[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-07-10 Thread amker at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 amker at gcc dot gnu.org changed: What|Removed |Added Status|NEW |RESOLVED

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-29 Thread amker at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 --- Comment #8 from amker at gcc dot gnu.org --- Author: amker Date: Thu Jun 29 10:41:28 2017 New Revision: 249778 URL: https://gcc.gnu.org/viewcvs?rev=249778=gcc=rev Log: PR tree-optimization/81196 * tree-ssa-loop-niter.c

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-27 Thread glisse at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 --- Comment #7 from Marc Glisse --- (In reply to amker from comment #6) > But below is necessary, right? > > /* { dg-require-effective-target vect_perm_short } */ Yes. Cool, I didn't remember we had exactly the right test :-) Or you could

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-27 Thread amker at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 --- Comment #6 from amker at gcc dot gnu.org --- (In reply to Marc Glisse from comment #5) > (In reply to amker from comment #4) > > Hmm, the function can only be vectorized with "-march=skylake"? > > Er, it also vectorizes without any -march on

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-26 Thread glisse at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 --- Comment #5 from Marc Glisse --- (In reply to amker from comment #4) > Hmm, the function can only be vectorized with "-march=skylake"? Er, it also vectorizes without any -march on x86_64 (with shorter vectors).

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-26 Thread amker at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 --- Comment #4 from amker at gcc dot gnu.org --- Hmm, the function can only be vectorized with "-march=skylake"? So what requirement is needed to add a test case for this? Thanks.

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-26 Thread amker at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 --- Comment #3 from amker at gcc dot gnu.org --- (In reply to Richard Biener from comment #1) > Probably some more elaborate handling in number_of_iterations_cond is > required: > > /* We can handle the case when neither of the sides of the

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-26 Thread amker at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 --- Comment #2 from amker at gcc dot gnu.org --- (In reply to Richard Biener from comment #1) > Probably some more elaborate handling in number_of_iterations_cond is > required: > > /* We can handle the case when neither of the sides of the

[Bug tree-optimization/81196] Number of iterations found for p!=q but not for p

2017-06-26 Thread rguenth at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81196 Richard Biener changed: What|Removed |Added Status|UNCONFIRMED |NEW Last reconfirmed|