A logic-in-memory design with 3-terminal magnetic tunnel junction function evaluators for convolutional neural networks

Analog implementations of neuromorphic circuits within digital systems are increasingly becoming attractive due to the high throughput and low energy per operation they offer. Magnetic logic devices based on spin-orbit torque offer a pathway to low-power resistive analog circuits. We present the magnetic tunnel junction (MTJ) function evaluator, a design for a logic device that evaluates nonlinear and linear functions for neural networks. We model the device and extend it into a functional design implementation in a logic-in-memory architecture in a hybrid process with magnetic device layers and 45 nm CMOS.

[1]  Geoffrey S. D. Beach,et al.  Current-induced domain wall motion , 2008 .

[2]  S. Fukami,et al.  Observation of the intrinsic pinning of a magnetic domain wall in a ferromagnetic nanowire. , 2011, Nature materials.

[3]  Luc Thomas,et al.  Discrete domain wall positioning due to pinning in current driven motion along nanowires. , 2011, Nano letters.

[4]  Michael J. Donahue,et al.  OOMMF: Object Oriented MicroMagnetic Framework , 2016 .

[5]  Tao Zhang,et al.  PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[6]  Kaushik Roy,et al.  Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets , 2015, IEEE Transactions on Biomedical Circuits and Systems.

[7]  D. Ralph,et al.  Spin-Torque Switching with the Giant Spin Hall Effect of Tantalum , 2012, Science.

[8]  Satoru Emori,et al.  Current-driven domain wall motion along high perpendicular anisotropy multilayers: The role of the Rashba field, the spin Hall effect, and the Dzyaloshinskii-Moriya interaction , 2013 .

[9]  Y. Leblebici,et al.  Large-scale neural networks implemented with non-volatile memory as the synaptic weight element: Comparative performance analysis (accuracy, speed, and power) , 2015, 2015 IEEE International Electron Devices Meeting (IEDM).

[10]  Chung Lam,et al.  A Novel Reconfigurable Sensing Scheme for Variable Level Storage in Phase Change Memory , 2011, 2011 3rd IEEE International Memory Workshop (IMW).

[11]  Yu Wang,et al.  Exploring the Precision Limitation for RRAM-Based Analog Approximate Computing , 2016, IEEE Design & Test.

[12]  S. Parkin,et al.  Chiral spin torque at magnetic domain walls. , 2013, Nature nanotechnology.

[13]  H. Ohno,et al.  Tunnel magnetoresistance of 604% at 300K by suppression of Ta diffusion in CoFeB∕MgO∕CoFeB pseudo-spin-valves annealed at high temperature , 2008 .

[14]  C. Ross,et al.  Low Energy Magnetic Domain Wall Logic in Short, Narrow, Ferromagnetic Wires , 2012, IEEE Magnetics Letters.

[15]  Madison,et al.  Interface depinning, self-organized criticality, and the Barkhausen effect. , 1995, Physical review letters.

[16]  Satoru Emori,et al.  Current-driven dynamics of Dzyaloshinskii domain walls in the presence of in-plane fields: Full micromagnetic and one-dimensional analysis , 2014 .

[17]  F. García-Sánchez,et al.  The design and verification of MuMax3 , 2014, 1406.7635.

[18]  C. A. Ross,et al.  Logic circuit prototypes for three-terminal magnetic tunnel junctions with mobile domain walls , 2016, Nature Communications.

[19]  Kaushik Roy,et al.  Hybrid Spintronic-CMOS Spiking Neural Network With On-Chip Learning: Devices, Circuits and Systems , 2015, ArXiv.

[20]  Caroline A. Ross,et al.  Micromagnetic modeling of domain wall motion in sub-100-nm-wide wires with individual and periodic edge defects , 2015 .