This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH] RS6000: Vectorize 32 bit int multiplication
- From: Geoffrey Keating <geoffk at geoffk dot org>
- To: Devang Patel <dpatel at apple dot com>
- Cc: gcc-patches at gcc dot gnu dot org
- Date: 17 Apr 2005 20:53:37 -0700
- Subject: Re: [PATCH] RS6000: Vectorize 32 bit int multiplication
- References: <087F9479-7F79-4DDF-8A13-4F52EBFDA2C5@apple.com>
Devang Patel <dpatel@apple.com> writes:
> Adding this new pattern allows vectorizer to vectorize 32 bit int
> multiplications.
> Bootstrapped and tested on powerpc-darwin.
>
> 2005-04-15 Devang Patel <dpatel@apple.com>
>
> * config/rs6000/atlivec.md (mulv4si3): New pattern.
>
> * gcc.dg/vect/vect-11.c: Require effective target
> vect_int_mult.
> * gcc.dg/vect/vect-11a.c: New.
> * gcc.dg/vect/vect-none.c: Update.
> * lib/target-supports.exp
> (check_effective_target_vect_int_mult): New.
>
> OK for mainline ?
OK.