Error-Resilient Spintronics via the Shannon- Inspired Model of Computation

The energy and delay reductions from CMOS scaling have stagnated, motivating the search for a CMOS replacement. Spintronic devices are one of the promising beyond-CMOS alternatives. However, they exhibit high switching error rates of 1% or more when operated at energy and delay comparable to CMOS, rendering them incompatible with the deterministic nature of digital implementations. In this paper, we employ a Shannon-inspired model of computation to enhance the tolerance of all-spin logic (ASL)-based implementations to gate-level switching errors. We develop the logic-level path delay reallocation techniques to shape the output error statistics and propose a novel error compensation scheme to achieve $1000\times $ higher tolerance to device-level switching errors while maintaining the classification accuracy of an ASL-based support vector machine (SVM) classifier.

[1]  Naresh R. Shanbhag,et al.  Soft digital signal processing , 2001, IEEE Trans. Very Large Scale Integr. Syst..

[2]  Dmitri E. Nikonov,et al.  Benchmarking of Beyond-CMOS Exploratory Devices for Logic Integrated Circuits , 2015, IEEE Journal on Exploratory Solid-State Computational Devices and Circuits.

[3]  Sachin S. Sapatnekar,et al.  CoMET: Composite-Input Magnetoelectric- Based Logic Technology , 2016, IEEE Journal on Exploratory Solid-State Computational Devices and Circuits.

[4]  Bruce E. Hajek,et al.  On the maximum tolerable noise for reliable computation by formulas , 1991, IEEE Trans. Inf. Theory.

[5]  Naresh R. Shanbhag,et al.  An Energy-Efficient ECG Processor in 45-nm CMOS Using Statistical Error Compensation , 2013, IEEE Journal of Solid-State Circuits.

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  Dmitri E. Nikonov,et al.  Static and Clocked Spintronic Circuit Design and Simulation With Performance Analysis Relative to CMOS , 2014, IEEE Transactions on Circuits and Systems I: Regular Papers.

[8]  Houman Homayoun,et al.  Dynamic single and Dual Rail spin transfer torque look up tables with enhanced robustness under CMOS and MTJ process variations , 2016, 2016 IEEE 34th International Conference on Computer Design (ICCD).

[9]  Kaushik Roy,et al.  Probabilistic Deep Spiking Neural Systems Enabled by Magnetic Tunnel Junction , 2016, IEEE Transactions on Electron Devices.

[10]  Kang L. Wang,et al.  Write Error Rate and Read Disturbance in Electric-Field-Controlled Magnetic Random-Access Memory , 2017, IEEE Magnetics Letters.

[11]  David Blaauw,et al.  Low-Power and Compact Analog-to-Digital Converter Using Spintronic Racetrack Memory Devices , 2017, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[12]  Leonard J. Schulman,et al.  On the maximum tolerable noise of k-input gates for reliable computation by formulas , 2003, IEEE Trans. Inf. Theory.

[13]  Dmitri E. Nikonov,et al.  Material Targets for Scaling All Spin Logic , 2012, ArXiv.

[14]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[15]  Jacques-Olivier Klein,et al.  Analytical Macrospin Modeling of the Stochastic Switching Time of Spin-Transfer Torque Devices , 2015, IEEE Transactions on Electron Devices.

[16]  Karthik Yogendra,et al.  Exploring Spin-Transfer-Torque Devices for Logic Applications , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[17]  S. Datta,et al.  Proposal for an all-spin logic device with built-in memory. , 2010, Nature nanotechnology.

[18]  Dmitri E. Nikonov,et al.  Spin-Orbit Logic with Magnetoelectric Nodes: A Scalable Charge Mediated Nonvolatile Spintronic Logic , 2015, 1512.05428.

[19]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[20]  K. Roy,et al.  Spin-Based Neuron Model With Domain-Wall Magnets as Synapse , 2012, IEEE Transactions on Nanotechnology.

[21]  G. Huang,et al.  An Energy-Efficient Nonvolatile In-Memory Computing Architecture for Extreme Learning Machine by Domain-Wall Nanowire Devices , 2015, IEEE Transactions on Nanotechnology.

[22]  Naresh R. Shanbhag,et al.  Robust and energy-efficient DSP systems via output probability processing , 2010, 2010 IEEE International Conference on Computer Design.

[23]  Douglas L. Jones,et al.  Stochastic computation , 2010, Design Automation Conference.

[24]  Supriyo Datta,et al.  Intrinsic optimization using stochastic nanomagnets , 2016, Scientific Reports.

[25]  Azad Naeemi,et al.  A Proposal for Energy-Efficient Cellular Neural Network Based on Spintronic Devices , 2016, IEEE Transactions on Nanotechnology.

[26]  Naresh R. Shanbhag,et al.  Soft N-Modular Redundancy , 2012, IEEE Transactions on Computers.

[27]  Yiran Chen,et al.  Spintronics based stochastic computing for efficient Bayesian inference system , 2017, 2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC).

[28]  Naresh R. Shanbhag,et al.  Perfect error compensation via algorithmic error cancellation , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[29]  Byonghyo Shim.  Error -Tolerant Digital Signal Processing , 2005 .

[30]  M. Tran,et al.  A Portable Dynamic Switching Model for Perpendicular Magnetic Tunnel Junctions Considering Both Thermal and Process Variations , 2015, IEEE Transactions on Magnetics.

[31]  J. Neumann.  Probabilistic Logic and the Synthesis of Reliable Organisms from Unreliable Components , 1956 .

[32]  Kaushik Roy,et al.  Spintastic: Spin-based stochastic logic for energy-efficient computing , 2015, 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[33]  Naveen Verma,et al.  Shannon-Inspired Statistical Computing for the Nanoscale Era , 2019, Proceedings of the IEEE.

[34]  Douglas L. Jones,et al.  Low power and error resilient PN code acquisition filter via statistical error compensation , 2011, 2011 IEEE Custom Integrated Circuits Conference (CICC).

[35]  Swaroop Ghosh,et al.  Domain Wall Memory based Convolutional Neural Networks for Bit-width Extendability and Energy-Efficiency , 2016, ISLPED.

[36]  Naresh R. Shanbhag,et al.  Error-Resilient Motion Estimation Architecture , 2008, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[37]  Naresh R. Shanbhag,et al.  Low-power filtering via adaptive error-cancellation , 2003, IEEE Trans. Signal Process..

[38]  Ali H. Shoeb,et al.  Application of machine learning to epileptic seizure onset detection and treatment , 2009 .

[39]  Supriyo Datta,et al.  A building block for hardware belief networks , 2016, Scientific Reports.

[40]  Naresh R. Shanbhag,et al.  Embedded Algorithmic Noise-Tolerance for Signal Processing and Machine Learning Systems via Data Path Decomposition , 2016, IEEE Transactions on Signal Processing.

[41]  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.

[42]  W. Rippard,et al.  Switching Distributions for Perpendicular Spin-Torque Devices Within the Macrospin Approximation , 2012, IEEE Transactions on Magnetics.

[43]  Kaushik Roy,et al.  SPINDLE: SPINtronic Deep Learning Engine for large-scale neuromorphic computing , 2014, 2014 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED).

[44]  Nicholas Pippenger,et al.  Reliable computation by formulas in the presence of noise , 1988, IEEE Trans. Inf. Theory.

[45]  Behtash Behin-Aein,et al.  Numerical Fokker-Planck simulation of stochastic write error in spin torque switching with thermal noise , 2016, 2016 74th Annual Device Research Conference (DRC).