数据分配策略优化的全条带遥感影像流水线并行处理

如何快速处理大区域覆盖的高分辨率全条带遥感影像是遥感应用急需解决的问题。提出分布式环境下全条带遥感影像并行处理模型。该模型采用了数据并行和流水线并行两级并行方法。首先综合考虑遥感数据及其处理算法的特殊性和分布式环境的异构性,提出一种新的数据分配策略,然后在计算节点引入流水线并行技术。实验结果显示,该模型不仅可以灵活进行复杂的数据处理,还能有效提高数据处理效率。在7个计算节点的环境下,相较于传统的串行处理方法,可获得24.32的加速比。     

基于栅格空间的移动机器人快速路径规划方法

基于栅格空间的节点扩展方式,提出了一种移动机器人快速路径规划的新方法;在引人可视性概念的基础上,通过对传统八邻域法扩展节点进行改进,成功将节点间派生关系由物理相邻引申到逻辑相邻,从而完成任意方向的节点扩展;采用启发式搜索算法D*Lite进行搜索,将应用两种扩展方式的算法在VC环境下分别实现并进行了分析比较;仿真结果表明,新算法不仅极大缩短了路径长度而且显著降低了执行时间。文章提出的算法很好地解决了移动机器人快速路径规划问题。     

基于GPU和矩阵分块的增强植被指数计算

增强植被指数(enhanced vegetation index,EVI)算法是生态遥感领域的重要算法,被广泛应用在植被分类、作物长势检测和自然灾害监测等方面。而随着遥感影像获取能力的不断提升,在使用传统的EVI算法处理数据量较大的影像时会出现内存占用率较高且耗时较长的现象,给应用系统的快速响应带来了不便。针对这种情况,结合EVI算法特点,提出一种基于GPU和矩阵分块的EVI算法,充分利用CPU和GPU各自的优势提高算法执行效率。对于需要分块处理的影像数据,该计算方法根据影像数据大小、系统可用内存和GPU可用显存计算出分块数目,在CPU端将影像数据按照相同的规则进行分块,然后将分块后数据在GPU端进行EVI运算,最后将运算结果返回到CPU。实验结果表明,EVI算法经过改进后的运算速度得到了有效的提高,内存使用率得到有效的降低,验证了被改进算法的优越性。     

一种改进的背景提取算法

背景提取,是利用背景差分法获取目标的重要步骤。针对传统背景提取算法需要处理大数据量的问题,本文算法在传统背景提取算法的基础上,利用一段时间内,相邻图像相同位置的灰度值基本处在同一平稳区间的原理和思路,通过对小数据量的多次操作来获取背景图像。实验结果证明,这种做法可以在使用较少内存使用量的基础上获得比较好的效果,并可快速有效地对背景进行更新。     

地图自动输入系统中快速输入等值线群的算法

研究地图中等值线群的快速输入问题,给出了自动跟踪提取等值线群的有效算法。该算法在跟踪提取各圈等值线的过程中顺以脱离人工干预,能自动识别并处理相邻等值线的碰撞问题,自动弥合等值线上的缺口。     

无线传感器网络中代码分发流水线算法的研究

在无线传感器网络中,为了适应时间、环境和需求的变化,在传感器节点部署以后,不可避免地要对其代码进行更新。介绍了代码分发协议Deluge的基本原理,提出了基于节点距离的流水线算法,新算法有效地解决了Deluge协议在流水线中的隐终端问题,进一步减少了数据包的冲突,提高了流水线的并行度。仿真结果证明了新算法的有效性。     

求解置换流水线调度问题的改进萤火虫优化算法

针对最小化最大完成时间的置换流水线调度问题,提出了一种改进的离散萤火虫优化算法。在传统萤火虫优化算法的基础上,采用基于升序排序的随机键编码方式对萤火虫种群进行离散化处理,使用NEH算法对萤火虫种群进行初始化处理,结合遗传算法的交叉变异思想改进位置更新策略,采用个体变异方式解决孤立个体问题,提高算法的寻优能力。最后通过典型算例对改进算法进行仿真测试,实验结果表明该算法求解置换流水线调度问题时具备很强的寻优能力和鲁棒性,明显优于传统萤火虫优化算法和遗传算法,是解决置换流水线调度问题的一种有效算法。     

