From: Paul Lalonde <plalonde@telus.net>
To: Jack Johnson <knapjack@gmail.com>,
Fans of the OS Plan 9 from Bell Labs <9fans@cse.psu.edu>
Subject: Re: [9fans] Plan9 on the Cell...
Date: Tue, 24 May 2005 16:30:11 -0700 [thread overview]
Message-ID: <DF8CC085-F799-4807-8358-6F0E1A487A44@telus.net> (raw)
In-Reply-To: <6e35c06205052416184b8a53c8@mail.gmail.com>
I can't comment too deeply without treading into NDA land, but from
public sources it's safe to say that the difficulty in programming
the SPEs isn't so much in code generation (although automatic
parallelization will continue to be a grail) but in data movement.
The SPEs have only explicit "cache" in the sense that the local
memory is very fast, but doesn't share an address space with the PU.
Instead, you DMA chunks back and forth as needed and rely on DMA
bandwidth (and sufficiency of channels) to fill relatively large
chunks of "cache" explicitly instead of relying on automated cache-
line granularity. That makes you think of the machine architecture
pretty much any time you design an algorithm to run on the SPE -
which I guess puts it in line with other parallelization methods :-
( Wherefrom, of course, comes the interesting systems work :-)
Paul
On 24-May-05, at 4:18 PM, Jack Johnson wrote:
> On 5/24/05, Paul Lalonde <plalonde@telus.net> wrote:
>
>> The SPEs, of course, are the interesting part from the systems point
>> of view.
>>
>
> I'm a layman, so speaking completely out my posterior here, but I read
> a paper somewhere that lead me to believe that some of the vectorizing
> techniques used on the Crays could be applied well to the cell
> processors. True?
>
> Not that I recall seeing a Cray port on sources.... ;)
>
> -Jack
>
next prev parent reply other threads:[~2005-05-24 23:30 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-05-24 19:05 Paul Lalonde
2005-05-24 19:26 ` Eric Van Hensbergen
2005-05-24 23:04 ` Paul Lalonde
2005-05-24 23:18 ` Jack Johnson
2005-05-24 23:27 ` Eric Van Hensbergen
2005-05-24 23:30 ` Paul Lalonde [this message]
2005-05-25 3:11 ` Bruce Ellis
2005-05-27 16:53 ` Paul Lalonde
2005-05-28 6:29 ` andrey mirtchovski
2005-05-28 14:51 ` Eric Van Hensbergen
2005-05-28 17:45 ` Ronald G. Minnich
2005-05-28 17:56 ` Ronald G. Minnich
2005-05-28 18:11 ` Jack Johnson
2005-05-28 18:31 ` jmk
2005-05-28 18:34 ` Paul Lalonde
2005-05-29 6:35 ` Noah Evans
2005-05-29 9:26 ` Charles Forsyth
2005-05-30 20:43 ` Eric Van Hensbergen
2005-06-03 11:55 ` Noah Evans
2005-06-03 12:57 ` Eric Van Hensbergen
2005-06-03 15:46 ` Dave Eckhardt
2005-06-03 16:43 ` Ronald G. Minnich
2005-06-03 17:33 ` Brantley Coile
2005-06-03 21:22 ` David Leimbach
2005-05-29 9:26 ` Charles Forsyth
2005-05-24 23:26 ` Eric Van Hensbergen
2005-05-25 9:10 ` C H Forsyth
2005-05-25 15:07 ` Ronald G. Minnich
[not found] ` <a4e6962a050525081244ed619d@mail.gmail.com>
2005-05-25 15:13 ` Fwd: " Eric Van Hensbergen
2005-05-25 15:30 ` C H Forsyth
2005-06-21 16:46 ` Eric Van Hensbergen
2005-06-10 14:04 ` Eric Van Hensbergen
2005-06-10 16:44 ` Paul Lalonde
2005-06-10 18:43 ` Bruce Ellis
2005-06-11 3:17 ` Ronald G. Minnich
2005-06-11 3:38 ` Tim Newsham
2005-06-11 3:45 ` Ronald G. Minnich
2005-06-11 19:36 ` C H Forsyth
2005-06-12 21:36 ` arisawa
2005-06-12 22:55 ` Eric Van Hensbergen
2005-06-12 23:54 ` George Gensure
2005-06-13 2:39 ` Ronald G. Minnich
2005-06-13 5:17 ` Martin C. Atkins
2005-05-28 19:21 jmk
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=DF8CC085-F799-4807-8358-6F0E1A487A44@telus.net \
--to=plalonde@telus.net \
--cc=9fans@cse.psu.edu \
--cc=knapjack@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 NNTP newsgroup(s).