面向甚大规模集成电路的时延驱动布局方法

本文针对甚大规模集成电路的时延驱动布局问题提出了一个新的解决途径,其策略是将结群技术应用于二次规划布局过程中.结群的作用是可大幅度地降低布局部件的数量.本文设计了一个高效的结群算法CARGO,其优点是具有全局最优性并且运行速度很快.采用了一个基于路径的时延驱动二次规划布局算法对结群后的电路完成布局过程.由于二次规划布局算法能够在很短时间内寻找到全局最优解,故本文的算法更有希望彻底解决甚大规模电路的布局问题.在一组MCMC标准测试电路上对算法进行了测试,得到了满意的结果.     

一种新型宏模块和标准单元的混合模式布局算法

本文针对包含有宏模块和标准单元的超大规模集成电路布局问题, 提出了一个新的混合模式布局算法MMP.该算法综合应用了自底向上的结群策略,数学规划和Slicing划分等技术.MMP算法可以对宏模块和小单元同时求解,算法稳定性好,实用性强,不但求解质量高,而且运算速度快.我们对一组来自工业界的设计实例进行了测试,实验结果表明,MMP是非常实用而高效的.     

标准单元布局中的高效结群算法

本文提出了一个高效的结群算法,用以解决在超大规模条件下标准单元模式集成电路的布局问题.与传统结群算法相比,本算法的特色在于在结群之前,建立和组织了表示所有单元之间连接关系的信息库,使得结群算法具有全局优化性和无冗余计算的特点.本结群算法已应用于二次规划布局过程中.实验结果表明,本算法无论在结群质量和结群速度方面都非常理想,从而成功地解决了超大规模电路的布局问题.     

优化时延与拥挤度的增量式布局算法

提出了一种优化时延的增量式布局算法,该算法根据时延分析的结果在迭代求解的过程中动态调整线网权值.在此基础上,提出了三种同时优化时延和拥挤度的多目标优化的布局算法,在满足时延和拥挤度约束的前提下对关键路径上的单元进行位置调整.实验结果表明该算法能够有效地提高芯片速度并降低走线拥挤.对于优化线长得到的布局方案,最长路径上的时延值在增量式布局之后能够降低10%.     

优化时延与拥挤度的增量式布局算法

提出了一种优化时延的增量式布局算法,该算法根据时延分析的结果在迭代求解的过程中动态调整线网权值.在此基础上,提出了三种同时优化时延和拥挤度的多目标优化的布局算法,在满足时延和拥挤度约束的前提下对关键路径上的单元进行位置调整.实验结果表明该算法能够有效地提高芯片速度并降低走线拥挤.对于优化线长得到的布局方案,最长路径上的时延值在增量式布局之后能够降低10 % .     

最大流算法应用于二次线性规划布局合法化过程

以力导向为基础的解析型算法如今越来越多地被应用到FPGA布局问题当中去,二次线性规划算法便是其中一种,其使用数学的方法求解拉力模型矩阵,以得到理论的最优解.但在实际的算法实现当中,二次线性规划虽体现出了其较快求解的特性,其解却存有重叠的问题,尚需进一步合法化以解决重叠问题.现有的合法化过程一般较为随意,并无系统性算法,...     

一种新的基于结群的混合模式划分方法

提出一种专用于带有预设计模块的混合模式布局的划分算法.它基于扩展的MFFC结群算法,结合自下而上的结群和自上而下的划分为一体进行混和模式下的划分.这样不仅可以使划分能够考虑电路本身的逻辑依赖,而且可以得到很好的\"最小割\"划分结果.实验结果表明,这种划分算法在层次式混合模式布局流程里起到了显著的作用.将此算法和当今国际上著名的划分包HMETIS 进行比较,结果表明此算法有一定的优势.     

网络延迟聚类的宏观预警的检测点放置

大规模异常事件爆发,使网络可用性受到严重威胁。引发人们对大规模入侵检测系统的研究,其检测效果直接取决于网络检测点选取。大规模网络预警检测点放置问题被转化为网络拓扑有权图聚类问题。针对层次聚类算法面临的初始点选择问题提出基于出度分离初始点选择算法,降低聚类结果对初值的依赖。同时,提出改进双向层次聚类算法DHC,有效降低了结果簇数量。实验证明,此算法整体最优并成功应用于测得的真实全国骨干网络,有效解决了检测点放置问题。     

用户兴趣感知的内容副本优化放置算法

提出了用户兴趣感知的内容副本优化放置算法。该算法首先基于聚类算法从用户访问日志提取各用户的群体内容兴趣主题,依据其所辖用户的个体兴趣度加权得其群体兴趣度,并对其进行实时更新;然后在非线性优化模型下,以最小化平均响应时间为目标,优先放置群体兴趣度较大的副本,以实现被放置副本与用户内容兴趣主题的最大匹配。在平均响应时间、请求响应匹配度、负载均衡和邻近副本利用率等方面,与1-Greedy-Insert等算法进行对比,仿真结果显示各性能指标平均提升了约30%,验证了算法的有效性。     

基于划分的力矢量布局算法

提出了一个全新的基于划分的力矢量布局算法．针对大规模集成电路的布局问题,采用基于并行结群技术的递归划分方法进行分解解决,并结合改进的力矢量算法对划分所得的子电路进行迭代布局优化．通过对MCNC标准单元测试电路的实验,与FengShui布局工具相比,该布局算法在花费稍长一点的时间内获得了平均减少12%布局总线长度的良好效果．     

A New Clustering-Based Partitioning Method for VLSI Mixed-Mode Placement

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.     

