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:20230124T171527Z
LOCATION:C146
DTSTART;TZID=America/Chicago:20221114T110000
DTEND;TZID=America/Chicago:20221114T113000
UID:submissions.supercomputing.org_SC22_sess441_ws_h2rc110@linklings.com
SUMMARY:Fast and Energy-Efficient Derivatives Risk Analysis: Streaming Opt
 ion Greeks on Xilinx and Intel FPGAs
DESCRIPTION:Workshop\n\nFast and Energy-Efficient Derivatives Risk Analysi
 s: Streaming Option Greeks on Xilinx and Intel FPGAs\n\nKlaisoongnoen, Bro
 wn, Brown\n\nWhile FPGAs have enjoyed success in accelerating high-frequen
 cy financial workloads for some time, their use for quantitative finance, 
 which is the use of mathematical models to analyze financial markets and s
 ecurities, has been far more limited to-date. In this presentation, we ext
 end our previous work accelerating the industry standard Securities Techno
 logy Analysis Center's (STAC) derivatives risk analysis benchmark STAC-A2,
  by first porting this from the existing Xilinx implementation to an Intel
  Stratix-10 FPGA, exploring the challenges encountered when moving from on
 e FPGA architecture to another and suitability of techniques. We then pres
 ent a host-data-streaming approach that ultimately outperforms our previou
 s version on a Xilinx Alveo U280 FPGA by up to 4.6 times and requiring 9 t
 imes less energy at the largest problem size, while outperforming the CPU 
 and GPU versions by up to 8.2 and 5.2 times respectively.\n\nSession Forma
 t: Recorded\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR