1 / 3

Computing R&D for LHCb upgrade

Computing R&D for LHCb upgrade. Computing for LHCb upgrade detector is an order of magnitude larger scale than LHCb today c.f. Atlas or Alice today Computing resources scarce, unlikely to scale Need R&D to meet the challenge Examples of R&D:

frieda
Download Presentation

Computing R&D for LHCb upgrade

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. Computing R&D for LHCb upgrade • Computing for LHCb upgrade detector is an order of magnitude larger scale than LHCb today • c.f. Atlas or Alice today • Computing resources scarce, unlikely to scale • Need R&D to meet the challenge • Examples of R&D: • Evolution of physics software framework (Gaudi) to support multi-core CPU, GPU etc. • c.f. PH-SFT initiatives • Large database technology • Support order of magnitude more metadata • Support likely changes to computing model – e.g. data mining • Scale production system (Dirac) to order of magnitude more jobs/files • Explore new ideas for computing model • e.g. dynamic data placement, c.f. WLCG activities

  2. PH-LBC offline and LHCb upgrade • Current PH-LBC offline computing manpower fully committed to support LHCb data analysis • Offline production activities • Software consolidation and optimisation activities • Physics software coordination • Including for use in LHCb upgrade studies • None of above likely to reduce during 2013-2014 shutdown • Must take leading role in upgrade R&D • LHCb computing expertise concentrated at CERN • Junior manpower (students, young postdocs) available in the collaboration, but cannot work in isolation • Very few experienced computing staff who can supervise them • Long term interest of the group • Would require strengthening of PH-LBC staff • Several LDs to lead new R&D activities • And share existing support activities so that existing staff can also participate effectively in R&D

  3. Needed manpower • Existing manpower fully committed to coordinating computing operations of existing experiment • Injection of new manpower needed to share coordination of operations activities and allow CERN group to take leading role in R&D • Unlikely that this new qualified manpower can be found within existing collaboration • On the assumption that no help is forthcoming from collaboration: • CERN group would need a minimum of 2 new LDs from 2013 to coordinate upgrade R&D • Would bring the LBC offline team to the same strength as it was in ~2002, when we were developing the Gaudi framework but did not have to support a running experiment. • Would also need to increase the student and applied fellow allocations, by ~2 students and ~1 fellow.

More Related