Relax constraints for reduction vectorization

Summary:
Gating vectorizing reductions on *all* fastmath flags seems unnecessary;
`reassoc` should be sufficient.

Reviewers: tvvikram, mkuper, kristof.beyls, sdesmalen, Ayal

Reviewed By: sdesmalen

Subscribers: dcaballe, huntergr, jmolloy, mcrosier, jlebar, bixia, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D57728

llvm-svn: 355868

3 files changed, 19 insertions, 4 deletions

diff --git a/llvm/include/llvm/Analysis/IVDescriptors.h b/llvm/include/llvm/Analysis/IVDescriptors.h
index 254cabfc85b..4e8b6ec202c 100644
--- a/llvm/include/llvm/Analysis/IVDescriptors.h
+++ b/llvm/include/llvm/Analysis/IVDescriptors.h
@@ -89,10 +89,12 @@ public:
   RecurrenceDescriptor() = default;
 
   RecurrenceDescriptor(Value *Start, Instruction *Exit, RecurrenceKind K,
-                       MinMaxRecurrenceKind MK, Instruction *UAI, Type *RT,
-                       bool Signed, SmallPtrSetImpl<Instruction *> &CI)
-      : StartValue(Start), LoopExitInstr(Exit), Kind(K), MinMaxKind(MK),
-        UnsafeAlgebraInst(UAI), RecurrenceType(RT), IsSigned(Signed) {
+                       FastMathFlags FMF, MinMaxRecurrenceKind MK,
+                       Instruction *UAI, Type *RT, bool Signed,
+                       SmallPtrSetImpl<Instruction *> &CI)
+      : StartValue(Start), LoopExitInstr(Exit), Kind(K), FMF(FMF),
+        MinMaxKind(MK), UnsafeAlgebraInst(UAI), RecurrenceType(RT),
+        IsSigned(Signed) {
     CastInsts.insert(CI.begin(), CI.end());
   }
 
@@ -198,6 +200,8 @@ public:
 
   MinMaxRecurrenceKind getMinMaxRecurrenceKind() { return MinMaxKind; }
 
+  FastMathFlags getFastMathFlags() { return FMF; }
+
   TrackingVH<Value> getRecurrenceStartValue() { return StartValue; }
 
   Instruction *getLoopExitInstr() { return LoopExitInstr; }
@@ -237,6 +241,9 @@ private:
   Instruction *LoopExitInstr = nullptr;
   // The kind of the recurrence.
   RecurrenceKind Kind = RK_NoRecurrence;
+  // The fast-math flags on the recurrent instructions.  We propagate these
+  // fast-math flags into the vectorized FP instructions we generate.
+  FastMathFlags FMF;
   // If this a min/max recurrence the kind of recurrence.
   MinMaxRecurrenceKind MinMaxKind = MRK_Invalid;
   // First occurrence of unasfe algebra in the PHI's use-chain.
diff --git a/llvm/include/llvm/IR/Operator.h b/llvm/include/llvm/IR/Operator.h
index fefb13c66d4..8199c65ca8a 100644
--- a/llvm/include/llvm/IR/Operator.h
+++ b/llvm/include/llvm/IR/Operator.h
@@ -187,6 +187,12 @@ public:
 
   FastMathFlags() = default;
 
+  static FastMathFlags getFast() {
+    FastMathFlags FMF;
+    FMF.setFast();
+    return FMF;
+  }
+
   bool any() const { return Flags != 0; }
   bool none() const { return Flags == 0; }
   bool all() const { return Flags == ~0U; }
diff --git a/llvm/include/llvm/Transforms/Utils/LoopUtils.h b/llvm/include/llvm/Transforms/Utils/LoopUtils.h
index f81b7367292..c724a3ed105 100644
--- a/llvm/include/llvm/Transforms/Utils/LoopUtils.h
+++ b/llvm/include/llvm/Transforms/Utils/LoopUtils.h
@@ -296,6 +296,7 @@ getOrderedReduction(IRBuilder<> &Builder, Value *Acc, Value *Src, unsigned Op,
 Value *getShuffleReduction(IRBuilder<> &Builder, Value *Src, unsigned Op,
                            RecurrenceDescriptor::MinMaxRecurrenceKind
                                MinMaxKind = RecurrenceDescriptor::MRK_Invalid,
+                           FastMathFlags FMF = FastMathFlags(),
                            ArrayRef<Value *> RedOps = None);
 
 /// Create a target reduction of the given vector. The reduction operation
@@ -308,6 +309,7 @@ Value *createSimpleTargetReduction(IRBuilder<> &B,
                                    unsigned Opcode, Value *Src,
                                    TargetTransformInfo::ReductionFlags Flags =
                                        TargetTransformInfo::ReductionFlags(),
+                                   FastMathFlags FMF = FastMathFlags(),
                                    ArrayRef<Value *> RedOps = None);
 
 /// Create a generic target reduction using a recurrence descriptor \p Desc