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: -ftree-vectorize can't vectorize plus?

From: "Daniel Berlin" <dberlin at dberlin dot org>
To: "Dorit Nuzman" <DORIT at il dot ibm dot com>
Cc: "Rask Ingemann Lambertsen" <rask at sygehus dot dk>, gcc at gcc dot gnu dot org
Date: Mon, 11 Sep 2006 11:27:16 -0400
Subject: Re: -ftree-vectorize can't vectorize plus?
References: <20060910201654.GM29852@sygehus.dk> <OFE0AA6654.92D62363-ONC22571E6.00388DAB-C22571E6.0038C656@il.ibm.com>

On 9/11/06, Dorit Nuzman <DORIT@il.ibm.com> wrote:

>    A silly little testcase which the vectorizer doesn't vectorize:
>
....
> autovecttest.c:11: note: not vectorized: relevant stmt not
> supported: D.1861_9 = (signed char) D.1860_8

Can these type casts (from uchar to schar and back) be cleaned away by some
pass before vectorization,


Uh, what do you mean "cleaned away"?
You can't just legally ignore them, they are changing the overflow behavior.

Follow-Ups:
- Re: -ftree-vectorize can't vectorize plus?
  - From: Dorit Nuzman

References:
- -ftree-vectorize can't vectorize plus?
  - From: Rask Ingemann Lambertsen
- Re: -ftree-vectorize can't vectorize plus?
  - From: Dorit Nuzman

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