扩展job shop模型的启发式批量流水线调度算法

提出了改进的job shop模型,定义了工作中心以及关键节点的概念。将流水线与批量调度策略引入到新的模型中,并在此基础上提出了一个关于扩展job shop模型的启发式批量流水线调度算法。在关键节点进行选择时,通过回溯计算其余产品的开始时间,使用贪心算法选择优先级最高的产品进行排序。该优先级法则由三个优先级变量组合而成,分别囊括了价值高低、时间紧要程度以及剩余加工时间这三个影响因素。进行加工时,设定最小加工批量,在一个工序内实现多套设备的并行加工,同时在两个相邻工序之间实现流水线加工,从而缩短加工时间,提高了生产效率。通过仿真表明该策略能取得较好的结果。     

基于FP-Growth的图上随机游走推荐方法

推荐是促进诸如社交网络等应用活跃度的重要模式,但 庞大 的节点规模以及复杂的节点间关系给社交网络的推荐问题带来了挑战。随机游走是一种能够有效解决这类推荐问题的策略,但传统的随机游走算法没有充分考虑相邻节点间影响力的差异。提出一种基于FP-Growth的图上随机游走推荐方法,其基于社交网络的图结构,引入FP-Growth算法来挖掘相邻节点之间的频繁度,在此基础上构造转移概率矩阵来进行随机游走计算,最后得到好友重要程度排名并做出推荐。该方法既保留了随机游走方法能有效缓解数据稀疏性等特性,又权衡了不同节点连接关系的差异性。实验结果表明,提出的方法比传统随机游走算法的推荐性能更佳。     

基于形态学的网格节点提取算法

针对网格图像节点提取的问题,提出了一种通过对网格图像进行滤波、二值化、细化及去除毛刺,利用形态学处理,最终实现网格图像节点的提取的算法。实验表明该算法能够有效的提取网格图像的节点,为后续的图像匹配等工作确定基础。     

快速不变矩算法基于CUDA的并行实现研究

不变矩自提出以来被广泛应用于目标识别系统中进行特征描述,这需要能够实时计算不变矩值。虽然人们提出了许多不变矩的快速算法,仍无法在单台PC机上实现不变矩的实时计算。本文分析了基于差分矩因子的不变矩快速算法的并行性,提出了一种基于CUDA（Compute Unified Device Architecture）的快速不变矩并行实现方法,并在NVIDIA Tesla C1060 GPU（Graphic Processing Unit）上实现。对所提出算法的计算性能与普通串行算法进行了对比分析。实验结果表明,本文所提出的并行计算方法极大地提高了不变矩的计算速度,可有效地用来进行实时特征提取。     

Cholesky分解细粒度并行算法

本文提出了一种Cholesky分解细粒度流水线并行算法,该算法可以处理任意规模的数据,可以充分开发FP-GA加速器提供的细粒度并行。实验表明,该算法具有很好的可扩展性,在Xilinx XC5 VLX330 FPGA上能够集成36个处理单元(PE),当矩阵的阶为16384、运行频率为200MHz时性能达到14.3GFLOPS。     

ON THE OPTIMALITY OF ALLEN AND KENNEDY'S ALGORITHM FOR PARALLELISM EXTRACTION IN NESTED LOOPS

We explore the link between dependence abstractions and maximal parallelism extraction in nested loops. Our goal is to find, for each dependence abstraction, the minimal transformations needed for maximal parallelism extraction. The result of this paper is that Allen and Kennedy's algorithm is optimal when dependences are approximated by dependence levels. This means that even the most sophisticated algorithm cannot detect more parallelism than found by Allen and Kennedy's algorithm, as long as dependence level is the only information available. In other words, loop distribution is sufficient for detecting maximal parallelism in dependence graphs with levels.     

面向混合异构架构的模型并行训练优化方法

随着混合异构平台的发展,出现了类型不一的加速设备,如何在混合异构平台中充分利用这些不同类型的设备,以及如何在多个计算设备之间部署深度学习模型,而且训练大型和复杂模型的重要性不断提高.数据并行(DP)是应用最广泛的并行化策略,但是如果数据并行训练中的设备数量不断增加,设备之间的通信开销就会成为瓶颈.此外,每个步骤因设备性...     

基于FPGA的多路视频合成与去噪设计

在嵌入式视频处理领域,针对视频实时性要求高的特点,提出一种基于现场可编程门阵列(FPGA)的多路视频合成和去噪方法,包含四路视频合成一路视频的具体实现方案,以及对合成后的一路视频进行中值滤波的去噪算法,使用DDR2SDRAM作为视频的帧缓存,设计中值滤波算法的硬件结构和逻辑结构。系统设计采用Verilog语言进行描述,并在Xilinx的FPGA上进行逻辑综合和硬件测试。实验结果表明,该方法利用FPGA实现了硬件并行和流水线技术,可保证视频的实时处理。     

An automated nondestructive testing system for the surface of pressure pipeline welds

