Multiprocessor Computer Systems Research Articles

A numerical method for ergodic optimal control of switching diffusions with reflection

The ergodic or long run average cost control problem for diffusions is one of the classical problems of stochastic control that still eludes a completely satisfactory treatment. This is certainly true for the setting in which the systems to be controlled is modeled by the solution of a switching stochastic differential equation with reflection (SSDER). In this paper, we advance in this rather difficult problem by setting forth preliminary results for the unidimensional case. Besides carving out a numerical method, our treatment of the ergodic control in this scenario straddles issues of existence and uniqueness of solution of the SSDER and a verification theorem for the associated HJB equation. We conclude by illustrating the effectiveness of the method considering the control of energy consumption in a large parallel processing computer system composed of one queue and several processing stations.

TASK SCHEDULING OPTIMISATION OF DISTRIBUTED REAL-TIME COMPUTING SYSTEMS.

Distributed computing structures for production and special purposes represent the resources of soft or hard real-time systems. The problem of task planning is to determine the optimal distribution according to the generalized criterion of system utility. The article discusses the methods of building a schedule, based on the theory of planning. It is shown that the most effective step in this process is the optimisation of the activity of the enterprises or organizations at all levels - economic, technical, informational, etc., under the conditions of natural limitations on time resources. Since the optimisation of schedule planning occupies a fundamentally important place in the process of organizing the effective operation of a distributed multiprocessor computing system, the possibilities of using this theory in creating an optimal schedule based on the theory of queues with ordinary and marked applications are considered. The theoretical basis of the planning optimisation problem is a multistage system with M storage units and a set of N´M services. In order to organize the schedule optimality criteria to ensure ease of description, storage and software implementation, a conditional division of criteria into geographic, technical or transit categories with a description of the corresponding priority value is proposed. Taking into account these components, an expression for the average waiting time in the queue for a marked demand is derived. The scheme of the conceptual approach to the construction of a multi-core computer with the distribution of periodic and sporadic tasks is presented. The scheme of the real-time system (RTS) in hardware and software implementation is also presented. Background streams in RTS are activated by RT operating system (RT OS) commands and are embedded in primary streams. The above demonstrates the versatility of the proposed approach to scheduling a multiprocessor computing structure and its ability to meet the user's work requirements in real time.

An algorithm for fast multiplication of elements in 2-groups based on the Zhegalkin polynomials

Network design for a multiprocessor computing system or data center is an important problem where the search for graph models that have attractive topological properties and allow the use of efficient routing algorithms is carried out. Cayley graphs have the indicated properties, in particular such as high symmetry, hierarchical structure, recursive design, high connectivity and fault tolerance. The definition of the Cayley graph implies that the vertices of the graph are elements of some algebraic group. Selecting a group and its generating elements allows us to obtain a graph that meets the necessary requirements for diameter, degree of vertices, number of nodes, etc. A large number of scientific articles and monographs are devoted to solving this problem. The goal of this work is to create an algorithm for fast multiplication of elements in finite 2-groups whose exponent is 2n. The first section of the article provides a theoretical justification for the algorithm for fast multiplication in finite 2-groups. It is shown that elements of these groups can be represented in the form of bit strings, and their multiplication is carried out based on the Zhegalkin polynomials. The second section presents the pseudocode of the algorithm on the basis of which the Zhegalkin polynomials are calculated. The third section demonstrates an example of obtaining the Zhegalkin polynomials for a two-generated group of exponent 4. In conclusion, the prospects for using the algorithm on the real hardware are discussed.

Features of Creating Parallel Programs for the Parallel Dataflow Computing System "Buran"

