This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH] Fix PR40648 -- Fix misaligned store vectorizer patch
- From: Revital1 Eres <ERES at il dot ibm dot com>
- To: gcc-patches at gcc dot gnu dot org
- Date: Tue, 3 Nov 2009 15:33:20 +0200
- Subject: Re: [PATCH] Fix PR40648 -- Fix misaligned store vectorizer patch
- References: <OFB84C78B2.44F012B0-ONC225765C.0031B677-C225765C.0036F3A7@il.ibm.com>
> This patch changes the decision of the vectorizer when to peel for
> alignment.
> The misaligned store vectorizer patch
> (http://gcc.gnu.org/ml/gcc-patches/2009-06/msg00492.html) set the
> decision of when to peel such that peeling was only considered if there
> is an unsupported misaligned access. This change caused degradation on
> targets that support misaligned accesses as it seems peeling is preferred
> when the access is misaligned. The attached patch
> tries to fix that by retrieving part of the the original behavior -
peeling
> is considered if there is misaligned accesses. (misalign load or store as
> opposed to only stores in the former behavior).
My mistake -- peeling should be considered only for stores.
I am now testing a patch.
Sorry for the confusion,
Revital
The decision of when to
> peel/version etc. should be integrated in the cost model using target
> dependent queries and I intend to address this next.
>
> Bootstrapped with vectorization enabled on powerpc64 and regtested
> on x86_64.
>
> OK for mainline?
>
> Thanks,
> Revital
>
> (See attached file: patch_fix_misalign_2710.txt)(See attached file:
> changelog.txt)[attachment "patch_fix_misalign_2710.txt" deleted by
Revital1
> Eres/Haifa/IBM] [attachment "changelog.txt" deleted by Revital1
Eres/Haifa/IBM]