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:20260422T000713Z
LOCATION:301-302-303
DTSTART;TZID=America/Denver:20231114T113000
DTEND;TZID=America/Denver:20231114T120000
UID:submissions.supercomputing.org_SC23_sess172_pap389@linklings.com
SUMMARY:Automated Mapping of Task-Based Programs onto Distributed and Hete
 rogeneous Machines
DESCRIPTION:Thiago S. F. X. Teixeira (Stanford University), Alexandra Henz
 inger (Massachusetts Institute of Technology (MIT)), and Rohan Yadav and A
 lex Aiken (Stanford University)\n\nIn a parallel and distributed applicati
 on, a mapping is a selection of a processor for each computation or task a
 nd memories for the data collections that each task accesses.  Finding hig
 h-performance mappings is challenging, particularly on heterogeneous hardw
 are with multiple choices for processors and memories.  We show that fast 
 mappings are sensitive to the machine, application, and input.  Porting to
  a new machine, modifying the application, or using a different input size
  may necessitate re-tuning the mapping to maintain the best possible perfo
 rmance.\n\nWe present AutoMap, a system that automatically tunes the mappi
 ng to the hardware used and finds fast mappings without user intervention 
 or code modification.  In contrast, hand-written mappings often require da
 ys of experimentation.  AutoMap utilizes a novel constrained coordinate-wi
 se descent search algorithm that balances the trade-off between running co
 mputations quickly and minimizing data movement.  AutoMap discovers mappin
 gs up to 2.41x faster than custom, hand-written mappers.\n\nTag: Heterogen
 eous Computing, Programming Frameworks and System Software, Task Paralleli
 sm\n\nRegistration Category: Tech Program Reg Pass\n\nReproducibility Badg
 es: Artifact Available, Artifact Functional, Results Reproduced\n\nSession
  Chair: Claudia Fohry (University of Kassel, Germany)\n\n
END:VEVENT
END:VCALENDAR