This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Vectorizer Pragmas
- From: Jakub Jelinek <jakub at redhat dot com>
- To: Renato Golin <renato dot golin at linaro dot org>
- Cc: gcc <gcc at gcc dot gnu dot org>
- Date: Sat, 15 Feb 2014 20:26:27 +0100
- Subject: Re: Vectorizer Pragmas
- Authentication-results: sourceware.org; auth=none
- References: <CAMSE1kcaRgyF_HawBSDPvkt2=jP+dXDQJowHOMQ7XmHZCCWLhQ at mail dot gmail dot com>
- Reply-to: Jakub Jelinek <jakub at redhat dot com>
On Sat, Feb 15, 2014 at 06:56:42PM +0000, Renato Golin wrote:
> 1. Local pragma (#pragma vectorize), which is losing badly on the
> argument that it's yet-another pragma to do mostly the same thing many
> others do.
>
> 2. Using OMP SIMD pragmas (#pragma simd, #pragma omp simd) which is
> already standardised (OMP 4.0 I think), but that doesn't cover all the
> semantics we may want in the future, plus it's segregated and may
> confuse the users.
GCC supports #pragma GCC ivdep/#pragma simd/#pragma omp simd, the last one
can be used without rest of OpenMP by using -fopenmp-simd switch.
I don't see why we would need more ways to do the same thing.
Jakub