This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH][RFC] Fix complex multiplication vectorization on x86_64
- From: Uros Bizjak <ubizjak at gmail dot com>
- To: Richard Guenther <rguenther at suse dot de>, GCC Patches <gcc-patches at gcc dot gnu dot org>
- Date: Wed, 30 Jul 2008 23:43:00 +0200
- Subject: Re: [PATCH][RFC] Fix complex multiplication vectorization on x86_64
Hello!
The problem starts with the testsuite which either can be tuned to
have vect_extract_even_odd or not, but not, as x86_64 requires,
only turn on support for vect_extract_even_odd for SImode or larger
element sizes. Any suggestions how to deal with this?
We can perhaps split check_effective_target_vect_extract_even_odd
procedure to check_effective_target_vect_extract_even_odd_{narrow,wide}
and use equivalent vect_extract_* functions in target selectors.
IMO, we can then simply use vect_extract_even_odd_wide in functions that
fail due to extra vectorisations and vect_extract_even_odd_narrow with
(depending on operands) logical and of vect_extract_even_odd_wide in
other vect-strided-* functions.
Uros.