[NFC] Refactor target intrinsic call lowering

Refactor intrinsic call handling in SelectionDAGBuilder and IRTranslator
to prepare the addition of intrinsic support to the callbr instruction,
which should then share code with the handling of the normal call
instruction.

Author: ro-i

llvm/include/llvm/CodeGen/GlobalISel/IRTranslator.h

@@ -297,6 +297,10 @@ class IRTranslator : public MachineFunctionPass {
   /// \pre \p U is a call instruction.
   bool translateCall(const User &U, MachineIRBuilder &MIRBuilder);
 
+  bool translateTargetIntrinsic(
+      const CallBase &CB, Intrinsic::ID ID, MachineIRBuilder &MIRBuilder,
+      TargetLowering::IntrinsicInfo *TgtMemIntrinsicInfo = nullptr);
+
   /// When an invoke or a cleanupret unwinds to the next EH pad, there are
   /// many places it could ultimately go. In the IR, we have a single unwind
   /// destination, but in the machine CFG, we enumerate all the possible blocks.

llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp

@@ -2800,20 +2800,34 @@ bool IRTranslator::translateCall(const User &U, MachineIRBuilder &MIRBuilder) {
   if (translateKnownIntrinsic(CI, ID, MIRBuilder))
     return true;
 
+  TargetLowering::IntrinsicInfo Info;
+  bool IsTgtMemIntrinsic = TLI->getTgtMemIntrinsic(Info, CI, *MF, ID);
+
+  return translateTargetIntrinsic(CI, ID, MIRBuilder,
+                                  IsTgtMemIntrinsic ? &Info : nullptr);
+}
+
+/// Translate a call to a target intrinsic.
+/// Depending on whether TLI->getTgtMemIntrinsic() is true, TgtMemIntrinsicInfo
+/// is a pointer to the correspondingly populated IntrinsicInfo object.
+/// Otherwise, this pointer is null.
+bool IRTranslator::translateTargetIntrinsic(
+    const CallBase &CB, Intrinsic::ID ID, MachineIRBuilder &MIRBuilder,
+    TargetLowering::IntrinsicInfo *TgtMemIntrinsicInfo) {
   ArrayRef<Register> ResultRegs;
-  if (!CI.getType()->isVoidTy())
-    ResultRegs = getOrCreateVRegs(CI);
+  if (!CB.getType()->isVoidTy())
+    ResultRegs = getOrCreateVRegs(CB);
 
   // Ignore the callsite attributes. Backend code is most likely not expecting
   // an intrinsic to sometimes have side effects and sometimes not.
   MachineInstrBuilder MIB = MIRBuilder.buildIntrinsic(ID, ResultRegs);
-  if (isa<FPMathOperator>(CI))
-    MIB->copyIRFlags(CI);
+  if (isa<FPMathOperator>(CB))
+    MIB->copyIRFlags(CB);
 
-  for (const auto &Arg : enumerate(CI.args())) {
+  for (const auto &Arg : enumerate(CB.args())) {
     // If this is required to be an immediate, don't materialize it in a
     // register.
-    if (CI.paramHasAttr(Arg.index(), Attribute::ImmArg)) {
+    if (CB.paramHasAttr(Arg.index(), Attribute::ImmArg)) {
       if (ConstantInt *CI = dyn_cast<ConstantInt>(Arg.value())) {
         // imm arguments are more convenient than cimm (and realistically
         // probably sufficient), so use them.
@@ -2842,29 +2856,32 @@ bool IRTranslator::translateCall(const User &U, MachineIRBuilder &MIRBuilder) {
   }
 
   // Add a MachineMemOperand if it is a target mem intrinsic.
-  TargetLowering::IntrinsicInfo Info;
-  // TODO: Add a GlobalISel version of getTgtMemIntrinsic.
-  if (TLI->getTgtMemIntrinsic(Info, CI, *MF, ID)) {
-    Align Alignment = Info.align.value_or(
-        DL->getABITypeAlign(Info.memVT.getTypeForEVT(F->getContext())));
-    LLT MemTy = Info.memVT.isSimple()
-                    ? getLLTForMVT(Info.memVT.getSimpleVT())
-                    : LLT::scalar(Info.memVT.getStoreSizeInBits());
+  if (TgtMemIntrinsicInfo) {
+    const Function *F = CB.getCalledFunction();
+
+    Align Alignment = TgtMemIntrinsicInfo->align.value_or(DL->getABITypeAlign(
+        TgtMemIntrinsicInfo->memVT.getTypeForEVT(F->getContext())));
+    LLT MemTy =
+        TgtMemIntrinsicInfo->memVT.isSimple()
+            ? getLLTForMVT(TgtMemIntrinsicInfo->memVT.getSimpleVT())
+            : LLT::scalar(TgtMemIntrinsicInfo->memVT.getStoreSizeInBits());
 
