caml-list - the Caml user's mailing list
 help / color / mirror / Atom feed
From: "David MENTRE" <dmentre@linux-france.org>
To: "Christophe Raffalli" <Christophe.Raffalli@univ-savoie.fr>
Cc: caml-list@yquem.inria.fr
Subject: Re: [Caml-list] minithread (was OCaml on Sony PS3)
Date: Tue, 4 Dec 2007 15:25:36 +0100	[thread overview]
Message-ID: <3d13dcfc0712040625u2eb4e1f6la3b97063c99fb722@mail.gmail.com> (raw)
In-Reply-To: <4754643A.6020503@univ-savoie.fr>

Hello,

2007/12/3, Christophe Raffalli <Christophe.Raffalli@univ-savoie.fr>:
> If you launch one minithread per SPU or CORE with a minor heap of the
> correct size and you fine tune you application to produce not too much
> cache misses, then, I think this simple model could be usefull ????

I might have not completely understood your proposal but it seems to
me that those mini-threads do not solve the issue. In the Cell
architecture, the SPU are *independent* processors. They access the
main memory through DMA like operations and do not have cache. In
other words, for you mini-threads to work on the SPU, you need to fit
the mini-thread s' data, code and environment (e.g. GC) in 256 KB of
memory. As Xavier said, it seems quite difficult if not impossible.

Yours,
david


  reply	other threads:[~2007-12-04 14:25 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-09-06  6:20 More registers in modern day CPUs Tom
2007-09-06  7:17 ` [Caml-list] " skaller
2007-09-06  9:07 ` Richard Jones
2007-09-06 14:55 ` Chris King
2007-09-06 15:17   ` Brian Hurt
2007-09-06 15:54     ` Harrison, John R
2007-09-06 17:10       ` David MENTRE
2007-09-06 18:27         ` Harrison, John R
2007-09-06 18:28         ` Christophe Raffalli
2007-09-06 18:48           ` Brian Hurt
2007-09-06 18:48           ` Pal-Kristian Engstad
2007-11-20 15:32             ` [Caml-list] OCalm on Sony PS3 (was Re: More registers in modern day CPUs) Mike Hogan
2007-11-21 17:20               ` Richard Jones
2007-11-21 19:05                 ` [Caml-list] OCaml " Mike Hogan
2007-11-23  6:44                 ` Mike Hogan
2007-12-02 10:14               ` [Caml-list] OCalm " Xavier Leroy
2007-12-02 16:22                 ` Mike Hogan
2007-12-02 22:19                   ` Konrad Meyer
2007-12-03  0:09                     ` [Caml-list] OCaml " Mike Hogan
2007-12-03 20:16                       ` minithread (was OCaml on Sony PS3) Christophe Raffalli
2007-12-04 14:25                         ` David MENTRE [this message]
2007-12-04 14:37                         ` [Caml-list] " Basile STARYNKEVITCH
2007-12-04 16:25                           ` Mattias Engdegård
2007-12-04 17:33                         ` Gerd Stolpmann
2007-12-04 18:00                         ` Mike Hogan
2007-12-04  2:29                 ` [Caml-list] OCalm on Sony PS3 (was Re: More registers in modern day CPUs) Gordon Henriksen
2007-09-06 20:48   ` [Caml-list] More registers in modern day CPUs Richard Jones
     [not found]   ` <20070906204524.GB10798@furbychan.cocan.org>
2007-09-06 20:59     ` Chris King

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=3d13dcfc0712040625u2eb4e1f6la3b97063c99fb722@mail.gmail.com \
    --to=dmentre@linux-france.org \
    --cc=Christophe.Raffalli@univ-savoie.fr \
    --cc=caml-list@yquem.inria.fr \
    /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 NNTP newsgroup(s).