BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:AskALCF: An Intelligent HPC User Support System in the Age of AI
DTSTART:20260826T160000Z
DTEND:20260826T170000Z
DTSTAMP:20260918T214600Z
UID:indico-event-944@events.cels.anl.gov
CONTACT:ALCFevents@alcf.anl.gov
DESCRIPTION:Register to join our August 26\, 2026\, webinar\, “AskALCF:
  An Intelligent HPC User Support System in the Age of AI\,” to learn ho
 w AI can streamline HPC user support by bringing together facility documen
 tation\, scheduler manuals\, programming-model references\, and accumulate
 d support knowledge into a unified\, continuously improving system.\nHPC u
 ser support is challenging because the information users need is often dis
 tributed across many sources\, and solutions developed through support tic
 kets do not always make their way back into the documentation. AskALCF is 
 designed to close that gap by exposing a shared knowledge base spanning AL
 CF\, OLCF\, NERSC\, and LLNL documentation\, along with PBS and Slurm sche
 duler resources and CUDA\, oneAPI\, SYCL\, and HIP-ROCm programming refere
 nces\, through a chatbot interface accessible to both users and AI coding 
 assistants.\nBeyond answering questions\, AskALCF powers an autonomous sup
 port pipeline that can triage difficult queries and incoming tickets\, rep
 roduce issues on real systems\, compare results against the knowledge base
  to identify documentation gaps\, and generate human-reviewed pull request
 s to improve support materials. In this way\, the system becomes more effe
 ctive with every resolved case.\nIn this webinar\, Huihuo Zheng of the Arg
 onne Leadership Computing Facility will present the AskALCF architecture\,
  demonstrate its capabilities live on real ALCF systems\, and share lesson
 s learned about building trustworthy AI-driven support for leadership-clas
 s computing environments.\nHuihuo Zheng is a computer scientist at the Arg
 onne Leadership Computing Facility (ALCF)\, Argonne National Laboratory\, 
 where his current work centers on agentic AI for high-performance computin
 g — AI agents that plan\, build\, run\, and debug scientific workloads a
 cross DOE leadership systems\, and that automate HPC user support. His bro
 ader research spans scalable deep-learning training and AI/ML for scientif
 ic computing. He holds a Ph.D. in Physics.\n\nhttps://events.cels.anl.gov/
 event/944/
IMAGE;VALUE=URI:https://events.cels.anl.gov/event/944/logo-3104902259.png
LOCATION:Online
URL:https://events.cels.anl.gov/event/944/
END:VEVENT
END:VCALENDAR