Pressure pipelines are widely used in hydropower generation, oil and gas transmission, and other fields. After years of operation, a pressure pipeline needs regular maintenance to ensure its safety. At present, manual detection methods are unable to meet this demand. An automatic pressure pipeline detection technology is urgently needed to achieve improved efficiency and accuracy. On the basis of the above requirements, a wall-climbing robot is designed for automatic pressure pipe inspection and maintenance tasks. Moreover, rapid nondestructive testing of welds on the inner surface of pressure pipelines was performed, and a weld tracking function was developed for wall-climbing robots. We propose an algorithm framework for weld recognition and centerline extraction by combining computer vision technology with traditional image processing technology using visual images. The experimental verification of the wall-climbing robot designed in this paper and the algorithm framework for weld recognition and centerline extraction were performed based on actual pressure pipelines. The results show that the algorithm framework developed based on the wall-climbing robot equipped with an industrial camera for pressure pipeline weld detection can achieve greatly improved efficiency, and the actual weld identification accuracy can exceed 90%, which is very meaningful for practical applications.     

Memory Renaming: Fast, Early and Accurate Processing of Memory Communication

As processors continue to exploit more instruction level parallelism, greater demands are placed on the performance of the memory system. In this paper, we introduce a novel modification of the processor pipeline called memory renaming . Memory renaming applies register access techniques to load and store instructions to speed the processing of memory traffic. The approach works by accurately predicting memory communication early in the pipeline and then re - mapping the communication to fast physical registers. This work extends previous studies of data value and dependence speculation. When memory renaming is added to the processor pipeline, renaming can be applied to 30-50 % of all memory references, translating to an overall improvement in execution time of up to 14 % for current pipeline configurations. As store forward delay times grow larger, renaming support can lead to performance improvements of as much as 42 %. Furthermore, this improvement is seen across all memory segments—including the heap segment which has often been difficult to manage efficiently.     

一种高效的基于局部特征的显著区域检测算法

图像特征提取是图像/视频检索问题的关键。研究人员发现,假如对整张图像或视频帧做特征提取,会产生大量的特征信息,从而影响图像/视频帧的匹配时间。由于人们通常只对图像中部分关键的区域感兴趣,因此在对图像做局部特征提取时可以先对图像进行显著区域检测,排除非关键区域上的特征信息,从而减低匹配所需的特征点数,提高匹配的处理速度。但是由于传统的显著区域检测算法计算复杂,会对图像特征提取过程产生额外的时间开销。提出一种快速的显著区域检测算法,根据局部特征提取算法特征检测阶段得到的特征点分布,利用最大子矩阵和算法,在损失较小的准确度的情况下快速检测出图像的显著区。     

五帧差分和边缘检测的运动目标检测

为了改进传统三帧差分的运动目标检测方法易出现的空洞和与虚假边缘的现象, 提出了一种基于五帧差分和边缘检测相融合的运动目标检测方法。该算法首先利用优化的Canny边缘检测算法快速提取五帧连续图像的边缘图像, 然后对五帧连续的边缘图像进图像的五帧差分运算, 最后通过阈值分割和形态学处理完成对目标的提取。该方法计算简单, 实验结果表明, 该算法准确率高, 连通性好, 能满足实时性检测的要求。     

A case study of different task implementations for multioutput stages in non-trivial parallel pipeline applications

Task-based libraries, such as Intel’s Threading Building Blocks (TBB), are promising tools that help programmers to develop parallel code in a productive way, thanks to high-level constructors which simplify the chore of efficiently exploiting system resources. In this paper we focus on one type of task parallelism, pipeline parallelism, which is becoming an increasingly popular parallel programming pattern for streaming applications in the domain of digital signal processing, graphics, compression and encryption. Specifically, TBB provides a high-level template to express pipeline parallelism, but it is limited to representing simple pipeline structures. We address the issue of non-trivial parallel pipeline structures in which one or more stages in the pipeline have more items leaving than arriving, a problem for which the current TBB pipeline template does not provide support. In this work, we describe a new Multioutput filter that we have incorporated into the TBB pipeline framework to deal with these multioutput stages. Using real world streaming applications from different computational domains (dedup and scenerecog), we also compare the performance of our implementation using the Multioutput filter in the TBB pipeline template to other more complex TBB task-based implementations that only use the standard filters. We also develop new analytical models for each implementation to better understand the resources utilization in each case. Performance evaluation and analysis shows that the implementation based on the Multioutput filter outperforms the other solutions because: it promotes finer task parallelism, which is more suited to the TBB task-stealing mechanism in order to better exploit the resources; and it also reduces the overheads related to memory and task management.