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:20181221T160742Z
LOCATION:D221
DTSTART;TZID=America/Chicago:20181113T110000
DTEND;TZID=America/Chicago:20181113T111500
UID:submissions.supercomputing.org_SC18_sess277_drs122@linklings.com
SUMMARY:Linear Algebra Is the Right Way to Think About Graphs
DESCRIPTION:Doctoral Showcase\nComputational Biology, Exascale, GPUs, Grap
 h Algorithms, Linear Algebra, Machine Learning, Sparse Computation, Worksh
 op Reg Pass, Tutorial Reg Pass, Tech Program Reg Pass, Exhibits Reg Pass, 
 Exhibits - Exhibit Hall Only Reg Pass, Doctoral Showcase\n\nLinear Algebra
  Is the Right Way to Think About Graphs\n\nYang, Owens, Buluc\n\nGraph alg
 orithms are challenging to implement on new accelerators such as GPUs. To 
 address this problem, GraphBLAS is an innovative on-going effort by the gr
 aph analytics community to formulate graph algorithms as sparse linear alg
 ebra, so that they can be expressed in a performant, succinct and in a bac
 kend-agnostic manner. Initial research efforts in implementing GraphBLAS o
 n GPUs for graph processing and analytics have been promising, but challen
 ges such as feature-incompleteness and poor performance still exist compar
 ed to their vertex-centric ("think like a vertex") graph framework counter
 parts. For our thesis, we propose a multi-language graph framework aiming 
 to simplify the development of graph algorithms, which 1) provides a multi
 -language GraphBLAS interface for the end-users to express, develop, and r
 efine graph algorithms more succinctly than existing distributed graph fra
 meworks; 2) abstracts away from the end-users performance-tuning decisions
 ; 3) utilizes the advantages of existing low-level GPU computing primitive
 s to maintain high performance.
URL:https://sc18.supercomputing.org/presentation/?id=drs122&sess=sess277
END:VEVENT
END:VCALENDAR