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:20181221T160727Z
LOCATION:D168
DTSTART;TZID=America/Chicago:20181112T105500
DTEND;TZID=America/Chicago:20181112T112000
UID:submissions.supercomputing.org_SC18_sess140_ws_isav116@linklings.com
SUMMARY:PaDaWAn: a Python Infrastructure for Loosely Coupled In Situ Workf
 lows
DESCRIPTION:Workshop\nData Analytics, Data Management, Visualization, Work
 shop Reg Pass\n\nPaDaWAn: a Python Infrastructure for Loosely Coupled In S
 itu Workflows\n\nCapul, Morais, Lekien, Perache\n\nThis paper presents PaD
 aWAn, an infrastructure written in Python to provide loosely coupled in si
 tu capabilities to accelerate file-based simulation workflows.  It provide
 s services for in-memory data exchange between applications and a simple c
 onfiguration model to switch from a file-based workflow to a loosely coupl
 ed in situ workflow. The infrastructure is currently based on CEA-DAM Herc
 ule parallel I/O library by providing an ABI-compatible library to interce
 pt simulation data in a transparent way and to facilitate integration into
  existing simulation codes and tools. PaDaWAn implements a producer-consum
 er pattern with buffering of data in an in-memory staging service with aut
 omatic memory management and running on dedicated resources.\n\nWe describ
 e the key design decisions and main architectural features, and share the 
 lessons learned from the development of the infrastructure and from test r
 uns on two production-like workflow cases. We conclude on the perspectives
  for our infrastructure.
URL:https://sc18.supercomputing.org/presentation/?id=ws_isav116&sess=sess1
 40
END:VEVENT
END:VCALENDAR