Parallel Heuristics Research Articles

The Discovery of Aspect: A Heuristic Parallel Corpus Study of Ingressive, Continuative and Resumptive Viewpoint Aspect

Languages differ in how systematically and obligatorily they encode conceptual categories such as tense and aspect. By drawing on large parallel corpora, these differences can be exploited heuristically: expressive obligatoriness and the systematicity of a conceptual category in one language can function as a probe for other languages that do not (evidently) encode it. This study applies this method—called heuristic translation mining (HTM)—to viewpoint aspect in Mandarin (an aspect-oriented language) and Dutch (a non-aspect-oriented language). Specifically, it takes the Mandarin aspect markers 起来-qilai (“ingressive”) and 下去-xiaqu (“continuative”) and collects translation strategies for these markers from a corpus of five Mandarin novels and their Dutch translations. The outcomes are methodological, descriptive and theoretical in nature. Methodologically, it is shown how conceptual templates consisting of temporal boundaries and phases facilitate annotating specific types of viewpoint aspect consistently. Descriptively, the exercise indicates at which linguistic levels viewpoint aspect may be encoded in a non-aspect-oriented language. Theoretically, conducting an HTM analysis with several aspect markers at once makes it possible to quantify (non-)marking of conceptual content; it turns out that the types of viewpoint under study correspond to varying marking frequencies, which may correlate with conceptual complexity.

Parallel Computing for Multi-Objective Train Rescheduling

In railway traffic systems, it is essential to achieve a high punctuality to satisfy the goals of the involved stakeholders. Thus, whenever disturbances occur, it is important to effectively reschedule trains while considering the perspectives of various stakeholders. This typically involves solving a multi-objective train rescheduling problem, which is much more complex than its single-objective counterpart. Solving such a problem in real time for practically relevant problem sizes is computationally challenging. The reason is that the rescheduling solution(s) of interest are dispersed across a large search tree. The tree needs to be navigated fast while pruning off branches leading to undesirable solutions and exploring branches leading to potentially desirable solutions. The use of parallel computing enables such a fast navigation of the tree. This article presents a heuristic parallel algorithm to solve the multi-objective train rescheduling problem. The parallel algorithm combines a depth-first search with simultaneous breadth-wise tree exploration while searching the tree for solutions. An existing parallel algorithm for single-objective train rescheduling has been redesigned, primarily, by (i) pruning based on multiple metrics, and (ii) maintaining a set of upper bounds. The redesign improved the quality of the obtained rescheduling solutions and showed better speedups for several disturbance scenarios.

An approach for heuristic parallel LDTW distance optimization method with bio-inspired strategy

An approach for heuristic parallel LDTW distance optimization method with bio-inspired strategy

UNIFIED PARALLEL ALGORITHM AND PROGRAMMING COMPLEX OF OPTIMAL PLANNING OF NON-UNIFORM FLOWS IN THE NETWORKS

Purpose. The purpose of the article is to develop a universal unified parallel synchronous algorithm for the implementation of tasks for calculation of maximum one- and multicommodity flows, as well as the creation of a software complex that provides the formation of surface graph models of flows and performs optimal planning of non-uniform flows in transport and other networks. Methodology. The paper investigates the possibilities of previously created and comprehensively verified heuristic parallel synchronous algorithm for calculating maximum one- and multicommodity flows in the networks, establishes its potential limitations, and determines additional advanced procedures that transform the algorithm into a universal parallel algorithm. The proposed parallel synchronous algorithm uses a width-first search strategy while simultaneously identifying possible paths of flows through the network with an estimation of their throughput. Herewith the possibility of analyzing several incremental flows across the network in one iteration was studied. Findings. The article proposes a universal unified parallel synchronous algorithm for calculating maximum flows in networks and develops a unified procedure and software package for planning of non-uniform as well as competitive flows in transport and other networks. The developed software complex implements the problems of formation of surface graph models of networks, for which the problem of optimal planning of non-uniform and competitive multicriteria flows in transport networks is solved. Originality. The article develops a new universal unified parallel synchronous algorithm and procedure for the calculation of optimal uniform, multicommodity and competitive flows in transport networks. Practical value. The practical value of the obtained results is determined by the universal capabilities and efficiency of the procedure for planning non-uniform flows in the networks based on the application of a new parallel synchronous algorithm, as well as the developed software complex, which provides the ability to solve the problems of analysis and planning of uniform and multicommodity flows in transport networks, as well as the implementation of calculation tasks of competitive models of transport and information flows formation. The software complex has a built-in editor of interactive network modeling and a toolbar, which provides both creation of new and downloading existing graphs of networks from the modeling libraries, preservation of optimum flows in the network in the form of an image and a text file, output of errors when working with the program.

