Synchronization and communication costs of loop partitioning onshared-memory multiprocessor systems

The author presents strategies for static loop decomposition and scheduling as well as computer-assisted run-time scheduling that take into account, in addition to the cost of performing operations, the overhead costs associated with a decomposition and schedule. An algorithm for static decomposition of multidimensional loops based on the operation execution costs, communication costs, and synchronization costs is discussed. Synchronization instructions are introduced to ensure correct program execution following program decomposition. An algorithm for determining the explicit synchronization instruction that should be introduced to ensure correct execution of a program with arbitrarily nested loops is presented. Techniques for reducing run-time scheduling and communication and synchronization costs due to self-scheduling of multidimensional loops are also presented. Experiments performed on the Encore multiprocessor system demonstrate that the techniques developed can reduce overhead costs     

A performance oriented multi-loop constrained adaptive robust tracking control of one-degree-of-freedom mechanical systems: Theory and experiments

A performance oriented multi-loop approach to the adaptive robust tracking control of one-degree-of-freedom mechanical systems with input saturation, state constraints, parametric uncertainties and input disturbances is presented. The control system contains three loops. In the outer loop, constrained optimization algorithms are developed to generate a replanned trajectory on-line at a low sampling rate so that the converging speed of the overall system response to the desired target is maximized while not causing input saturation and the violation of state constraints. In the inner loop, a constrained adaptive robust control (ARC) law is synthesized and implemented at high sampling rate to achieve the required robust tracking performances with respect to the replanned trajectory even with various types of uncertainties and input saturation. In the middle loop, a set-membership identification (SMI) algorithm is implemented to obtain a tighter estimate of the upper bound of the inertia so that more aggressive replanned trajectory could be used to further improve the overall system response speed. Interaction of the three loops is explicitly characterized by a set of inequalities that the design variables of each loop have to satisfy. It is theoretically shown that the resulting closed-loop system can track feasible desired trajectories with a guaranteed converging time and steady-state tracking accuracy without violating the state constraints. Experiments have been carried out on a linear motor driven industrial positioning system to compare the proposed multi-loop constrained ARC algorithm with some of the traditional control algorithms. Comparative experimental results obtained confirm the superior performance of the proposed algorithm over existing ones.     

Two approaches for solving the buffer allocation problem in unreliable production lines

This paper presents an integrated approach to solve the buffer allocation problem in unreliable production lines so as to maximize the throughput rate of the line with minimum total buffer size. The proposed integrated approach has two control loops; the inner loop and the outer loop. While the inner loop control includes an adaptive tabu search algorithm proposed by Demir et al. [8], binary search and tabu search are proposed for the outer loop. These nested loops aim at minimizing the total buffer size to achieve the desired throughput level. To improve the efficiency of the proposed tabu search, alternative neighborhood generation mechanisms are developed. The performances of the proposed algorithms are evaluated by extensive computational experimentation, and the results are reported.     

Phase and amplitude sinusoidal dither adaptive control system

In many control system applications an adaptive system is required to accommodate changes in plant dynamics. A self-adaptive system described herein adjusts two control system parameters to maintain the closed-loop response essentially constant in spite of large changes in the plant gain and pole-zero locations. The adaptive system uses a high-frequency dither frequency to interrogate the state of the control system. Two self-adaptive performance criteria (SAPC) adjust the two adaptive parameters. One SAPC is based upon the amplitude response to the dither frequency and the other is based upon the phase response. The adaptive loop associated with the amplitude SAPC adjusts the control system loop gain; the adaptive loop associated with the phase SAPC adjusts a variable compensation network. A method is developed for analyzing the stability and performance of the self-adaptive parameter adjustment loops. The stability analysis includes the interaction between these adaptive loops. This two-parameter adaptive system is applied to a specific example to illustrate the techniques developed in the paper.     

