[llvm-dev] [RFC] New pass: LoopExitValues

Steve King via llvm-dev llvm-dev at lists.llvm.org
Tue Sep 15 10:32:55 PDT 2015


On Mon, Sep 14, 2015 at 11:57 AM, Philip Reames
<listmail at philipreames.com> wrote:
> However, your transformation would have the effect of
> increasing the live range of the variable in the loop and introducing an
> extra scheduling dependency.  I'm not entirely sure how that would work out
> in practice if the use outside the loop is a ways from the loop exit.  Have
> you given this any thought?  I suspect that the profitability heuristic
> would need tuning to get right (or at least not wrong for key cases.)
>

Assuming we should not interfere with the (hopefully) temporary
redundancy created by IndVarSimplify, then why would the live range
created here be of special concern vs. the live range of all the other
variables in a given function?


More information about the llvm-dev mailing list