Extractive summarization using complex networks and syntactic dependency

The realization that statistical physics methods can be applied to analyze written texts represented as complex networks has led to several developments in natural language processing, including automatic summarization and evaluation of machine translation. Most importantly, so far only a few metrics of complex networks have been used and therefore there is ample opportunity to enhance the statistics-based methods as new measures of network topology and dynamics are created. In this paper, we employ for the first time the metrics betweenness, vulnerability and diversity to analyze written texts in Brazilian Portuguese. Using strategies based on diversity metrics, a better performance in automatic summarization is achieved in comparison to previous work employing complex networks. With an optimized method the Rouge score (an automatic evaluation method used in summarization) was 0.5089, which is the best value ever achieved for an extractive summarizer with statistical methods based on complex networks for Brazilian Portuguese. Furthermore, the diversity metric can detect keywords with high precision, which is why we believe it is suitable to produce good summaries. It is also shown that incorporating linguistic knowledge through a syntactic parser does enhance the performance of the automatic summarizers, as expected, but the increase in the Rouge score is only minor. These results reinforce the suitability of complex network methods for improving automatic summarizers in particular, and treating text in general.     

激波与火焰面相互作用数值模拟的GPU加速

为考察计算机图形处理器（GPU）在计算流体力学中的计算能力,采用基于CPU/GPU异构并行模式的方法对激波与火焰界面相互作用的典型可压缩反应流进行数值模拟,优化并行方案,考察不同网格精度对计算结果和计算加速性能的影响.结果表明,和传统的基于信息传递的MPI 8线程并行计算相比,GPU并行模拟结果与MPI并行模拟结果相同;两种计算方法的计算时间均随网格数量的增加呈线性增长趋势,但GPU的计算时间比MPI明显降低.当网格数量较小时（1.6×10⁴）,GPU计算得到的单个时间步长平均时间的加速比为8.6;随着网格数量的增加,GPU的加速比有所下降,但对较大规模的网格数量（4.2×10⁶）,GPU的加速比仍可达到5.9.基于GPU的异构并行加速算法为可压缩反应流的高分辨率大规模计算提供了较好的解决途径.     

KSSOLV-GPU：一款利用GPU高效求解Kohn-Sham方程的平面波基组密度泛函理论MATLAB程序包

KSSOLV(Kohn-Sham Solver)是一款用于求解平面波基组下Kohn-Sham方程(KS-DFT)的MATLAB(Matrix Laboratory)工具箱. 在KS-DFT的基态计算中,通常自洽场迭代中Kohn-Sham哈密顿量的对角化是最昂贵的部分. 为了使得个人计算机也能够执行数百个原子的中等大小KS-DFT计算,本文提出了一种CPU-GPU的混合编程方案,通过调用MATLAB内置的并行计算工具箱来加速在KSSOLV中实现的迭代对角化算法. 比较了KSSOLV-GPU在RTX3090、V100、A100三种GPU上的性能;结果表明,对于包含128个原子的块状硅体系,与串行的CPU计算相比,混合CPU-GPU的编程可以实现约10倍的加速. 特别是其在最新的民用GPU显卡RTX3090上也具有优秀的表现,可以预想到在不远的将来,KSSOLV-GPU借助MATLAB强大的可视化能力与GPU的加速支持可以在一台配备了民用GPU显卡的个人电脑上实现常规的DFT计算分析与可视化,从而降低了材料模拟与计算领域的门槛.     

Implementation of Multi-GPU Based Lattice Boltzmann Method for Flow Through Porous Media

The lattice Boltzmann method (LBM) can gain a great amount of performance benefit by taking advantage of graphics processing unit (GPU) computing, and thus, the GPU, or multi-GPU based LBM can be considered as a promising and competent candidate in the study of large-scale fluid flows. However, the multi-GPU based lattice Boltzmann algorithm has not been studied extensively, especially for simulations of flow in complex geometries. In this paper, through coupling with the message passing interface (MPI) technique, we present an implementation of multi-GPU based LBM for fluid flow through porous media as well as some optimization strategies based on the data structure and layout, which can apparently reduce memory access and completely hide the communication time consumption. Then the performance of the algorithm is tested on a one-node cluster equipped with four Tesla C1060 GPU cards where up to 1732 MFLUPS is achieved for the Poiseuille flow and a nearly linear speedup with the number of GPUs is also observed.     