A Mandarin map for Dutch durativity*

Abstract The linguistic expression of aspectuality poses a challenge for linguistic research of Dutch, because the language does not have a grammaticalized means of expression exclusively for this purpose. Instead, its expression appears to be highly diffuse. This study investigates the expression of one type of aspectuality in Dutch, namely durative aspect, which is highly grammaticalized in Mandarin Chinese. Through the method of parallel text analysis, this feature of Mandarin is employed instrumentally in mapping out the expression of durative aspect in Dutch both quantitatively and qualitatively, in terms of Construction Grammar. Theoretical and methodological considerations are also explored: it is proposed that the present method is best termed heuristic parallel analysis, differentiating it from conceptual parallel approaches; and it is argued that a quantitative overview should be complemented by a qualitative component. Finally, the results – expressional categories notated as (partially) schematic constructions – are compared with existing models, specifically that of the Algemene Nederlandse Spraakkunst (ANS), concluding that the durativity of posture constructions, the perfect, and pluractionality should be integrated into its account.

Parallel Heuristics for Balanced Graph Partitioning Based on Richness of Implicit Knowledge

Balanced graph partitioning (BGP) has a wide range of applications that involve many large-scale distributed data processing problems. However, most of the existing approaches to parallel graph partitioning neglect the problem of the richness of implicit knowledge (RIK) residing in big graph and the knowledge cohesion after graph partitioning. In this paper, we propose a parallel balanced graph partitioning framework called JA-BE-JA-RIK, which improves the original heuristic JA-BE-JA algorithm by evaluating RIK such that parallel BGP can be more efficiently made under the condition of obtaining the good edge-cut value and high knowledge cohesion. We introduce the concept about RIK and further present a quantitative measure to dynamically evaluate the RIK values during parallel BGP. Based on the Hadoop platform, we also implemented both frameworks and JA-BE-JA. The extensive experiments were made for illustrating efficacy of our JA-BE-JA-RIK approach in comparison with the traditional JA-BE-JA algorithm. The experimental results show that our parallel BGP approach can obtain the RIK value as higher as possible within a closer number of edge-cuts in comparison with the traditional JA-BE-JA algorithm.

Highly scalable SFC-based dynamic load balancing and its application to atmospheric modeling

Load balance is one of the major challenges for efficient supercomputing, especially for applications that exhibit workload variations. Various dynamic load balancing and workload partitioning methods have been developed to handle this issue by migrating workload between nodes periodically during the runtime. However, on today’s top HPC systems–and even more so on future exascale systems–runtime performance and scalability of these methods becomes a concern, due to the costs exceeding the benefits of dynamic load balancing. In this work, we focus on methods based on space-filling curves (SFC), a well-established and comparably fast approach for workload partitioning. SFCs reduce the partitioning problem from n dimensions to one dimension. The remaining task, the so-called 1D partitioning problem or chains-on-chains partitioning problem, is to decompose a 1D workload array into consecutive, balanced partitions. While published parallel heuristics for this problem cannot reliably deliver the required workload balance, especially at large scale, exact algorithms are infeasible due to their sequential nature. We therefore propose a hierarchical method that combines a heuristic and an exact algorithm and allows to trade-off between these two approaches. We compare load balance, execution time, application communication, and task migration of the algorithms using real-life workload data from two different applications on two different HPC systems. The hierarchical method provides a significant speed-up compared to exact algorithms and yet achieves nearly the optimal load balance. On a Blue Gene/Q system, it is able to partition 2.6 million tasks for 524288 processes with over 99% of the optimal balance in 23.4 ms only, while a published fast exact algorithm requires 6.4 s. We also provide a comparison to parallel load balancing methods implemented in the Zoltan library and present results from applying our methods to COSMO-SPECS+FD4, a detailed atmospheric simulation model that requires frequent dynamic load balancing to run efficiently at large scale.

Space-Efficient Parallel Construction of Succinct Representations of Suffix Tree Topologies

A compressed suffix tree usually consists of three components: a compressed suffix array, a compressed LCP-array, and a succinct representation of the suffix tree topology. There are parallel algorithms that construct the suffix array and the LCP-array, but none for the third component. In this article, we present parallel algorithms on shared memory architectures that construct the balanced parentheses sequence (BPS), an explicit succinct representation of the suffix tree topology, as well as the enhanced balanced parentheses representation (eBPR), an implicit succinct representation of the suffix tree topology. For both representations, this article presents a sequential construction algorithm (a new one for the BPS), a linear work and O (log n ) time parallel construction algorithm, and a heuristic parallel construction algorithm that works very well in practice. The experimental results show that our methods are well suited for real-world applications.

