BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160558Z
LOCATION:Track 5
DTSTART;TZID=America/New_York:20201111T143100
DTEND;TZID=America/New_York:20201111T150000
UID:submissions.supercomputing.org_SC20_sess195_ws_mchpc102@linklings.com
SUMMARY:Hostile Cache Implications for Small, Dense Linear Solves
DESCRIPTION:Workshop\n\nHostile Cache Implications for Small, Dense Linear
  Solves\n\nDeakin, Cownie, McIntosh-Smith, Lovegrove, Smedley-Stevenson\n\
 nThe full assembly of the stiffness matrix in finite element codes can be 
 prohibitive in terms of memory footprint resulting from storing that enorm
 ous matrix. An optimisation and work around, particularly effective for di
 scontinuous Galerkin based approaches, is to construct and solve the small
  dense linear systems locally within each element and avoid the global ass
 embly entirely. The different independent linear systems can be solved con
 currently in a batched manner, however we have found that the memory subsy
 stem can show destructive behaviour in this paradigm, severely affecting t
 he performance. In this paper we demonstrate the range of performance that
  can be obtained by allocating the local systems differently, along with e
 vidence to attribute the reasons behind these differences.\n\nRegistration
  Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR