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:20211208T164510Z
LOCATION:Level 2 - Lobby
DTSTART;TZID=America/Los_Angeles:20211208T180000
DTEND;TZID=America/Los_Angeles:20211208T190000
UID:dac_DAC 2021_sess244@linklings.com
SUMMARY:Late Breaking Results Posters & Networking Reception
DESCRIPTION:Late Breaking Results Poster, Networking Reception\n\nLate Bre
 aking Results: Incremental 3D Global Routing Considering Cell Movement\n\n
 Zou\n\nThis paper proposes incremental 3D global routing considering cell 
 movement and complex routing constraints to relocate cells and reroute net
 s. We first apply queue-based 3D maze routing to improve an initial routin
 g solution. Efficient multi-net-based location estimation is then presente
 d to find t...\n\n---------------------\nLate Breaking Results: Paralleliz
 ing Net Routing with cGANs\n\nUtyamishev, P.-Vaisband\n\nObstacle-avoiding
  multiterminal net routing approach is proposed. The approach is inspired 
 by deep learning image processing. The key idea is based on training a con
 ditional generative adversarial network (cGAN) to interpret a routing task
  as a graphical bitmap and consequently map it to an optimal ...\n\n------
 ---------------\nLate Breaking Results: Heterogeneous Circuit Layout Cente
 rline Extraction for Mask Verification\n\nBai\n\nParasitic inductance esti
 mation and calculation based on the extracted centerline result play an im
 portant role in mask verification. This paper formulates the centerline ex
 traction problem as a Voronoi diagram to collect centerline points. We the
 n present a graph-based invalid centerline removal me...\n\n--------------
 -------\nLate Breaking Results: Attention in Graph2Seq Neural Networks tow
 ards Push-Button Analog IC Placement\n\nMartins\n\nIn this paper, disrupti
 ve research using modern embedding techniques and an attention-based encod
 er-decoder deep learning model is conducted to automate analog layout synt
 hesis. The attention-based Graph2Seq is inherently independent of the numb
 er of devices within a circuit topology and their order...\n\n------------
 ---------\nLate Breaking Results: An Effective Legalization Algorithm for 
 Heterogeneous FPGAs with Complex Constraints\n\nHuang\n\nAn ideal legaliza
 tion method should remove all overlaps and satisfy the design rules (clock
 , routability, location and chain constraints, etc.) while minimizing both
  the average and maximum movements. This paper first identifies a virtual 
 range to cluster an instance with the location constraint and...\n\n------
 ---------------\nPhysical Adversarial Attacks of Diffractive Deep Neural N
 etworks\n\nLi, Yu\n\nDiffractive Deep Neural Network (D2NNs) can work as a
  neural network with the diffraction of light and have demonstrated signif
 icant performance improvements in energy efficiency in broad security-sens
 itive applications. In this work, we develop the first adversarial attack 
 formulations over optical...\n\n---------------------\nLate Breaking Resul
 ts: Novel Discrete Dynamic Filled Function Algorithm for Acyclic Graph Par
 titioning\n\nChen\n\nThese paper models a circuit as a directed graph and 
 considers acyclic graph partitioning to minimize edge cuts. This problem d
 iffers from the traditional problem because of the acyclicity constraint. 
 Unlike traditional heuristics that tend to be trapped in local minima, we 
 present a novel discrete ...\n\n\nVirtual Program: Presented In-Person
END:VEVENT
END:VCALENDAR