Richard,
I found
http://www.cis.upenn.edu/~milom/cis501-Fall05/lectures/10_dlp.pdf
which I think will clarify this taxonomy for me, and it ties in to the
Single/many instruction S/M data thing too. Gosh this "beowulfry" thing has
alot of stuff. Arithmetic Algebraic Geometry is simpler.
Peter (lyi
Richard,
No not at all ("..which you already know"), as you might guess from the
abysmal typography of my question, I'm a newbie to distributed computing; I
just have a distributable algorithm.
1. I'll try to write a minimal wiki entry for DLP to go along with the
existing ones for ILP and MLP, b
-- Original message --
From: "Peter St. John" <[EMAIL PROTECTED]>
DLP? Wiki has entries for Indtruction Level Parallelism and Thread LP (alsom
Memory LP) but
not DLP?
Hey Peter,
That would be "data level parallelism". So, ILP is very low level parallelism
which
wor
>Dear MPI Mavens,
>
>What is the current state of the art for MPI (or PVM or other parallel
>code) debuggers? I vaguely recall some review articles on this on CWM
>and/or CM, and of course there has been list discussion in the past, but
>a quick summary would be very useful.
We use two different
Tim Cutts wrote:
On 18-Oct-07, [EMAIL PROTECTED] wrote:
Thanks, didn't know about the preseeding method. Also, there seems to be a
kickstart, at least for ubuntu. Has anyone compared FAI to kickstart (for
ubuntu/debian)?
[snipped]
http://drbl.sourceforge.net/
From the website:
"Peacefully
Hi, Antoine!
I am interested to use PBLAS functions in my applicattion.
I would like to know if there si any possibility to
imroove performance for my current platform (Itanium
Linux). As I know you are one of the developers of PBLAS.
Could you please provide me with some algorithm notes of
Wow; my takeaway is a wiki for man pages, fantastic. It just went above
"ugu" on my home page.
Thanks!
Peter
On 10/17/07, Mark Hahn <[EMAIL PROTECTED]> wrote:
>
> >> not me. raid is too important to be trusted to hardware - have you
> >> tried MD's check/scrub features? though afaik it doesn't
On Thu, 18 Oct 2007, Bogdan Costescu wrote:
On Thu, 18 Oct 2007, Robert G. Brown wrote:
but on highly INhomogeneous hardware, slow and undependable networks, and
the like -- if it dies
This discussion being on the beowulf list, I can agree with kickstart being
used on INhomogenous hardware,
DLP? Wiki has entries for Indtruction Level Parallelism and Thread LP (alsom
Memory LP) but not DLP?
Peter
>Perhaps you are refering to the TRIPS Polymorphic Processor from U of Texas
which can be configured to favor ILP, DLP, or TLP application types. I
think I sent out this reference a while b
On Thu, 18 Oct 2007, Robert G. Brown wrote:
but on highly INhomogeneous hardware, slow and undependable
networks, and the like -- if it dies
This discussion being on the beowulf list, I can agree with kickstart
being used on INhomogenous hardware, but not on slow and undependable
networks; h
On Thu, 18 Oct 2007, Tim Cutts wrote:
The real killer advantages of FAI, for me, are the SSH server so I can
monitor the install remotely, and the detailed logging. Both of these
are invaluable for diagnosing installation problems.
With kickstart, you can start a VNC connection, check out:
h
Reuti wrote:
Hi,
Am 16.10.2007 um 16:08 schrieb Sean Ward:
I've started work on a web service which contains several potentially
long running processing steps (molecular dynamics), which are perfect
to farm out to the fairly large (90 node) Beowulf I have access to.
The primary issue is tran
Dear MPI Mavens,
What is the current state of the art for MPI (or PVM or other parallel
code) debuggers? I vaguely recall some review articles on this on CWM
and/or CM, and of course there has been list discussion in the past, but
a quick summary would be very useful.
rgb
--
Robert G. Brown
On Thu, 18 Oct 2007, Tim Cutts wrote:
The real killer advantages of FAI, for me, are the SSH server so I can
monitor the install remotely, and the detailed logging. Both of these
are invaluable for diagnosing installation problems.
They certainly do sound useful, I agree. I'm hoping that if
Hi,
Am 16.10.2007 um 16:08 schrieb Sean Ward:
I've started work on a web service which contains several
potentially long running processing steps (molecular dynamics),
which are perfect to farm out to the fairly large (90 node) Beowulf
I have access to. The primary issue is translating req
On 18-Oct-07, [EMAIL PROTECTED] wrote:
> Thanks, didn't know about the preseeding method. Also, there seems to be a
> kickstart, at least for ubuntu. Has anyone compared FAI to kickstart (for
> ubuntu/debian)?
The fundamental approach is rather different. As I understand it,
kickstart basically r
> Debian/Ubuntu both have automated install methods. There's the
> 'preseeding' method, which is pretty similar in principle to
> kickstart; you just tell the installer where to find all the answers
> to the questions it would have asked.
>
> There's also the more flexible FAI, which is what we te
17 matches
Mail list logo
