[llvm] [LoopVectorize] Perform loop versioning for some early exit loops (PR #120603)

[Florian Hahn via llvm-commits]

https://github.com/fhahn commented:

Are there any guarantees related to alignment of pointers and dereferenceability of loads on the LLVM IR level? I had brief look in LangRef but couldn't find anything. 

Could the assumption cause problems with HW/software extensions, .e.g. something like AArch64 MTE or a software layer that checks out-of-bounds accesses? Not super familiar with the details of MTE, but I think it tracks sizes of allocations on smaller granularity than page sizes and traps on out-of-bound accesses. 

https://github.com/llvm/llvm-project/pull/120603