共查询到19条相似文献,搜索用时 140 毫秒
1.
2.
多维递归方程组在并行求解时存在串并行不一致问题,提供三种Krylov子空间迭代求解方法———PCG/ATCG和GMRES来解决这一问题,并采用典型算例对这三种Krylov子空间迭代方法进行正确性验证和加速比测试.试验表明这三种Krylov子空间迭代法在并行规模较大的情况下,均能够正确求解多维递归方程组,并且加速特性良好. 相似文献
3.
泊松-玻尔兹曼方程(Poisson-Boltzmann Equation,PBE)是广泛应用于溶剂化生物分子静电分析的隐式溶剂化模型.本文在原有有限元软件基础上对近来提出的基于高阶有限元求解PBE的无条件稳定方法~([9])设计并实现了一种高效的并行计算方法.无条件稳定方法对PBE拟时间迭代求解,避开了强非线性导致的不稳定性.基于非结构化四面体网格本文设计实现了基于代数分解的求解稀疏线性方程组的高效并行模型.规模可扩展至6400 CPU核,并行效率达到近86%.大规模并行迭代求解线性方程组是计算科学领域的共性问题,它的高效并行实现不仅对实际生物分子静电分析提供了很好的基础,也可扩展至其他各应用领域. 相似文献
4.
《计算机应用与软件》2013,(3)
研究医学生物图像的快速分割问题。针对传统图像分割算法效率低、分割不准确的缺陷,提出一种利用水平集自动演化获得最优图像分割的方法。首先,定义水平集方程,并针对方程中不同分量进行分析,确定以图像灰度为依据的最优化算法;然后通过对差分方程的离散化,定义最优化算法的求解步骤,并使得该最优化计算方法能并行化处理。该方法可以有效地对医学图像进行分割,尤其适合并行化GPU处理,在确保图像分割质量的前提下,极大地提高了运算效率。 相似文献
5.
6.
三维激光烧蚀流体界面不稳定性程序的并行化 总被引:1,自引:0,他引:1
在共享存储并行机和MPP并行机上,基于MPI(MessagePassingInterface)并行编程环境,本文研究三维激光烧蚀界而不稳定性程序(Lared-S)的并行实现.三维激光烧蚀的数值模拟采用分裂方法,其90%以上的计算负载存在于流体方程和热传导方程的求解(流体方程的求解采用分裂显格式,热传导方程的求解采用分裂隐格式).本文给出基于三维分裂格式的交替平面数据通信模式.分裂隐格式的求解转化为三对角方程组的求解,其并行实现采用块流水线并行算法.数值实验结果表明交替平面数据通信策略和块流水线并行算法是有效且可扩展的.在共享存储并行机上,应用64台处理机获得93%以上的并行效率;在MPP并行机上,应用128台处理机获得90%以上的并行效率. 相似文献
7.
数据不规则问题全相关Block递归方程组多维流水线并行技术研究 总被引:1,自引:0,他引:1
主要讨论数据不规则问题全相关Block递归方程组多维流水线并行的实现.首先给出全相关Block递归方程组的模型方程,并从图论的角度给出了流水关系有向图的定义以及流水线并行条件的判别准则,分析了影响流水线并行效率的主要因素.在此基础上,提出一种基于流水关系有向图的流水线并行实现算法并应用于数据不规则问题.实验结果表明该方法在复杂区域情况下也可以取得较高的效率. 相似文献
8.
根据解反应扩散方程的自适应样条小波-交替方向(SW-ADI)方法,使用MPI、OpenMP两种并行编程模式,对串行程序进行了直接并行化,并在上海大学的高性能计算机自强2000上分别用MPI和OpenMP实现了对方程的求解。对运算结果进行了分析并给出了与串行程序相比较的并行加速比。 相似文献
9.
求解偏微分方程组是许多流体力学问题的数值模拟中所碰到的关键问题之一,但是设计相应的并行算法并实现都会碰到开发周期长,难度大的问题.介绍的可移植可扩展科学计算工具箱PETSc(Portable,Extensible Toolkit for Scientific Computation)突破性地解决了这一问题,它能够实现自动并行处理.通过求解三对角方程问题实例,并和基于MPI(message passing interface)方法手工编写的并行代码作了比较,给出了并行性能的分析结果. 相似文献
10.
有限差分法是求解偏微分方程近似解的一种重要的数值方法。串行算法并不能高效的解决大规模复杂计算问题,并行化计算方法可提高复杂计算问题的效率,从而使并行机上计算有限差分问题成为可能。二维场中拉普拉斯方程的差分格式非常适合并行化方法的计算,将串行部分并行化以提高大规模计算的效率具有重要的现实意义。MPI(消息传递接口)是实现并行程序设计的标准之一。虚拟进程(MPI_PROC_NULL)的引用简化了MPI编程中的通信部分,串行算法可更改为并行化计算方法,最终实现有限差分方法的并行化计算。 相似文献
11.
