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:D166
DTSTART;TZID=America/Chicago:20181112T140000
DTEND;TZID=America/Chicago:20181112T143000
UID:submissions.supercomputing.org_SC18_sess173_ws_espm107@linklings.com
SUMMARY:Asynchronous Execution of Python Code on Task Based Runtime System
 s
DESCRIPTION:Mohammad Tohid, Bibek Wagle, Shahrzad Shirzad, Patrick Diehl, 
 Adrian Serio, Alireza Kheirkhahan, and Parsa Amini (Louisiana State Univer
 sity); Katy Williams (University of Arizona); Kevin Huck (University of Or
 egon); and Steven Brandt and Hartmut Kaiser (Louisiana State University)\n
 \nDespite advancements in the areas of parallel and distributed computing,
  the complexity of programming on High Performance Computing (HPC) resourc
 es has deterred many domain experts, especially in the areas of machine le
 arning and artificial intelligence (AI), from utilizing performance benefi
 ts of such systems.  Researchers and scientists favor high-productivity la
 nguages to avoid the inconvenience of programming in low-level languages a
 nd costs of acquiring the necessary skills required for programming at thi
 s level. In recent years, Python, with the support of linear algebra libra
 ries like NumPy, has gained popularity despite facing limitations which pr
 event this code from distributed runs. Here we present a solution which ma
 intains both high level programming extractions as well as parallel and di
 stributed efficiency. Phylanx, is an asynchronous array processing toolkit
  which transforms Python and NumPy operations into code which can be execu
 ted in parallel on HPC resources by mapping Python and NumPy functions and
  variables into a dependency tree executed by HPX, a general purpose, para
 llel, task-based runtime system written in C++. Phylanx additionally provi
 des introspection and visualization capabilities for debugging and perform
 ance analysis. We have tested foundations of our approach by comparing our
  implementation of widely used machine learning algorithms to accepted Num
 Py standards.\n\nTag: Accelerators, Exascale, Parallel Programming Languag
 es, Libraries, and Models\n\nRegistration Category: Workshop Reg Pass\n\nS
 ession Chairs: Dhabaleswar K. (DK) Panda (The Ohio State University), Karl
  Schulz (Advanced Micro Devices (AMD) Inc), and Hari Subramoni (The Ohio S
 tate University)\n\n
END:VEVENT
END:VCALENDAR