[llvm] [LoadStoreVectorizer] Fill gaps in load/store chains to enable vectorization (PR #159388)

[Nikita Popov via llvm-commits]

nikic wrote:

> > The problem here is that even if this may be valid from a hardware perspective, it is not necessarily valid in LLVM IR.
> 
> Would widening into a masked load that masks the unused elements (so that they are not loaded) be legal in LLVM IR? That'd still allow the backend to issue a fully covered load if the backend knows that this is ok for the particular platform.

Yeah, a masked load is definitely fine.

https://github.com/llvm/llvm-project/pull/159388