On Fri, Dec 14, 2012 at 12:10:43AM +, Lux, Jim (337C) wrote:
> What's interesting about this is system is that it is a good illustration
> that there's a lot more expense and hassle than selecting the motherboard.
>
> While the RPI might only be $35, you also have to buy a SD card ($10-12)
>
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 12/12/12 22:45, Hearns, John wrote:
> http://www.theregister.co.uk/2012/12/12/linux_no_longer_runs_on_386_cpus/
The pull request from Ingo is instructive:
https://lkml.org/lkml/2012/12/11/131
A lot of cleanup is possible (including dropping a bu
Hi Jim,
I think the whole idea about that Pi Cluster was not to build a HPC machine
but more to demonstrate it can be done and also have students a tinker with
it.
The Pi are quite small, so you can do that in a class, without worring you get
deaf or the AC will not cope with the heat ;-)
It
What's interesting about this is system is that it is a good illustration that
there's a lot more expense and hassle than selecting the motherboard.
While the RPI might only be $35, you also have to buy a SD card ($10-12) power
supplies, cables, boxes or mounting hardware, not to mention a netwo
Hi Eric,
already been done in Southampton University:
http://www.southampton.ac.uk/mediacentre/features/raspberry_pi_supercomputer.shtml
;-)
Note: that is not the cluster called Iridis (also located there) :D
Jörg
On Donnerstag 13 Dezember 2012 Lee Eric wrote:
> Hi,
>
> I'm wondering if it'
On a bang for the buck, horsepower wise, it's usually better to go single
processor than spread the load across many smaller processors, unless your
application can make use of parallelism (so while you get fewer MIPS total for
a given amount of cash, your problem completes faster, and that's wo
Yeah did you already check which big capital S processor the
raspberry Pi has?
Single core ARM and low clocked.
If you cluster ARMs, why not get for a few dollar more a quadcore
1.7Ghz ARM A9.
For example:
http://www.hardkernel.com/renewal_2011/products/prdt_info.php?
g_code=G135341370451
On 12/13/2012 10:18 AM, Lee Eric wrote:
> Hi,
>
> I'm wondering if it's possible to create a small HPC by using Raspberry
> Pi computers. It's only a draft idea comes to my mind. So any issues w/
> this idea?
We actually had a prolonged discussion about this a month or two back
Eric (check the be
Hi,
I'm wondering if it's possible to create a small HPC by using Raspberry Pi
computers. It's only a draft idea comes to my mind. So any issues w/ this
idea?
Thanks.
Eric
___
Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing
To
http://www.theregister.co.uk/2012/12/12/linux_no_longer_runs_on_386_cpus/
John Hearns | CFD Hardware Specialist | McLaren Racing Limited
McLaren Technology Centre, Chertsey Road, Woking, Surrey GU21 4YH, UK
T: +44 (0) 1483 262000
D: +44 (0) 1483 262352
F: +44 (0) 1483 261928
E: john.hea...@mc
In HPC never as long as there is competition in HPC.
Big fat thick manycores will dominate of course.
Otherwise you'll eat 10x power especially for the interconnects which
is the biggest problem to solve.
Just do the math.
Price of 1 Tesla/Xeon Phi is on average $3k.
For $3600 you've got 1.3
Good article:
http://www.zdnet.com/linux-3-7-arrives-arm-developers-rejoice-708638/
When do we think 64 bit ARM will come in to general use in HPC?
Also TCP Fast Open looks interesting https://lwn.net/Articles/508865/
John Hearns | CFD Hardware Specialist | McLaren Racing Limited
McLaren T
http://ascr-discovery.science.doe.gov/exascale/exa_fault_print.html
ASCR DISCOVERY – Exascale Science
At exascale, being oblivious to a fault keeps apps running
Posted December 12, 2012
Computer scientist Maya Gokhale is optimistic about exascale computing’s
fast, bright future. But to achieve
Hi all,
I got a cluster with Supermicro X8DTT-H motherboards which have the Intel
Corporation 82574L Gigabit Network Connection, running Debian Linux (Squeeze)
kernel 2.6.32-5-amd64 on it.
The only time I had problems with the network card was when it stopped working
altogether. Upgrading the
Hi,
I had an issue with 82574L before, and the Intel guys had to buy the same
hardware for their lab in order to find and fix the issue. It was a new
SuperMicro motherboard:
http://comments.gmane.org/gmane.linux.drivers.e1000.devel/6734
Are you using the latest driver from Intel? I see you alre
(designed as a drop-in replacement for L2 cache in low-power SoCs).
http://www.toshiba.co.jp/about/press/2012_12/pr1001.htm
Toshiba's New STT-MRAM Memory Element Promises
World's Best Power Consumption and to Outperform SRAM
Cuts power consumption of mobile processor by two-thirds
10 Dec, 201
16 matches
Mail list logo
