BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260522T150116Z
LOCATION:C146
DTSTART;TZID=America/Chicago:20181114T103000
DTEND;TZID=America/Chicago:20181114T120000
UID:submissions.supercomputing.org_SC18_sess183@linklings.com
SUMMARY:Task-Based Programming
DESCRIPTION:Runtime-Assisted Cache Coherence Deactivation in Task Parallel
  Programs\n\nWith increasing core counts, the scalability of directory-bas
 ed cache coherence has become a challenging problem. To reduce the area an
 d power needs of the directory, recent proposals reduce its size by classi
 fying data as private or shared, and disable coherence for private data. H
 owever, existing ...\n\n\nPaul Caheny (Barcelona Supercomputing Center, Po
 lytechnic University of Catalonia); Lluc Alvarez (Barcelona Supercomputing
  Center); Mateo Valero and Miquel Moretó (Barcelona Supercomputing Center,
  Polytechnic University of Catalonia); and Marc Casas (Barcelona Supercomp
 uting Center)\n---------------------\nDynamic Tracing: Memoization of Task
  Graphs for Dynamic Task-Based Runtimes\n\nMany recent programming systems
  for both supercomputing and data center workloads generate task graphs to
  express computations that run on parallel and distributed machines. Due t
 o the overhead associated with constructing these graphs the dependence an
 alysis that generates them is often statically ...\n\n\nWonchan Lee (Stanf
 ord University), Elliott Slaughter (SLAC National Accelerator Laboratory),
  Michael Bauer and Sean Treichler (Nvidia Corporation), Todd Warszawski (S
 tanford University), Michael Garland (Nvidia Corporation), and Alex Aiken 
 (Stanford University)\n---------------------\nA Divide and Conquer Algorit
 hm for DAG Scheduling Under Power Constraints\n\nWe consider the problem o
 f scheduling a parallel computation–represented as a directed acyclic grap
 h (DAG)–on a distributed parallel system with a global resource constraint
 –specifically a global power budget–and configurable resources, allowing a
  range of different power/performance tradeoffs. Ther...\n\n\nGökalp Demir
 ci, Ivana Marincic, and Henry Hoffmann (University of Chicago)\n\nTag: Alg
 orithms, Architectures, Memory, Networks, Parallel Programming Languages, 
 Libraries, and Models, Power, Programming Systems, Scheduling\n\nRegistrat
 ion Category: Tech Program Reg Pass\n\nSession Chair: Patrick S. McCormick
  (Los Alamos National Laboratory (LANL))
END:VEVENT
END:VCALENDAR