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:20260522T150115Z
LOCATION:C141/143/149
DTSTART;TZID=America/Chicago:20181113T153000
DTEND;TZID=America/Chicago:20181113T160000
UID:submissions.supercomputing.org_SC18_sess212_pap511@linklings.com
SUMMARY:HiCOO: Hierarchical Storage of Sparse Tensors
DESCRIPTION:Jiajia Li, Jimeng Sun, and Richard Vuduc (Georgia Institute of
  Technology)\n\nThis paper proposes a new storage format for sparse tensor
 s, called Hierarchical COOrdinate (HiCOO; pronounced: “haiku”). It derives
  from coordinate (COO) format, arguably the de facto standard for general 
 sparse tensor storage. HiCOO improves upon COO by compressing the indices 
 in units of sparse tensor blocks, with the goals of preserving the “mode-a
 gnostic” simplicity of COO while reducing the bytes needed to represent th
 e tensor and promoting data locality. We evaluate HiCOO by implementing a 
 single-node, multicore-parallel version of the matricized tensor-times-Kha
 tri-Rao product (MTTKRP) operation, which is the most expensive computatio
 nal core in the widely used CANDECOMP/PARAFAC decomposition(CPD) algorithm
 . This MTTKRP implementation achieves up to 23.0× (6.8× on average) speedu
 p over COO format and up to 15.6× (3.1× on average) speedup over another s
 tate-of-the-art format, compressed sparse fiber (CSF), by using less or co
 mparable storage of them. When used within CPD, we also observe speedups a
 gainst COO- and CSF-based implementations.\n\nTag: Algorithms, Graph Algor
 ithms, Linear Algebra, Machine Learning, Sparse Computation\n\nRegistratio
 n Category: Tech Program Reg Pass\n\nFinalist: BSP Finalist\n\nSession Cha
 ir: Howie Huang (George Washington University)\n\n
END:VEVENT
END:VCALENDAR