概说并行计算结构力学

基于向量机和并行机两大类并行计算机，对线性静力和动力问题，非线性静力和动力问题，本文概说了相应于这两大类并行机一般的求解方法。     

求解非线性方程组Newton—PCG并行算法

基于向量机（Ｖｅｃｔｏｒ Ｃｏｍｐｕｔｅｒ），应用二次迭代法和不完全的Ｃｈｏｌｅｓｋｉ不塞入分解原理，建立了求解非线性方程组的Ｎｅｗｔｏｎ－ＰＣＧ并行算法。     

求解非线性方程组Newton－PCG并行算法

基于向量机（ＶｅｃｔｏｒＣｏｍｐｕｔｅｒ），应用一次迭代法和不完全的Ｃｈｏｌｅｓｋｉ不塞入分解原理，建立了求解非线性方程组的Ｎｅｗｔｏｎ－ＰＣＧ并行算法。     

Computational intellectual analytical theory of computational analytical approach to rotating flow of non-Newtonian fluid

Ａｎｅｗｆｉｅｌｄｏｆｍｏｄｅｒｎｃｏｍｐｕｔｅｒｓｃｉｅｎｃｅ—ａｒｔｉｆｉｃｉａｌｉｎｔｅｌｌｉｇｅｎｃｅｉｓｄｅｖｅｌｏｐｅｄｒａｐｉｄｌｙ．Ｔｈｅｓｙｍｂｏｌｉｃｍａｎｉｐｕｌａｔｉｏｎｉｓｔｈｅｆｒｏｎｔｄｉｒｅｃｔｉｏｎｉｎｔｈｅａｒｔｉｆｉｃｉａｌｉｎｔｅｌｌｉｇｅｎｃｅ．Ａｓｅｒｉｅｓｏｆｔｈｅｃｏｍｐｕｔｅｒｓｏｆｔｗａｒｅｉｓｄｅｖｅｌｏｐｅｄｆｏｒｔｈｅｃｏｍｐｕｔａｔｉｏｎａｌｍａｎｉｐｕｌａｔｉｏｎ,ｓｕｃｈａｓＭａｃｓｙｍａ,Ｍａｐｌｅ,Ｍａｔｈｅｍａｔｉｃａ,ｔｏｃ…     

On the spectral equivalence of unconventional finite elements and their conventional relatives

ＩｎｔｒｏｄｕｃｔｉｏｎＩｎｒｅｃｅｎｔｙｅａｒｓ,ｗｉｔｈｔｒｅｍｅｎｄｏｕｓｄｅｖｅｌｏｐｍｅｎｔｏｆｐａｒａｌｌｅｌｃｏｍｐｕｔｅｒｓ,ｔｈｅｐｒｏｂｌｅｍｏｆｈｏｗｔｏｃｏｎｓｔｒｕｃｔｅｆｆｅｃｔｉｖｅｄｏｍａｉｎｄｅｃｏｍｐｏｓｉｔｉｏｎｐａｒａｌｌｅｌａｌｇｏｒｉｔｈｍｓｆｏｒｌｉｎｅａｒｓｙｓｔｅｍａｒｉｓｉｎｇｆｒｏｍｔｈｅｆｉｎｉｔｅｅｌｅｍｅｎｔｄｉｓｃｒｅｔｉｚａｔｉｏｎｈａｓｂｅｃｏｍｅｔｈｅｆｏｃｕｓｉｎｔｈｅｆｉｅｌｄｏｆｓｃｉｅｎｔｉｆｉｃｃｏｍｐｕｔａｔｉｏｎａｌ…     

OBJECT-ORIENTED FINITE ELEMENT ANALYSIS AND PROGRAMMING IN VC++

ＩｎｔｒｏｄｕｃｔｉｏｎＳｉｎｃｅｆｉｎｉｔｅｅｌｅｍｅｎｔａｎａｌｙｓｉｓｐｒｏｇｒａｍｓｄｅａｌｗｉｔｈｔｈｅｔｈｅｏｒｉｅｓａｎｄｍｅｔｈｏｄｓｏｆｔｈｒｅｅｆｉｅｌｄｓｏｆｍｅｃｈａｎｉｃｓ,ａｐｐｌｉｅｄｍａｔｈｅｍａｔｉｃｓａｎｄｃｏｍｐｕｔｅｒｓｃｉｅｎｃｅ,ｔｈｅｙａｒｅｃｏｍｐｌｉｃａｔｅｄａｎｄｅｒｒｏｒ＿ｐｒｏｎｅ .Ｄｕｒｉｎｇｄｅｖｅｌｏｐｍｅｎｔｐｅｏｐｌｅａｌｌｔｈｒｏｕｇｈｓｅｅｋｔｈｅｍｅｔｈｏｄｔｏｉｍｐｒｏｖｅｐｒｏｇｒａｍｓ.Ｔｈｅｏｂｊｅｃｔ＿ｏｒｉｅｎｔｅ…     

THE SIMPLE SHEAR OSCILLATION AND THE RESTRICTIONS TO ELASTIC-PLASTIC CONSTITUTIVE RELATIONS

ＩｎｔｒｏｄｕｃｔｉｏｎＳｉｎｃｅＤｉｅｎｅｓ（１９７９），ＮａｇｔｅｇａｌａｎｄＤｅＪｏｎｇ（１９８２）ｅｔａｌｈａｄｏｃａｓｉｏｎａｌｙｆｏｕｎｄｔｈｅｐｈｅｎｏｍｅｎａｏｆｓｉｍｐｌｅｓｈｅａｒｏｓｃｉｌａｔｉｏｎｕｓｉｎｇｔｈｅｇｅｎｅｒａｌ...     

STUDY ON STEADY SURGE PRESSURE FOR YIELD-PSEUDOPLASTIC FLUID IN A CONCENTRIC

ＷａｎｇＨａｉｇｅ（汪海阁）；ＬｉｕＸｉｓｈｅｎｇ（刘希圣）（ＲｅｃｅｉｖｅｄＪｕｌｙ８，１９９４；ＣｏｍｍｕｎｉｃａｔｅｄｂｙＣｈｉｅｎＷｅｉｚａｎｇ）Ａｂｓｔｒａｃｔ：Ｓｕｒｇｅｐｒｅｓｓｕｒｅｃａｕｓｅｄｂｙｐｉｐｅｍｏｖｉｎｇｔｈｒｏｕｇｈｔ...     

Existence and iterative algorithms of solutions for generalized mixed quasi-variational inequalities

１　ＰｒｏｂｌｅｍｓＬｅｔＨｂｅａｒｅａｌＨｉｌｂｅｒｔｓｐａｃｅｗｉｔｈｎｏｒｍａｎｄｉｎｎｅｒｐｒｏｄｕｃｔｓｄｅｎｏｔｅｄｂｙ‖·‖ａｎｄ〈·,·〉ｒｅｓｐｅｃｔｉｖｅｌｙ．ＬｅｔＫｂｅａｃｌｏｓｅｄｃｏｎｖｅｘｓｕｂｓｅｔｉｎＨａｎｄｆ：Ｈ→Ｈｂｅａｓｉｎｇｌｅｖａｌｕｅｄｍａｐｐｉｎｇ．Ｔｈｅｃｌａｓｓｉｃａｌｖａｒｉａｔｉｏｎａｌｉｎｅｑｕａｌｉｔｙｐｒｏｂｌｅｍ（ＶＩＰ（ｆ,Ｋ））ｉｓｔｏｆｉｎｄ＾ｘ∈Ｋ（＾ｘ）,ｓｕｃｈｔｈａｔ〈ｆ（＾ｘ）,ｙ－＾ｘ〉≥０　　（ｙ∈Ｋ）．（１）…     

复杂微力－电系统的细微尺度力学

现代高新技术的崛起，提出了大量新的经典力学所不能完全包容的力学问题。这将是现代应用力学发展的巨大动力。微电子技术中微电子材料、器件、系统和微电子－机械系统（ｍｉｃｒｏｅｌｅｃｔｒｏ－ｍｅｃｈａｎｉｃａｌｓｙｓｔｅｍ，ＭＥＭＳ）所组成的复杂微力－电系统，是跨世纪发展的新科技方向，本文简要介绍了复杂微力，电系统的工业技术背景和发展；综述了这一领域存在的力学问题，主要讨论细微尺度下的结构力学与破坏力学。并评介与展望了这一新的力学领域的研究状况和发展趋势。     

有限元瞬态响应分析软件的一种并行开发方法

瞬态响应分析是有限元动力分析的重要内容之一，而串行计算机上运行的有限元软件在解题规模和速度上都受到很大限制。为此，基于系统集成思想对串行有限元软件进行并行开发。分析得出了瞬态响应分析并行开发的重点——位移方程组的瞬态响应，给出了线性方程组并行求解的思路和实现方法。用一个实例系统的实现验证了上述开发思路，从而也为并行应用软件开发探索了一条新的途径；最后对并行求解程序进行了算例验证。     

A Review of Parallel Computing in Computational Aeroacoustics

This paper discusses parallel computing applied to computational aeroacoustics problems. Computer hardware, software and algorithms are also described. A short history of parallel computers is given, along with some discussion of future prospects. We have reviewed much of the literature, but this review is not exhaustive. Finite difference, finite volume, and finite element methods are briefly discussed. There is also a discussion of how aeroacoustic problems scale, and how that relates to computational requirements.     

有限元程序的一种并行化算法

传统的以串行计算机为物质基础的有限元算法分析未能满足科学研究和工程技术发展的需要．并行处理技术的发展为解决此类问题提供了新的契机．机群式并行计算机是当今较为流行的一种并行处理方式．根据有限元法的特点，提出了一种并行有限元算法，并在多处理机分布式内存并行计算机环境下完成了面向对象并行有限元程序的编制．算例表明该算法能大大提高其分析速度，而且算法简单，实现方便．     

A HIERARCHICAL PARALLEL COMPUTING APPROACH FOR STRUCTURAL STATIC FINITE ELEMENT ANALYSIS

根据分布式存储并行计算机的体系结构特点,提出了一种结构静力有限元分层并行计算方法. 该方法在两级分区两次缩聚策略的基础上不仅实现了大量数据的分布式存储,提高了数据的内存访问速率;而且实现了计算过程的三层并行,有效提高了通信效率;此外,它还进一步降低了界面方程的规模,大幅度减少了界面方程的求解时间. 因此,它能够充分利用分布式存储并行计算机的体系结构特点提升大规模并行计算效率. 最后通过典型数值算例验证了该方法的正确性和有效性.     

结构静力有限元分层并行计算方法

根据分布式存储并行计算机的体系结构特点,提出了一种结构静力有限元分层并行计算方法. 该方法在两级分区两次缩聚策略的基础上不仅实现了大量数据的分布式存储,提高了数据的内存访问速率;而且实现了计算过程的三层并行,有效提高了通信效率;此外,它还进一步降低了界面方程的规模,大幅度减少了界面方程的求解时间. 因此,它能够充分利用分布式存储并行计算机的体系结构特点提升大规模并行计算效率. 最后通过典型数值算例验证了该方法的正确性和有效性.      

Real-Time Multibody System Dynamic Simulation: Part I. A Modified Recursive Formulation and Topological Analysis

ABSTRACT

ABSTRACT With the advent of parallel computers and recursive dynamics formulations, multibody mechanical systems such as ground vehicles can be simulated in real time. This permits the engineer to rapidly modify design parameters, evaluate dynamic performance, and improve designs, prior to fabrication and testing. Perhaps more important, real-time simulation can be used for simulation with the operator-in-the-loop, permitting system design to be optimized for the capability of the human operator. To achieve the goal of real-time simulation, a modified recursive dynamics formulation and a topological analysis method for the formulation are presented in Part I. A parallel computational algorithm that exploits inherent parallelism in the modified recursive formulation and numerical results will be presented in Part II. By combining the topological analysis method and the parallel algorithm, an efficient general-purpose dynamic simulation method is developed for real-time simulation on shared memory parallel processors.     

Finite element ground-water models implemented on vector computers

Finite element models, optimized for running on conventional serial computers, are not suitable to make use of the potentional high performance of today's vector or parallel computers. Also, automatic vectorization by the compiler or manual vectorization at the local level do not by far lead to the required and expected computational speed. A global change of the overall program logic or a complete redesign becomes necessary, i.e. a completely new generation of program systems has to be created, considering the new hardware characteristics and abilities. A new computer-independent programming technique for finite element problems to be implemented on vector computers is proposed and the test results of scalar and vectorized program structures on a conventional serial and on a non-conventional pipeline computer are discussed.     

Large-scale high performance computation on 3D explosion and shock problems

Explosion and shock often involve large deformation, interface treatment between multi-material, and strong discontinuity. The Eulerian method has advantages for solving these problems. In parallel computation of the Eulerian method, the physical quantities of the computaional cells do not change before the disturbance reaches to these cells. Computational efficiency is low when using fixed partition because of load imbalance. To solve this problem, a dynamic parallel method in which the computation domain expands with disturbance is used. The dynamic parallel program is designed based on the generally used message passing interface model. The numerical test of dynamic parallel program agrees well with that of the original parallel program, also agrees with the actual situation.     

结构有限元分析并行处理的研究进展

在过去20年, 由于并行计算机的出现, 对结构工程应用的有限元算法研究已取得很大的进展. 为了将串行机上运行的算法改成并行和研制适应于并行计算机的新方法, 一直在进行大量的研究. 本文论述了该领域一些已有的有限元并行算法, 对适应结构工程的一些有限元并行算法进行概括. 对该领域的未来发展趋势作了展望.