Parallelization of MATLAB for Euro50 integrated modeling
(2004) 5497. p.604-610- Abstract
- MATLAB and its companion product Simulink are commonly used tools insystems modelling and other scientific disciplines. A cross-disciplinaryintegrated MATLAB model is used to study the overall performance of theproposed 50m optical and infrared telescope, Euro50. However thecomputational requirements of this kind of end-to-end simulation of thetelescope's behaviour, exceeds the capability of an individualcontemporary Personal Computer. By parallelizing the model, primarily ona functional basis, it can be implemented across a Beowulf cluster ofgeneric PCs. This requires MATLAB to distribute in some way data andcalculations to the cluster nodes and combine completed results. Therehave been a number of attempts to produce toolkits to allow... (More)
- MATLAB and its companion product Simulink are commonly used tools insystems modelling and other scientific disciplines. A cross-disciplinaryintegrated MATLAB model is used to study the overall performance of theproposed 50m optical and infrared telescope, Euro50. However thecomputational requirements of this kind of end-to-end simulation of thetelescope's behaviour, exceeds the capability of an individualcontemporary Personal Computer. By parallelizing the model, primarily ona functional basis, it can be implemented across a Beowulf cluster ofgeneric PCs. This requires MATLAB to distribute in some way data andcalculations to the cluster nodes and combine completed results. Therehave been a number of attempts to produce toolkits to allow MATLAB to beused in a parallel fashion. They have used a variety of techniques. Herewe present findings from using some of these toolkits and proposedadvances. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/528447
- author
- Browne, Michael ; Andersen, Torben LU ; Enmark, Anita LU ; Moraru, Dan LU and Shearer, Andrew
- organization
- publishing date
- 2004
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Modeling and Systems Engineering for Astronomy (Proceedings of the SPIE)
- editor
- Craig, Simon C. and Cullum, Martin J.
- volume
- 5497
- pages
- 604 - 610
- publisher
- SPIE
- external identifiers
-
- scopus:10444225640
- ISBN
- 0-8194-5429-X
- DOI
- 10.1117/12.551317
- language
- English
- LU publication?
- yes
- id
- 361cf5e2-eb5e-4d15-8533-a4f32fef85ed (old id 528447)
- date added to LUP
- 2016-04-04 12:20:28
- date last changed
- 2024-01-13 04:33:27
@inproceedings{361cf5e2-eb5e-4d15-8533-a4f32fef85ed, abstract = {{MATLAB and its companion product Simulink are commonly used tools insystems modelling and other scientific disciplines. A cross-disciplinaryintegrated MATLAB model is used to study the overall performance of theproposed 50m optical and infrared telescope, Euro50. However thecomputational requirements of this kind of end-to-end simulation of thetelescope's behaviour, exceeds the capability of an individualcontemporary Personal Computer. By parallelizing the model, primarily ona functional basis, it can be implemented across a Beowulf cluster ofgeneric PCs. This requires MATLAB to distribute in some way data andcalculations to the cluster nodes and combine completed results. Therehave been a number of attempts to produce toolkits to allow MATLAB to beused in a parallel fashion. They have used a variety of techniques. Herewe present findings from using some of these toolkits and proposedadvances.}}, author = {{Browne, Michael and Andersen, Torben and Enmark, Anita and Moraru, Dan and Shearer, Andrew}}, booktitle = {{Modeling and Systems Engineering for Astronomy (Proceedings of the SPIE)}}, editor = {{Craig, Simon C. and Cullum, Martin J.}}, isbn = {{0-8194-5429-X}}, language = {{eng}}, pages = {{604--610}}, publisher = {{SPIE}}, title = {{Parallelization of MATLAB for Euro50 integrated modeling}}, url = {{http://dx.doi.org/10.1117/12.551317}}, doi = {{10.1117/12.551317}}, volume = {{5497}}, year = {{2004}}, }