[llvm] [VPlan] Split VPWidenMemoryInstructionRecipe (NFCI). (PR #87411)

[via llvm-commits]

================
@@ -9464,27 +9463,19 @@ static Instruction *lowerLoadUsingVectorIntrinsics(IRBuilderBase &Builder,
   return Call;
 }
 
-void VPWidenMemoryInstructionRecipe::execute(VPTransformState &State) {
-  VPValue *StoredValue = isStore() ? getStoredValue() : nullptr;
-
+void VPWidenLoadRecipe::execute(VPTransformState &State) {
   // Attempt to issue a wide load.
-  LoadInst *LI = dyn_cast<LoadInst>(&Ingredient);
-  StoreInst *SI = dyn_cast<StoreInst>(&Ingredient);
-
-  assert((LI || SI) && "Invalid Load/Store instruction");
-  assert((!SI || StoredValue) && "No stored value provided for widened store");
-  assert((!LI || !StoredValue) && "Stored value provided for widened load");
+  auto *LI = cast<LoadInst>(&Ingredient);
 
   Type *ScalarDataTy = getLoadStoreType(&Ingredient);
-
   auto *DataTy = VectorType::get(ScalarDataTy, State.VF);
   const Align Alignment = getLoadStoreAlignment(&Ingredient);
-  bool CreateGatherScatter = !isConsecutive();
+  bool CreateGather = !isConsecutive();
 
   auto &Builder = State.Builder;
   InnerLoopVectorizer::VectorParts BlockInMaskParts(State.UF);
-  bool isMaskRequired = getMask();
-  if (isMaskRequired) {
+  bool IsMaskRequired = getMask();
----------------
ayalz wrote:

Now that loads and stores are handled separately, it makes sense for each to get its mask while taking care of each part, instead of preparing BlockInMaskParts, and do so once for all EVL/gather/consecutive cases. I.e.,
```
  for (unsigned Part = 0; Part < State.UF; ++Part) {
    Value *NewLI;
    Value *Mask = nullptr;
    if (VPValue *VPMask = getMask()) {
      Mask = State.get(VPMask, Part);
      if (isReverse())
        Mask = Builder.CreateVectorReverse(Mask, "reverse");
    }
    // TODO: split this into several classes for better design.
    if (State.EVL) {
    ...
  }
```

https://github.com/llvm/llvm-project/pull/87411