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:20181221T160905Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181114T083000
DTEND;TZID=America/Chicago:20181114T170000
UID:submissions.supercomputing.org_SC18_sess323_post188@linklings.com
SUMMARY:FeatherCNN: Fast Inference Computation with TensorGEMM on ARM Arch
 itectures
DESCRIPTION:Poster\nTech Program Reg Pass, Exhibits Reg Pass\n\nFeatherCNN
 : Fast Inference Computation with TensorGEMM on ARM Architectures\n\nLan, 
 Meng, Hundt, Schmidt, Deng...\n\nThis poster presents a fast inference com
 putation library for ARM architecture named as CNNForward. CNNForward is t
 rying to improve the efficiency of inference computation for convolutional
  neural networks on ARM-based multi-core and many-core architectures using
  both mathematical formula reconstruction/simplification and in-depth NEON
  instruction optimization. Experimental results reveal that, forward compu
 tation for VGG-16 on a server with 64 ARM A72 cores, CNNForward can scale 
 up to 32 cores with an parallel efficiency of 33%, and achieve 35.4x, 8.7x
  and 10.6x speedup over Caffe+OpenBlas, Caffe2+Eigen and Caffe2+NNPACK, re
 spectively.
URL:https://sc18.supercomputing.org/presentation/?id=post188&sess=sess323
END:VEVENT
END:VCALENDAR