On Thu, Jan 18, 2007 at 09:31:07PM -0800, Jim Lux wrote:
> In an interesting coincidence of references, my wife and daughter's
> horse is named "The dread pirate Roberts", the reference to which I
> have found is almost as dating as a former competitor of mine
... you just hang out with the wro
Mark Hahn wrote:
Yes, it is. And more so if this cluster/LAN can also utilize som type
of "MOSIX" system. This will substatially increase the throughput of
"standard serial" processes.
hmm, curious argument - why do you think MOSIX will be more efficient
than a "normal" cluster when confront
HP's CCS announcement from early 11/06:
http://www.hp.com/hpinfo/newsroom/press/2006/061106a.html?jumpid=reg_R1002_USEN
michael
At 04:41 PM 1/18/2007, Robert G. Brown wrote:
On Thu, 18 Jan 2007, Jim Lux wrote:
And likewise, WinXP on the desktop. A company with 20,000 WinXP
desktops cannot t
At 04:41 PM 1/18/2007, Robert G. Brown wrote:
On Thu, 18 Jan 2007, Jim Lux wrote:
And likewise, WinXP on the desktop. A company with 20,000 WinXP
desktops cannot tolerate BSODs and mystery hangs on a significant
fraction of those desktops at any frequency. When your call center
operators ar
At 04:41 PM 1/18/2007, Robert G. Brown wrote:
On Thu, 18 Jan 2007, Jim Lux wrote:
And likewise, WinXP on the desktop. A company with 20,000 WinXP
desktops cannot tolerate BSODs and mystery hangs on a significant
fraction of those desktops at any frequency. When your call center
operators ar
On Thu, 18 Jan 2007, Jim Lux wrote:
And likewise, WinXP on the desktop. A company with 20,000 WinXP desktops
cannot tolerate BSODs and mystery hangs on a significant fraction of those
desktops at any frequency. When your call center operators are being timed
to the second, the sysadmin folks
At 09:10 AM 1/18/2007, Robert G. Brown wrote:
... while plotting their nefarious plan to perpetuate their World
Domination.
Is there a higher calling than that?
Geeks do not live in the Universe to which I was referring -- the one
where corporate shirts are doing CBA and risk assessments...
David Mathog <[EMAIL PROTECTED]> wrote:
> > Did you go here:
> >
> > http://www.tyanpsc.com/
>
> No here:
>
>http://www.tyan.com/products/html/clusterservers.html
>
> Looks like Tyan has a few more links to put into their main website.
Remember that the PSC on the Tyan website is th
> And got it. The title is:
>
>"The Case of the Missing Supercomputing Performance"
I wondered if you were talking about that paper but it's from lanl not sandia,
it should be essential reading for everyone working with large clusters.
Ashley,
__
At 07:42 AM 1/18/2007, Robert G. Brown wrote:
On Thu, 18 Jan 2007, Richard Walsh wrote:
Ashley Pittman wrote:
On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote
Yes, it is. And more so if this cluster/LAN can also utilize som type
of "MOSIX" system. This will substatially increase
> Did you go here:
>
> http://www.tyanpsc.com/
No here:
http://www.tyan.com/products/html/clusterservers.html
Looks like Tyan has a few more links to put into their main website.
Regards,
David Mathog
[EMAIL PROTECTED]
Manager, Sequence Analysis Facility, Biology Division, Caltech
___
Håkon Bugge wrote:
You wrote:
There is a very good paper showing the effects of skew at scale by
Kerberyson, et al from Sandia.
Googling on Kerberyson gave zero hits. Since I am working on a
solution for the problem; would be nice to have that paper. You have a
reference (or pdf)?
Hak
>> The PSC will eventually hold up
>> to 40 cores and plug into a wall outlet.
>
> That's going to be quite a challenge with 40 Xeon cores. Even if
> they can beat the maximum powerconsumption down to 50W per
> core that's still not going to work on a 20A wall outlet unless
> there's no other elec
> The PSC will eventually hold up
> to 40 cores and plug into a wall outlet.
