Stochastic job stream scheduling method for cipher chip with multi-cryptography

Aiming at the rich of safety requirements of tasks which resulting in random cross access to multi cipher algorithms, a hierarchical hardware scheduling method was presented with associated control based on data identifica-tion. The first level was responsible for distributing tasks to different cipher clusters, and by optimizing the search logic to achieve rapid distribution of data. The second level was responsible for completing the context-related tasks in scheduling order by adding an association control module and association queues. Intermediate state storage module realized the saving of the intermediate state in serial cipher algorithm modes, which was indexed by task ID. Pre-processing module process data inputted by the succeeding tasks. It is proved that the proposed scheduling algo-rithm solves the problem of random cross encryption and decryption in many-to-many communication model of high-speed data stream.     

SIMD图像处理机存储系统研究

为了获得尽可能高的并行计算单元的计算能力,对SIMD图像处理机的存储系统进行了深入研究.该存储系统根据图像处理应用的特点,使用基于编译获得的数据流存取全局信息进行数据流调度,有效地提高了数据存取的速度,满足了并行计算单元对数据存取速度的要求,为SIMD图像处理机系统性能的提高提供了支持.     

雷达系统超精简流式AES加密器设计和优化

为了满足雷达系统对信息加密传输的要求,对高级加密标准（AES）的计数模式（CTR）重新设计,将其改进成流加密的工作模式。通过进行结构折叠和算法重用,有效地减小了资源占用,提高了吞吐率。在Spartan3型号的FPGA上,仅占用728个slice就可以实现276.53Mbps的吞吐率。本设计实现了节省硬件资源的纯逻辑模式和速度较高的分布式内存模式,并且完成实时密钥调度和流水线设计,获得了高可靠性、高吞吐率和高安全性。通过对实际雷达数据的加密实验,验证了该设计的有效性,显示了流加密模式的AES在雷达系统加密传输中的强大潜力。     

高速序列密码算法芯片设计技术

论文介绍了序列密码算法芯片的基本结构,提出了高速序列密码算法芯片的实现技术,并通过实际芯片的设计证明了方法的有效性。     

Parallel Image Processing Technology of Surface Detection System

To improve image processing speed and detection precision of a surface detection system on a strip surface, based on the analysis of the characteristics of image data and image processing in detection system on the strip surface, the design of parallel image processing system and the methods of algorithm implementation have been studied. By using field programmable gate array（FPGA） as hardware platform of implementation and considering the characteristic of detection system on the strip surface, a parallel image processing system implemented by using multi IP kernel is designed. According to different computing tasks and the load balancing capability of parallel processing system, the system could set different calculating numbers of nodes to meet the system＇s demand and save the hardware cost.     

流水行云:支持可扩展的并行分布式流处理系统

数据流处理系统,无论是集中式还是分布式,都需要克服单点瓶颈问题.不仅如此,如果数据流处理系统是静态配置的,那么还会出现处理节点供给不足或者过剩的情况,为此本文提出了一种支持可扩展的并行分布式数据流处理系统-流水行云,该系统根据有状态算子将查询拓扑划分为并行处理的子查询,并且通过有状态算子的分发器和收集器实现了数据流的保序,同时最大化减少并行处理的通信开销,不仅如此,结合负载均衡和重配置的可扩展技术使得该系统能够根据输入负载动态调整处理节点的负载和个数.60个节点组成的集群的实验证明了该系统的可扩展能力.     

基于神经网络混沌吸引子的混合加密

把Diffe-Hellman密钥交换协议和流密码算法相结合,设计了一种基于神经网络混沌吸引子的混合加密算法。算法采用基于混沌吸引子的Diffe-Hellman公钥体制,保证了密钥分发的安全性,同时拥有流密码速度快的优点,提高了加密速度,因此实用性较好,能够满足下一代通信实时快速的需求。分析了算法的安全性和加解密效率,利用vc编程实现算法,并对仿真生成的密钥流和密文进行测试。实验结果表明,算法具有较好的安全性和加解密速度。     

