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:20240626T180033Z
LOCATION:3004\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20240626T114200
DTEND;TZID=America/Los_Angeles:20240626T120000
UID:dac_DAC 2024_sess132_RESEARCH725@linklings.com
SUMMARY:A High-Performance Stochastic Simulated Bifurcation Ising Machine
DESCRIPTION:Research Manuscript\n\nTingting Zhang (University of Alberta);
  Hongqiao Zhang, Zhengkun Yu, and Siting Liu (Shanghai Tech University); a
 nd Jie Han (University of Alberta)\n\nIsing model-based computers have rec
 ently emerged as high-performance solvers for combinatorial optimization p
 roblems (COPs). For Ising model, a simulated bifurcation (SB) algorithm se
 arches for the solution by solving pairs of differential equations. The SB
  machine benefits from massive parallelism but suffers from high energy. D
 ynamic stochastic computing implements accumulation-based operations effic
 iently. This article proposes a high-performance stochastic SB machine (SS
 BM) for solving COPs with efficient hardware. To this end, we develop a st
 ochastic SB (sSB) algorithm such that the multiply-and-accumulate (MAC) op
 eration is converted to multiplexing and addition while the numerical inte
 gration is implemented by using signed stochastic integrators (SSIs). Spec
 ifically, the sSB stochastically ternarizes position values used for the M
 AC operation. A stochastic computing SB cell (SC-SBC) is constructed by us
 ing two SSIs for area efficiency. Additionally, a binary-stochastic comput
 ing SB cell (BSC-SBC) uses one binary integrator and one SSI to achieve a 
 reduced delay. Based on sSB, an SSBM is then built by using the SC-SBC or 
 BSC-SBC as the basic building block. The designs and syntheses of two SSBM
 s with 2000 fully connected spins require at least 1.13 times smaller area
  than the state-of-the-art designs.\n\nTopic: Design\n\nKeyword: Quantum C
 omputing\n\nSession Chair: Kanad Basu (The University of Texas)
END:VEVENT
END:VCALENDAR