Recommit "[LoopVectorize][AArch64] Enable ordered reductions by default for AArch64"

This reverts the revert ab9296f.

The issue causing the revert should be fixed in 9baed02.

Author: fhahn

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -662,6 +662,9 @@ class TargetTransformInfo {
   /// Return true if the target supports masked expand load.
   bool isLegalMaskedExpandLoad(Type *DataType) const;
 
+  /// Return true if we should be enabling ordered reductions for the target.
+  bool enableOrderedReductions() const;
+
   /// Return true if the target has a unified operation to calculate division
   /// and remainder. If so, the additional implicit multiplication and
   /// subtraction required to calculate a remainder from division are free. This
@@ -1508,6 +1511,7 @@ class TargetTransformInfo::Concept {
   virtual bool isLegalMaskedGather(Type *DataType, Align Alignment) = 0;
   virtual bool isLegalMaskedCompressStore(Type *DataType) = 0;
   virtual bool isLegalMaskedExpandLoad(Type *DataType) = 0;
+  virtual bool enableOrderedReductions() = 0;
   virtual bool hasDivRemOp(Type *DataType, bool IsSigned) = 0;
   virtual bool hasVolatileVariant(Instruction *I, unsigned AddrSpace) = 0;
   virtual bool prefersVectorizedAddressing() = 0;
@@ -1890,6 +1894,9 @@ class TargetTransformInfo::Model final : public TargetTransformInfo::Concept {
   bool isLegalMaskedExpandLoad(Type *DataType) override {
     return Impl.isLegalMaskedExpandLoad(DataType);
   }
+  bool enableOrderedReductions() override {
+    return Impl.enableOrderedReductions();
+  }
   bool hasDivRemOp(Type *DataType, bool IsSigned) override {
     return Impl.hasDivRemOp(DataType, IsSigned);
   }

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

@@ -263,6 +263,8 @@ class TargetTransformInfoImplBase {
 
   bool isLegalMaskedExpandLoad(Type *DataType) const { return false; }
 
+  bool enableOrderedReductions() const { return false; }
+
   bool hasDivRemOp(Type *DataType, bool IsSigned) const { return false; }
 
   bool hasVolatileVariant(Instruction *I, unsigned AddrSpace) const {

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -410,6 +410,10 @@ bool TargetTransformInfo::isLegalMaskedExpandLoad(Type *DataType) const {
   return TTIImpl->isLegalMaskedExpandLoad(DataType);
 }
 
+bool TargetTransformInfo::enableOrderedReductions() const {
+  return TTIImpl->enableOrderedReductions();
+}
+
 bool TargetTransformInfo::hasDivRemOp(Type *DataType, bool IsSigned) const {
   return TTIImpl->hasDivRemOp(DataType, IsSigned);
 }

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

@@ -299,6 +299,8 @@ class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
     return BaseT::isLegalNTStore(DataType, Alignment);
   }
 
+  bool enableOrderedReductions() const { return true; }
+
   InstructionCost getInterleavedMemoryOpCost(
       unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
       Align Alignment, unsigned AddressSpace,

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -331,7 +331,7 @@ static cl::opt<bool>
                            cl::desc("Prefer in-loop vector reductions, "
                                     "overriding the targets preference."));
 
-cl::opt<bool> ForceOrderedReductions(
+static cl::opt<bool> ForceOrderedReductions(
     "force-ordered-reductions", cl::init(false), cl::Hidden,
     cl::desc("Enable the vectorisation of loops with in-order (strict) "
              "FP reductions"));
@@ -1317,8 +1317,7 @@ class LoopVectorizationCostModel {
   /// the IsOrdered flag of RdxDesc is set and we do not allow reordering
   /// of FP operations.
   bool useOrderedReductions(const RecurrenceDescriptor &RdxDesc) {
-    return ForceOrderedReductions && !Hints->allowReordering() &&
-           RdxDesc.isOrdered();
+    return !Hints->allowReordering() && RdxDesc.isOrdered();
   }
 
   /// \returns The smallest bitwidth each instruction can be represented with.
@@ -10225,7 +10224,13 @@ bool LoopVectorizePass::processLoop(Loop *L) {
     return false;
   }
 
-  if (!LVL.canVectorizeFPMath(ForceOrderedReductions)) {
+  bool AllowOrderedReductions;
+  // If the flag is set, use that instead and override the TTI behaviour.
+  if (ForceOrderedReductions.getNumOccurrences() > 0)
+    AllowOrderedReductions = ForceOrderedReductions;
+  else
+    AllowOrderedReductions = TTI->enableOrderedReductions();
+  if (!LVL.canVectorizeFPMath(AllowOrderedReductions)) {
     ORE->emit([&]() {
       auto *ExactFPMathInst = Requirements.getExactFPInst();
       return OptimizationRemarkAnalysisFPCommute(DEBUG_TYPE, "CantReorderFPOps",

llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll

@@ -2,7 +2,7 @@
 ; RUN: opt < %s -loop-vectorize -scalable-vectorization=on -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-ordered-reductions=false -hints-allow-reordering=true  -S 2>%t | FileCheck %s --check-prefix=CHECK-UNORDERED
 ; RUN: opt < %s -loop-vectorize -scalable-vectorization=on -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-ordered-reductions=true  -hints-allow-reordering=false -S 2>%t | FileCheck %s --check-prefix=CHECK-ORDERED
 ; RUN: opt < %s -loop-vectorize -scalable-vectorization=on -mtriple aarch64-unknown-linux-gnu -mattr=+sve -force-ordered-reductions=true  -hints-allow-reordering=true  -S 2>%t | FileCheck %s --check-prefix=CHECK-UNORDERED
-; RUN: opt < %s -loop-vectorize -scalable-vectorization=on -mtriple aarch64-unknown-linux-gnu -mattr=+sve -hints-allow-reordering=false -S 2>%t | FileCheck %s --check-prefix=CHECK-NOT-VECTORIZED
+; RUN: opt < %s -loop-vectorize -scalable-vectorization=on -mtriple aarch64-unknown-linux-gnu -mattr=+sve -hints-allow-reordering=false -S 2>%t | FileCheck %s --check-prefix=CHECK-ORDERED
 
 define float @fadd_strict(float* noalias nocapture readonly %a, i64 %n) #0 {
 ; CHECK-ORDERED-LABEL: @fadd_strict

llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd.ll

@@ -2,7 +2,7 @@
 ; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -force-ordered-reductions=false -hints-allow-reordering=true  -S 2>%t | FileCheck %s --check-prefix=CHECK-UNORDERED
 ; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -force-ordered-reductions=true  -hints-allow-reordering=false -S 2>%t | FileCheck %s --check-prefix=CHECK-ORDERED
 ; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -force-ordered-reductions=true  -hints-allow-reordering=true  -S 2>%t | FileCheck %s --check-prefix=CHECK-UNORDERED
-; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -hints-allow-reordering=false -S 2>%t | FileCheck %s --check-prefix=CHECK-NOT-VECTORIZED
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -hints-allow-reordering=false -S 2>%t | FileCheck %s --check-prefix=CHECK-ORDERED
 
 define float @fadd_strict(float* noalias nocapture readonly %a, i64 %n) {
 ; CHECK-ORDERED-LABEL: @fadd_strict