[llvm] [AMDGPU] Support lowering of cluster related instrinsics (PR #157978)

[Matt Arsenault via llvm-commits]

================
@@ -9528,6 +9643,19 @@ SDValue SITargetLowering::lowerWaveID(SelectionDAG &DAG, SDValue Op) const {
                      DAG.getConstant(25, SL, VT), DAG.getConstant(5, SL, VT));
 }
 
+SDValue SITargetLowering::lowerConstHwRegRead(SelectionDAG &DAG, SDValue Op,
+                                              AMDGPU::Hwreg::Id HwReg,
+                                              unsigned LowBit,
+                                              unsigned Width) const {
+  SDLoc SL(Op);
----------------
arsenm wrote:

Move to selection? 

https://github.com/llvm/llvm-project/pull/157978