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:20240116T190003Z
LOCATION:601
DTSTART;TZID=America/Denver:20231113T090000
DTEND;TZID=America/Denver:20231113T123000
UID:submissions.supercomputing.org_SC23_sess443@linklings.com
SUMMARY:AI Assisted Software Development for HPC (AI4DEV)
DESCRIPTION:Workshop\n\nAI-Driven Performance Metaprogramming\n\nRecent ad
 vances in artificial intelligence methods show the enormous potential of A
 I methods. The underlying concepts are embedding spaces to represent real-
 world information. These embedding spaces have been used to represent, tra
 nsform, and work with complex information in large-language models bu...\n
 \n\nTorsten Hoefler (ETHZ)\n---------------------\nAI4DEV – Morning Break\
 n---------------------\nUnlocking the Potential of Large Language Models f
 or High-Performance Computing Code\n\nHigh-Performance Computing (HPC) has
  long been the driving force behind advancements in science, engineering, 
 and beyond. Yet, realizing the full potential of HPC applications has ofte
 n been hampered by the intricate nature of programming for the underlying 
 parallel systems. In this keynote, we expl...\n\n\nGal Oren (Technion - Is
 rael Institute of Technology)\n---------------------\nMPI-RICAL: Data-Driv
 en MPI Distributed Parallelism Assistance with Transformers\n\nMessage Pas
 sing Interface (MPI) plays a crucial role in distributed memory paralleliz
 ation across multiple nodes. However, parallelizing MPI code manually, and
  specifically, performing domain decomposition, is a challenging, error-pr
 one task. In this paper, we address this problem by developing MPI-...\n\n
 \nNadav Schneider and Tal Kadosh (Ben-Gurion University of the Negev, Isra
 el; IAEC); Niranjan Hasabnis and Timothy Mattson (Intel Labs); Yuval Pinte
 r (Ben-Gurion University of the Negev, Israel); and Gal Oren (Technion - I
 srael Institute of Technology)\n---------------------\nVSCuda: LLM-Based C
 UDA Extension for Visual Studio Code\n\nSince CUDA was introduced around 1
 5 years ago, it  has developed constantly to accommodate many different fu
 nctionalities. For beginners in particular, it is already difficult rememb
 er the expected function parameters of commonly used CUDA features, let al
 one optimize their code by exploiting these ...\n\n\nBrian Chen, Nafis Mus
 takin, Alvin Hoang, Sakib Fuad, and Daniel Wong (University of California,
  Riverside)\n---------------------\nOpening Remarks\n\nOpening remarks for
  the AI4DEV Workshop\n\n\nIgnacio Laguna (Lawrence Livermore National Labo
 ratory (LLNL))\n---------------------\nLLVM in the Age of LLMs:  Machine L
 earning for IR and Optimization and More\n\nWilliam S. Moses (University o
 f Illinois)\n\nTag: Artificial Intelligence/Machine Learning, Software Eng
 ineering\n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs: Gi
 orgis Georgakoudis (Lawrence Livermore National Laboratory (LLNL)), Ignaci
 o Laguna (Lawrence Livermore National Laboratory (LLNL)), and Konstantinos
  Parasyris (Lawrence Livermore National Laboratory (LLNL))
END:VEVENT
END:VCALENDAR