[llvm] [AMDGPU] Add additional optimization cases for llvm.amdgcn.wave.shuffle intrinsic (PR #182357)

[Matt Arsenault via llvm-commits]

================
@@ -483,6 +479,12 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
     return HasDPP && (HasGFX90AInsts || getGeneration() >= GFX10);
   }
 
+  bool hasDPPRowXMask() const { return HasDPP && getGeneration() >= GFX10; }
----------------
arsenm wrote:

Overlap with https://github.com/llvm/llvm-project/pull/182391

https://github.com/llvm/llvm-project/pull/182357