On Thu, 22 Nov 2007, Jeffrey B. Layton wrote:
> A quick question about the list. Can I post job openings to the list or
> is that in bad taste?
It's in bad taste. I tolerate it only for prolific posters, but anything
beyond a short trailing note at the end of a long technical post is likely
to
David Mathog wrote:
Operator overloading reminds me of Bill Clinton's:
"It depends what the meaning of 'is' is." If operator
overloading is used unwisely, so that the meaning of "+" is not just
"addition of this type of data", then pity the poor schmuck who has to
maintain the code. Unfortunat
Ekechi Nwokah wrote:
Hi,
Does anyone know of any software RAID solutions that come close to the
performance of a commodity RAID card such as LSI/3ware/Areca for
direct-attached drives?
For small numbers of drives, yes, the MD driver is superb with two
(well, really three) caveats.
First: N
Hi,
As I mentioned in my previous posting, the 20 node Tyan S2891 Dual
Opteron dual core Debian cluster (1 NFS providing head node, 19 diskless
compute nodes) is currently experiencing 2 intermittent problems which
I'm trying to diagnose.
After a few days of testing and digging through syste
Hello list,
i was trying to find some info about the i/o-access of secondary
storage of applications, which uses the distributed file system. And
it seems that it's not the popular topic.
I've found a paper about penguinometer, there is some discriptions
about the access specification of some ap
All,
Regarding the Matlab vs Octave debate, has anyone looked at Scilab? It
has signal processing toolkits, ode solvers and a few other add-ons
that might be of interest. Also does decent graphics & animations.
Stephen
___
Beowulf mailing list, Beo
Brian Dobbins wrote:
I had at one point a simple script that would allow me to select a
kernel type at job submit time, it would load that up, reboot the nodes
with that kernel, and then run my job. Sometimes this was incredibly
useful, as I found a difference of roughly 20-25% performance
Except that swraid does usually not support hotswap replacing of a failed drive
without interrupting the server's current workload and without an admin logging
in and doing some risky mdadm / scsidriver surgery.
Michael
Sent from my GoodLink synchronized handheld (www.good.com)
-Origin
performance of a commodity RAID card such as LSI/3ware/Areca for
direct-attached drives?
Yes. Of course there's a factor of 10 or more in the various cards
offered by those vendors. Adaptec is another popular brand.
I've had good luck with recent 3ware, and heard Areca is good.
both LSI and
Does anyone know of any software RAID solutions that come close to the
performance of a commodity RAID card such as LSI/3ware/Areca for
direct-attached drives?
yes, MD, the standard Linux software raid, is generally faster
than HW raid. yes, this can be argued, though not in any kind
of slam-
Quoting "Robert G. Brown" <[EMAIL PROTECTED]>, on Wed 21 Nov 2007
07:36:43 AM PST:
On Wed, 21 Nov 2007, Jim Lux wrote:
Quoting "Robert G. Brown" <[EMAIL PROTECTED]>, on Wed 21 Nov 2007
05:56:51 AM PST:
On Tue, 20 Nov 2007, Jim Lux wrote:
Octave is nice, but the graphics are MUCH be
Quoting "Robert G. Brown" <[EMAIL PROTECTED]>, on Wed 21 Nov 2007
06:47:16 AM PST:
On Tue, 20 Nov 2007, Joshua Baker-LePain wrote:
You do raise an interesting question. Would one student running
an application on N machines need N copies under their academic
student license?
Almost c
On Wed, Nov 21, 2007 at 07:17:27PM -0500, Robert G. Brown wrote:
> Making it time for .. THANKSGIVING BREAK!
Darn, I was figuring you were going to answer, "But EVERYONE wants to
hear my theories!"
I mean, that's what *I* think...
-- g
___
Beowulf mai
Ekechi Nwokah wrote:
Hi,
Does anyone know of any software RAID solutions that come close to the
Yes, better even.
performance of a commodity RAID card such as LSI/3ware/Areca for
direct-attached drives?
