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

[Luke Lau via llvm-commits]

================
@@ -3671,8 +3674,159 @@ 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 *BlockInMask = getMask();
+  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();
+
+  auto CreateGroupMask = [&BlockInMask, &State,
+                          &InterleaveFactor]() -> Value * {
+    auto *ResBlockInMask = State.get(BlockInMask);
+    SmallVector<Value *> Ops(InterleaveFactor, ResBlockInMask);
+    return interleaveVectors(State.Builder, Ops, "interleaved.mask");
+  };
----------------
lukel97 wrote:

Is CreateGroupMask only called in one place? Can we just inline the lambda

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