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:20211207T055338Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211119T103000
DTEND;TZID=America/Chicago:20211119T105000
UID:submissions.supercomputing.org_SC21_sess107_ws_corr102@linklings.com
SUMMARY:Performance of Dynamic Data Race Detection
DESCRIPTION:Workshop\n\nPerformance of Dynamic Data Race Detection\n\nProt
 ze, Thärigen, Wahle\n\nBenchmarks like DataRaceBench help evaluate the cla
 ssification quality of data race detection tools for simple memory access 
 patterns. Various publications use short-running benchmark kernels from Om
 pSRC and DRB also for performance benchmarking. Due to the short execution
  time, one-time initialization overhead dominates and results are not repr
 esentative for real codes. This paper proposes a new problem class for SPE
 C OMP 2012 designed to analyze the runtime overhead of data race detection
  tools. \n\nPrior work reported runtime overheads of 80x and higher for th
 e OpenMP data race detection tool Archer. We use our newly proposed input 
 data set to investigate the significant runtime overhead of dynamic data r
 ace detection for specific applications. With the help of performance anal
 ysis techniques, we can identify the root cause. Finally, we propose a mod
 ification of ThreadSanitizer, limiting the runtime overhead for these appl
 ications to less than 40x.\n\nTag: Online Only, Correctness, Parallel Prog
 ramming Languages and Models, Reliability and Resiliency, Software Enginee
 ring\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR