检索结果-内蒙古大学图书馆

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

作者： Zheng, Ran Jiang, Yingxin Wang, Yibo Su, Yongbo Zheng, Long Yao, Pengcheng 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 School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China

ISBN: (纸本)9783031226762

Graph processing has evolved and expanded swiftly with artificial intelligence and big data technology. High-Bandwidth Memory (HBM), which delivers terabyte-level memory bandwidth, has opened up new development possibilities for FPGA-based graph accelerators. However, despite the tremendous expansion of underlying hardware capabilities, existing graph accelerators have not benefited too much. In this paper, we observe that the uniformed on-chip memory hierarchy is the key to the low scalability of existing graph accelerators. We present a novel graph accelerator with a distributed on-chip memory hierarchy called GraphS. The on-chip memory of GraphS is divided into numerous tiny blocks, each of which is assigned to only one Processing Element (PE). Different PEs are connected through a scalable network-on-chip (NoC). For realistic graphs with power-law properties, a degree-aware preprocessing method is designed to balance the workload among different PEs. Our results with various graph algorithms demonstrate that GraphS can outperform state-of-the-art ForeGraph by up to 21.84 ×. © 2023, Springer Nature Switzerland AG.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

RTGA: A Redundancy-free Accelerator for High-Performance Temporal Graph Neural Network Inference 24

RTGA: A Redundancy-free Accelerator for High-Performance Tem...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Yu, Hui Zhang, Yu Tan, Andong Lu, Chenze Zhao, Jin Liao, Xiaofei Jin, Hai Liu, Haikun National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9798400706011

Temporal Graph Neural Network (TGNN) has attracted much research attention because it can capture the dynamic nature of complex networks. However, existing solutions suffer from redundant computation overhead and excessive off-chip communications for TGNN inference because they often rely on redundant graph sampling and repeatedly fetching the features and vertex memory. This paper proposes a redundancy-free accelerator, RTGA, for high-performance TGNN inference. Specifically, RTGA proposes a redundancy-aware execution approach with temporal tree into a novel accelerator design to effectively eliminate unnecessary data processing for fewer redundant computations and off-chip communications and also designs a temporal-aware data caching method to improve data locality for TGNN. We have implemented and evaluated RTGA on a Xilinx Alveo U280 FPGA card. Compared with cutting-edge software solutions (i.e., TGN and TGL) and hardware solutions (i.e., BlockGNN and FlowGNN), RTGA improves the performance of TGNN inference by an average of 473.2x, 87.4x, 8.2x, and 6.9x and saves energy by 542.8x, 102.2x, 9.4x, and 8.3x, respectively. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction 37

ES-Mask: Evolutionary Strip Mask for Explaining Time Series ...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Sun, Yifei Song, Cheng Lu, Feng Li, Wei Jin, Hai Zomaya, Albert Y. 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 Centre for Distributed and High Performance Computing School of Computer Science University of Sydney Australia

ISBN: (纸本)9781577358800

Machine learning models are increasingly used in time series prediction with promising results. The model explanation of time series prediction falls behind the model development and makes less sense to users in understanding model decisions. This paper proposes ES-Mask, a post-hoc and model-agnostic evolutionary strip mask-based saliency approach for time series applications. ES-Mask designs the mask consisting of strips with the same salient value in consecutive time steps to produce binary and sustained feature importance scores over time for easy understanding and interpretation of time series. ES-Mask uses an evolutionary algorithm to search for the optimal mask by manipulating strips in rounds, thus is agnostic to models by involving no internal model states in the search. The initial experiments on MIMIC-III data set show that ES-Mask outperforms state-of-the-art methods. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

HMvisor: dynamic hybrid memory management for virtual machines

引用

Science China(Information Sciences) 2021年第9期64卷 74-89页

作者： Dang YANG Haikun LIU Hai JIN Yu ZHANG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing LabSchool of Computer Science and Technology Huazhong University of Science and Technology

Emerging non-volatile memory(NVM) technologies promise high density, low cost and dynamic random access memory(DRAM)-like performance, at the expense of limited write endurance and high write energy consumption. It is more practical to use NVM combining with the traditional DRAM. However, the hybrid memory management such as page migration becomes more challenging in a virtualization environment because virtual machines(VMs) are unaware of the memory heterogeneity. In this paper, we propose HMvisor, a hypervisor and VM coordinated hybrid memory management mechanism to better utilize DRAM and NVM resources. HMvisor exposes the memory heterogeneity to VMs by mapping virtual NUMA nodes to different physical NUMA nodes. We propose a lightweight and efficient page migration mechanism by decoupling page hotness tracking from page migration. HMvisor performs those operations in the hypervisor and VMs separately, without disrupting the execution of VMs. We also propose a memory resource trading policy to adjust the capacity of DRAM and NVM for each VM, with the monetary cost unchanged. We implement our prototype system based on QEMU/KVM and evaluate it with several benchmarks. Experimental results show that HMvisor can reduce 50% of write traffic to NVM with less than 5% performance overhead. Moreover, the hybrid memory adjustment scheme in HMvisor can significantly improve application performance by up to 30×.

