!fixup Add AddAdditionalAccumulators TTI flag

Author: fhahn

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -638,6 +638,8 @@ class TargetTransformInfo {
     /// Fall back to the generic logic to determine whether multi-exit unrolling
     /// is profitable if set to false.
     bool RuntimeUnrollMultiExit;
+    /// Allow unrolling to add parallel reduction phis.
+    bool AddAdditionalAccumulators;
   };
 
   /// Get target-customized preferences for the generic loop unrolling

llvm/include/llvm/Transforms/Utils/UnrollLoop.h

@@ -79,6 +79,7 @@ struct UnrollLoopOptions {
   const Instruction *Heart = nullptr;
   unsigned SCEVExpansionBudget;
   bool RuntimeUnrollMultiExit = false;
+  bool AddAdditionalAccumulators = false;
 };
 
 LLVM_ABI LoopUnrollResult UnrollLoop(Loop *L, UnrollLoopOptions ULO,

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -4984,6 +4984,7 @@ getAppleRuntimeUnrollPreferences(Loop *L, ScalarEvolution &SE,
       SE.getSmallConstantTripMultiple(L, L->getExitingBlock()) % 2 == 0) {
     UP.Partial = true;
     UP.MaxCount = 4;
+    UP.AddAdditionalAccumulators = true;
   }
 
   const SCEV *BTC = SE.getSymbolicMaxBackedgeTakenCount(L);
@@ -5004,6 +5005,7 @@ getAppleRuntimeUnrollPreferences(Loop *L, ScalarEvolution &SE,
   if (HasParellelizableReductions) {
     UP.Runtime = true;
     UP.DefaultUnrollRuntimeCount = 4;
+    UP.AddAdditionalAccumulators = true;
   }
 
   // Try to unroll small loops, of few-blocks with low budget, if they have

llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp

@@ -220,6 +220,7 @@ TargetTransformInfo::UnrollingPreferences llvm::gatherUnrollingPreferences(
   UP.MaxIterationsCountToAnalyze = UnrollMaxIterationsCountToAnalyze;
   UP.SCEVExpansionBudget = SCEVCheapExpansionBudget;
   UP.RuntimeUnrollMultiExit = false;
+  UP.AddAdditionalAccumulators = false;
 
   // Override with any target specific settings
   TTI.getUnrollingPreferences(L, SE, UP, &ORE);
@@ -1354,6 +1355,7 @@ tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI, ScalarEvolution &SE,
   ULO.Heart = getLoopConvergenceHeart(L);
   ULO.SCEVExpansionBudget = UP.SCEVExpansionBudget;
   ULO.RuntimeUnrollMultiExit = UP.RuntimeUnrollMultiExit;
+  ULO.AddAdditionalAccumulators = UP.AddAdditionalAccumulators;
   LoopUnrollResult UnrollResult = UnrollLoop(
       L, ULO, LI, &SE, &DT, &AC, &TTI, &ORE, PreserveLCSSA, &RemainderLoop, AA);
   if (UnrollResult == LoopUnrollResult::Unmodified)

llvm/lib/Transforms/Utils/LoopUnroll.cpp

@@ -671,8 +671,10 @@ llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
   // to not exit.
   DenseMap<PHINode *, RecurrenceDescriptor> Reductions;
   bool CanAddAdditionalAccumulators =
-      UnrollAddParallelReductions && !CompletelyUnroll &&
-      L->getNumBlocks() == 1 &&
+      (UnrollAddParallelReductions.getNumOccurrences() > 0
+           ? UnrollAddParallelReductions
+           : ULO.AddAdditionalAccumulators) &&
+      !CompletelyUnroll && L->getNumBlocks() == 1 &&
       (ULO.Runtime ||
        (ExitInfos.contains(Header) && ((ExitInfos[Header].TripCount != 0 &&
                                         ExitInfos[Header].BreakoutTrip == 0))));