[PATCH] D62498: [x86] split 256-bit store of concatenated vectors

[Sanjay Patel via Phabricator via llvm-commits]

spatel added a comment.

In D62498#1518518 <https://reviews.llvm.org/D62498#1518518>, @lebedev.ri wrote:

> Can we ever happen to get volatile/atomic stores here?


Good question - I didn't think about those. We have an ISD::ATOMIC_STORE node type, so that means we can rule out atomics? The existing split transform intended for SandyBridge doesn't appear to check for volatile either, so we might have an existing bug. I'll see if there's any test coverage for these cases.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D62498/new/

https://reviews.llvm.org/D62498