A general memristor-based partial differential equation solver

Zidan, Mohammed A.; Jeong, YeonJoo; Lee, Jihang; Chen, Bing; Huang, Shuo; Kushner, Mark J.; Lü, Wei

doi:10.1038/s41928-018-0100-6

Cited by 210 publications

(167 citation statements)

References 38 publications

Supporting

Mentioning

167

Contrasting

Order By: Relevance

“…c) Implementation of the Jacobi method using memristor crossbar array which can be used to iteratively solve Poisson's partial differential equation. Reproduced with permission . Copyright 2018, Springer Nature Publishing AG.…”

Section: Other Arithmetic Acceleratorsmentioning

confidence: 99%

“…The finite scale of memristive crossbar places further constraint on practical applications. Despite the above issues at the device level, the potential of using memristor‐based hardware in high‐precision computing tasks is demonstrated by a memristor‐based partial differential equation (PDE) solver, as shown in Figure (c). Solving PDEs is of generalized significance in simulation, prediction and optimization problems .…”

Section: Other Arithmetic Acceleratorsmentioning

confidence: 99%

See 1 more Smart Citation

Memristive Devices and Networks for Brain‐Inspired Computing

Zhang

et al. 2019

Physica Rapid Research Ltrs

View full text Add to dashboard Cite

As the era of big data approaches, conventional digital computers face increasing difficulties in performance and power efficiency due to their von Neumann architecture. As a result, there is recently a tremendous upsurge of investigations on brain-inspired neuromorphic hardware with high parallelism and improved efficiency. Memristors are considered as promising building blocks for the realization of artificial synapses and neurons and can therefore be utilized to construct hardware neural networks. Here, a review is provided on existing approaches for the implementation of artificial synapses and neurons based on memristive devices; and the respective advantages and disadvantages of these approaches are evaluated. This is followed by a discussion of hardware accelerators and neuromorphic computing systems that exploit the parallel, in-memory and analog characteristics of memristive crossbar arrays as well as the intrinsic dynamics of memristors. Finally, the outstanding challenges are addressed that have not yet been resolved in the present studies, and future advances are discussed that might be needed for building intelligent and energy efficient neuromorphic systems.

show abstract

Section: Other Arithmetic Acceleratorsmentioning

confidence: 99%

Section: Other Arithmetic Acceleratorsmentioning

confidence: 99%

Memristive Devices and Networks for Brain‐Inspired Computing

Zhang

et al. 2019

Physica Rapid Research Ltrs

View full text Add to dashboard Cite

show abstract

“…Resistive memories, also known as memristors (1), including resistive switching memory (RRAM) and phase-change memory (PCM), are emerging as a novel technology for high-density storage (2,3), neuromorphic hardware (4,5), and stochastic security primitives, such as random number generators (6,7). Thanks to their ability to store analog values and to their excellent programming speed, resistive memories have also been demonstrated for executing in-memory computing (8)(9)(10)(11)(12)(13)(14)(15)(16)(17), which eliminates the data transfer between the memory and the processing unit to improve the time and energy efficiency of computation. With a cross-point architecture, resistive memories can be naturally used to perform matrix-vector multiplication (MVM) by exploiting fundamental physical laws such as the Ohm's law and the Kirchhoff's law of electric circuits (8).…”

Section: Introductionmentioning

confidence: 99%

One-step regression and classification with cross-point resistive memory arrays

et al. 2020

View full text Add to dashboard Cite

One Sentence Summary: Machine learning algorithms such as linear regression and logisticregression are trained in one step with crosspoint resistive memory arrays.2 Abstract: Machine learning has been getting a large attention in the recent years, as a tool to process big data generated by ubiquitous sensors in our daily life. High speed, low energy computing machines are in demand to enable real-time artificial intelligence at the edge, i.e., without the support of a remote frame server in the cloud. Such requirements challenge the complementary metal-oxide-semiconductor (CMOS) technology, which is limited by the Moore's law approaching its end and the communication bottleneck in conventional computing architecture. Novel computing concepts, architectures and devices are thus strongly needed to accelerate data-intensive applications. Here we show a crosspoint resistive memory circuit with feedback configuration can execute linear regression and logistic regression in just one step by computing the pseudoinverse matrix of the data within the memory. The most elementary learning operation, that is the regression of a sequence of data and the classification of a set of data, can thus be executed in one single computational step by the novel technology. One-step learning is further supported by simulations of the prediction of the cost of a house in Boston and the training of a 2-layer neural network for MNIST digit recognition. The results are all obtained in one computational step, thanks to the physical, parallel, and analog computing within the crosspoint array.

show abstract

“…Thirdly, the high‐density monolithic integration provides much more area efficiency. And lastly, the memristors being fabricated nowadays are reported to be suitable for some real computing tasks …”

Section: Introductionmentioning

confidence: 99%

Functional Demonstration of a Memristive Arithmetic Logic Unit (MemALU) for In‐Memory Computing

Cheng

Yin

et al. 2019

Adv Funct Materials

View full text Add to dashboard Cite

The development of in-memory computing has opened up possibilities to build next-generation non-von-Neumann computing architecture. Implementation of logic functions within the memristors can significantly improve the energy efficiency and alleviate the bandwidth congestion issue. In this work, the demonstration of arithmetic logic unit functions is presented in a memristive crossbar with implemented non-volatile Boolean logic and arithmetic computing. For logic implementation, a standard operating voltage mode is proposed for executing reconfigurable stateful IMP, destructive OR, NOR, and non-destructive OR logic on both the word and bit lines. No additional voltages are needed beyond "V P " and its negative component. With these basic logic functions, other Boolean functions are constructed within five devices in at most five steps. For arithmetic computing, the fundamental functions including an n-bit full adder with high parallelism as well as efficient increment, decrement, and shift operations are demonstrated. Other arithmetic blocks, such as subtraction, multiplication, and division are further designed. This work provides solid evidence that memristors can be used as the building block for in-memory computing, targeting various low-power edge computing applications.

show abstract

A general memristor-based partial differential equation solver

Cited by 210 publications

References 38 publications

Memristive Devices and Networks for Brain‐Inspired Computing

Memristive Devices and Networks for Brain‐Inspired Computing

One-step regression and classification with cross-point resistive memory arrays

Functional Demonstration of a Memristive Arithmetic Logic Unit (MemALU) for In‐Memory Computing

Contact Info

Product

Resources

About