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:20260202T201808Z
LOCATION:230
DTSTART;TZID=America/Chicago:20251120T104500
DTEND;TZID=America/Chicago:20251120T110000
UID:submissions.supercomputing.org_SC25_sess534_drs112@linklings.com
SUMMARY:Analytics4X: General-Purpose Framework for Analysis and Optimizati
 on of HPC Data Movement
DESCRIPTION:Ian Lumsden (University of Tennessee, Knoxville)\n\nAs scienti
 fic applications tackle more complex problems, data movement has also grow
 n in complexity to the point of slowing execution time and compromising ti
 me-to-solution, hindering the pace of scientific discovery. In this work, 
 we claim that, to continue to accelerate scientific discovery in the exasc
 ale era and beyond, we need a general-purpose, adaptable analytic framewor
 k for optimizing data movement in both monolithic and modular workflow-bas
 ed applications. To design this framework, we study data movement across t
 hree diverse HPC applications, deriving three key lessons learned that gui
 de the optimization of application I/O. First, profile-level performance a
 nalysis can be extended to reveal detailed data movement patterns. Second,
  middleware can substantially improve data movement efficiency for workflo
 ws by aligning I/O with workflow execution patterns. Third, matching I/O p
 hases to targeted storage systems can yield substantial performance gains,
  but requires phase-aware monitoring and tuning. We use these lessons lear
 ned to design features—fine-grained I/O filtering, middleware-level workfl
 ow analysis, and dynamic phase-to-storage mapping—that we integrate into t
 he general-purpose Analytics4X (A4X) framework to optimize performance acr
 oss a wide range of applications and I/O patterns.\n\nTag: Research & ACM 
 SRC Posters\n\nRecording: Livestreamed, Recorded\n\nRegistration Category:
  Technical Program Reg Pass\n\nSession Chairs: Yanfei Guo (Argonne Nationa
 l Laboratory (ANL)); Shirley Moore (University of Texas at El Paso); Kento
  Sato (RIKEN Center for Computational Science (R-CCS)); Chris Schlipalius 
 (Pawsey Supercomputing Research Centre; Commonwealth Scientific and Indust
 rial Research Organisation (CSIRO), Australia); and Anja Gerbes (Georg-Aug
 ust-Universität Göttingen)\n\n
END:VEVENT
END:VCALENDAR