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:20211207T055342Z
LOCATION:230-231-232
DTSTART;TZID=America/Chicago:20211116T103000
DTEND;TZID=America/Chicago:20211116T120000
UID:submissions.supercomputing.org_SC21_sess177@linklings.com
SUMMARY:Efficient Deep Learning Tools
DESCRIPTION:Paper\n\nKAISA: An Adaptive Second-Order Optimizer Framework f
 or Deep Neural Networks\n\nPauloski, Huang, Huang, Venkataraman, Chard...\
 n\nKronecker-factored Approximate Curvature (K-FAC) has recently been show
 n to converge faster in deep neural network (DNN) training than stochastic
  gradient descent (SGD); however, K-FAC's larger memory footprint hinders 
 its applicability to large models. We present KAISA, a K-FAC-enabled, Adap
 table, ...\n\n---------------------\nEnable Simultaneous DNN Services Base
 d on Deterministic Operator Overlap and Precise Latency Prediction\n\nCui,
  Zhao, Chen, Zheng, Leng...\n\nWhile user-facing services experience diurn
 al load patterns, co-locating services improve the hardware utilization. P
 rior work on co-locating services on GPUs run queries sequentially, as the
  latencies of the queries are neither stable nor predictable when running 
 simultaneously. The input sensitive...\n\n---------------------\nTensor Pr
 ocessing Primitives: A Programming Abstraction for Efficiency and Portabil
 ity in Deep Learning Workloads\n\nGeorganas, Kalamkar, Avancha, Adelman, A
 nderson...\n\nDuring the past decade, novel deep learning (DL) algorithms/
 workloads and hardware have been developed to tackle a wide range of probl
 ems. Despite the advances in workload/hardware ecosystems, the programming
  methodology of DL-systems is stagnant. DL-workloads leverage either highl
 y-optimized, yet p...\n\n\nTag: Machine Learning and Artificial Intelligen
 ce\n\nRegistration Category: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR