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:20181221T160910Z
LOCATION:C147/148/154
DTSTART;TZID=America/Chicago:20181114T133000
DTEND;TZID=America/Chicago:20181114T150000
UID:submissions.supercomputing.org_SC18_sess299_pan112@linklings.com
SUMMARY:Reconfigurable Computing for HPC: Will It Make It this Time?
DESCRIPTION:Panel\nTech Program Reg Pass\n\nReconfigurable Computing for H
 PC: Will It Make It this Time?\n\nCappello, Hoefler, Sano, Gokhale, Putnam
 ...\n\nReconfigurable computing has been adopted in many domains requiring
  fast computing with a relatively low power budget. It has been recently i
 ntroduced in large-scale systems such as the Cloud and extreme-scale data 
 centers. The end of Moore's law and the introduction of devices with excep
 tional floating point computing capabilities make reconfigurable computing
  more attractive than ever for HPC. Many questions are open.  How to progr
 am efficiently reconfigurable devices at high level?  Where to put the rec
 onfigurable devices (compute node, network, storage)?  What algorithms/dat
 a representation provide advantage for reconfigurable devices over CPUs an
 d GPUs?  What metrics should be used to measure performance of reconfigura
 ble devices and to compare with CPUs and GPUs?  The panel will explore the
 se questions and discuss why reconfigurable computing did not succeed in H
 PC in the past and why it could make it this time. The panelists will be r
 econfigurable computing experts from industry and academia.
URL:https://sc18.supercomputing.org/presentation/?id=pan112&sess=sess299
END:VEVENT
END:VCALENDAR