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:20260202T201300Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251121T080000
DTEND;TZID=America/Chicago:20251121T120000
UID:submissions.supercomputing.org_SC25_sess620_post296@linklings.com
SUMMARY:Scalable Multi-Node Multi-GPU Datalog Engine with Energy-Aware Pro
 filing
DESCRIPTION:Ahmedur Rahman Shovon (Argonne National Laboratory (ANL)) and 
 Sidharth Kumar (University of Illinois Chicago)\n\nExascale computing, pow
 ered by GPUs, is reshaping high-performance computing. Declarative languag
 es such as Datalog naturally benefit from this shift, as recursive rules c
 an be compiled into GPU-optimized relational operations. Unlike SQL, Datal
 og executes queries iteratively until a fixed point is reached, making it 
 ideal for graph mining, deductive database, and symbolic AI. Existing engi
 nes (SLOG, LogicBlox, and Soufflé) target multi-core architectures and lac
 k support for distributed multi-GPU systems. We address this gap with MNMG
 Datalog, the first multi-node, multi-GPU Datalog engine, which combines CU
 DA for intra-node parallelism with MPI for inter-node communication. Our d
 esign introduces GPU-parallel joins, scalable recursive aggregation, and i
 terative all-to-all communication strategies. To assess performance and ef
 ficiency, we developed Powerlog, the first GPU-based Datalog engine energy
  profiler. Experiments on Argonne’s Polaris supercomputer show up to 32× s
 peedups over state-of-the-art distributed engines and reveal tradeoffs bet
 ween scaling and energy use, establishing a foundation for energy-aware de
 clarative analytics at scale.\n\nTag: Research & ACM SRC Posters\n\nRegist
 ration Category: Technical Program Reg Pass\n\nSession Chairs: Kento Sato 
 (RIKEN Center for Computational Science (R-CCS)); Anja Gerbes (Georg-Augus
 t-Universität Göttingen); and Chris Schlipalius (Pawsey Supercomputing Res
 earch Centre; Commonwealth Scientific and Industrial Research Organisation
  (CSIRO), Australia)\n\n
END:VEVENT
END:VCALENDAR