[PATCH] D25350: [X86] Enable interleaved memory accesses by default

[Michael Kuperstein via llvm-commits]

mkuper added a comment.

In https://reviews.llvm.org/D25350#569327, @RKSimon wrote:

> We're seeing some minor but consistent regressions (< 1%) on some internal tests.


That's really interesting - that means it's firing. :-)

Can you provide a reproducer? I can see basically three possible sources of regressions:

1. We're still doing very bad lowering for some shuffle sequences.
2. The cost model is too optimistic regarding the cost of the sequence, even with optimal lowering.
3. "Normal" vectorizer flakiness - the cost model is doing the right thing about the interleave sequence, but we shouldn't be vectorizing regardless. So without interleaving enabled we were just getting lucky.

I really hope what you're seeing is a case of (1).


https://reviews.llvm.org/D25350