diff options
Diffstat (limited to 'lib/Target/X86/X86ISelLowering.cpp')
| -rw-r--r-- | lib/Target/X86/X86ISelLowering.cpp | 13 |
1 files changed, 11 insertions, 2 deletions
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp index f4f37a894620..e1a6d22f0616 100644 --- a/lib/Target/X86/X86ISelLowering.cpp +++ b/lib/Target/X86/X86ISelLowering.cpp @@ -13884,7 +13884,6 @@ static SDValue lowerVectorShuffleAsLanePermuteAndPermute( int NumEltsPerLane = NumElts / NumLanes; SmallVector<int, 4> SrcLaneMask(NumLanes, SM_SentinelUndef); - SmallVector<int, 16> LaneMask(NumElts, SM_SentinelUndef); SmallVector<int, 16> PermMask(NumElts, SM_SentinelUndef); for (int i = 0; i != NumElts; ++i) { @@ -13899,10 +13898,20 @@ static SDValue lowerVectorShuffleAsLanePermuteAndPermute( return SDValue(); SrcLaneMask[DstLane] = SrcLane; - LaneMask[i] = (SrcLane * NumEltsPerLane) + (i % NumEltsPerLane); PermMask[i] = (DstLane * NumEltsPerLane) + (M % NumEltsPerLane); } + // Make sure we set all elements of the lane mask, to avoid undef propagation. + SmallVector<int, 16> LaneMask(NumElts, SM_SentinelUndef); + for (int DstLane = 0; DstLane != NumLanes; ++DstLane) { + int SrcLane = SrcLaneMask[DstLane]; + if (0 <= SrcLane) + for (int j = 0; j != NumEltsPerLane; ++j) { + LaneMask[(DstLane * NumEltsPerLane) + j] = + (SrcLane * NumEltsPerLane) + j; + } + } + // If we're only shuffling a single lowest lane and the rest are identity // then don't bother. // TODO - isShuffleMaskInputInPlace could be extended to something like this. |