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

Legalizer: Add support for splitting insert_subvectors. 

We handle this by spilling the whole thing to the stack and doing the
insertion as a store.

PR19492. This happens in real code because the vectorizer creates v2i128 when AVX is enabled.

llvm-svn: 211435
This commit is contained in:
Benjamin Kramer 2014-06-21 12:56:42 +00:00
parent d46e4a2303
commit b7f5fb5751
3 changed files with 72 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
View File

@ -570,6 +570,7 @@ private:
void SplitVecRes_BUILD_VECTOR(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_CONCAT_VECTORS(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_EXTRACT_SUBVECTOR(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_INSERT_SUBVECTOR(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_FPOWI(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_INSERT_VECTOR_ELT(SDNode *N, SDValue &Lo, SDValue &Hi);
void SplitVecRes_LOAD(LoadSDNode *N, SDValue &Lo, SDValue &Hi);

38
llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
View File

@ -545,6 +545,7 @@ void DAGTypeLegalizer::SplitVectorResult(SDNode *N, unsigned ResNo) {
case ISD::BUILD_VECTOR: SplitVecRes_BUILD_VECTOR(N, Lo, Hi); break;
case ISD::CONCAT_VECTORS: SplitVecRes_CONCAT_VECTORS(N, Lo, Hi); break;
case ISD::EXTRACT_SUBVECTOR: SplitVecRes_EXTRACT_SUBVECTOR(N, Lo, Hi); break;
case ISD::INSERT_SUBVECTOR: SplitVecRes_INSERT_SUBVECTOR(N, Lo, Hi); break;
case ISD::FP_ROUND_INREG: SplitVecRes_InregOp(N, Lo, Hi); break;
case ISD::FPOWI: SplitVecRes_FPOWI(N, Lo, Hi); break;
case ISD::INSERT_VECTOR_ELT: SplitVecRes_INSERT_VECTOR_ELT(N, Lo, Hi); break;
@ -765,6 +766,43 @@ void DAGTypeLegalizer::SplitVecRes_EXTRACT_SUBVECTOR(SDNode *N, SDValue &Lo,
TLI.getVectorIdxTy()));
}
void DAGTypeLegalizer::SplitVecRes_INSERT_SUBVECTOR(SDNode *N, SDValue &Lo,
SDValue &Hi) {
SDValue Vec = N->getOperand(0);
SDValue SubVec = N->getOperand(1);
SDValue Idx = N->getOperand(2);
SDLoc dl(N);
GetSplitVector(Vec, Lo, Hi);
// Spill the vector to the stack.
EVT VecVT = Vec.getValueType();
EVT SubVecVT = VecVT.getVectorElementType();
SDValue StackPtr = DAG.CreateStackTemporary(VecVT);
SDValue Store = DAG.getStore(DAG.getEntryNode(), dl, Vec, StackPtr,
MachinePointerInfo(), false, false, 0);
// Store the new subvector into the specified index.
SDValue SubVecPtr = GetVectorElementPointer(StackPtr, SubVecVT, Idx);
Type *VecType = VecVT.getTypeForEVT(*DAG.getContext());
unsigned Alignment = TLI.getDataLayout()->getPrefTypeAlignment(VecType);
Store = DAG.getStore(Store, dl, SubVec, SubVecPtr, MachinePointerInfo(),
false, false, 0);
// Load the Lo part from the stack slot.
Lo = DAG.getLoad(Lo.getValueType(), dl, Store, StackPtr, MachinePointerInfo(),
false, false, false, 0);
// Increment the pointer to the other part.
unsigned IncrementSize = Lo.getValueType().getSizeInBits() / 8;
StackPtr =
DAG.getNode(ISD::ADD, dl, StackPtr.getValueType(), StackPtr,
DAG.getConstant(IncrementSize, StackPtr.getValueType()));
// Load the Hi part from the stack slot.
Hi = DAG.getLoad(Hi.getValueType(), dl, Store, StackPtr, MachinePointerInfo(),
false, false, false, MinAlign(Alignment, IncrementSize));
}
void DAGTypeLegalizer::SplitVecRes_FPOWI(SDNode *N, SDValue &Lo,
SDValue &Hi) {
SDLoc dl(N);

33
llvm/test/CodeGen/X86/vec_split.ll
View File

@ -40,3 +40,36 @@ define <32 x i16> @split32(<32 x i16> %a, <32 x i16> %b, <32 x i8> %__mask) {
%2 = select <32 x i1> %1, <32 x i16> %a, <32 x i16> %b
ret <32 x i16> %2
}
; PR19492
define i128 @split128(<2 x i128> %a, <2 x i128> %b) {
; SSE4-LABEL: split128:
; SSE4: addq
; SSE4: adcq
; SSE4: addq
; SSE4: adcq
; SSE4: addq
; SSE4: adcq
; SSE4: ret
; AVX1-LABEL: split128:
; AVX1: addq
; AVX1: adcq
; AVX1: addq
; AVX1: adcq
; AVX1: addq
; AVX1: adcq
; AVX1: ret
; AVX2-LABEL: split128:
; AVX2: addq
; AVX2: adcq
; AVX2: addq
; AVX2: adcq
; AVX2: addq
; AVX2: adcq
; AVX2: ret
%add = add nsw <2 x i128> %a, %b
%rdx.shuf = shufflevector <2 x i128> %add, <2 x i128> undef, <2 x i32> <i32 undef, i32 0>
%bin.rdx = add <2 x i128> %add, %rdx.shuf
%e = extractelement <2 x i128> %bin.rdx, i32 1
ret i128 %e
}