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:20260202T201257Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251121T080000
DTEND;TZID=America/Chicago:20251121T120000
UID:submissions.supercomputing.org_SC25_sess620_post226@linklings.com
SUMMARY:Practical Viability of Translating Legacy Fortran Code to C++ Usin
 g Large Language Models
DESCRIPTION:Ren Imai and Masatoshi Kawai (Tohoku University), Keichi Takah
 ashi (The University of Osaka), and Hiroyuki Takizawa (Tohoku University)\
 n\nIn this study, we discuss the practicality and limitations of using cur
 rent large language models (LLMs) for automatically translating Fortran le
 gacy codes to C++, so that legacy codes written in Fortran can be moderniz
 ed to exploit the performance and features available only in C++. Moreover
 , we investigate the effectiveness of in-context learning (ICL: translatio
 n using custom prompts) and interactive translation (IT: re-translating th
 e code when a compile error occurs) at automatic Fortran-to-C++ translatio
 n. In our evaluation, the rate of producing the same results as the origin
 al code, called the output match rate, is used as the primary evaluation m
 etric. The evaluation results not only demonstrate that it is difficult ev
 en for the latest LLM to achieve 100% accurate translation at present, but
  also that ICL and IT are effective to improve the accuracy.\n\nTag: Resea
 rch & ACM SRC Posters\n\nRegistration Category: Technical Program Reg Pass
 \n\nSession Chairs: Kento Sato (RIKEN Center for Computational Science (R-
 CCS)); Anja Gerbes (Georg-August-Universität Göttingen); and Chris Schlipa
 lius (Pawsey Supercomputing Research Centre; Commonwealth Scientific and I
 ndustrial Research Organisation (CSIRO), Australia)\n\n
END:VEVENT
END:VCALENDAR
