BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T143139Z
LOCATION:B312
DTSTART;TZID=America/New_York:20241117T110000
DTEND;TZID=America/New_York:20241117T113000
UID:submissions.supercomputing.org_SC24_sess739_ws_ss112@linklings.com
SUMMARY:Increasing Energy Efficiency of Astrophysics Simulations Through G
 PU Frequency Scaling
DESCRIPTION:Osman Seckin Simsek (University of Basel, Switzerland); Jean-G
 uillaume Piccinali (Swiss National Supercomputing Centre (CSCS)); and Flor
 ina Ciorba (University of Basel, Switzerland)\n\nThe growing demand for HP
 C necessitates significant energy consumption, posing a sustainability cha
 llenge for HPC centers, users, and society, especially\ndue to stricter en
 vironmental regulations. While efforts exist to reduce overall system ener
 gy consumption, optimizations\nfor GPU-based workloads, has received insuf
 ficient attention for workload-specific energy-efficiency optimizations. T
 his work addresses this issue by proposing\ndynamic approaches to increase
  energy-efficiency by controlling the GPU frequency dynamically through co
 de instrumentation.\nWe further investigate\nthe energy-performance trade-
 off by comparing both static and dynamic GPU frequency scaling strategies 
 as well as DVFS within SPH-EXA, a newly\ndeveloped, open-source, and GPU-c
 entric simulation framework\nspecializing in astrophysical simulations. Ou
 r\nfindings demonstrate that code instrumentation enables detailed\nenergy
  consumption acquisition beyond traditional HPC system\nmonitoring, while 
 dynamic frequency scaling of computational\nkernels achieves energy reduct
 ion with limited performance loss.\nThis approach empowers researchers to 
 develop more sustainable\nlarge-scale scientific simulations running mainl
 y on GPUs.\n\nTag: Energy Efficiency, HPC Infrastructure, Sustainability\n
 \nRegistration Category: Workshop Reg Pass\n\nSession Chairs: Cate Berard 
 (US Department of Energy); James H. Rogers (Oak Ridge National Laboratory 
 (ORNL)); Fumiyoshi Shoji (RIKEN Center for Computational Science (R-CCS), 
 Center for Computational Science); Michèle Weiland (EPCC, The University o
 f Edinburgh; The University of Edinburgh); and Mike Woodacre (Hewlett Pack
 ard Enterprise (HPE))\n\n
END:VEVENT
END:VCALENDAR