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

[Mel Chen via llvm-commits]

================
@@ -3690,8 +3693,153 @@ void VPInterleaveRecipe::print(raw_ostream &O, const Twine &Indent,
 }
 #endif
 
-InstructionCost VPInterleaveRecipe::computeCost(ElementCount VF,
-                                                VPCostContext &Ctx) const {
+void VPInterleaveEVLRecipe::execute(VPTransformState &State) {
+  assert(!State.Lane && "Interleave group being replicated.");
+  assert(State.VF.isScalable() &&
+         "Only support scalable VF for EVL tail-folding.");
+  assert(!NeedsMaskForGaps &&
+         "Masking gaps for scalable vectors is not yet supported.");
+  const InterleaveGroup<Instruction> *Group = IG;
+  Instruction *Instr = Group->getInsertPos();
+
+  // Prepare for the vector type of the interleaved load/store.
+  Type *ScalarTy = getLoadStoreType(Instr);
+  unsigned InterleaveFactor = Group->getFactor();
+  assert(InterleaveFactor <= 8 &&
+         "Unsupported deinterleave/interleave factor for scalable vectors");
+  ElementCount WideVF = State.VF * InterleaveFactor;
+  auto *VecTy = VectorType::get(ScalarTy, WideVF);
+
+  VPValue *Addr = getAddr();
+  Value *ResAddr = State.get(Addr, VPLane(0));
+  Value *EVL = State.get(getEVL(), VPLane(0));
+  Value *InterleaveEVL = State.Builder.CreateMul(
+      EVL, ConstantInt::get(EVL->getType(), InterleaveFactor), "interleave.evl",
+      /* NUW= */ true, /* NSW= */ true);
+  LLVMContext &Ctx = State.Builder.getContext();
+
+  Value *GroupMask = nullptr;
+  if (VPValue *BlockInMask = getMask()) {
+    SmallVector<Value *> Ops(InterleaveFactor, State.get(BlockInMask));
+    GroupMask = interleaveVectors(State.Builder, Ops, "interleaved.mask");
+  } else {
+    GroupMask =
+        State.Builder.CreateVectorSplat(WideVF, State.Builder.getTrue());
+  }
+
+  const DataLayout &DL = Instr->getDataLayout();
+  // Vectorize the interleaved load group.
+  if (isa<LoadInst>(Instr)) {
+    CallInst *NewLoad = State.Builder.CreateIntrinsic(
+        VecTy, Intrinsic::vp_load, {ResAddr, GroupMask, InterleaveEVL}, nullptr,
+        "wide.vp.load");
+    NewLoad->addParamAttr(0,
+                          Attribute::getWithAlignment(Ctx, Group->getAlign()));
+
+    Group->addMetadata(NewLoad);
+
+    ArrayRef<VPValue *> VPDefs = definedValues();
----------------
Mel-Chen wrote:

cd9e90764ef71cf1acf25eed5aa7d5ca2054aa5e
I use VPDef::getVPValue.

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