The use of modern multi-core and multi-processor computer systems for actual tasks is not effective enough, even taking into account the use of parallel programming technologies. The solution to the problem of efficient loading of computing resources can be the transition to computing models and architectures that are inherently parallel. One of such architectures is the Parallel Dataflow Computing System (PDCS) "Buran", which implements a dataflow computing model with a dynamically formed context. A feature of the dataflow computing model is the activation of computations by data readiness, which affects both the architecture of the computing system and the creation of programs for such systems. Differences between imperative and dataflow programming paradigms are also reflected in the route of creating a program, especially its parallel implementation. The route of creating a dataflow parallel program differs markedly from the traditional one. Already at the first stage, a parallel algorithm is created and implemented (including the algorithm for generating initial data). Next, this algorithm is debugged when it is executed on an emulator or model of the system with one computing core. After that, the selection and configuration of function of computation distribution is performed, the program is executed (without changing its code) on the emulator or model of the system with several computing cores, and, finally, the program is debugged in multi-core mode. These stages of the route differ from similar stages of the traditional route, both in form and in essence. Unlike traditional parallel, and even more so sequential programs, it can be said that a dataflow program in equal parts consists of a program code that implements a task, an algorithm for generating initial data, and a function of computation distribution. This thesis is demonstrated by the example of solving the problem of finding sum of array elements, where the difference between the implementations is in the algorithm for generating initial data, which radically affects the nature of the dataflow program passing. Careful attention to each of the parts of the dataflow program is the key to the correct and efficient solution of problems on the PDCS, which provides support to the programmer at the hardware level.

Solving of the Biological Kinetics Problem on a Heterogeneous Multiprocessor Computer System

Solving of the Biological Kinetics Problem on a Heterogeneous Multiprocessor Computer System

MODULE HIGH-EFFICIENCY MULTIPROCESSOR SYSTEM WITH MULTIDIMENSIONAL AGGREGATING OF CHANNELS OF NETWORK INTERFACE

Context. In modern terms problem of constructing of the multiprocessor systems the special value acquires the base of standard popular technologies and components. It is caused by that such systems became popular and cheap vehicle platforms for highperformance calculations. In addition, practice pulls out problems complete decision of which in most cases possibly only due to application of high-performance calculations. Consequently, a theme of constructing of the cluster multiprocessor systems for today is actual, interesting and is on the stage of the active development. At the same time, the new high-quality stage of development of the multiprocessor cluster systems lies in area of the use of new modern network technologies. Presently the problem of choice and analysis of network technologies for the module multiprocessor cluster systems did not get due development, as well as problem of reorganization of structure ofnetwork interfaceby aggregating of channels of network interface.
 Objective. An aim is in-process put improvement of structure and increase of the productivity of the multiprocessor computer system by the multidimensional aggregating of channels of network interface, adapted to the decision of tasks of the investigated class.
 Method. The task of increase of efficiency of the module multiprocessor computer system is decided due to multidimensional aggregating of channels of network interface. Offered approach allowed not only to promote efficiency of parallelization but also substantially to decrease time of calculations. Such results succeeded to be attained due to diminishing to time of border exchange of data between the calculable knots of the cluster system.
 Results. A feature offered approach is that he allowed to realize a direct exchange data between main memory of knots of the multiprocessor system, that promotes the fast-acting of calculations and provides high-speed access to memory of her slave -nodes. Thus during an exchange by data between the knots of the system the system CPU gets unloaded and loading of channel which passes between the knots of the computer system goes down, that assists diminishing of time of border exchange of data between the calculable knots of the system.
 Conclusions. The results of the conducted experiments showed that the worked out multiprocessor system was used for creation of new technological processes. So, she is used in a fluidizer intensification of the сфероидизируещего annealing of long-length steelwork. Directly the technological process of heat treatment of metal acquires such advantages, as a high yield, substantial mionectic energy consumption and allows to carry out control of technological parameters in the modes of unisothermal treatment of metal.

RESEARCH OF MULTICHANNEL MODES OF THE NETWORK INTERFACE OF MODULAR COMPUTING SYSTEMS

This paper considers the so-called "blade" server solutions of multiprocessor computing systems, where several same-type mother modules are installed in one enclosure. The main feature of the clustered system, which is considered in this paper, is that the data interchange among computing nodes is carried out in a separate network, which operates at the channel level using channel bonding mechanisms. This provided an increase in the speed of data interchange and reduced the load of the channel that connects the nodes of the cluster. Further reseraches were aimed at implementing a procedure for increasing the efficiency of parallelization by introducing of multichannel modes of the network interface of modular computing systems. The conducted studies have created the prerequisites for a quantitative assessment of the effectiveness of a multiprocessor computing system in the implementation of a multi-channel operation mode of a cluster network.

