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:20260924T172456Z
LOCATION:B309
DTSTART;TZID=America/New_York:20241120T140000
DTEND;TZID=America/New_York:20241120T143000
UID:submissions.supercomputing.org_SC24_sess379_pap563@linklings.com
SUMMARY:MCBound: an Online Framework to Characterize and Classify Memory/C
 ompute-bound HPC Jobs
DESCRIPTION:Francesco Antici, Andrea Bartolini, Zeynep Kiziltan, and Ozalp
  Babaoglu (University of Bologna, Italy) and Yuetsu Kodama (RIKEN)\n\nMode
 rn high-performance computing (HPC) systems play a fundamental role in dri
 ving scientific research, as they execute computationally intensive jobs f
 rom diverse domains. However, HPC jobs are characterized by conflicting co
 mputational requirements, which may cause inefficiency in resource usage, 
 system throughput and energy consumption. One approach to tackle this prob
 lem is to distinguish between memory/compute-bound jobs at submission time
 , to make informed decisions about their execution. In this paper, we pres
 ent MCBound, the first online data-driven framework to classify HPC jobs a
 s memory/compute-bound before execution. We propose a systematic memory/co
 mpute-bound job characterization technique, and we use it to analyze the d
 ata of 2.2 million jobs run on the Supercomputer Fugaku. We implement MCBo
 und for Fugaku and classify the jobs executed during February 2024. Our ap
 proach is proven effective, as it obtains an F1-macro average score of at 
 least 0.89, while incurring a negligible overhead on the system's operatio
 ns.\n\nTag: Fault-Tolerance, Reliability, Maintainability, and Adaptabilit
 y, Middleware and System Software, Performance Evaluation and/or Optimizat
 ion Tools, Runtime Systems\n\nRegistration Category: Tech Program Reg Pass
 \n\nSession Chair: Camille Coti (École de Technologie Supérieure)\n\n
END:VEVENT
END:VCALENDAR