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:20250626T233526Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241120T100000
DTEND;TZID=America/New_York:20241120T170000
UID:submissions.supercomputing.org_SC24_sess533_post137@linklings.com
SUMMARY:GNN-RL: An Intelligent HPC Resource Scheduler
DESCRIPTION:Kyrian Chinemeze Adimora and Hongyang Sun (University of Kansa
 s)\n\nEfficient resource allocation in high-performance computing (HPC) en
 vironments is crucial for optimizing utilization, minimizing make-span, an
 d enhancing throughput. We propose GNN-RL, a novel intelligent scheduler t
 hat leverages a hybrid Graph Neural Network and Reinforcement Learning mod
 el, learning from historical workload data to implement optimal scheduling
  policies. Experimental results show that GNN-RL significantly outperforms
  conventional methods. Compared to the First-Come-First-Served (FCFS) base
 line, GNN-RL achieves a 2.1-fold increase in resource utilization (84.25\%
  vs. 39.84\%), a 114-fold improvement in throughput (40,061.86 vs. 351.69 
 jobs/s), and a 114-fold reduction in make-span (4.50s vs. 513.11s). GNN-RL
  also surpasses EASY Backfilling, with 1.3 times higher resource utilizati
 on and 2 times better throughput and make-span. The fairness index remains
  consistent, indicating that GNN-RL maintains fairness while improving oth
 er metrics. Our findings suggest GNN-RL is a significant advancement in in
 telligent HPC resource management, enabling more efficient and responsive 
 computing environments.\n\nRegistration Category: Tech Program Reg Pass, E
 xhibits Reg Pass\n\nSession Chairs: Ayesha Afzal (Friedrich-Alexander Univ
 ersity, Erlangen-Nuremberg; Erlangen National High Performance Computing C
 enter); Sally Ellingson (University of Kentucky); and Alan Sussman (Univer
 sity of Maryland)\n\n
END:VEVENT
END:VCALENDAR