File Manager

003 File Manager

Current Path: /usr/src/contrib/llvm-project/llvm/lib/Target/ARM

usr / src / contrib / llvm-project / llvm / lib / Target / ARM /

📁 ..
📄 A15SDOptimizer.cpp(24.01 KB)
📄 ARM.h(2.78 KB)
📄 ARM.td(73.6 KB)
📄 ARMAsmPrinter.cpp(80.17 KB)
📄 ARMAsmPrinter.h(5.74 KB)
📄 ARMBaseInstrInfo.cpp(209.03 KB)
📄 ARMBaseInstrInfo.h(36.07 KB)
📄 ARMBaseRegisterInfo.cpp(34.2 KB)
📄 ARMBaseRegisterInfo.h(7.84 KB)
📄 ARMBasicBlockInfo.cpp(5.18 KB)
📄 ARMBasicBlockInfo.h(5.25 KB)
📄 ARMCallLowering.cpp(19.74 KB)
📄 ARMCallLowering.h(1.89 KB)
📄 ARMCallingConv.cpp(11.8 KB)
📄 ARMCallingConv.h(2.43 KB)
📄 ARMCallingConv.td(14.63 KB)
📄 ARMConstantIslandPass.cpp(90.84 KB)
📄 ARMConstantPoolValue.cpp(11.53 KB)
📄 ARMConstantPoolValue.h(10.1 KB)
📄 ARMExpandPseudoInsts.cpp(115.56 KB)
📄 ARMFastISel.cpp(106.14 KB)
📄 ARMFeatures.h(2.48 KB)
📄 ARMFrameLowering.cpp(102.32 KB)
📄 ARMFrameLowering.h(4.02 KB)
📄 ARMHazardRecognizer.cpp(3.41 KB)
📄 ARMHazardRecognizer.h(1.54 KB)
📄 ARMISelDAGToDAG.cpp(206.42 KB)
📄 ARMISelLowering.cpp(728.6 KB)
📄 ARMISelLowering.h(38.98 KB)
📄 ARMInstrCDE.td(24.04 KB)
📄 ARMInstrFormats.td(93.92 KB)
📄 ARMInstrInfo.cpp(4.2 KB)
📄 ARMInstrInfo.h(1.49 KB)
📄 ARMInstrInfo.td(243.51 KB)
📄 ARMInstrMVE.td(299.67 KB)
📄 ARMInstrNEON.td(436.25 KB)
📄 ARMInstrThumb.td(65.92 KB)
📄 ARMInstrThumb2.td(211.06 KB)
📄 ARMInstrVFP.td(110.46 KB)
📄 ARMInstructionSelector.cpp(39.12 KB)
📄 ARMLegalizerInfo.cpp(18.8 KB)
📄 ARMLegalizerInfo.h(2.41 KB)
📄 ARMLoadStoreOptimizer.cpp(94.44 KB)
📄 ARMLowOverheadLoops.cpp(60.28 KB)
📄 ARMMCInstLower.cpp(7.2 KB)
📄 ARMMachineFunctionInfo.cpp(821 B)
📄 ARMMachineFunctionInfo.h(9.68 KB)
📄 ARMMacroFusion.cpp(2.36 KB)
📄 ARMMacroFusion.h(966 B)
📄 ARMOptimizeBarriersPass.cpp(3.43 KB)
📄 ARMParallelDSP.cpp(26.82 KB)
📄 ARMPerfectShuffle.h(382.02 KB)
📄 ARMPredicates.td(14.16 KB)
📄 ARMRegisterBankInfo.cpp(18.18 KB)
📄 ARMRegisterBankInfo.h(1.41 KB)
📄 ARMRegisterBanks.td(577 B)
📄 ARMRegisterInfo.cpp(685 B)
📄 ARMRegisterInfo.h(845 B)
📄 ARMRegisterInfo.td(24.53 KB)
📄 ARMSchedule.td(15.13 KB)
📄 ARMScheduleA57.td(62.61 KB)
📄 ARMScheduleA57WriteRes.td(11.43 KB)
📄 ARMScheduleA8.td(49.59 KB)
📄 ARMScheduleA9.td(130.35 KB)
📄 ARMScheduleM4.td(4.77 KB)
📄 ARMScheduleR52.td(44.27 KB)
📄 ARMScheduleSwift.td(50.53 KB)
📄 ARMScheduleV6.td(12.34 KB)
📄 ARMSelectionDAGInfo.cpp(9.21 KB)
📄 ARMSelectionDAGInfo.h(2.81 KB)
📄 ARMSubtarget.cpp(16.73 KB)
📄 ARMSubtarget.h(31.56 KB)
📄 ARMSystemRegister.td(5.42 KB)
📄 ARMTargetMachine.cpp(19.74 KB)
📄 ARMTargetMachine.h(3.48 KB)
📄 ARMTargetObjectFile.cpp(3.75 KB)
📄 ARMTargetObjectFile.h(1.67 KB)
📄 ARMTargetTransformInfo.cpp(63.49 KB)
📄 ARMTargetTransformInfo.h(10.22 KB)
📁 AsmParser
📁 Disassembler
📁 MCTargetDesc
📄 MLxExpansionPass.cpp(11.56 KB)
📄 MVEGatherScatterLowering.cpp(40.3 KB)
📄 MVETailPredication.cpp(23.2 KB)
📄 MVEVPTBlockPass.cpp(10.77 KB)
📄 MVEVPTOptimisationsPass.cpp(16.46 KB)
📁 TargetInfo
📄 Thumb1FrameLowering.cpp(39.45 KB)
📄 Thumb1FrameLowering.h(3.48 KB)
📄 Thumb1InstrInfo.cpp(5.73 KB)
📄 Thumb1InstrInfo.h(2.38 KB)
📄 Thumb2ITBlockPass.cpp(9.09 KB)
📄 Thumb2InstrInfo.cpp(26.43 KB)
📄 Thumb2InstrInfo.h(3.75 KB)
📄 Thumb2SizeReduction.cpp(40.25 KB)
📄 ThumbRegisterInfo.cpp(21.75 KB)
📄 ThumbRegisterInfo.h(2.44 KB)
📁 Utils