Yes. Of course there's a factor of 10 or more in the various cards
offered by those ve
On Wed, 21 Nov 2007, David Mathog wrote:
It would have been interesting if C++ had implemented operator
definition instead of operator overloading (ie, redefinition).
For instance like:
A = B + C D
Admittedly it looks a bit odd, but when maintaining the code a
programmer would see and know
On Wed, 21 Nov 2007, Peter St. John wrote:
Speaking of octonions (ahem), has everyone read "An Exceptionally
Simple Theory of Everything"?
The wiki article is at
http://en.wikipedia.org/wiki/An_Exceptionally_Simple_Theory_of_Everything
and the ArXiv item, 31 pp PDF, I think worth skimming even i
On Wed, 21 Nov 2007, Greg Lindahl wrote:
On Wed, Nov 21, 2007 at 02:48:48PM -0500, Robert G. Brown wrote:
But what if they'd STARTED by selling NeXTStep as a Unix for PCs back
before Linux was really born, for $50 a seat. OS/2 and Windows BOTH
would have been stillborn, and Jobs would be Gate
Hi,
Does anyone know of any software RAID solutions that come close to the
performance of a commodity RAID card such as LSI/3ware/Areca for
direct-attached drives?
With the availability multi-core chips and SSE instruction sets, it
would seem to me that this is doable. Would be nice to not have t
Robert G. Brown wrote
> On Wed, 21 Nov 2007, David Mathog wrote:
> Unless, of course, one works in a graded (geometric) division algebra...
> but yes, I agree. And it isn't much harder to call csum(a,b,c) where
> they are complex structs, or do whatever the GSL uses to accomplish the
> same thing
On Wed, Nov 21, 2007 at 02:48:48PM -0500, Robert G. Brown wrote:
> But what if they'd STARTED by selling NeXTStep as a Unix for PCs back
> before Linux was really born, for $50 a seat. OS/2 and Windows BOTH
> would have been stillborn, and Jobs would be Gates today.
Dude, at some point your "hey
Speaking of octonions (ahem), has everyone read "An Exceptionally
Simple Theory of Everything"?
The wiki article is at
http://en.wikipedia.org/wiki/An_Exceptionally_Simple_Theory_of_Everything
and the ArXiv item, 31 pp PDF, I think worth skimming even if not
...any of several relevant difficult spe
Robert G. Brown wrote:
A = B + CROSS_PRODUCT(C,D)
Ah but are A and B vectors or pseudovectors? Just kidding...;-)
Quaternions ... :)
--
Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics LLC,
email: [EMAIL PROTECTED]
web : http://www.scalableinformatics.com
http://jackra
On Wed, 21 Nov 2007, Tim Cutts wrote:
It didn't work for Mac OS X's previous incarnation, though, in the form of
NextSTEP, did it? Selling that platform as an OS and abandoning hardware
manufacture did not save NeXT.
Yeah, but that's because it was too late and everybody knew that while
Next
On Thu, 22 Nov 2007, Jeffrey B. Layton wrote:
A quick question about the list. Can I post job openings to the list or
is that in bad taste?
People have certainly done so in the past. I think of it this way. If
you contribute a lot of signal to the list, absolutely. That means that
if you pe
On Wed, 21 Nov 2007, David Mathog wrote:
Joe Landman <[EMAIL PROTECTED]> wrote:
There are a myriad
of ways to handle complex in C, but you can't easily write
complex A,B,C,D
A = B + C*D
with anything like the clarity of Fortran.
The reason it's clear is that + means additio
On Wed, 21 Nov 2007, Mark Hahn wrote:
I also think that Apples' current success has a lot more to do with its
Apple's current success is as a music-playing-jewelry company,
currently expanding into the status-symbol-phone market.
there is some status-symbol leakage ("halo effect") into their
On 21 Nov 2007, at 3:00 pm, Robert G. Brown wrote:
On Wed, 21 Nov 2007, Tim Cutts wrote:
I have to say I have some sympathy with that view. Much though I
love OS X as a desktop OS, I have to wonder why anyone would jump
through hoops building a cluster running just Darwin, when they
cou
> -Original Message-
> [mailto:[EMAIL PROTECTED] On Behalf Of Tom Elken
> Sent: Wednesday, November 21, 2007 9:02 AM
> To: andrew holway; Beowulf Mailing List
> Subject: RE: [Beowulf] scaling SPECint_base2000 for harpertown
>
> > http://www.moonet.co.uk/2004
>
> >From what I can interpr
A quick question about the list. Can I post job openings to the list or
is that in bad taste?
