检索结果-内蒙古大学图书馆

Evaluating RISC-V Vector Instruction Set Architecture Extension with Computer Vision Workloads

Journal of Computer Science & Technology 2023年第4期38卷 807-820页

作者：李若时彭平邵志远金海郑然 National Engineering Research Center for Big Data Technology and System Huazhong University of Science and Technology Wuhan 430074China Services Computing Technology and System Laboratory Huazhong University of Science and TechnologyWuhan 430074 China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan 430074China

Computer vision(CV)algorithms have been extensively used for a myriad of applications *** the multimedia data are generally well-formatted and regular,it is beneficial to leverage the massive parallel processing power of the underlying platform to improve the performances of CV *** Instruction Multiple Data(SIMD)instructions,capable of conducting the same operation on multiple data items in a single instruction,are extensively employed to improve the efficiency of CV *** this paper,we evaluate the power and effectiveness of RISC-V vector extension(RV-V)on typical CV algorithms,such as Gray Scale,Mean Filter,and Edge *** our examinations,we show that compared with the baseline OpenCV implementation using scalar instructions,the equivalent implementations using the RV-V(version 0.8)can reduce the instruction count of the same CV algorithm up to 24x,when processing the same input ***,the actual performances improvement measured by the cycle counts is highly related with the specific implementation of the underlying RV-V *** our evaluation,by using the vector co-processor(with eight execution lanes)of Xuantie C906,vector-version CV algorithms averagely exhibit up to 2.98x performances speedups compared with their scalar counterparts.

关键词： RISC-V vector extension single instruction multiple data(SIMD) computer vision OpenCV

来源：评论

学校读者我要写书评

暂无评论

SpaHet: A Software/Hardware Co-design for Accelerating Heterogeneous-Sparsity based Sparse Matrix Multiplication 24

SpaHet: A Software/Hardware Co-design for Accelerating Heter...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Huang, Haoqin Yao, Pengcheng An, Zhaozeng Sun, Yufei Hu, Ao Xu, Peng Zheng, Long Liao, Xiaofei Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China

ISBN: (纸本)9798400706011

Sparse general matrix-matrix multiplication is widely used in data mining applications. Its irregular memory access patterns limit the performance of general-purpose processors, thus motivating many FPGA-based hardware innovations in recent years. Nevertheless, existing accelerators fail to efficiently support heterogeneous input matrix sparsity, which is universal in various real-world applications. With in-depth experimental analysis, we observe that their performance is bottlenecked by their fixed tiling mechanisms, which only alleviate the irregularity of one input matrix. Based on the observation, we propose SpaHet, a software/hardware co-design to accelerate heterogeneous-sparsity based sparse matrix multiplication. SpaHet adopts a dual-adaptive sliding window mechanism to cover the reuse characteristics of both input matrices simultaneously. With a specialized exploration algorithm, the window-based mechanism can automatically find the optimal tiling strategy instead of applying a fixed one based on empirical experience. A sparsity-aware merge tree is also proposed to maximize the output matrix reuse via accumulating intermediate results thoroughly. Our results on a Xilinx Alveo U280 accelerator card show that SpaHet outperforms state-of-the-art CPU-, GPU- and FPGA-based solutions by 7.71×, 1.1×, and 2.74× in performance, respectively. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

Towards Redundancy-Free Recommendation Model Training via Reusable-aware Near-Memory Processing 24

Towards Redundancy-Free Recommendation Model Training via Re...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Liu, Haifeng Zheng, Long Huang, Yu Huang, Haoyan Liao, Xiaofei Hai, Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China

ISBN: (纸本)9798400706011

The memory-intensive embedding layer in recommendation model continues to be the performance bottleneck. While prior works have attempted to improve the embedding layer performance by exploiting the data locality to cache the frequently accessed embedding vectors and their partial sums. However, these solutions rely on the static cache, which is inapplicable in the embedding training scenario where the embedding vectors are updated frequently. To this end, this paper proposes ReFree, a redundancy-free near-memory processing (NMP) solution for recommendation model training. Specifically, ReFree identifies the reusable data in realtime for both embedding layer forward and backward stages and leverages a lightweight NMP architecture to enable redundancy-free near-memory acceleration of the entire embedding training process. Evaluation results on real-world datasets show that ReFree outperforms the state-of-the-art solutions by 10.9× and reduces 5.3× energy consumption on average. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning 31

