[PATCH] expose ILP for associative operations in the DAG

[James Molloy]

I personally think it'd be best done as late as possible, that way we can
crank the heuristics all the way up to 11 and still hopefully not regress
code.

On Thu, 14 May 2015 at 22:01 Sanjay Patel <spatel at rotateright.com> wrote:

> On Thu, May 14, 2015 at 2:24 PM, James Molloy <james at jamesmolloy.co.uk>
> wrote:
>
> > It sounds like the best time to do this if at all possible is in
> MachineInst form,
>
> > where we have MachineTraceMetrics and accurate register pressure
> information.
>
> >
>
> > Is there a reason why you're not doing it there? I know it's more
> awkward, but
>
> > it really seems we need accurate register pressure if we're not going to
> make it
>
> > cripplingly conservative.
>
>
> I only have marginal reasons for trying this here rather than with
> MachineInsts: I really wanted to make this easy for any target to opt-in,
> nobody pushed me away from a DAG transform, and I've never attempted a
> machine-level transform. If the consensus is that it's better done later
> when we have more register knowledge, I'll certainly give it a try.
>
>
> http://reviews.llvm.org/D9780
>
> EMAIL PREFERENCES
>   http://reviews.llvm.org/settings/panel/emailpreferences/
>
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150514/a2233ae5/attachment.html>