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

Use movss to insert_vector_elt(v, s, 0). 

llvm-svn: 27782
This commit is contained in:
Evan Cheng 2006-04-17 22:45:49 +00:00
parent 36dd7c98d1
commit 5421206c4b
2 changed files with 37 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -3015,28 +3015,41 @@ SDOperand X86TargetLowering::LowerOperation(SDOperand Op, SelectionDAG &DAG) {
N2 = DAG.getConstant(cast<ConstantSDNode>(N2)->getValue(), MVT::i32);
return DAG.getNode(X86ISD::PINSRW, VT, N0, N1, N2);
} else if (MVT::getSizeInBits(BaseVT) == 32) {
// Use two pinsrw instructions to insert a 32 bit value.
unsigned Idx = cast<ConstantSDNode>(N2)->getValue();
Idx <<= 1;
if (MVT::isFloatingPoint(N1.getValueType())) {
if (N1.getOpcode() == ISD::LOAD) {
// Just load directly from f32mem to R32.
N1 = DAG.getLoad(MVT::i32, N1.getOperand(0), N1.getOperand(1),
N1.getOperand(2));
} else {
N1 = DAG.getNode(ISD::SCALAR_TO_VECTOR, MVT::v4f32, N1);
N1 = DAG.getNode(ISD::BIT_CONVERT, MVT::v4i32, N1);
N1 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, MVT::i32, N1,
DAG.getConstant(0, MVT::i32));
if (Idx == 0) {
// Use a movss.
N1 = DAG.getNode(ISD::SCALAR_TO_VECTOR, VT, N1);
MVT::ValueType MaskVT = MVT::getIntVectorWithNumElements(4);
MVT::ValueType BaseVT = MVT::getVectorBaseType(MaskVT);
std::vector<SDOperand> MaskVec;
MaskVec.push_back(DAG.getConstant(4, BaseVT));
for (unsigned i = 1; i <= 3; ++i)
MaskVec.push_back(DAG.getConstant(i, BaseVT));
return DAG.getNode(ISD::VECTOR_SHUFFLE, VT, N0, N1,
DAG.getNode(ISD::BUILD_VECTOR, MaskVT, MaskVec));
} else {
// Use two pinsrw instructions to insert a 32 bit value.
Idx <<= 1;
if (MVT::isFloatingPoint(N1.getValueType())) {
if (N1.getOpcode() == ISD::LOAD) {
// Just load directly from f32mem to R32.
N1 = DAG.getLoad(MVT::i32, N1.getOperand(0), N1.getOperand(1),
N1.getOperand(2));
} else {
N1 = DAG.getNode(ISD::SCALAR_TO_VECTOR, MVT::v4f32, N1);
N1 = DAG.getNode(ISD::BIT_CONVERT, MVT::v4i32, N1);
N1 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, MVT::i32, N1,
DAG.getConstant(0, MVT::i32));
}
}
N0 = DAG.getNode(ISD::BIT_CONVERT, MVT::v8i16, N0);
N0 = DAG.getNode(X86ISD::PINSRW, MVT::v8i16, N0, N1,
DAG.getConstant(Idx, MVT::i32));
N1 = DAG.getNode(ISD::SRL, MVT::i32, N1, DAG.getConstant(16, MVT::i8));
N0 = DAG.getNode(X86ISD::PINSRW, MVT::v8i16, N0, N1,
DAG.getConstant(Idx+1, MVT::i32));
return DAG.getNode(ISD::BIT_CONVERT, VT, N0);
}
N0 = DAG.getNode(ISD::BIT_CONVERT, MVT::v8i16, N0);
N0 = DAG.getNode(X86ISD::PINSRW, MVT::v8i16, N0, N1,
DAG.getConstant(Idx, MVT::i32));
N1 = DAG.getNode(ISD::SRL, MVT::i32, N1, DAG.getConstant(16, MVT::i8));
N0 = DAG.getNode(X86ISD::PINSRW, MVT::v8i16, N0, N1,
DAG.getConstant(Idx+1, MVT::i32));
return DAG.getNode(ISD::BIT_CONVERT, VT, N0);
}
return SDOperand();

5
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -2414,6 +2414,11 @@ def : Pat<(v4i32 (vector_shuffle (bc_v4i32 (loadv2i64 addr:$src)), (undef),
MOVSLDUP_shuffle_mask)),
(MOVSLDUPrm addr:$src)>, Requires<[HasSSE3]>;
// vector_shuffle v1, v2 <4, 1, 2, 3>
def : Pat<(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
MOVS_shuffle_mask)),
(MOVLPSrr VR128:$src1, VR128:$src2)>;
// 128-bit logical shifts
def : Pat<(int_x86_sse2_psll_dq VR128:$src1, imm:$src2),
(v2i64 (PSLLDQri VR128:$src1, (PSxLDQ_imm imm:$src2)))>,