[PATCH] D63060: [InstCombine] usub.sat(a, b) + b => umax(a, b) (PR42178)

[Nikita Popov via Phabricator via llvm-commits]

nikic added a comment.

As pointed out on the GH issue, alive is correct here and it's just the printing of the counterexample that was wrong.

The transform is not correct, because it increases the number of uses of A. If A is undef, it may evaluate to a different value for each use :(

Not sure what to do here now...


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D63060/new/

https://reviews.llvm.org/D63060