All issues

We consider an application of the Message Passing Interface (MPI) technology for parallelization of the program code which solves equation of the linear elasticity theory. The solution of this equation describes the propagation of elastic waves in demormable rigid bodies. The solution of such direct problem of seismic wave propagation is of interest in seismics and geophysics. Our implementation of solver uses grid-characteristic method to make simulations. We consider technique to reduce time of communication between MPI processes during the simulation. This is important when it is necessary to conduct modeling in complex problem formulations, and still maintain the high level of parallelism effectiveness, even when thousands of processes are used. A solution of the problem of effective communication is extremely important when several computational grids with arbirtrary geometry of contacts between them are used in the calculation. The complexity of this task increases if an independent distribution of the grid nodes between processes is allowed. In this paper, a generalized approach is developed for processing contact conditions in terms of nodes reinterpolation from a given section of one grid to a certain area of the second grid. An efficient way of parallelization and establishing effective interprocess communications is proposed. For provided example problems we provide wave fileds and seismograms for both 2D and 3D formulations. It is shown that the algorithm can be realized both on Cartesian and on structured (curvilinear) computational grids. The considered statements demonstrate the possibility of carrying out calculations taking into account the surface topographies and curvilinear geometry of curvilinear contacts between the geological layers. Application of curvilinear grids allows to obtain more accurate results than when calculating only using Cartesian grids. The resulting parallelization efficiency is almost 100% up to 4096 processes (we used 128 processes as a basis to find efficiency). With number of processes larger than 4096, an expected gradual decrease in efficiency is observed. The rate of decline is not great, so at 16384 processes the parallelization efficiency remains at 80%.

А new cloud center of parallel computing is to be created in the Laboratory of Information Technologies (LIT) of the Joint Institute for Nuclear Research JINR) what is expected to improve significantly the efficiency of numerical calculations and expedite the receipt of new physically meaningful results due to the more rational use of computing resources. To optimize a scheme of parallel computations at a cloud environment it is necessary to test this scheme for various combinations of equipment parameters (processor speed and numbers, throughput оf а communication network etc). As a test problem, the parallel MPI algorithm for calculations of the long Josephson junctions (LDJ) is chosen. Problems of evaluating the impact of abovementioned factors of computing mean on the computing speed of the test problem are solved by simulation with the simulation program SyMSim developed in LIT.

The simulation of the LDJ calculations in the cloud environment enable users without a series of test to find the optimal number of CPUs with a certain type of network run the calculations in a real computer environment. This can save significant computational time in countable resources. The main parameters of the model were obtained from the results of the computational experiment conducted on a special cloud-based testbed. Computational experiments showed that the pure computation time decreases in inverse proportion to the number of processors, but depends significantly on network bandwidth. Comparison of results obtained empirically with the results of simulation showed that the simulation model correctly simulates the parallel calculations performed using the MPI-technology. Besides it confirms our recommendation: for fast calculations of this type it is needed to increase both, — the number of CPUs and the network throughput at the same time. The simulation results allow also to invent an empirical analytical formula expressing the dependence of calculation time by the number of processors for a fixed system configuration. The obtained formula can be applied to other similar studies, but requires additional tests to determine the values of variables.

A hybrid cluster implies the use of computational devices with radically different architectures. Usually, these are conventional CPU architecture (e.g. x86_64) and GPU architecture (e. g. NVIDIA CUDA). Creating and exploiting such a cluster requires some experience: in order to harness all computational power of the described system and get substantial speedup for computational tasks many factors should be taken into account. These factors consist of hardware characteristics (e.g. network infrastructure, a type of data storage, GPU architecture) as well as software stack (e.g. MPI implementation, GPGPU libraries). So, in order to run scientific applications GPU capabilities, software features, task size and other factors should be considered.

This report discusses opportunities and problems of hybrid computations. Some statistics from tests programs and applications runs will be demonstrated. The main focus of interest is open source applications (e. g. OpenFOAM) that support GPGPU (with some parts rewritten to use GPGPU directly or by replacing libraries).

There are several approaches to organize heterogeneous computations for different GPU architectures out of which CUDA library and OpenCL framework are compared. CUDA library is becoming quite typical for hybrid systems with NVIDIA cards, but OpenCL offers portability opportunities which can be a determinant factor when choosing framework for development. We also put emphasis on multi-GPU systems that are often used to build hybrid clusters. Calculations were performed on a hybrid cluster of SPbU computing center.

One of problems in developing the gas condensate fields lies on the fact that the condensed hydrocarbons in the gas-bearing layer can get stuck in the pores of the formation and hence cannot be extracted. In this regard, research is underway to increase the recoverability of hydrocarbons in such fields. This research includes a wide range of studies on mathematical simulations of the passage of gas condensate mixtures through a porous medium under various conditions.

In the present work, within the classical approach based on the Darcy law and the law of continuity of flows, we formulate an initial-boundary value problem for a system of nonlinear differential equations that describes a depletion of a multicomponent gas-condensate mixture in porous reservoir. A computational scheme is developed on the basis of the finite-difference approximation and the fourth order Runge .Kutta method. The scheme can be used for simulations both in the spatially one-dimensional case, corresponding to the conditions of the laboratory experiment, and in the two-dimensional case, when it comes to modeling a flat gas-bearing formation with circular symmetry.

The computer implementation is based on the combination of C++ and Maple tools, using the MPI parallel programming technique to speed up the calculations. The calculations were performed on the HybriLIT cluster of the Multifunctional Information and Computing Complex of the Laboratory of Information Technologies of the Joint Institute for Nuclear Research.

