Greetings all,
I am just curious, if the problem is embarrassingly parallel , then how
effective using MPI over a 'MapReduce' implementation(apache Hadoop ) .
thanks in advance,
umanga
Hi all,
I want to trace my program, having used vampirTrace to generate tracing
info, except for Vampir, where can I download free tools to parse the
tracing info?
Thanks in advance.
Lin
On Sun, 2009-07-12 at 19:49 -0500, Yin Feng wrote:
> Can you give me a further explanation about why results are different
> when it ran it on mutiprocessors against single processor?
Floating point number are problematical for a number of reasons, they
are only *approximations of real numbers bec
On Mon, 2009-07-13 at 16:06 +0900, Ashika Umanga Umagiliya wrote:
> I am just curious, if the problem is embarrassingly parallel , then how
> effective using MPI over a 'MapReduce' implementation(apache Hadoop ) .
Almost impossible. You could implement MapReduce on top of MPI fairly
trivially h
Dear all,
I've some old D33x Dolphin SCI cards and I would like to use OpenMPI on
Linux rather than the Dolphin-provided NMPI. Has somebody tried this
before?
Thanks!
Rodrigo
--
Rodrigo Delgado Urzúa
Industrial and Information Technology Engineer
Office of Modeling and Development Externa
Hi Jody,
Have you tried turning off Hyper-Threading with the Processor
Preference Pane?
The processor palette is include in the CHUD package when you
installed the developer tools. It lives in /Developer/Extras/
PreferencePanes; launch it and it will get added to the system
preferences.
I've been using openmpi-1.2.x for 2 years to dynamically create python
bindings for my application code. I've just downloaded and installed
openmpi-1.3.2, and I now get the following error when trying to run python
with one of my bindings:
/data/python/current/bin/python: symbol lookup error:
/da
Here's my advice: Don't trust anyones advice. Benchmark it yourself and
see.
The problems vary so wildly that only you can tell if your problem will
benefit from oversubscription. It really depends on too many factors to
accurately predict: schedulers, memory usage, network/interconnect
hard
Hi Robert,
Hakon Bugge presented a paper on this at ISC09. He found that SMT helped
several SPEC MPI benchmarks. (He used Platform MPI, not Open MPI.)
He did not oversubscribe, though. He just enabled SMT, which allowed the OS to
allocate spare CPU cycles during IO wait, etc.
My conclusions
Hi Tom,
as discussed, the following threads may help You?
http://www.open-mpi.org/community/lists/users/2009/02/8158.php
http://www.open-mpi.org/faq/?category=running#loading-libmpi-dynamically
With best regards,
Rainer
On Monday 13 July 2009 12:53:54 pm Evans, Thomas M. wrote:
> I've been usin
Rodrigo,
There is no support for Dolphin SCI cards in Open MPI. I'm not aware
of anybody writing the support for SCI in Open MPI either. So I guess
right now you're stuck with the Dolphin MPI ...
george.
On Jul 13, 2009, at 10:13 , Rodrigo Delgado Urzúa wrote:
Dear all,
I've some old
> Date: Mon, 13 Jul 2009 14:27:13 -0400
> From: Rainer Keller
> Subject: Re: [OMPI users] Python Binding problem with openmpi-1.3.2
> To: us...@open-mpi.org
> Cc: "Evans, Thomas M."
> Message-ID: <200907131427.13656.kel...@ornl.gov>
> Content-Type: Text/Plain; charset=iso-8859-1
>
> Hi Tom,
> as
Hi Robert,
I got inspired by your question to run a few more tests. They are
crude, and I don't have actual cpu timing information because of a
library mismatch. However:
Setup:
Xserve, 2x2.26 GHz Quad-core Intel Xeon
6.0 Gb memory 1067 MHz DDR3
Mac OS X 10.5.6
Nodes are connected with a
13 matches
Mail list logo
