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:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20240626T180000
DTEND;TZID=America/Los_Angeles:20240626T190000
UID:dac_DAC 2024_sess237_RESEARCH1028@linklings.com
SUMMARY:Hybrid Stochastic Computing of Linear Time O(N) and Its In-Memory 
 Computing for High Performances
DESCRIPTION:Work-in-Progress Poster\n\nYuhao Chen, LI hongge, Xiaoyu Guo, 
 Yinjie Song, and Xinyu Zhu (Beihang University)\n\nSC reduces the complexi
 ty of arithmetic circuits but brings extra conversion cost and time comple
 xity of O(2^N), which leads to a much lower efficiency than binary. This p
 aper proposes a linear-time-complexity, O(N), and conversion-free hybrid s
 tochastic computing (HSC). Moreover, a hybrid stochastic computing in-memo
 ry method is proposed, mapping multiplication and addition of HSC into mem
 ory's enable and addressing circuit. Thus, any original memory can realize
  HSC operation without additional circuits. The experiment shows that FPGA
 -based block memory (BRAM) operating matrix multiplication reaches 1.152 T
 OPS and 17.2 TOPS/W·bit. Each 18K-BRAM provides 18 GOPS performance (INT8)
  with 8.34 mW at 600 MHz.\n\nTopic: AI, Autonomous Systems, Cloud, Design,
  EDA, Embedded Systems, IP, Security
END:VEVENT
END:VCALENDAR