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:20240626T180034Z
LOCATION:3004\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20240626T141500
DTEND;TZID=America/Los_Angeles:20240626T143000
UID:dac_DAC 2024_sess145_RESEARCH812@linklings.com
SUMMARY:CAMO: Correlation-Aware Mask Optimization with Modulated Reinforce
 ment Learning
DESCRIPTION:Research Manuscript\n\nXiaoxiao Liang (The Hong Kong Universit
 y of Science and Technology (Guangzhou)), Haoyu Yang (NVIDIA), Kang Liu (H
 uazhong University of Science and Technology), Bei Yu (The Chinese Univers
 ity of Hong Kong), and Yuzhe Ma (The Hong Kong University of Science and T
 echnology (Guangzhou))\n\nOptical proximity correction (OPC) is a vital st
 ep to ensure printability in modern VLSI manufacturing. Various OPC approa
 ches have been proposed, which are typically data-driven and hardly involv
 e particular considerations of the OPC problem, leading to potential perfo
 rmance bottlenecks. In this paper, we propose CAMO, a reinforcement learni
 ng-based OPC system that integrates important principles of the OPC proble
 m. CAMO explicitly involves the spatial correlation among the neighboring 
 segments and an OPC-inspired modulation for movement action selection. Exp
 eriments are conducted on via patterns and metal patterns. The results dem
 onstrate that CAMO outperforms state-of-the-art OPC engines from both acad
 emia and industry.\n\nTopic: Design\n\nKeyword: Design for Manufacturabili
 ty and Reliability\n\nSession Chairs: Shao-Yun Fang (National Taiwan Unive
 rsity of Science and Technology) and Biying Xu (The Hong Kong University o
 f Science and Technology (Guangzhou))
END:VEVENT
END:VCALENDAR
