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:20230124T171522Z
LOCATION:C155
DTSTART;TZID=America/Chicago:20221113T103000
DTEND;TZID=America/Chicago:20221113T105200
UID:submissions.supercomputing.org_SC22_sess428_ws_p3hpc121@linklings.com
SUMMARY:Understanding Strong Scaling on GPUs Using Empirical Performance S
 aturation Size
DESCRIPTION:Workshop\n\nUnderstanding Strong Scaling on GPUs Using Empiric
 al Performance Saturation Size\n\nEberius, Rogers, Roth\n\nThe roofline mo
 del provides a concise overview of the maximum performance capabilities of
  a given computer system through a combination of peak memory bandwidth an
 d compute performance rates. The increasing complexity of scheduling and c
 aches in recent GPUs, however, has introduced complicated performance vari
 ability that is not captured by arithmetic intensity alone. This work exam
 ines the effect of problem size and GPU launch configurations on roofline 
 performance for V100, A100, MI100, and MI250X graphics processing units. W
 e introduce an extended roofline model that takes problem size into accoun
 t, and find that strong scaling on GPUs can be characterized by “saturatio
 n problem sizes” as additional key metrics. Saturation problem sizes break
  up a plot of GPU performance vs. problem size into three distinct perform
 ance regimes– size-limited, cache-bound, and DRAM-bound. With our extended
  roofline model, we are able to provide a robust view of these performance
  regimes across recent GPU architectures.\n\nSession Format: Recorded\n\nT
 ag: Performance Portability\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR