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:20260402T024533Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20250623T180000
DTEND;TZID=America/Los_Angeles:20250623T190000
UID:dac_DAC 2025_sess287_LBR115@linklings.com
SUMMARY:Late Breaking Results: Hybrid Logic Optimization with Predictive S
 elf-Supervision
DESCRIPTION:Rongliang Fu (The Chinese University of Hong Kong); Ran Zhang 
 (Institute of Computing Technology, Chinese Academy of Sciences); Ziyang Z
 heng, Zhengyuan Shi, and Yuan Pu (The Chinese University of Hong Kong); Ju
 nying Huang (Institute of Computing Technology, Chinese Academy of Science
 s); and Qiang Xu and Tsung-Yi Ho (The Chinese University of Hong Kong)\n\n
 Hybrid optimization is an emerging approach in logic synthesis, focusing o
 n applying diverse optimization methods to different parts of a logic circ
 uit. This paper analyzes the relationship between each vertex and its corr
 esponding optimization method. We extract a subgraph centered on each vert
 ex and quantify the logic optimization results of these subgraphs as verte
 x features. Based on these features, we propose a circuit partitioning met
 hod to cluster the logic circuit, enabling the final optimized circuit to 
 be constructed by merging clusters optimized with their respective methods
 . Additionally, we introduce a self-supervised prediction model to efficie
 ntly obtain vertex features. The experimental results targeting LUT mappin
 g demonstrate that our method achieves improvements of 8.48\% in area and 
 9.81\% in delay compared to the state-of-the-art.\n\n
END:VEVENT
END:VCALENDAR