Approaching human language with complex networks

The interest in modeling and analyzing human language with complex networks is on the rise in recent years and a considerable body of research in this area has already been accumulated. We survey three major lines of linguistic research from the complex network approach: 1) characterization of human language as a multi-level system with complex network analysis; 2) linguistic typological research with the application of linguistic networks and their quantitative measures; and 3) relationships between the system-level complexity of human language (determined by the topology of linguistic networks) and microscopic linguistic (e.g., syntactic) features (as the traditional concern of linguistics). We show that the models and quantitative tools of complex networks, when exploited properly, can constitute an operational methodology for linguistic inquiry, which contributes to the understanding of human language and the development of linguistics. We conclude our review with suggestions for future linguistic research from the complex network approach: 1) relationships between the system-level complexity of human language and microscopic linguistic features; 2) expansion of research scope from the global properties to other levels of granularity of linguistic networks; and 3) combination of linguistic network analysis with other quantitative studies of language (such as quantitative linguistics).     

Importance of explicit vectorization for CPU and GPU software performance

Much of the current focus in high-performance computing is on multi-threading, multi-computing, and graphics processing unit (GPU) computing. However, vectorization and non-parallel optimization techniques, which can often be employed additionally, are less frequently discussed. In this paper, we present an analysis of several optimizations done on both central processing unit (CPU) and GPU implementations of a particular computationally intensive Metropolis Monte Carlo algorithm. Explicit vectorization on the CPU and the equivalent, explicit memory coalescing, on the GPU are found to be critical to achieving good performance of this algorithm in both environments. The fully-optimized CPU version achieves a 9× to 12× speedup over the original CPU version, in addition to speedup from multi-threading. This is 2× faster than the fully-optimized GPU version, indicating the importance of optimizing CPU implementations.     

MATLAB语言在色谱保留指数预测中的应用

简要介绍了当今世界先进的科学与工程计算软件MATLAB.MATLAB是一种高性能的数值计算的科学计算语言,具有程序开发环境简洁直观、数值稳定性好、函数资源丰富的特点.本文以具体计算方法为例,讨论了MATLAB在数值计算中的应用,得出MATLAB软件建立多元回归模型的优越性,预测了色谱保留指数.     

NeuDATool：支持GPU硬件加速和计算机集群跨节点并行的开源中子散射数据分析软件

实验势精修是20世纪80年代英国散裂中子源无定型材料组开发的用于分析中子散射实验数据的软件. 实验势精修的目标是根据中子散射数据重建样品的三维原子结构. 在过去的几十年,实验势精修被广泛用于中子散射实验数据分析,为实验用户提供了可靠的分析结果. 但是实验势精修是基于共享内存并行计算(OpenMP)的Fortran程序,不支持计算机服务器集群跨节点并行加速和GPU加速;这限制了它的分析速度. 随着计算机服务器集群的广泛建设和GPU加速技术的普遍使用,有必要重新编写EPSR程序以提高运算速度. 本文使用面向对象的C++语言,开发了一套实现EPSR算法的开源软件包NeuDATool;软件通过MPI和CUDA C实现了计算机集群跨节点并行和GPU加速. 使用液态水和玻璃态二氧化硅的中子散射实验数据对软件进行了测试. 测试显示软件可以正确重建出样品的三维原子结构;并且模拟体系达到10万原子以上时,使用GPU加速可以比串行的CPU算法提高400倍以上的模拟速度. NeuDATool为中子实验用户尤其是对熟悉C++编程并希望定义特殊分析算法的实验科学家提供了一种新的选择.     

共焦显微镜扫描工作台的系统建模与动态分析

共焦显微镜扫描工作台动态模型是研究控制系统的重要依据,它直接影响工作台的重复定位精度.提出了将机械部分和电气部分分开建模的方法,建立了系统数学模型,该方法具有较好的可移植性,建模过程简单,有利于分析系统各环节对系统控制性能的影响.在MATLAB/Simulink下进行仿真,2 s内系统达到了稳定状态,证明了系统具有很好的动态特性,满足控制的要求.     

