From: James Tomaschke <james@orcasystems.com>
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Subject: Re: [9fans] threads vs forks
Date: Tue, 3 Mar 2009 20:44:43 -0800 [thread overview]
Message-ID: <49AE073B.3070501@orcasystems.com> (raw)
In-Reply-To: <086f4496e85bfab0a28a5c19dad17554@quanstro.net>
erik quanstrom wrote:
>> I think the reason why you didn't see parallelism come out earlier in
>> the PC market was because they needed to create new mechanisms for I/O.
>> AMD did this with Hypertransport, and I've seen 32-core (8-socket)
>> systems with this. Now Intel has their own I/O rethink out there.
>
> i think what you're saying is equivalent to saying
> (in terms i understand) that memory bandwidth was
> so bad that a second processor couldn't do much work.
Yes bandwidth and latency.
>
> but i haven't found this to be the case. even the
> highly constrained pentium 4 gets some milage out of
> hyperthreading for the tests i've run.
>
> the intel 5000-series still use a fsb. and they seem to
> scale well from 1 to 4 cores.
Many of the circuit simulators I use fall flat on their face after 4
cores, say. However I blame this on their algorithm not hardware.
I wasn't making an AMD vs Intel comment, just that AMD had created HTX
along with their K8 platform to address scalability concerns with I/O.
> are there benchmarks that show otherwise similar
> hypertransport systems trouncing intel in multithreaded
> performance? i don't recall seeing anything more than
> a moderate (15-20%) advantage.
I don't have a 16-core Intel system to compare with, but:
http://en.wikipedia.org/wiki/List_of_device_bandwidths#Computer_buses
I think the reason why Intel developed their Common Systems Interconnect
(now called QuickPath Interconnect) was to address it's shortcomings.
Both AMD and Intel are looking at I/O because it is and will be a
limiting factor when scaling to higher core counts.
>
> - erik
>
>
next prev parent reply other threads:[~2009-03-04 4:44 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-03 11:52 hugo rivera
2009-03-03 15:19 ` David Leimbach
2009-03-03 15:32 ` Uriel
2009-03-03 16:15 ` hugo rivera
2009-03-03 15:33 ` hugo rivera
2009-03-03 18:11 ` Roman V. Shaposhnik
2009-03-03 18:38 ` Bakul Shah
2009-03-06 18:47 ` Roman V Shaposhnik
2009-03-06 20:38 ` David Leimbach
2009-03-07 8:00 ` Bakul Shah
2009-03-07 0:21 ` Bakul Shah
2009-03-07 2:20 ` Brian L. Stuart
2009-03-03 23:08 ` J.R. Mauro
2009-03-03 23:15 ` Uriel
2009-03-03 23:23 ` J.R. Mauro
2009-03-03 23:54 ` Devon H. O'Dell
2009-03-04 0:33 ` J.R. Mauro
2009-03-04 0:54 ` erik quanstrom
2009-03-04 1:54 ` J.R. Mauro
2009-03-04 3:18 ` James Tomaschke
2009-03-04 3:30 ` erik quanstrom
2009-03-04 4:44 ` James Tomaschke [this message]
2009-03-04 5:05 ` J.R. Mauro
2009-03-04 5:50 ` erik quanstrom
2009-03-04 6:08 ` andrey mirtchovski
2009-03-04 16:52 ` J.R. Mauro
2009-03-04 17:14 ` ron minnich
2009-03-04 17:27 ` William Josephson
2009-03-04 18:15 ` erik quanstrom
2009-03-05 3:32 ` J.R. Mauro
2009-03-05 3:39 ` erik quanstrom
2009-03-05 3:55 ` William K. Josephson
2009-03-05 4:00 ` erik quanstrom
2009-03-05 4:16 ` William K. Josephson
2009-03-07 3:01 ` William Josephson
2009-03-07 3:31 ` erik quanstrom
2009-03-07 6:00 ` William Josephson
2009-03-07 13:58 ` erik quanstrom
2009-03-07 14:37 ` William Josephson
2009-03-07 15:05 ` erik quanstrom
2009-03-07 15:28 ` William K. Josephson
2009-03-07 5:00 ` lucio
2009-03-07 5:08 ` William Josephson
2009-03-07 5:19 ` erik quanstrom
2009-03-07 5:45 ` [9fans] Flash William K. Josephson
2009-03-07 14:42 ` erik quanstrom
2009-03-07 14:56 ` William Josephson
2009-03-07 15:39 ` Russ Cox
2009-03-07 16:34 ` erik quanstrom
2009-03-07 5:24 ` [9fans] threads vs forks lucio
2009-03-04 5:19 ` David Leimbach
2009-03-04 2:47 ` John Barham
2009-03-04 5:24 ` blstuart
2009-03-04 5:37 ` erik quanstrom
2009-03-04 16:29 ` Roman V Shaposhnik
2009-03-04 16:56 ` john
2009-03-06 9:39 ` maht
2009-03-04 5:07 ` David Leimbach
2009-03-04 5:35 ` John Barham
2009-03-03 16:00 ` ron minnich
2009-03-03 16:28 ` hugo rivera
2009-03-03 17:31 ` ron minnich
2009-03-03 16:47 ` John Barham
2009-03-04 9:37 ` Vincent Schut
2009-03-04 9:58 ` hugo rivera
2009-03-04 10:30 ` Vincent Schut
2009-03-04 10:45 ` hugo rivera
2009-03-04 11:15 ` Vincent Schut
2009-03-04 11:33 ` hugo rivera
2009-03-04 13:23 ` Uriel
2009-03-04 14:57 ` ron minnich
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=49AE073B.3070501@orcasystems.com \
--to=james@orcasystems.com \
--cc=9fans@9fans.net \
/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).