This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Scheduling an early complete loop unrolling pass?
- From: Dorit Nuzman <DORIT at il dot ibm dot com>
- To: Richard Guenther <rguenther at suse dot de>
- Cc: gcc at gcc dot gnu dot org, Jan Hubicka <hubicka at ucw dot cz>, tomby at atrey dot karlin dot mff dot cuni dot cz, "Linthicum, Tony" <tony dot linthicum at amd dot com>
- Date: Mon, 5 Feb 2007 21:13:10 +0200
- Subject: Re: Scheduling an early complete loop unrolling pass?
Richard Guenther <rguenther@suse.de> wrote on 05/02/2007 18:16:05:
> On Mon, 5 Feb 2007, Jan Hubicka wrote:
...
> > Did you run some benchmarks?
>
> Not yet - I'm looking at the C++ SPEC 2006 benchmarks at the moment
> and using vectorization there seems to do a lot of collateral damage
> (maybe not measurable though).
>
Interesting. In SPEC 2000 there is also a hot small loop in the only C++
benchmark (eon), which get vectorized, and as a result degrades
performance. We really should not vectorize such loops, and the solution
is:
1. FORNOW: use --param min-vect-loop-bound=2 (or some value greater than
0).
2. SOON: rely on the vectorizer to do the cost analysis and decide not to
vectorize such loops, using a cost model - this is in the works.
dorit
> Richard.
>
> --
> Richard Guenther <rguenther@suse.de>
> Novell / SUSE Labs