基于Hamilton理论的可逆冷带轧机速度张力系统无张力计控制

基于反馈耗散Hamilton理论研究了可逆冷带轧机速度张力系统的无张力计控制问题. 首先,对系统速度张力外环(主轧机速度环和左、右卷取机张力控制环)进行预反馈控制, 并采用反馈耗散Hamilton理论完成了速度张力外环控制器的设计. 其次, 为了实现系统的无张力计控制及对摄动参数的自适应估计, 基于"扩张系统+反馈"方法完成了系统速度张力外环自适应状态观测器的设计. 再次, 为了实现可逆冷带轧机主轧机速度和左、右卷取机张力间的协调控制及对外扰不确定项的干扰抑制, 基于backstepping方法完成了系统电流内环鲁棒控制器的设计. 理论分析表明, 所提出的控制方法能够保证闭环系统的鲁棒稳定性. 最后, 基于某1422mm可逆冷带轧机速度张力系统的实际数据进行仿真, 并同串级PI控制方法相比较, 结果验证了本文所提方法的有效性.     

基于DSP的电机双闭环控制系统

提出了一种基于DSP的电机双闭环控制系统设计方法,解决了采用单片机控制电机时运算速度慢和运用单闭环控制时动态性能不佳的问题。采用速度环和电流环组成双闭环控制系统,运用增量式编码器对直流电机测速和霍尔电流传感器检测电流,充分利用F2812的接口资源,同时结合PI算法实现电机速度精确控制。在MATLABSIMULINK仿真环境中建立直流电机双闭环系统模型,对双闭环控制算法进行仿真并获得到较好的效果。基于DSP的双闭环控制系统结构简单,外围设备少,易进行控制算法的二次开发。     

The establishment of edge-based loop algebra theory of kinematic chains and its applications

Based on the edge-based array representation of loops in the topological graphs of kinematic chains, this paper first proposes three arithmetic operations of loops. Then the concept of the independent loop set as well as its determination rules is introduced, and a new structure decomposition algorithm of kinematic chains is presented. Based on the algorithm, an automatic and efficient method for rigid sub-chain detection and driving pair selection of kinematic chains is proposed. Finally, an index is proposed to assess computation complexity of kinematic analysis with respect to different driving pair selections.     

基于串级PID和复合滤波算法板球控制系统设计

本文设计了一种基于串级PID算法和复合滤波的板球控制系统,通过多级错频获取速度差和位置差,并复合滑窗滤波和低通滤波算法,给出了以小球速度差为内环,位置偏差为外环的双闭环平衡控制策略,在simulink平台搭建了仿真模型并进行研究,同时利用J-Scope调试软件进行实际效果波形检测,结果表明本文设计应用的串级PID算法相对于经典单闭环位置式PID算法稳定性更强,系统稳态误差越小,添加复合滤波后,系统抖动明显减弱,位置控制更加精确,增强了板球控制系统实时控制动态响应效果。     

EFFECTIVE PARALLELIZATION TECHNIQUES FOR LOOP NESTS WITH NON-UNIFORM DEPENDENCES

The parallelism of loop nests with non-uniform dependences is difficult to extract and ineffectively explored by the existing parallelization schemes. In this paper, we propose new efficient techniques in extracting parallelism of loop nests with non-uniform dependences using their irregularity. By this way, current highly parallel multiprocessor systems such as multithreaded and clustering multiprocessor systems can be fully utilized. These four mechanisms are (a) parallelization part splitting, (b) partial parallelization decomposition, (c) irregular loop interchange and (d) growing pattern detection. They explore parallelisms of special parallel patterns for nested loops with non-uniform dependences. The loop transformations used in uniform loops are also applied in non-uniform dependence loops after legality tests. We apply the results of classical convex theory and detect special parallel patterns of dependence vectors. We also proposed an algorithm that combines above mechanisms to enhance parallelism. We demonstrate that our technique gives much better speedup and extracts more parallelism than the existing techniques. Thus, we are encouraged by these apparent enhancements to pursue further development.     

