Parallelization of scientific legacy code
| dc.creator | Hernández, Karem Briceño | |
| dc.date.accessioned | 2016-11-14T23:12:23Z | |
| dc.date.available | 2011-02-18T19:13:25Z | |
| dc.date.available | 2016-11-14T23:12:23Z | |
| dc.date.issued | 2003-12 | |
| dc.degree.department | Computer Science | en_US |
| dc.description.abstract | Presently, The National Aeronautics and Space Administration (NASA) conducts research through its Earth Observation System (EOS) to answer questions about global dynamics. The most comprehensive EOS instrument is MODIS (The Moderate-resolution Imaging Spectroradiometer) which has several data products. One of these products is MODIS LAI/FPAR (MOD 15). The algorithm for this product consists of two modules: M0DI5A1 which produces series of daily candidates LAI/FPAR data products and MOD15A2 which produces a 8-day composite to be archived. The purpose of the present work is to demonstrate that in spite of the elevated cost implied, parallelization for particular EOS applications might be worthwhile. For this, a previous analysis four years ago of tae serial M0D15A1 code was completed showing that the time may be reduced significantly. For that reason, some changes were made to the code with tae purpose of miming it on parallel. With these changes, an experimental run performed with threads demonstrated that m fact the time reduces to half of the time by using two processors m comparison with the serial version that used only one processor. Given that platforms with more than 2 processors were not readily available at that time, because of price, it is until now that we can easily perform those tests. Therefore, parallelization of this code was motivated to experiment with more processors m order to verify the level of performance that this code could attain, which is the main objective of the present work. With these experiments, it is confirmed that parallelization does improve the execution tune for this particular product but it does not scale up as it is estimated. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/2346/9922 | en_US |
| dc.language.iso | eng | |
| dc.publisher | Texas Tech University | en_US |
| dc.rights.availability | Unrestricted. | |
| dc.subject | Programming (Mathematics) | en_US |
| dc.subject | Parallel programming (Computer science) | en_US |
| dc.subject | Programming languages (Electronic computers) | en_US |
| dc.title | Parallelization of scientific legacy code | |
| dc.type | Thesis |