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:20260202T201804Z
LOCATION:274
DTSTART;TZID=America/Chicago:20251117T111000
DTEND;TZID=America/Chicago:20251117T113000
UID:submissions.supercomputing.org_SC25_sess215_ws_ai4s121@linklings.com
SUMMARY:A Query Engine for Scientific Data Exploration using Theory, Simul
 ation, and Artificial Intelligence Models
DESCRIPTION:Abhishek Dwaraki (Hewlett Packard Enterprise Labs, Hewlett Pac
 kard Enterprise); Sreenivas. R. Sukumar, Christopher D. Rickett, Clarete R
 iana Crasta, and Harumi Kuno (Hewlett Packard Enterprise (HPE)); Michael N
 eal, Pankaj Pandey, and Ryan Yates (University of Mississippi); Karlon Wes
 t (Hewlett Packard Enterprise (HPE)); Amar Gopal Chittiboyina and Ikhlas A
 . Khan (University of Mississippi); and John L. Byrne, Sekwon Lee, and Dav
 id Emberson (Hewlett Packard Enterprise (HPE))\n\nModern scientific discov
 ery increasingly integrates simulations, data, and AI models. Existing sys
 tems rarely let scientists compose expressive queries that retrieve multi-
 modal datasets and invoke complex simulations or AI inferences. We introdu
 ce the Intelligent Data Search (IDS) framework to bridge this gap. IDS ext
 ends the Cray Graph Engine to provide a scalable in-memory datastore (feat
 ure, vector, and knowledge graph), a unified query engine combining keywor
 d, set-theoretic, and linear-algebraic operators, a model repository for U
 DFs and pre-trained AI models, and a distributed multi-tier cache for inte
 rmediate and simulation outputs. We evaluate IDS on a life-sciences workfl
 ow with the NCNPR, integrating AlphaFold, AutoDock Vina, and Smith–Waterma
 n within a single query. Results show strong HPC scaling, a complex “what-
 could-be” query executing millions of searches and thousands of inferences
  in seconds, and 5–15× end-to-end speedup from caching. IDS empowers scien
 tists to ask and iterate model-driven “what-if” questions over petascale d
 ata with minimal latency.\n\nRecording: Livestreamed, Recorded\n\nRegistra
 tion Category: Technical Program Reg Pass, Workshop Reg Pass\n\nSession Ch
 airs: Gokcen Kestor (Barcelona Supercomputing Center (BSC); University of 
 California, Merced); Dong Li (University of California, Merced); and Mural
 i Emani (Argonne National Laboratory (ANL))\n\n
END:VEVENT
END:VCALENDAR