From: Uros Bizjak <ubizjak@gmail.com>
To: Vladimir Yakovlev <vbyakovl23@gmail.com>
Cc: gcc-patches@gcc.gnu.org
Subject: Re: [RFC, x86] Changes for AVX and AVX2 processors
Date: Sun, 30 Dec 2012 13:21:00 -0000 [thread overview]
Message-ID: <CAFULd4Y3L0b8d+LPWgKuRtAx=W59gS6BANhE21e3PmEM8ZOWSQ@mail.gmail.com> (raw)
In-Reply-To: <CAK1BsWo-iWDNcukpNqKsp7OrpE+k9riZV0=9Z3FxuGK+4DW24w@mail.gmail.com>
On Sat, Dec 29, 2012 at 5:57 PM, Vladimir Yakovlev <vbyakovl23@gmail.com> wrote:
> I did changes. Please take a look.
>
> 2012/12/29, Uros Bizjak <ubizjak@gmail.com>:
>> On Sat, Dec 29, 2012 at 6:26 AM, Vladimir Yakovlev <vbyakovl23@gmail.com>
>> wrote:
>>
>>> processor_alias_table contains the same processor type for all
>>> "corei7", "corei7-avx", "core-avx-i" and "core-avx2". At least, it has
>>> consequence on checking x86_avx256_split_unaligned_load &
>>> ix86_tune_mask: for all these processors it results the same. Moreover
>>> we cannot turn new features on for AVX/AVX2 using
>>> initial_ix86_tune_features.
>>
>> corei7, corei7-avx and core-avx-i are all based on sandybridge (=
>> PROCESSOR_COREI7) architecture. The only problematic entry is
>> core-avx2, which should be based on new architecture. I propose
>> PROCESSOR_HASWELL, in the same way as we have PROCESSOR_NOCONA.
@@ -2467,6 +2470,7 @@
"nocona",
"core2",
"corei7",
+ "coreavx2",
"atom",
"geode",
"k6",
This string should match processor_alias_table name, so "core-avx2".
@@ -28709,6 +28716,10 @@
arg_str = "corei7";
priority = P_PROC_SSE4_2;
break;
+ case PROCESSOR_HASWELL:
+ arg_str = "core_avx2";
+ priority = P_PROC_SSE4_2;
+ break;
case PROCESSOR_ATOM:
arg_str = "atom";
priority = P_PROC_SSSE3;
This is part of a processor dispatcher functionality. To support this
functionality, some more changes are needed, so it is IMO best to
leave this part out for now. I would also like the author of processor
dispatcher to review changes in this area.
On a related note, it looks to me that corei7 should declare
P_PROC_AVX here (this change should be part of another patch).
Other than that , the patch looks OK, but please repost final version
with a correct ChangeLog.
Uros.
next prev parent reply other threads:[~2012-12-30 13:21 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-28 13:36 Uros Bizjak
2012-12-29 5:26 ` Vladimir Yakovlev
2012-12-29 10:07 ` Uros Bizjak
[not found] ` <CAK1BsWpUdUg+ivi7pFdbUr8R45YjhbBCNhmN=98sMmW99dy-tg@mail.gmail.com>
2012-12-29 16:57 ` Vladimir Yakovlev
2012-12-30 13:21 ` Uros Bizjak [this message]
2012-12-30 16:05 ` Vladimir Yakovlev
2012-12-30 18:05 ` Uros Bizjak
2013-01-10 11:12 ` Vladimir Yakovlev
2013-01-10 11:28 ` Uros Bizjak
2013-01-10 11:31 ` Jakub Jelinek
2013-01-11 11:25 ` Vladimir Yakovlev
2013-01-11 11:27 ` Jakub Jelinek
2013-01-11 12:15 ` Vladimir Yakovlev
2013-01-11 12:21 ` Uros Bizjak
2013-01-11 12:38 ` Vladimir Yakovlev
2013-01-15 10:08 ` Kirill Yukhin
2012-12-30 11:59 ` Uros Bizjak
-- strict thread matches above, loose matches on Subject: below --
2012-12-27 17:07 Vladimir Yakovlev
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='CAFULd4Y3L0b8d+LPWgKuRtAx=W59gS6BANhE21e3PmEM8ZOWSQ@mail.gmail.com' \
--to=ubizjak@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=vbyakovl23@gmail.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).