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:20230124T171524Z
LOCATION:C141
DTSTART;TZID=America/Chicago:20221113T133000
DTEND;TZID=America/Chicago:20221113T143000
UID:submissions.supercomputing.org_SC22_sess421_misc169@linklings.com
SUMMARY:Compressed Number Representations for High-Performance Computing
DESCRIPTION:Workshop\n\nCompressed Number Representations for High-Perform
 ance Computing\n\nLindstrom\n\nThrough simulation, observation, and experi
 ments, far more data is being generated today than can reasonably be store
 d to disk and later analyzed without any form of data reduction.  Moreover
 , with deepening memory hierarchies, dwindling per-core memory bandwidth, 
 and increasing heterogeneity, even on-node data movement between memory an
 d registers makes for a significant performance bottleneck and primary sou
 rce of power consumption.  Hence, it is becoming increasingly important th
 at the bits being moved and stored in numerical computations are free of r
 edundancy and represent valuable information rather than error.\n\nThis ta
 lk gives an overview of zfp, a compressed number representation and multi-
 dimensional array container that mitigates the challenges of data movement
  using high-speed, lossy (but optionally error-bounded) compression.  zfp 
 reduces I/O time and off-line storage by 1-2 orders of magnitude depending
  on accuracy requirements, as dictated by user-set error tolerances.  Uniq
 ue among data compressors, zfp also supports constant-time read/write rand
 om access to individual array elements from compressed storage.  zfp's com
 pressed arrays appear to the user like conventional uncompressed arrays an
 d can often be integrated into existing applications with minimal code cha
 nges.  When used in numerical computations, zfp arrays provide a fine-grai
 ned knob on precision while achieving accuracy comparable to IEEE floating
  point at half the storage or less, reducing both memory footprint and ban
 dwidth.  Several application use cases are presented that demonstrate redu
 ced storage, increased accuracy, and improved performance.\n\nSession Form
 at: Recorded\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR