| IDL on supercomputing cluster? [message #57723] |
Mon, 24 December 2007 02:18  |
![Sid[1] is currently offline](theme/default/images/xoffline.png.pagespeed.ic.XRkd1fkXye.png "Sid[1] is currently offline")
Sid[1]
Messages: 4
Registered: October 2005
|
Junior Member |
|
|
Hello,
I am wondering if it is at all possible for IDL to thread processes in
a supercomputing cluster.
Here are the specifications of the clusters:
1. 64 bit 16 quad AMD Opteron (Rev F) 2218 Dual Core Processors, 2.60
Ghz; total 16*16GB RAM, Loading Sharing Facility (LSF) with Simple
Linux Utility for Resource Management (SLURM)
2. 64 bit 8x4 AlphaServer ES45 68/1250 Systems, 1.25 GHz; total 76GB
RAM on 8 nodes
Thanks very much.
|
|
|
|
| Re: IDL on supercomputing cluster? [message #57817 is a reply to message #57723] |
Wed, 26 December 2007 08:19  |
edkase
Messages: 6
Registered: January 2006
|
Junior Member |
|
|
Sid,
FastDL (http://www.txcorp.com/products/FastDL/) from Tech-X
Corporation enables IDL processing in a cluster computing environment
for your Linux system. Our solution has not been ported to any Alpha-
based systems. FastDL supports two methods of parallel computing.
1) TaskDL supports task farming, a form of parallel computing where
the processes do not need to communicate while computations occur.
You may combine the results at the end. An example application would
be rendering frames of an animation in separate processes, and then
combining the sequence of frames into a movie. Other examples would
include parameter sweeps or Monte Carlo simulations.
2) mpiDL supports full interprocess communication during computations
using the Message Passing Interface (MPI). For example, you may
process tiles that are a subset of a larger image and need to
communicate values along the edges of neighboring tiles to ensure a
consistent result when the larger image is viewed in total.
If you have interest in these solutions, please contact
sales@txcorp.com. Thank you.
Ed Kase
Director of Marketing and Business Development
Tech-X Corporation
5621 Arapahoe Ave., Suite A
Boulder, CO 80303
P: 303-444-2416
F: 303-448-7756
ekase@txcorp.com
www.txcorp.com
On Dec 24, 3:18 am, Sid <malu.s...@gmail.com> wrote:
> Hello,
>
> I am wondering if it is at all possible for IDL to thread processes in
> a supercomputing cluster.
>
> Here are the specifications of the clusters:
>
> 1. 64 bit 16 quad AMD Opteron (Rev F) 2218 Dual Core Processors, 2.60
> Ghz; total 16*16GB RAM, Loading Sharing Facility (LSF) with Simple
> Linux Utility for Resource Management (SLURM)
>
> 2. 64 bit 8x4 AlphaServer ES45 68/1250 Systems, 1.25 GHz; total 76GB
> RAM on 8 nodes
>
> Thanks very much.
|
|
|
|
| Re: IDL on supercomputing cluster? [message #57821 is a reply to message #57723] |
Mon, 24 December 2007 06:51 |
David Fanning
Messages: 11724
Registered: August 2001
|
Senior Member |
|
|
Sid writes:
> I am wondering if it is at all possible for IDL to thread processes in
> a supercomputing cluster.
>
> Here are the specifications of the clusters:
>
> 1. 64 bit 16 quad AMD Opteron (Rev F) 2218 Dual Core Processors, 2.60
> Ghz; total 16*16GB RAM, Loading Sharing Facility (LSF) with Simple
> Linux Utility for Resource Management (SLURM)
>
> 2. 64 bit 8x4 AlphaServer ES45 68/1250 Systems, 1.25 GHz; total 76GB
> RAM on 8 nodes
I think you will be VERY interested in the products from
Tech-X Corporation, which allow IDL to be used in exactly
this way:
http://www.txcorp.com/products/FastDL/
Cheers,
David
--
David Fanning, Ph.D.
Fanning Software Consulting, Inc.
Coyote's Guide to IDL Programming: http://www.dfanning.com/
Sepore ma de ni thui. ("Perhaps thou speakest truth.")
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
