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:20260202T201249Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251120T080000
DTEND;TZID=America/Chicago:20251120T170000
UID:submissions.supercomputing.org_SC25_sess533_post182@linklings.com
SUMMARY:Optimizing Task-Driven Offloading in LLVM
DESCRIPTION:Jan Kraus, Joachim Jenke, and Christian Terboven (Chair for Hi
 gh-Performance Computing i12, RWTH Aachen University)\n\nWe investigate an
  inefficiency in the LLVM OpenMP runtime related to accelerator offloading
 . The current implementation manages asynchronous GPU tasks by polling asy
 nc handles, which introduces CPU overhead. We propose replacing this polli
 ng model with an event-driven approach that detaches target tasks by defau
 lt. In our design, each asynchronous task is associated with an event that
  is fulfilled once the GPU kernel completes, allowing the task to yield ex
 ecution. This eliminates repeated polling and reduces scheduling overhead.
  We implemented this mechanism using existing features in the LLVM OpenMP 
 runtime, relying on a host callback function provided by CUDA. Experiments
  on NVIDIA H100 GPUs show runtime improvements of up to 75% for independen
 t tasks once matrix sizes exceed 128×128, with benefits appearing at even 
 smaller sizes when task dependencies are present. For large kernels, the e
 ffect diminishes as execution time dominates.\n\nTag: Research & ACM SRC P
 osters\n\nRegistration Category: Technical Program Reg Pass\n\nSession Cha
 irs: Kento Sato (RIKEN Center for Computational Science (R-CCS)); Chris Sc
 hlipalius (Pawsey Supercomputing Research Centre; Commonwealth Scientific 
 and Industrial Research Organisation (CSIRO), Australia); and Anja Gerbes 
 (Georg-August-Universität Göttingen)\n\n
END:VEVENT
END:VCALENDAR