BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211208T164413Z
LOCATION:Level 2 - Lobby
DTSTART;TZID=America/Los_Angeles:20211208T180000
DTEND;TZID=America/Los_Angeles:20211208T190000
UID:dac_DAC 2021_sess244_LBR122@linklings.com
SUMMARY:Late Breaking Results: Parallelizing Net Routing with cGANs
DESCRIPTION:Late Breaking Results Poster, Networking Reception\n\nLate Bre
 aking Results: Parallelizing Net Routing with cGANs\n\nUtyamishev, P.-Vais
 band\n\nObstacle-avoiding multiterminal net routing approach is proposed. 
 The approach is inspired by deep learning image processing. The key idea i
 s based on training a conditional generative adversarial network (cGAN) to
  interpret a routing task as a graphical bitmap and consequently map it to
  an optimal routing solution represented by another bitmap. The system is 
 implemented in Python/Keras, trained on synthetically generated data, eval
 uated on typical high-resolution benchmarks, and compared with state-of-th
 e-art traditional deterministic and deep learning solutions. The proposed 
 system yields between 10.75x and 83.33x speedup over the traditional route
 r without wirelength overhead due to effective parallelization on GPU hard
 ware.\n\nVirtual Program: Presented In-Person
END:VEVENT
END:VCALENDAR