Neuromorphic 3D Integrated Circuit: A Hybrid, Reliable and Energy Efficient Approach for Next Generation Computing

In this paper, we proposed to use 3D integration technology to create a neuromorphic hardware system that is compatible with current technology, provides high system speed, high density, massively parallel processing, low power consumption, and small footprint. The Through Silicon Vias (TSVs) used in the 3D neuromorphic structure provide high density integration and energy efficient links for transferring information through multiple neuron layers. This work details how a 3D neuromorphic system is benefited from the redundant TSV with substantial design-area reduction. We discussed the yield and reliability issues and explained the impact in neuromorphic 3D system design. A spiking neuron model is developed for the proposed 3D system. Furthermore, a new methodology have been proposed by introducing oxide around the bump that could significantly enhance the TSV capacitance in 3D Neuromorphic Computing (NC) system.

[1]  Bashir M. Al-Hashimi,et al.  Cost-Effective TSV Grouping for Yield Improvement of 3D-ICs , 2011, 2011 Asian Test Symposium.

[2]  Chulsoon Hwang,et al.  Capacitance-Enhanced Through-Silicon Via for Power Distribution Networks in 3D ICs , 2016, IEEE Electron Device Letters.

[3]  Olivier Temam,et al.  Capacitance of TSVs in 3-D stacked chips a problem? Not for neuromorphic systems! , 2012, DAC Design Automation Conference 2012.

[4]  Yang Yi,et al.  A novel circuit model for multiple Through Silicon Vias (TSVs) in 3D IC , 2013, 2013 IEEE International 3D Systems Integration Conference (3DIC).

[5]  Kuan-Neng Chen,et al.  Reliability of key technologies in 3D integration , 2013, Microelectron. Reliab..

[6]  Piotr Dudek,et al.  Compact silicon neuron circuit with spiking and bursting behaviour , 2008, Neural Networks.

[7]  Alister Hamilton,et al.  Analog VLSI Circuit Implementation of an Adaptive Neuromorphic Olfaction Chip , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.

[8]  Olivier Temam,et al.  The improbable but highly appropriate marriage of 3D stacking and neuromorphic accelerators , 2014, 2014 International Conference on Compilers, Architecture and Synthesis for Embedded Systems (CASES).

[9]  Yang Yi,et al.  Impedance extraction for 3-D structures with multiple dielectrics using preconditioned boundary element method , 2007, 2007 IEEE/ACM International Conference on Computer-Aided Design.

[10]  Giacomo Indiveri,et al.  Memory and Information Processing in Neuromorphic Systems , 2015, Proceedings of the IEEE.

[11]  David Blaauw,et al.  Centip3De: A Cluster-Based NTC Architecture With 64 ARM Cortex-M3 Cores in 3D Stacked 130 nm CMOS , 2013, IEEE Journal of Solid-State Circuits.

[12]  Lingjia Liu,et al.  An Analytical Through Silicon Via (TSV) Surface Roughness Model Applied to a Millimeter Wave 3-D IC , 2015, IEEE Transactions on Electromagnetic Compatibility.

[13]  André van Schaik,et al.  A compact aVLSI conductance-based silicon neuron , 2015, 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[14]  Joungho Kim,et al.  Frequency and time domain measurement of through-silicon via (TSV) failure , 2012, 2012 IEEE 21st Conference on Electrical Performance of Electronic Packaging and Systems.

[15]  Narayan Srinivasa,et al.  Energy-Efficient Neuron, Synapse and STDP Integrated Circuits , 2012, IEEE Transactions on Biomedical Circuits and Systems.

[16]  Kyung-Wook Paik,et al.  3D-TSV vertical interconnection method using Cu/SnAg double bumps , 2012, 2012 3rd IEEE International Workshop on Low Temperature Bonding for 3D Integration.

[17]  G. Katti,et al.  An Analytical Capacitance Model for Through-Silicon Vias in Floating Silicon Substrate , 2016, IEEE Transactions on Electron Devices.

[18]  Yang Yi,et al.  Spike-Time-Dependent Encoding for Neuromorphic Processors , 2015, ACM J. Emerg. Technol. Comput. Syst..

[19]  Bernard Brezzo,et al.  TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[20]  John H. Lau,et al.  TSV manufacturing yield and hidden costs for 3D IC integration , 2010, 2010 Proceedings 60th Electronic Components and Technology Conference (ECTC).

[21]  Patrick Camilleri,et al.  A Neuromorphic aVLSI network chip with configurable plastic synapses , 2007, 7th International Conference on Hybrid Intelligent Systems (HIS 2007).