BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085744Z
LOCATION:HG D 3.2
DTSTART;TZID=Europe/Stockholm:20190614T103000
DTEND;TZID=Europe/Stockholm:20190614T110000
UID:submissions.pasc-conference.org_PASC19_sess112_msa245@linklings.com
SUMMARY:torc_py: Supporting Task-Based Parallelism in Python
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Emerg
 ing Application Domains, Engineering\n\ntorc_py: Supporting Task-Based Par
 allelism in Python\n\nChatzidoukas\n\nTask-based parallelism has been esta
 blished as one of the main forms of code parallelization, where asynchrono
 us tasks are launched and distributed across the processing units of a loc
 al machine, a cluster or a supercomputer. The tasks can be either complete
 ly decoupled, corresponding to a set of independent jobs, or be part of an
  iterative algorithm where the task results are processed and drive the ne
 xt step. Typical use cases include the application of the same function to
  different data, parametric searches and algorithms used in numerical opti
 mization and Bayesian uncertainty quantification. In this work, we introdu
 ce torc_py, a platform-agnostic adaptive load balancing library that orche
 strates scheduling of multiple function evaluations on both shared and dis
 tributed memory platforms. The library is implemented on top of MPI and mu
 ltithreading and provides lightweight support for nested loops and map fun
 ctions. Experimental results using representative applications demonstrate
  the flexibility and efficiency of the proposed Python package.
END:VEVENT
END:VCALENDAR