数据流程序动态调度与优化

为了解决数据流编程模型的可用性问题,使其能在兼顾程序并行性的前提下适用于动态数据交互速率的流应用,设计了一种动态调度与静态优化相结合的数据流编译系统。编译器以COStream语言编写的源程序为输入,通过对源程序进行分析,以动态速率的数据通信边作为边界划分程序到粗粒度的子图,在子图内部应用静态优化。根据子图的每个计算单元的工作量估计计算资源的使用状况,实现子图内计算单元到处理器核的映射,经过阶段划分分配子图内计算单元到相应流水阶段。在运行时,每个子图在各个处理器核上均启动一个线程,通过对线程间通信的优化,避免了运行时多个线程对同一段内存同时读写产生的同步开销,减少了线程的上下文切换次数。使用信号量控制子图内线程间的同步,基于各子图计算单元运行时数据交互速率并结合当前线程的状态,动态调度各个子图的执行,构建动态的软件流水线,生成相应多线程目标代码。实验以通用X86-64多核处理器作为实验平台,测试和分析数据流编译的性能。实验结果表明,编译系统可以实现动态数据交互速率的数据流应用,扩大了编译系统可用性并且具有一定加速效果。     

OKCM: improving parallel task scheduling in high-performance computing systems using online learning

The Journal of Supercomputing - Task scheduling is becoming increasingly important in large-scale high-performance computing real-time systems as the parallel scale, number and types of task...     

Profit maximization based task scheduling in hybrid clouds using whale optimization technique

ABSTRACT

In cloud computing system, task scheduling plays an important key role. The tasks provided by the user to allocate in cloud have to pay for the share of resources that are used by them. The requirement of task scheduling in the cloud environment has become more and more complex, and the amount of resources and tasks is growing rapidly. Therefore, an efficient task-scheduling algorithm is necessary for allocating the task efficiently in the cloud, which can achieve minimum resource utilization, minimum processing time, high efficiency, and maximum profit. In hybrid clouds to maximize the profit of a private cloud while guaranteeing the service delay bound of delay-tolerant tasks is studied in this article. Here, a new metaheuristic technique inspired from the bubble-net hunting technique of humpback whales, namely whale optimization algorithm (WOA), has been applied to solve the task-scheduling problem. Then WOA algorithm is compared with existing algorithms such as artificial bee colony algorithm (ABC) and Genetic algorithm (GA). The experimental result shows that the proposed WOA algorithm greatly increases the efficiency and achieves maximum profit for the private cloud.     

Dynamic scheduling of task graphs in multi-FPGA systems using critical path

SRAM-based FPGAs feature high performance and flexibility. Thus, they have found many applications in modern high-performance computing (HPC) systems. These systems suffer from the limitation of the computing resources problem for running HPC applications. Therefore, multi-FPGA systems have been emerged to alleviate such resource limitations. In this regard, efficient scheduling strategies are required to dynamically steer the execution of applications—represented as task graphs—on a set of connected FPGAs. In this paper, a heuristic-based dynamic critical path-aware scheduling technique named CPA is presented to schedule task graphs on multi-FPGA systems. The proposed technique, by considering the computation and communication capabilities of FPGAs, dynamically assigns priority to tasks in different steps in order to achieve better makespans. The proposed technique has been evaluated by conducting several experiments on real-world and three different shapes of random task graphs with different number of tasks, and its efficiency has been compared with that of three task graph scheduling approaches. The obtained results demonstrate that the proposed CPA technique outperforms well-known heuristic scheduling strategies and improves their makespan by 13.47% on average. In addition, the experiments show that the proposed technique generates the schedules in the order of milliseconds and the average of its yielded makespans is 12.05% longer than that of an optimum schedule.

     

考虑任务均衡的加油车动态调度问题

为了提高机场资源利用率以及航班的正点率,合理调度机场加油车为航班进行燃油加注服务势在必行。考虑到航班实际时刻的不可预知性,需建立动态规划时间窗,为窗口依据航班预计时刻捕捉到的航班构建机场车辆调度模型,利用自适应分支定价算法求解模型,从而配置车辆与人员,规划车辆的行驶路线,衔接任务,实现车辆行驶时间最短,加油员工作量均衡的目的。在华北某机场真实数据上进行仿真实验,结果表明,自适应分支定价算法优化下的车辆行驶时间与加油员工作量的标准差分较节约算法分别减小1.38%和7.47%,验证了算法的优势,且算法在机场其他地面服务规划问题中同样适用。     

面向温度优化的片上网络任务调度方法

随着片上网络规模的扩大和研究的逐步深入,如何将芯片上众多的任务进行合理的调度成为系统温度优化的关键之一。针对片上网络任务调度问题, 提出一种基于最短曼哈顿距离的任务调度SMDS方案。该策略充分考虑核通信图中通信节点对之间最短曼哈顿路径,通过搜索算法寻找任务调度的目的节点,使用模拟退火算法确定任务调度对。实验结果显示,与传统的分布式任务调度 DTM策略相比,针对6*6、8*8和10*10的拓扑结构,SMDS实验方案在迁移次数方面的平均优化率分别为2208%、21.74%和23.02%。在平均跳数方面的平均优化率分别为24.04%、29.18%和23.04%,实现了系统温度优化。     

