[CostModel] Unify getMemoryOpCost

Use getMemoryOpCost from the generic implementation of getUserCost
and have getInstructionThroughput return the result of that for loads
and stores.

This also means that the X86 implementation of getUserCost can be
removed with the functionality folded into its getMemoryOpCost.

Differential Revision: https://reviews.llvm.org/D80984

Author: sparker-arm

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

@@ -851,6 +851,19 @@ class TargetTransformInfoImplCRTPBase : public TargetTransformInfoImplBase {
     case Instruction::ZExt:
     case Instruction::AddrSpaceCast:
       return TargetTTI->getCastInstrCost(Opcode, Ty, OpTy, CostKind, I);
+    case Instruction::Store: {
+      auto *SI = cast<StoreInst>(U);
+      Type *ValTy = U->getOperand(0)->getType();
+      return TargetTTI->getMemoryOpCost(Opcode, ValTy, SI->getAlign(),
+                                        SI->getPointerAddressSpace(),
+                                        CostKind, I);
+    }
+    case Instruction::Load: {
+      auto *LI = cast<LoadInst>(U);
+      return TargetTTI->getMemoryOpCost(Opcode, U->getType(), LI->getAlign(),
+                                        LI->getPointerAddressSpace(),
+                                        CostKind, I);
+    }
     }
     // By default, just classify everything as 'basic'.
     return TTI::TCC_Basic;

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -888,6 +888,8 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
 
     // Assuming that all loads of legal types cost 1.
     unsigned Cost = LT.first;
+    if (CostKind != TTI::TCK_RecipThroughput)
+      return Cost;
 
     if (Src->isVectorTy() &&
         Src->getPrimitiveSizeInBits() < LT.second.getSizeInBits()) {

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -1307,17 +1307,9 @@ int TargetTransformInfo::getInstructionThroughput(const Instruction *I) const {
     return getCmpSelInstrCost(I->getOpcode(), ValTy, I->getType(),
                               CostKind, I);
   }
-  case Instruction::Store: {
-    const StoreInst *SI = cast<StoreInst>(I);
-    Type *ValTy = SI->getValueOperand()->getType();
-    return getMemoryOpCost(I->getOpcode(), ValTy, SI->getAlign(),
-                           SI->getPointerAddressSpace(), CostKind, I);
-  }
-  case Instruction::Load: {
-    const LoadInst *LI = cast<LoadInst>(I);
-    return getMemoryOpCost(I->getOpcode(), I->getType(), LI->getAlign(),
-                           LI->getPointerAddressSpace(), CostKind, I);
-  }
+  case Instruction::Store:
+  case Instruction::Load:
+    return getUserCost(I, CostKind);
   case Instruction::ZExt:
   case Instruction::SExt:
   case Instruction::FPToUI:

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -671,6 +671,10 @@ int AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Ty,
                                     MaybeAlign Alignment, unsigned AddressSpace,
                                     TTI::TargetCostKind CostKind,
                                     const Instruction *I) {
+  // TODO: Handle other cost kinds.
+  if (CostKind != TTI::TCK_RecipThroughput)
+    return 1;
+
   auto LT = TLI->getTypeLegalizationCost(DL, Ty);
 
   if (ST->isMisaligned128StoreSlow() && Opcode == Instruction::Store &&

llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp

@@ -878,6 +878,10 @@ int ARMTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
                                 MaybeAlign Alignment, unsigned AddressSpace,
                                 TTI::TargetCostKind CostKind,
                                 const Instruction *I) {
+  // TODO: Handle other cost kinds.
+  if (CostKind != TTI::TCK_RecipThroughput)
+    return 1;
+
   std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Src);
 
   if (ST->hasNEON() && Src->isVectorTy() &&

llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp

@@ -152,6 +152,10 @@ unsigned HexagonTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
                                          TTI::TargetCostKind CostKind,
                                          const Instruction *I) {
   assert(Opcode == Instruction::Load || Opcode == Instruction::Store);
+  // TODO: Handle other cost kinds.
+  if (CostKind != TTI::TCK_RecipThroughput)
+    return 1;
+
   if (Opcode == Instruction::Store)
     return BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
                                   CostKind, I);

llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp

@@ -212,8 +212,12 @@ int PPCTTIImpl::getIntImmCostInst(unsigned Opcode, unsigned Idx,
 unsigned
 PPCTTIImpl::getUserCost(const User *U, ArrayRef<const Value *> Operands,
                         TTI::TargetCostKind CostKind) {
-  // We already implement getCastInstrCost and perform the vector adjustment there.
-  if (!isa<CastInst>(U) && U->getType()->isVectorTy()) {
+  // We already implement getCastInstrCost and getMemoryOpCost where we perform
+  // the vector adjustment there.
+  if (isa<CastInst>(U) || isa<LoadInst>(U) || isa<StoreInst>(U))
+    return BaseT::getUserCost(U, Operands, CostKind);
+
+  if (U->getType()->isVectorTy()) {
     // Instructions that need to be split should cost more.
     std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, U->getType());
     return LT.first * BaseT::getUserCost(U, Operands, CostKind);
@@ -862,6 +866,10 @@ int PPCTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
 
   int Cost = BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
                                     CostKind);
+  // TODO: Handle other cost kinds.
+  if (CostKind != TTI::TCK_RecipThroughput)
+    return Cost;
+
   Cost = vectorCostAdjustment(Cost, Opcode, Src, nullptr);
 
   bool IsAltivecType = ST->hasAltivec() &&

llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp

@@ -1029,6 +1029,10 @@ int SystemZTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
                                     const Instruction *I) {
   assert(!Src->isVoidTy() && "Invalid type");
 
+  // TODO: Handle other cost kinds.
+  if (CostKind != TTI::TCK_RecipThroughput)
+    return 1;
+
   if (!Src->isVectorTy() && Opcode == Instruction::Load && I != nullptr) {
     // Store the load or its truncated or extended value in FoldedValue.
     const Instruction *FoldedValue = nullptr;

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

@@ -2961,6 +2961,20 @@ int X86TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
                                 MaybeAlign Alignment, unsigned AddressSpace,
                                 TTI::TargetCostKind CostKind,
                                 const Instruction *I) {
+  // TODO: Handle other cost kinds.
+  if (CostKind != TTI::TCK_RecipThroughput) {
+    if (isa_and_nonnull<StoreInst>(I)) {
+      Value *Ptr = I->getOperand(1);
+      // Store instruction with index and scale costs 2 Uops.
+      // Check the preceding GEP to identify non-const indices.
+      if (auto *GEP = dyn_cast<GetElementPtrInst>(Ptr)) {
+        if (!all_of(GEP->indices(), [](Value *V) { return isa<Constant>(V); }))
+          return TTI::TCC_Basic * 2;
+      }
+    }
+    return TTI::TCC_Basic;
+  }
+
   // Handle non-power-of-two vectors such as <3 x float>
   if (VectorType *VTy = dyn_cast<VectorType>(Src)) {
     unsigned NumElem = VTy->getNumElements();
@@ -3807,22 +3821,6 @@ int X86TTIImpl::getIntImmCostIntrin(Intrinsic::ID IID, unsigned Idx,
   return X86TTIImpl::getIntImmCost(Imm, Ty, CostKind);
 }
 
-unsigned
-X86TTIImpl::getUserCost(const User *U, ArrayRef<const Value *> Operands,
-                        TTI::TargetCostKind CostKind) {
-  if (isa<StoreInst>(U)) {
-    Value *Ptr = U->getOperand(1);
-    // Store instruction with index and scale costs 2 Uops.
-    // Check the preceding GEP to identify non-const indices.
-    if (auto GEP = dyn_cast<GetElementPtrInst>(Ptr)) {
-      if (!all_of(GEP->indices(), [](Value *V) { return isa<Constant>(V); }))
-        return TTI::TCC_Basic * 2;
-    }
-    return TTI::TCC_Basic;
-  }
-  return BaseT::getUserCost(U, Operands, CostKind);
-}
-
 // Return an average cost of Gather / Scatter instruction, maybe improved later
 int X86TTIImpl::getGSVectorCost(unsigned Opcode, Type *SrcVTy, Value *Ptr,
                                 unsigned Alignment, unsigned AddressSpace) {

llvm/lib/Target/X86/X86TargetTransformInfo.h

@@ -191,9 +191,6 @@ class X86TTIImpl : public BasicTTIImplBase<X86TTIImpl> {
 
   int getIntImmCost(const APInt &Imm, Type *Ty, TTI::TargetCostKind CostKind);
 
-  unsigned getUserCost(const User *U, ArrayRef<const Value *> Operands,
-                       TTI::TargetCostKind);
-
   int getIntImmCostInst(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty,
                         TTI::TargetCostKind CostKind);
   int getIntImmCostIntrin(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,