llvm-project

de1c2f24 - [LoopVectorizer][AArch64] Move getMinTripCountTailFoldingThreshold later. (#132170)

[LoopVectorizer][AArch64] Move getMinTripCountTailFoldingThreshold later. (#132170) This moves the checks of MinTripCountTailFoldingThreshold later, during the calculation of whether to tail fold. This allows it to check beforehand whether tail predication is required, either for scalable or fixed-width vectors. This option is only specified for AArch64, where it returns the minimum of 5. This patch aims to allow the vectorization of TC=4 loops, preventing them from performing slower when SVE is present.