Editing: ARMSelectionDAGInfo.cpp

//===-- ARMSelectionDAGInfo.cpp - ARM SelectionDAG Info -------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the ARMSelectionDAGInfo class.
//
//===----------------------------------------------------------------------===//

#include "ARMTargetMachine.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/IR/DerivedTypes.h"
using namespace llvm;

#define DEBUG_TYPE "arm-selectiondag-info"

// Emit, if possible, a specialized version of the given Libcall. Typically this
// means selecting the appropriately aligned version, but we also convert memset
// of 0 into memclr.
SDValue ARMSelectionDAGInfo::EmitSpecializedLibcall(
    SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
    SDValue Size, unsigned Align, RTLIB::Libcall LC) const {
  const ARMSubtarget &Subtarget =
      DAG.getMachineFunction().getSubtarget<ARMSubtarget>();
  const ARMTargetLowering *TLI = Subtarget.getTargetLowering();

// Only use a specialized AEABI function if the default version of this
  // Libcall is an AEABI function.
  if (std::strncmp(TLI->getLibcallName(LC), "__aeabi", 7) != 0)
    return SDValue();

// Translate RTLIB::Libcall to AEABILibcall. We only do this in order to be
  // able to translate memset to memclr and use the value to index the function
  // name array.
  enum {
    AEABI_MEMCPY = 0,
    AEABI_MEMMOVE,
    AEABI_MEMSET,
    AEABI_MEMCLR
  } AEABILibcall;
  switch (LC) {
  case RTLIB::MEMCPY:
    AEABILibcall = AEABI_MEMCPY;
    break;
  case RTLIB::MEMMOVE:
    AEABILibcall = AEABI_MEMMOVE;
    break;
  case RTLIB::MEMSET:
    AEABILibcall = AEABI_MEMSET;
    if (ConstantSDNode *ConstantSrc = dyn_cast<ConstantSDNode>(Src))
      if (ConstantSrc->getZExtValue() == 0)
        AEABILibcall = AEABI_MEMCLR;
    break;
  default:
    return SDValue();
  }

// Choose the most-aligned libcall variant that we can
  enum {
    ALIGN1 = 0,
    ALIGN4,
    ALIGN8
  } AlignVariant;
  if ((Align & 7) == 0)
    AlignVariant = ALIGN8;
  else if ((Align & 3) == 0)
    AlignVariant = ALIGN4;
  else
    AlignVariant = ALIGN1;

TargetLowering::ArgListTy Args;
  TargetLowering::ArgListEntry Entry;
  Entry.Ty = DAG.getDataLayout().getIntPtrType(*DAG.getContext());
  Entry.Node = Dst;
  Args.push_back(Entry);
  if (AEABILibcall == AEABI_MEMCLR) {
    Entry.Node = Size;
    Args.push_back(Entry);
  } else if (AEABILibcall == AEABI_MEMSET) {
    // Adjust parameters for memset, EABI uses format (ptr, size, value),
    // GNU library uses (ptr, value, size)
    // See RTABI section 4.3.4
    Entry.Node = Size;
    Args.push_back(Entry);

// Extend or truncate the argument to be an i32 value for the call.
    if (Src.getValueType().bitsGT(MVT::i32))
      Src = DAG.getNode(ISD::TRUNCATE, dl, MVT::i32, Src);
    else if (Src.getValueType().bitsLT(MVT::i32))
      Src = DAG.getNode(ISD::ZERO_EXTEND, dl, MVT::i32, Src);

Entry.Node = Src;
    Entry.Ty = Type::getInt32Ty(*DAG.getContext());
    Entry.IsSExt = false;
    Args.push_back(Entry);
  } else {
    Entry.Node = Src;
    Args.push_back(Entry);

Entry.Node = Size;
    Args.push_back(Entry);
  }

char const *FunctionNames[4][3] = {
    { "__aeabi_memcpy",  "__aeabi_memcpy4",  "__aeabi_memcpy8"  },
    { "__aeabi_memmove", "__aeabi_memmove4", "__aeabi_memmove8" },
    { "__aeabi_memset",  "__aeabi_memset4",  "__aeabi_memset8"  },
    { "__aeabi_memclr",  "__aeabi_memclr4",  "__aeabi_memclr8"  }
  };
  TargetLowering::CallLoweringInfo CLI(DAG);
  CLI.setDebugLoc(dl)
      .setChain(Chain)
      .setLibCallee(
          TLI->getLibcallCallingConv(LC), Type::getVoidTy(*DAG.getContext()),
          DAG.getExternalSymbol(FunctionNames[AEABILibcall][AlignVariant],
                                TLI->getPointerTy(DAG.getDataLayout())),
          std::move(Args))
      .setDiscardResult();
  std::pair<SDValue,SDValue> CallResult = TLI->LowerCallTo(CLI);

return CallResult.second;
}

SDValue ARMSelectionDAGInfo::EmitTargetCodeForMemcpy(
    SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
    SDValue Size, Align Alignment, bool isVolatile, bool AlwaysInline,
    MachinePointerInfo DstPtrInfo, MachinePointerInfo SrcPtrInfo) const {
  const ARMSubtarget &Subtarget =
      DAG.getMachineFunction().getSubtarget<ARMSubtarget>();
  // Do repeated 4-byte loads and stores. To be improved.
  // This requires 4-byte alignment.
  if (Alignment < Align(4))
    return SDValue();
  // This requires the copy size to be a constant, preferably
  // within a subtarget-specific limit.
  ConstantSDNode *ConstantSize = dyn_cast<ConstantSDNode>(Size);
  if (!ConstantSize)
    return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size,
                                  Alignment.value(), RTLIB::MEMCPY);
  uint64_t SizeVal = ConstantSize->getZExtValue();
  if (!AlwaysInline && SizeVal > Subtarget.getMaxInlineSizeThreshold())
    return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size,
                                  Alignment.value(), RTLIB::MEMCPY);

unsigned BytesLeft = SizeVal & 3;
  unsigned NumMemOps = SizeVal >> 2;
  unsigned EmittedNumMemOps = 0;
  EVT VT = MVT::i32;
  unsigned VTSize = 4;
  unsigned i = 0;
  // Emit a maximum of 4 loads in Thumb1 since we have fewer registers
  const unsigned MaxLoadsInLDM = Subtarget.isThumb1Only() ? 4 : 6;
  SDValue TFOps[6];
  SDValue Loads[6];
  uint64_t SrcOff = 0, DstOff = 0;

// FIXME: We should invent a VMEMCPY pseudo-instruction that lowers to
  // VLDM/VSTM and make this code emit it when appropriate. This would reduce
  // pressure on the general purpose registers. However this seems harder to map
  // onto the register allocator's view of the world.

