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

[Matt Arsenault 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
----------------
arsenm wrote:

the scalar cache isn't coherent with vector, it's difficult to migrate that direction 

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