BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20181221T160743Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181114T083000
DTEND;TZID=America/Chicago:20181114T170000
UID:submissions.supercomputing.org_SC18_sess342_drs107@linklings.com
SUMMARY:Compiler and Runtime Based Parallelization and Optimization for GP
 Us
DESCRIPTION:Doctoral Showcase\nWorkshop Reg Pass, Tutorial Reg Pass, Tech 
 Program Reg Pass, Exhibits Reg Pass, Exhibits - Exhibit Hall Only Reg Pass
 \n\nCompiler and Runtime Based Parallelization and Optimization for GPUs\n
 \nOzen, Labarta, Ayguade\n\nThis thesis targets directive-based programmin
 g models to enhance their capability for GPU programming.  It introdu
 ces a new dialect model, which is a combination of OpenMP and OmpSs. The n
 ew model allows the use of multiple GPUs in conjunction with the heavily m
 ultithreaded capabilities in multicore processors automatically. The thesi
 s also focuses on code transformation techniques and proposes the LazyNP m
 ethod to support nested parallelism for irregular applications such as spa
 rse matrix operations, graph and graphics algorithms. Finally, the thesis 
 conducts a thorough exploration of loop scheduling methods on GPUs to find
  the advantage and disadvantages of them. It then proposes the concept of 
 optimized dynamic loop scheduling.<br /><br />The contributions of this th
 esis improve the programmability of GPUs. This has had an outstanding impa
 ct on the whole OpenMP and OpenACC language committee. Additionally, it in
 cludes contributions to widely used compilers such as Mercurium, Clang and
  PGI compilers.
URL:https://sc18.supercomputing.org/presentation/?id=drs107&sess=sess342
END:VEVENT
END:VCALENDAR

