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:20260422T143138Z
LOCATION:B310
DTSTART;TZID=America/New_York:20241117T105500
DTEND;TZID=America/New_York:20241117T112000
UID:submissions.supercomputing.org_SC24_sess737_ws_ia104@linklings.com
SUMMARY:xBS-GNN: Accelerating Billion-Scale GNN Training on FPGA
DESCRIPTION:Yi-Chien Lin (University of Southern California (USC)), Zhijie
  Xu (University of Michigan), and Viktor Prasanna (University of Southern 
 California (USC))\n\nGraph Neural Networks (GNNs) have been used in a vari
 ety of challenging applications. However, training GNN models is time-cons
 uming as it incur high volume of irregular data accessing due to its graph
 -structured input data; such a challenge is further exacerbated in real-wo
 rld applications as they often involve large-scale graphs with over billio
 ns of edges. Most existing GNN accelerators cannot scale to billion-scale 
 graphs due to memory limitation. We propose xBS-GNN, an accelerator optimi
 zed for billion-scale GNN training. To achieve high training throughput, x
 BS-GNN jointly exploits several optimizations, including (1) a novel data 
 placement policy, along with (2) a vertex-renaming technique and memory-ef
 ficient lookup table design for fast data retrieval, and (3) a feature qua
 ntization mechanism to reduce memory traffic. We evaluate xBS-GNN on three
  large datasets. xBS-GNN achieves up to 8.39x speedup over a widely-used G
 PU baseline and up to 5.13x speedup over a state-of-the-art GNN training a
 ccelerator.\n\nTag: Graph Algorithms, Heterogeneous Computing, Programming
  Frameworks and System Software\n\nRegistration Category: Workshop Reg Pas
 s\n\nSession Chairs: Michela Becchi (North Carolina State University); Joh
 n Feo (Pacific Northwest National Laboratory (PNNL)); Antonino Tumeo (Paci
 fic Northwest National Laboratory (PNNL)); and Ana Lucia Varbanescu (Unive
 rsity of Twente, Netherlands; University of Amsterdam, Netherlands)\n\n
END:VEVENT
END:VCALENDAR