Thanks!
Jeff
___
Beowulf mailing list, Beowulf@beowulf.org
To change your subscription (digest mode or unsubscribe) visit
http://www.beowulf.org/mailman/lis
Mark Hahn wrote:
Apple's current success is as a music-playing-jewelry company,
currently expanding into the status-symbol-phone market.
there is some status-symbol leakage ("halo effect") into their
pretty-computer sideline.
One way to see if this is true is to go to the MacWorld Expo
exhi
Joe Landman <[EMAIL PROTECTED]> wrote:
> There are a myriad
> of ways to handle complex in C, but you can't easily write
>
> complex A,B,C,D
>
> A = B + C*D
>
> with anything like the clarity of Fortran.
The reason it's clear is that + means addition, and * means
multiplication, ex
I also think that Apples' current success has a lot more to do with its
Apple's current success is as a music-playing-jewelry company,
currently expanding into the status-symbol-phone market.
there is some status-symbol leakage ("halo effect")
into their pretty-computer sideline. although maco
My crystal ball shows an advent of solaris simply because its not the
soon-to-be-microsoft-dominated linux codebase. .. Shudder...
Then again with software patent wars the actual codebase does not matter
anymore...
Michael
Sent from my GoodLink synchronized handheld (www.good.com)
-Origi
> [mailto:[EMAIL PROTECTED] On Behalf Of andrew holway
> I recently got SPECint_base2000 figures from intel for
> harpertown using low optimisation flags (-O2 -pthread -fPIC).
> This benchmark is commonly used in particle physics circles
> to provide a common base.
> I was expecting the number
>
> > I just get spoiled with the substantially better graphing capabilities
> of
> > Matlab, and some of the toolbox things that one gets used to. Sure, one
> > could probably find equivalents (or write them) for Octave, but it's
> nice
> > when it's just right there.
>
> I don't "use" either one
Jim Lux wrote:
I just get spoiled with the substantially better graphing capabilities
of Matlab, and some of the toolbox things that one gets used to.
Sure, one could probably find equivalents (or write them) for Octave,
but it's nice when it's just right there.
Agreed. A few years ago I wro
On Wed, 21 Nov 2007, Geoff wrote:
While their OS is indeed constrained to their hardware, you can freely
install and run other OSs on their hardware (Windows, Linux and *BSD) so I
would agree they tend to position themselves as a hardware company but I
disagree that they will need to make a ch
On Wed, 21 Nov 2007 at 10:36am, Robert G. Brown wrote
I'm just describing what Duke had, which I'm pretty familiar with
because we faced these actual costs a couple of years ago and had to go
renegotiate our whole deal with them. It is a bit better now -- I think
Duke just dickered out an unlim
Jeffrey B. Layton wrote:
In Fortran it's always been x**y. The good compilers let x and y be any
data types (I've not tried using a complex as the exponent though).
It should be noted that I haven't been actively using Fortran for the
better part of the last decade. This is not a choice issu
On Tue, 20 Nov 2007 at 8:49pm, Jim Lux wrote
Quoting Joshua Baker-LePain <[EMAIL PROTECTED]>, on Tue 20 Nov 2007 05:07:23 PM
PST:
On Tue, 20 Nov 2007 at 4:28pm, Jim Lux wrote
Quoting Joe Landman <[EMAIL PROTECTED]>, on Tue 20 Nov 2007
04:09:04 PM PST:
Anyone need an adjunct ... :) I was
Robert G. Brown wrote:
[ language war elided ]
Fortran's I/O commands are terrible. Fortran is miserable if you have
Well, yes ...
to manipulate text. Fortran isn't the easiest thing (consequently) to
Just remember, all text is an array I wrote a rough equivalent of
strtok in fo
Robert G. Brown wrote:
And textbook prices are, frankly, highway robbery as well. I have a
couple of them online for free, and students all over the world use
them. A textbook SHOULD cost around $25, not $125. And one day
Awe ... cmon ... professors have to make a living too ... :^
--
Jo
On Thu, 22 Nov 2007, Jeffrey B. Layton wrote:
You haven't tried anything F90 or above. Take a look at some tutorials.
It's basically the same as in C now. You have allocation, pointers
(if you want them).
And if we can just get C to add binary exponentiation, and fortran to
add {} support for
Is this expected? These are aggregate figures for a dual socket
machine with 1.5GB ram per core.
why not? spec2000 is terrifically in-cache.
___
Beowulf mailing list, Beowulf@beowulf.org
To change your subscription (digest mode or unsubscribe) visit
One day Apple will make up its mind about whether it is a hardware
company or a software company. I vote soft, and thought that once they
supported generic Intel even their main company management would "get
it". It continues to think "hard" though, probably because they
armtwist a significan
On Wed, 21 Nov 2007, Jim Lux wrote:
Quoting "Robert G. Brown" <[EMAIL PROTECTED]>, on Wed 21 Nov 2007 05:56:51 AM
PST:
On Tue, 20 Nov 2007, Jim Lux wrote:
Octave is nice, but the graphics are MUCH better in Matlab, and
there's all those toolboxes full of cool stuff (signal processing,
On Wed, 21 Nov 2007, Tim Cutts wrote:
I have to say I have some sympathy with that view. Much though I love OS X
as a desktop OS, I have to wonder why anyone would jump through hoops
building a cluster running just Darwin, when they could probably have done it
much more easily, and with much
Robert G. Brown wrote:
On Tue, 20 Nov 2007, Donald Shillady wrote:
Hi, I am one of those old grey-haired Professors who spent years since
1963 using variants of FORTRAN with time out for four years of enforced
Burroughs ALGOL and then back to FORTRAN. In Chemistry education there
is an added
On Tue, 20 Nov 2007, Joshua Baker-LePain wrote:
You do raise an interesting question. Would one student running an
application on N machines need N copies under their academic student
license?
Almost certainly yes.
Raise that to certainly yes. I have a student who is using matlab this
sem
On Tue, 20 Nov 2007, Nathan Moore wrote:
Our institution has a site license for Mathematica and between that and a
compiled langauge, I feel guilty telling my students to spend more money on
something that seems to be of only marginal utility. Also, (and I'm sure
I'm wrong on this), Matlab seem
On Tue, 20 Nov 2007, Donald Shillady wrote:
Hi, I am one of those old grey-haired Professors who spent years since
1963 using variants of FORTRAN with time out for four years of enforced
Burroughs ALGOL and then back to FORTRAN. In Chemistry education there
is an added problem of students who
Quoting "Robert G. Brown" <[EMAIL PROTECTED]>, on Wed 21 Nov 2007
05:56:51 AM PST:
On Tue, 20 Nov 2007, Jim Lux wrote:
Octave is nice, but the graphics are MUCH better in Matlab, and
there's all those toolboxes full of cool stuff (signal processing,
control systems, maps, etc.)
An
On Tue, 20 Nov 2007, Jim Lux wrote:
Octave is nice, but the graphics are MUCH better in Matlab, and there's
all those toolboxes full of cool stuff (signal processing, control systems,
maps, etc.)
And, an academic license for Matlab is only $100. That's less than the
textbook likely cost
I recently got SPECint_base2000 figures from intel for harpertown
using low optimisation flags (-O2 -pthread -fPIC). This benchmark is
commonly used in particle physics circles to provide a common base.
I was expecting the numbers to scale pretty much exactly but if you
look at the link below the
I ran a 32 node/64 cpu and a 16 node 32 cpu (although I tinkered with
hyperthreading for twice that) for 3 years or so.
Mryinet was stable, did occasionally have problems with job clean up, but I've
seen similar with infinipath, infiniband, and even ethernet. We had a few
support calls and got
55 matches
Mail list logo
