[NewPM] Fix placement of LoopFlatten

[aeubanks]

Summary

https://reviews.llvm.org/D90402 was inconsistent with where it put
LoopFlatten between the two pass managers. It also missed adding it to
the non-O1 function simplification pipeline.

PR48738

[SjoerdMeijer]

I was going to look at this today, but thanks for fixing! :-)
LGTM

llvm/lib/Passes/PassBuilder.cpp

PassBuilder::buildO1FunctionSimplificationPipeline(OptimizationLevel Level,
   LPM1.addPass(LoopInstSimplifyPass());
   LPM1.addPass(LoopSimplifyCFGPass());
 
   LPM1.addPass(LoopRotatePass(/* Disable header duplication */ true));
   // TODO: Investigate promotion cap for O1.
   LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap));
   LPM1.addPass(SimpleLoopUnswitchPass());
 
-  if (EnableLoopFlatten)
-    FPM.addPass(LoopFlattenPass());
   LPM2.addPass(LoopIdiomRecognizePass());
   LPM2.addPass(IndVarSimplifyPass());
 
   for (auto &C : LateLoopOptimizationsEPCallbacks)
     C(LPM2, Level);
 
   LPM2.addPass(LoopDeletionPass());
   // Do not enable unrolling in PreLinkThinLTO phase during sample PGO
PassBuilder::buildO1FunctionSimplificationPipeline(OptimizationLevel Level,
   // this once as it is immutable.
   FPM.addPass(
       RequireAnalysisPass<OptimizationRemarkEmitterAnalysis, Function>());
   FPM.addPass(createFunctionToLoopPassAdaptor(
       std::move(LPM1), EnableMSSALoopDependency, /*UseBlockFrequencyInfo=*/true,
       DebugLogging));
   FPM.addPass(SimplifyCFGPass());
   FPM.addPass(InstCombinePass());
+  if (EnableLoopFlatten)
+    FPM.addPass(LoopFlattenPass());
   // The loop passes in LPM2 (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, /*UseBlockFrequencyInfo=*/false,
       DebugLogging));
 
   // Delete small array after loop unroll.
   FPM.addPass(SROA());
PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
   // this once as it is immutable.
   FPM.addPass(
       RequireAnalysisPass<OptimizationRemarkEmitterAnalysis, Function>());
   FPM.addPass(createFunctionToLoopPassAdaptor(
       std::move(LPM1), EnableMSSALoopDependency, /*UseBlockFrequencyInfo=*/true,
       DebugLogging));
   FPM.addPass(SimplifyCFGPass());
   FPM.addPass(InstCombinePass());
+  if (EnableLoopFlatten)
+    FPM.addPass(LoopFlattenPass());
   // 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, /*UseBlockFrequencyInfo=*/false,
       DebugLogging));
 
   // Delete small array after loop unroll.