[llvm] VPlan: simplify mul with zero (PR #127521)

[Ramkumar Ramachandra via llvm-commits]

artagnon wrote:

> > See surrounding code. Yes, LV introduces plenty of trivial constructs like mul with 1, not(not(V)) etc. when building the VPlan.
> 
> Is there a test for this? The test affected in this PR has a mul of 0 in the input

Thanks, just noticed that the mul with 1 seems to be introduced by versioning strides, but I'm struggling to introduce a mul with 0: perhaps the DerivedIV matchers handle the only trivial mul with 0s introduced.

https://github.com/llvm/llvm-project/pull/127521