Sparse-Dense Matrix Multiplication (SpMM) on GPUs has gained significant attention because of its importance in modern applications and the increasing computing power of GPUs in the last decade. Previous SpMM studies have focused on the importance of storage format and load balance for the overall performance of SpMM on GPUs. However, very little attention has been paid to the efficacy of coalesced memory access in improving the efficiency of data loading, which incurs a notable overhead that amounts to an average of more than 32% of the overall performance, according to our experimental observation. Existing state-of-the-art (SOTA) solutions fail to adequately support coalesced memory access of both sparse and dense matrices between the global memory and threads on GPUs. In this paper, we propose an efficient algorithm called Swift.11Swift is available at https://github.com/MinttHu/Swift.git that speeds up the loading of both sparse and dense matrices of SpMM on modern GPUs. Leveraging coalesced memory access, Swift achieves high loading efficiency by sorting both the columns of the sparse matrix and elements of the dense matrix based on the number of non-zero elements and balancing the load by handling the regular and irregular parts differently and judiciously. Swift takes the Compressed Sparse Column format as an implementation case study to prove the concept and gain insights. We conduct a comprehensive comparison of Swift with four SOTA solutions: ASpT, cuSPARSE, RoDe, and Sputnik, using the full SuiteSparse Matrix Collection as the workload. The experimental results on RTX 4080s, RTX 3090Ti, A100, and V100 demonstrate that our method outperforms the baselines significantly.

Anomaly detection (AD) has attracted remarkable attention in hyperspectral image (HSI) processing fields, most existing deep learning (DL) based algorithms indicate dramatic potential for detecting anomaly samples through specific training process under current scenario. However, the limited prior information and the catastrophic forgetting problem indicate crucial challenges for existing DL structure in open scenarios cross-domain detection. In order to improve the detection performance, a novel capsule differential adversarial continual learning framework (CL-CaGAN) is proposed to elevate the cross-scenario learning performance for facilitating the real application of DL-based structure in hyperspectral anomaly detection (HAD) task. First, a modified capsule structure with adversarial learning network is constructed to estimate the background distribution for surmounting the deficiency of prior information. To mitigate the catastrophic forgetting phenomenon, clustering-based sample replay strategy and a designed extra self-distillation regularization are integrated for merging the history and future knowledge in continual AD task, while the discriminative learning ability from previous detection scenario to current scenario are retained by the elaborately designed structure with continual learning strategy. In addition, the differentiable enhancement is enforced to augment the generation performance of the training data for further stabilizing the training process with better convergence, this procedure further efficiently consolidates the reconstruction ability of background samples. To verify the effectiveness of our proposed CL-CaGAN, we conduct experiments on several real HSIs, the results indicate that the proposed CL-CaGAN demonstrates higher detection performance and continuous learning capacity for mitigating the catastrophic forgetting under cross-domain scenarios.

Sparse Matrix-Vector Multiplication (SpMV) on GPUs has gained significant attention because of SpMV's importance in modern applications and the increasing computing power of GPUs in the last decade. Previous studies have emphasized the importance of data loading for the overall performance of SpMV and demonstrated the efficacy of coalesced memory access in enhancing data loading efficiency. However, existing approaches fall far short of reaching the full potential of data loading on modern GPUs. In this paper, we propose an efficient algorithm called FastLoad, that speeds up the loading of both sparse matrices and input vectors of SpMV on modern GPUs. Leveraging coalesced memory access, FastLoad achieves high loading efficiency and load balance by sorting both the columns of the sparse matrix and elements of the input vector based on the number of non-zero elements while organizing non-zero elements in blocks to avoid thread divergence. FastLoad takes the Compressed Sparse Column (CSC) format as an implementation case to prove the concept and gain insights. We conduct a comprehensive comparison of FastLoad with the CSC-based SpMV, cuSPARSE, CSR5, and TileSpMV, using the full SuiteSparse Matrix Collection as workload. The experimental results on RTX 3090 Ti demonstrate that our method outperforms the others in most matrices, with geometric speedup means over CSC-based, cuSPARSE, CSR5, and TileSpMV being 2.12×, 2.98×, 2.88×, and 1.22×, respectively.

Energy harvesting (EH) technology is an effective way to resolve the energy supply problem for green Internet of Things application. However, it is extremely vulnerable to the unpredictable environmental changes, and as a result, sensor nodes are charged in an uncontrollable way. In this paper, we focus on EH cooperative wireless sensor networks (EHC-WSNs), a new type of WSNs that integrates EH and wireless energy transfer technologies to provide the continuous and controllable energy supply. We propose the graphene-grid deployment strategy to guarantee energy coverage and network connectivity, whereby a Graphene-based Energy Cooperation Management (GECM) mechanism is designed under the energy-neutral operation. Furthermore, we divide GECM into two different phases, i.e., graphene-based energy cooperative charging strategy and graphene-based opportunistic cooperative routing algorithm, which are optimized according to the graphene-grid structure. Extensive simulations show that the proposed GECM can maximize the harvested energy utilization and prolong the network lifetime.

Energy savings optimization becomes one of the major concerns in the wireless sensor network (WSN) routing protocol design, due to the fact that most sensor nodes are equipped with the limited nonrechargeable battery power. In this paper, we focus on minimizing energy consumption and maximizing network lifetime for data relay in one-dimensional (1-D) queue network. Following the principle of opportunistic routing theory, multihop relay decision to optimize the network energy efficiency is made based on the differences among sensor nodes, in terms of both their distance to sink and the residual energy of each other. Specifically, an Energy Saving via Opportunistic Routing (ENS_OR) algorithm is designed to ensure minimum power cost during data relay and protect the nodes with relatively low residual energy. Extensive simulations and real testbed results show that the proposed solution ENS_OR can significantly improve the network performance on energy saving and wireless connectivity in comparison with other existing WSN routing schemes.

MOTIVATION: Hepatitis B virus and hepatitis C virus are the two leading causes resulting in hepatocellular carcinoma (HCC). It is observed that hepatitis C virus (HCV) is relatively difficult to induce HCC compared with hepatitis B virus (HBV). This motivates us to reveal the reasons behind this from the viewpoint of immune genes. RESULTS: To distinguish the immune genes with low-level expression in HBV-induced HCC, but high-level expression in HCV-induced HCC, the concept of distinction immune gene is proposed. A filter is then designed to screen these genes. By using gene positive network with strong correlations between genes, the genes are further filtered to form the set of key distinction immune genes. The 23 key distinction immune genes are screened, which are divided into four clusters, T cells, B cells, immune signalling and major histocompatibility complex. It is evident that the screened genes are important immune genes, which are activated in HCV-induced HCC, but inactivated in HBV-induced HCC. In HCV-induced HCC, the structures of HCV adaptively update, so that they are difficult to be identified by antigens. Therefore, the clinic advice is either to increase the update speed of antigens or reduce the update speed of the viruses during the treatment of HCV-induced HCC. Moreover, it is also advised to add T cells or add the expression levels of T cells to strengthen the ability to kill cancer cells. In contrast, HBV updates slowly, but the immunity system in HBV-induced HCC has been damaged seriously. As a result, the clinic advice is to improve the immune ability of patients subjected to HBV-induced HCC, such as increasing immunoglobulin, T cells and B cells and so forth.