Net Clustering Based Constructive and Iterative Improvement Approaches for Macro-Cell Placement

We propose a net clustering based RT-level macro-cell placement approaches. Static timing analysis identifies critical nets and critical primary input/output paths. Net clustering (based on shared macro-cells and net criticality) yields clusters wherein each cluster has strongly interdependent nets. The circuit is modeled as a graph in which each vertex v represents a net and each edge (v,u) a shared cell between nets v and u. The net clusters are obtained by applying a clique partitioning algorithm on the circuit graph. Two approaches to generate placements at RTL are proposed: constructive (cluster growth) approach and iterative improvement (simulated annealing) based approach. In the constructive approach, a cluster-level floorplanning is performed and a cluster ordering is obtained. The cluster ordering is used by a constructive procedure to generate the physical placement. In the case of iterative improvement based approach, a good ordering of clusters is obtained using simulated annealing.We report experimental results for five RTL datapaths implemented in 0.35 m technology to demonstrate the efficacy of the proposed approaches. We compared the layouts produced by our approaches with those produced by Flint, an automatic floor planner in Lager IV Silicon Compiler [1]. For constructive placement approach, we obtained an average decrease of 43.4% in longest wirelength and 32.4% in total wirelength. The average area reduction is 7.3%. On the other hand, for the SA-based approach, we obtained an average decrease of 57.6% in longest wirelength and 42.2% in total wirelength. The average reduction in the bounding-box area is 12.3%. As expected, the SA-based approach yielded better optimization results, due to its ability to climb out of local minima.     

HR-DO: High reliable–delay optimized controller placement in software-defined networking

Currently, networking technologies are pivoting towards software-defined networking (SDN) due to its easy management and centralized control system. The SDN network metrics, such as latency, scalability, robustness, and reliability largely depends on controller placement in the network domain. In view of betterment and best progression of network quality, the above mentioned network metrics need to be laid more emphases by considering controller placement. To achieve better network quality, an HR-DO (high reliable–delay optimized controller placement) is proposed. Fuzzy C-means, a meta-heuristic optimization algorithm, is used to optimize the number of controllers required in the network due to its effectiveness in cluster selection. It also eases the network latency. In addition, a minimal cut set-based Boolean logic approach and natural connectivity metric are used to improve the reliability and robustness of SDN with minimum worst-case latency. To check the performance, the proposed HR-DO is implemented on a topology-zoo network data set (OS3E and Chinanet). For comparison purposes, OCPA and K-means algorithms are taken into the account of latency, reliability, and robustness as parameters. The performance of the HR-DO approach outperforms over K-means and OCPA with respect to latency, reliability, and robustness.     

大规模混合模式初始详细布局算法

以大规模混合模式布局问题为背景,提出了有效的初始详细布局算法.在大规模混合模式布局问题中,由于受到计算复杂性的限制,有效的初始布局算法显得非常重要.该算法采用网络流方法来满足行容量约束,采用线性布局策略解决单元重叠问题.同时,为解决大规模设计问题,整体上采用分治策略和简化策略,有效地控制问题的规模,以时间开销的少量增加换取线长的明显改善.实验结果表明该算法能够取得比较好的效果,平均比PAFLO算法有16%的线长改善,而CPU计算时间只有少量增加.     

大规模混合模式初始详细布局算法

以大规模混合模式布局问题为背景 ,提出了有效的初始详细布局算法 .在大规模混合模式布局问题中 ,由于受到计算复杂性的限制 ,有效的初始布局算法显得非常重要 .该算法采用网络流方法来满足行容量约束 ,采用线性布局策略解决单元重叠问题 .同时 ,为解决大规模设计问题 ,整体上采用分治策略和简化策略 ,有效地控制问题的规模 ,以时间开销的少量增加换取线长的明显改善 .实验结果表明该算法能够取得比较好的效果 ,平均比 PAFL O算法有 1 6 %的线长改善 ,而 CPU计算时间只有少量增加     

A Novel OFDM Timing Offset Estimation Algorithm

1　Introduction　OrthogonalFrequencyDivisionMultiplexing(OFDM )isamethodsuitableforhigh ratedatatransmissioninwirelesscommunications .However,thereareseverallimitingfactorsinthecommercialapplicationofOFDMforapplyingtohigh ratemo bilecommunication ,suchasDopplerfrequencyshift,synchronization ,channelestimation ,peak to averagepowerratio .　Schmidl[1 ] completedsynchronizationusingspecialPNsequence,buttheestimateisnot precise.Minn[2～ 3] andByungjoon[4] improvethealgorithmperformance,butth…