Performance evaluations research of multiprocessor system in the problem of heat treatment of metal products

The paper aims to research performance evaluations of a multiprocessor system in the problem of metal heat treatment. The research aims at the performance evaluations of a multiprocessor computer system. That reveals the problem of matching the computing capabilities of multiprocessor system processors with this system network interface. On the example of solving the problem of metal products heat treatment, analytical relations are derived to determine the optimal number of nodes of the cluster system according to the selected processors. The values of the consistency coefficient of the selected processors' capabilities, the network interface, and the size of the computing domain are derived. Estimates of cluster system performance at solving the metal heat treatment problem for various processors’ classes are defined.

Параллельное решение краевых задач с помощью технологии OpenMP

The paper introduces the results of the theoretical and experimental analysis of the Robust Multigrid Technique (RMT), a computational algorithm designed for the numerical solution of (initial-)boundary value problems for the equations of mathematical physics in black-box software. The purpose of the study was to develop robust, efficient and large-scale granulated algorithm for solving a wide class of nonlinear applied problems. The paper describes the algebraic and geometric parallelisms of the RMT and the multigrid cycle for solving nonlinear problems. The OpenMP technology was used to implement the parallel RMT. Computational experiments related to the solution of the Dirichlet problem for the Poisson equation in the unit cube were performed on a personal computer using 3, 9 and 27 threads (p = 3, 9, 27) and on a multiprocessor computer system with shared memory using 27 threads (p = 27). The highest achieved efficiency of the parallel RMT is E ≈ 0.95 at N > 106 and p = 3 and E ≈ 0.80 at N > 107 and p = 27. Findings of the research reveal that the determining factor affecting the efficiency of the parallel RMT is the limited memory performance of multicore computing systems. The complexity of the sequential iteration of the V-cycle and the parallel iteration of the RMT was theoretically analyzed. The study shows that the parallel iteration of the RMT, implemented on 27 threads, will be executed several times faster than the sequential iteration of the V-loop

Aggregation arrangement features of network interface channels in multiprocessor computing systems

The paper identifies ways to increase the multiprocessor computing system performance by reorganizing the architecture of its network interface. It is shown that the computational parallelization performance significantly depends on many factors, the most essential of which is the data transfer between the boundary nodes of a multiprocessor system, which is the algorithm's slowest part and can significantly reduce the effect of increasing the number of processors. Hence, it was established that improving the multiprocessor systems performance by reorganizing the network interface structure is relevant interesting nowadays, and its study is at the active development stage. The research aims at the aggregation arrangement of network interface channels in multiprocessor computing systems. It is shown that the main channel aggregation mode advantage is that the data interchange speed is significantly increased, as well as the reliability of the cluster system.

Simulation modeling of a computer system multithreaded architecture using AnyLogic

The simulation is the most effective way to investigate information processing in computer systems. Computer system simulation is advantageous due to the fact, that such class of systems are well formalized in the form of queuing systems. Any computer system can be considered in terms of queuing system theory as an interconnected set of requests for service, system re-sources, queues to resources, and rules of service. The problem with the study of computer systems is that the existing simulation software tools have been developed as universal tools for the study of general-purpose systems. There are no specialized libraries or separate modeling tools for the study of computer systems. Therefore, modeling computer systems based on the use of standard libraries of such a modern modeling tool as AnyLogic, and the possible creation of elements of a specialized library is of great importance. The objective of the paper is to model multithreaded computing in a multiprocessor computer system using AnyLogic software. The designed computer system diagram enables us to have a deep insight into all details of information processing, and the obtained characteris-tics of the computer system, such as CPU usage coefficients, queue dynamics, distribution of thread execution time in the system, etc., allow us to determine the most effective configuration of the system, the parameters of its elements and operation modes.

МЕТОД ОРГАНИЗАЦИИ ДИСКРЕТНО-СОБЫТИЙНЫХ ВЫЧИСЛЕНИЙ ДЛЯ ОБРАБОТКИ БОЛЬШИХ РАЗРЕЖЕННЫХ НЕСТРУКТУРИРОВАННЫХ МАТРИЦ НА РВС

Increasing models complexity objects and processes study, in different sphere of science andtechnology, set up plenty issues to necessary to use high-performance computing systems. Arraysmatrix processing by cluster multiprocessor computing systems in conjunction special methodsaimed at organizing parallel computations, basically obtain computing performance system isquite high. However, that computational efficiency is not observed for all types of matrices. Matrixstructure be in a position contain large amount of insignificant elements, large dimension andunstructured portrait. Calculation execute for described kind of matrices on cluster multiprocessorcomputing system couldn't achieve close peak performance. Considering that processing methodsleave out the complex structure of the matrix being processed. As a result, the performance of thesystem is significantly reduced. The development of cluster MCS methods doesn't allow for fullensure high performance for class of problems processing of large sparse unstructured matrices.Rigid architecture of processor commutation net doesn’t take into account the peculiarities of suchmatrices, and lead to non-uniformity loading processor. To achieve performance close the peakfor tasks large sparse unstructured matrices processing necessary to use reconfigurable computingsystems. RCS architecture allows adapting computation structure to the problem solved. Thismakes it possible to organize pipeline processing, such a way that computational resource RCSused only for informational significant operations. In addition using generally accepted methodsfor structural organization of high-performance computing for RCS, it is necessary to develop aformat for storing and transferring large sparse unstructured matrices, to determine the principlesof constructing basic matrix macro-operations and the possibility of organizing composite discrete-event matrix functions for solving applied problems. Сconsequently method founding laidallows organizing computations operands, which are large sparse unstructured matrices. Theapplication this method for organizing computations can significantly increase productivity, andprovide an increase in the efficiency of such a system.

A software package for solving grid equations in areas with geometry "stretched" along one of the spatial directions

A method for solving grid equations in areas with geometry "stretched" along one of the spatial directions is proposed. Method proposed for model includes pollutants whose concentration in the Azov Sea, according to the analysis of scientific publications and environmental databases, exceeds the maximum permissible concentration (MPC). The mechanism of the preconditioner formation is described. The estimation of the minimum and maximum eigenvalues is performed. Using object-oriented analysis and design, a class library has been implemented to solve the problem of impurity propagation in a shallow reservoir. The architecture of an information system to support scientific research capable of functioning in conditions of using heterogeneous computing environments is described. The system is based on the requirement of the maximum possible use of free software in order to minimize capital and operational costs. The system uses classes that allow you to read and write information about the geometry of the object under study and the parameters of the calculated grid. Numerical experiments were carried out using the developed software package, including the proposed mathematical model, focused on the multiprocessor computing system (MCS). The dependences of the SLAE solution time on the number of diagonals and the order of the matrix are obtained. The number of iterations for solving grid equations has been experimentally determined depending on the ratio of the number of nodes in spatial coordinates.

Optimization of the amount of transmitted data in parallel algorithms for iterative methods with a triangular preconditioner

Software has been developed in the C++ programming language using the MPI parallel programming technology, designed for mathematical modeling of the transport of substances in coastal systems. When calculating the dynamics of the spread of a pollutant, the decomposition of the computational domain was carried out to organize the computational process on a multiprocessor computer system K-60 in KIAM RAS. To solve the system of grid equations obtained as a result of the approximation of the problem, iterative methods were used, with a triangular preconditioner.

Information security models of real-time multiprocessor computing systems

Information security models of real-time multiprocessor computing systems

Evaluation of the reliability of special software for real-time multiprocessor computing systems

Evaluation of the reliability of special software for real-time multiprocessor computing systems

A Linguistic Study of Speech Comprehension and Production in Aphasic Speakers

Distributed memory is a term used in computer science to describe a multiprocessor computer system in which each processor has its own private memory. Computational jobs can only work with local data, so if you need remote data, you'll have to communicate with one or more remote processors. Parallel and distributed computing are frequently used together. Distributed parallel computing employs many computing devices to process tasks in parallel, whereas parallel computing on a single computer uses multiple processors to execute tasks in parallel. Distributed systems are designed separately from the core network. There are different kinds of distributed systems such as peer-to-peer (P2P) networks, groups, grids, distributed storage systems. The multicore processor can be classified into two types: homogeneous and heterogeneous. This paper reviews the impact of the distributed-memory parallel processing approach on performance-enhancing of multicomputer-multicore systems. Also, number of methods have been introduced which used in distributed-memory systems and discuss which method is the best and enhance multicore performance in distributed systems. The best methods were those which used an operating system named gun/Linux 4.8.0-36, intel Xeon 2.5, python programming language.

