23 June 2023 in Science Advances
Memristor-enabled in-memory computing provides an unconventional computing paradigm to surpass the energy efficiency of von Neumann computers. Owing to the limitation of the computing mechanism, while the crossbar structure is desirable for dense computation, the system’s energy and area efficiency degrade substantially in performing sparse computation tasks, such as scientific computing. In this work, we report a high-efficiency in-memory sparse computing system based on a self-rectifying memristor array. This system originates from an analog computing mechanism that is motivated by the device’s self-rectifying nature, which can achieve an overall performance of ~97 to ~11 TOPS/W for 2- to 8-bit sparse computation when processing practical scientific computing tasks. Compared to previous in-memory computing system, this work provides over 85 times improvement in energy efficiency with an approximately 340 times reduction in hardware overhead. This work can pave the road toward a highly efficient in-memory computing platform for high-performance computing.
14 February 2025 in Science Advances
Memristive in-memory computing has demonstrated potential for solving matrix equations in scientific computing. However, the inherent inaccuracies of analog mechanisms create challenges in achieving high-precision solutions while maintaining low-energy consumption. This study introduces a memristive matrix equation solver that considerably accelerates solutions by performing mathematical iterations directly within an analog domain. Our approach facilitates rapid approximate solutions with a scalable circuit topology and expedites the high-precision refinement process by substantially reducing the digital-to-analog conversion overhead. We experimentally validated this methodology using a heterogeneous computing system. We performed simulations of multiple scientific problems on these circuits, including solving the diffusion equation and modeling equilibration in silicon P-N junctions. Notably, our memristive solver, combined with digital refinement, achieved software-equivalent precision (with an error of 10 −12 ). Compared to conventional digital processing units, this approach offered a 128-fold improvement in solution speed and a 160-fold reduction in energy consumption. This work establishes a foundation for future scientific computing using imprecise analog devices.
11 October 2023 in APL Machine Learning
In-memory computing (IMC) using emerging nonvolatile devices has received considerable attention due to its great potential for accelerating artificial neural networks and machine learning tasks. As the basic concept and operation modes of IMC are now well established, there is growing interest in employing its wide and general application. In this perspective, the path that leads memristive IMC to general-purpose machine learning is discussed in detail. First, we reviewed the development timeline of machine learning algorithms that employ memristive devices, such as resistive random-access memory and phase-change memory. Then we summarized two typical aspects of realizing IMC-based general-purpose machine learning. One involves a heterogeneous computing system for algorithmic completeness. The other is to obtain the configurable precision techniques for the compromise of the precision-efficiency dilemma. Finally, the major directions and challenges of memristive IMC-based general-purpose machine learning are proposed from a cross-level design perspective.
20 June 2025 in Science Advances
Emerging artificial intelligence for science (AI-for-Science) algorithms, such as the Fourier neural operator (FNO), enabled fast and efficient scientific simulation. However, extensive data transfers and intensive high-precision computing are necessary for network training, which challenges conventional digital computing platforms. Here, we demonstrated the potential of a heterogeneous computing-in-memristor (CIM) system to accelerate the FNO for scientific modeling tasks. Our system contains eight four-kilobit memristor chips with embedded floating-point computing workflows and a heterogeneous training scheme, representing a heterogeneous CIM platform that leverages precision-limited analog devices to accelerate floating-point neural network training. We demonstrate the capabilities of this system by solving the one-dimensional Burgers’ equation and modeling the three-dimensional thermal conduction phenomenon. An expected nearly 116 times to 21 times increase in computational energy efficiency was achieved, with solution precision comparable to those of digital processors. Our results extend in-memristor computing applicability beyond edge neural networks and facilitate construction of future AI-for-Science computing platforms.
1 January 2026 in IEEE Transactions on Circuits and Systems I: Regular Papers