顯式并行性 的英文怎麼說

中文拼音 [xiǎnshìbīnghángxìng]
顯式并行性 英文
explicit parallelism
  • 顯 : Ⅰ形容詞1 （明顯） apparent; obvious; noticeable; evident 2 （有名聲有權勢的） illustrious and inf...
  • 式 : 名詞1 （樣式） type; style 2 （格式） pattern; form 3 （儀式; 典禮） ceremony; ritual 4 （自然科...
  • 行 : 行Ⅰ名詞1 （行列） line; row 2 （排行） seniority among brothers and sisters:你行幾? 我行三。where...
  • 性 : Ⅰ名詞1 （性格） nature; character; disposition 2 （性能; 性質） property; quality 3 （性別） sex ...
  1. With the rapid development of high - speed networks and the design of software for network parallel computing such as pvm, mpi, express linda and p4, the merits of network parallel computing, such as small costs, quick returns, strong flexility and high ratio of performance to costs, are more outstanding, making the network parallel computing be favored by more and more universities and research institutes both at home and abroad and become one of the important branches of parallel and distributed computing

    高速信息網路的飛速發展以及網路并行計算支撐軟體如pvm 、 mpi 、 express 、 linda ， p4等的出現，使得網路并行計算的投資少、見效快、靈活性強、性能價格比高等諸多優點顯得更加突出，受到國內外越來越多的大學和科研單位的青睞，已成為并行計算和分散式計算技術的重要發展方向。
  2. In this text, we first do some research on the genetic algorithm about clustering, discuss about the way of coding and the construction of fitness function, analyze the influence that different genetic manipulation do to the effect of cluster algorithm. then analyze and research on the way that select the initial value in the k - means algorithm, we propose a mix clustering algorithm to improve the k - means algorithm by using genetic algorithm. first we use k - learning genetic algorithm to identify the number of the clusters, then use the clustering result of the genetic clustering algorithm as the initial cluster center of k - means clustering. these two steps are finished based on small database which equably sampling from the whole database, now we have known the number of the clusters and initial cluster center, finally we use k - means algorithm to finish the clustering on the whole database. because genetic algorithm search for the best solution by simulating the process of evolution, the most distinct trait of the algorithm is connotative parallelism and the ability to take advantage of the global information, so the algorithm take on strong steadiness, avoid getting into the local

    本文首先對聚類分析的遺傳演算法進行了研究，討論了聚類問題的編碼方式和適應度函數的構造方案與計算方法，分析了不同遺傳操作對聚類演算法的性能和聚類效果的影響意義。然後對k - means演算法中初值的選取方法進行了分析和研究，提出了一種基於遺傳演算法的k - means聚類改進（混合聚類演算法） ，在基於均勻采樣的小樣本集上用k值學習遺傳演算法確定聚類數k ，用遺傳聚類演算法的聚類結果作為k - means聚類的初始聚類中心，最後在已知初始聚類數和初始聚類中心的情況下用k - means演算法對完整數據集進行聚類。由於遺傳演算法是一種通過模擬自然進化過程搜索最優解的方法，其顯著特點是隱含并行性和對全局信息的有效利用的能力，所以新的改進演算法具有較強的穩健性，可避免陷入局部最優，大大提高聚類效果。
  3. Genetic algorithm, as a computational model simulating the biological evolution process of the genetic selection theory of dar - win, is a whole new global optimization algorithm and is widely used in many fields with its remarkable characteristic of simplicity, commonability, stability, suitability for parallel processing, high - efficiency, and practibility. on the other hand, there are many op - timization problems in the field of digital image processing, such as image compression, pattern - recognition, image rectification, image segmentation, 3d image recovery, image inquiry, and or so. in fact all these problems can be generalized as the problem of searching for a global optimal solution in a large solution space, which is the classic application field of genetic algorithm

    遺傳演算法是模擬達爾文的遺傳選擇和自然淘汰的生物進化過程的計算模型，是一種新的全局優化搜索演算法，具有簡單通用、穩定性強、適于并行處理以及高效、實用等顯著特點，在很多領域得到了廣泛應用，另一方面，在圖像處理領域有很多優化問題如圖像壓縮，模式識別，圖像校準，圖像分割，三維重建，圖像檢索等等，實際上都等同於一個大范圍搜索尋優問題，而最優化問題是遺傳演算法經典應用領域，因此遺傳演算法完全勝任在圖像處理中優化方面的計算。
  4. Working at automatic mode the system can transmit the data to computer through the parallel port which work at epp ( enhanced parallel port ) mode. then the computer shows the characteristic relation curves and acquires the characteristic arithmetic expression. the sampling frequency reach to 4khz, the core of control system is microcontroller uint ( mcu ) 89c51 ， the data acquisition is 12 bite

    也可以工作在自動方式下通過并行介面（工作于epp模式） ，把測量到的數據輸入計算機，在計算機上顯示特性參數間的關系曲線，以及求出參數間的數學關系式，其采樣頻率可達4khz 。
  5. Abstract : the computational and compositional features are very important while constructing parallel software for the workstation clusters. however, lack of suitable supporting environment for parallel software development makes most existing distributed parallel software systems very weak in these two aspects, especially in the compositional feature. in this paper, a distributed object based framework for parallel computation is proposed. the goal of the framework is to achieve high efficiency for parallel computing, to construct a mechanism to encapsulate and reuse parallel programs, and to guarantee load balancing and fault tolerance. the framework is a four - layer model that includes an object - group layer and a mobile object layer. the experimental results verify the efficiency of the scheme

    文摘:在為工作站機群構造并行軟體的過程中，計算特徵和組成特徵非常重要.但是，由於缺乏有效的支撐環境，當今的分散式并行計算軟體系統效率低下，這在計算特徵方面尤為明顯.提出一個基於分散式對象的并行計算框架，目的在於保證高效的并行計算開發，提供封裝和復用并行程序的機制，並保證系統的動態平衡和容錯性.框架是4層模型，包括對象組層和移動對象層.實驗結果證明了方案的有效性
  6. In each sub - population, breeding and evaluation are implemented using multi - threaded mechanism. the benchmark problems numerical experiment results demonstrate that the proposed method can rapidly converge to the pareto optimal front and spread widely along the front

    在做了這兩種方式的并行化以後不僅可以獲得更好的計算性能，在pareto最優解集的優化效果上有更顯著的改進。
  7. Comparing with the traditional parallel interface chips, they have fewer legs ~ smaller volume and use fewer resources. therefore, multiple channel data selecting controls keyboar &. display and alarm are realized through at89c52 ? four eight - bit i / o interface, without extending other i / o interface, making the system simplified and reliability increased

    單片機的i / o介面晶元全部採用最新的串列工作方式介面晶元，與傳統的并行介面晶元相比，它們引腳數少，體積小，佔用的口資源少，因此用at89c52的4個8位的i / o口就完成了多個通道的數據採集、控制、鍵盤、顯示和報警等功能，沒有擴展其它i / o介面，使系統接線簡化，可靠性提高。
  8. In the parallel computation, there are two strategies, namely sbs and ebe ; for the nonlinear problem solution, there are direct and iterative algorithms, but for dynamic analysis there are explicit and implicit integration, and high precision direct integration

    有限元并行計算有sbs 、 ebe兩種策略，非線性求解有直接與迭代解法，動力時程分析有顯式、隱式和精細時程積分法。
  9. We summarized several main reasons of low parallel efficiency of the npupar system, and improved it accordingly. in our test, the efficiency of the programs generated by modified npupar increased remarkablely ( about 10 % ). we also make deep quantitative analysis for the super - linear speedup in the test

    通過對兩個實際的cfd實常式序的對比測試，改進后的npupar系統在保證正確性的基礎上并行效率有了明顯的提高（普遍提高了10左右） ，並對測試中出現的超線性加速比做了深入的定量分析。
  10. 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

    本文討論、分析、總結了通用的自動并行化技術：相關性分析理論、程序變換技術、并行模式以及同步通信與優化問題等等，它們是本文研究工作的理論基礎；針對研究對象，深入分析了cfd計算的特點，特別是顯式差分計算的特點；並歸納出傳統的自動并行化技術在cfd應用中存在的問題：并行粒度小、難以獲得全局統一的數據劃分方式，對于分佈存儲結構的并行機難以獲得高效率。
分享友人
分享到 Line

分享到臉書