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:20241120T082410Z
LOCATION:HG E 1.2
DTSTART;TZID=Europe/Stockholm:20240604T140000
DTEND;TZID=Europe/Stockholm:20240604T143000
UID:submissions.pasc-conference.org_PASC24_sess181_pap131@linklings.com
SUMMARY:Hybrid Parallel Tucker Decomposition of Streaming Data
DESCRIPTION:Paper\n\nSaibal De and Hemanth Kolla (Sandia National Laborato
 ries), Antoine Meyer (NexGen Analytics), Eric T. Phipps (Sandia National L
 aboratories), and Francesco Rizzi (NexGen Analytics)\n\nTensor decompositi
 ons have emerged as powerful tools of multivariate data analysis, providin
 g the foundation of numerous analysis methods. The Tucker decomposition in
  particular has been shown to be quite effective at compressing high-dimen
 sional scientific data sets. However, applying these techniques to modern 
 scientific simulation data is challenged by the massive data volumes these
  codes can produce, requiring scalable tensor decomposition methods that c
 an exploit the hybrid parallelism available on modern computing architectu
 res, as well as support in situ processing to compute decompositions as th
 ese simulations generate data. In this work, we overcome these challenges 
 by presenting a first-ever hybrid parallel and performance-portable approa
 ch for Tucker decomposition of both batch and streaming data. Our work is 
 based on the TuckerMPI package, which provides scalable, distributed memor
 y Tucker decomposition techniques, as well as prior work on a sequential s
 treaming Tucker decomposition algorithm. We extend TuckerMPI to hybrid par
 allelism through the use of the Kokkos/Kokkos-Kernels performance portabil
 ity packages, develop a hybrid parallel streaming Tucker decomposition alg
 orithm, and demonstrate performance and portability of these approaches on
  a variety of large-scale scientific data sets on both CPU and GPU archite
 ctures.\n\nDomain: Computational Methods and Applied Mathematics\n\nSessio
 n Chair: Fazeleh Kazemian (Australian National University)
END:VEVENT
END:VCALENDAR