[llvm] [NVPTX] Add float to tf32 conversion intrinsics (PR #124316)

[Artem Belevich via llvm-commits]

================
@@ -311,6 +311,9 @@ def enable_ptxas(ptxas_executable):
             (12, 2),
             (12, 3),
             (12, 4),
+            (12, 5),
+            (12, 6),
+            (12, 8),
----------------
Artem-B wrote:

This should probably be a separate commit, as it has little to do with the rest of the patch.

https://github.com/llvm/llvm-project/pull/124316