BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000712Z
LOCATION:507
DTSTART;TZID=America/Denver:20231112T151500
DTEND;TZID=America/Denver:20231112T154000
UID:submissions.supercomputing.org_SC23_sess431_ws_drbsd101@linklings.com
SUMMARY:What Operations Can Be Performed Directly on Compressed Arrays and
  with What Error?
DESCRIPTION:Tripti Agarwal, Harvey Dam, and Ganesh Gopalakrishnan (Univers
 ity of Utah) and Dorra Ben Khalifa and Matthieu Martel (University of Perp
 ignan, France)\n\nIn response to the rapidly escalating data movement-rela
 ted costs of computing with large matrices and tensors, several lossy comp
 ression methods have been developed that help reduce the volume of data mo
 ved. Unfortunately, all these methods require the data to be decompressed 
 before operating on the data. In this work, we develop a lossy compressor 
 called PyBlaz that supports a dozen operations directly on compressed data
  while also offering good compression ratios. PyBlaz is based on the PyTor
 ch framework, and thus can be run on CPUs or GPUs without any code changes
 . We evaluate the efficacy of PyBlaz on data sets originating in three non
 -trivial applications: shallow-water simulation, MRI segmentation, and plu
 tonium fission. Our results demonstrate that PyBlaz’s compressed-domain op
 erations achieve good scalability while incurring errors well within accep
 table limits. To our knowledge, this is the first such lossy compressor th
 at supports compressed-domain operations in the realm of handling scientif
 ic datasets.\n\nTag: Data Analysis, Visualization, and Storage, Data Compr
 ession\n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs: Shen
 g Di (Argonne National Laboratory (ANL), University of Chicago); Dingwen T
 ao (Institute of Computing Technology, Chinese Academy of Sciences; Univer
 sity of Chinese Academy of Sciences); Ana Gainaru (Oak Ridge National Labo
 ratory (ORNL)); Jieyang Chen (University of Oregon); Shadi Ibrahim (French
  Institute for Research in Computer Science and Automation (INRIA)); and X
 in Liang (Oregon State University)\n\n
END:VEVENT
END:VCALENDAR