Organization of parallel-pipeline calculations for modeling the pollutant distribution process in a reservoir

One of the most acute problems for today is the water pollution. For rapid decision in emergency situations, it is necessary to develop effective software and algorithmic tools that allow us to make accurate forecasts of the environmental situation changing of coastal systems. Water pollution of the Azov and Black Seas by storm drains and human waste products leads to an increase of toxic substances concentrations that significantly exceed the maximum permissible values. The pollution transport problem is solved on the basis of the Navier-Stokes and the diffusion-convection-reaction equations. As a result of discretization of the continuous problem of transport of pollutants using the finite-difference approach for a rectangular grid, we obtain a system of linear algebraic equations (SLAE) of large dimension, which require significant time costs. To increase the efficiency of calculations (to reduce the time) on a multiprocessor computer system (MCS), there is a need to develop effective parallel algorithms for solving SLAE. The decomposition method for a two-dimensional computational domain is proposed in this paper, which allows organizing a parallel-pipeline process of calculations as follows: at each stage of calculations, each processor core simultaneously processes fragments of the computational domain that are offset from each other. This process is described in the form of a graph, in which each node corresponds to fragments of the computational domain, and the edges – a sign of the adjacency of fragments.

Parallel algorithms for solving diffusion-convection problems on a multiprocessor computer system using hybrid MPI / OpenMP technology

The paper deals with the mathematical models, algorithms and software for mathematical modeling of coastal systems’ water pollution spreading dynamics under various unfavorable phenomena of natural and artificial genesis, developed for high-performance cluster systems. Methods for partitioning the computational domain for solving diffusion-convection problems have been developed, which allow for efficient parallelization of a computationally complex modeling problem, taking into account the architecture of the multiprocessor system used. The developed mathematical models are based on high-precision models of hydrophysics and hydrobiology and take into account the peculiarities of water systems in the south of the Rostov region, as well as factors of hydrobiological dynamics such as microturbulent diffusion and advective transport in various directions, mechanisms of primary and secondary pollution of coastal systems, taking into account currents. The paper presents algorithms for solving a simulated problem based on MPI parallelization technology, as well as based on mixed MPI + OpenMP technology. Numerical experiments have been carried out and the two technologies efficiency comparison has been made in the conditions of computing cluster used.

Real-time simulation of accidental passive transport of radioactive pollutant from a proposed nuclear power plant

Power plant’s site selection is a complex task and involves through analyses of multi-disciplinary processes which are interlinked with each other. The site selection for nuclear power plants additionally requires an assessment of radiation doses to the environment and public during normal operation and in the case of an accident. This demands the problem of radioactive particles’ dispersion in atmosphere to be analysed in real time for a comprehensive set of radioactive release scenarios in prevailing meteorological conditions in the plant surroundings. In this study, a local scale atmospheric dispersion problem, considering a hypothetical accidental release (1 Bq s−1 of I-131) from a nuclear power plant is simulated with a combination of weather forecasting and particle dispersion codes on a multiprocessor computer system. The meteorological parameters are predicted with a weather research and forecasting (WRF) model and used in Lagrangian particle dispersion model based code FLEXPART to calculate the trajectory of released particles, and thereby, the estimation of spatial I-131 dose distribution. The concentration of particles and radiation doses were calculated for release heights of 10, 57, and 107 m and found in a reasonable agreement with the observed data and better than an earlier investigation done with regional atmospheric modelling system (RAMS) code. A comparison between the results of WRF and RAMS for various meteorological parameters revealed that better space–time predictions of wind speeds and directions by WRF had a profound effect on tracing the trajectories of particles and thereby the spatial dose distribution. The particles followed the changes in wind direction predicted by WRF that were known to prevail in the region.