[llvm] [NVPTX] Add support for ldmatrix extensions introduced in PTX 9.4 (PR #224264)

via llvm-commits llvm-commits at lists.llvm.org
Thu Sep 17 04:10:38 PDT 2026


github-actions[bot] wrote:

<!--LLVM CODE FORMAT COMMENT: {darker}-->


:warning: Python code formatter, darker found issues in your code. :warning:

<details>
<summary>
You can test this locally with the following command:
</summary>

``````````bash
darker --check --diff -r origin/main...HEAD llvm/test/CodeGen/NVPTX/wmma-ptx94-sm90a.py llvm/test/CodeGen/NVPTX/wmma.py
``````````

:warning:
The reproduction instructions above might return results for more than one PR
in a stack if you are using a stacked PR workflow. You can limit the results by
changing `origin/main` to the base branch/commit you want to compare against.
:warning:

</details>

<details>
<summary>
View the diff from darker here.
</summary>

``````````diff
--- wmma.py	2026-09-17 10:59:07.000000 +0000
+++ wmma.py	2026-09-17 11:10:05.696264 +0000
@@ -423,11 +423,12 @@
         make_ldmatrix_ops(["m8n8"], ["x1", "x2", "x4"], ["b16"])
         + make_ldmatrix_ops(
             ["m16n16"], ["x1", "x2"], ["b8", "b8x16.b6x16_p32", "b8x16.b4x16_p64"]
         )
         + make_ldmatrix_ops(
-            ["m8n16"], ["x1", "x2", "x4"],
+            ["m8n16"],
+            ["x1", "x2", "x4"],
             ["b8x16.b6x16_p32", "b8x16.b4x16_p64", "s8.s4"],
         )
     )
 
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/224264


More information about the llvm-commits mailing list