On 11/20/12 10:49 AM, Duke Nguyen wrote:
> Hi folks,
>
> So I was able to try warewulf to boot up our nodes following this
> guide:
> http://hpc.admin-magazine.com/Articles/Warewulf-Cluster-Manager-Master-and-Compute-Nodes.
>
> I got everything running up to the final step: log into node. The n
On Tue, 20 Nov 2012, Christopher Samuel wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> On 20/11/12 05:23, Robert G. Brown wrote:
>
>> I don't know if these cache sizes are per core or per system,
>
> Install hwloc and run lstopo.. :-)
>
> http://www.open-mpi.org/projects/hwloc/
Way
Hi folks,
So I was able to try warewulf to boot up our nodes following this guide:
http://hpc.admin-magazine.com/Articles/Warewulf-Cluster-Manager-Master-and-Compute-Nodes.
I got everything running up to the final step: log into node. The node
(192.168.200.2) is up, showing up log in screen on
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 20/11/12 01:28, Douglas Eadline wrote:
> Though not formally announced, Semiaccurate seems to have learned
> that AMD is leaving the X86 server business.
Whilst sad (and possibly inaccurate) it wouldn't surprise me if they
did that in the long te
On Mon, 19 Nov 2012, Douglas Eadline wrote:
> Intel has a single socket Xeon (E3-12XX series Sandy/Ivy-Bridge)
> and will work on single socket motherboards. Mostly designed for
> the small office/home server these have more "server" features,
> basically ECC, and cost slightly more than the i-5/7
On 11/19/2012 08:58 PM, Douglas Eadline wrote:
>
>>
>> On 11/19/2012 03:07 PM, Douglas Eadline wrote:
>>> But I have to give Intel soem major geek credit. Bringing the original
>>> Star Trek bridge to SC12 was the highlight of the show. And yes I sat
>>> in Kirk's chair and have the pictures to pro
On 11/19/12 10:54 PM, Duke Nguyen wrote:
> On 11/19/12 9:43 PM, Joe Landman wrote:
>> If you don't want the headache of re-inventing this wheel yourself, I'd
>> recommend the Warewulf distribution http://warewulf.lbl.gov/trac . One
>> of the best around for this stuff.
>>
> On 11/19/12 8:04 PM, Tr
On Mon, 19 Nov 2012, Administrator wrote:
> On 19/11/12 22:43, graham.mull...@syngenta.com wrote:
>
>> Next you'll say that the old guys are the ones who have used punched cards
> > and know (well, maybe knew) the different between Fortran 66 and 77.
>
> Or can remember the wild party we threw whe
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 20/11/12 11:03, Robert G. Brown wrote:
> Way cool. I wonder where they pull the data from if not proc.
/sys :-)
Well, that and various syscalls I think (especially on other OS's).
> Of course, being as how it is open source, if I wondered enoug
>
> On 11/19/2012 03:07 PM, Douglas Eadline wrote:
>> But I have to give Intel soem major geek credit. Bringing the original
>> Star Trek bridge to SC12 was the highlight of the show. And yes I sat
>> in Kirk's chair and have the pictures to prove it.
>
> Interesting... I found that insulting. The
Nah.. you just slide the other disk into the drive of the 1130 to run the
second compiler pass. Who needs that much extra memory anyway.
Jim Lux
-Original Message-
From: beowulf-boun...@beowulf.org [mailto:beowulf-boun...@beowulf.org] On
Behalf Of Administrator
Sent: Monday, November
No, it's if you know the difference between an 026 and 029 keypunch. Bonus
points if you know how to do multipunch on a 026 to get parenthesis for a
machine that's expecting 029.
If you're a real stud geek, you used a drum card, so you could "tab" to column
7.
Jim Lux
-Original Message---
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Interesting news, given what I wrote earlier..
http://www.forbes.com/sites/jeanbaptiste/2012/11/19/intel-ceo-fall-signals-move-to-arm-closer-ties-with-apple/
# The change of leadership at Intel could bring a real
# sea change for the entire semicondu
>From the URL in the original post :
Updated 11/19/2012@10:15am: AMD contacted us with an official denial
of the story and stated that Kaveri and the big cores are still on
track.
___
Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computi
On 19/11/12 22:43, graham.mull...@syngenta.com wrote:
> Next you'll say that the old guys are the ones who have used punched cards
> and know (well, maybe knew) the different between Fortran 66 and 77.
Or can remember the wild party we threw when we increased core from 4K
to 8K
P.S. What's
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 20/11/12 05:23, Robert G. Brown wrote:
> I don't know if these cache sizes are per core or per system,
Install hwloc and run lstopo.. :-)
http://www.open-mpi.org/projects/hwloc/
- --
Christopher SamuelSenior Systems Administrator
VLSC
RGB wrote: "No, it is only the OLD GUYS like me and Doug that were kids when
Star
Trek first appeared and have the proper degree of nostalgic geekery. "
I wasn't feeling old until I read that. Next you'll say that the old guys are
the ones who have used punched cards and know (well, maybe knew)
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 19/11/12 19:19, Duke Nguyen wrote:
> Thanks for your very honest advice! Unfortunately it is not
> similar situation like in US, where we can find companies with
> appropriate services to help and assist us.
You might want to look at trying xCAT,
On Mon, 19 Nov 2012, Vincent Diepeveen wrote:
>
> On Nov 19, 2012, at 6:12 PM, Robert G. Brown wrote:
>
>> On Mon, 19 Nov 2012, Vincent Diepeveen wrote:
>>
>>> If you measure memory latency at all 8 cores at the same time, it's
>>> even more horrible.
>>
>> Thanks for a remarkably clear and useful
On Mon, 19 Nov 2012, Prentice Bisbal wrote:
>
> On 11/19/2012 03:07 PM, Douglas Eadline wrote:
>> But I have to give Intel soem major geek credit. Bringing the original
>> Star Trek bridge to SC12 was the highlight of the show. And yes I sat
>> in Kirk's chair and have the pictures to prove it.
>
On 11/19/2012 03:07 PM, Douglas Eadline wrote:
> But I have to give Intel soem major geek credit. Bringing the original
> Star Trek bridge to SC12 was the highlight of the show. And yes I sat
> in Kirk's chair and have the pictures to prove it.
Interesting... I found that insulting. The typical
On Nov 19, 2012, at 9:07 PM, Douglas Eadline wrote:
>
>> On 11/19/2012 09:28 AM, Douglas Eadline wrote:
>>> Though not formally announced, Semiaccurate seems to have learned
>>> that AMD is leaving the X86 server business.
>>>
>>> http://semiaccurate.com/2012/11/19/amd-kills-off-big-cores-kaveri
On Nov 19, 2012, at 8:37 PM, Robert G. Brown wrote:
> On Mon, 19 Nov 2012, Douglas Eadline wrote:
>
>>
>>> On Mon, 19 Nov 2012, Douglas Eadline wrote:
>>>
Intel has a single socket Xeon (E3-12XX series Sandy/Ivy-Bridge)
and will work on single socket motherboards. Mostly designed for
>>
On 11/19/12 9:43 PM, Joe Landman wrote:
> If you don't want the headache of re-inventing this wheel yourself, I'd
> recommend the Warewulf distribution http://warewulf.lbl.gov/trac . One
> of the best around for this stuff.
>
On 11/19/12 8:04 PM, Tru Huynh wrote:
> You could ease your way and try
About ten years ago, when we choose CPUs for supercomputer in our
supercomputer center. AMD cpus have much better performance than Intel
cpus. It is a great pity to hear this news, although I hope this will NOT
be true...It is good to have choice instead of only one
On Mon, Nov 19, 2012 at
On 11/19/2012 03:07 PM, Douglas Eadline wrote:
>> of course the article was amended at 10:15am to say that AMD contacted
>> them to say that Kaveri and the big cores are still on track.
Good. They do have value, and I'd hate to see them leave this market.
They do need to fix a few things though
> On 11/19/2012 09:28 AM, Douglas Eadline wrote:
>> Though not formally announced, Semiaccurate seems to have learned
>> that AMD is leaving the X86 server business.
>>
>> http://semiaccurate.com/2012/11/19/amd-kills-off-big-cores-kaveri-steamroller-and-excavator/
>>
>>
> of course the article was
On Mon, 19 Nov 2012, Douglas Eadline wrote:
>
>> On Mon, 19 Nov 2012, Douglas Eadline wrote:
>>
>>> Intel has a single socket Xeon (E3-12XX series Sandy/Ivy-Bridge)
>>> and will work on single socket motherboards. Mostly designed for
>>> the small office/home server these have more "server" featur
On Nov 19, 2012, at 7:23 PM, Robert G. Brown wrote:
> On Mon, 19 Nov 2012, Vincent Diepeveen wrote:
>
>>
>> On Nov 19, 2012, at 6:12 PM, Robert G. Brown wrote:
>>
>>> On Mon, 19 Nov 2012, Vincent Diepeveen wrote:
>>>
If you measure memory latency at all 8 cores at the same time, it's
ev
> On Mon, 19 Nov 2012, Douglas Eadline wrote:
>
>> Intel has a single socket Xeon (E3-12XX series Sandy/Ivy-Bridge)
>> and will work on single socket motherboards. Mostly designed for
>> the small office/home server these have more "server" features,
>> basically ECC, and cost slightly more than t
> On Mon, 19 Nov 2012, Vincent Diepeveen wrote:
>
>> If you measure memory latency at all 8 cores at the same time, it's
>> even more horrible.
>
> Thanks for a remarkably clear and useful reply, Vincent. This nearly
> precisely mirrors my own measurements with a more floating point
> intensive t
On 11/19/12 8:04 PM, Tru Huynh wrote:
>> So to summarize:
>> * boot using liveCD -> OK, logging in fine
>> * boot using rsync of master node's system -> OK, cant log in
> SElinux is probably on the way, did you relabel?
Interesting. Since I am familiar with debian-based distros, these
selinux
On Nov 19, 2012, at 6:12 PM, Robert G. Brown wrote:
> On Mon, 19 Nov 2012, Vincent Diepeveen wrote:
>
>> If you measure memory latency at all 8 cores at the same time, it's
>> even more horrible.
>
> Thanks for a remarkably clear and useful reply, Vincent. This nearly
> precisely mirrors my own
On Mon, 19 Nov 2012, Vincent Diepeveen wrote:
> If you measure memory latency at all 8 cores at the same time, it's
> even more horrible.
Thanks for a remarkably clear and useful reply, Vincent. This nearly
precisely mirrors my own measurements with a more floating point
intensive task. The lar
"The Mali-T604 is the first GPU based on the Midgard architecture and
offers scalability from one to four cores."
Assuming a single core doesn't have 'minicores' of some sort i wish
them lots of fun with this.
The Cortex A15 quadcore under full load eats 6 watts is expectation now.
That's do
On Nov 19, 2012, at 3:43 PM, Robert G. Brown wrote:
> On Mon, 19 Nov 2012, Douglas Eadline wrote:
>
>>
>> Though not formally announced, Semiaccurate seems to have learned
>> that AMD is leaving the X86 server business.
>>
>> http://semiaccurate.com/2012/11/19/amd-kills-off-big-cores-kaveri-
>>
http://www.tgdaily.com/hardware-features/67548-mont-blanc-supercomputer-powered-by-samsungs-exynos
Mont-Blanc supercomputer powered by Samsung's Exynos
Posted on November 17, 2012 - 10:00 by Trent Nouveau
The European-based Mont-Blanc project has selected Samsung's flagship Exynos
platform as t
On 11/19/2012 03:43 AM, Duke Nguyen wrote:
> Hi folks,
>
> So per advices and suggestions, we started to look for booting our nodes
> throught Gbit Ethernet. The OS of our choice is Scientific Linux 6.3 -
> SL6.3 (for all master and client nodes). There are bunches of
> guides/instructions out ther
On 11/19/2012 09:28 AM, Douglas Eadline wrote:
>
> Though not formally announced, Semiaccurate seems to have learned
> that AMD is leaving the X86 server business.
>
> http://semiaccurate.com/2012/11/19/amd-kills-off-big-cores-kaveri-steamroller-and-excavator/
/sigh
Hoping this is a low signal co
Question becomes is how is the graphics card division doing. I think that
is what is keeping them a float.
On Mon, Nov 19, 2012 at 3:43 PM, Robert G. Brown wrote:
> On Mon, 19 Nov 2012, Douglas Eadline wrote:
>
> >
> > Though not formally announced, Semiaccurate seems to have learned
> > that AM
On Mon, 19 Nov 2012, Douglas Eadline wrote:
>
> Though not formally announced, Semiaccurate seems to have learned
> that AMD is leaving the X86 server business.
>
> http://semiaccurate.com/2012/11/19/amd-kills-off-big-cores-kaveri-steamroller-and-excavator/
Hi Doug,
Sad, but not surprising at th
If AMD sells the GPU division and sells patents they own in x64 then
of course the best thing to do is
pay out all that cash to the shareholders and liquidate the company.
On Nov 19, 2012, at 3:28 PM, Douglas Eadline wrote:
>
> Though not formally announced, Semiaccurate seems to have learned
Though not formally announced, Semiaccurate seems to have learned
that AMD is leaving the X86 server business.
http://semiaccurate.com/2012/11/19/amd-kills-off-big-cores-kaveri-steamroller-and-excavator/
--
Doug
--
Mailscanner: Clean
___
Beowulf m
> On 11/13/12 3:32 PM, Beat Rubischon wrote:
>> "PXE Boot" is a nice container (buzzword? :-) for a hand full of simple
>> steps. First the PXE Boot ROM asks for a DHCP address, second it will
>> load PXElinux over tftp. PXElinux will ask again for a configuration
>> file and finally loads the ker
Hi folks,
So per advices and suggestions, we started to look for booting our nodes
throught Gbit Ethernet. The OS of our choice is Scientific Linux 6.3 -
SL6.3 (for all master and client nodes). There are bunches of
guides/instructions out there in the net, but I focused and learnt from
mainl
On Nov 19, 2012, at 9:19 AM, Duke Nguyen wrote:
>
> Thanks for your very honest advice! Unfortunately it is not similar
> situation like in US, where we can find companies with appropriate
> services to help and assist us. In Vietnam, where we are now, cluster
> systems are already rare. In fact I
On 11/13/12 3:32 PM, Beat Rubischon wrote:
> "PXE Boot" is a nice container (buzzword? :-) for a hand full of simple
> steps. First the PXE Boot ROM asks for a DHCP address, second it will
> load PXElinux over tftp. PXElinux will ask again for a configuration
> file and finally loads the kernel and
47 matches
Mail list logo