关键词： hypervisor virtual machine non-volatile memory hybrid memory management

来源：评论

学校读者我要写书评

暂无评论

Towards trustworthy blockchain systems in the era of “Internet of value”: development, challenges, and future trends

引用

Science China(Information Sciences) 2022年第5期65卷 250-260页

作者： Hai JIN Jiang XIAO 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 TechnologyHuazhong University of Science and Technology

Since the advent of cryptocurrencies such as Bitcoin, blockchain, as their underlying technologies,has drawn a massive amount of attention from both academia and the industry. This ever-evolving technology inherits the “genes” of distributed systems, offering significant advantages of immutability, transparency,auditability, and tamper-resistance. These benefits help blockchain re-establish public confidence, and hold the significant promise of reliable information sharing and value transfer. Therefore, blockchain has become the foundation of crucial strategic deployments in countries across the world, and the fundamental basis for building the next generation Web 3.0 — “Internet of value”. In this article, we will start with unraveling the essential ingredients of blockchain technology, and showing the characteristics of each of these ingredients in the context of distributed systems. We will then present the core technical challenges that need to be addressed prior to unleashing its full potential, including its performance, scalability, and cross-chain interoperability. Finally, we will introduce the recent developments of blockchain systems, and discuss the future trends of the blockchain ecosystem.

关键词： blockchain distributed systems internet of value challenges development

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Deep Learning with Iterative Gradient Descent Optimization

引用

ACM/IMS Transactions on Data Science 2021年第4期2卷 1–27页

作者： Ding, Xiaofeng Chen, Lin Zhou, Pan Jiang, Wenbin Jin, Hai National Engineering Research Center for Big Data Technology and System Lab 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 Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

Deep learning has achieved great success in various areas and its success is closely linked to the availability of massive data. But in general, a large dataset could include sensitive data and therefore the model should have the capability to avoid privacy leakage. To achieve this aim, many works apply the famous privacy framework named differential privacy into deep learning to preserve privacy. In this article, we propose a novel perturbed iterative gradient descent optimization (PIGDO) algorithm and prove that this algorithm satisfies the differential privacy. Besides, we propose a modified moments accountant (MMA) method to conduct the privacy analysis and obtain a tighter bound of privacy loss compared with the original moments accountant method. A number of experiments demonstrate that our optimization algorithm can not only improve the model accuracy and training speed, but also achieve better privacy guarantees over the state-of-the-art algorithm while reaching the equivalent accuracy. We provide codes for all of our experiments in https://***/CGCL-codes/***. © 2022 Association for computing Machinery.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

High-Performance and Resource-Efficient Dynamic Memory Management in High-Level Synthesis 24

High-Performance and Resource-Efficient Dynamic Memory Manag...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Qinggang Zheng, Long An, Zhaozeng Huang, Haoqin Zhu, Haoran Huang, Yu Yao, Pengcheng Liao, Xiaofei Jin, Hai National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Zhejiang Lab Hangzhou China

ISBN: (纸本)9798400706011

With the merits of high productivity and ease of use, highlevel synthesis (HLS) tools bring hope to fast FPGA-based architecture development. However, their usability and popularity are still limited due to lack of support for dynamic memory management (DMM). Though HLS-compatible DMM solutions have been proposed recently, nevertheless, based on our investigation, none of them can hit high performance (i.e., minimal memory (de-)allocation latency) and resource efficiency (i.e., managing arbitrarily sized memory with minimal FPGA resource consumption) with one stone, seriously limiting their practicality. In response, we propose HeroDMM, a high-performance and resource-efficient dynamic memory manager for HLS. Specifically, HeroDMM organizes the managed memory area with a novel cartesian-like tree (CT) structure, a key to resolving the dilemma between (de-)allocation latency and resource efficiency standing in front of prior efforts. With the CT structure, HeroDMM further devises a delicate memory management algorithm and specializes the hardware implementation for achieving ever-higher performance while ensuring resource efficiency. Results show that HeroDMM outperforms state-of-the-art HLS-compatible DMM solutions by 61.69%∼99.99% in performance improvement and 23.79%∼97.22% in resource consumption savings. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

A Multi-Dimensional Assessment Model and Its Application in E-learning Courses of Computer Science 20

A Multi-Dimensional Assessment Model and Its Application in ...

