BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240116T191700Z
LOCATION:603
DTSTART;TZID=America/Denver:20231112T145500
DTEND;TZID=America/Denver:20231112T152000
UID:submissions.supercomputing.org_SC23_sess433_ws_ships101@linklings.com
SUMMARY:Domain-Specific Energy Modeling for Drug Discovery and Magnetohydr
 odynamics Applications
DESCRIPTION:Workshop\n\nLorenzo Carpentieri, Marco D'Antonio, Kaijie Fan, 
 Luigi Crisci, and Biagio Cosenza (University of Salerno); Federico Ficarel
 li and Daniele Cesarini (CINECA); Gianmarco Accordi, Davide Gadioli, and G
 ianluca Palermo (Polytechnic University of Milan); Peter Thoman and Philip
  Salzmann (University of Innsbruck); Philipp Gschwandtner (University of I
 nnsbruck, PH3 GmbH); Markus Wippler (PH3 GmbH); Filippo Marchetti and Dani
 ele Gregori (E4); and Andrea Rosario Beccari (Dompé Farmaceutici Spa)\n\nF
 requency scaling is a well-known energy-saving power management technique 
 that modulates the device frequency to explore the trade-off between energ
 y and performance.  Higher energy savings require a frequency tuning phase
  since different applications can have different energy and time behavior 
 depending on the frequency setting.  Machine learning models can be used t
 o predict the optimal frequency configuration based on static or dynamic f
 eatures extracted from the target application.  While general-purpose ener
 gy models can be very accurate on a wide range of applications their accur
 acy can be limited by the specific input of the target application.  We pr
 esent an energy characterization that spans the fields of drug discovery a
 nd magnetohydrodynamics by using two real-world applications as case studi
 es: LiGen and Cronos.  To overcome the limitations of general-purpose appr
 oaches, we define two domain-specific energy models, which enhance the gen
 eral-purpose energy models by leveraging the target application's input pa
 rameter to increase the accuracy.\n\nTag: Artificial Intelligence/Machine 
 Learning, Energy Efficiency, Green Computing, Performance Measurement, Mod
 eling, and Tools, Sustainability\n\nRegistration Category: Workshop Reg Pa
 ss\n\nSession Chairs: Andrea Borghesi (University of Bologna; Department o
 f Electrical, Electronic and Information Engineering) and Daniela Loreti (
 University of Bologna)
END:VEVENT
END:VCALENDAR