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:20260522T150121Z
LOCATION:D172
DTSTART;TZID=America/Chicago:20181112T155500
DTEND;TZID=America/Chicago:20181112T162000
UID:submissions.supercomputing.org_SC18_sess168_ws_ia112@linklings.com
SUMMARY:A Block-Oriented, Parallel, and Collective Approach to Sparse Inde
 finite Preconditioning on GPUs
DESCRIPTION:Daniel Thuerck (Technical University Darmstadt); Maxim Naumov 
 (Facebook); Michael Goesele (Graphics, Capture and Massively Parallel Comp
 uting; Technical University Darmstadt); and Michael Garland (Nvidia Corpor
 ation)\n\nLarge sparse symmetric indefinite matrices are notoriously hard 
 to precondition. They often lack  diagonal dominance and exhibit Schur-com
 plements that render zero fill-in factorization preconditioning ineffectiv
 e. Pivoting, a necessity for stable LDLt factorizations, complicates paral
 lel approaches that can take advantage of the latest massively-parallel HP
 C hardware such as GPUs. We present an approach based on ad-hoc blocking a
 nd reordering strategies that allows local, independent collective-oriente
 d processing of small dense blocks. A hybrid block-memory layout compensat
 es for irregular memory access patterns found in sparse matrices. Our meth
 od allows restricted fill-in, supernodal pivoting and a dual threshold dro
 pping strategy at little additional cost. It delivers robust preconditione
 rs that in our experiments obtain an average speedup of ~6x even for tough
  matrices from optimization problems.\n\nTag: Architectures, Data Analytic
 s, Graph Algorithms\n\nRegistration Category: Workshop Reg Pass\n\nSession
  Chairs: Vito Giovanni Castellana (Pacific Northwest National Laboratory (
 PNNL)), John Feo (Pacific Northwest National Laboratory (PNNL)), and Anton
 ino Tumeo (Pacific Northwest National Laboratory (PNNL))\n\n
END:VEVENT
END:VCALENDAR