From: Jeff Law <jeffreyalaw@gmail.com>
To: Andrew Stubbs <ams@codesourcery.com>,
"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH] vect: Vectorize via libfuncs
Date: Tue, 13 Jun 2023 10:28:14 -0600 [thread overview]
Message-ID: <d2d38588-50fd-c578-0575-6a67532b9569@gmail.com> (raw)
In-Reply-To: <0e5fddf8-8605-a0d6-eede-1a8fcf12535c@codesourcery.com>
On 6/13/23 09:55, Andrew Stubbs wrote:
> Subject:
> [PATCH] vect: Vectorize via libfuncs
> From:
> Andrew Stubbs <ams@codesourcery.com>
> Date:
> 6/13/23, 09:55
>
> To:
> "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
>
>
> This patch allows vectorization when operators are available as
> libfuncs, rather that only as insns.
>
> This will be useful for amdgcn where we plan to vectorize loops that
> contain integer division or modulus, but don't want to generate inline
> instructions for the division algorithm every time.
>
> The change should have not affect architectures that do not define
> vector-mode libfuncs.
>
> OK for mainline?
>
> Andrew
>
> 230613-vect-allow-libfuncs.patch
>
> vect: vectorize via libfuncs
>
> This patch allows vectorization when the libfuncs are defined.
>
> gcc/ChangeLog:
>
> * tree-vect-generic.cc: Include optabs-libfuncs.h.
> (get_compute_type): Check optab_libfunc.
> * tree-vect-stmts.cc: Include optabs-libfuncs.h.
> (vectorizable_operation): Check optab_libfunc.
>
> diff --git a/gcc/tree-vect-generic.cc b/gcc/tree-vect-generic.cc
> index b7d4a919c55..4d784a70c0d 100644
> --- a/gcc/tree-vect-generic.cc
> +++ b/gcc/tree-vect-generic.cc
> @@ -44,6 +44,7 @@ along with GCC; see the file COPYING3. If not see
> #include "gimple-fold.h"
> #include "gimple-match.h"
> #include "recog.h" /* FIXME: for insn_data */
> +#include "optabs-libfuncs.h"
>
>
> /* Build a ternary operation and gimplify it. Emit code before GSI.
> @@ -1714,7 +1715,8 @@ get_compute_type (enum tree_code code, optab op, tree type)
> machine_mode compute_mode = TYPE_MODE (compute_type);
> if (VECTOR_MODE_P (compute_mode))
> {
> - if (op && optab_handler (op, compute_mode) != CODE_FOR_nothing)
> + if (op && (optab_handler (op, compute_mode) != CODE_FOR_nothing
> + || optab_libfunc (op, compute_mode)))
Formatting nit. Bring the && down and align it under OP. That'll
require re-indenting the optab_libfunc call as well.
OK with that nit.
jeff
prev parent reply other threads:[~2023-06-13 16:28 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-13 15:55 Andrew Stubbs
2023-06-13 16:28 ` Jeff Law [this message]
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=d2d38588-50fd-c578-0575-6a67532b9569@gmail.com \
--to=jeffreyalaw@gmail.com \
--cc=ams@codesourcery.com \
--cc=gcc-patches@gcc.gnu.org \
/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).