Graph Convolutional Networks (GCNs) have been widely applied in fields such as social network analysis and recommendation systems. Recently, deep GCNs have emerged, enabling the exploration of deeper hidden information. Compared to traditional shallow GCNs, deep GCNs feature significantly more layers, leading to considerable computational and data movement challenges. Processing-In-Memory (PIM) offers a promising solution for efficiently handling GCNs by enabling near-data computation, thus reducing data transfer between processing units and memory. However, previous work mainly focused on shallow GCNs and has shown limited performance with deep GCNs. In this paper, we present Dancer, an innovative PIM-based GCN accelerator. Dancer optimizes data movement during the inference process, significantly improving efficiency and reducing energy consumption. Specifically, we introduce a novel compressed graph storage architecture and a dynamic quantization technique to minimize data transfers at each layer of the GCN. Additionally, through a detailed analysis of weight dynamics changes, we propose a sparsity propagation strategy to further alleviate the computational and data transfer burden between layers. Experimental results demonstrate that, compared to current state-of-the-art methods, Dancer achieves 3.7× speedup, 7.6× energy efficiency, and reduces of 9.6× DRAM access on average.

Forward-looking multi-input multi-output synthetic aperture radar (FL-MIMO-SAR) is the state-of-the-art technique to achieve the high-resolution image of the front area. However, the performance of FL-MIMO-SAR is primary limited by left-right Doppler ambiguity resolution. To address this issue, a novel space-time cascade imaging framework is proposed. Concretely, the Doppler-division multiplexing MIMO (DDM-MIMO) scheme is adopted to achieve the waveform orthogonality and the back-projection (BP) time-domain algorithm is applied to obtain high-resolution SAR images. Furthermore, the effect of array errors is analyzed and calibrated, which is essential for subsequent Doppler ambiguity resolution using the linearly constrained minimum variance (LCMV) beamforming. Finally, experimental analysis is performed to confirm the effectiveness of the proposal.

Lack of full use of phase information is a common problem in synthetic aperture radar (SAR) automatic target recognition (ATR). In this paper, we propose a complex manifold multi-scale feature fusion network (CMMFF-Net) for SAR image target recognition. Unlike traditional complex-valued networks, we extend SAR complex images to complex manifold space and construct a complex-valued manifold feature extraction module, which can extract manifold features from SAR amplitude and phase images. Moreover, the multiscale feature extraction and fusion module helps to further extract richer and discriminative target features by fusing multiscale information. Experimental results on SAR complex image dataset demonstrate the effectiveness of proposed method.

Graph Convolutional Networks (GCNs) are powerful learning approaches for graph-structured data. GCNs are both computing- and memory-intensive. The emerging 3D-stacked computation-in-memory (CIM) architecture provides a promising solution to process GCNs efficiently. The CIM architecture can provide near-data computing, thereby reducing data movement between computing logic and memory. However, previous works do not fully exploit the CIM architecture in both dataflow and mapping, leading to significant energy consumption.This paper presents Lift, an energy-efficient GCN accelerator based on 3D CIM architecture using software and hardware co-design. At the hardware level, Lift introduces a hybrid architecture to process vertices with different characteristics. Lift adopts near-bank processing units with a push-based dataflow to process vertices with strong re-usability. A dedicated unit is introduced to reduce massive data movement caused by high-degree vertices. At the software level, Lift adopts a hybrid mapping to further exploit data locality and fully utilize the hybrid computing resources. The experimental results show that the proposed scheme can significantly reduce data movement and energy consumption compared with representative schemes.