[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 Martin Liška changed: What|Removed |Added Status|NEW |RESOLVED Resolution|---

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 --- Comment #9 from Marc Glisse --- I think we can close it, you fixed the main issue (thanks!). Were you leaving it open so someone might investigate alternate versions of the nonzero predictor?

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 Martin Liška changed: What|Removed |Added Assignee|marxin at gcc dot gnu.org |unassigned at gcc dot gnu.org

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 --- Comment #7 from Martin Liška --- Author: marxin Date: Wed Jun 21 12:51:46 2017 New Revision: 249450 URL: https://gcc.gnu.org/viewcvs?rev=249450=gcc=rev Log: Make early return predictor more precise. 2017-06-21 Martin Liska

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 --- Comment #6 from Martin Liška --- (In reply to Martin Liška from comment #5) > Author: marxin > Date: Tue May 2 15:00:47 2017 > New Revision: 247501 > > URL: https://gcc.gnu.org/viewcvs?rev=247501=gcc=rev > Log: > Remove LTO_STREAMER_DEBUG

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 --- Comment #5 from Martin Liška --- Author: marxin Date: Tue May 2 15:00:47 2017 New Revision: 247501 URL: https://gcc.gnu.org/viewcvs?rev=247501=gcc=rev Log: Remove LTO_STREAMER_DEBUG (PR lto/79489). 2017-05-02 Martin Liska

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 --- Comment #4 from Martin Liška --- Created attachment 40746 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=40746=edit Patch for nonzero on non-boolean types With the patch, I get following numbers for CPU2006 SPEC: HEURISTICS

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 --- Comment #3 from Jan Hubicka --- > 1) we wrongly match early return heuristics. It's a known issue as mentioned > in > predict.def: > > /* Branch causing function to terminate is probably not taken. >FIXME: early return currently

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 --- Comment #2 from Marc Glisse --- (In reply to Martin Liška from comment #1) > 1) we wrongly match early return heuristics. Ah, right, that seems like an important heuristic, but it is very eager, it applies even if both branches lead to

[Bug tree-optimization/79489] Strange static branch prediction for n != 0

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79489 Martin Liška changed: What|Removed |Added Status|UNCONFIRMED |NEW Last reconfirmed|