That's going to be quite a challenge with 40 Xeon cores. Even if
they can beat the maximum powerconsumption down to 50W per
core that's still not going to work on a 20A wall outlet unless
there's no other electrical loa
At 06:53 AM 1/18/2007, Eric Shook wrote:
Ashley Pittman wrote:
On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote:
Eric Shook wrote:
I talked to our SGI rep about this yesterday and he told me they
are not really targeting "hard-core" university research where
Linux/UNIX already ha
On Thu, 18 Jan 2007, Richard Walsh wrote:
Robert that universe includes me ... ;-) ... I was only qualifying
Ashley's statement about operating
system impact on HPC cluster efficiency/performance. The Windows/Linux
cluster market analysis
can continue ...
Sure, Richard, but you (
Yes, it is. And more so if this cluster/LAN can also utilize som type
of "MOSIX" system. This will substatially increase the throughput of
"standard serial" processes.
hmm, curious argument - why do you think MOSIX will be more efficient
than a "normal" cluster when confronted with a trivial/s
On Thursday 18 January 2007 15:17, Richard Walsh wrote:
...
> While I agree with this argument, especially at small scale, at
> very large scale operating
> system derived load imbalance (so-called skew, due to the random
> nature of system
> call driven interrupts) can destroy scala
Robert G. Brown wrote:
On Thu, 18 Jan 2007, Richard Walsh wrote:
Ashley Pittman wrote:
On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote
Yes, it is. And more so if this cluster/LAN can also utilize som type
of "MOSIX" system. This will substatially increase the throughput of
"stan
snip
>>
>>My understanding of pricing (for the windows portion) is that it
>>adds (as an OS) $500USD to each node. So for a 32 node machine,
>>this is an extra $16k USD "tax" added on. Doesn't include the
>>absolutely necessary antivirus, anti-spyware, ...
>
> Probably wouldn't be that expensiv
On Thu, 18 Jan 2007, Richard Walsh wrote:
Ashley Pittman wrote:
On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote
Yes, it is. And more so if this cluster/LAN can also utilize som type
of "MOSIX" system. This will substatially increase the throughput of
"standard serial" processes.
On Thu, 2007-01-18 at 08:17 -0600, Richard Walsh wrote:
> Ashley Pittman wrote:
> > On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote
> >> Yes, it is. And more so if this cluster/LAN can also utilize som type
> >> of "MOSIX" system. This will substatially increase the throughput of
> >>
Hello folks,
Does anybody use the array-processing language ZPL? The last reference I can
find to it is about two years ago; for example, the latest nightly "Cutting
Edge" build was: *"Last reflected modification: Tue Nov 16 18:55:55 PST 2004
"* (from http://www.cs.washington.edu/research/zpl/do
Ashley Pittman wrote:
On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote:
Eric Shook wrote:
I talked to our SGI rep about this yesterday and he told me they are not
really targeting "hard-core" university research where Linux/UNIX
already has a strong foot hold. Instead this is for
Ashley Pittman wrote:
On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote
Yes, it is. And more so if this cluster/LAN can also utilize som type
of "MOSIX" system. This will substatially increase the throughput of
"standard serial" processes.
I find this statement hard to compreh
It is a powerful combination microsoft + sgi.
Not because of the mouse saying to the elephant when crossing a river over a
wooden bridge: "We make a lot of noise don't we?"
But rather because SGI has something microsoft can't deliver. Machine that
to a limited number of cpu's provide a shared
On Wed, 2007-01-17 at 08:50 +0100, Mikael Fredriksson wrote:
> Eric Shook wrote:
> > I talked to our SGI rep about this yesterday and he told me they are not
> > really targeting "hard-core" university research where Linux/UNIX
> > already has a strong foot hold. Instead this is for the Business
27 matches
Mail list logo
