From: "Michael V. Zolotukhin" <michael.v.zolotukhin@gmail.com>
To: Thomas Schwinge <thomas@codesourcery.com>
Cc: Ilya Verbin <iverbin@gmail.com>,
Richard Biener <richard.guenther@gmail.com>,
Uday Khedker <uday@cse.iitb.ac.in>,
hubicka@ucw.cz, rth@redhat.com, kirill.yukhin@gmail.com,
gcc@gcc.gnu.org, Jakub Jelinek <jakub@redhat.com>
Subject: Re: Questions about LTO infrastructure and pragma omp target
Date: Tue, 03 Sep 2013 18:30:00 -0000 [thread overview]
Message-ID: <20130903182956.GH43295@msticlxl57.ims.intel.com> (raw)
In-Reply-To: <87ioyhhkk9.fsf@kepler.schwinge.homeip.net>
Hi Thomas,
> The idea, as we discussed it at the GNU Tools Cauldron's Acceleration
> BoF, is that the host program (for at least some acceleration devices)
> will be responsible for loading the acceleration device's code to the
> device, using some support library that is specific to each acceleration
> device
Unfortunately, I missed the Cauldron, though I'm familiar with the
general idea and now I'm trying to clarify details.
> and for that it is useful to have the the code readily accessible
> in the host program, and thus link it in as "data".
Oh, if we just link the target binary as a data section into the host
binary, then I see no problems in that, it seems absolutely feasible
with the existing infrastructure. I just thought (seemingly it was
incorrect) that we're speaking about linking of target code with the
host code.
> > And the question about multi-target support here still remains open.
>
> Many questions are still open -- but I'm glad there is activity on this
> topic, and I'm sure we'll be able to converge with the designs we have or
> are currently developing.
Thanks, I'm sure in that too:)
Best regards, Michael
> Thomas
next prev parent reply other threads:[~2013-09-03 18:30 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-15 13:44 Ilya Verbin
2013-08-15 15:00 ` Jakub Jelinek
2013-08-15 19:19 ` Richard Biener
2013-08-23 13:15 ` Ilya Verbin
2013-08-23 14:38 ` Jakub Jelinek
2013-08-28 9:59 ` Basile Starynkevitch
2013-08-23 15:05 ` Richard Biener
2013-08-23 15:06 ` Jakub Jelinek
2013-08-25 22:36 ` Ilya Verbin
2013-08-26 7:32 ` Jakub Jelinek
2013-09-03 14:00 ` Michael V. Zolotukhin
2013-09-03 14:19 ` Jakub Jelinek
2013-09-03 15:18 ` Michael V. Zolotukhin
2013-09-03 17:39 ` Thomas Schwinge
2013-09-03 18:30 ` Michael V. Zolotukhin [this message]
2013-09-03 18:54 ` Jakub Jelinek
2013-09-03 19:09 ` Michael V. Zolotukhin
2013-09-16 17:14 ` Ilya Verbin
2013-09-17 8:12 ` Richard Biener
2013-09-17 11:31 ` Ilya Verbin
2013-09-17 11:54 ` Jakub Jelinek
2013-09-17 11:56 ` Richard Biener
2013-09-17 12:15 ` Jakub Jelinek
2013-09-19 10:45 ` Ilya Verbin
2013-09-19 10:50 ` Jakub Jelinek
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=20130903182956.GH43295@msticlxl57.ims.intel.com \
--to=michael.v.zolotukhin@gmail.com \
--cc=gcc@gcc.gnu.org \
--cc=hubicka@ucw.cz \
--cc=iverbin@gmail.com \
--cc=jakub@redhat.com \
--cc=kirill.yukhin@gmail.com \
--cc=richard.guenther@gmail.com \
--cc=rth@redhat.com \
--cc=thomas@codesourcery.com \
--cc=uday@cse.iitb.ac.in \
/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).