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:20260422T000712Z
LOCATION:708
DTSTART;TZID=America/Denver:20231113T143000
DTEND;TZID=America/Denver:20231113T150000
UID:submissions.supercomputing.org_SC23_sess451_misc236@linklings.com
SUMMARY:An Autonomous Execution Model for GPUs:  When CPUs Take a Back Sea
 t
DESCRIPTION:Didem Unat (Koç University, Turkey)\n\nIn conventional multi-G
 PU configurations, the host manages execution, kernel launches, communicat
 ion, and synchronization, incurring unnecessary overhead. To mitigate this
 , we present a CPU-free model that delegates control to the devices themse
 lves, especially benefiting communication-intensive applications. Utilizin
 g techniques such as persistent kernels, specialized thread blocks, and de
 vice-initiated communication, we create autonomous multi-GPU code that dra
 stically reduces communication overhead. Our approach is demonstrated with
  popular solvers, including 2D/3D Jacobian stencil and Conjugate Gradient 
 (CG). We are currently developing its compiler technology, applying the mo
 del to a broader set of applications and its debugging/profiling tools.\n\
 nTag: Large Scale Systems, Middleware and System Software, Programming Fra
 meworks and System Software\n\nRegistration Category: Workshop Reg Pass\n\
 nSession Chairs: Dhabaleswar K. (DK) Panda (The Ohio State University), Ka
 rl Schulz (Advanced Micro Devices (AMD) Inc), Aamir Shafi (The Ohio State 
 University), and Hari Subramoni (The Ohio State University)\n\n
END:VEVENT
END:VCALENDAR