双混沌自同步流密码算法的设计与应用

视频在网络传输过程中需要利用密码进行加密以获得数据的保密性。针对视频存在数据量大和实时性强的特点,提出了一种双混沌自同步流密码算法,以提升加密视频的安全性能和加密效率。密码算法由两个离散时间混沌系统构成：首先,采用混沌反控制方法设计两个三维离散时间混沌系统;然后,将第一个混沌系统的状态变量作为第二个混沌系统的反控制器;最后,将第二个混沌系统迭代产生的状态变量与明文信息进行加密操作。该算法能够有效抵御选择密文攻击与分别征服攻击,具备良好的安全性能。实验测试表明,算法能够达到每秒25帧以上的实时性能,具有良好的加密效率。     

Grid job scheduling using Route with Genetic Algorithm support

In 2006 the Route load balancing algorithm was proposed and compared to other techniques aiming at optimizing the process allocation in grid environments. This algorithm schedules tasks of parallel applications considering computer neighborhoods (where the distance is defined by the network latency). Route presents good results for large environments, although there are cases where neighbors do not have an enough computational capacity nor communication system capable of serving the application. In those situations the Route migrates tasks until they stabilize in a grid area with enough resources. This migration may take long time what reduces the overall performance. In order to improve such stabilization time, this paper proposes RouteGA (Route with Genetic Algorithm support) which considers historical information on parallel application behavior and also the computer capacities and load to optimize the scheduling. This information is extracted by using monitors and summarized in a knowledge base used to quantify the occupation of tasks. Afterwards, such information is used to parameterize a genetic algorithm responsible for optimizing the task allocation. Results confirm that RouteGA outperforms the load balancing carried out by the original Route, which had previously outperformed others scheduling algorithms from literature.     

面向异构信号处理平台的负载均衡算法

针对当前异构信号处理平台中信号处理应用的调度算法优化目标单一且调度结果中处理器负载不均衡的问题，提出了一种基于蚁群优化算法的负载均衡算法。该算法结合蚁群优化算法的快速搜索能力和组合优化能力，以信号处理应用的调度长度和处理器负载均衡为优化目标，对初始信息素矩阵和蚂蚁的遍历顺序进行改进，提出调度长度启发因子和负载均衡启发因子对处理器选择公式进行改进，利用轮盘赌策略确定信号处理应用各子任务分配的处理器，完成信号处理应用的调度。仿真结果表明，该算法得到调度结果在调度长度和负载均衡方面均有改进，可以充分发挥各处理器性能，提高异构信号处理平台的整体效率。     

Load prediction based elastic resource scheduling strategy in Flink

In order to solve the problem that the load of big data stream computing platform fluctuates drastically while the cluster was suffering from the performance bottleneck due to the shortage of computing resources,the load prediction based elastic resource scheduling strategy in Flink (LPERS-Flink) was proposed.Firstly,the load prediction model was set up as the foundation to propose the load prediction algorithm and predict the variation tendency of the processing load.Secondly,the resource judgment model was set up to identify the performance bottleneck and resource redundancy of the cluster while the resource scheduling algorithm was proposed to draw up the resource rescheduling plan.Finally,the online load migration algorithm was proposed to execute the resource rescheduling plan and migrate processing load among nodes efficiently.The experimental results show that the strategy provides better performance promotion in the application with drastically fluctuating processing load.The scale and resource configuration of the cluster responded to the variation of processing load in time and the communication overhead of the load migration was reduced effectively.     

分布式数据流的渐增式聚集维护算法

分布式处理是数据流管理中的主流技术，SWAT算法可以有效地减少聚集操作时通信量．提高分布式系统信道的使用率。文章在SWAT算法的基础上，改变不同结点的更新周期，平衡了算法的计算速度和精确度．并且使用国际通用数据集，在斯坦福大学开发的STREAM系统上进行了测试。对于分布式系统．在数据流数据速率变化比较快的情况下，用时少、误差小。     

基于统计模型的三线阵CCD影像并行匹配算法

在基于统计方法实现CCD影像匹配算法的基础上,提出了CCD影像匹配计算任务的分解方法和计算任务的调度策略,进一步构建了基于统计模型的三线阵CCD影像匹配算法的并行计算方案。并通过实验进行了验证,结果表明,对于CCD影像该并行匹配算法获得了良好的加速比,可扩展性好。适用于超大规模的三线阵CCD影像中同名像点的匹配计算。     

