BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250822T115808Z
LOCATION:Room 6.0D13
DTSTART;TZID=Europe/Stockholm:20250618T120000
DTEND;TZID=Europe/Stockholm:20250618T123000
UID:submissions.pasc-conference.org_PASC25_sess173_pap106@linklings.com
SUMMARY:Leveraging Large Language Models for Code Translation and Software
  Development in Scientific Computing
DESCRIPTION:Akash Dhruv and Anshu Dubey (Argonne National Laboratory)\n\nT
 he emergence of foundational models and generative artificial intelligence
  (GenAI) is poised to transform productivity in scientific computing, espe
 cially in code development, refactoring, and translating from one programm
 ing language to another. However, because the output of GenAI cannot be gu
 aranteed to be correct, manual intervention remains necessary. Some of thi
 s intervention can be automated through task-specific tools, alongside add
 itional methodologies for correctness verification and effective prompt de
 velopment. We explored the application of GenAI in assisting with code tra
 nslation, language interoperability, and codebase inspection within a lega
 cy Fortran codebase used to simulate particle interactions at the Large Ha
 dron Collider (LHC). In the process, we developed a tool, CodeScribe, whic
 h combines prompt engineering with user supervision to establish an effici
 ent process for code conversion. In this paper, we demonstrate how CodeScr
 ibe assists in converting Fortran code to C++, generating Fortran-C APIs f
 or integrating legacy systems with modern C++ libraries, and providing dev
 eloper support for code organization and algorithm implementation. We also
  address the challenges of AI-driven code translation and highlight its be
 nefits for enhancing productivity in scientific computing workflows.\n\nDo
 main: Engineering, Life Sciences, Computational Methods and Applied Mathem
 atics\n\nSession Chair: Zhaohui Song (Zhaohui Song, Politecnico di Milano,
  Italy)\n\n
END:VEVENT
END:VCALENDAR