BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000713Z
LOCATION:607
DTSTART;TZID=America/Denver:20231112T162900
DTEND;TZID=America/Denver:20231112T164700
UID:submissions.supercomputing.org_SC23_sess435_ws_pdsw101@linklings.com
SUMMARY:GrIOt: Graph-Based Modeling of HPC Application I/O Call Stacks for
  Predictive Prefetch
DESCRIPTION:Louis-Marie Nicolas (National Institute of Advanced Technologi
 es of Brittany (ENSTA Bretagne), Bull Atos Technologies); Salim Mimouni an
 d Philippe Couvée (Bull Atos Technologies); and Jalil Boukhobza (National 
 Institute of Advanced Technologies of Brittany (ENSTA Bretagne))\n\nModern
  HPC storage systems use tiers of heterogeneous storage technologies to co
 mpromise between capacity, performance, and cost. Prefetching is a techniq
 ue used in these systems to move the right data at the right time from a s
 lower to a high-performance tier in order to improve performance with a li
 mited cost. Prefetching requires  knowledge of the application I/O pattern
 s, which can be extracted through I/O tracing tools or functions call stac
 ks. State-of-the-art solutions based on the latter focus on applications w
 ith regular I/O profiles because of scalability issues. In this paper, we 
 present an approach based on I/O call stacks that models I/O patterns for 
 both regular and irregular applications by using directed graphs. We prese
 nt two different models for prefetching with different trade-offs between 
 complexity and accuracy of the prefetch predictions. Our models were able 
 to predict I/Os with an accuracy of up to 98%, while keeping a lower overh
 ead.\n\nTag: Data Analysis, Visualization, and Storage, Data Movement and 
 Memory\n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs: Sure
 n Byna (The Ohio State University, Lawrence Berkeley National Laboratory (
 LBNL)); Jay Lofstead (Sandia National Laboratories, University of New Mexi
 co); Bing Xie (Microsoft Corporation); and Amelie Chi Zhou (Hong Kong Bapt
 ist University)\n\n
END:VEVENT
END:VCALENDAR