[llvm] [NVPTX] Add intrinsic support for specialized prmt variants (PR #140951)

[Alex MacLean via llvm-commits]

================
@@ -661,6 +661,126 @@ all bits set to 0 except for %b bits starting at bit position %a. For the
 '``clamp``' variants, the values of %a and %b are clamped to the range [0, 32],
 which in practice is equivalent to using them as is.
 
+'``llvm.nvvm.prmt``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+.. code-block:: llvm
+
+    declare i32 @llvm.nvvm.prmt(i32 %a, i32 %b, i32 %c)
----------------
AlexMaclean wrote:

Fixed

https://github.com/llvm/llvm-project/pull/140951