This is the mail archive of the gcc@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: Does unrolling prevents doloop optimizations?

From: Zdenek Dvorak <rakdver at kam dot mff dot cuni dot cz>
To: Ayal Zaks <ZAKS at il dot ibm dot com>
Cc: gcc at gcc dot gnu dot org, Mircea Namolaru <namolaru at il dot ibm dot com>, Vladimir Yanovsky <volodyan at gmail dot com>
Date: Sat, 30 Jun 2007 19:36:12 +0200
Subject: Re: Does unrolling prevents doloop optimizations?
References: <20070630075232.GA7748@kam.mff.cuni.cz> <OF090979DB.55DDA057-ONC225730A.00363DA3-C225730A.00369A28@il.ibm.com>

Hello,

> > > It doesn't seem that the number of iterations analysis from loop-iv.c
> deals
> > > with EQ closing branches.
> >
> > loop-iv works just fine for EQ closing branches.
> >
> 
> Thanks for the clarification (I didn't see EQ in iv_number_of_iterations's
> switch (cond)).

that is because we canonicalize the condition before that to a NE
condition.

Zdenek

Follow-Ups:
- Re: Does unrolling prevents doloop optimizations?
  - From: Ayal Zaks

References:
- Re: Does unrolling prevents doloop optimizations?
  - From: Zdenek Dvorak
- Re: Does unrolling prevents doloop optimizations?
  - From: Ayal Zaks

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]