Numerical results are compared with the experimental data on the pressure dependence of output of a ninecomponent hydrocarbon mixture obtained at a laboratory facility (VNIIGAZ, Ukhta). The calculations were performed for two types of porous filler in the laboratory model of the formation: terrigenous filler at 25 .„R and carbonate one at 60 .„R. It is shown that the approach developed ensures an agreement of the numerical results with experimental data. By fitting of numerical results to experimental data on the depletion of the laboratory reservoir, we obtained the values of the parameters that determine the inter-phase transition coefficient for the simulated system. Using the same parameters, a computer simulation of the depletion of a thin gas-bearing layer in the circular symmetry approximation was carried out.

This paper targets programmers and developers interested in utilizing parallel programming techniques to enhance application performance. The Oracle Solaris Studio software provides state-of-the-art optimizing and parallelizing compilers for C, C++ and Fortran, an advanced debugger, and optimized mathematical and performance libraries. Also included are an extremely powerful performance analysis tool for profiling serial and parallel applications, a thread analysis tool to detect data races and deadlock in memory parallel programs, and an Integrated Development Environment (IDE). The Oracle Message Passing Toolkit software provides the high-performance MPI libraries and associated run-time environment needed for message passing applications that can run on a single system or across multiple compute systems connected with high performance networking, including Gigabit Ethernet, 10 Gigabit Ethernet, InfiniBand and Myrinet. Examples of OpenMP and MPI are provided throughout the paper, including their usage via the Oracle Solaris Studio and Oracle Message Passing Toolkit products for development and deployment of both serial and parallel applications on SPARC and x86/x64 based systems. Throughout this paper it is demonstrated how to develop and deploy an application parallelized with OpenMP and/or MPI.

The paper gives a detailed description of the developed methods for simulating the turbulent flow around a helicopter rotor and calculating its aerodynamic characteristics. The system of Reynolds-averaged Navier – Stokes equations for a viscous compressible gas closed by the Spalart –Allmaras turbulence model is used as the basic mathematical model. The model is formulated in a non-inertial rotating coordinate system associated with a rotor. To set the boundary conditions on the surface of the rotor, wall functions are used.

The numerical solution of the resulting system of differential equations is carried out on mixed-element unstructured grids including prismatic layers near the surface of a streamlined body.The numerical method is based on the original vertex-centered finite-volume EBR schemes. A feature of these schemes is their higher accuracy which is achieved through the use of edge-based reconstruction of variables on extended quasi-onedimensional stencils, and a moderate computational cost which allows for serial computations. The methods of Roe and Lax – Friedrichs are used as approximate Riemann solvers. The Roe method is corrected in the case of low Mach flows. When dealing with discontinuities or solutions with large gradients, a quasi-one-dimensional WENO scheme or local switching to a quasi-one-dimensional TVD-type reconstruction is used. The time integration is carried out according to the implicit three-layer second-order scheme with Newton linearization of the system of difference equations. To solve the system of linear equations, the stabilized conjugate gradient method is used.

The numerical methods are implemented as a part of the in-house code NOISEtte according to the two-level MPI–OpenMP parallel model, which allows high-performance computations on meshes consisting of hundreds of millions of nodes, while involving hundreds of thousands of CPU cores of modern supercomputers.

Based on the results of numerical simulation, the aerodynamic characteristics of the helicopter rotor are calculated, namely, trust, torque and their dimensionless coefficients.

Validation of the developed technique is carried out by simulating the turbulent flow around the Caradonna – Tung two-blade rotor and the KNRTU-KAI four-blade model rotor in hover mode mode, tail rotor in duct, and rigid main rotor in oblique flow. The numerical results are compared with the available experimental data.

This work is devoted to molecular dynamic modeling of the thermal impact processes on the metal sample consisting of nickel atoms. For the solution of this problem, a continuous mathematical model on the basis of the classical Newton mechanics equations has been used; a numerical method based on the Verlet scheme has been chosen; a parallel algorithm has been offered, and its realization within the MPI and OpenMP technologies has been executed. By means of the developed parallel program, the investigation of thermodynamic equilibrium of nickel atoms’ system under the conditions of heating a sample to desired temperature has been executed. In numerical experiments both optimum parameters of calculation procedure and physical parameters of analyzed process have been defined. The obtained numerical results are well corresponding to known theoretical and experimental data.

In this paper, we introduce the concept of non-uniform cellular genetic algorithm, in which a number of parameters that affect the operation of genetic operators is dependent on the location of the cells of a given cellular space. The results of numerical comparison of non-uniform cellular genetic algorithms with the standard genetic algorithms, showing the advantages of the proposed approach while minimizing multimodal functions with a large number of local extrema, are presented. The coarse-grained parallel implementation of the non-uniform algorithms using the technology of MPI is considered.

Course “Natural models of parallel computing”, given for senior students of the Faculty of Computational Mathematics and Cybernetics, Moscow State University, is devoted to the issues of supercomputer implementation of natural computational models and is, in fact, an introduction to the theory of natural computing, a relatively new branch of science, formed at the intersection of mathematics, computer science and natural sciences (especially biology). Topics of the natural computing include both already classic subjects such as cellular automata, and relatively new, introduced in the last 10–20 years, such as swarm intelligence. Despite its biological origin, all these models are widely applied in the fields related to computer data processing. Research in the field of natural computing is closely related to issues and technology of parallel computing. Presentation of theoretical material of the course is accompanied by a consideration of the possible schemes for parallel computing, in the practical part of the course it is supposed to perform by the students a software implementation using MPI technology and numerical experiments to investigate the effectiveness of the chosen schemes of parallel computing.