BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240116T185911Z
LOCATION:E Concourse
DTSTART;TZID=America/Denver:20231114T100000
DTEND;TZID=America/Denver:20231114T170000
UID:submissions.supercomputing.org_SC23_sess290_drs106@linklings.com
SUMMARY:Charged Particle Track Reconstruction Algorithms for Massively Par
 allel Systems
DESCRIPTION:Doctoral Showcase, Posters\n\nStephen Nicholas Swatman (Univer
 sity of Amsterdam, European Organization for Nuclear Research (CERN))\n\nT
 he reconstruction of the trajectories of charged particles through detecto
 r experiments is a core computational task in the domain of high-energy ph
 ysics. Upcoming upgrades to accelerators such as the Large Hadron Collider
  as well as to experiments like ATLAS threaten to render existing CPU-base
 d approaches to track reconstruction insufficient, and the use of massivel
 y parallel systems - GPGPUs in particular - is an important opportunity to
  meet future data processing requirements. In my thesis, I investigate the
  feasibility of GPGPU-based track reconstruction from performance engineer
 ing perspective: I focus on structured analysis of application performance
 , the development of statistical and analytical models of performance, met
 hods for mitigating the challenges of GPGPU programming, and the design an
 d implementation of novel track reconstruction algorithms. The key contrib
 utions of my thesis include the development of novel algorithms for hit cl
 ustering, seed finding, and combinatorial Kalman filtering, key parts of t
 he track reconstruction process. These algorithms suffer from significant 
 load imbalance and thread divergence, and I have developed a novel statist
 ical method for estimating the performance effects of this, as well as to 
 guide optimization through thread refinement and coarsening. I have develo
 ped a method for the automated design space exploration of data storage me
 thods for magnetic fields, which play a crucial role in track reconstructi
 on. Furthermore, I have developed an evolutionary method for finding layou
 ts for multi-dimensional arrays in hierarchical memory systems. My thesis 
 will be concluded by a comprehensive study of the performance of track rec
 onstruction, as guided by the aforementioned research.\n\nTag: Accelerator
 s, Applications\n\nRegistration Category: Tech Program Reg Pass, Exhibits 
 Reg Pass
END:VEVENT
END:VCALENDAR