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Zhai, Jiaqi Shi, Xuanhua Huang, Kaiyi Ye, Chencheng Hu, Weifang He, Bingsheng Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore

ISBN: (纸本)9798331506476

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication. © 2025 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Ciphertext-Policy Attribute-Based Encryption with Short Keys

引用

Chinese Journal of Electronics 2025年第4期23卷 655-660页

作者： Peng Xu Yong Tang Wenbin Jiang Hai Jin Deqing Zou Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Ciphertext-policy attribute-based encryption (CP-ABE) allows a user with some attributes to decrypt the ciphertexts associated with these attributes. Though several CP-ABE schemes with the constant size ciphertext were proposed to reduce the communication cost, their master public and secret keys still have the size linear in the total number of attributes. These schemes are unpractical for the attribute-scalable and many-attributes scenario. A new CP-ABE scheme is proposed. Each attribute is mapped to a mathematical value by a combination method. The master public and secret keys of the proposed CP-ABE scheme have the size linear in the binary size of a hash function's range. It has the comparable performance with existing schemes in the aspects like the time costs of encryption and decryption, the expressiveness of access policy and the provable security.

关键词： Costs Encryption

来源：评论

学校读者我要写书评

暂无评论

FedRKG: A Privacy-Preserving Federated Recommendation Framework via Knowledge Graph Enhancement 18th

FedRKG: A Privacy-Preserving Federated Recommendation Framew...

引用

18th International Conference on Green, Pervasive, and Cloud computing, GPC 2023

作者： Yao, Dezhong Liu, Tongtong Cao, Qi Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Computing Science University of Glasgow Glasgow United Kingdom

ISBN: (纸本)9789819998951

Federated Learning (FL) has emerged as a promising approach for preserving data privacy in recommendation systems by training models locally. Recently, Graph Neural Networks (GNN) have gained popularity in recommendation tasks due to their ability to capture high-order interactions between users and items. However, privacy concerns prevent the global sharing of the entire user-item graph. To address this limitation, some methods create pseudo-interacted items or users in the graph to compensate for missing information for each client. Unfortunately, these methods introduce random noise and raise privacy concerns. In this paper, we propose FedRKG, a novel federated recommendation system, where a global knowledge graph (KG) is constructed and maintained on the server using publicly available item information, enabling higher-order user-item interactions. On the client side, a relation-aware GNN model leverages diverse KG relationships. To protect local interaction items and obscure gradients, we employ pseudo-labeling and Local Differential Privacy (LDP). Extensive experiments conducted on three real-world datasets demonstrate the competitive performance of our approach compared to centralized algorithms while ensuring privacy preservation. Moreover, FedRKG achieves an average accuracy improvement of 4% compared to existing federated learning baselines. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Towards High-Performance Graph Processing: From a Hardware/Software Co-Design Perspective

引用

Journal of Computer Science & Technology 2024年第2期39卷 245-266页

作者：廖小飞赵文举金海姚鹏程黄禹王庆刚赵进郑龙张宇邵志远 National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China

Graph processing has been widely used in many scenarios,from scientific computing to artificial *** processing exhibits irregular computational parallelism and random memory accesses,unlike traditional ***,running graph processing workloads on conventional architectures(e.g.,CPUs and GPUs)often shows a significantly low compute-memory ratio with few performance benefits,which can be,in many cases,even slower than a specialized single-thread graph *** domain-specific hardware designs are essential for graph processing,it is still challenging to transform the hardware capability to performance boost without coupled software *** article presents a graph processing ecosystem from hardware to *** start by introducing a series of hardware accelerators as the foundation of this ***,the codesigned parallel graph systems and their distributed techniques are presented to support graph ***,we introduce our efforts on novel graph applications and hardware *** results show that various graph applications can be efficiently accelerated in this graph processing ecosystem.

