BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160554Z
LOCATION:Track 2
DTSTART;TZID=America/New_York:20201112T103000
DTEND;TZID=America/New_York:20201112T110000
UID:submissions.supercomputing.org_SC20_sess208_ws_pmbsf114@linklings.com
SUMMARY:The Performance and Energy Efficiency Potential of FPGAs in Scient
 ific Computing
DESCRIPTION:Workshop\n\nThe Performance and Energy Efficiency Potential of
  FPGAs in Scientific Computing\n\nNguyen, Williams, Siracusa, MacLean, Doe
 rfler...\n\nHardware specialization is a promising direction for the futur
 e of digital computing. Reconfigurable technologies enable hardware specia
 lization with modest non-recurring engineering cost. In this paper, we use
  FPGAs to evaluate the benefits of building specialized hardware for numer
 ical kernels found in scientific applications. In order to properly evalua
 te performance, we not only compare Intel Arria 10 and Xilinx U280 perform
 ance against Intel Xeon, Intel Xeon Phi, and NVIDIA V100 GPUs, but we also
  extend the Empirical Roofline Toolkit (ERT) to FPGAs in order to assess o
 ur results in terms of the Roofline Model. Although FPGA performance is kn
 own to be far less than that of a GPU, we also benchmark the energy effici
 ency of each platform for the scientific kernels comparing to microbenchma
 rk and technological limits. Results show that while FPGAs struggle to com
 pete in absolute terms with GPUs on memory- and compute-intensive kernels,
  they require far less power and can deliver nearly the same energy effici
 ency.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR