[PATCH] D42235: [AArch64] Avoid unnecessary vector byte-swapping in big-endian

[Matthias Braun via Phabricator via llvm-commits]

MatzeB added reviewers: evandro, t.p.northover.
MatzeB added a comment.

This apparently defeats the logic in `splitStores()` (aka the infamous FeatureMisalignedSlow128Bit) because that code had an exception for v2i64 vector types but wants to split all other vector types. An internal test case of ours:

  define void @test_split_16B(<4 x float> %val, <4 x float>* %addr) {
    store <4 x float> %val, <4 x float>* %addr, align 8
    ret void
  }

would no longer show the store getting split.

Independently of this I disabled `FeatureMisalignedSlow128` for apple a few hours later so my interest is limited now :)

But I think Exynos is still using the "feature", so they may want to look into this.


Repository:
  rL LLVM

https://reviews.llvm.org/D42235