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:20210916T132446Z
LOCATION:Lise Girardin
DTSTART;TZID=Europe/Stockholm:20210708T153000
DTEND;TZID=Europe/Stockholm:20210708T160000
UID:submissions.pasc-conference.org_PASC21_sess177_pap127@linklings.com
SUMMARY:X-Composer: Enabling Cross-Environments In-Situ Workflows between 
 HPC and Cloud
DESCRIPTION:Paper\n\nX-Composer: Enabling Cross-Environments In-Situ Workf
 lows between HPC and Cloud\n\nLi, Wang, Yan, Song\n\nAs large-scale scient
 ific simulations and big data analyses become more popular, it is increasi
 ngly more expensive to store huge amounts of raw simulation results to per
 form post-analysis. To minimize the expensive data I/O, ``in-situ'' analys
 is is a promising approach, where data analysis applications analyze the s
 imulation generated data on the fly without storing it first. However, it 
 is challenging to organize, transform, and transport data at scales betwee
 n two semantically different ecosystems due to the distinct software and h
 ardware difference. To tackle these challenges, we design and implement th
 e X-Composer framework that bridges cross-ecosystem applications to form a
 n ``in-situ'' scientific workflow by performing data filtering, aggregatio
 n, and format conversions. X-Composer reorganizes simulation data as conti
 nuous data streams and feeds them seamlessly into the Cloud-based stream p
 rocessing services to minimize I/O overheads. For evaluation, we use X-Com
 poser to set up and execute a cross-ecosystem workflow, which consists of 
 a parallel Computational Fluid Dynamics simulation running on HPC, and a d
 istributed Dynamic Mode Decomposition analysis application running on Clou
 d. Our experimental results show that X-Composer can seamlessly couple HPC
  and Big Data jobs in their own native environments, achieve good scalabil
 ity, and provide high-fidelity analytics for ongoing simulations in real-t
 ime.\n\nDomain: Emerging Applications, Engineering
END:VEVENT
END:VCALENDAR