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:20210402T160030Z
LOCATION:Track 8
DTSTART;TZID=America/New_York:20201118T155100
DTEND;TZID=America/New_York:20201118T160200
UID:submissions.supercomputing.org_SC20_sess355_spostu116@linklings.com
SUMMARY:Predicting the Performance of Jobs in the Queue Using Machine Lear
 ning
DESCRIPTION:ACM Student Research Competition: Graduate Poster, ACM Student
  Research Competition: Undergraduate Poster\n\nPredicting the Performance 
 of Jobs in the Queue Using Machine Learning\n\nCostello, Bhatele\n\nIn rec
 ent years, several HPC facilities have started continuous monitoring of th
 eir systems and jobs to collect performance-related data for understanding
  performance and operational efficiency. Such data can be used to optimize
  the performance of individual jobs and the overall system by creating dat
 a-driven models that can predict the performance of pending jobs.  In this
  paper, we model the performance of representative control jobs using long
 itudinal system-wide monitoring data to explore the causes of performance 
 variability. Using machine learning, we are able to predict the performanc
 e of unseen jobs before they are executed based on the current system stat
 e. We analyze these prediction models in great detail to identify the feat
 ures that are dominant predictors of performance.We demonstrate that such 
 models can be application-agnostic and can be used for predicting performa
 nce of applications that are not included in training.\n\nTag: Student Pro
 gram\n\nRegistration Category: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR