[llvm] AMDGPU: Fix packed 16-bit inline constants (PR #76522)

[Joe Nash via llvm-commits]

================
@@ -1096,7 +1096,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
   bool hasDstSelForwardingHazard() const { return GFX940Insts; }
 
   // Cannot use op_sel with v_dot instructions.
-  bool hasDOTOpSelHazard() const { return GFX940Insts; }
+  bool hasDOTOpSelHazard() const { return GFX940Insts || GFX11Insts; }
----------------
Sisyph wrote:

I assume this is done in this patch to avoid having to special case these instructions in the fold logic. If so, its ok with me.

https://github.com/llvm/llvm-project/pull/76522