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:20211207T054812Z
LOCATION:227-228
DTSTART;TZID=America/Chicago:20211118T140000
DTEND;TZID=America/Chicago:20211118T143000
UID:submissions.supercomputing.org_SC21_sess179_pap538@linklings.com
SUMMARY:HPAC: Evaluating Approximate Computing Techniques on HPC OpenMP Ap
 plications
DESCRIPTION:Paper\n\nHPAC: Evaluating Approximate Computing Techniques on 
 HPC OpenMP Applications\n\nParasyris, Georgakoudis, Menon, Diffenderfer, L
 aguna...\n\nAs we approach the limits of Moore’s law, researchers are expl
 oring new paradigms for high-performance computing (HPC) systems. Approxim
 ate computing gained traction by promising to deliver computing power. How
 ever, due to the stringent accuracy requirements of HPC scientific applica
 tions, the adoption of approximate computing methods in HPC requires an in
 -depth understanding of the application’s amenability to approximations.\n
 \nWe develop HPAC, a framework with compiler and runtime support for code 
 annotation and transformation, and accuracy vs. performance trade-off anal
 ysis of OpenMP HPC applications. We perform an analysis of the effectivene
 ss of approximate computing techniques when applied to HPC applications. T
 he results reveal possible performance gains of approximation and its inte
 rplay with parallel execution. For instance, approximation in the LULESH p
 roxy application provides substantial performance gains due to the reducti
 on of memory accesses. However, approximation in the leukocyte benchmark i
 nduces load imbalance in the parallel execution and thus limiting the perf
 ormance gains.\n\nTag: Reproducibility Badge, Algorithms, Parallel Program
 ming Systems\n\nRegistration Category: Tech Program Reg Pass\n\nAward Fina
 list: Best Reproducibility Advancement Finalist\n\nReproducibility Badges:
  Artifact Available, Artifact Functional, Results Reproduced
END:VEVENT
END:VCALENDAR