[llvm] [LV][EVL] Support interleaved access with tail folding by EVL (PR #152070)

[Florian Hahn via llvm-commits]

================
@@ -2474,48 +2484,129 @@ class LLVM_ABI_FOR_TEST VPInterleaveRecipe : public VPRecipeBase {
   /// Return the mask used by this recipe. Note that a full mask is represented
   /// by a nullptr.
   VPValue *getMask() const {
-    // Mask is optional and therefore the last, currently 2nd operand.
+    // Mask is optional and the last operand.
     return HasMask ? getOperand(getNumOperands() - 1) : nullptr;
   }
 
+  /// Return true if the access needs a mask because of the gaps.
+  bool needsMaskForGaps() const { return NeedsMaskForGaps; }
+
+  const InterleaveGroup<Instruction> *getInterleaveGroup() { return IG; }
+
+  Instruction *getInsertPos() const { return IG->getInsertPos(); }
+
+  void execute(VPTransformState &State) override {
+    llvm_unreachable("VPInterleaveBase should not be instantiated.");
+  }
+
+  /// Return the cost of this recipe.
+  InstructionCost computeCost(ElementCount VF,
+                              VPCostContext &Ctx) const override;
+
+  /// Returns true if the recipe only uses the first lane of operand \p Op.
+  virtual bool onlyFirstLaneUsed(const VPValue *Op) const override = 0;
+
+  /// Returns the number of stored operands of this interleave group. Returns 0
+  /// for load interleave groups.
+  virtual unsigned getNumStoreOperands() const = 0;
+
   /// Return the VPValues stored by this interleave group. If it is a load
   /// interleave group, return an empty ArrayRef.
   ArrayRef<VPValue *> getStoredValues() const {
-    // The first operand is the address, followed by the stored values, followed
-    // by an optional mask.
-    return ArrayRef<VPValue *>(op_begin(), getNumOperands())
-        .slice(1, getNumStoreOperands());
+    return ArrayRef<VPValue *>(op_end() -
+                                   (getNumStoreOperands() + (HasMask ? 1 : 0)),
+                               getNumStoreOperands());
+  }
+};
+
+/// VPInterleaveRecipe is a recipe for transforming an interleave group of load
+/// or stores into one wide load/store and shuffles. The first operand of a
+/// VPInterleave recipe is the address, followed by the stored values, followed
+/// by an optional mask.
+class LLVM_ABI_FOR_TEST VPInterleaveRecipe final : public VPInterleaveBase {
+public:
+  VPInterleaveRecipe(const InterleaveGroup<Instruction> *IG, VPValue *Addr,
+                     ArrayRef<VPValue *> StoredValues, VPValue *Mask,
+                     bool NeedsMaskForGaps, DebugLoc DL)
+      : VPInterleaveBase(VPDef::VPInterleaveSC, IG, Addr, StoredValues, Mask,
+                         NeedsMaskForGaps, DL) {}
+
+  ~VPInterleaveRecipe() override = default;
+
+  VPInterleaveRecipe *clone() override {
+    return new VPInterleaveRecipe(IG, getAddr(), getStoredValues(), getMask(),
+                                  NeedsMaskForGaps, getDebugLoc());
   }
 
+  VP_CLASSOF_IMPL(VPDef::VPInterleaveSC)
+
   /// Generate the wide load or store, and shuffles.
   void execute(VPTransformState &State) override;
 
-  /// Return the cost of this VPInterleaveRecipe.
-  InstructionCost computeCost(ElementCount VF,
-                              VPCostContext &Ctx) const override;
-
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
   /// Print the recipe.
   void print(raw_ostream &O, const Twine &Indent,
              VPSlotTracker &SlotTracker) const override;
 #endif
 
-  const InterleaveGroup<Instruction> *getInterleaveGroup() { return IG; }
+  bool onlyFirstLaneUsed(const VPValue *Op) const override {
+    assert(is_contained(operands(), Op) &&
+           "Op must be an operand of the recipe");
+    return Op == getAddr() && !llvm::is_contained(getStoredValues(), Op);
+  }
 
-  /// Returns the number of stored operands of this interleave group. Returns 0
-  /// for load interleave groups.
-  unsigned getNumStoreOperands() const {
+  unsigned getNumStoreOperands() const override {
     return getNumOperands() - (HasMask ? 2 : 1);
   }
+};
 
-  /// The recipe only uses the first lane of the address.
+/// A recipe for interleaved access operations with vector-predication
+/// intrinsics. The first operand is the address, the second operand is the
+/// explicit vector length . Stored values and mask are optional operands.
----------------
fhahn wrote:

```suggestion
/// explicit vector length. Stored values and mask are optional operands.
```

https://github.com/llvm/llvm-project/pull/152070