检索结果-内蒙古大学图书馆

IEEE Transactions on Sustainable computing 2024年

作者： Zhang, Xinmin Wu, Song Gu, Lin He, Qiang 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 Wuhan Hubei430074 China

This paper presents ChestBox, a novel approach that utilizes state functions to facilitate low-latency state sharing for stateful serverless computing. When an application function needs to share a state, the state function creates a memory space with Linux's shared memory object to store the state. Other application functions can then read the state directly from the shared memory. ChestBox enables fast state sharing that avoids excessive memory overhead without compromising on-demand resource allocation compared to existing solutions. This effectively reduces the energy consumption of serverless computing and promotes sustainable computing. The implementation of ChestBox on Apache OpenWhisk unearths two major implementation challenges, which we address with respective optimization techniques, i.e., state function channel and state swapping. The evaluation of ChestBox with four real-world applications shows that compared with the state-of-The-Art approach, it can reduce state-sharing latency by up to 99.71%, while reducing execution costs by 24.59% and storage costs by 99.76%. © 2016 IEEE.

关键词： Storage allocation (computer)

来源：评论

学校读者我要写书评

暂无评论

Efficient Time-Evolving Stream Processing at Scale

arXiv

引用

arXiv 2018年

作者： Huang, Yu Services Computing Technology and System Lab Big Data Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

—Time-evolving stream datasets exist ubiquitously in many real-world applications where their inherent hot keys often evolve over times. Nevertheless, few existing solutions can provide efficient load balance on these time-evolving datasets while preserving low memory overhead. In this paper, we present a novel grouping approach (named FISH), which can provide the efficient time-evolving stream processing at scale. The key insight of this work is that the keys of time-evolving stream data can have a skewed distribution within any bounded distance of time interval. This enables to accurately identify the recent hot keys for the real-time load balance within a bounded scope. We therefore propose an epoch-based recent hot key identification with specialized intra-epoch frequency counting (for maintaining low memory overhead) and inter-epoch hotness decaying (for suppressing superfluous computation). We also propose to heuristically infer the accurate information of remote workers through computation rather than communication for cost-efficient worker assignment. We have integrated our approach into Apache Storm. Our results on a cluster of 128 nodes for both synthetic and real-world stream datasets show that FISH significantly outperforms state-of-the-art with the average and the 99th percentile latency reduction by 87.12% and 76.34% (vs. W-Choices), and memory overhead reduction by 99.96% (vs. Shuffle Grouping). Copyright © 2018, The Authors. All rights reserved.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Scheme for Ensuring Data Security on Cloud Data Storage in a Semi-trusted Third Party Auditor

Scheme for Ensuring Data Security on Cloud Data Storage in a...

引用

International Conference on Computer Science and Network technology

作者： Zaid Alaa Hussien Hai Jin Zaid Ameen Abduljabbar Mohammed Abdulridha Hussain Salah H. Abbdal Deqing Zou Cluster and Grid Computing Lab Big Data Technology and System Lab Services Computing Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781467381741

Cloud computing is a promising information technology service that allocates and reallocates resources when a client requires virtual data storage and network facility at any time and place. Cloud computing provides large data storage and management services at the lowest cost. Thus, it is crucial for many organizations and clients who seek such services. Data security and integrity are necessary and play important roles. However, these two issues are facing significant challenges. Therefore, a robust scheme is required to ensure security and privacy while transmitting or storing data in the cloud storage environment. We propose an efficient and robust scheme to ensure data security in a semi-trusted third party auditor. Our scheme adopts an advanced encryption standard to support data owner privacy, a cryptography hash function to maintain data owner integrity, and elliptic curve cryptography to ensure data confidentiality, correctness, and security when transmitting data over unsecure channels. A security analysis confirms that our scheme can withstand man-in-the-middle attack and provides data correctness.

关键词： Cloud storage data security elliptic curve cryptography hash function integrity semi-trusted third party auditor Data Security Elliptic curve cryptography cryptography Cloud computing computer information security Data Storage Scheme auditor Third party customers Management services Transmitting Data

来源：评论

学校读者我要写书评

暂无评论

RAHP: A Redundancy-aware Accelerator for High-performance Hypergraph Neural Network 57

RAHP: A Redundancy-aware Accelerator for High-performance Hy...

引用

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Yu, Hui Zhang, Yu He, Ligang Zhao, Yingqi Li, Xintao Xin, Ruida Zhao, Jin Liao, Xiaofei Liu, Haikun He, Bingsheng Jin, Hai School of Computer Science and Technology Huazhong University of Science and Technology Natl. Eng. Res. Ctr. for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan430074 China University of Warwick Department of Computer Science United Kingdom National University of Singapore Singapore

ISBN: (纸本)9798350350579

Hypergraph Neural Network (HyperGNN) has emerged as a potent methodology for dissecting intricate multilateral connections among various entities. Current software/hardware solutions leverage a sequential execution model that relies on hyperedge and vertex indices for conducting standard matrix operations for HyperGNN inference. Yet, they are impeded by the dual challenges of redundant computation and irregular memory access overheads. This is primarily due to the frequent and repetitive access and updating of a number of feature vectors corresponding to the same hyperedges and vertices. To address these challenges, we propose the first redundancy-aware accelerator, RAHP, which enables high performance execution of HyperGNN inference. Specifically, we present a redundancy-aware asynchronous execution approach into the accelerator design for HyperGNN to reduce redundant computations and off-chip memory accesses. To unveil opportunities for data reuse and unlock the parallelism that existing HyperGNN solutions fail to capture, it prioritizes vertices with the highest degree as roots, prefetching other vertices along the hypergraph structure to capture the common vertices among multiple hyperedges, and synchronizing the computations of hyperedges and vertices in real-time. By such means, this facilitates the concurrent processing of relevant hyperedge and vertex computations of the common vertices along the hypergraph topology, resulting in smaller redundant computations overhead. Furthermore, by efficiently caching intermediate results of the common vertices, it curtails memory traffic and off-chip communications. To fully harness the performance potential of our proposed approach in the accelerator, RAHP incorporates a topology-driven data loading mechanism to minimize off-chip memory accesses on the fly. It is also endowed with an adaptive data synchronization scheme to mitigate the effects of conflicting updates of both hyperedges and vertices. Moreover, RAHP emplo

关键词： accelerator HyperGNN redundancy-aware

来源：评论

学校读者我要写书评

暂无评论

Software-Defined, Fast and Strongly-Consistent Data Replication for RDMA-Based PM Datastores

Software-Defined, Fast and Strongly-Consistent Data Replicat...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Haodi Lu Haikun Liu Chencheng Ye Xiaofei Liao Fubing Mao Yu Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computing Science and Technology Huazhong University of Science and Technology China

Modern storage systems typically replicate data on multiple servers to provide high reliability and availability. However, most commercially-deployed datastores often fail to offer low latency, high throughput, and strong consistency at the same time. This paper presents Whale, a Remote Direct Memory Access (RDMA) based primary-backup replication system for in-memory datastores. Whale achieves both low latency and strong consistency by decoupling metadata multicasting from data replication for all backup nodes, and using an optimistic commitment mechanism to respond to client write requests earlier. Whale achieves high throughput by propagating writes from the primary node to backup nodes asynchronously via RDMA-optimized chain replication. To further reduce the cost of data replication, we design a log-structured datastore to fully exploit the advantages of one-sided RDMA and Persistent Memory (PM). We implement Whale on a cluster equipped with PM and InfiniBand RDMA networks. Experimental results show that Whale achieves much higher throughput and lower latency than state-of-the-art replication protocols.

关键词：

来源：评论

学校读者我要写书评

暂无评论

china in the eyes of news media:a case study under COVID-19 epidemic

引用

Frontiers of Information technology & Electronic Engineering 2021年第11期22卷 1443-1457页

作者： Hong HUANG Zhexue CHEN Xuanhua SHI Chenxu WANG Zepeng HE Hai JIN Mingxin ZHANG Zongya LI National Engineering Research Center for Big Data Technology and System Huazhong University of Science and TechnologyWuhan430074China Services Computing Technology and System Lab Huazhong University of Science and TechnologyWuhan430074China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan430074China School of Journalism and Information Communication Huazhong University of Science and TechnologyWuhan430074China

As one of the early COVID-19 epidemic outbreak areas,china attracted the global news media’s attention at the beginning of *** the epidemic period,Chinese people united and actively fought against the ***,in the eyes of the international public,the situation reported about china is not *** better understand how the international public portrays china,especially during the epidemic,we present a case study with big data *** aim to answer three questions:(1)What has the international media focused on during the COVID-19 epidemic period?(2)What is the media’s tone when they report china?(3)What is the media’s attitude when talking about china?In detail,we crawled more than 280000 pieces of news from 57 mainstream media agencies in 22 countries and made some interesting *** example,international media paid more attention to Chinese livelihood during the COVID-19 epidemic *** March and April,“progress of Chinese vaccines,”“specific drugs and treatments,”and“virus outbreak in U.S.”became the media’s most common *** terms of news attitude,Cuba,Malaysia,and Venezuela had a positive attitude toward china,while France,Canada,and the United Kingdom had a negative *** study can help understand china’s image in the eyes of the international media and provide a sound basis for image analysis.

关键词： Country image COVID-19 epidemic Topic mining Entity Tone of news Emotion

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Processing Guarantees on Performance of Stream Data Processing

Exploring the Impact of Processing Guarantees on Performance...

