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:20260522T150126Z
LOCATION:D166
DTSTART;TZID=America/Chicago:20181112T154500
DTEND;TZID=America/Chicago:20181112T160000
UID:submissions.supercomputing.org_SC18_sess173_ws_espm101@linklings.com
SUMMARY:Analysis of Explicit vs. Implicit Tasking in OpenMP Using Kripke
DESCRIPTION:Charles C. Jin and Muthu Baskaran (Reservoir Labs Inc)\n\nDyna
 mic task-based parallelism has become a widely-accepted paradigm in the qu
 est for exascale computing. In this work, we deliver a non-trivial demonst
 ration of the advantages of explicit over implicit tasking in OpenMP 4.5 i
 n terms of both expressiveness and performance. We target the Kripke bench
 mark, a mini-application used to test the performance of discrete particle
  codes, and find that the dependence structure of the core “sweep” kernel 
 is well-suited for dynamic task-based systems. Our results show that expli
 cit tasking delivers a 31.7% and 8.1% speedup over a pure implicit impleme
 ntation for a small and large problem, respectively, while a hybrid varian
 t also underperforms the explicit variant by 13.1% and 5.8%, respectively.
 \n\nTag: Accelerators, Exascale, Parallel Programming Languages, Libraries
 , and Models\n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs
 : Dhabaleswar K. (DK) Panda (The Ohio State University), Karl Schulz (Adva
 nced Micro Devices (AMD) Inc), and Hari Subramoni (The Ohio State Universi
 ty)\n\n
END:VEVENT
END:VCALENDAR