为了克服按矩阵加权信息融合非稳态Kalman滤波器的在线计算负担大的缺点,和按标量加权融合Kalman滤波器精度较低的缺点,应用现代时间序列分析方法,提出了按对角阵加权的线性最小方差多传感器信息融合稳态Kalman滤波器.它等价于状态分量按标量加权信息融合Kalman滤波器,实现了解耦信息融合Kalman滤波器.它的精度和计算负担介于按矩阵和按标量加权融合器两者之间,且便于实时应用.为了计算最优加权,提出了计算稳态滤波误差方差阵和协方差阵的Lyapunov方程.一个三传感器的雷达跟踪系统的仿真例子说明了其有效性. 相似文献
12.
This note considers the problem of minimax state estimation of the states of a linear time-invariant system which is driven by and observed in the presence of noise processes with uncertain second-order statistics. When the process noise and observations are scalars, the problem is shown to be equivalent to a scalar minimax estimation problem. The existence of a minimax solution is thereby established, and the minimax filter is shown to be a linear transformation of the minimax filter for the scalar problem. 相似文献
13.
14.
Methods for characterizing CRT displays 总被引:23,自引:0,他引:23
Roy S. Berns 《Displays》1996,16(4):173-182
Computer-controlled CRT displays can be described by a two-stage model. The first stage consists of a linear transformation matrix relating radiometric scalars of each channel with either spectral radiance or tristimulus values. The second stage is non-linear and relates digital counts with the radiometric scalars for each channel. The term system gamm, Γ, is introduced to define the non-linear stage. Γ can be characterized by either direct measurement or using a theoretical model with gain, kg, offset, ko, and exponential, γ, parameters. Techniques and recommendations are given both to determine the transformation matrix coefficients and estimate Γ using several methods. Special attention is given to Macintosh imaging systems. Key issues include channel and spatial independence tests, including optical flare due to internal reflections, and problems arising from preset video look-up table entries. 相似文献
15.
针对现有粉红噪声的生成方法所存在的计算过程复杂,与理想粉红噪声相比偏差较大等问题,本文提出了一种利用自回归滑动平均(Auto-regressive moving average,ARMA)模型法生成粉红噪声的新方法。首先,构造一个待定系数的ARMA模型,并通过Z变换和功率谱估计的公式进行推导;其次,利用已知的粉红噪声模拟滤波器的传递函数H(s)和双线性Z变换法推导出IIR数字滤波器的传递函数H(z),进而得到粉红噪声的ARMA模型;最后,利用MATLAB对生成的粉红噪声进行功率谱估计并与理想的粉红噪声进行对比。由MATLAB仿真结果可知,利用该方法生成的粉红噪声与理想的粉红噪声拟合度更高,完全符合粉红噪声的各项性能要求。 相似文献
16.
Karen Hovsepian Peter Anselmo Subhasish Mazumdar 《Knowledge and Information Systems》2011,26(2):195-223
We present a classification algorithm built on our adaptation of the Generalized Lotka–Volterra model, well-known in mathematical
ecology. The training algorithm itself consists only of computing several scalars, per each training vector, using a single
global user parameter and then solving a linear system of equations. Construction of the system matrix is driven by our model
and based on kernel functions. The model allows an interesting point of view of kernels’ role in the inductive learning process.
We describe the model through axiomatic postulates. Finally, we present the results of the preliminary validation experiments. 相似文献
17.
18.
从软件需求定义到形式功能堆约的自动转换是需求工程的重要问题之一。文中以软件需求定义语言NDRDL和形式功能规给语言Z为基础,探讨了基间的自动转换技术,特别是从NDRDL需求定义自动获取Z形式规约中状态空间与操作定义的技术。 相似文献
19.
This paper is aimed at developing modern computer technologies and methods of concurrent programming designed to improve the efficiency of solving fundamental scientific and applied problems of numerical simulation in aerodynamics and physical gas dynamics. Theoretical issues concerning the design of aircraft involving large amounts of computations are also examined. This paper is focused on theoretical issues of paralleling available methods and algorithms for solving complex integro-differential systems of equations. A number of paralleling methods are considered based on various types of decomposition of the original problem into several subproblems that can be solved concurrently (decomposition by physicomathematical processes of the technological chain of computations and by the corresponding processes that can be performed concurrently (horizontal paralleling), and decomposition by the computational geometric domains and by the corresponding processes that can be performed concurrently (vertical paralleling)). The efficiency of these methods is compared and the optimal paralleling method is found. The results of the theoretical study are used in developing the third-generation package of programs for solving aerodynamics and gas dynamics problems called Potok-3. 相似文献