1 / 12

Group 1 Presentation

Group 1 Presentation. Mauro Barbieri Rabih Bashroush Mauro Cancian Giacinto Donvito Sven Hermann Rainer Schmidt Peter Turner. Cross-matching Astronomical Catalogues. At present the work is done using ad hoc written program running on 1 machine

bob
Download Presentation

Group 1 Presentation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Group 1 Presentation Mauro Barbieri Rabih Bashroush Mauro Cancian Giacinto Donvito Sven Hermann Rainer Schmidt Peter Turner

  2. Cross-matching Astronomical Catalogues • At present the work is done using ad hoc written program running on 1 machine • CM for an area of 5x10-4 of the total sky need about 2 hours of CPU time on a P4 2.8GHz, this translate to about 170 day of CPU • Applications : • GAIA ESA astrometric mission data validation • OMEGATRANS & RATS survey for detection of extrasolar planets • on flight image reduction for the instruments of second generation mounted on VLT at ESO • Cross Matching(CM) of astronomical sources detected at different wavelenghts and present in differents catalogs (or images) • Why need the GRID? • CE : Splitting the CM in various parallels tasks reduce the execution time • SE : The catalogs considered contains few billions of sources each • GDSE / OGSA-DAI : The catalogs are stored in differents relational databases

  3. Grid Technology Solution • GLite/MW • High-Throughput / Access more CPUs • DAG-Man • Dependencies of Jobs (Pixels) • Condor • Scheduling Jobs • GDSE / OGSA-DAI • Accessing astronomical databases • JAM / Webservices • Job Monitoring Application

  4. DAG-man 5 4 6 3 7 1 8 2 9

  5. Accessing Databases RB UI WN

  6. Prog. Exercise – Status 1/2 • Java Service -> Web Service • GT4 (WSRF) Random Case Impl. • Gilda Submission (security: no certificates installed) • OGSA-DAI • Pillar Search • Region • Pillar • Plaque • Text

  7. Prog. Exercise – Status 2/2 java -classpath $CLASSPATH Regular -8922.635 -9908.625 -8922.515 -9908.55 2000 probe26.eps http://server5.gs.unina.it:8080/PillarsOfWisdom/surface java -classpath $CLASSPATH Regular -8922.635 -9908.625 -8922.515 -9908.55 2000 probe27.eps http://server6.gs.unina.it:8080/PillarsOfWisdom/surface

  8. Contribution of Group Members • All participants in our group contributed equally to the various tasks • Java/Detection/Grid-Scheduling • Web and Grid Services • OGSA-DAI • Presentation

  9. Feedback to GS • No hard copies of material. Presentations not on-line ahead of time. • Some leading experts did not present as advertised (Foster, De Roure). • Some poor presentations (SOAP, XML, GT4 (low content)). • Reluctance to accept and accommodate feedback in first week. • Not enough 'free' time e.g. for progessive exercise ,to absorb material, and for life outside School. • Make Java ex. available before School start. • Short notice changes, some poor coordination and 'goal' shifting. • Last minute implementation (eg Web Service exercise, GT4).

  10. Feedback to GS • Hands on intro to variety of Grid and WS middleware & technologies. • Presentations by leading Grid developers and users. Some excellent. • Interesting progressive ex. culminating in transition to Grid Services. • Working and collaborating with a diverse yet cohesive group. • Considerable and impressive effort in tutorial material preparation.

  11. “… und lass ihn fliegen!”“… and set it free!” The knowledge GGFISSGC05

More Related