BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163557Z
LOCATION:603
DTSTART;TZID=America/Denver:20191118T163000
DTEND;TZID=America/Denver:20191118T170000
UID:submissions.supercomputing.org_SC19_sess122_ws_pmbsf112@linklings.com
SUMMARY:Performance Analysis of Deep Learning Workloads on Leading-Edge Sy
 stems
DESCRIPTION:Workshop\n\nPerformance Analysis of Deep Learning Workloads on
  Leading-Edge Systems\n\nRen, Yoo, Hoisie\n\nThis work examines the perfor
 mance of leading-edge systems designed for machine learning computing, inc
 luding the NVIDIA DGX-2, Amazon Web Services (AWS) P3, IBM Power System Ac
 celerated Compute Server AC922, and a consumer-grade Exxact TensorEX TS4 G
 PU server. Representative deep learning workloads from the fields of compu
 ter vision and natural language processing are the focus of the analysis. 
 Performance analysis is performed along with a number of important dimensi
 ons. Performance of the communication interconnects and large and high-thr
 oughput deep learning models are considered. Different potential use model
 s for the systems as standalone and in the cloud also are examined. The ef
 fect of various optimization of the deep learning models and system config
 urations is included in the analysis.\n\nTag: Workshop Reg Pass, Benchmark
 s, Performance, Scientific Computing, Simulation\n\nRegistration Category:
  Workshop Reg Pass, Benchmarks, Performance, Scientific Computing, Simulat
 ion
URL:https://sc19.supercomputing.org/presentation/?id=ws_pmbsf112&sess=sess
 122
END:VEVENT
END:VCALENDAR