// The number of MEMCPY pseudo-instructions to emit. We use up to
  // MaxLoadsInLDM registers per mcopy, which will get lowered into ldm/stm
  // later on. This is a lower bound on the number of MEMCPY operations we must
  // emit.
  unsigned NumMEMCPYs = (NumMemOps + MaxLoadsInLDM - 1) / MaxLoadsInLDM;

// Code size optimisation: do not inline memcpy if expansion results in
  // more instructions than the libary call.
  if (NumMEMCPYs > 1 && Subtarget.hasMinSize()) {
    return SDValue();
  }

SDVTList VTs = DAG.getVTList(MVT::i32, MVT::i32, MVT::Other, MVT::Glue);

for (unsigned I = 0; I != NumMEMCPYs; ++I) {
    // Evenly distribute registers among MEMCPY operations to reduce register
    // pressure.
    unsigned NextEmittedNumMemOps = NumMemOps * (I + 1) / NumMEMCPYs;
    unsigned NumRegs = NextEmittedNumMemOps - EmittedNumMemOps;

Dst = DAG.getNode(ARMISD::MEMCPY, dl, VTs, Chain, Dst, Src,
                      DAG.getConstant(NumRegs, dl, MVT::i32));
    Src = Dst.getValue(1);
    Chain = Dst.getValue(2);

DstPtrInfo = DstPtrInfo.getWithOffset(NumRegs * VTSize);
    SrcPtrInfo = SrcPtrInfo.getWithOffset(NumRegs * VTSize);

EmittedNumMemOps = NextEmittedNumMemOps;
  }

if (BytesLeft == 0)
    return Chain;

// Issue loads / stores for the trailing (1 - 3) bytes.
  auto getRemainingValueType = [](unsigned BytesLeft) {
    return (BytesLeft >= 2) ? MVT::i16 : MVT::i8;
  };
  auto getRemainingSize = [](unsigned BytesLeft) {
    return (BytesLeft >= 2) ? 2 : 1;
  };

unsigned BytesLeftSave = BytesLeft;
  i = 0;
  while (BytesLeft) {
    VT = getRemainingValueType(BytesLeft);
    VTSize = getRemainingSize(BytesLeft);
    Loads[i] = DAG.getLoad(VT, dl, Chain,
                           DAG.getNode(ISD::ADD, dl, MVT::i32, Src,
                                       DAG.getConstant(SrcOff, dl, MVT::i32)),
                           SrcPtrInfo.getWithOffset(SrcOff));
    TFOps[i] = Loads[i].getValue(1);
    ++i;
    SrcOff += VTSize;
    BytesLeft -= VTSize;
  }
  Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other,
                      makeArrayRef(TFOps, i));

i = 0;
  BytesLeft = BytesLeftSave;
  while (BytesLeft) {
    VT = getRemainingValueType(BytesLeft);
    VTSize = getRemainingSize(BytesLeft);
    TFOps[i] = DAG.getStore(Chain, dl, Loads[i],
                            DAG.getNode(ISD::ADD, dl, MVT::i32, Dst,
                                        DAG.getConstant(DstOff, dl, MVT::i32)),
                            DstPtrInfo.getWithOffset(DstOff));
    ++i;
    DstOff += VTSize;
    BytesLeft -= VTSize;
  }
  return DAG.getNode(ISD::TokenFactor, dl, MVT::Other,
                     makeArrayRef(TFOps, i));
}

SDValue ARMSelectionDAGInfo::EmitTargetCodeForMemmove(
    SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
    SDValue Size, Align Alignment, bool isVolatile,
    MachinePointerInfo DstPtrInfo, MachinePointerInfo SrcPtrInfo) const {
  return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size,
                                Alignment.value(), RTLIB::MEMMOVE);
}

SDValue ARMSelectionDAGInfo::EmitTargetCodeForMemset(
    SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
    SDValue Size, Align Alignment, bool isVolatile,
    MachinePointerInfo DstPtrInfo) const {
  return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size,
                                Alignment.value(), RTLIB::MEMSET);
}

003 File Manager

Editing: ARMSelectionDAGInfo.cpp

Upload File

Create Folder