关键词： graph processing hardware accelerator software system high performance ecosystem

来源：评论

学校读者我要写书评

暂无评论

LSGraph: A Locality-centric High-performance Streaming Graph Engine 24

LSGraph: A Locality-centric High-performance Streaming Graph...

引用

19th European Conference on Computer Systems, EuroSys 2024

作者： Qi, Hao Wu, Yiyang He, Ligang Zhang, Yu Luo, Kang Cai, Minzhi Jin, Hai Zhang, Zhan Zhao, Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom Zhejiang Lab China

ISBN: (纸本)9798400704376

Streaming graph has been broadly employed across various application domains. It involves updating edges to the graph and then performing analytics on the updated graph. However, existing solutions either suffer from poor data locality and high computation complexity for streaming graph analytics, or need high overhead to search and move graph data to ensure ordered neighbors during streaming graph update. This paper presents a novel locality-centric streaming graph engine, called LSGraph, to enable efficient both graph analytics and graph update. The main novelty of this engine is a differentiated hierarchical indexed streaming graph representation approach to achieve efficient data search and movement for graph update and also maintain data locality and ordered neighbors for efficient graph analytics simultaneously. Besides, a locality-aware streaming graph data update mechanism is also proposed to efficiently regulate the distance of data movement, minimizing the overhead of memory access during graph update. We have implemented LSGraph and conducted a systematic evaluation on both real-world and synthetic datasets. Compared with three cutting-edge streaming graph engines, i.e., Terrace, Aspen, and PaC-tree, LSGraph achieves 2.98×-81.08×, 1.46×-12.56×, and 1.26×-10.31× speedups during graph update, while obtaining 1.02×-4.28×, 1.58×-3.55×, and 1.20×-2.72× speedups during graph analytics, respectively. © 2024 Owner/Author.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Anole: A Lightweight and Verifiable Learned-Based Index for Time Range Query on Blockchain Systems 28th

Anole: A Lightweight and Verifiable Learned-Based Index for...

引用

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Chang, Jian Li, Binhong Xiao, Jiang Lin, Licheng Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783031306365

Time range query is essential to facilitate a wide range of blockchain applications such as data provenance in the supply chain. Existing blockchain systems adopt the storage-consuming tree-based index structure for better query performance, however, fail to efficiently work for most blockchain nodes with limited resources. In this paper, we propose Anole, a lightweight and verifiable time range query mechanism, to present the feasibility of building up a learned-based index to achieve high performance and low storage costs on blockchain systems. The key idea of Anole is to exploit the temporal characteristics of blockchain data distribution and design a tailored lightweight index to reduce storage costs. Moreover, it uses a digital signature to guarantee the correctness and completeness of query results by considering the learned index’s error bounds, and applies batch verification to further improve verification performance. Experimental results demonstrate that Anole improves the query performance by up to 10 × and reduces the storage overhead by 99.4 % compared with the state-of-the-art vChain+. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Efficient Remote Memory Paging for Disaggregated Memory Systems 1

引用

22nd International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2022

作者： Wang, Tao Liu, Haikun Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9783031226779

ISBN: (纸本)9783031226762

Memory disaggregation has attracted increasing attention in recent years because it is a cost-efficient approach to scale memory capacity for applications in a data center. However, the latency of remote memory access is a major concern in disaggregated memory systems. This paper presents VANDI, a virtual memory paging mechanism that allows applications to use remote memory pools transparently. VANDI enables effective data caching and prefetching mechanisms to address the problem of high access latency in disaggregated memory systems. VANDI exploits a low-complexity cache replacement strategy to optimize the asynchronous staging queue so that the remote write latency can be significantly reduced. VANDI can also prefetch data in multi-granularity from a remote memory pool in an adaptive manner, and thus further improves the hit rate of the local cache to reduce the read latency of remote memory. Our extensive experiments using micro-benchmarks show that VANDI can improve the performance of typical remote paging system–Infiniswap by up to 15 × –102 ×. VANDI can also improve the performance of state-of-the-art disaggregated memory system–Valet by 1.2 × –2.7 ×. For typical machine learning workloads, VANDI can achieve 20% to 80% performance improvement compared with the state-of-the-art Valet. © 2023, Springer Nature Switzerland AG.

关键词： Paging systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：