引用

21st Annual Conference of the Special Interest Group in Information technology Education, SIGITE 2020

作者： Luo, Jiwen Lu, Feng Wang, Tao Key Lab. of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China 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 Wuhan China

ISBN: (纸本)9781450370455

Computer science is a practical discipline. It is always a great challenge to evaluate students' computer practice using computer-aided means for large scale students. We always need to address problems such as suspected plagiarism and deviation of the overall difficulty factor. In this paper, a multi-dimensional assessment model is designed for CS courses based on the detailed practice processing data in an E-learning system. The model comprehensively evaluates the students' learning process and results in three aspects of correctness, originality, and quality detection. Besides, the teacher can easily participate in the assessment according to their needs. The correctness is an essential requirement, and the originality is based on the clustering results of students' behaviors after clone detection to curb homework plagiarism. SonarQube is used to detect code quality and put forward higher requirements for codes. Manual participation intelligence has improved the flexibility and applicability of the model to a certain extent. We applied this model on the EduCoder online education platform and carried out a comprehensive analysis of 485 students in the Parallel Programming Principles and Practice Class of Huazhong University of Science and technology. Experiment results confirm the distinction, rationality, and fairness of the model in assessing student performance. It not only gives students a credible, comprehensive score in large-scale online practical programming courses but also gives teachers and students corresponding suggestions based on the evaluation results. Furthermore, the model can be extended to other online education platforms. © 2020 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Public auditing for secure data storage in cloud through a third party auditor using modern ciphertext 11

Public auditing for secure data storage in cloud through a t...

引用

11th International Conference on Information Assurance and Security, IAS 2015

作者： Hussien, Zaid Alaa Jin, Hai Abduljabbar, Zaid Ameen Yassin, Ali A. Hussain, Mohammed Abdulridha Abbdal, Salah H. Zou, Deqing Cluster and Grid Computing Laboratory Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China University of Basrah Basrah Iraq

ISBN: (纸本)9781467387156

Outsourced data in cloud and computation results are not always trustworthy because data owners lack physical possession and control over the data as a result of virtualization, replication, and migration techniques. Protecting outsourced data from security threats has become a challenging and potentially formidable task in cloud computing;hence, many schemes have focused on ameliorating this problem and on enabling public auditability for cloud data storage security. These schemes drop into two categories: total computation cost and burden on client side. Researchers have used bilinear map technology with public key cryptography. Although this technology is highly efficient, computation time is long and overhead cost is high. The client needs to perform numerous computations to ensure the integrity of data storage. To reduce auditing cost, we propose an efficient and robust scheme to maintain data integrity in cases that involve public auditing. Our scheme adopts modern cipher cryptography with a cryptographic hash function. We consider allowing a third party auditor to preprocess data on behalf of cloud users before uploading them to cloud service providers and then verifying data integrity afterward. Our proposed scheme has important security characteristics, such as privacy, key management, low cost computation, key exchange, low overhead cost, no burden on client side, inability of cloud service providers to create correct verifier respond without data, and one-time key. Finally, efficiency analysis shows that our scheme is faster and more cost-efficient than the bilinear map-based scheme. © 2015 IEEE.

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

Robust image document authentication code with autonomous biometrie key generation, selection, and updating in cloud environment 11

Robust image document authentication code with autonomous bi...

引用

11th International Conference on Information Assurance and Security, IAS 2015

作者： Abduljabbar, Zaid Ameen Jin, Hai Hussien, Zaid Alaa Yassin, Ali A. Hussain, Mohammed Abdulridha Abbdal, Salah H. Zou, Deqing Cluster and Grid Computing Lab Services Computing Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China University of Basrah Basrah Iraq Southern Technical University Basrah Iraq

ISBN: (纸本)9781467387156

Recently, security issues are obstructing the development and using of cloud computing services. Authentication and integrity play an important role in the cloud security, and numerous concerns have been raised to recognize any tampering with exchanges of the image document between two entities (sender and receiver) within the cloud environment. However, none of the existing solutions reduce the probability of known attacks by combining cryptographic hash function with a strong factor that should be periodically changed. For this reason, in this paper we propose a robust one-time image document authentication scheme based on combining non-interactive onetime biometric key and a robust wavelet-based cryptographic hashing scheme. The result of the combination is one-time image document authentication code (OMAC). OMAC is hidden in an image document as a cover image through reversible data embedding steganography. The proposed scheme has several important security attributes, such as key agreement, biometric key management, robust OMAC, invulnerability, and efficiency. In biometric key management, key generation, key selection, and key update algorithms are performed autonomously by the sender and the receiver;thus, no interaction between them is needed. © 2015 IEEE.

关键词： Authentication

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：