     // TODO: We currently just fallback to address space 0 if getTgtMemIntrinsic
     //       didn't yield anything useful.
     MachinePointerInfo MPI;
-    if (Info.ptrVal)
-      MPI = MachinePointerInfo(Info.ptrVal, Info.offset);
-    else if (Info.fallbackAddressSpace)
-      MPI = MachinePointerInfo(*Info.fallbackAddressSpace);
+    if (TgtMemIntrinsicInfo->ptrVal)
+      MPI = MachinePointerInfo(TgtMemIntrinsicInfo->ptrVal,
+                               TgtMemIntrinsicInfo->offset);
+    else if (TgtMemIntrinsicInfo->fallbackAddressSpace)
+      MPI = MachinePointerInfo(*TgtMemIntrinsicInfo->fallbackAddressSpace);
     MIB.addMemOperand(MF->getMachineMemOperand(
-        MPI, Info.flags, MemTy, Alignment, CI.getAAMetadata(),
-        /*Ranges=*/nullptr, Info.ssid, Info.order, Info.failureOrder));
+        MPI, TgtMemIntrinsicInfo->flags, MemTy, Alignment, CB.getAAMetadata(),
+        /*Ranges=*/nullptr, TgtMemIntrinsicInfo->ssid,
+        TgtMemIntrinsicInfo->order, TgtMemIntrinsicInfo->failureOrder));
   }
 
-  if (CI.isConvergent()) {
-    if (auto Bundle = CI.getOperandBundle(LLVMContext::OB_convergencectrl)) {
+  if (CB.isConvergent()) {
+    if (auto Bundle = CB.getOperandBundle(LLVMContext::OB_convergencectrl)) {
       auto *Token = Bundle->Inputs[0].get();
       Register TokenReg = getOrCreateVReg(*Token);
       MIB.addUse(TokenReg, RegState::Implicit);

llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -3489,8 +3489,7 @@ void SelectionDAGBuilder::visitCallBr(const CallBrInst &I) {
 
   // Update successor info.
   addSuccessorWithProb(CallBrMBB, Return, BranchProbability::getOne());
-  for (unsigned i = 0, e = I.getNumIndirectDests(); i < e; ++i) {
-    BasicBlock *Dest = I.getIndirectDest(i);
+  for (BasicBlock *Dest : I.getIndirectDests()) {
     MachineBasicBlock *Target = FuncInfo.getMBB(Dest);
     Target->setIsInlineAsmBrIndirectTarget();
     // If we introduce a type of asm goto statement that is permitted to use an
@@ -5312,18 +5311,26 @@ void SelectionDAGBuilder::visitAtomicStore(const StoreInst &I) {
   DAG.setRoot(OutChain);
 }
 
-/// visitTargetIntrinsic - Lower a call of a target intrinsic to an INTRINSIC
-/// node.
-void SelectionDAGBuilder::visitTargetIntrinsic(const CallInst &I,
-                                               unsigned Intrinsic) {
-  // Ignore the callsite's attributes. A specific call site may be marked with
-  // readnone, but the lowering code will expect the chain based on the
-  // definition.
+/// Check if this intrinsic call depends on the chain (1st return value)
+/// and if it only *loads* memory.
+/// Ignore the callsite's attributes. A specific call site may be marked with
+/// readnone, but the lowering code will expect the chain based on the
+/// definition.
+std::pair<bool, bool>
+SelectionDAGBuilder::getTargetIntrinsicCallProperties(const CallBase &I) {
   const Function *F = I.getCalledFunction();
   bool HasChain = !F->doesNotAccessMemory();
   bool OnlyLoad =
       HasChain && F->onlyReadsMemory() && F->willReturn() && F->doesNotThrow();
 
+  return {HasChain, OnlyLoad};
+}
+
+SmallVector<SDValue, 8> SelectionDAGBuilder::getTargetIntrinsicOperands(
+    const CallBase &I, bool HasChain, bool OnlyLoad,
+    TargetLowering::IntrinsicInfo *TgtMemIntrinsicInfo) {
+  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+
   // Build the operand list.
   SmallVector<SDValue, 8> Ops;
   if (HasChain) {  // If this intrinsic has side-effects, chainify it.
@@ -5335,17 +5342,10 @@ void SelectionDAGBuilder::visitTargetIntrinsic(const CallInst &I,
     }
   }
 
