[TTI][RISCV] Add cost modelling for intrinsic vp.load.ff (llvm#160470)

Split out from llvm#151300 to isolate TargetTransformInfo cost modelling for
fault-only-first loads from VPlan implementation details. This change
adds costing support for vp.load.ff independently of the VPlan work.

For now, model a vp.load.ff as cost-equivalent to a vp.load.

Author: arcbbb

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -1619,6 +1619,11 @@ class TargetTransformInfo {
       TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput,
       bool UseMaskForCond = false, bool UseMaskForGaps = false) const;
 
+  /// \return The cost of vp intrinsic vp.load.ff.
+  LLVM_ABI InstructionCost getFirstFaultLoadCost(
+      Type *DataTy, Align Alignment,
+      TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput) const;
+
   /// A helper function to determine the type of reduction algorithm used
   /// for a given \p Opcode and set of FastMathFlags \p FMF.
   static bool requiresOrderedReduction(std::optional<FastMathFlags> FMF) {

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

@@ -885,6 +885,12 @@ class TargetTransformInfoImplBase {
     return 1;
   }
 
+  virtual InstructionCost
+  getFirstFaultLoadCost(Type *DataTy, Align Alignment,
+                        TTI::TargetCostKind CostKind) const {
+    return InstructionCost::getInvalid();
+  }
+
   virtual InstructionCost
   getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                         TTI::TargetCostKind CostKind) const {

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -1795,6 +1795,14 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
         }
       }
 
+      if (ICA.getID() == Intrinsic::vp_load_ff) {
+        Type *RetTy = ICA.getReturnType();
+        Type *DataTy = cast<StructType>(RetTy)->getElementType(0);
+        Align Alignment;
+        if (auto *VPI = dyn_cast_or_null<VPIntrinsic>(ICA.getInst()))
+          Alignment = VPI->getPointerAlignment().valueOrOne();
+        return thisT()->getFirstFaultLoadCost(DataTy, Alignment, CostKind);
+      }
       if (ICA.getID() == Intrinsic::vp_scatter) {
         if (ICA.isTypeBasedOnly()) {
           IntrinsicCostAttributes MaskedScatter(

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -1218,6 +1218,15 @@ InstructionCost TargetTransformInfo::getInterleavedMemoryOpCost(
   return Cost;
 }
 
+InstructionCost
+TargetTransformInfo::getFirstFaultLoadCost(Type *DataTy, Align Alignment,
+                                           TTI::TargetCostKind CostKind) const {
+  InstructionCost Cost =
+      TTIImpl->getFirstFaultLoadCost(DataTy, Alignment, CostKind);
+  assert(Cost >= 0 && "TTI should not produce negative costs!");
+  return Cost;
+}
+
 InstructionCost
 TargetTransformInfo::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                                            TTI::TargetCostKind CostKind) const {

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -24884,6 +24884,22 @@ bool RISCVTargetLowering::isLegalStridedLoadStore(EVT DataType,
   return true;
 }
 
+bool RISCVTargetLowering::isLegalFirstFaultLoad(EVT DataType,
+                                                Align Alignment) const {
+  if (!Subtarget.hasVInstructions())
+    return false;
+
+  EVT ScalarType = DataType.getScalarType();
+  if (!isLegalElementTypeForRVV(ScalarType))
+    return false;
+
+  if (!Subtarget.enableUnalignedVectorMem() &&
+      Alignment < ScalarType.getStoreSize())
+    return false;
+
+  return true;
+}
+
 MachineInstr *
 RISCVTargetLowering::EmitKCFICheck(MachineBasicBlock &MBB,
                                    MachineBasicBlock::instr_iterator &MBBI,

llvm/lib/Target/RISCV/RISCVISelLowering.h

@@ -425,6 +425,10 @@ class RISCVTargetLowering : public TargetLowering {
   /// alignment is legal.
   bool isLegalStridedLoadStore(EVT DataType, Align Alignment) const;
 
+  /// Return true if a fault-only-first load of the given result type and
+  /// alignment is legal.
+  bool isLegalFirstFaultLoad(EVT DataType, Align Alignment) const;
+
   unsigned getMaxSupportedInterleaveFactor() const override { return 8; }
 
   bool fallBackToDAGISel(const Instruction &Inst) const override;

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -1070,6 +1070,17 @@ InstructionCost RISCVTTIImpl::getInterleavedMemoryOpCost(
   return MemCost + ShuffleCost;
 }
 
+InstructionCost
+RISCVTTIImpl::getFirstFaultLoadCost(Type *DataTy, Align Alignment,
+                                    TTI::TargetCostKind CostKind) const {
+  EVT DataTypeVT = TLI->getValueType(DL, DataTy);
+  if (!TLI->isLegalFirstFaultLoad(DataTypeVT, Alignment))
+    return BaseT::getFirstFaultLoadCost(DataTy, Alignment, CostKind);
+
+  return getMemoryOpCost(Instruction::Load, DataTy, Alignment, 0, CostKind,
+                         {TTI::OK_AnyValue, TTI::OP_None}, nullptr);
+}
+
 InstructionCost RISCVTTIImpl::getGatherScatterOpCost(
     unsigned Opcode, Type *DataTy, const Value *Ptr, bool VariableMask,
     Align Alignment, TTI::TargetCostKind CostKind, const Instruction *I) const {

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h

@@ -191,6 +191,10 @@ class RISCVTTIImpl final : public BasicTTIImplBase<RISCVTTIImpl> {
       Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
       bool UseMaskForCond = false, bool UseMaskForGaps = false) const override;
 
+  InstructionCost
+  getFirstFaultLoadCost(Type *DataTy, Align Alignment,
+                        TTI::TargetCostKind CostKind) const override;
+
   InstructionCost getGatherScatterOpCost(unsigned Opcode, Type *DataTy,
                                          const Value *Ptr, bool VariableMask,
                                          Align Alignment,