ABSTRACT
Neurophysiological architecture using 3D integration technology offers a high device interconnection density as well as fast and energy efficient links among the neuron and synapses layers. In this paper, we propose to reconfigure the Through-Silicon-Vias (TSVs) to serve as the neuronal membrane capacitors that map the membrane electrical activities in a hybrid 3D neuromorphic system. We also investigate new methodology that could significantly enhance the TSV capacitance to achieve a high efficiency of signal processing through membrane. An optimal CAD framework is designed to optimally utilize such TSV devices, and resolve the signal-integrity issues arising at fast data rates during massively parallel data transmissions. The electrical performance of the 3D neuromorphic chip is compared against the ones of the 2D counterpart design to demonstrate the advantages of our design and methodology.
- C. Mead, Analog VLSI and neural systems. Addison-Wesley, Boston, MA, USA. Google ScholarDigital Library
- DARPA Synapse Program: http://www.artificialbrains.com/darpa-synapse-program.Google Scholar
- I. Loi, F. Angiolini, S. Fujita, S. Mitra, and L. Benini, "Characterization, and implementation of fault-tollerant vertical links for 3-D network-on-chip," IEEE Trans. Comput.-Aided Design Integr. Circuits Syst., vol. 30, no. 1, pp. 124--134, 2011. Google ScholarDigital Library
- U. R. Tida, R. Yang, C. Zhuo and Y. Shi, "On the Efficacy of Through-Silicon-Via Inductors," in IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 23, no. 7, pp. 1322--1334, July 2015.Google ScholarCross Ref
- U. R. Tida, C. Zhuo and Y. Shi, "Novel Through-Silicon-Via Inductor-Based On-Chip DC-DC Converter Designs in 3D ICs," in ACM Journal on Emerging Technologies in Computing Systems (JETC), vol. 11, no. 2, Nov. 2014. Google ScholarDigital Library
- J. H. Lau, "TSV Manufacturing Yield and Hidden Costs for 3D IC Integration," in Proc. Of Electronic Components and Technology Conference (ECTC), pp. 1031--1042, 2010.Google Scholar
- C. Zhao, B. Wysocki, C. Thiem, N. McDonald, J. Li, and Y. Yi, "Energy Efficient Spiking Temporal Encoder Design for Neuromorphic Computing Systems," IEEE Trans. on Multi-Scale Computing Systems (TMSCS), vol. 2, no. 4, pp. 265--276, 2016.Google ScholarCross Ref
- C. Zhao, J. Li, and Y, Yi, "Making neural encoding robust and energy-efficient: an advanced analog temporal encoder for brain-inspired computing systems," in Proceedings of IEEE/ACM International Conference on Computer Aided Design (ICCAD), 2016, pp. 1--6. Google ScholarDigital Library
- D.H. Kim et al., "3D-MAPS: 3D Massively Parallel Processor with Stacked Memory," in Proc. IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pp. 188--190, 2012.Google Scholar
- H.-Y. Huang, Y.-S. Huang, C.-L. Hsu, "Built-in Self-test/repair Scheme for TSV-based Three dimensional Integrated Circuits," in Proc. of IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), pp. 56--59, 2010.Google Scholar
- A. Joubert, M. Duranton, B. Belhadj, O. Temam, and R. Heliot, "Capacitance of TSVs in 3D stacked chips a problem? Not for neuromorphic systems," In proc. DAC'12. pp. 1260--1261. Google ScholarDigital Library
- K. Ryan, S. Tanachutiwat, and W. Wang, "3D CMOL Crossnet for Neuromorphic Network Applications," Nano-Net, Springer Berlin Heidelberg, 3, 2009, pp. 1--5.Google Scholar
- B. Belhadj, A. Valentian, P. Vivet, M. Duranton, L. He, O. Temam, "The improbable but highly appropriate marriage of 3D stacking and neuromorphic accelerators," In proc. Int. Conf. on Compilers, Architec. Synth for Embedded Syst. (12-17 Oct. 2014), 1--9. Google ScholarDigital Library
- Y. Yi, Y. Zhou, X. Fu, and F. Shen, "Modeling Differential Through-Silicon-Vias (TSVs) with Voltage Dependent and Nonlinear Capacitance," Journal of Selected Areas in Microelectronics (JSAM), Cyber Journals, vol.3, no. 6, pp. 1--9, 2013.Google Scholar
- S. M. Sze, Physics of Semiconductor Devices. New York: Wiley, 1981.Google Scholar
- Y. Yi, Y. Liu, Y. Zhou, and W. Becker, "Minimizing crosstalk in highspeed differential buses by optimizing power/ground and signal assignment," in Proceedings of 18th IEEE conference on Electrical Performance of electronic Packaging (EPEP), pp. 255--258, 2009.Google Scholar
- G. Katti, M. Stucchi, J. Van Olmen, K. De Meyer and W. Dehaene, "Through-Silicon-Via Capacitance Reduction Technique to Benefit 3-D IC Performance," in IEEE Electron Device Letters, vol. 31, no. 6, pp. 549--551, June 2010.Google ScholarCross Ref
- Adaptation of Enhanced TSV Capacitance as Membrane Property in 3D Brain-inspired Computing System
Recommendations
Neuromorphic 3D Integrated Circuit: A Hybrid, Reliable and Energy Efficient Approach for Next Generation Computing
GLSVLSI '17: Proceedings of the on Great Lakes Symposium on VLSI 2017In 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 ...
The study of TSV-induced and strained silicon-enhanced stress in 3D-ICs
AbstractIn this work, we discuss the influence of strained silicon technology on transistors in the context of Through Silicon Via (TSV) thermal stress. An accurate thermal stress distribution around a single TSV is firstly obtained by finite ...
Highlights- An accurate stress distribution of a complete TSV structure through FEA simulation.
Comparing Through-Silicon-Via (TSV) Void/Pinhole Defect Self-Test Methods
Three methods have been proposed to test Through-Silicon-Vias (TSV) electrically prior to 3D integration. These test methods are (1) sense amplification; (2) leakage current monitor; and (3) capacitance bridge methods. These tests are aimed at detecting ...
Comments