-  // Info is set by getTgtMemIntrinsic
-  TargetLowering::IntrinsicInfo Info;
-  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
-  bool IsTgtIntrinsic = TLI.getTgtMemIntrinsic(Info, I,
-                                               DAG.getMachineFunction(),
-                                               Intrinsic);
-
   // Add the intrinsic ID as an integer operand if it's not a target intrinsic.
-  if (!IsTgtIntrinsic || Info.opc == ISD::INTRINSIC_VOID ||
-      Info.opc == ISD::INTRINSIC_W_CHAIN)
-    Ops.push_back(DAG.getTargetConstant(Intrinsic, getCurSDLoc(),
+  if (!TgtMemIntrinsicInfo || TgtMemIntrinsicInfo->opc == ISD::INTRINSIC_VOID ||
+      TgtMemIntrinsicInfo->opc == ISD::INTRINSIC_W_CHAIN)
+    Ops.push_back(DAG.getTargetConstant(I.getIntrinsicID(), getCurSDLoc(),
                                         TLI.getPointerTy(DAG.getDataLayout())));
 
   // Add all operands of the call to the operand list.
@@ -5368,13 +5368,88 @@ void SelectionDAGBuilder::visitTargetIntrinsic(const CallInst &I,
     }
   }
 
+  if (auto Bundle = I.getOperandBundle(LLVMContext::OB_convergencectrl)) {
+    auto *Token = Bundle->Inputs[0].get();
+    SDValue ConvControlToken = getValue(Token);
+    assert(Ops.back().getValueType() != MVT::Glue &&
+           "Did not expected another glue node here.");
+    ConvControlToken =
+        DAG.getNode(ISD::CONVERGENCECTRL_GLUE, {}, MVT::Glue, ConvControlToken);
+    Ops.push_back(ConvControlToken);
+  }
+
+  return Ops;
+}
+
+SDVTList SelectionDAGBuilder::getTargetIntrinsicVTList(const CallBase &I,
+                                                       bool HasChain) {
+  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+
   SmallVector<EVT, 4> ValueVTs;
   ComputeValueVTs(TLI, DAG.getDataLayout(), I.getType(), ValueVTs);
 
   if (HasChain)
     ValueVTs.push_back(MVT::Other);
 
-  SDVTList VTs = DAG.getVTList(ValueVTs);
+  return DAG.getVTList(ValueVTs);
+}
+
+/// Get an INTRINSIC node for a target intrinsic which does not touch touch
+/// memory.
+SDValue SelectionDAGBuilder::getTargetNonMemIntrinsicNode(
+    const CallBase &I, bool HasChain, SmallVector<SDValue, 8> &Ops,
+    SDVTList &VTs) {
+  if (!HasChain)
+    return DAG.getNode(ISD::INTRINSIC_WO_CHAIN, getCurSDLoc(), VTs, Ops);
+  if (!I.getType()->isVoidTy())
+    return DAG.getNode(ISD::INTRINSIC_W_CHAIN, getCurSDLoc(), VTs, Ops);
+  return DAG.getNode(ISD::INTRINSIC_VOID, getCurSDLoc(), VTs, Ops);
+}
+
+/// Set root, convert return type if necessaey and check alignment.
+SDValue SelectionDAGBuilder::handleTargetIntrinsicRet(const CallBase &I,
+                                                      bool HasChain,
+                                                      bool OnlyLoad,
+                                                      SDValue Result) {
+  if (HasChain) {
+    SDValue Chain = Result.getValue(Result.getNode()->getNumValues() - 1);
+    if (OnlyLoad)
+      PendingLoads.push_back(Chain);
+    else
+      DAG.setRoot(Chain);
+  }
+
+  if (I.getType()->isVoidTy())
+    return Result;
+
+  if (!isa<VectorType>(I.getType()))
+    Result = lowerRangeToAssertZExt(DAG, I, Result);
+
+  MaybeAlign Alignment = I.getRetAlign();
+
+  // Insert `assertalign` node if there's an alignment.
+  if (InsertAssertAlign && Alignment) {
+    Result = DAG.getAssertAlign(getCurSDLoc(), Result, Alignment.valueOrOne());
+  }
+
+  return Result;
+}
+
+/// visitTargetIntrinsic - Lower a call of a target intrinsic to an INTRINSIC
+/// node.
+void SelectionDAGBuilder::visitTargetIntrinsic(const CallInst &I,
+                                               unsigned Intrinsic) {
+  auto [HasChain, OnlyLoad] = getTargetIntrinsicCallProperties(I);
+
+  // Info is set by getTgtMemIntrinsic
+  TargetLowering::IntrinsicInfo Info;
+  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+  bool IsTgtMemIntrinsic =
+      TLI.getTgtMemIntrinsic(Info, I, DAG.getMachineFunction(), Intrinsic);
+
+  SmallVector<SDValue, 8> Ops = getTargetIntrinsicOperands(
+      I, HasChain, OnlyLoad, IsTgtMemIntrinsic ? &Info : nullptr);
+  SDVTList VTs = getTargetIntrinsicVTList(I, HasChain);
 
