Interconnect networks for memristor crossbar

As the down-scaling of CMOS technology reaches inherent physical device limits, major challenges arise such as reliability, power consumption, etc. Novel technologies are under investigation as an alternative for next-generation VLSI circuits. Memristor is one of the promising candidates due to its scalability, non-volatility, practically zero leakage, high integration density, etc. Several applications have been proposed for the memristor crossbar architecture; examples are neuromophic, memories and logic circuits. This paper proposes a generic and flexible interconnect network for memristor-based logic circuits within a crossbar architecture. The scheme is based on the use of reserved memristors (within the crossbar) and the execution of copy operations from and/or to the reserved memristors; it can be applied both at intra-tile as well as inter-tile level, where a tile is a basic block performing a simple logic function. To illustrate the potential of the proposed scheme, two intra-tile and one inter-tile case study are evaluated using SPICE simulation, and their incurred costs are analyzed; the case studies consist of interconnect networks for (a) a specific function within a tile (i.e., the matrix transpose), (b) generic logic functions within a tile, and (c) communication between tiles.

[1]  Uri C. Weiser,et al.  Memristor-Based Material Implication (IMPLY) Logic: Design Principles and Methodologies , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[2]  Henk Corporaal,et al.  Memristor based computation-in-memory architecture for data-intensive applications , 2015, 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[3]  Jacques-Olivier Klein,et al.  Nanodevice-based novel computing paradigms and the neuromorphic approach , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[4]  Narayan Srinivasa,et al.  A functional hybrid memristor crossbar-array/CMOS system for data storage and neuromorphic applications. , 2012, Nano letters.

[5]  Andrew S. Tanenbaum,et al.  Computer networks, 4th Edition , 2002 .

[6]  Jeyavijayan Rajendran,et al.  Leveraging Memristive Systems in the Construction of Digital Logic Circuits , 2012, Proceedings of the IEEE.

[7]  G. Snider,et al.  Computing with hysteretic resistor crossbars , 2005 .

[8]  R. Dittmann,et al.  Redox‐Based Resistive Switching Memories – Nanoionic Mechanisms, Prospects, and Challenges , 2009, Advanced materials.

[9]  Jussi H. Poikonen,et al.  Memristive Stateful Logic , 2014 .

[10]  Wei Lu,et al.  Two-terminal resistive switches (memristors) for memory and logic applications , 2011, 16th Asia and South Pacific Design Automation Conference (ASP-DAC 2011).

[11]  R. Waser,et al.  Memristors: Devices, Models, and Applications , 2012 .

[12]  Richard P. Runyon,et al.  The energy crisis , 1972 .

[13]  Uri C. Weiser,et al.  TEAM: ThrEshold Adaptive Memristor Model , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[14]  Sung-Mo Kang,et al.  Memristors: Devices, Models, and Applications [Scanning the Issue] , 2012, Proc. IEEE.

[15]  John Chesshire,et al.  Energy crisis , 1977, Nature.