[PATCH] D30309: CodeGen: BlockPlacement: Precompute layout for chains of triangles.
Xinliang David Li via llvm-commits
llvm-commits at lists.llvm.org
Thu Mar 2 15:55:13 PST 2017
On Thu, Mar 2, 2017 at 3:43 PM, Kyle Butt via Phabricator <
reviews at reviews.llvm.org> wrote:
> iteratee added inline comments.
>
>
> ================
> Comment at: lib/CodeGen/MachineBlockPlacement.cpp:152
> + "triangle tail duplication heuristic to kick in. 0 to
> disable."),
> + cl::init(2),
> + cl::Hidden);
> ----------------
> davidxl wrote:
> > Should the default be 3?
> If I had found anywhere where it was likely to cause problems in my
> benchmarking, I would bump it to 3, but I haven't.
>
My advice is to start with a slightly more conservative setting initially.
David
>
>
> ================
> Comment at: lib/CodeGen/MachineBlockPlacement.cpp:1061
> +/// longer chains)
> +/// 2) The chains are statically correlated. Branch probabilities have a
> very
> +/// U-shaped distribution. If the branches in a chain are all from the
> same
> ----------------
> davidxl wrote:
> > 2) This is not entirely true -- it depends on the length the chain
> (e.g, when branch proabiity to Pdom blocks are low). Perhaps remove 2).
> No, It's accurate. If you know that the frequencies are correlated, but
> not whether they're high or low, than this is profitable. Even if the
> individual branch decisions are independent.
>
> If by the length of the chain, you mean that the only correlations that
> matter are neighbors, then that is correct and I can add a note about that.
>
>
> https://reviews.llvm.org/D30309
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170302/31ec054f/attachment.html>
More information about the llvm-commits
mailing list