相关论文: Spin Wave Based Approximate Computing

Modern Neural Network (NN) architectures heavily rely on vast numbers of multiply-accumulate arithmetic operations, constituting the predominant computational cost. Therefore, this paper proposes a high-throughput, scalable and energy…

Several microring resonator (MRR) based analog photonic architectures have been proposed to accelerate general matrix-matrix multiplications (GEMMs) in deep neural networks with exceptional throughput and energy efficiency. To implement…

In this paper, two approximate 3*3 multipliers are proposed and the synthesis results of the ASAP-7nm process library justify that they can reduce the area by 31.38% and 36.17%, and the power consumption by 36.73% and 35.66% compared with…

Recent sustainability drives place energy-consumption metrics in centre-stage for the design of future radio access networks (RAN). At the same time, optimising the trade-off between performance and system energy usage by machine-learning…

Altermagnetic (AM) materials have recently attracted significant interest due to the non-relativistic momentum-dependent spin splitting of their electronic band structure which may be useful for antiferromagnetic (AFM) spintronics. So far,…

We report on the first experimental demonstration of majority logic operation using spin waves in a scaled device with an in-line input and output layout. The device operation is based on the interference of spin waves generated and…

Solving the shallow water equations efficiently is critical to the study of natural hazards induced by tsunami and storm surge, since it provides more response time in an early warning system and allows more runs to be done for…

An efficient hardware implementation for Simultaneous Localization and Mapping (SLAM) methods is of necessity for mobile autonomous robots with limited computational resources. In this paper, we propose a resource-efficient FPGA…

Data movement in memory-intensive workloads, such as deep learning, incurs energy costs that are over three orders of magnitude higher than the cost of computation. Since these workloads involve frequent data transfers between memory and…

The computing wall and data movement challenges of deep neural networks (DNNs) have exposed the limitations of conventional CMOS-based DNN accelerators. Furthermore, the deep structure and large model size will make DNNs prohibitive to…

Artificial Neural Networks (ANNs) have found widespread applications in tasks such as pattern recognition and image classification. However, hardware implementations of ANNs using conventional binary arithmetic units are computationally…

Dedicated hardware accelerators are suitable for parallel computational tasks. Moreover, they have the tendency to accept inexact results. These hardware accelerators are extensively used in image processing and computer vision…

Fluid antenna (FA), as an emerging antenna technology, fully exploits spatial diversity. This paper integrates FA with the receive spatial modulation (RSM) scheme and proposes a novel FA-empowered RSM (FA-RSM) system. In this system, the…

Federated learning (FL) has attracted increasing attention as a promising approach to driving a vast number of end devices with artificial intelligence. However, it is very challenging to guarantee the efficiency of FL considering the…

Contemporary wireless communication systems rely on Multi-User Multiple-Input Multiple-Output (MU-MIMO) techniques. In such systems, each Access Point (AP) is equipped with multiple antenna elements and serves multiple devices…

In this paper, we propose a Spin-Torque (ST) based sensing scheme that can enable energy efficient multi-bit long distance interconnect architectures. Current-mode interconnects have recently been proposed to overcome the performance…

Function approximation is crucial in Flexible Electronics (FE), where applications demand efficient computational techniques within strict constraints on size, power, and performance. Devices like wearables and compact sensors are…

Compute-in-memory (CiM) is a promising approach to improving the computing speed and energy efficiency in dataintensive applications. Beyond existing CiM techniques of bitwise logic-in-memory operations and dot product operations, this…

Numerically optimised microwave pulses are used to increase excitation efficiency and modulation depth in electron spin resonance experiments performed on a spectrometer equipped with an arbitrary waveform generator. The optimisation…

Producing reliable acoustic subsurface velocity models still remains the main bottleneck of the oil and gas industry's traditional imaging sequence. In complex geological settings, the output of conventional ray-based or wave-equation-based…