From: Andrew Pinski <pinskia@gmail.com>
To: Marcus Shawcroft <marcus.shawcroft@gmail.com>
Cc: Philipp Tomsich <philipp.tomsich@theobroma-systems.com>,
"Gopalasubramanian, Ganesh" <Ganesh.Gopalasubramanian@amd.com>,
"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH, aarch64] Add prefetch support
Date: Tue, 13 Jan 2015 14:32:00 -0000 [thread overview]
Message-ID: <CA+=Sn1k-qucM2fZLqQCtTh62i0jsKcvD8=3foCso0mE=J4s4tQ@mail.gmail.com> (raw)
In-Reply-To: <CAFqB+PzJsnWyDLrDgp_s1U8FO_B4BZL7BZFVuhFOPuiL10fz3A@mail.gmail.com>
On Tue, Jan 13, 2015 at 6:13 AM, Marcus Shawcroft
<marcus.shawcroft@gmail.com> wrote:
> On 11 January 2015 at 02:37, Andrew Pinski <pinskia@gmail.com> wrote:
>> On Tue, Nov 11, 2014 at 6:47 AM, Marcus Shawcroft
>> <marcus.shawcroft@gmail.com> wrote:
>>> On 30 October 2014 08:54, Gopalasubramanian, Ganesh
>>> <Ganesh.Gopalasubramanian@amd.com> wrote:
>>>
>>>> 2014-10-30 Ganesh Gopalasubramanian <Ganesh.Gopalasubramanian@amd.com>
>>>
>>> Check the whitespace in your ChangeLog line.
>>>
>>>> * config/arm/types.md (define_attr "type"): Add prefetch.
>>>
>>> The existing schedulers use 'load1'. We can of course split that into
>>> two introducing "prefetch" and update all of the existing schedulers
>>> to reflect the change. However I suggest we do that as a separate
>>> activity when someone actually needs the distinction, note this change
>>> will require updating the schedulers for both ARM and AArch64 backends
>>> not just those relevant to AArch64. For this prefetch patch I suggest
>>> we go with the existing "load1".
>>
>> I will need this change for ThunderX schedule. The Pref instruction
>> is single issued while load1 can be dual issued.
>
> Hi
>
> https://gcc.gnu.org/ml/gcc-patches/2015-01/msg00802.html
>
> Philipp when you deal with Ramana's request above to split
> load1->load1/prefetch in the existing schedulers I suggest you also
> split it in aarch64/thunderx.md in order to retain existing behaviour.
> Andrew can then follow up add the "right" behaviour when he is ready.
> Andrew OK ?
Yes that sounds ok to me. I was going to submit an update to
thunderx.md file this week anyways.
Thanks,
Andrew
>
> Cheers
> /Marcus
next prev parent reply other threads:[~2015-01-13 14:18 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-30 9:00 Gopalasubramanian, Ganesh
2014-11-11 14:48 ` Marcus Shawcroft
2014-11-14 20:45 ` Gopalasubramanian, Ganesh
2014-11-17 13:31 ` Richard Henderson
2014-12-01 6:13 ` Gopalasubramanian, Ganesh
2014-12-01 7:49 ` Gopalasubramanian, Ganesh
2014-12-02 0:09 ` Richard Henderson
2014-12-03 13:49 ` Marcus Shawcroft
2015-01-11 8:53 ` Andrew Pinski
2015-01-13 14:31 ` Marcus Shawcroft
2015-01-13 14:32 ` Andrew Pinski [this message]
2015-01-13 14:58 ` Dr. Philipp Tomsich
-- strict thread matches above, loose matches on Subject: below --
2014-07-04 10:57 Gopalasubramanian, Ganesh
2014-07-05 20:42 ` Gopalasubramanian, Ganesh
2014-07-09 8:54 ` Richard Earnshaw
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='CA+=Sn1k-qucM2fZLqQCtTh62i0jsKcvD8=3foCso0mE=J4s4tQ@mail.gmail.com' \
--to=pinskia@gmail.com \
--cc=Ganesh.Gopalasubramanian@amd.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=marcus.shawcroft@gmail.com \
--cc=philipp.tomsich@theobroma-systems.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).