From: Szabolcs Nagy <szabolcs.nagy@arm.com>
To: Janne Blomqvist <blomqvist.janne@gmail.com>
Cc: nd@arm.com, GCC Development <gcc@gcc.gnu.org>,
Fortran List <fortran@gcc.gnu.org>,
Steve Ellcey <sellcey@cavium.com>
Subject: Re: libmvec in gcc to have vector math in fortran
Date: Tue, 10 Apr 2018 11:35:00 -0000 [thread overview]
Message-ID: <80c395e1-9de5-1d9c-35b6-1ccfdfa6a9e5@arm.com> (raw)
In-Reply-To: <CAO9iq9FvH9Mbmec+tDO5_31vaKiu3p=WGhAXuFFUq8EJEeiQ-g@mail.gmail.com>
On 10/04/18 11:14, Janne Blomqvist wrote:
> As I mentioned previously in that thread you linked to, the fortran frontend never generates a direct call to libm sin(), or for that matter
> ZGVbN2v_sin(). Instead it generates a "call" to __builtin_sin(). And similarly for other libm functions that have gcc builtins. The middle-end
> optimizers are then free to do whatever optimizations they like on that __builtin_sin call, such as constant folding, and at least as far as the
> fortran frontend is concerned, vectorizing if -mveclibabi= or such is in effect.
the generated builtin call is not the issue (same happens in c),
the knowledge about libc declarations is.
the middle-end has no idea what functions can be vectorized,
only the libc knows it and declares this in c headers.
this is the problem i'm trying to solve.
next prev parent reply other threads:[~2018-04-10 10:22 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-10 10:14 Szabolcs Nagy
2018-04-10 10:22 ` Janne Blomqvist
2018-04-10 11:35 ` Szabolcs Nagy [this message]
2018-04-10 12:55 ` Jakub Jelinek
2018-04-10 13:26 ` Richard Biener
2018-04-10 13:42 ` Jakub Jelinek
2018-04-10 13:27 ` Richard Biener
2018-04-10 13:35 ` Richard Biener
2018-04-18 8:41 ` Szabolcs Nagy
2018-04-18 8:57 ` Richard Biener
2018-06-14 22:41 ` Richard Biener
2018-06-15 8:39 ` Florian Weimer
2018-06-15 8:40 ` Szabolcs Nagy
2018-06-15 9:08 ` Richard Biener
2018-06-15 8:41 ` Richard Biener
2018-06-15 9:33 ` Florian Weimer
2018-06-15 11:39 ` Richard Biener
2018-06-15 20:59 ` Thomas Koenig
2018-06-15 22:41 ` Joseph Myers
2018-06-18 11:10 ` Richard Biener
2018-06-18 16:02 ` Joseph Myers
2018-06-18 16:22 ` Richard Biener
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=80c395e1-9de5-1d9c-35b6-1ccfdfa6a9e5@arm.com \
--to=szabolcs.nagy@arm.com \
--cc=blomqvist.janne@gmail.com \
--cc=fortran@gcc.gnu.org \
--cc=gcc@gcc.gnu.org \
--cc=nd@arm.com \
--cc=sellcey@cavium.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).