A parallel heuristics for the single allocation hub location problem

This paper introduces a cooperative parallel heuristic for the uncapacitated single allocation hub location problem. The proposed heuristic consists in combining multiple parallel ILS-RVND local search and Path-Relinking, cooperating through asynchronously exchaging solutions in a shared pool. This method as devised to tackle large scale instances up to 3038 nodes. Generally, papers in the literature solve problems up to 400 nodes. The combination of efficient methods of search allowed the proposed heuristic to explore efficiently the space of search, and outperformed four well known heuristics of the literature for the select instances.

Stability and instability of Ellis and phantom wormholes: Are there ghosts?

It is concluded in the literature that Ellis wormhole is unstable under small perturbations and would decay either to the Schwarzschild black hole or expand away to infinity. While this deterministic conclusion of instability is correct, we show that the Ellis wormhole reduces to Schwarzschild black hole \textit{only} when the Ellis solution parameter $\gamma $ assumes a complex value $-i$. We shall then reexamine stability of Ellis and phantom wormholes from the viewpoint of local and asymptotic observers by using a completely different approach, viz., we adapt Tangherlini's nondeterministic, prequantal statistical simulation about photon motion in the real optical medium to an effective medium reformulation of motions obtained via Hamilton's optical-mechanical analogy in a gravity field. A crucial component of Tangherlini's idea is the observed increase of momentum of the photons entering a real medium. We show that this fact has a heuristic parallel in the effective medium\ version of the Pound-Rebka experiment in gravity. Our conclusion is that there is a non-zero probability that Ellis and phantom wormholes could appear stable or unstable depending on the location of observers and on the values of $\gamma$, leading to the possibility of \textit{ghost wormholes} (like ghost stars). The Schwarzschild horizon, however, would always appear certainly stable ($R=1$, $T=0$) to observers regardless of their location. Phantom wormholes of bounded mass in the extreme limit $a\rightarrow -1$ are also shown to be stable just as the Schwarzschild black hole is. We shall propose a thought experiment showing that our non-deterministic results could be numerically translated into observable deterministic signatures of ghost wormholes.

Parallel heuristics for scalable community detection

Community detection has become a fundamental operation in numerous graph-theoretic applications. It is used to reveal natural divisions that exist within real world networks without imposing prior size or cardinality constraints on the set of communities. Despite its potential for application, there is only limited support for community detection on large-scale parallel computers, largely owing to the irregular and inherently sequential nature of the underlying heuristics. In this paper, we present parallelization heuristics for fast community detection using the Louvain method as the serial template. The Louvain method is an iterative heuristic for modularity optimization. Originally developed by Blondel et al. in 2008, the method has become increasingly popular owing to its ability to detect high modularity community partitions in a fast and memory-efficient manner. However, the method is also inherently sequential, thereby limiting its scalability. Here, we observe certain key properties of this method that present challenges for its parallelization, and consequently propose heuristics that are designed to break the sequential barrier. For evaluation purposes, we implemented our heuristics using OpenMP multithreading, and tested them over real world graphs derived from multiple application domains (e.g., internet, citation, biological). Compared to the serial Louvain implementation, our parallel implementation is able to produce community outputs with a higher modularity for most of the inputs tested, in comparable number or fewer iterations, while providing absolute speedups of up to 16x using 32 threads.

Parallelized user clicks recognition from massive HTTP data based on dependency graph model

With increasingly complex website structure and continuously advancing web technologies, accurate user clicks recognition from massive HTTP data, which is critical for web usage mining, becomes more difficult. In this paper, we propose a dependency graph model to describe the relationships between web requests. Based on this model, we design and implement a heuristic parallel algorithm to distinguish user clicks with the assistance of cloud computing technology. We evaluate the proposed algorithm with real massive data. The size of the dataset collected from a mobile core network is 228.7GB. It covers more than three million users. The experiment results demonstrate that the proposed algorithm can achieve higher accuracy than previous methods.

A novel genetic probability decoding (GPD) algorithm for the FEC code in optical communications

A new genetic probability decoding (GPD) algorithm to be fit for forward error correction (FEC) codes of optical communications, based on the genetic algorithm, is proposed through the characteristic analysis of optical communications. This novel algorithm can further optimize the matched filter's output of demodulator by applying the channel interference probability statistics and taking the advantage of the genetic algorithm's heuristic parallel search capability to restore a more likelihood transmission code. The theoretical performance analysis and the simulation result of the GPD algorithm show the proposed GPD algorithm has a relatively low decoding complexity because it won’t be affected by the number of code symbols, as well as a faster decoding speed and a better decoding correction-error performance. Therefore, the proposed GPD algorithm is a better practical decoding algorithm.

A framework for parallel large-scale global optimization

The paper describes the design and implementation of BNB-Solver, an object-oriented framework for discrete and continuous parallel global optimization. The framework supports exact branch-and-bound algorithms, heuristic methods and hybrid approaches. BNB-Solver provides a support for distributed and shared memory architectures. The implementation for distributed memory machines is based on MPI and thus can run on almost any computational cluster. In order to take advantages of multicore processors we provide a separate multi-threaded implementation for shared memory platforms. We introduce a novel collaborative scheme for combining exact and heuristic search methods that provides the support for sophisticated parallel heuristics and convenient balancing between exact and heuristic methods. In the experimental results section we discuss a nonlinear programming solver and a highly efficient knapsack solver that significantly outperforms existing parallel implementations.