引用

2017 17th IEEE International Conference on Communication technology (ICCT 2017)

作者： Syed Muhammad Abrar Akber Changfu Lin Hanhua Chen Fan Zhang Hai Jin Cluster and Grid Computing Lab Services Computing Technology and System Lab Big Data Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology

Processing semantics ensure tuple processing guarantees during system recovery from failures. It determines whether particular tuples are re-processed or not upon system recovery. Processing semantics facilitate to maintain real-time response as well as correctness of results in stream data processing. Existing literature is in real deficit to provide sufficient resources exclusively on processing semantics. This work focuses on reviewing processing semantics in stream data processing *** article aims at exploring the impact of processing guaran-tees on performance of stream data processing. We summarize current research directions to guarantee processing semantics,based on prominent stream processing engines. Furthermore,we compare throughput for a couple of representative stream processing engines under all possible processing *** experiments show that at-most once processing guarantee provides the highest throughput among other guarantees. Lastly,challenges for further research are also discussed in this paper.

关键词： stream data processing processing semantic processing guarantee at-least once at-most once exactly-once

来源：评论

学校读者我要写书评

暂无评论

Automatic power-aware reconfiguration of processor resource in virtualized clusters

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2011年第7期48卷 1123-1133页

作者： Jin, Hai Deng, Li Wu, Song Shi, Xuanhua Zhou, Like Key Laboratory of Services Computing Technology and System Huazhong University of Science and Technology Ministry of Education Wuhan 430074 China Key Laboratory of Cluster and Grid Computing of Hubei Province Huazhong University of Science and Technology Wuhan 430074 China

Virtualization provides significant benefits of system maintenance, load balancing, fault tolerance, and power-saving in clusters or data centers. It also enables dynamic reconfiguration of computing resource for application environment. However, current dynamic resource control approaches mainly focus on how to satisfy the application-level quality of service (QoS) when application workloads vary with time. They are driven by application performance, which is often specific to certain class of applications and also weakens the response capability of control systems. In this paper, a resource-use-status-driven resource reconfiguration scheme (RUSiC) is presented to automatically adapt to dynamic workload changes to meet the demands of application performance. According to the new characteristics introduced by system virtualization, the scheme is designed to be a two-layer resource reconfiguration model to exactly grasp the demands of applications. Based on real resource use status, the scheme adjusts proper resource configuration for applications in time. Furthermore, the scheme introduces power-saving into resource reconfiguration process and avoids considerable unnecessary power and cooling consumption by reducing the number of active physical nodes in a new resource configuration. Experiments demonstrate that the scheme can quickly detect and respond to shifting resource demands as application workloads change over time.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Virtual machine VCPU scheduling in the multi-core environment: Issues and challenges

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2011年第7期48卷 1216-1224页

作者： Jin, Hai Zhong, Alin Wu, Song Shi, Xuanhua Key Laboratory of Services Computing Technology and System Huazhong University of Science and Technology Ministry of Education Wuhan 430074 China Key Laboratory of Cluster and Grid Computing of Hubei Province Huazhong University of Science and Technology Wuhan 430074 China

The policies and mechanisms of VCPU (virtual CPU) scheduling in a virtual machine system are key factors to determine the system performance. Because the architecture of the software stack in the virtual machine system is different from the traditional computer systems, when scheduling the VCPUs in virtual machines, simply adopting scheduling strategies and algorithms of existing operating systems without any modifications can lead to drastic degradation of the system performance. Moreover, with the multi-core technology being employed for physical processors, the complexity of the VCPU scheduling is increased. Firstly, the architecture of the virtual machine system and its two-stage scheduling framework are depicted and analyzed in detail in this paper. Because the deterministic mapping relationship between application threads and physical cores is difficult to establish in the two-stage framework, and part functions of operating systems move down to virtual machine monitor, VCPU scheduling will confront many problems and challenges that mainly embody four aspects: the semantic gap between guest operating systems and a virtual machine monitor, the synchronization mechanisms in a multiprocessor operating system, the structure of shared cache in multi-core processors and emerging asymmetric multi-core structure. And then advantages and limitations of the existing solutions for these problems are discussed and analyzed deeply, and suggestions for further researches are presented.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Hiding Policy and Checking Policy Consistency

A New Approach for Hiding Policy and Checking Policy Consist...

引用

International Conference on Information Security and Assurance, ISA

作者： Deqing Zou Zhensong Liao Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Huazhong University of Science and Technology Wuhan China

Automated trust negotiation (ATN) is a new means to establish trust relationship through the mutual exchange of access control policy and credentials in the open and distributed environments. In ATN, access control policy plays a key role in protecting resources from unauthorized access. In practice, a policy may contain sensitive information, and its disclosure may cause damages. In order to protect the sensitive policy or its content, the policy is usually designed complex. Even worse, the policy may be self contradictory, which would lead the negotiation to fail. To solve such a problem, a new approach for checking policy consistency is proposed in the paper. In the approach, we analyze why the policy inconsistency happens and specify how to avoid it by simplifying a compound policy. Meanwhile, the approach is proved useful to hide policy by presenting some useful theorems to generate minimal policy set and credential set.

关键词： Access control Protection Privacy Internet Information security grid computing Computer science Resource management Application software National security

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：