maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Add some generic expansion logic for SMULO and UMULO. Fixes UMULO 

support for x86, and UMULO/SMULO for many architectures, including PPC 
(PR4201), ARM, and Cell. The resulting expansion isn't perfect, but it's
not bad.

llvm-svn: 73477
This commit is contained in:
Eli Friedman 2009-06-16 06:58:29 +00:00
parent 48021d15d6
commit abfad5d61e
4 changed files with 85 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
View File

@ -2768,6 +2768,53 @@ void SelectionDAGLegalize::ExpandNode(SDNode *Node,
ISD::SETULT : ISD::SETUGT)); ISD::SETULT : ISD::SETUGT));
break; break;
} }
case ISD::UMULO:
case ISD::SMULO: {
MVT VT = Node->getValueType(0);
SDValue LHS = Node->getOperand(0);
SDValue RHS = Node->getOperand(1);
SDValue BottomHalf;
SDValue TopHalf;
static unsigned Ops[2][3] =
{ { ISD::MULHU, ISD::UMUL_LOHI, ISD::ZERO_EXTEND },
{ ISD::MULHS, ISD::SMUL_LOHI, ISD::SIGN_EXTEND }};
bool isSigned = Node->getOpcode() == ISD::SMULO;
if (TLI.isOperationLegalOrCustom(Ops[isSigned][0], VT)) {
BottomHalf = DAG.getNode(ISD::MUL, dl, VT, LHS, RHS);
TopHalf = DAG.getNode(Ops[isSigned][0], dl, VT, LHS, RHS);
} else if (TLI.isOperationLegalOrCustom(Ops[isSigned][1], VT)) {
BottomHalf = DAG.getNode(Ops[isSigned][1], dl, DAG.getVTList(VT, VT), LHS,
RHS);
TopHalf = BottomHalf.getValue(1);
} else if (TLI.isTypeLegal(MVT::getIntegerVT(VT.getSizeInBits() * 2))) {
MVT WideVT = MVT::getIntegerVT(VT.getSizeInBits() * 2);
LHS = DAG.getNode(Ops[isSigned][2], dl, WideVT, LHS);
RHS = DAG.getNode(Ops[isSigned][2], dl, WideVT, RHS);
Tmp1 = DAG.getNode(ISD::MUL, dl, WideVT, LHS, RHS);
BottomHalf = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, VT, Tmp1,
DAG.getIntPtrConstant(0));
TopHalf = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, VT, Tmp1,
DAG.getIntPtrConstant(1));
} else {
// FIXME: We should be able to fall back to a libcall with an illegal
// type in some cases cases.
// Also, we can fall back to a division in some cases, but that's a big
// performance hit in the general case.
assert(0 && "Don't know how to expand this operation yet!");
}
if (isSigned) {
Tmp1 = DAG.getConstant(VT.getSizeInBits() - 1, TLI.getShiftAmountTy());
Tmp1 = DAG.getNode(ISD::SRA, dl, VT, BottomHalf, Tmp1);
TopHalf = DAG.getSetCC(dl, TLI.getSetCCResultType(VT), TopHalf, Tmp1,
ISD::SETNE);
} else {
TopHalf = DAG.getSetCC(dl, TLI.getSetCCResultType(VT), TopHalf,
DAG.getConstant(0, VT), ISD::SETNE);
}
Results.push_back(BottomHalf);
Results.push_back(TopHalf);
break;
}
case ISD::BUILD_PAIR: { case ISD::BUILD_PAIR: {
MVT PairTy = Node->getValueType(0); MVT PairTy = Node->getValueType(0);
Tmp1 = DAG.getNode(ISD::ZERO_EXTEND, dl, PairTy, Node->getOperand(0)); Tmp1 = DAG.getNode(ISD::ZERO_EXTEND, dl, PairTy, Node->getOperand(0));

15
llvm/test/CodeGen/CellSPU/mul-with-overflow.ll Normal file
View File

@ -0,0 +1,15 @@
; RUN: llvm-as < %s | llc -march=cellspu
declare {i16, i1} @llvm.smul.with.overflow.i16(i16 %a, i16 %b)
define i1 @a(i16 %x) zeroext nounwind {
%res = call {i16, i1} @llvm.smul.with.overflow.i16(i16 %x, i16 3)
%obil = extractvalue {i16, i1} %res, 1
ret i1 %obil
}
declare {i16, i1} @llvm.umul.with.overflow.i16(i16 %a, i16 %b)
define i1 @b(i16 %x) zeroext nounwind {
%res = call {i16, i1} @llvm.umul.with.overflow.i16(i16 %x, i16 3)
%obil = extractvalue {i16, i1} %res, 1
ret i1 %obil
}

15
llvm/test/CodeGen/PowerPC/mul-with-overflow.ll Normal file
View File

@ -0,0 +1,15 @@
; RUN: llvm-as < %s | llc -march=ppc32
declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
define i1 @a(i32 %x) zeroext nounwind {
%res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %x, i32 3)
%obil = extractvalue {i32, i1} %res, 1
ret i1 %obil
}
declare {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
define i1 @b(i32 %x) zeroext nounwind {
%res = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %x, i32 3)
%obil = extractvalue {i32, i1} %res, 1
ret i1 %obil
}

8
llvm/test/CodeGen/X86/umul-with-overflow.ll Normal file
View File

@ -0,0 +1,8 @@
; RUN: llvm-as < %s | llc -march=x86 | grep "\\\\\\\<mul"
declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
define i1 @a(i32 %x) zeroext nounwind {
%res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %x, i32 3)
%obil = extractvalue {i32, i1} %res, 1
ret i1 %obil
}