Parallel block tridiagonalization of real symmetric matrices

Two parallel block tridiagonalization algorithms and implementations for dense real symmetric matrices are presented. Block tridiagonalization is a critical pre-processing step for the block tridiagonal divide-and-conquer algorithm for computing eigensystems and is useful for many algorithms desiring the efficiencies of block structure in matrices. For an “effectively” sparse matrix, which frequently results from applications with strong locality properties, a heuristic parallel algorithm is used to transform it into a block tridiagonal matrix such that the eigenvalue errors remain bounded by some prescribed accuracy tolerance. For a dense matrix without any usable structure, orthogonal transformations are used to reduce it to block tridiagonal form using mostly level 3 BLAS operations. Numerical experiments show that block tridiagonal structure obtained from this algorithm directly affects the computational complexity of the parallel block tridiagonal divide-and-conquer eigensolver. Reduction to block tridiagonal form provides significantly lower execution times, as well as memory traffic and communication cost, over the traditional reduction to tridiagonal form for eigensystem computations.

Comparative study of serial and parallel heuristics used to design combinational logic circuits

In this article, we perform a comparative study of different heuristics used to design combinational logic circuits. This study mainly emphasizes the use of local search hybridized with a genetic algorithm (GA) and the impact of introducing parallelism. Our results indicate that a hybridization of a GA with a local search algorithm (simulated annealing) is beneficial and that the use of parallelism not only introduces a speedup in the algorithms compared (as expected) but also allows us to improve the quality of the solutions found.

Parallel LAN/WAN heuristics for optimization

We present in this work a wide spectrum of results on analyzing the behavior of parallel heuristics (both pure and hybrid) for solving optimization problems. We focus on several evolutionary algorithms as well as on simulated annealing. Our goal is to offer a first study on the possible changes in the search mechanics that the algorithms suffer when shifting from a LAN network to a WAN environment. We will address six optimization tasks of considerable complexity. The results show that, despite their expected slower execution time, the WAN versions of our algorithms consistently solve the problems. We report also some interesting results in which WAN algorithms outperform LAN ones. Those results are further extended to analyze the behavior of the heuristics in WAN with a larger number of processors and different connectivities.

Parallel LAN/WAN heuristics for optimization

We present in this work a wide spectrum of results on analyzing the behavior of parallel heuristics (both pure and hybrid) for solving optimization problems. We focus on several evolutionary algorithms as well as on simulated annealing. Our goal is to offer a first study on the possible changes in the search mechanics that the algorithms suffer when shifting from a LAN network to a WAN environment. We will address six optimization tasks of considerable complexity. The results show that, despite their expected slower execution time, the WAN versions of our algorithms consistently solve the problems. We report also some interesting results in which WAN algorithms outperform LAN ones. Those results are further extended to analyze the behavior of the heuristics in WAN with a larger number of processors and different connectivities.

On-line parallel heuristics, processor scheduling and robot searching under the competitive framework

In this paper we investigate parallel searches on m concurrent rays for a point target t located at some unknown distance along one of the rays. A group of p agents or robots moving at unit speed searches for t. The search succeeds when an agent reaches the point t. Given a strategy S the competitive ratio is the ratio of the time needed by the agents to find t using S and the time needed if the location of t had been known in advance. We provide a strategy with competitive ratio of 1+2( m/ p−1)( m/( m− p)) m/ p and prove that this is optimal. This problem has applications in multiple heuristic searches in AI as well as robot motion planning. The case p = 1 is known in the literature as the cow path problem.

COMBINING SPECTRAL SEQUENCING AND PARALLEL SIMULATED ANNEALING FOR THE MINLA PROBLEM

In this paper we present and analyze new sequential and parallel heuristics to approximate the Minimum Linear Arrangement problem (MinLA). The heuristics consist in obtaining a first global solution using Spectral Sequencing and improving it locally through Simulated Annealing. In order to accelerate the annealing process, we present a special neighborhood distribution that tends to favor moves with high probability to be accepted. We show how to make use of this neighborhood to parallelize the Metropolis stage on distributed memory machines by mapping partitions of the input graph to processors and performing moves concurrently. The paper reports the results obtained with this new heuristic when applied to a set of large graphs, including graphs arising from finite elements methods and graphs arising from VLSI applications. Compared to other heuristics, the measurements obtained show that the new heuristic improves the solution quality, decreases the running time and offers an excellent speedup when ran on a commodity network made of nine personal computers.