TY - GEN
T1 - Ultra low power associative computing with spin neurons and resistive crossbar memory
AU - Sharad, Mrigank
AU - Fan, Deliang
AU - Roy, Kaushik
PY - 2013
Y1 - 2013
N2 - Emerging resistive-crossbar memory (RCM) technology can be promising for computationally-expensive analog pattern-matching tasks. However, the use of CMOS analog-circuits with RCM would result in large power-consumption and poor scalability, thereby eschewing the benefits of RCM-based computation. We propose the use of low-voltage, fast-switching, magneto-metallic 'spin-neurons' for ultra low-power non-Boolean computing with RCM. We present the design of analog associative memory for face recognition using RCM, where, substituting conventional analog circuits with spin-neurons can achieve ̃100x lower power. This makes the proposed design ̃1000× more energy-efficient than a 45nm-CMOS digital ASIC, thereby significantly enhancing the prospects of RCM based computational hardware.
AB - Emerging resistive-crossbar memory (RCM) technology can be promising for computationally-expensive analog pattern-matching tasks. However, the use of CMOS analog-circuits with RCM would result in large power-consumption and poor scalability, thereby eschewing the benefits of RCM-based computation. We propose the use of low-voltage, fast-switching, magneto-metallic 'spin-neurons' for ultra low-power non-Boolean computing with RCM. We present the design of analog associative memory for face recognition using RCM, where, substituting conventional analog circuits with spin-neurons can achieve ̃100x lower power. This makes the proposed design ̃1000× more energy-efficient than a 45nm-CMOS digital ASIC, thereby significantly enhancing the prospects of RCM based computational hardware.
KW - Emerging circuits and devices
KW - Magnets
KW - Memory
KW - Spin-transfer torque
KW - Spintronics
UR - http://www.scopus.com/inward/record.url?scp=84879876861&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84879876861&partnerID=8YFLogxK
U2 - 10.1145/2463209.2488866
DO - 10.1145/2463209.2488866
M3 - Conference contribution
AN - SCOPUS:84879876861
SN - 9781450320719
T3 - Proceedings - Design Automation Conference
BT - Proceedings of the 50th Annual Design Automation Conference, DAC 2013
T2 - 50th Annual Design Automation Conference, DAC 2013
Y2 - 29 May 2013 through 7 June 2013
ER -