基于入侵杂草蝙蝠双子群优化的装备保障编组协同任务规划

针对装备保障编组协同任务规划问题,构建以时效优先为目标,考虑保障任务时序逻辑关系、任务执行质量和保障编组占用冲突等复杂约束以及保障编组能力更新机制的数学模型,提出一种基于入侵杂草蝙蝠混合算法的双子群任务规划方法.首先,采用佳点集初始化方法,在解空间生成具有均匀分布特征的种群;其次,设计具有修复操作的解编码和任务优先排序,实现任务-编组-时间的匹配和冲突消解;再次,划分双子群,利用入侵杂草优化算法和Fuch混沌蝙蝠优化算法协同进化;最后,应用重组算子引导种群进化,均衡算法全局探索和局部搜索能力.仿真算例表明,所提方法可对大规模复杂任务分配方案进行精确高效的求解.     

可信禁忌粒子群优化网格任务调度算法

网格任务调度是典型的NP（Non-Polynomial）难题,基于粒子群优化智能算法,提出一种新的任务调度算法,目标是使所有任务整体完成时间最小。算法首先随机产生一群粒子,然后对粒子的位置和速度不断迭代,获得可以接受的任务调度方案,并从中选择一组信任度最高的作为较优解,再利用禁忌搜索算法由较优解获得最优解。仿真实验结果表明,与遗传算法相比更适合于求解规模较大的网格任务调度问题。     

Dynamic hard-real-time scheduling using genetic algorithm for multiprocessor task with resource and timing constraints

Most publications in shop scheduling area focus on the static scheduling problems and seldom take into account the dynamic disturbances such as machine breakdown or new job arrivals. Motivated by the computational complexity of the scheduling problems, genetic algorithms (GAs) have been applied to improve both the efficiency and the effectiveness for NP-hard optimization problems. However, a pure GA-based approach tends to generate illegal schedules due to the crossover and the mutation operators. It is often the case that the gene expression or the genetic operators need to be specially tailored to fit the problem domain or some other schemes may be combined to solve the scheduling problems. This study presents a GA-based approach combined with a feasible energy function for multiprocessor scheduling problems with resource and timing constraints in dynamic real-time scheduling. Moreover, an easy-understood genotype is designed to generate legal schedules. The results of the experiments demonstrate that the proposed approach performs rapid convergence to address its applicability and generate good-quality schedules.     

一种多核系统任务调度算法动态度量方法

任务调度算法的优劣直接影响系统的功能和性能,对其进行功能验证和性能评价具有很强的现实意义。本文改进IMC构建多核系统任务调度算法的功能模型,扩展aCSL从逻辑层次上刻画任务调度算法的性能指标,并基于改进的IMC和扩展的aCSL提出了一种多核系统任务调度算法动态度量方法实现对任务调度算法的功能验证和性能评价。用例分析表明本文提出的动态度量方法能有效对任务调度算法进行功能和性能的描述和度量,为多核系统任务调度算法的正确执行提供了有力支撑。     

Dynamic task scheduling modeling in unstructured heterogeneous multiprocessor systems

An algorithm is proposed for scheduling dependent tasks in time-varying heterogeneous multiprocessor systems, in which computational power and links between processors are allowed to change over time. Link contention is considered in the multiprocessor scheduling problem. A linear switching-state space-modeling paradigm is introduced to enable theoretical analysis from a system engineering perspective. Theoretical analysis of this model shows its robustness against changes in processing power and link failure. The proposed algorithm uses a fuzzy decision-making procedure to handle changes in the multiprocessor system. The efficiency of the proposed algorithm is illustrated by several random experiments and comparison against a recent benchmark approach. The results show up to 18% average improvement in makespan, especially for larger scale systems.     

基于正交自适应鲸鱼优化的云计算任务调度

针对任务调度中存在的任务完成时间长、系统执行任务成本高且系统负载不均衡等问题,提出了一种基于正交自适应鲸鱼优化算法（OAWOA）的云计算任务调度方法。首先,将正交试验设计（OED）应用于种群初始化和全局搜索阶段,以提升和维持种群的多样性,避免算法过早陷入局部收敛状态;然后,利用自适应指数递减因子和双向搜索机制,来进一步加强算法的全局搜索能力;最后,对适应度函数进行优化,从而使算法实现多目标优化。通过仿真实验将所提的算法与鲸鱼优化算法（WOA）、粒子群优化（PSO）算法、蝙蝠算法（BA）以及其他两种改进的WOA进行比较。实验结果表明,在任务规模为50和500时所提算法都取得了更好的收敛效果,并且得到的系统执行任务的总时间和总成本均低于其他几种算法,同时负载均衡度仅低于BA。可见,所提算法在降低系统执行任务的总时间和总成本以及提高系统负载均衡方面均表现出了显著的优势。     

基于资源状态蚁群算法的云计算任务分配

针对云计算中的任务分配问题,分析任务资源之间的数学模型,提出一种基于资源状态蚁群算法,相对一般蚁群算法,加入虚拟机实时状态,更精确地表达云计算任务分配的问题.通过CloudSim工具设计仿真实验,实验结果表明,与最近Cristian Mateos提出的蚁群改进算法相比,该算法在任务完成时间、算法稳定收敛方面取得了较好表现,以RR算法为基准,该算法提高后的时间比例稳定在RR算法任务完成时间的60％～65％,稳定性提高4.7倍.     

