[clang] [llvm] [mlir] [AMDGPU] Add ptr.s.buffer.load intrinsic, use it from Clang (PR #209243)

[Scott Linder via cfe-commits]

================
@@ -1485,6 +1485,33 @@ def int_amdgcn_s_buffer_load : DefaultAttrsIntrinsic <
   [IntrNoMem, ImmArg<ArgIndex<2>>]>,
   AMDGPURsrcIntrinsic<0>;
 
+// Generate an s_buffer_load instruction, falling back to buffer_load if the offset
+// is not uniform. This operates like the s.buffer.load intrinsic, but uses a buffer
----------------
slinder1 wrote:

We should probably update the old intrinsic wording too, then?

Alternatively it seems like we can define one in terms of the other. I.e. keep your now wording, and update the comment for the old intrinsic to be "an int_amdgcn_ptr_s_buffer_load except <describe the difference>"

https://github.com/llvm/llvm-project/pull/209243