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:20230124T171521Z
LOCATION:C155
DTSTART;TZID=America/Chicago:20221114T113000
DTEND;TZID=America/Chicago:20221114T120000
UID:submissions.supercomputing.org_SC22_sess453_ws_pmbsf106@linklings.com
SUMMARY:Going Green: Optimizing GPUs for Energy Efficiency through Model-S
 teered Auto-Tuning
DESCRIPTION:Workshop\n\nGoing Green: Optimizing GPUs for Energy Efficiency
  through Model-Steered Auto-Tuning\n\nSchoonhoven, Veenboer, van Werkhoven
 , Batenburg\n\nGraphics Processing Units (GPUs) have revolutionized the co
 mputing landscape over the past decade. However, the growing energy demand
 s of data centers and computing facilities equipped with GPUs come with si
 gnificant capital and environmental costs. The energy consumption of GPU a
 pplications greatly depend on how well they are optimized. Auto-tuning is 
 an effective and commonly applied technique of finding the optimal combina
 tion of algorithm, application, and hardware parameters to optimize perfor
 mance of a GPU application. In this paper, we introduce new energy monitor
 ing and optimization capabilities in Kernel Tuner, a generic auto-tuning t
 ool for GPU applications. These capabilities enable us to investigate the 
 difference between tuning for execution time and various approaches to imp
 rove energy efficiency, and investigate the differences in tuning difficul
 ty. Additionally, our model for GPU power consumption greatly reduces the 
 large tuning search space by providing clock frequencies for which a GPU i
 s likely most energy efficient.\n\nSession Format: Recorded\n\nTag: Applic
 ations, Architectures, Benchmarking, Exascale Computing, Modeling and Simu
 lation, Performance, Performance Portability\n\nRegistration Category: Wor
 kshop Reg Pass
END:VEVENT
END:VCALENDAR