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:20260422T000711Z
LOCATION:708
DTSTART;TZID=America/Denver:20231112T155000
DTEND;TZID=America/Denver:20231112T161000
UID:submissions.supercomputing.org_SC23_sess438_ws_corr105@linklings.com
SUMMARY:Data Race Detection Using Large Language Models
DESCRIPTION:Le Chen (Iowa State University, Lawrence Livermore National La
 boratory (LLNL)); Xianzhong Ding (University of California, Merced); Pei-H
 ung Lin and Chunhua Liao (Lawrence Livermore National Laboratory (LLNL)); 
 Murali Emani (Argonne National Laboratory (ANL)); and Tristan Vanderbrugge
 n (Lawrence Livermore National Laboratory (LLNL))\n\nLarge language models
  (LLMs) are demonstrating significant promise as an alternate strategy to 
 facilitate analyses and optimizations of high-performance computing progra
 ms, circumventing the need for resource-intensive manual tool creation. In
  this paper, we explore a novel LLM-based data race detection approach com
 bining prompting engineering and fine-tuning techniques. We create a dedic
 ated dataset named DRB-ML, which is derived from DataRaceBench, with fine-
 grain labels showing the presence of data race pairs and their associated 
 variables, line numbers, and read/write information. DRB-ML is then used t
 o evaluate representative LLMs and fine-tune open-source ones.  Our experi
 ment shows that LLMs can be a viable approach to data race detection. Howe
 ver, they still cannot compete with traditional data race detection tools 
 when we need detailed information about variable pairs causing data races.
 \n\nTag: Applications, Software Engineering\n\nRegistration Category: Work
 shop Reg Pass\n\nSession Chairs: Ignacio Laguna (Lawrence Livermore Nation
 al Laboratory (LLNL)); Cindy Rubio-González (University of California, Dav
 is); and Emmanuelle Saillard (French Institute for Research in Computer Sc
 ience and Automation (INRIA))\n\n
END:VEVENT
END:VCALENDAR