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:20220715T000421Z
LOCATION:3002\, Level 3
DTSTART;TZID=America/Los_Angeles:20220714T143700
DTEND;TZID=America/Los_Angeles:20220714T150000
UID:dac_DAC 2022_sess140_RESEARCH108@linklings.com
SUMMARY:YOLoC: DeploY Large-Scale Neural Network by ROM-based Computing-in
 -Memory using ResiduaL Branch on a Chip
DESCRIPTION:Research Manuscript\n\nYOLoC: DeploY Large-Scale Neural Networ
 k by ROM-based Computing-in-Memory using ResiduaL Branch on a Chip\n\nChen
 , Yin, Tan, Lee, Yang...\n\nComputing-in-Memory (CiM) is a promising techn
 ology to achieve higher energy efficiency in Matrix-Vector Multiplication.
   However, existing SRAM-CiMs, suffer from limited memory density, which w
 ill weaken the advantages of CiM. We proposed a ROM-based CiM that could p
 erform MVM in a higher computable memory density array than SRAM. A fine-t
 une technology for ROM-CiM called Residual Compress is proposed to make RO
 M-CiM transfer to various tasks without retape-out. Evaluation in 28nm pro
 cess shows 10x area saving and 30% energy efficiency improvement. Our prop
 osed ROM-CiM has provided opportunities of enabling a new paradigm for fut
 ure tiny-scale embedded object detection applications.\n\nTopic: Design\n\
 nKeyword: In-memory and Near-memory Computing
END:VEVENT
END:VCALENDAR