卫星任务调度统一化建模与多策略协同求解方法

针对卫星任务调度“一星一系统”、测运控分离的现状,以卫星执行任务产生的星上独立事件和星地协同事件作为调度对象,以事件可执行时机作为调度资源,建立卫星任务调度统一化约束满足模型,将传统运控任务调度与测控任务调度纳入统一的建模方法.为保障模型的通用性和适应性,设计包含构造启发式、智能优化和针对性算法改进的多策略协同求解方法,搭建卫星任务调度算法与调度模型松耦合、模块化的系统架构.实验测试表明,所提出方法能够弥补传统模型在敏捷遥感卫星任务调度和高轨卫星测控调度场景下的局限性,在Benchmark问题和实际应用场景中均表现出良好的适用性和优化效果.     

多种任务调度混合的IB-LBM并行优化方法

在使用浸入边界-格子玻尔兹曼方法（IB-LBM）求解流场时,为了得出比较精确的结果,往往需要规模较大、较密集的流场网格,这就会造成模拟过程时间长的问题。为了提高模拟的效率,利用IB-LBM局部计算的特点,结合OpenMP中三种不同的任务调度方式,给出了IB-LBM的并行优化方法。在并行优化中混合使用三种任务调度方式,以弥补单一任务调度造成的负载不均衡问题;将IB-LBM进行结构化分解,测试每一结构部分的最优调度方式,根据实验结果选择最优的调度组合方式,而在不同线程数下,最优的组合方式是不同的。优化结果通过并行加速比来检验,可以得出：在线程数较少的情况下,加速比趋近于理想状态;在线程数较多的情况下,虽然线程开辟和销毁的额外时间消耗对性能的优化产生了影响,模型的并行性能仍有了很大的提升。流场的模拟结果显示,在进行并行优化后, IB-LBM对流固耦合问题模拟的准确性并没有受到影响。     

改进离散粒子群算法及其在飞机装配任务调度中的应用研究

论文阐述了飞机装配过程中任务调度的重要意义,介绍了当前调度算法的 研究现状,对离散粒子群优化算法进行研究并在此基础上提出一种基于激励原则的改进离散 粒子群优化算法。最后以某型飞机尾段装配流程为对象对改进后的算法进行验证,得到良好 效果。     

An infrastructure for embedded systems using task scheduling

Task scheduling in heterogeneous environments such as cloud data centers is considered to be an NP-complete problem. Efficient task scheduling will lead to balance the load on the virtual machines (VMs) thereby achieving effective resource utilization. Hence there is a need for a new scheduling framework to perform load balancing amid considering multiple quality of service (QoS) metrics such as makespan, response time, execution time, and task priority. Multi-core Web server is difficult to achieve dynamic balance in the process of remote dynamic request scheduling, so it is necessary to improve it based on the traditional scheduling algorithm to enhance the actual effect of the algorithm. This article do research on the multi-core Web server, Focusing on multi-core Web server queuing model. On this basis, the author draws the drawbacks of the multi-core Web server in the remote dynamic request scheduling algorithm, and improves the traditional algorithm with the demand analysis. Not only it overcomes the drawbacks of traditional algorithms, but also promotes the system threads carrying the same amount of tasks, and promotes the server being always in a dynamic balance. On the basis of this, it achieves an effective solution to customer requests.     

改进遗传算法的并行任务调度

并行任务调度是一个NP完全问题,它关注资源的分配和并行任务调度,要求具有高性能的调度算法,且能求解出高质量的解。提出了一种基于改进遗传算法的并行任务调度算法,在算法初始化种群产生时引入任务向量矩阵来表示任务、资源以及调度的关系,并采用启发式方法得到初始化种群,提高种群质量;采用规则约束的交叉和变异操作,提高个体的质量;提出了加速进化策略,有效地避免了早熟。仿真实验结果表明,该改进算法能更有效地求解并行任务调度问题。     

基于Kriging代理模型的动态云任务调度方法

任务调度在云计算环境中发挥着重要作用。提出一种基于Kriging代理模型的动态云任务调度方法。通过对云任务在不同资源组合下的性能表现进行Kriging代理模型建模并优化,从而得到对应于该云任务的最优资源分配方案;利用云平台的API,可动态对该云任务实施资源调度。基于OpenStack开源云平台,对两个工程计算应用进行了任务调度性能测试,结果表明该方法可有效动态调整云任务中的资源配给,按需按优对平台中的云任务进行资源调度。