1 files changed, 15 insertions, 48 deletions

diff --git a/contrib/llvm-project/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/contrib/llvm-project/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index f82e161fb846..8e135d80f4f2 100644
--- a/contrib/llvm-project/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/contrib/llvm-project/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -8174,13 +8174,20 @@ VPRecipeBase *VPRecipeBuilder::tryToWidenMemory(Instruction *I,
   bool Consecutive =
       Reverse || Decision == LoopVectorizationCostModel::CM_Widen;
 
+  VPValue *Ptr = isa<LoadInst>(I) ? Operands[0] : Operands[1];
+  if (Consecutive) {
+    auto *VectorPtr = new VPVectorPointerRecipe(Ptr, getLoadStoreType(I),
+                                                Reverse, I->getDebugLoc());
+    Builder.getInsertBlock()->appendRecipe(VectorPtr);
+    Ptr = VectorPtr;
+  }
   if (LoadInst *Load = dyn_cast<LoadInst>(I))
-    return new VPWidenMemoryInstructionRecipe(*Load, Operands[0], Mask,
-                                              Consecutive, Reverse);
+    return new VPWidenMemoryInstructionRecipe(*Load, Ptr, Mask, Consecutive,
+                                              Reverse);
 
   StoreInst *Store = cast<StoreInst>(I);
-  return new VPWidenMemoryInstructionRecipe(*Store, Operands[1], Operands[0],
-                                            Mask, Consecutive, Reverse);
+  return new VPWidenMemoryInstructionRecipe(*Store, Ptr, Operands[0], Mask,
+                                            Consecutive, Reverse);
 }
 
 /// Creates a VPWidenIntOrFpInductionRecpipe for \p Phi. If needed, it will also
@@ -9475,8 +9482,8 @@ void VPWidenMemoryInstructionRecipe::execute(VPTransformState &State) {
   InnerLoopVectorizer::VectorParts BlockInMaskParts(State.UF);
   bool isMaskRequired = getMask();
   if (isMaskRequired) {
-    // Mask reversal is only neede for non-all-one (null) masks, as reverse of a
-    // null all-one mask is a null mask.
+    // Mask reversal is only needed for non-all-one (null) masks, as reverse of
+    // a null all-one mask is a null mask.
     for (unsigned Part = 0; Part < State.UF; ++Part) {
       Value *Mask = State.get(getMask(), Part);
       if (isReverse())
@@ -9485,44 +9492,6 @@ void VPWidenMemoryInstructionRecipe::execute(VPTransformState &State) {
     }
   }
 
-  const auto CreateVecPtr = [&](unsigned Part, Value *Ptr) -> Value * {
-    // Calculate the pointer for the specific unroll-part.
-    Value *PartPtr = nullptr;
-
-    // Use i32 for the gep index type when the value is constant,
-    // or query DataLayout for a more suitable index type otherwise.
-    const DataLayout &DL =
-        Builder.GetInsertBlock()->getModule()->getDataLayout();
-    Type *IndexTy = State.VF.isScalable() && (isReverse() || Part > 0)
-                        ? DL.getIndexType(PointerType::getUnqual(
-                              ScalarDataTy->getContext()))
-                        : Builder.getInt32Ty();
-    bool InBounds = false;
-    if (auto *gep = dyn_cast<GetElementPtrInst>(Ptr->stripPointerCasts()))
-      InBounds = gep->isInBounds();
-    if (isReverse()) {
-      // If the address is consecutive but reversed, then the
-      // wide store needs to start at the last vector element.
-      // RunTimeVF =  VScale * VF.getKnownMinValue()
-      // For fixed-width VScale is 1, then RunTimeVF = VF.getKnownMinValue()
-      Value *RunTimeVF = getRuntimeVF(Builder, IndexTy, State.VF);
-      // NumElt = -Part * RunTimeVF
-      Value *NumElt =
-          Builder.CreateMul(ConstantInt::get(IndexTy, -(int64_t)Part), RunTimeVF);
-      // LastLane = 1 - RunTimeVF
-      Value *LastLane =
-          Builder.CreateSub(ConstantInt::get(IndexTy, 1), RunTimeVF);
-      PartPtr = Builder.CreateGEP(ScalarDataTy, Ptr, NumElt, "", InBounds);
-      PartPtr =
-          Builder.CreateGEP(ScalarDataTy, PartPtr, LastLane, "", InBounds);
-    } else {
-      Value *Increment = createStepForVF(Builder, IndexTy, State.VF, Part);
-      PartPtr = Builder.CreateGEP(ScalarDataTy, Ptr, Increment, "", InBounds);
-    }
-
-    return PartPtr;
-  };
-
   // Handle Stores:
   if (SI) {
     State.setDebugLocFrom(SI->getDebugLoc());
@@ -9543,8 +9512,7 @@ void VPWidenMemoryInstructionRecipe::execute(VPTransformState &State) {
           // We don't want to update the value in the map as it might be used in
           // another expression. So don't call resetVectorValue(StoredVal).
         }
-        auto *VecPtr =
-            CreateVecPtr(Part, State.get(getAddr(), VPIteration(0, 0)));
+        auto *VecPtr = State.get(getAddr(), Part);
         if (isMaskRequired)
           NewSI = Builder.CreateMaskedStore(StoredVal, VecPtr, Alignment,
                                             BlockInMaskParts[Part]);
@@ -9568,8 +9536,7 @@ void VPWidenMemoryInstructionRecipe::execute(VPTransformState &State) {
                                          nullptr, "wide.masked.gather");
       State.addMetadata(NewLI, LI);
     } else {
-      auto *VecPtr =
-          CreateVecPtr(Part, State.get(getAddr(), VPIteration(0, 0)));
+      auto *VecPtr = State.get(getAddr(), Part);
       if (isMaskRequired)
         NewLI = Builder.CreateMaskedLoad(
             DataTy, VecPtr, Alignment, BlockInMaskParts[Part],