CXX_FAST_TLS calling convention: performance improvement for AArch64.

[oota-llvm.git] / lib / Target / AArch64 / AArch64ISelLowering.cpp

diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index 4fe8565a06c84facc68e13c57fa927f07f57bd56..9f5beff121002a5e9103f31b57af3f3762c0406f 100644 (file)
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -3271,6 +3271,19 @@ AArch64TargetLowering::LowerReturn(SDValue Chain, CallingConv::ID CallConv,
     Flag = Chain.getValue(1);
     RetOps.push_back(DAG.getRegister(VA.getLocReg(), VA.getLocVT()));
   }
+  const AArch64RegisterInfo *TRI = Subtarget->getRegisterInfo();
+  const MCPhysReg *I =
+      TRI->getCalleeSavedRegsViaCopy(&DAG.getMachineFunction());
+  if (I) {
+    for (; *I; ++I) {
+      if (AArch64::GPR64RegClass.contains(*I))
+        RetOps.push_back(DAG.getRegister(*I, MVT::i64));
+      else if (AArch64::FPR64RegClass.contains(*I))
+        RetOps.push_back(DAG.getRegister(*I, MVT::getFloatingPointVT(64)));
+      else
+        llvm_unreachable("Unexpected register class in CSRsViaCopy!");
+    }
+  }
 
   RetOps[0] = Chain; // Update chain.
 
@@ -10003,3 +10016,49 @@ Value *AArch64TargetLowering::getSafeStackPointerLocation(IRBuilder<> &IRB) cons
       IRB.CreateConstGEP1_32(IRB.CreateCall(ThreadPointerFunc), TlsOffset),
       Type::getInt8PtrTy(IRB.getContext())->getPointerTo(0));
 }
+
+void AArch64TargetLowering::initializeSplitCSR(MachineBasicBlock *Entry) const {
+  // Update IsSplitCSR in AArch64unctionInfo.
+  AArch64FunctionInfo *AFI = Entry->getParent()->getInfo<AArch64FunctionInfo>();
+  AFI->setIsSplitCSR(true);
+}
+
+void AArch64TargetLowering::insertCopiesSplitCSR(
+    MachineBasicBlock *Entry,
+    const SmallVectorImpl<MachineBasicBlock *> &Exits) const {
+  const AArch64RegisterInfo *TRI = Subtarget->getRegisterInfo();
+  const MCPhysReg *IStart = TRI->getCalleeSavedRegsViaCopy(Entry->getParent());
+  if (!IStart)
+    return;
+
+  const TargetInstrInfo *TII = Subtarget->getInstrInfo();
+  MachineRegisterInfo *MRI = &Entry->getParent()->getRegInfo();
+  for (const MCPhysReg *I = IStart; *I; ++I) {
+    const TargetRegisterClass *RC = nullptr;
+    if (AArch64::GPR64RegClass.contains(*I))
+      RC = &AArch64::GPR64RegClass;
+    else if (AArch64::FPR64RegClass.contains(*I))
+      RC = &AArch64::FPR64RegClass;
+    else
+      llvm_unreachable("Unexpected register class in CSRsViaCopy!");
+
+    unsigned NewVR = MRI->createVirtualRegister(RC);
+    // Create copy from CSR to a virtual register.
+    // FIXME: this currently does not emit CFI pseudo-instructions, it works
+    // fine for CXX_FAST_TLS since the C++-style TLS access functions should be
+    // nounwind. If we want to generalize this later, we may need to emit
+    // CFI pseudo-instructions.
+    assert(Entry->getParent()->getFunction()->hasFnAttribute(
+               Attribute::NoUnwind) &&
+           "Function should be nounwind in insertCopiesSplitCSR!");
+    Entry->addLiveIn(*I);
+    BuildMI(*Entry, Entry->begin(), DebugLoc(), TII->get(TargetOpcode::COPY),
+            NewVR)
+        .addReg(*I);
+
+    for (auto *Exit : Exits)
+      BuildMI(*Exit, Exit->begin(), DebugLoc(), TII->get(TargetOpcode::COPY),
+              *I)
+          .addReg(NewVR);
+  }
+}