Fwd: 10% runtime regression in rnflow Polyhedron benchmark

2012-09-26 Thread Sergey Ostanevich
-- Forwarded message -- From: Sergey Ostanevich Date: Wed, Sep 26, 2012 at 4:55 PM Subject: Re: 10% runtime regression in rnflow Polyhedron benchmark To: Dominique Dhumieres On Mon, Sep 17, 2012 at 1:18 PM, Dominique Dhumieres wrote: > Hi Uros, > >> Recent patch i

Re: 10% runtime regression in rnflow Polyhedron benchmark

2012-09-17 Thread Dominique Dhumieres
Hi Uros, > Recent patch introduced 10% runtime regression on x86_64 targets in > rnflow Polyhedron benchmark [1]. Did somebody alread bisected to the > offending patch? I see it since some time. It is on my TODO list to open a new PR. You can suppress the slowdown with -fno-tree-loop-if-convert.

10% runtime regression in rnflow Polyhedron benchmark

2012-09-17 Thread Uros Bizjak
Hello! Recent patch introduced 10% runtime regression on x86_64 targets in rnflow Polyhedron benchmark [1]. Did somebody alread bisected to the offending patch? [1] http://gcc.opensuse.org/c++bench/polyhedron/polyhedron-summary.txt-2-0.html Uros.