[llvm] [NVPTX] Add support for clamped funnel shift intrinsics (PR #113228)

[Artem Belevich via llvm-commits]

================
@@ -319,6 +319,64 @@ used in the '``llvm.nvvm.idp4a.[us].u``' variants, while sign-extension is used
 with '``llvm.nvvm.idp4a.[us].s``' variants. The dot product of these 4-element
 vectors is added to ``%c`` to produce the return.
 
+Bit Manipulation Intrinsics
+---------------------------
+
+'``llvm.nvvm.fshl.clamp.*``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+.. code-block:: llvm
+
+    declare i32 @llvm.nvvm.fshl.clamp.i32(i32 %a, i32 %b, i32 %c)
+
+Overview:
+"""""""""
+
+The '``llvm.nvvm.fshl.clamp``' family of intrinsics performs a clamped funnel
+shift left. These intrinsics are very similar to '``llvm.fshl``', except the
+shift ammont is clamped at the integer width (instead of modulo it). Currently,
+only ``i32`` is supported.
+
+Semantics:
+""""""""""
+
+The '``llvm.nvvm.fshl.clamp``' family of intrinsic functions performs a clamped
+funnel shift left: the first two values are concatenated as { %a : %b } (%a is
+the most significant bits of the wide value), the combined value is shifted
----------------
Artem-B wrote:

Can we rename `%a, %b, %c` -> `%hi,%lo,%n`so the purpose of each argument is obvious from the function syntax alone, without having to read and parse a paragraph-long sentence?


https://github.com/llvm/llvm-project/pull/113228