[llvm] [LV][VPlan] Add initial support for CSA vectorization (PR #121222)

[Michael Maitland via llvm-commits]

================
@@ -2358,6 +2394,208 @@ void VPScalarCastRecipe ::print(raw_ostream &O, const Twine &Indent,
 }
 #endif
 
+#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
+void VPConditionalScalarAssignmentHeaderPHIRecipe::print(
+    raw_ostream &O, const Twine &Indent, VPSlotTracker &SlotTracker) const {
+  O << Indent << "EMIT ";
+  printAsOperand(O, SlotTracker);
+  O << " = csa-data-phi ";
+  printOperands(O, SlotTracker);
+}
+#endif
+
+void VPConditionalScalarAssignmentHeaderPHIRecipe::execute(
+    VPTransformState &State) {
+  // PrevBB is this BB
+  IRBuilder<>::InsertPointGuard Guard(State.Builder);
+  State.Builder.SetInsertPoint(State.CFG.PrevBB->getFirstNonPHI());
+
+  Value *InitData = State.get(getVPInitData(), 0);
+  PHINode *DataPhi =
+      State.Builder.CreatePHI(InitData->getType(), 2, "csa.data.phi");
+  BasicBlock *PreheaderBB = State.CFG.getPreheaderBBFor(this);
+  DataPhi->addIncoming(InitData, PreheaderBB);
+  // Note: We didn't add Incoming for the new data since
+  // VPConditionalScalarAssignmentDataUpdateRecipe may not have been executed.
+  // We let VPConditionalScalarAssignmentDataUpdateRecipe::execute add the
+  // incoming operand to DataPhi.
+
+  State.set(this, DataPhi);
+}
+
+InstructionCost VPConditionalScalarAssignmentHeaderPHIRecipe::computeCost(
+    ElementCount VF, VPCostContext &Ctx) const {
+  if (VF.isScalar())
+    return 0;
+
+  InstructionCost C = 0;
+  auto *VTy = VectorType::get(Ctx.Types.inferScalarType(this), VF);
+  const TargetTransformInfo &TTI = Ctx.TTI;
+
+  // FIXME: These costs should be moved into VPInstruction::computeCost. We put
+  // them here for now since there is no VPInstruction::computeCost support.
+  // ConditionalScalarAssignmentInitMask
+  C += TTI.getShuffleCost(TargetTransformInfo::SK_Broadcast, VTy);
+  // ConditionalScalarAssignmentInitData
+  C += TTI.getShuffleCost(TargetTransformInfo::SK_Broadcast, VTy);
+  return C;
+}
+
+#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
+void VPConditionalScalarAssignmentDataUpdateRecipe::print(
+    raw_ostream &O, const Twine &Indent, VPSlotTracker &SlotTracker) const {
+  O << Indent << "EMIT ";
+  printAsOperand(O, SlotTracker);
+  O << " = csa-data-update ";
+  printOperands(O, SlotTracker);
+}
+#endif
+
+void VPConditionalScalarAssignmentDataUpdateRecipe::execute(
+    VPTransformState &State) {
+  Value *AnyOf = State.get(getVPAnyOf(), /*NeedsScalar=*/true);
+  Value *DataUpdate = getVPDataPhi() == getVPTrue() ? State.get(getVPFalse())
+                                                    : State.get(getVPTrue());
+  PHINode *DataPhi = cast<PHINode>(State.get(getVPDataPhi()));
+  Value *DataSel =
+      State.Builder.CreateSelect(AnyOf, DataUpdate, DataPhi, "csa.data.sel");
+
+  DataPhi->addIncoming(DataSel, State.CFG.PrevBB);
+
+  State.set(this, DataSel);
+}
+
+InstructionCost VPConditionalScalarAssignmentDataUpdateRecipe::computeCost(
+    ElementCount VF, VPCostContext &Ctx) const {
+  if (VF.isScalar())
+    return 0;
+
+  InstructionCost C = 0;
+  auto *VTy = VectorType::get(Ctx.Types.inferScalarType(this), VF);
+  auto *MaskTy = VectorType::get(IntegerType::getInt1Ty(VTy->getContext()), VF);
+  constexpr TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
+  const TargetTransformInfo &TTI = Ctx.TTI;
+
+  // Data Update
+  C += TTI.getCmpSelInstrCost(Instruction::Select, VTy, MaskTy,
+                              CmpInst::BAD_ICMP_PREDICATE, CostKind);
+
+  // FIXME: These costs should be moved into VPInstruction::computeCost. We put
+  // them here for now since they are related to updating the data and there is
+  // no VPInstruction::computeCost support at the moment.
----------------
michaelmaitland wrote:

Updated.

https://github.com/llvm/llvm-project/pull/121222