[llvm-branch-commits] [llvm] [SystemZ] Backport memops handling (avoid unaligned VL/VSTs). (PR #196359)

[Cullen Rhodes via llvm-branch-commits]

c-rhodes wrote:

> Yes, this is indeed an optimization improvement, by avoiding certain instances of unaligned vector load/store instructions that can sometimes have bad performance.

Can you clarify how bad? The backporting criteria can be a bit ambiguous but it does seem to permit critical performance improvements: https://llvm.org/docs/HowToReleaseLLVM.html#release-patch-rules

>    Bug fix releases Patches should be limited to bug fixes or very safe and critical performance improvements. Patches must maintain both API and ABI compatibility with the X.1.0 release.

https://github.com/llvm/llvm-project/pull/196359