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:20200129T163559Z
LOCATION:507
DTSTART;TZID=America/Denver:20191117T153000
DTEND;TZID=America/Denver:20191117T155000
UID:submissions.supercomputing.org_SC19_sess108_ws_pawatm103@linklings.com
SUMMARY:Pygion: Flexible, Scalable Task-Based Parallelism with Python
DESCRIPTION:Workshop\n\nPygion: Flexible, Scalable Task-Based Parallelism 
 with Python\n\nSlaughter, Aiken\n\nDynamic languages provide the flexibili
 ty needed to implement expressive support for task-based parallel programm
 ing constructs. We present Pygion, a Python interface for the Legion task-
 based programming system, and show that it can provide features comparable
  to Regent, a statically typed programming language with dedicated support
  for the Legion programming model. Furthermore, we show that the dynamic n
 ature of Python permits the implementation of several key optimizations (i
 ndex launches, futures, mapping) currently implemented in the Regent compi
 ler. Together these features enable Pygion code that is comparable in expr
 essiveness to Regent, but more flexible, and substantially more concise, l
 ess error prone, and easier to use than C++ Legion code. We show that, in 
 combination with high-performance kernels written in the Regent programmin
 g language, Pygion is able to achieve efficient, scalable execution on up 
 to 1024 nodes of the heterogeneous supercomputer Piz Daint.\n\nTag: Worksh
 op Reg Pass, MPI, Parallel Application Frameworks, Parallel Programming La
 nguages, Libraries, and Models, Python, Scalable Computing\n\nRegistration
  Category: Workshop Reg Pass, MPI, Parallel Application Frameworks, Parall
 el Programming Languages, Libraries, and Models, Python, Scalable Computin
 g
URL:https://sc19.supercomputing.org/presentation/?id=ws_pawatm103&sess=ses
 s108
END:VEVENT
END:VCALENDAR

