BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:FAST PARALLELIZED TRACKING ALGORITHM FOR THE MUON DETECTOR OF THE 
 CBM EXPERIMENT AT FAIR
DTSTART;VALUE=DATE-TIME:20100225T151000Z
DTEND;VALUE=DATE-TIME:20100225T153500Z
DTSTAMP;VALUE=DATE-TIME:20130521T154712Z
UID:indico-contribution-16@cern.ch
DESCRIPTION:Speakers: Mr. LEBEDEV\, Andrey (GSI\, Darmstadt / JINR\, Dubna
 )\nParticle trajectory recognition is an important and challenging task in
  the Compressed Baryonic Matter (CBM) experiment at the future FAIR accele
 rator at Darmstadt. The tracking algorithms have to process terabytes of i
 nput data produced in particle collisions. Therefore\, the speed of the tr
 acking software is extremly important for data analysis. In this contribut
 ion\, a fast parallel track reconstruction algorithm which uses available 
 features of modern processors is presented. These features comprize a SIMD
  instruction set and multithreading. The first allows to pack several data
  items into one register and to operate on all of them in parallel thus ac
 hieving more operations per cycle. The second feature enables the routines
  to exploit all available CPU cores and hardware threads. This parallelize
 d version of the tracking algorithm has been compared to the initial seria
 l scalar version which uses a similar approach for tracking. A speed up fa
 ctor of 140 was achieved (from 630 msec/event to 4.5 msec/event) for an In
 tel Core 2 Duo processor at 2.26 GHz.\n\nhttp://indico.cern.ch/contributio
 nDisplay.py?contribId=16&sessionId=12&confId=59397
LOCATION:Jaipur\, India
URL:http://indico.cern.ch/contributionDisplay.py?contribId=16&sessionId=12
 &confId=59397
END:VEVENT
END:VCALENDAR