Return the preferred shuffle strategy when expanding a reduction.
Declared in <llvm/Analysis/TargetTransformInfoImpl.h>
virtual
TTI::ReductionShuffle
getPreferredExpandedReductionShuffle(IntrinsicInst const* II) const;The shuffle pattern used to expand the given reduction intrinsic.
| Name | Description |
|---|---|
| II | Intrinsic instruction being rewritten or combined. |