   APU   - xnack           - Absolute      - *pal-amdpal*  - Ryzen 7 4700G

``````````

</details>


https://github.com/llvm/llvm-project/pull/109690