[clang] [llvm] [AMDGPU] Add target intrinsic for s_prefetch_data (PR #107133)

[Matt Arsenault via cfe-commits]

================
@@ -2689,6 +2689,12 @@ def int_amdgcn_global_load_tr_b128 : AMDGPULoadIntrinsic<global_ptr_ty>;
 def int_amdgcn_wave_id :
   DefaultAttrsIntrinsic<[llvm_i32_ty], [], [NoUndef<RetIndex>, IntrNoMem, IntrSpeculatable]>;
 
+def int_amdgcn_s_prefetch_data :
+  Intrinsic<[], [llvm_anyptr_ty, llvm_i32_ty],
----------------
arsenm wrote:

Comment the operands? How is this different from the regular llvm.prefetch? 

https://github.com/llvm/llvm-project/pull/107133