Porting and scaling OpenACC applications on massively-parallel,GPU-accelerated supercomputers

An increasing number of massively-parallel supercomputers are based on heterogeneous node architectures combining traditional, powerful multicore CPUs with energy-efficient GPU accelerators. Such systems offer high computational performance with modest power consumption. As the industry trend of closer integration of CPU and GPU silicon continues, these architectures are a possible template for future exascale systems. Given the longevity of large-scale parallel HPC applications, it is important that there is a mechanism for easy migration to such hybrid systems. The OpenACC programming model offers a directive-based method for porting existing codes to run on hybrid architectures. In this paper, we describe our experiences in porting the Himeno benchmark to run on the Cray XK6 hybrid supercomputer. We describe the OpenACC programming model and the changes needed in the code, both to port the functionality and to tune the performance. Despite the additional PCIe-related overheads when transferring data from one GPU to another over the Cray Gemini interconnect, we find the application gives very good performance and scales well. Of particular interest is the facility to launch OpenACC kernels and data transfers asynchronously, which speeds the Himeno benchmark by 5%–10%. Comparing performance with an optimised code on a similar CPU-based system (using 32 threads per node), we find the OpenACC GPU version to be just under twice the speed in a node-for-node comparison. This speed-up is limited by the computational simplicity of the Himeno benchmark and is likely to be greater for more complicated applications.     

Identifying Influential Nodes in Complex Networks Based on Multiple Local Attributes and Information Entropy

Identifying influential nodes in complex networks has attracted the attention of many researchers in recent years. However, due to the high time complexity, methods based on global attributes have become unsuitable for large-scale complex networks. In addition, compared with methods considering only a single attribute, considering multiple attributes can enhance the performance of the method used. Therefore, this paper proposes a new multiple local attributes-weighted centrality (LWC) based on information entropy, combining degree and clustering coefficient; both one-step and two-step neighborhood information are considered for evaluating the influence of nodes and identifying influential nodes in complex networks. Firstly, the influence of a node in a complex network is divided into direct influence and indirect influence. The degree and clustering coefficient are selected as direct influence measures. Secondly, based on the two direct influence measures, we define two indirect influence measures: two-hop degree and two-hop clustering coefficient. Then, the information entropy is used to weight the above four influence measures, and the LWC of each node is obtained by calculating the weighted sum of these measures. Finally, all the nodes are ranked based on the value of the LWC, and the influential nodes can be identified. The proposed LWC method is applied to identify influential nodes in four real-world networks and is compared with five well-known methods. The experimental results demonstrate the good performance of the proposed method on discrimination capability and accuracy.     

众核处理架构在水下航行器相位编码脉冲回波检测中的应用

针对宽带编码脉冲、多输入多输出等新型目标探测体制发展带来的运算量和数据存储需求剧增的问题,根据水下航行器相位编码脉冲回波检测算法的数据级并行特点,提出应用图形处理器(Graphics Processing Unit,GPU)众核处理架构,并从任务分配策略、数据处理流程、GPU硬件资源利用率和存储器访问等角度考虑,设计了算法在GPU上的并行实现框架。利用湖试数据测试了桌面级GPU平台、嵌入式GPU平台与基于多核数字信号处理器(Digital Signal Processor,DSP)的传统航行器信号处理平台的性能,与多核DSP平台相比,嵌入式GPU平台在功耗、运算性能等方面更有优势。研究结果表明采用嵌入式GPU平台可大幅提升每瓦特性能指标并简化系统设计,能满足新型航行器探测系统大数据量、低功耗和实时性的应用需求。      

GPU accelerated Monte Carlo simulation of the 2D and 3D Ising model

The compute unified device architecture (CUDA) is a programming approach for performing scientific calculations on a graphics processing unit (GPU) as a data-parallel computing device. The programming interface allows to implement algorithms using extensions to standard C language. With continuously increased number of cores in combination with a high memory bandwidth, a recent GPU offers incredible resources for general purpose computing. First, we apply this new technology to Monte Carlo simulations of the two dimensional ferromagnetic square lattice Ising model. By implementing a variant of the checkerboard algorithm, results are obtained up to 60 times faster on the GPU than on a current CPU core. An implementation of the three dimensional ferromagnetic cubic lattice Ising model on a GPU is able to generate results up to 35 times faster than on a current CPU core. As proof of concept we calculate the critical temperature of the 2D and 3D Ising model using finite size scaling techniques. Theoretical results for the 2D Ising model and previous simulation results for the 3D Ising model can be reproduced.     

大规模声学边界元法的GPU并行计算

提出一种大规模声学边界元法的高效率、高精度GPU并行计算方法.基于Burton-Miller边界积分方程,推导适于GPU的并行计算格式并实现了传统边界元法的GPU加速算法.为提高原型算法的效率,研究GPU数据缓存优化方法.由于GPU的双精度浮点运算能力较低,为了降低数值误差,研究基于单精度浮点运算实现的doublesingle精度算法.数值算例表明,改进的算法实现了最高89.8%的GPU使用效率,且数值精度与直接使用双精度数相当,而计算时间仅为其1/28,显存消耗也仅为其一半.该方法可在普通PC机(8GB内存,NVIDIA Ge Force 660 Ti显卡)上快速完成自由度超过300万的大规模声学边界元分析,计算速度和内存消耗均优于快速边界元法.     

