diff options
Diffstat (limited to 'llvm/lib/Target/X86/X86ISelLowering.cpp')
| -rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.cpp | 32 |
1 files changed, 14 insertions, 18 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index 5303d7a406a..dcc6ab2620d 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -7825,24 +7825,20 @@ X86TargetLowering::LowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG) const { } // Next, we iteratively mix elements, e.g. for v4f32: - // Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> - // : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> - // Step 2: unpcklps X, Y ==> <3, 2, 1, 0> - unsigned EltStride = NumElems >> 1; - while (EltStride != 0) { - for (unsigned i = 0; i < EltStride; ++i) { - // If Ops[i+EltStride] is undef and this is the first round of mixing, - // then it is safe to just drop this shuffle: V[i] is already in the - // right place, the one element (since it's the first round) being - // inserted as undef can be dropped. This isn't safe for successive - // rounds because they will permute elements within both vectors. - if (Ops[i+EltStride].isUndef() && - EltStride == NumElems/2) - continue; - - Ops[i] = getUnpackl(DAG, dl, VT, Ops[i], Ops[i + EltStride]); - } - EltStride >>= 1; + // Step 1: unpcklps 0, 1 ==> X: <?, ?, 1, 0> + // : unpcklps 2, 3 ==> Y: <?, ?, 3, 2> + // Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> + for (unsigned Scale = 1; Scale < NumElems; Scale *= 2) { + // Generate scaled UNPCKL shuffle mask. + SmallVector<int, 16> Mask; + for(unsigned i = 0; i != Scale; ++i) + Mask.push_back(i); + for (unsigned i = 0; i != Scale; ++i) + Mask.push_back(NumElems+i); + Mask.append(NumElems - Mask.size(), SM_SentinelUndef); + + for (unsigned i = 0, e = NumElems / (2 * Scale); i != e; ++i) + Ops[i] = DAG.getVectorShuffle(VT, dl, Ops[2*i], Ops[(2*i)+1], Mask); } return Ops[0]; } |
