The part of control card development mainly consists of the definition and completion of parallel bus inside the cards container , the assignation of address , the applications of gal devices and the program and debugging of eprom software 控制卡研制部分的主要内容包括并行机箱内总线的定义与控制，系统寻址空间分配， gal器件应用，控制卡eprom程序设计等。
The performance model has been validated against the implementation results obtained on a dawing tci700 parallel computer and can be readily used to estimate the performance before the optimistic simulation is implemented 在曙光tc1700并行机上的性能实验表明，我们的解析性性能分析模型得到的结果与实际实现的结果是非常接近的，可以用于乐观仿真实现前的性能预测。
The conflict can be resolved by the parallel compute , but two questions exist at the same time . firstly , the related high rank parallel software is so scarce that the parallel computer can only used by the professional programmer 并行机的出现为复杂结构精细分析提供了硬件基础，但由于高层次并行软件的缺乏使得并行计算机往往只能由专业程序员使用，另外，并行机价格昂贵，不易普及。
This article details the arrangement relationship of independence , order , deflection order and the waterfall arrangement ways according to path number and running time , with the stress on the " trapezoid " arithmetic of batch process in parallel computer 摘要介绍了含有独立、顺序、有偏序关系的批作业的梳理，以及批作业按作业序列路径数、运行时间长短排序的瀑布式方法，重点讲述了并行机批作业执行时的“梯形”算法。
To analyze the factors that influence the performance and put forward the further research issues . we parallized practical programs in cfd using paractive . and we tested the parallel programs obtained on yh - iii super computer , pc clusters and sgi workstation 我们使用paractive对国防科大提供的cfd实际算例和有关的标准测试算例实现了并行化，并且分别以银河-并行机， pc机群系统及sgi工作站为测试平台进行了性能测试。
So , we must design multimedia application - oriented computer architecture to fit the data processing demand of video compressing programs , we analyzed the parallelism of two representative video compressing programs - opendivx and tml9 , and drew a conclusion that it is effective to run video compressing application programs on the processor which uses parallel arithmetic units 相对于视频压缩应用而言，普通计算机的处理能力大大落后于处理需求。因此，对于多媒体应用，必须采用并行的方法来解决，但是不能简单地使用普通并行机，必须针对这部分应用的特点，采用并行的思想来设计面向多媒体应用的计算机体系结构。
Cellular element method is a new numerical computing method . in this method the integer analysis of structure is changed into a series of part analysis by using the idea of cellular automata . it may have a good future in the aspect of large structure because it hardly have any special request on the capability of computer . simultaneity , it can be developed into a high parallel arithmetic to suit for the request of parallel computer in the future 元胞单元法是新近出现的一种数值计算方法，它引用元胞自动机的思想将有限元对结构的整体分析变成局域求解，对计算机容量要求低，在大型复杂结构的计算方面具有良好的前景，同时可望形成一种高度并行的算法，适用于未来并行机的要求，是一种富有发展潜力的新的数值方法。
We analysed the traditional automatic parallelization technology , including dependency analysis theory , program transformation technology , parallel scheme and the optimization of related synchronization and communication etc , which are the theoretical basis of the whole article . cfd computing features , especially the features of explicit difference computing , have also been further ananlysed . we also summarized drawbacks of traditional automatic parallelization technology used in cfd : small parallel granularity , difficulty in attaining global identical data partition , and difficulty in attaining high parallel efficiency on distributed memory system 本文讨论、分析、总结了通用的自动并行化技术：相关性分析理论、程序变换技术、并行模式以及同步通信与优化问题等等，它们是本文研究工作的理论基础；针对研究对象，深入分析了cfd计算的特点，特别是显式差分计算的特点；并归纳出传统的自动并行化技术在cfd应用中存在的问题：并行粒度小、难以获得全局统一的数据划分方式，对于分布存储结构的并行机难以获得高效率。
In the thesis a new count expression of mesh fractal dimension is introduced , on the basis of it the storage and operation counts of directs solution methods , assembly global stiffness iterative methods and ebe iterative methods have been analyzed and compared , a conclusion has been obtained that the storage and operation counts of direct solution methods is the most , the storage counts of the ebe iterative methods is the least . estimating compute scale for ebe iterative methods at shuguang 2000 parallel computer , it is make out that compute scale is large in the extreme if make the most of the memory of every processor . by analyzing the parallel compute performance of 2d upend - step flow calculation , it is proved that ebe iterative methods can achieve upper speedup rations 本文还提出了一种网格分维新的计算公式，并基于网格分维对直接解法，组集总刚矩阵的迭代解法和基于ebe的迭代解法等三种方法的存储量和计算量进行了分析和比较，得出了直接解法无论存储量和计算量均最大，基于ebe迭代解法存储量最小的结论；在曙光2000并行机上估计了基于ebe迭代解法的计算规模，说明只要充分利用各处理机的内存，可解问题的规模是非常巨大的；对二维倒台阶流并行计算进行了性能分析，表明基于ebe策略的迭代解法能获得较高的加速比。
Firstly , we study problems where job preemption is allowed under the generalized delay condition , i . e . delay is caused by both setup time and time of some fraction of work must be repeated if preemption occurs . we generalize the notion of job preemption by using two kinds of preempt - setup - repeat models representing these conditions 通过刻化上述条件，给出了两种中断一安装重复模型一般化了任务可中断的概念，同时我们研究并给出了并行机排序问题p _ 2 | prmp | c _ ( max )在中断?重复模型下的静态调度算法。
