The method is also tested by finite volume scheme and partitioning algorithm of euler equation in parallel computing in fluid dynamics . the testing results demonstrate that the suggested method in this method is of practical and scientific significance in parallel computing in fluid dynamics 本文還結(jié)合euler方程的有限體積格式和區(qū)域分解算法對文中的算法在流體力學(xué)并行計算中進行了進一步的驗證,從數(shù)值計算結(jié)果可以看出,本文提出的算法能夠很好地應(yīng)用于計算流體力學(xué)并行計算,具有一定的科學(xué)應(yīng)用價值。
It is efficient when applied in the control intensive design but the quality of synthesis " results is not well accepted when used for other type of design . the other is a multi - target hls optimization method , used before the subtask of hls scheduling . the essence of the method is a system partition algorithm , the multi - target optimization is reflected when convert the behavioral description into a graph . the purpose of the partition is to find the explicit control relation and parallel computation 其二是提出了一種多目標(biāo)的高級綜合優(yōu)化策略,該方法用在高級綜合的調(diào)度之前,其核心是對系統(tǒng)進行劃分,在將行為描述轉(zhuǎn)化為內(nèi)部表示模型的時,通過探索中間表示結(jié)果的關(guān)系來發(fā)現(xiàn)原設(shè)計描述中的控制關(guān)系和并行計算,以便在高級綜合中取得理想的結(jié)果,同時將行為描述轉(zhuǎn)化為圖的過程中體現(xiàn)多種優(yōu)化目的,所采用的中間表示模型為基于petri網(wǎng)的內(nèi)部表示模型,劃分采用了模擬退火算法。
Abstract : the parallel computer ' s resource can be used efficiently by proper task partitioning and parallel granularity controlling . by analyzing the characteristic of simulation program , this paper points out a task partitioning algorithm which take state equations as core and right - hand function as object . the algorithm has been used in the automatic parallel tools which we have developed and the application results have showed good effect on parallel simulation 文摘:有效地進行任務(wù)劃分、控制并行粒度,才能充分利用并行計算機的資源,通過對復(fù)雜連續(xù)系統(tǒng)仿真程序特點的分析,提出了以狀態(tài)方程為核心、以右函數(shù)段的計算為主要對象的自動任務(wù)劃分算法,使用結(jié)果表明具有很好的并行效果。
Firstly , the size of the graph is reduced by collapsing vertices and edges . then , each smaller graph is divided into a certain number of subdomains by means of initial partitioning algorithm . finally , these subdomains are refined back to the original graph through mapping and multi - partitioning refinement strategy 首先通過圖的頂點和邊的收縮將圖逐層縮小,然后在小圖上用初始分區(qū)算法將它劃分為給定數(shù)目的子區(qū),最后利用映射和多分區(qū)調(diào)整策略將小圖上的分區(qū)細(xì)化回歸到原始圖。
A new dynamic process model partition and distribution method is proposed in this thesis , which can delete the redundant information form distributed executing sites gradually during the process execution , and still support dynamic change of the workflow processes . the process partition algorithm is studied in detail , and the architecture of a fully distributed workflow executing system is put forward based on this algorithm 當(dāng)前兩種主要的工作流分布式執(zhí)行方法? ?可移動代理和過程定義分割? ?不能同時解決工作流動態(tài)更改和運行時數(shù)據(jù)傳輸量大的問題,本文提出一種新的過程模型動態(tài)分割和動態(tài)分配方法,它可以在運行時逐步從分布式執(zhí)行站點上去除冗余信息,并保證得到的部分過程模型仍能支持動態(tài)更改。
Abstract : an efficient partitioning algorithm for mixed - mode placement , extended - mffc - based partitioning , is presented . it combines the bottom - up clustering and the top - down partitioning together . to do this , designers can not only cluster cells considering logic dependency but also partition them aiming at min - cut . experimental results show that extended - mffc - based partitioning performs well in mixed - mode placement with big pre - designed blocks . by comparison with the famous partitioning package hmetis , this partitioning proves its remarkable function in mixed - mode placement 文摘:提出一種專用于帶有預(yù)設(shè)計模塊的混合模式布局的劃分算法.它基于擴展的mffc結(jié)群算法,結(jié)合自下而上的結(jié)群和自上而下的劃分為一體進行混和模式下的劃分.這樣不僅可以使劃分能夠考慮電路本身的邏輯依賴,而且可以得到很好的"最小割"劃分結(jié)果.實驗結(jié)果表明,這種劃分算法在層次式混合模式布局流程里起到了顯著的作用.將此算法和當(dāng)今國際上著名的劃分包hmetis進行比較,結(jié)果表明此算法有一定的優(yōu)勢