[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[amker at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

amker at gcc dot gnu.org changed:

   What|Removed |Added

 Status|NEW |RESOLVED
 Resolution|--- |FIXED

--- Comment #12 from amker at gcc dot gnu.org ---
Should be fixed.

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[law at redhat dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

Jeffrey A. Law  changed:

   What|Removed |Added

   Priority|P3  |P4
 CC||law at redhat dot com

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[janus at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #11 from janus at gcc dot gnu.org ---
r242664 seems to fix the issue I reported in comment 3/4. Thanks!

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[amker at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #10 from amker at gcc dot gnu.org ---
Author: amker
Date: Mon Nov 21 14:58:19 2016
New Revision: 242664

URL: https://gcc.gnu.org/viewcvs?rev=242664=gcc=rev
Log:
gcc/testsuite
PR testsuite/78114
* gfortran.dg/vect/fast-math-mgrid-resid.f: Add additional
options.  Refine test by checking predictive commining PHI
nodes in vectorized loop wrto vector factor.

Modified:
trunk/gcc/testsuite/ChangeLog
trunk/gcc/testsuite/gfortran.dg/vect/fast-math-mgrid-resid.f

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[amker at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #9 from amker at gcc dot gnu.org ---
(In reply to r...@cebitec.uni-bielefeld.de from comment #8)
> > --- Comment #6 from amker at gcc dot gnu.org ---
> > But for tests:
> > FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times 
> > pcom
> > "Executing predictive commoning without unrolling" 1
> > FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times 
> > pcom
> > "Predictive commoning failed: no suitable chains" 0
> >
> > they happened before 20161011.  I tried revision at:
> > commit ab93a7014158ec67a0b34e2986742da8a55013f9
> > Author: sje 
> > Date:   Wed Oct 5 18:42:10 2016 +
> >
> > 2016-10-05  Steve Ellcey  
> >
> > * MAINTAINERS: Update email address after it got reverted.
> >
> >
> > git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@240801
> > 138bc75d-0d04-0410-961f-82ee72b054a4
> >
> > And it's not working either?
> 
> In my tests (Solaris on various x86 systems, both Intel and AMD), the
> failure started consistently between 20161011 (r240990) and 20161013
> (r241136).
> 
>   Rainer

This case tests if predictive commoning finds out shared memory access between
vectorized loop, but it has to check all possible predictive commoning
opportunities for all loops, i.e, including prologue and epilogue loops. 
Unfortunately, vectorizer peels the loop in different ways depending on cost,
and on different targets.
For example, for solaris x86 toolchain, prologue loop isn't peeled, that's why
the newly added test string failed.
For haswel, I think it has been failed for long time because there is no
predictive commonging opportunity with vf > 2.
IMHO, we should refine test only checking predictive commoning for vectorized
loop (which is the test means to do), and also skip test for vf!=2.
For the latter issue, we maybe able to change test code making it stands for
vf>2 cases too.

Thanks,
bin

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[ro at CeBiTec dot Uni-Bielefeld.DE]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #8 from ro at CeBiTec dot Uni-Bielefeld.DE  ---
> --- Comment #6 from amker at gcc dot gnu.org ---
> But for tests:
> FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times 
> pcom
> "Executing predictive commoning without unrolling" 1
> FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times 
> pcom
> "Predictive commoning failed: no suitable chains" 0
>
> they happened before 20161011.  I tried revision at:
> commit ab93a7014158ec67a0b34e2986742da8a55013f9
> Author: sje 
> Date:   Wed Oct 5 18:42:10 2016 +
>
> 2016-10-05  Steve Ellcey  
>
> * MAINTAINERS: Update email address after it got reverted.
>
>
> git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@240801
> 138bc75d-0d04-0410-961f-82ee72b054a4
>
> And it's not working either?

In my tests (Solaris on various x86 systems, both Intel and AMD), the
failure started consistently between 20161011 (r240990) and 20161013
(r241136).

Rainer

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[amker at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #7 from amker at gcc dot gnu.org ---
Here is the reason failing with haswell.
The loop is vectorized by vf=4, but iteration distance for all possible
predictive commoning chains are at most 2 (by iterations), so after vf=4
vectorization, there is no predictive commoning opportunities.

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[amker at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #6 from amker at gcc dot gnu.org ---
But for tests:
FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times pcom
"Executing predictive commoning without unrolling" 1
FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times pcom
"Predictive commoning failed: no suitable chains" 0

they happened before 20161011.  I tried revision at:
commit ab93a7014158ec67a0b34e2986742da8a55013f9
Author: sje 
Date:   Wed Oct 5 18:42:10 2016 +

2016-10-05  Steve Ellcey  

* MAINTAINERS: Update email address after it got reverted.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@240801
138bc75d-0d04-0410-961f-82ee72b054a4

And it's not working either?

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[amker at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #5 from amker at gcc dot gnu.org ---
It's because the loop is vectorized by vf=2 with -mavx2, while by vf=4 with
-march=haswell.  In that case the peeled prolog iterates more than 1 times,
resulting in test failure.

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[janus at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

--- Comment #4 from janus at gcc dot gnu.org ---
(In reply to janus from comment #3)
> At r241973, I see these failures on x86_64-linux-gnu:

... but only if I configure using --with-arch=haswell.

(the CPU on that machine is Intel(R) Core(TM) i5-4460  CPU @ 3.20GHz)

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[janus at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

janus at gcc dot gnu.org changed:

   What|Removed |Added

 CC||janus at gcc dot gnu.org

--- Comment #3 from janus at gcc dot gnu.org ---
At r241973, I see these failures on x86_64-linux-gnu:

FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times pcom
"Executing predictive commoning without unrolling" 1
FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times pcom
"Predictive commoning failed: no suitable chains" 0
FAIL: gfortran.dg/vect/fast-math-mgrid-resid.f   -O   scan-tree-dump-times pcom
"Loop iterates only 1 time, nothing to do" 1

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[amker at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

amker at gcc dot gnu.org changed:

   What|Removed |Added

   Assignee|unassigned at gcc dot gnu.org  |amker at gcc dot gnu.org

--- Comment #2 from amker at gcc dot gnu.org ---
I will investigate it.

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[dominiq at lps dot ens.fr]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

Dominique d'Humieres  changed:

   What|Removed |Added

 Status|UNCONFIRMED |NEW
   Last reconfirmed||2016-10-26
 Ever confirmed|0   |1

--- Comment #1 from Dominique d'Humieres  ---
Confirmed.

[Bug tree-optimization/78114] [7 regression] gfortran.dg/vect/fast-math-mgrid-resid.f FAILs

[ro at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78114

Rainer Orth  changed:

   What|Removed |Added

   Target Milestone|--- |7.0