6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-07-24 22:24:54 +00:00
Code Issues Projects Releases Wiki Activity

[ARM] Use AEABI aligned function variants

Browse Source 
AEABI defines aligned variants of memcpy etc. that can be faster than
the default version due to not having to do alignment checks. When
emitting target code for these functions make use of these aligned
variants if possible. Also convert memset to memclr if possible.

Differential Revision: http://reviews.llvm.org/D8060


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237127 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
John Brawn
2015-05-12 13:13:38 +00:00
parent 00666a17ff
commit e38f45effc
3 changed files with 223 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

179
lib/Target/ARM/ARMSelectionDAGInfo.cpp
View File

@@ -24,6 +24,114 @@ ARMSelectionDAGInfo::ARMSelectionDAGInfo(const DataLayout &DL)
ARMSelectionDAGInfo::~ARMSelectionDAGInfo() {
}
// 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, 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 = TLI->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)
.setCallee(TLI->getLibcallCallingConv(LC),
Type::getVoidTy(*DAG.getContext()),
DAG.getExternalSymbol(FunctionNames[AEABILibcall][AlignVariant],
TLI->getPointerTy()), std::move(Args), 0)
.setDiscardResult();
std::pair<SDValue,SDValue> CallResult = TLI->LowerCallTo(CLI);
return CallResult.second;
}
SDValue
ARMSelectionDAGInfo::EmitTargetCodeForMemcpy(SelectionDAG &DAG, SDLoc dl,
SDValue Chain,
@@ -42,10 +150,12 @@ ARMSelectionDAGInfo::EmitTargetCodeForMemcpy(SelectionDAG &DAG, SDLoc dl,
// within a subtarget-specific limit.
ConstantSDNode *ConstantSize = dyn_cast<ConstantSDNode>(Size);
if (!ConstantSize)
return SDValue();
return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size, Align,
RTLIB::MEMCPY);
uint64_t SizeVal = ConstantSize->getZExtValue();
if (!AlwaysInline && SizeVal > Subtarget.getMaxInlineSizeThreshold())
return SDValue();
return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size, Align,
RTLIB::MEMCPY);
unsigned BytesLeft = SizeVal & 3;
unsigned NumMemOps = SizeVal >> 2;
@@ -142,59 +252,26 @@ ARMSelectionDAGInfo::EmitTargetCodeForMemcpy(SelectionDAG &DAG, SDLoc dl,
makeArrayRef(TFOps, i));
}
// Adjust parameters for memset, EABI uses format (ptr, size, value),
// GNU library uses (ptr, value, size)
// See RTABI section 4.3.4
SDValue ARMSelectionDAGInfo::
EmitTargetCodeForMemmove(SelectionDAG &DAG, SDLoc dl,
SDValue Chain,
SDValue Dst, SDValue Src,
SDValue Size, unsigned Align,
bool isVolatile,
MachinePointerInfo DstPtrInfo,
MachinePointerInfo SrcPtrInfo) const {
return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size, Align,
RTLIB::MEMMOVE);
}
SDValue ARMSelectionDAGInfo::
EmitTargetCodeForMemset(SelectionDAG &DAG, SDLoc dl,
SDValue Chain, SDValue Dst,
SDValue Src, SDValue Size,
unsigned Align, bool isVolatile,
MachinePointerInfo DstPtrInfo) const {
const ARMSubtarget &Subtarget =
DAG.getMachineFunction().getSubtarget<ARMSubtarget>();
// Use default for non-AAPCS (or MachO) subtargets
if (!Subtarget.isAAPCS_ABI() || Subtarget.isTargetMachO() ||
Subtarget.isTargetWindows())
return SDValue();
const ARMTargetLowering &TLI = *Subtarget.getTargetLowering();
TargetLowering::ArgListTy Args;
TargetLowering::ArgListEntry Entry;
// First argument: data pointer
Type *IntPtrTy = TLI.getDataLayout()->getIntPtrType(*DAG.getContext());
Entry.Node = Dst;
Entry.Ty = IntPtrTy;
Args.push_back(Entry);
// Second argument: buffer size
Entry.Node = Size;
Entry.Ty = IntPtrTy;
Entry.isSExt = false;
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
Src = DAG.getNode(ISD::ZERO_EXTEND, dl, MVT::i32, Src);
// Third argument: value to fill
Entry.Node = Src;
Entry.Ty = Type::getInt32Ty(*DAG.getContext());
Entry.isSExt = true;
Args.push_back(Entry);
// Emit __eabi_memset call
TargetLowering::CallLoweringInfo CLI(DAG);
CLI.setDebugLoc(dl).setChain(Chain)
.setCallee(TLI.getLibcallCallingConv(RTLIB::MEMSET),
Type::getVoidTy(*DAG.getContext()),
DAG.getExternalSymbol(TLI.getLibcallName(RTLIB::MEMSET),
TLI.getPointerTy()), std::move(Args), 0)
.setDiscardResult();
std::pair<SDValue,SDValue> CallResult = TLI.LowerCallTo(CLI);
return CallResult.second;
return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size, Align,
RTLIB::MEMSET);
}