3D-stacked DRAM is a key technology enabling the development of large language models (LLMs). However, the intensive computational demands lead to substantial energy consumption resulting from large-scale data movement. Integrating processing-in-memory (PIM) within DRAM has been employed to reduce data movement, but it elevates manufacturing costs and incurs additional area and power consumption. On the other hand, implementing processing-near-memory (PNM) outside the DRAM controller fails to eliminate the high energy consumption associated with interconnects during data transfer. To address these challenges, we propose a processing-in-controller (PIC) architecture aimed at 3D-stacked DRAM for efficient data movement. A size-scalable General Matrix-Vector Multiplication (GEMV) structure is proposed, supporting configurations ranging from 16 × 16 to 128 × 128, thereby enhancing its adaptability for a variety of applications. To address the low throughput bottleneck caused by DDR read latency, a ping-pong buffer with weight prefetching is introduced in the PNM. Based on 28 nm CMOS technology, experimental results demonstrate that the energy consumption of this PIC is 0.22 pJ/bit, while data movement efficiency improves by nearly 92% compared to traditional DRAM operations.

Frequency offset estimate (FOE) is utilized to correct the incremental phase deviation caused by transceiver local oscillator mismatches, and determine the performance of the successive carrier offset compensation module. The FFT-based FOE method offers stability and controlled precision. However, as the FFT scale increases, the algorithm’s complexity also rises, which hinders real-time implementation of high-precision FOE hardware. While several research efforts aim to simplify the algorithm, there is limited focus on hardware implementation. In this paper, we introduce a semi-folded 256-point FFT with 64-way parallelism. By reusing the 64-point FFT module, computations are completed within four clock cycles, resulting in circuit area and power savings. We further leverage the semi-folded FFT structure to implement the FOE circuit. The experiments demonstrate that under the 28nm process technology, the semi-folded FFT achieves an area efficiency of 0.0043/(mm2/GS) and a power efficiency of 2.44mW/GS when working at a frequency of 714MHz. Additionally, when working at 500MHz the semi-foleded based FOE circuit has an area of 0.787mm2and a power consumption of 319.1mW, meets the requirements of a 256Gbps 16QAM communication system.

Carrier phase recovery (CPR) determines the accuracy of the receiver in modern coherent optical communication. The accurate estimation and tracking of carriers are particularly vital with the increase of throughput for long-distance transmit. It is a challenge to implement a real-time system because the computational complexity increases with fractional bits. Moreover, the conversion between polar coordinates and Cartesian coordinates introduces a high latency. In this paper, we present an FPGA implementation of low latency Viterbi-Viterbi 4thPower Estimation (VV4E) based CPR, which mainly performs the computation in Cartesian coordinates and implements the trigonometric function with a look-up table (LUT). Evaluations on Xilinx ZCU102 show that at a frequency of 370MHz, it introduces a 22-cycle latency to handle the 29.6 GBd QPSK signals, which is the minimum value to our knowledge.

Infrared (IR) small target detection has been extensively studied due to its importance in IR search and tracking (IRST) systems. Existing methods have some limitations in suppressing cluttered high-contrast backgrounds, which may result in more false detections. In this letter, on the one hand, we propose an improved fuzzy C-mean (IFCM) clustering to accurately segment IR small targets and complex backgrounds. On the other hand, an IFCM-based descriptor fusing multiple features (IFCM-MF) is proposed to suppress complex backgrounds. First, a sliding window is designed to quickly extract the candidate pixels. Then, to better enhance the target and suppress the background, we construct an IFCM-based local window and calculate the IFCM-MF. Finally, IR small targets are detected by adaptive thresholding operation. The experimental results show that our method can better suppress cluttered high-contrast backgrounds and significantly improve the detection performance with high speed.

Soft error is a major reliability concern in advanced technology nodes. Although mitigating Soft Error Rate (SER) will inevitably sacrifice area and power, few studies paid attention to optimization methods to explore trade-offs between area, power and SER. This paper proposes an optimization framework based on Bayesian approach for soft-error-tolerant circuit design. It comprises two steps:1) data preprocessing and 2) Bayesian optimization. In the preprocessing step, a strategy incorporating k-means algorithm and a novel sequencing algorithm is used to cluster Flip-Flops (FFs) with similar SER in order to reduce the dimensionality for the subsequent step. Bayesian Neural Network (BNN) is the applied surrogate model for acquiring the posterior distribution of three design metrics, while the Lower confidence bound (LCB) functions are employed as acquisition functions to select the next point based on BNN when optimizing. Finally, the non-dominated sorting genetic algorithm (NSGA-II) is used to search the Pareto Optimal Front (POF) solutions of three LCB functions. Experimental results demonstrate the proposed framework has a 1.4x improvement in accuracy and a 70% reduction in SER with acceptable increases in power and area.

Although photogrammetry has long been used as the primary method to produce digital elevation models (DEMs), there are still some locations that are not covered by multiangle images because of various limitations. Moreover, traditional interpolation methods for producing denser DEMs often cause oversmoothing, particularly over rough terrain. To formulate a robust procedure that is capable of reconstructing the terrain surface using sparse ground control points in heterogeneous areas, this letter describes an improved spatial enhancement method combining perspective shape from shading (SFS) using a single optical image. This method is called SFS-based densification using multispectral information (SDMI). First, the image irradiance equation based on the perspective Lambertian model is formulated as a static Hamilton–Jacobi equation and is solved using a fast sweeping strategy. We then reconstruct the relative surface shape and apply an edge-preserved iterative interpolation method to generate a higher resolution DEM grid. Multispectral information is used to reveal the actual surface reflection properties, and the land surface is classified into several types to better estimate surface reflectance. Experiments indicate that SDMI is effective for the interpolation of a sparse grid DEM over heterogeneous terrain.

This paper describes a morphological compensation algorithm for the enhancement of grayscale image compression under the standard of JPEG and JPEG2000, which is more effective for remote sense image than for natural image. Morphological reconstruction is a nonlinear filter. When used for image enhancement it dilates some pixels while preserving the edge information. The algorithm has a close relationship with morphological reconstruction. When this compensation algorithm is applied to images, among which there are images compressed by standard JPEG2000 and JPEG, it can improve the quality of decompressed image.

The satellite remote image is degraded obviously due to the diffraction-limitation of imaging system and the atmosphere turbulence and etc.. Namely, the observed image blurred by a low-pass filter whose transfer function vanishes beyond imaging system cut-off spatial frequency (omegac).Processes that achieve the recreation of frequencies beyond the image pass- band are usually referred to as super-resolution algorithms. Although, multi-frame super-resolution has more potential for spatial resolution improvement, as for remote sensing image, single-frame super-resolution is prerequisite in many cases. One remote imaging blurred model is put forward basing on PSF (point spread function) optimal estimation. Then a sub-blocks non-iterative method is adapted to improve the image spatial resolution effectively with only single-frame low spatial resolution image. With this scheme, the high spatial resolution spots5 panchromatic 2.5 m image can be reconstructed from single-frame 5 m panchromatic spots5 image. The MTF is used as impersonal standard to estimate the spatial resolution improvement and image quality. As result, the high frequency detail information and effective band of image are compensated perfectly with SNR improved.