[LoopUtils] Add an extra parameter OpValue to propagateIRFlags function,

If OpValue is non-null, we only consider operations similar to OpValue
when intersecting.

Differential Revision: https://reviews.llvm.org/D35292


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@308428 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 19 insertions, 12 deletions

diff --git a/include/llvm/Transforms/Utils/LoopUtils.h b/include/llvm/Transforms/Utils/LoopUtils.h
index 1344285917ba..94e20b83754e 100644
--- a/include/llvm/Transforms/Utils/LoopUtils.h
+++ b/include/llvm/Transforms/Utils/LoopUtils.h
@@ -531,8 +531,10 @@ Value *createTargetReduction(IRBuilder<> &B, const TargetTransformInfo *TTI,
 
 /// Get the intersection (logical and) of all of the potential IR flags
 /// of each scalar operation (VL) that will be converted into a vector (I).
+/// If OpValue is non-null, we only consider operations similar to OpValue
+/// when intersecting.
 /// Flag set: NSW, NUW, exact, and all of fast-math.
-void propagateIRFlags(Value *I, ArrayRef<Value *> VL);
+void propagateIRFlags(Value *I, ArrayRef<Value *> VL, Value *OpValue = nullptr);
 
 } // end namespace llvm
 
diff --git a/lib/Transforms/Utils/LoopUtils.cpp b/lib/Transforms/Utils/LoopUtils.cpp
index 58b70be95d99..3c522786641a 100644
--- a/lib/Transforms/Utils/LoopUtils.cpp
+++ b/lib/Transforms/Utils/LoopUtils.cpp
@@ -1376,16 +1376,21 @@ Value *llvm::createTargetReduction(IRBuilder<> &Builder,
   }
 }
 
-void llvm::propagateIRFlags(Value *I, ArrayRef<Value *> VL) {
-  if (auto *VecOp = dyn_cast<Instruction>(I)) {
-    if (auto *I0 = dyn_cast<Instruction>(VL[0])) {
-      // VecOVp is initialized to the 0th scalar, so start counting from index
-      // '1'.
-      VecOp->copyIRFlags(I0);
-      for (int i = 1, e = VL.size(); i < e; ++i) {
-        if (auto *Scalar = dyn_cast<Instruction>(VL[i]))
-          VecOp->andIRFlags(Scalar);
-      }
-    }
+void llvm::propagateIRFlags(Value *I, ArrayRef<Value *> VL, Value *OpValue) {
+  auto *VecOp = dyn_cast<Instruction>(I);
+  if (!VecOp)
+    return;
+  auto *Intersection = (OpValue == nullptr) ? dyn_cast<Instruction>(VL[0])
+                                            : dyn_cast<Instruction>(OpValue);
+  if (!Intersection)
+    return;
+  const unsigned Opcode = Intersection->getOpcode();
+  VecOp->copyIRFlags(Intersection);
+  for (auto *V : VL) {
+    auto *Instr = dyn_cast<Instruction>(V);
+    if (!Instr)
+      continue;
+    if (OpValue == nullptr || Opcode == Instr->getOpcode())
+      VecOp->andIRFlags(V);
   }
 }