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:20260522T150118Z
LOCATION:D170
DTSTART;TZID=America/Chicago:20181112T111000
DTEND;TZID=America/Chicago:20181112T113000
UID:submissions.supercomputing.org_SC18_sess169_ws_daac101@linklings.com
SUMMARY:DiG: Enabling Out-of-Band Scalable High-Resolution Monitoring for 
 Data-Center Analytics, Automation, and Control
DESCRIPTION:Antonio Libri (ETH Zurich), Andrea Bartolini (University of Bo
 logna), and Luca Benini (ETH Zurich)\n\nData centers are increasing in siz
 e and complexity, and we need scalable approaches to support their automat
 ed analysis and control. Performance, power consumption and reliability ar
 e their key "vital signs". State-of-the-Art monitoring systems provide bui
 lt-in tools to collect performance measurements, and custom solutions to g
 et insight on their power consumption. However, with the increase in measu
 rement resolution (in time and space) and the ensuing huge amount of measu
 rement data to handle, new challenges arise, such as bottlenecks on the ne
 twork bandwidth, storage and software overhead on the monitoring units. To
  face these challenges we propose a novel monitoring platform for data cen
 ters, which enables real-time high-resolution profiling (i.e., all availab
 le performance counters and the entire signal bandwidth of the power consu
 mption at the plug - sampling up to 20us) and analytics, both on the edge 
 (node-level analysis) and on a centralized unit (cluster-level analysis). 
 The monitoring infrastructure is completely out-of-band, scalable, technol
 ogy agnostic and low cost.\n\nTag: Build Systems, Clouds and Distributed C
 omputing, Data Analytics, Deep Learning, Education, HPC Center Planning an
 d Operations, Heterogeneous Systems, Resource Management, Scheduling, Scie
 ntific Computing, State of the Practice, Visualization, HPC, Containers, D
 atacenter, Industry, monitoring\n\nRegistration Category: Workshop Reg Pas
 s\n\nSession Chairs: Yong Chen (Texas Tech University), Tim Cockerill (Tex
 as Advanced Computing Center (TACC)), Dong Dai (University of Delaware), a
 nd Alan Sill (Texas Tech University)\n\n
END:VEVENT
END:VCALENDAR