Merge commit '7e06cf8f1ba2' from llvm.org/main into apple/main

Author: git apple-llvm automerger

llvm/include/llvm/Transforms/Scalar/LoopFlatten.h

@@ -24,7 +24,8 @@ class LoopFlattenPass : public PassInfoMixin<LoopFlattenPass> {
 public:
   LoopFlattenPass() = default;
 
-  PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
+  PreservedAnalyses run(LoopNest &LN, LoopAnalysisManager &LAM,
+                        LoopStandardAnalysisResults &AR, LPMUpdater &U);
 };
 
 } // end namespace llvm

llvm/lib/Passes/PassBuilder.cpp

@@ -617,7 +617,7 @@ PassBuilder::buildO1FunctionSimplificationPipeline(OptimizationLevel Level,
   FPM.addPass(SimplifyCFGPass());
   FPM.addPass(InstCombinePass());
   if (EnableLoopFlatten)
-    FPM.addPass(LoopFlattenPass());
+    FPM.addPass(createFunctionToLoopPassAdaptor(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),
@@ -792,7 +792,7 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
   FPM.addPass(SimplifyCFGPass());
   FPM.addPass(InstCombinePass());
   if (EnableLoopFlatten)
-    FPM.addPass(LoopFlattenPass());
+    FPM.addPass(createFunctionToLoopPassAdaptor(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.
@@ -1842,7 +1842,7 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
 
   // More loops are countable; try to optimize them.
   if (EnableLoopFlatten && Level.getSpeedupLevel() > 1)
-    MainFPM.addPass(LoopFlattenPass());
+    MainFPM.addPass(createFunctionToLoopPassAdaptor(LoopFlattenPass()));
 
   if (EnableConstraintElimination)
     MainFPM.addPass(ConstraintEliminationPass());

llvm/lib/Passes/PassRegistry.def

@@ -248,7 +248,7 @@ FUNCTION_PASS("guard-widening", GuardWideningPass())
 FUNCTION_PASS("load-store-vectorizer", LoadStoreVectorizerPass())
 FUNCTION_PASS("loop-simplify", LoopSimplifyPass())
 FUNCTION_PASS("loop-sink", LoopSinkPass())
-FUNCTION_PASS("loop-flatten", LoopFlattenPass())
+FUNCTION_PASS("loop-unroll-and-jam", LoopUnrollAndJamPass())
 FUNCTION_PASS("lowerinvoke", LowerInvokePass())
 FUNCTION_PASS("lowerswitch", LowerSwitchPass())
 FUNCTION_PASS("mem2reg", PromotePass())
@@ -389,6 +389,7 @@ LOOP_PASS("canon-freeze", CanonicalizeFreezeInLoopsPass())
 LOOP_PASS("dot-ddg", DDGDotPrinterPass())
 LOOP_PASS("invalidate<all>", InvalidateAllAnalysesPass())
 LOOP_PASS("licm", LICMPass())
+LOOP_PASS("loop-flatten", LoopFlattenPass())
 LOOP_PASS("loop-idiom", LoopIdiomRecognizePass())
 LOOP_PASS("loop-instsimplify", LoopInstSimplifyPass())
 LOOP_PASS("loop-interchange", LoopInterchangePass())

llvm/lib/Transforms/Scalar/LoopFlatten.cpp

@@ -658,10 +658,10 @@ static bool FlattenLoopPair(FlattenInfo &FI, DominatorTree *DT, LoopInfo *LI,
   return DoFlattenLoopPair(FI, DT, LI, SE, AC, TTI);
 }
 
-bool Flatten(DominatorTree *DT, LoopInfo *LI, ScalarEvolution *SE,
+bool Flatten(LoopNest &LN, DominatorTree *DT, LoopInfo *LI, ScalarEvolution *SE,
              AssumptionCache *AC, TargetTransformInfo *TTI) {
   bool Changed = false;
-  for (auto *InnerLoop : LI->getLoopsInPreorder()) {
+  for (Loop *InnerLoop : LN.getLoops()) {
     auto *OuterLoop = InnerLoop->getParentLoop();
     if (!OuterLoop)
       continue;
@@ -671,29 +671,17 @@ bool Flatten(DominatorTree *DT, LoopInfo *LI, ScalarEvolution *SE,
   return Changed;
 }
 
-PreservedAnalyses LoopFlattenPass::run(Function &F,
-                                       FunctionAnalysisManager &AM) {
-  auto *DT = &AM.getResult<DominatorTreeAnalysis>(F);
-  auto *LI = &AM.getResult<LoopAnalysis>(F);
-  auto *SE = &AM.getResult<ScalarEvolutionAnalysis>(F);
-  auto *AC = &AM.getResult<AssumptionAnalysis>(F);
-  auto *TTI = &AM.getResult<TargetIRAnalysis>(F);
+PreservedAnalyses LoopFlattenPass::run(LoopNest &LN, LoopAnalysisManager &LAM,
+                                       LoopStandardAnalysisResults &AR,
+                                       LPMUpdater &U) {
 
   bool Changed = false;
 
   // The loop flattening pass requires loops to be
   // in simplified form, and also needs LCSSA. Running
   // this pass will simplify all loops that contain inner loops,
   // regardless of whether anything ends up being flattened.
-  for (const auto &L : *LI) {
-    if (L->isInnermost())
-      continue;
-    Changed |=
-        simplifyLoop(L, DT, LI, SE, AC, nullptr, false /* PreserveLCSSA */);
-    Changed |= formLCSSARecursively(*L, *DT, LI, SE);
-  }
-
-  Changed |= Flatten(DT, LI, SE, AC, TTI);
+  Changed |= Flatten(LN, &AR.DT, &AR.LI, &AR.SE, &AR.AC, &AR.TTI);
 
   if (!Changed)
     return PreservedAnalyses::all();
@@ -740,5 +728,10 @@ bool LoopFlattenLegacyPass::runOnFunction(Function &F) {
   auto &TTIP = getAnalysis<TargetTransformInfoWrapperPass>();
   auto *TTI = &TTIP.getTTI(F);
   auto *AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
-  return Flatten(DT, LI, SE, AC, TTI);
+  bool Changed = false;
+  for (Loop *L : *LI) {
+    auto LN = LoopNest::getLoopNest(*L, *SE);
+    Changed |= Flatten(*LN, DT, LI, SE, AC, TTI);
+  }
+  return Changed;
 }