[NFC] integrate Function SLU into O3

[drcut]

Summary

Integrate FunctionPass LoopUnswitch implementation into the O3 pipeline. In default, it will not be invoked.

llvm/lib/Passes/PassBuilderPipelines.cpp

cl::desc(
         "Prevent running the simplification pipeline on a function more "
         "than once in the case that SCC mutations cause a function to be "
         "visited multiple times as long as the function has not been changed"));
 
 static cl::opt<bool> EnableMergeFunctions(
     "enable-merge-functions", cl::init(false), cl::Hidden,
     cl::desc("Enable function merging as part of the optimization pipeline"));
 
+static cl::opt<bool> UseFuncPassNonTrivialLoopUnswitch(
+    "use-funcpass-nontrivial-unswitch", cl::init(false), cl::Hidden,
+    cl::desc("Use FuncPass implementation for non-trivial LoopUnswitch"));
+
 PipelineTuningOptions::PipelineTuningOptions() {
   LoopInterleaving = true;
   LoopVectorization = true;
   SLPVectorization = false;
   LoopUnrolling = true;
   ForgetAllSCEVInLoopUnroll = ForgetSCEVInLoopUnroll;
   LicmMssaOptCap = SetLicmMssaOptCap;
   LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap;
LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap,
                         /*AllowSpeculation=*/false));
 
   // Disable header duplication in loop rotation at -Oz.
   LPM1.addPass(
       LoopRotatePass(Level != OptimizationLevel::Oz, isLTOPreLink(Phase)));
   // TODO: Investigate promotion cap for O1.
   LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap,
                         /*AllowSpeculation=*/true));
+  bool RequireFuncNonTrivialUnswitching = (Level == OptimizationLevel::O3) &&
+                                          EnableO3NonTrivialUnswitching &&
+                                          UseFuncPassNonTrivialLoopUnswitch;
+  if (!RequireFuncNonTrivialUnswitching) {
     LPM1.addPass(
         SimpleLoopUnswitchPass(/* NonTrivial */ Level == OptimizationLevel::O3 &&
                               EnableO3NonTrivialUnswitching));
     if (EnableLoopFlatten)
       LPM1.addPass(LoopFlattenPass());
+  } else {
+    LPM1.addPass(SimpleLoopUnswitchPass(
+        /* NonTrivial */ false));
+  }
 
   LPM2.addPass(LoopIdiomRecognizePass());
   LPM2.addPass(IndVarSimplifyPass());
 
   for (auto &C : LateLoopOptimizationsEPCallbacks)
     C(LPM2, Level);
 
   LPM2.addPass(LoopDeletionPass());
PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
 
   // We provide the opt remark emitter pass for LICM to use. We only need to do
   // this once as it is immutable.
   FPM.addPass(
       RequireAnalysisPass<OptimizationRemarkEmitterAnalysis, Function>());
   FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM1),
                                               /*UseMemorySSA=*/true,
                                               /*UseBlockFrequencyInfo=*/true));
+  if (RequireFuncNonTrivialUnswitching) {
+    FPM.addPass(FuncSimpleLoopUnswitchPass());
+    if (EnableLoopFlatten) {
+      // CFGs generated by FuncSLU should be simplified before LoopFlatten
+      FPM.addPass(
+            SimplifyCFGPass(SimplifyCFGOptions().convertSwitchRangeToICmp(true)));
+      FPM.addPass(createFunctionToLoopPassAdaptor(
+          LoopFlattenPass(),
+          /*UseMemorySSA=*/true, /*UseBlockFrequencyInfo=*/true));
+    }
+  }
   FPM.addPass(
       SimplifyCFGPass(SimplifyCFGOptions().convertSwitchRangeToICmp(true)));
   FPM.addPass(InstCombinePass());
   // The loop passes in LPM2 (LoopIdiomRecognizePass, IndVarSimplifyPass,
   // LoopDeletionPass and LoopFullUnrollPass) do not preserve MemorySSA.
   // *All* loop passes must preserve it, in order to be able to use it.
   FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM2),
                                               /*UseMemorySSA=*/false,