An official website of the United States government
The non-volatile Resistive RAM (ReRAM) crossbar has shown great potential in accelerating inference in various machine learning models However, it suffers from high reprogramming energy, hindering its usage for on-device adaption to new tasks. Recently, parameter-efficient fine-tuning methods, such as Low-Rank Adaption (LoRA), have been proposed to train few parameters while matching full fine-tuning performance. However, in ReRAM crossbar, the reprogramming cost of LoRA is non-trivial and will increase significantly when adapting to multi-tasks on the device. To address this issue, we are the first to propose LoRAFusion, a parameter-efficient multi-task on-device learning framework for ReRAM crossbar via fusion of pre-trained LoRA modules. LoRAFusion is a group of LoRA modules that are one-time learned based on diverse domain-specific tasks and deployed to the crossbar, acting as the pool of background knowledge. Then given a new unseen task, those LoRA modules are frozen (i.e., no energy-hungry ReRAM cells reprograming), only the proposed learnable layer-wise LoRA fusion coefficient and magnitude vector parameters are trained on-device to weighted-combine pre-trained LoRA modules, which significantly reduces the training parameter size. Our comprehensive experiments show LoRAFusion only uses 3% of the number of trainable parameters in LoRA (148K vs. 4700K), with 0.19% accuracy drop. Codes are available at https://github.com/ASU-ESIC-FAN-Lab/LoRAFusion
more »
« less
This content will become publicly available on October 26, 2026
PIGen: Accelerating ReRAM Co-Design via Generative Physics-Informed Modeling
Resistive Random-Access Memory (ReRAM) offers promising capabilities for data-intensive computing, but optimizing device parameters across diverse materials and operating conditions presents significant challenges. In this paper, we introduce PIGen, an integrated framework that bridges device physics and system-level performance targets through a dual approach: a Physics-Informed Neural Network (PINN) for efficient device modeling and a Conditional Variational Autoencoder (CVAE) for design parameter generation. The PINN model integrates physical constraints with data-driven learning, demonstrating superior accuracy in predicting ReRAM switching dynamics even with sparse training data—a critical advantage when experimental measurements are limited. Building upon this foundation, the CVAE-based generative system translates user- defined performance targets (endurance, latency, energy) into optimized design parameters (material, voltage, pulse width). This unified approach enables automated technology-application co-design, providing up to 93× computational speedup over traditional simulations while maintaining high prediction accuracy across multiple ReRAM materials. By automating parameter optimization and supporting rapid design space exploration, our framework significantly facilitates the development of tailored ReRAM solutions for diverse application requirements, potentially including energy-constrained IoT devices and high-performance computing systems.
more »
« less
- Award ID(s):
- 2346435
- PAR ID:
- 10695450
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3315-1560-7
- Page Range / eLocation ID:
- 1 to 9
- Format(s):
- Medium: X
- Location:
- Munich, Germany
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Microstructure-sensitive materials design has become popular among materials engineering researchers in the last decade because it allows the control of material performance through the design of microstructures. In this study, the microstructure is defined by an orientation distribution function. A physics-informed machine learning approach is integrated into microstructure design to improve the accuracy, computational efficiency, and explainability of microstructure-sensitive design. When data generation is costly and numerical models need to follow certain physical laws, machine learning models that are domain-aware perform more efficiently than conventional machine learning models. Therefore, a new paradigm called the physics-informed neural network (PINN) is introduced in the literature. This study applies the PINN to microstructure-sensitive modeling and inverse design to explore the material behavior under deformation processing. In particular, we demonstrate the application of PINN to small-data problems driven by a crystal plasticity model that needs to satisfy the physics-based design constraints of the microstructural orientation space. For the first problem, we predict the microstructural texture evolution of copper during a tensile deformation process as a function of initial texturing and strain rate. The second problem aims to calibrate the crystal plasticity parameters of the Ti-7Al alloy by solving an inverse design problem to match the PINN-predicted final texture prediction and the experimental data.more » « less
-
Microstructure-sensitive material design has become popular among materials engineering researchers in the last decade because it allows the control of material performance through the design of microstructures. In this study, the microstructure is defined by an orientation distribution function (ODF). A physics-informed machine learning approach is integrated into microstructure design to improve the accuracy, computational efficiency, and explainability of microstructure-sensitive design. When data generation is costly and numerical models need to follow certain physical laws, machine learning models that are domain-aware perform more efficiently than conventional machine learning models. Therefore, a new paradigm called Physics-Informed Neural Network (PINN) is introduced in the literature. This study applies the PINN to microstructure-sensitive modeling and inverse design to explore the material behavior under deformation processing. In particular, we demonstrate the application of PINN to small-data problems driven by a crystal plasticity model that needs to satisfy the physics-based design constraints of the microstructural orientation space. For the first problem, we predict the microstructural texture evolution of Copper during a tensile deformation process as a function of initial texturing and strain rate. The second problem aims to calibrate the crystal plasticity parameters of Ti-7Al alloy by solving an inverse design problem to match PINN-predicted final texture prediction and the experimental data.more » « less
-
No two fabricated Resistive Random Access Memory (ReRAM) devices are alike. Each device can have its own individual optimal set of operating parameters that gives the best performance. However, in an array each device needs to be measured in similar operating settings. Therefore, it is necessary to find the optimal settings where most devices will have the best performance across the entire array population. Traditional sampling methods require a large number of tests within an experimental space, which is time‐intensive and resource‐draining. As an alternative, this study proposes the adoption of the Latin square method under the Design of Experiments (DoE) framework for the characterization and performance optimization of arrays of ReRAM devices. This innovative approach drastically reduces the number of experimental tests, thereby offering a faster way to discern the impact of each factor and fine‐tune device parameters effectively. The core objective of employing this DoE technique is to harness its potential for optimizing parameters that significantly enhance the ON/OFF ratio and endurance of ReRAM devices. The optimization technique, performed on a CMOS‐integrated 20 k array of ReRAM devices, increases the device yield by ≈84%, compared to the previous integration with an unoptimized technique.more » « less
-
Fluid–structure interactions (FSI) underpin diverse biological and engineering systems, yet computational modeling of these interactions remains resource-intensive and constrained by high-dimensional parameter spaces. To address these limitations, we develop a data-driven, two-stage surrogate modeling framework leveraging Fourier neural operators (FNO) to accurately predict the hydrodynamic performance of biomimetic elastic propulsors across a broad range of design parameters. Our approach first maps geometric and physical parameters to the propulsor dynamic bending pattern and then uses this bending pattern to predict thrust, power, and efficiency. Trained using direct FSI simulation data, our surrogate model achieves three orders of magnitude speedup compared to the direct simulations while maintaining high accuracy. Crucially, the use of intermediate kinematic modeling significantly reduces the overall model size and enhances accuracy. Our FNO modeling framework enables rapid exploration of large design spaces, indicating strong potential for application in the design and optimization of FSI problems.more » « less
