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:20260422T143139Z
LOCATION:B311
DTSTART;TZID=America/New_York:20241118T102700
DTEND;TZID=America/New_York:20241118T104400
UID:submissions.supercomputing.org_SC24_sess755_ws_prot101@linklings.com
SUMMARY:Are Noise-Resilient Logical Timers Useful for Performance Analysis
 ?
DESCRIPTION:Gregor Corbin, Nour Daoud, and Bernd Mohr (Forschungszentrum J
 ülich) and Gustavo de Morais and Felix Wolf (Technical University Darmstad
 t)\n\nIn modern HPC systems, performance measurements are often disturbed 
 by noise.\nBecause repeating measurements to increase confidence in their 
 results is costly, alternative noise-resilient techniques are desirable. \
 nTherefore, we implement a logical clock, which does not rely on real-time
  measurements, in Score-P. \nWe explore several methods to model computati
 onal work with the time stamps, counting OpenMP loop iterations, LLVM basi
 c blocks/statements, or hardware counters.\nWe demonstrate the strengths a
 nd weaknesses of using logical time stamps in a trace analysis workflow wi
 th Score-P and Scalasca, by evaluating the performance problems we can fin
 d in three MPI+OpenMP mini-apps.\nBy design, logical measurements reliably
  show algorithmic issues, such as load imbalance, but cannot capture exter
 nal aspects of program execution, for example memory contention.\nIn summa
 ry, logical-time based measurements are a specialized but valuable additio
 n to the performance analyst's toolbox.\n\nTag: Debugging and Correctness 
 Tools, Performance Evaluation and/or Optimization Tools\n\nRegistration Ca
 tegory: Workshop Reg Pass\n\nSession Chairs: David Boehme (Lawrence Liverm
 ore National Laboratory (LLNL)); Kate Isaacs (University of Utah); Carmen 
 Navarrete (Leibniz Supercomputing Centre (LRZ)); and Emmanuelle Saillard (
 CEA, DAM, DIF)\n\n
END:VEVENT
END:VCALENDAR