显著度可控的DEM地形特征线提取

目的 基于数字高程模型（DEM）的地形山脊线和山谷线提取对地形模型简化、基于样本的地形合成和地形地貌研究有重要意义,针对许多传统算法无法对所提取特征线的显著度进行方便准确的控制,以及不支持环形特征线提取的问题,提出一种新的显著度可控的DEM地形特征线提取算法。方法 首先利用全局断面扫描算法提取特征点并计算各特征点的显著度,然后根据特征点的特征方向进行特征延伸以增强特征连通性,接着采用改进的Hilditch细线化算法对特征点集合进行细线化处理,之后为相邻特征点添加特征边,构成特征图,利用环路检测与破环算法检测特征图中的环路,并破除冗余小环路,最后根据分支显著度的相似度和分支方向一致性进行特征图分解,计算分解得到特征线的显著度并筛选得到最终特征线。结果 使用真实DEM数据提取最显著的若干条特征线,与现有的基于特征显著度的地形特征线提取算法进行对比,本文算法对特征图的分解能够更准确地提取主干特征线,而基于显著度的特征线筛选控制也更加准确合理。对提出的环路检测与破环算法进行实验验证,该算法能保留大的山脊线环路,破除小的冗余环路。结论 实验结果表明,本文算法能有效实现显著度可控的山脊线和山谷线自动提取,提取结果与人眼观察结果基本一致,同时能够支持含有环形特征的地形。     

An augmented Lagrangian decomposition method for quasi-separable problems in MDO

Several decomposition methods have been proposed for the distributed optimal design of quasi-separable problems encountered in Multidisciplinary Design Optimization (MDO). Some of these methods are known to have numerical convergence difficulties that can be explained theoretically. We propose a new decomposition algorithm for quasi-separable MDO problems. In particular, we propose a decomposed problem formulation based on the augmented Lagrangian penalty function and the block coordinate descent algorithm. The proposed solution algorithm consists of inner and outer loops. In the outer loop, the augmented Lagrangian penalty parameters are updated. In the inner loop, our method alternates between solving an optimization master problem and solving disciplinary optimization subproblems. The coordinating master problem can be solved analytically; the disciplinary subproblems can be solved using commonly available gradient-based optimization algorithms. The augmented Lagrangian decomposition method is derived such that existing proofs can be used to show convergence of the decomposition algorithm to Karush–Kuhn–Tucker points of the original problem under mild assumptions. We investigate the numerical performance of the proposed method on two example problems.     

基于分布式系统的可并行循环动态识别技术

针对分布式环境下可抽取观察循环的不规则串行程序循环的动态依赖关系分析问题,提出了一个基于观察/执行模型的动态分析算法.其贡献是:(1) 算法可并行执行于分布式系统;(2) 直接分析具有拷入和最后赋值操作的循环;(3) 给出了循环的并行化方法;(4) 并不要求循环是完全可并行的,对某些部分可并行循环,也支持其并行执行.理论分析和实验表明,在处理器数量适当的情况下,循环可以并行时,可以获得很好的加速比;不能并行时,对串行执行增加的开销也是小的.从而为分布式环境下开发更多的循环并行性提供了一种新的手段.     

四旋翼无人飞行器控制算法设计

针对Qball-X4四旋翼无人飞行器的自身特点,建立系统的非线性模型,采用姿态内环和位置外环的双闭环控制算法。线性二次型调节器（LQR）可以快速简便地求解出最优的状态反馈控制率,并且具有良好的鲁棒性,因而利用LQR控制算法来控制姿态内环。由于PID控制算法结构简单、鲁棒性强,因而控制位置外环。通过Matlab/Simulink和飞行试验对控制算法进行仿真和验证,结果表明,设计的控制算法能成功地实现飞行器的悬停控制,并达到较好的控制效果。     

鲁棒分散控制系统闭环传递矩阵的界

本文将Nyquist阵列用于对象模型具有非结构不确定性的分散控制系统.在假定返回差 矩阵为广义块对角优势的条件下,得到了当某个子块反馈为开路(或某个反馈回路为开路)时 的闭环传递矩阵(或闭环传递函数)的界及其特征值的包含域.这是标准的Ostrowski带的再 推广.     

基于ANOVA-like 方差分解的非线性系统控制性能评估

针对实际控制回路大多包含非线性特征,导致评估结果存在偏差的问题,以一类非线性系统为对象,首先分析其最小方差性能下限的存在性,并推导出其与系统干扰项的关系式;然后用正交最小二乘方法辨识系统闭环模型,进而使用ANOVA-like方差分解公式估计超前干扰项对输出方差的贡献,由此获得非线性系统的控制性能;最后,将所提出的方法与传统方法通过仿真实例进行比较.仿真结果表明,所提出的方法是可行且有效的.     

基于正交分解的递推子空间闭环辨识方法

为实现闭环系统在线辨识,提出递推正交分解闭环子空间辨识方法(RORT)。首先,根据闭环系统状态空间模型和数据间投影关系,构建确定-随机模型,并利用GIVENS变换实现投影向量的递推QR分解;然后,引入带遗忘因子的辨识算法,构建广义能观测矩阵的递推更新形式,以减少子空间辨识算法中QR分解和SVD分解的计算量;最后,针对某型号陀螺仪闭环系统进行实验。实验结果表明, RORT法的辨识拟合度高于91%,能够对陀螺仪闭环系统模型参数进行在线监测。     

Optimizing modulo scheduling to achieve reuse and concurrency for stream processors

Both reuse and concurrency are performance-critical for stream processors. When applying loop unrolling and software pipelining separately to stream-level loops, either reuse or concurrency or both may be inadequately exploited. In this paper, we optimize modulo scheduling to maximize stream reuse and improve concurrency for stream-level loops. The key insight is that an unrolled and software-pipelined stream-level loop could be described by a set of reuse equations. Guided by reuse equations, a reuse-aware modulo scheduling algorithm is developed to simultaneously optimize the two performance objectives, reuse, and concurrency, for a loop in a unified framework. Moreover, we describe a code generation algorithm to automatically produce the optimized loop from a given loop. The experimental results obtained on FT64 and by simulation demonstrate the effectiveness of the proposed approach.     

Online constrained optimization based adaptive robust control of a class of MIMO nonlinear systems with matched uncertainties and input/state constraints

A performance oriented two-loop control approach is proposed for a class of multiple-input–multiple-output (MIMO) systems with input saturation, state constraints, matched parametric uncertainties and input disturbances. In the inner loop, a constrained adaptive robust control (ARC) law is synthesized to achieve the required robust tracking performances with respect to on-line replanned trajectory in the presence of input saturation and various types of matched uncertainties. In the outer loop, a replanned trajectory is generated by solving a constrained optimization algorithm online to minimize the converging time of the overall system response to the desired trajectory while not violating various constraints. Interaction of the two loops is explicitly characterized by a set of inequalities that the design variables of each loop have to satisfy. It is theoretically shown that the resulting closed-loop system can track feasible desired trajectories with a guaranteed converging time and steady-state tracking accuracy without violating the state constraints. Since the system in study is most appropriate to describe the dynamics of the robotic systems, the control of a two-axis planar robotic manipulator is used as an application example. Comparative simulation results demonstrate the advantage of the proposed approach over the traditional approaches in practical applications.     

Performance evaluation and enhancement of multistage manufacturing systems with rework loops

The phenomena of machine failures, defects, multiple rework loops, etc., results in much difficulty in modeling rework systems, and therefore the performance analysis of such systems has been investigated limitedly in the past. We propose an analytical method for the performance evaluation of rework systems with unreliable machines and finite buffers. To characterize the rework flow in the system, a new 3M1B (three-machine and one-buffer) Markov model is first presented. Unlike previous models, it is capable of representing multiple rework loops, and the rework fraction of each loop is calculated based on the quality of material flow in the system. A decomposition method is then developed for multistage rework systems using the proposed 3M1B model as one of the building blocks. The experimental results demonstrate that the decomposition method provides accurate estimates of performance measures such as throughput and Work-In-Process (WIP). We have applied this method to several problems, such as the determination of the optimal inspection location and the identification of bottleneck machines in rework systems.     

Assembly line balancing under uncertainty: Robust optimization models and exact solution method

This research deals with line balancing under uncertainty and presents two robust optimization models. Interval uncertainty for operation times was assumed. The methods proposed generate line designs that are protected against this type of disruptions. A decomposition based algorithm was developed and combined with enhancement strategies to solve optimally large scale instances. The efficiency of this algorithm was tested and the experimental results were presented. The theoretical contribution of this paper lies in the novel models proposed and the decomposition based exact algorithm developed. Moreover, it is of practical interest since the production rate of the assembly lines designed with our algorithm will be more reliable as uncertainty is incorporated. Furthermore, this is a pioneering work on robust assembly line balancing and should serve as the basis for a decision support system on this subject.