负载均衡集群技术在企业级PDM系统平台的应用

为了确保企业应用系统在大流量的客户端请求下,在提高网络速率有限的情况下,能承受客户端大量并发访问请求,尽可能大地提高系统的处理能力以及高稳定性。本文提供了以负载均衡集群技术为系统平台架构的方案。该方案以产品管理系统软件为应用软件,安装配置结合使用小型服务器热备机制、负载均衡技术以及数据库均衡技术一同实现的系统平台架构。从系统平台底层,改变传统单台系统服务器的使用压力,均衡分配对系统服务的访问负载量,排除单点故障瓶颈,提高整体系统访问速度和工作的生产效率。     

可重构分组密码指令集处理器自动映射方法研究

计算资源与寄存器资源分配是可重构处理器自动并行映射的重要问题,该文针对可重构分组密码指令集处理器的资源分配问题,建立算子调度参数模型和处理器资源参数模型,研究了分组密码并行调度与资源消耗之间的约束关系;在此基础上提出基于贪婪思维、列表调度和线性扫描的自动映射算法,实现了分组密码在可重构分组密码指令集处理器上的自动映射。通过可用资源变化实验验证算法并行映射的有效性,并对AES-128算法的映射效果做了横向对比验证算法的先进性,所提自动映射算法对分组密码在可重构处理中的并行计算研究有一定的指导意义。     

基于RCSW的数据流速度异常检测算法研究

 目前许多应用领域产生数据流的流速不断地震荡,使得面向数据流的挖掘变得困难.系统采用RCSW来完成数据流抽取,提出了实时度T、关键时点集、数据流处理率的概念,并进一步提出了数据流速度异常检测算法.系统监控、预测数据流速,当数据流速异常减速或增速时,系统智能调节环形缓冲区和数据流处理率来应对异常,为解决数据流处理能力与流速、流量与有限空间之间的矛盾提供解决方案.实验表明数据流速度异常检测算法能够保证数据流的挖掘持续正常实施,最大程度的满足系统的实时性要求.     

面向数据流处理的元组跟踪方法

为了保证数据流中的每个元组得到可靠处理,传统的方法需要在内存中保存每个元组,直到它们被数据流处理系统正常处理,因此会带来很大的内存开销。为此提出了一种既能够保证元组得到可靠处理,又能够节省内存开销的元组跟踪方法。该方法包括内存分配策略、元组跟踪单元选择策略和校验值更新策略,这3个策略使得元组跟踪单元只保留元组标识符的异或校验值而不是元组减少内存开销,同时通过改进一致性散列变换实现元组跟踪单元的负载均衡。内存开销和负载均衡的相关实验表明,该方法能够有效实现对元组的跟踪和可靠处理。     

一种分布式并行I/O中新型动态数据调度算法

在研究并行I／O数据调度策略的基础上，提出了一种应用于分布式计算系统中的二次调度自主维护负载平衡的动态I／O调度算法（DIO_TSMB），实验结果表明了算法的有效性，最后指出了并行I／O数据调度的发展趋势。     

A nodes scheduling model based on Markov chain prediction for big streaming data analysis

Streaming data analysis is an important part of big data processing. However, streaming data is difficult to be analyzed and processed in real time because of the rapid data arriving speed and huge size of data set in stream model. The paper proposes a nodes scheduling model based on Markov chain prediction for analyzing big streaming data in real time by following three steps: (i) construct data state transition graph using Markov chain to predict the varying trend of big streaming data; (ii) choose appropriate cloud computing nodes to process big streaming data depending on the predicted result of the data state transition graph; and (iii) assign big streaming data to these computing nodes using the load balancing theory, which ensures that all subtasks are accomplished synchronously. Experiments demonstrate that the proposed scheduling algorithm can fast process big streaming data effectively. Copyright © 2014 John Wiley & Sons, Ltd.     

High-performance and high-concurrency encryption scheme for Hadoop platform

To address the problem that as preventing data leakage on Hadoop platform,the existing encryption schemes suffer from several problems (e.g.,single encryption algorithm,complicated key management,low encryption performance) and they cannot protect data stored in Hadoop effectively,a high-performance encryption and key management scheme for Hadoop was proposed.Firstly,a three-level key management system was extended with the domestic commercial cipher algorithm.Then,a new data structure for encryption zone key to reduce time consumption was designed.Finally,the computing process of data stream in parallel was scheduled.The experimental results show that compared with the existing Hadoop schemes,the proposed scheme can improve the efficiency of key management,and can speed up file encryption.