commit 3f5ce18658f0b6cc01853a02aede777d190ee52d
author Sanjoy Das <sanjoy@playingwithpointers.com> Tue Mar 12 01:31:44 2019 +0000
committer Sanjoy Das <sanjoy@playingwithpointers.com> Tue Mar 12 01:31:44 2019 +0000
tree 8585f01ca8bba472cf5b3bee143b3d87a74fc557
parent 3751ae4a94379d572cc722ee0beac8019241f5d4

Reland "Relax constraints for reduction vectorization"

Change from original commit: move test (that uses an X86 triple) into the X86
subdirectory.

Original description:
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: 355889

llvm/lib/Transforms/Utils/LoopUtils.cpp

diff --git a/llvm/lib/Transforms/Utils/LoopUtils.cpp b/llvm/lib/Transforms/Utils/LoopUtils.cpp
index c3a0268..045cb62 100644
--- a/llvm/lib/Transforms/Utils/LoopUtils.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUtils.cpp
@@ -671,13 +671,9 @@
   return true;
 }
 
-/// Adds a 'fast' flag to floating point operations.
-static Value *addFastMathFlag(Value *V) {
-  if (isa<FPMathOperator>(V)) {
-    FastMathFlags Flags;
-    Flags.setFast();
-    cast<Instruction>(V)->setFastMathFlags(Flags);
-  }
+static Value *addFastMathFlag(Value *V, FastMathFlags FMF) {
+  if (isa<FPMathOperator>(V))
+    cast<Instruction>(V)->setFastMathFlags(FMF);
   return V;
 }
 
@@ -761,7 +757,7 @@
 Value *
 llvm::getShuffleReduction(IRBuilder<> &Builder, Value *Src, unsigned Op,
                           RecurrenceDescriptor::MinMaxRecurrenceKind MinMaxKind,
-                          ArrayRef<Value *> RedOps) {
+                          FastMathFlags FMF, ArrayRef<Value *> RedOps) {
   unsigned VF = Src->getType()->getVectorNumElements();
   // VF is a power of 2 so we can emit the reduction using log2(VF) shuffles
   // and vector ops, reducing the set of values being computed by half each
@@ -786,7 +782,8 @@
     if (Op != Instruction::ICmp && Op != Instruction::FCmp) {
       // Floating point operations had to be 'fast' to enable the reduction.
       TmpVec = addFastMathFlag(Builder.CreateBinOp((Instruction::BinaryOps)Op,
-                                                   TmpVec, Shuf, "bin.rdx"));
+                                                   TmpVec, Shuf, "bin.rdx"),
+                               FMF);
     } else {
       assert(MinMaxKind != RecurrenceDescriptor::MRK_Invalid &&
              "Invalid min/max");
@@ -803,7 +800,7 @@
 /// flags (if generating min/max reductions).
 Value *llvm::createSimpleTargetReduction(
     IRBuilder<> &Builder, const TargetTransformInfo *TTI, unsigned Opcode,
-    Value *Src, TargetTransformInfo::ReductionFlags Flags,
+    Value *Src, TargetTransformInfo::ReductionFlags Flags, FastMathFlags FMF,
     ArrayRef<Value *> RedOps) {
   assert(isa<VectorType>(Src->getType()) && "Type must be a vector");
 
@@ -873,7 +870,7 @@
   }
   if (TTI->useReductionIntrinsic(Opcode, Src->getType(), Flags))
     return BuildFunc();
-  return getShuffleReduction(Builder, Src, Opcode, MinMaxKind, RedOps);
+  return getShuffleReduction(Builder, Src, Opcode, MinMaxKind, FMF, RedOps);
 }
 
 /// Create a vector reduction using a given recurrence descriptor.
@@ -888,28 +885,37 @@
   Flags.NoNaN = NoNaN;
   switch (RecKind) {
   case RD::RK_FloatAdd:
-    return createSimpleTargetReduction(B, TTI, Instruction::FAdd, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::FAdd, Src, Flags,
+                                       Desc.getFastMathFlags());
   case RD::RK_FloatMult:
-    return createSimpleTargetReduction(B, TTI, Instruction::FMul, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::FMul, Src, Flags,
+                                       Desc.getFastMathFlags());
   case RD::RK_IntegerAdd:
-    return createSimpleTargetReduction(B, TTI, Instruction::Add, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::Add, Src, Flags,
+                                       Desc.getFastMathFlags());
   case RD::RK_IntegerMult:
-    return createSimpleTargetReduction(B, TTI, Instruction::Mul, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::Mul, Src, Flags,
+                                       Desc.getFastMathFlags());
   case RD::RK_IntegerAnd:
-    return createSimpleTargetReduction(B, TTI, Instruction::And, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::And, Src, Flags,
+                                       Desc.getFastMathFlags());
   case RD::RK_IntegerOr:
-    return createSimpleTargetReduction(B, TTI, Instruction::Or, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::Or, Src, Flags,
+                                       Desc.getFastMathFlags());
   case RD::RK_IntegerXor:
-    return createSimpleTargetReduction(B, TTI, Instruction::Xor, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::Xor, Src, Flags,
+                                       Desc.getFastMathFlags());
   case RD::RK_IntegerMinMax: {
     RD::MinMaxRecurrenceKind MMKind = Desc.getMinMaxRecurrenceKind();
     Flags.IsMaxOp = (MMKind == RD::MRK_SIntMax || MMKind == RD::MRK_UIntMax);
     Flags.IsSigned = (MMKind == RD::MRK_SIntMax || MMKind == RD::MRK_SIntMin);
-    return createSimpleTargetReduction(B, TTI, Instruction::ICmp, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::ICmp, Src, Flags,
+                                       Desc.getFastMathFlags());
   }
   case RD::RK_FloatMinMax: {
     Flags.IsMaxOp = Desc.getMinMaxRecurrenceKind() == RD::MRK_FloatMax;
-    return createSimpleTargetReduction(B, TTI, Instruction::FCmp, Src, Flags);
+    return createSimpleTargetReduction(B, TTI, Instruction::FCmp, Src, Flags,
+                                       Desc.getFastMathFlags());
   }
   default:
     llvm_unreachable("Unhandled RecKind");