[llvm] [AMDGPU] LiveRegOptimizer: fix PHI same-BB filter; consider i8/i16 binops on SDWA (PR #155800)

[Matt Arsenault via llvm-commits]

================
@@ -126,7 +126,37 @@ class LiveRegOptimizer {
     return LK.first != TargetLoweringBase::TypeLegal;
   }
 
-  bool isOpLegal(Instruction *I) { return isa<StoreInst, IntrinsicInst>(I); }
+  bool isOpLegal(Instruction *I) {
+    if (auto *Intr = dyn_cast<IntrinsicInst>(I))
+      return true; // FIXME: narrow to known native intrinsics (DOT/MFMA/tbuffer) or use TTI cost.
----------------
arsenm wrote:

I think TTI already has its own collection of hacks for these costs already?We shouldn't need to implement them twice? 

https://github.com/llvm/llvm-project/pull/155800