   // Propagate fast-math-flags from IR to node(s).
   SDNodeFlags Flags;
@@ -5385,19 +5460,9 @@ void SelectionDAGBuilder::visitTargetIntrinsic(const CallInst &I,
   // Create the node.
   SDValue Result;
 
-  if (auto Bundle = I.getOperandBundle(LLVMContext::OB_convergencectrl)) {
-    auto *Token = Bundle->Inputs[0].get();
-    SDValue ConvControlToken = getValue(Token);
-    assert(Ops.back().getValueType() != MVT::Glue &&
-           "Did not expected another glue node here.");
-    ConvControlToken =
-        DAG.getNode(ISD::CONVERGENCECTRL_GLUE, {}, MVT::Glue, ConvControlToken);
-    Ops.push_back(ConvControlToken);
-  }
-
   // In some cases, custom collection of operands from CallInst I may be needed.
   TLI.CollectTargetIntrinsicOperands(I, Ops, DAG);
-  if (IsTgtIntrinsic) {
+  if (IsTgtMemIntrinsic) {
     // This is target intrinsic that touches memory
     //
     // TODO: We currently just fallback to address space 0 if getTgtMemIntrinsic
@@ -5417,34 +5482,11 @@ void SelectionDAGBuilder::visitTargetIntrinsic(const CallInst &I,
         Info.ssid, Info.order, Info.failureOrder);
     Result =
         DAG.getMemIntrinsicNode(Info.opc, getCurSDLoc(), VTs, Ops, MemVT, MMO);
-  } else if (!HasChain) {
-    Result = DAG.getNode(ISD::INTRINSIC_WO_CHAIN, getCurSDLoc(), VTs, Ops);
-  } else if (!I.getType()->isVoidTy()) {
-    Result = DAG.getNode(ISD::INTRINSIC_W_CHAIN, getCurSDLoc(), VTs, Ops);
   } else {
-    Result = DAG.getNode(ISD::INTRINSIC_VOID, getCurSDLoc(), VTs, Ops);
+    Result = getTargetNonMemIntrinsicNode(I, HasChain, Ops, VTs);
   }
 
-  if (HasChain) {
-    SDValue Chain = Result.getValue(Result.getNode()->getNumValues()-1);
-    if (OnlyLoad)
-      PendingLoads.push_back(Chain);
-    else
-      DAG.setRoot(Chain);
-  }
-
-  if (!I.getType()->isVoidTy()) {
-    if (!isa<VectorType>(I.getType()))
-      Result = lowerRangeToAssertZExt(DAG, I, Result);
-
-    MaybeAlign Alignment = I.getRetAlign();
-
-    // Insert `assertalign` node if there's an alignment.
-    if (InsertAssertAlign && Alignment) {
-      Result =
-          DAG.getAssertAlign(getCurSDLoc(), Result, Alignment.valueOrOne());
-    }
-  }
+  Result = handleTargetIntrinsicRet(I, HasChain, OnlyLoad, Result);
 
   setValue(&I, Result);
 }

llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.h

@@ -711,6 +711,17 @@ class SelectionDAGBuilder {
                        MCSymbol *&BeginLabel);
   SDValue lowerEndEH(SDValue Chain, const InvokeInst *II,
                      const BasicBlock *EHPadBB, MCSymbol *BeginLabel);
+
+  std::pair<bool, bool> getTargetIntrinsicCallProperties(const CallBase &I);
+  SmallVector<SDValue, 8> getTargetIntrinsicOperands(
+      const CallBase &I, bool HasChain, bool OnlyLoad,
+      TargetLowering::IntrinsicInfo *TgtMemIntrinsicInfo = nullptr);
+  SDVTList getTargetIntrinsicVTList(const CallBase &I, bool HasChain);
+  SDValue getTargetNonMemIntrinsicNode(const CallBase &I, bool HasChain,
+                                       SmallVector<SDValue, 8> &Ops,
+                                       SDVTList &VTs);
+  SDValue handleTargetIntrinsicRet(const CallBase &I, bool HasChain,
+                                   bool OnlyLoad, SDValue Result);
 };
 
 /// This struct represents the registers (physical or virtual)