diff options
Diffstat (limited to 'llvm/lib/Target/X86/X86ISelLowering.cpp')
| -rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.cpp | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index c7a42b15cb0..2cb8fce20fe 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -15879,6 +15879,18 @@ static SDValue lowerV4F64Shuffle(const SDLoc &DL, ArrayRef<int> Mask, Zeroable, Subtarget, DAG)) return Op; + // If we have lane crossing shuffles AND they don't all come from the lower + // lane elements, lower to SHUFPD(VPERM2F128(V1, V2), VPERM2F128(V1, V2)). + // TODO: Handle BUILD_VECTOR sources which getVectorShuffle currently + // canonicalize to a blend of splat which isn't necessary for this combine. + if (is128BitLaneCrossingShuffleMask(MVT::v4f64, Mask) && + !all_of(Mask, [](int M) { return M < 2 || (4 <= M && M < 6); }) && + (V1.getOpcode() != ISD::BUILD_VECTOR) && + (V2.getOpcode() != ISD::BUILD_VECTOR)) + if (SDValue Op = lowerShuffleAsLanePermuteAndSHUFP(DL, MVT::v4f64, V1, V2, + Mask, DAG)) + return Op; + // If we have one input in place, then we can permute the other input and // blend the result. if (isShuffleMaskInputInPlace(0, Mask) || isShuffleMaskInputInPlace(1, Mask)) |
