[NFCI][CostModel] Unify FNeg cost

[samparker]

Summary

Enable TTIImpl::getUserCost to handle FNeg so that getInstructionThroughput can call that instead. This means we can remove the code in the AMDGPU backend too.

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

int getUserCost(const User *U, ArrayRef<const Value *> Operands,
     case Instruction::URem:
     case Instruction::SRem:
     case Instruction::FRem:
     case Instruction::Shl:
     case Instruction::LShr:
     case Instruction::AShr:
     case Instruction::And:
     case Instruction::Or:
-    case Instruction::Xor: {
-      TargetTransformInfo::OperandValueKind Op1VK, Op2VK;
-      TargetTransformInfo::OperandValueProperties Op1VP, Op2VP;
-      Op1VK = TTI::getOperandInfo(U->getOperand(0), Op1VP);
-      Op2VK = TTI::getOperandInfo(U->getOperand(1), Op2VP);
+    case Instruction::Xor:
+    case Instruction::FNeg: {
+      TTI::OperandValueProperties Op1VP = TTI::OP_None;
+      TTI::OperandValueProperties Op2VP = TTI::OP_None;
+      TTI::OperandValueKind Op1VK =
+        TTI::getOperandInfo(U->getOperand(0), Op1VP);
+      TTI::OperandValueKind Op2VK = Opcode != Instruction::FNeg ?
+        TTI::getOperandInfo(U->getOperand(1), Op2VP) : TTI::OK_AnyValue;
       SmallVector<const Value *, 2> Operands(U->operand_values());
       return TargetTTI->getArithmeticInstrCost(Opcode, Ty, CostKind,
                                                Op1VK, Op2VK,
                                                Op1VP, Op2VP, Operands, I);
     }
     case Instruction::IntToPtr:
     case Instruction::PtrToInt:
     case Instruction::SIToFP:

llvm/lib/Analysis/TargetTransformInfo.cpp

int TargetTransformInfo::getInstructionThroughput(const Instruction *I) const {
   case Instruction::SRem:
   case Instruction::FRem:
   case Instruction::Shl:
   case Instruction::LShr:
   case Instruction::AShr:
   case Instruction::And:
   case Instruction::Or:
   case Instruction::Xor:
+  case Instruction::FNeg:
     return getUserCost(I, CostKind);
-  case Instruction::FNeg: {
-    TargetTransformInfo::OperandValueKind Op1VK, Op2VK;
-    TargetTransformInfo::OperandValueProperties Op1VP, Op2VP;
-    Op1VK = getOperandInfo(I->getOperand(0), Op1VP);
-    Op2VK = OK_AnyValue;
-    Op2VP = OP_None;
-    SmallVector<const Value *, 2> Operands(I->operand_values());
-    return getArithmeticInstrCost(I->getOpcode(), I->getType(), CostKind,
-                                  Op1VK, Op2VK,
-                                  Op1VP, Op2VP, Operands, I);
-  }
   case Instruction::Select:
   case Instruction::ICmp:
   case Instruction::FCmp:
   case Instruction::Store:
   case Instruction::Load:
   case Instruction::ZExt:
   case Instruction::SExt:
   case Instruction::FPToUI:

llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h

int getArithmeticReductionCost(
       bool IsPairwise,
       TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput);
 
   int getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                             TTI::TargetCostKind CostKind);
   int getMinMaxReductionCost(
     VectorType *Ty, VectorType *CondTy, bool IsPairwiseForm, bool IsUnsigned,
     TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput);
-
-  unsigned getUserCost(const User *U, ArrayRef<const Value *> Operands,
-                       TTI::TargetCostKind CostKind);
 };
 
 class R600TTIImpl final : public BasicTTIImplBase<R600TTIImpl> {
   using BaseT = BasicTTIImplBase<R600TTIImpl>;
   using TTI = TargetTransformInfo;
 
   friend BaseT;
 

llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp

bool GCNTTIImpl::areInlineCompatible(const Function *Caller,
   return CallerMode.isInlineCompatible(CalleeMode);
 }
 
 void GCNTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                          TTI::UnrollingPreferences &UP) {
   CommonTTI.getUnrollingPreferences(L, SE, UP);
 }
 
-unsigned
-GCNTTIImpl::getUserCost(const User *U, ArrayRef<const Value *> Operands,
-                        TTI::TargetCostKind CostKind) {
-  const Instruction *I = dyn_cast<Instruction>(U);
-  if (!I)
-    return BaseT::getUserCost(U, Operands, CostKind);
-
-  // Estimate different operations to be optimized out
-  switch (I->getOpcode()) {
-  case Instruction::FNeg:
-    return getArithmeticInstrCost(I->getOpcode(), I->getType(), CostKind,
-                                  TTI::OK_AnyValue, TTI::OK_AnyValue,
-                                  TTI::OP_None, TTI::OP_None, Operands, I);
-  default:
-    break;
-  }
-
-  return BaseT::getUserCost(U, Operands, CostKind);
-}
-
 unsigned R600TTIImpl::getHardwareNumberOfRegisters(bool Vec) const {
   return 4 * 128; // XXX - 4 channels. Should these count as vector instead?
 }
 
 unsigned R600TTIImpl::getNumberOfRegisters(bool Vec) const {
   return getHardwareNumberOfRegisters(Vec);
 }