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:20240116T191700Z
LOCATION:601
DTSTART;TZID=America/Denver:20231113T091000
DTEND;TZID=America/Denver:20231113T100000
UID:submissions.supercomputing.org_SC23_sess443_misc151@linklings.com
SUMMARY:AI-Driven Performance Metaprogramming
DESCRIPTION:Workshop\n\nTorsten Hoefler (ETHZ)\n\nRecent advances in artif
 icial intelligence methods show the enormous potential of AI methods. The 
 underlying concepts are embedding spaces to represent real-world informati
 on. These embedding spaces have been used to represent, transform, and wor
 k with complex information in large-language models but also many other do
 mains such as climate sciences or automated driving systems. In this talk,
  we focus on embedding spaces for programs and use those primarily to asse
 ss, analyze, and improve program performance. We start by deriving a first
  embedding from textual LLWM internal representation (IR) and show that it
  successfully predicts GPU execution times of programs. We then show that 
 textual representations bear the danger is missing context and being overl
 y sensitive to specific strings. Using a graph-based representation, we im
 prove the embedding to capture relationships such as data dependencies and
  flows in LLVM IR. Finally, we discuss DaCe's performance metaprogramming 
 capabilities and it's programmable graph-based IR. We then demonstrate how
  a graph-neural network (GNN)-based embedding can capture general performa
 nce properties. Those properties form the concept of Performance Embedding
 s for Transfer Tuning and can be used to select optimization metaprograms 
 to apply to transform the IR graph.\n\nTag: Artificial Intelligence/Machin
 e Learning, Software Engineering\n\nRegistration Category: Workshop Reg Pa
 ss\n\nSession Chairs: Giorgis Georgakoudis (Lawrence Livermore National La
 boratory (LLNL)), Ignacio Laguna (Lawrence Livermore National Laboratory (
 LLNL)), and Konstantinos Parasyris (Lawrence Livermore National Laboratory
  (LLNL))
END:VEVENT
END:VCALENDAR