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:20260422T000604Z
LOCATION:DEF Concourse
DTSTART;TZID=America/Denver:20231115T100000
DTEND;TZID=America/Denver:20231115T170000
UID:submissions.supercomputing.org_SC23_sess303_rpost193@linklings.com
SUMMARY:Toward Inductive Synthesis of Compiler Heuristics:  A Case Study w
 ith Register Allocation
DESCRIPTION:Mohammad Ali and Apan Qasem (Texas State University)\n\nThere 
 have been significant advances in machine learning-driven performance mode
 ling in recent years. One key limitation of such approaches is that their 
 success depends, to a large degree, on the formulation of the outcome or o
 bjective, which is typically done by human experts. In this paper, we prop
 ose a novel approach of automatically generating new optimization heuristi
 cs using inductive program synthesis. To explore the feasibility of this a
 pproach, we investigated the graph-coloring register allocation heuristic 
 used in the state-of-the-art compilers today. In particular, we focused on
  the task of live range splitting. The results show that when using a Gene
 tic Algorithm, we can obtain splitting heuristics that are within 10% of t
 he optimal split after 202 generations.\n\nTag: Artificial Intelligence/Ma
 chine Learning, Architecture and Networks, Heterogeneous Computing, I/O an
 d File Systems, Performance Measurement, Modeling, and Tools, Post-Moore C
 omputing, Programming Frameworks and System Software, Quantum Computing\n\
 nRegistration Category: Tech Program Reg Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR