>
>
>
>When you are trying to educate people about cluster computing, the most
>important thing is conveying the difficulties (both performance and
>infrastructure related) working at scale -- not simply showing off that
>the thing is "faster."
Precisely this..
The Arduino might be a bit too sma
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Folks, please can we give this HFT speculation a rest please.
- --
Christopher SamuelSenior Systems Administrator
VLSCI - Victorian Life Sciences Computation Initiative
Email: sam...@unimelb.edu.au Phone: +61 (0)3 903 55545
http://www.vls
for the record, setting up ldap is trivial. actually, configuring
a whole cluster with stateless nodes is pretty straight checklist...
> I'd really like to know what challenges people are facing in this area.
> Specific pain points.
funding. vendor lockin/licensing.
lack of design standard for
> I've done 4 nodes a bunch of times, and that seems a bit too trivial.
> Heck, there's a lot of people who have 4 computers in their office,
> forming a defacto heterogenous cluster.
I have a four node HP DL380 G8 cluster that im using to benchmark storage
devices at the moment. I'm using a com
I agree with Ellis 100%. Ellis, if you're still a student, you've got a
bright future ahead of you.
Prentice
On 09/12/2012 12:02 PM, Ellis H. Wilson III wrote:
> On 09/12/2012 11:42 AM, Vincent Diepeveen wrote:
>> On Sep 12, 2012, at 5:24 PM, Lux, Jim (337C) wrote:
>>> So, the question is... w
On 09/12/2012 12:42 PM, Vincent Diepeveen wrote:
>
> On Sep 12, 2012, at 6:02 PM, Ellis H. Wilson III wrote:
>>
>> In short, you've shared this negative, "if it's not faster then forget
>> about it" sentiment before Vincent, and it's neither constructive
>> to the
>> conversation nor to be reasonab
>
> When you are trying to educate people about cluster computing, the
> most
> important thing is conveying the difficulties (both performance and
> infrastructure related) working at scale -- not simply showing off
> that
> the thing is "faster."
HPC and beowulf are *only* about performance
On Sep 12, 2012, at 6:02 PM, Ellis H. Wilson III wrote:
>
> In short, you've shared this negative, "if it's not faster then forget
> about it" sentiment before Vincent, and it's neither constructive
> to the
> conversation nor to be reasonably expected from Professors trying
> to run
> a solid
On 09/12/2012 11:42 AM, Vincent Diepeveen wrote:
> On Sep 12, 2012, at 5:24 PM, Lux, Jim (337C) wrote:
>> So, the question is... what's the smallest number of nodes in a
>> "demo/toy" cluster that gives you the "big iron" feeling. I'm
>> going to guess that 4 is too few.
I'd say even 16 would g
On 09/12/2012 11:34 AM, Hearns, John wrote:
> And I *still* think that a cluster of arduinos would be fun, albeit slow. Is
> there a (limited) MPI implementation? There's some interesting I/O devices
> for arduino that might be intriguing in this context.. the 8x8 multicolor LED
> displays fo
On Sep 12, 2012, at 5:24 PM, Lux, Jim (337C) wrote:
> Harkening back to earlier "make a beowulf of X".. one can hold a
> Furby in one's hand.
>
> But anyway, this is kind of cool. It also shows some of the
> practical problems of scalability: cable management, for one. Look
> at that pictu
And I *still* think that a cluster of arduinos would be fun, albeit slow. Is
there a (limited) MPI implementation? There's some interesting I/O devices for
arduino that might be intriguing in this context.. the 8x8 multicolor LED
displays for instance.
That's interesting
I know where th
Harkening back to earlier "make a beowulf of X".. one can hold a Furby in one's
hand.
But anyway, this is kind of cool. It also shows some of the practical problems
of scalability: cable management, for one. Look at that picture of the 64 wall
warts plugged into a bunch of plug strips.
Here'
You still haven't got a clue is it?
Oh as a reminder, would you be prepared to do next exercise?
Please calculate for me for the past few years, including of course
the crash of 2008
and the flashcrash, how many datapoints each machine needs to proces
to simulate,
and also how much storage yo
I was just making the point that a finance houses modeling/simulation
computers are not dependent on low latency connections to the exchange.
Only their trading systems which will not be more than a few machines.
A UK bank/trading house could locate their simulation systems in Iceland
and just put
http://www.southampton.ac.uk/mediacentre/features/raspberry_pi_supercomputer.shtml
Southampton engineers a Raspberry Pi Supercomputer
Computational Engineers at the University of Southampton have built a
supercomputer from 64 Raspberry Pi computers and Lego.
The team, led by Professor Simon Cox
It seems that you first wrote:
>High Frequency Trading is actually a tiny amount of the world wide
>computer power. Far far less than HPC. This kit tends to be located
>very close to the exchange anyway. and is generally uninteresting in
t>erms of green IT.
>I recently met with one of the tec
17 matches
Mail list logo
