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:20241120T082409Z
LOCATION:HG F 3
DTSTART;TZID=Europe/Stockholm:20240604T170000
DTEND;TZID=Europe/Stockholm:20240604T173000
UID:submissions.pasc-conference.org_PASC24_sess112_msa148@linklings.com
SUMMARY:High Performance Kernel Code Generation Using Generative AI
DESCRIPTION:Minisymposium\n\nPedro Valero-Lara, William Godoy, and Keita T
 eranishi (Oak Ridge National Laboratory); Mustafa Al Lali and Alexis Huant
 e (Texas A&M University); and Prasanna Balaprakash and Jeffery Vetter (Oak
  Ridge National Laboratory)\n\nGenerative Artificial Intelligence (AI) tec
 hnologies, such as GPT and Llama, have shown promise in facilitating code 
 generation across a variety of programming languages. However, the domain 
 of high-performance scientific computing, which demands specialized expert
 ise, presents unique challenges that have led to mixed results in terms of
  both performance and correctness when applying Generative AI. This presen
 tation will delve into our experiments with employing Generative AI to dev
 elop established high-performance computing kernels, such as AXPY, GEMV, a
 nd GEMM. We examine the deployment of these AI models across various paral
 lel programming models and languages, including C++ (with OpenMP, OpenMP O
 ffload, OpenACC, CUDA, HIP), Fortran (utilizing OpenMP, OpenMP Offload, Op
 enACC), Python (via numpy, Numba, pyCUDA, cuPy), and Julia (through Thread
 s, CUDA.jl, AMDGPU.jl). Our analysis aims to assess the efficacy and corre
 ctness of Generative AI in generating scientific computing kernels, as wel
 l as its adaptability to the specialized requirements of high-performance 
 scientific computing. Through this exploration, we intend to illuminate th
 e potential of Generative AI as a tool for innovation within scientific co
 mputing, highlighting its capabilities and identifying its challenges that
  need to be overcome to fully leverage its potential.\n\nDomain: Computati
 onal Methods and Applied Mathematics\n\nSession Chairs: Florina Ciorba (Un
 iversity of Basel) and Harshitha Menon (Lawrence Livermore National Labora
 tory)
END:VEVENT
END:VCALENDAR