二维传热数值计算程序在图形卡上的实现

本文针对通用图形处理器(GPGPU)的特点,对二维传热数值求解算法及三类不同边界条件问题在GPU上的求解进行了分析.图形处理器是一种专用并行处理器,主要用于三维场景渲染加速,其结构和程序设计方式与CPU完全不同,但却比CPU具有更强的浮点运算能力和内存带宽.随着图形处理器可编程特性的发展,它已越来越超出原有的应用范围,向通用计算领域发展,成为一个新的研究领域.采用Jacobi迭代,能够在GPU上实现二维导热方程的求解.本文在已有研究的基础上,实现了二维导热计算的混合边界条件问题在GPU上的求解方法,通过计算时间的比较显示GPU在计算传热学中有良好应用前景.     

English and Chinese languages as weighted complex networks

In this paper, we analyze statistical properties of English and Chinese written human language within the framework of weighted complex networks. The two language networks are based on an English novel and a Chinese biography, respectively, and both of the networks are constructed in the same way. By comparing the intensity and density of connections between the two networks, we find that high weight connections in Chinese language networks prevail more than those in English language networks. Furthermore, some of the topological and weighted quantities are compared. The results display some differences in the structural organizations between the two language networks. These observations indicate that the two languages may have different linguistic mechanisms and different combinatorial natures.     

An empirical study of Chinese language networks

Chinese is spoken by the largest number of people in the world, and it is regarded as one of the most important languages. In this paper, we explore the statistical properties of Chinese language networks (CLNs) within the framework of complex network theory. Based on one of the largest Chinese corpora, i.e. People’s Daily Corpus, we construct two networks (CLN1 and CLN2) from two different respects, with Chinese words as nodes. In CLN1, a link between two nodes exists if they appear next to each other in at least one sentence; in CLN2, a link represents that two nodes appear simultaneously in a sentence. We show that both networks exhibit small-world effect, scale-free structure, hierarchical organization and disassortative mixing. These results indicate that in many topological aspects Chinese language shapes complex networks with organizing principles similar to other previously studied language systems, which shows that different languages may have some common characteristics in their evolution processes. We believe that our research may shed some new light into the Chinese language and find some potentially significant implications.     

Linear analysis of degree correlations in complex networks

Many real-world networks such as the protein–protein interaction networks and metabolic networks often display nontrivial correlations between degrees of vertices connected by edges. Here, we analyse the statistical methods used usually to describe the degree correlation in the networks, and analytically give linear relation in the degree correlation. It provides a simple and interesting perspective on the analysis of the degree correlation in networks, which is usefully complementary to the existing methods for degree correlation in networks. Especially, the slope in the linear relation corresponds exactly to the degree correlation coefficient in networks, meaning that it can not only characterize the level of degree correlation in networks, but also reflects the speed that the average nearest neighbours’ degree varies with the vertex degree. Finally, we applied our results to several real-world networks, validating the conclusions of the linear analysis of degree correlation. We hope that the work in this paper can be helpful for further understanding the degree correlation in complex networks.     

GPU implementations of the bond fluctuation model

We present two parallel implementations of the bond fluctuation model on graphics processors that outperform by a factor of up to 50 times an equivalent implementation on single CPU processor. The first algorithm is a parallelized version of an accelerated MC method published earlier in [S. Nedelcu, J.-U. Sommer, Single chain dynamics in polymer networks: a Monte Carlo study, J. Chem. Phys. 130 (2009) 204902]. In this first algorithm we use the parallel domain decomposition technique to avoid monomer collisions. In contrast, in the second algorithm we associate each monomer with a parallel process, where all monomers in the system are attempted to move simultaneously. In both cases, only monomer moves that result in allowed bonds and preserve lattice occupancy are accepted. To validate the correctness of the GPU algorithms we simulated monodisperse polymer melts at monomer number density 0.5 and compared static and dynamical properties with standard CPU implementations. We found good agreement between the CPU and the GPU results, which demonstrates the equivalence of the serial and parallel implementations. The influence of higher monomer number density is discussed.