Alexander V. Bogdanov

Constructing Virtual Private Supercomputer Using Virtualization and Cloud Technologies

One of efficient ways to conduct experiments on HPC platforms is to create custom virtual computing environments tailored to the requirements of users and their applications. In this paper we investigate virtual private supercomputer, an approach based on virtualization, data consolidation, and cloud technologies. Virtualization is used to abstract applications from underlying hardware and operating system while data consolidation is applied to store data in a distributed storage system. Both virtualization and data consolidation layers offer APIs for distributed computations and data processing. Combined, these APIs shift the focus from supercomputing technologies to problems being solved. Based on these concepts, we propose an approach to construct virtual clusters with help of cloud computing technologies to be used as on-demand private supercomputers and evaluate performance of this solution.

Regular and chaotic quantum dynamics in atom-diatom reactive collisions

A new microirreversible 3D theory of quantum multichannel scattering in the three-body system is developed. The quantum approach is constructed on the generating trajectory tubes which allow taking into account influence of classical nonintegrability of the dynamical quantum system. When the volume of classical chaos in phase space is larger than the quantum cell in the corresponding quantum system, quantum chaos is generated. The probability of quantum transitions is constructed for this case. The collinear collision of the Li + (FH) → (LiF) + H system is used for numerical illustration of a system generating quantum (wave) chaos.

Simulation of Space Charge Dynamics in High Intensive Beams on Hybrid Systems

The method for construction of analytical expressions for electric and magnetic fields for some set of the distributions of the charge density is described. These expressions are used for symbolic computation of the corresponding electric and magnetic fields generated by the beam during the evolution in accelerators. Here we focus on the use of the matrix form for Lie algebraic methods for calculating the beam dynamics in the presence of self-field of the beam. In particular, the corresponding calculations are based on the predictor-corrector method. The suggested approach allows not only to carry out numerical experiments, but also to provide accurate analytical analysis of the impact of different effects with the use of ready-made modules in accordance with the concept of Virtual Accelerator Laboratory. To simulate the large number of particle distributed resources for computations are used. Pros and cons of using described approach on hybrid systems are discussed. In particular, the investigation of overall performance of the predictor-corrector method is made.

Building a Virtual Cluster for 3D Graphics Applications

This paper discusses a possible approach to distributed visualization and rendering system infrastructure organization, based on Linux environment with the usage of virtualization technologies. Particular attention is paid to the minutiae, which may be encountered due to the environment setup and exploitation processes, and may affect system performance and usability. Some applications and development tools are studied, as they can provide a rapid onset of computing resources exploration.

Virtual Accelerator: Distributed Environment for Modeling Beam Accelerator Control System

Simulation of beam dynamics is an important step needed to aid the design and configuration of particle beam accelerators. A number of methods and software packages have been developed to address modeling in accelerator physics. However, the results of simulations often need to be validated by simultaneous usage of several packages for solving similar problem and comparing the results. In addition, different packages can be used together, each solving a single step of a problem and forming a workflow of processing steps together. In this paper we describe the Virtual Accelerator environment for modeling beam dynamics on distributed computational resources. We present the concepts and the design of the Virtual Accelerator, describe the prototype implementation and show early results.

Algorithm of Two-Level Parallelization for Direct Simulation Monte Carlo of Unsteady Floes in Molecular Gasdynamics

A general scheme of two-level parallelization (TLP) has been described for direct simulation Monte Carlo of unsteady gas flows on shared memory multiprocessor supercomputers. The high efficient algorithm of parallel statistically independent runs is used on the first level. The data parallelization is employed for the second one. Two versions of TLP algorithm are elaborated with static and dynamic load balacing. The dynamic processor reallocation technique is used for the dynamic load balancing. Two gasdynamic unsteady problems were used to study speedup and efficiency of the algorithms. The conditions of the efficient usage of the algorithms have been determined.

Distributed and Parallel Direct Simulation Monte Carlo of Rarefied Gas Flows

Two parallel direct simulation Monte Carlo (DSMC) algorithms for non-stationary and 3D gasdynamic problems computing are described. A parallel algorithm of DSMC was developed for non-stationary rarefied gas flows. High efficiency of the parallel algorithm was demonstrated by example of non-stationary gas expansion in vacuum from suddenly switched source. Speedup of the algorithm on Parsytec CC/16 parallel system was practically directly proportional to processors number. Other method of the DSMC parallelization which is based on domain decomposition was considered. Domain decomposition method was completed by time decomposition of modeling process and described in details. This method was employed for calculation of 3D side stream interaction with pulse jet. The problem was computed by the use of distributed calculations technique.

Problem-Solving Environment for Beam Dynamics Analysis in Particle Accelerators

In particle accelerator physics the problem is that we can not see what is going on inside the working machine. There are a lot of packages for modelling the behaviour of the particles in numerical or analytical way. But for most physicists it is better to see the picture in motion to say exactly what is happening and how to influence on this. The goal of this work is to provide scientists with such a problem-solving environment, which can not only do some numerical calculations, but show the dynamics of changes as a motion 3D picture. To do this we use the power of graphical processors from both sides: for general purpose calculations and for there direct appointment – drawing 3D motion. Besides, this environment should analyse the behaviour of the system to provide the user with all necessary information about the problem and how to deal with it.

Analog-Digital Approach in Human Brain Modeling

Many companies and institutions in their attempts construct decision-making system, face a bottleneck in performance of their systems. Training neural networks can take from several days to several weeks. The traditional approach suggests modification of modern systems and microcircuits as long as their performance reaches a permissible limit. A different approach, unconventional, looks for opportunities in computing inspired by the human brain, neuromorphic computing. The idea was proposed by the engineer Carver Mead in the 80s and suggests combining artificial neural networks with specialized microcircuits. The architecture of the microchip needs to reproduce the mechanisms of the human brain and to be a kind of hardware support for neural networks. Last decade is characterized by a sharp growth of interest in neuromorphic computing, human brain modeling and peculiarities of how it works during making decisions. This is evidenced by the launch of a large-scale research programs like DARPA SyNAPSE (USA) and the Human Brain Project (EU), the purpose of which is to build a microprocessor system, which resembles the human brain in functionality, size and energy consumption. Existing models of the brain even on powerful supercomputers require significant computation time and are not yet able to solve problems in real time. Since the human brain consists of two parts with different functions and different data processing principles, there is a very promising approach which suggests combining digital and analog systems into single one. In current collaboration we incorporate some results of study of activity of human brain as a base of building of hybrid computational system and foundation to the approach of running it.

Desktop supercomputer: what can it do?

The paper addresses the issues of solving complex problems that require using supercomputers or multiprocessor clusters available for most researchers nowadays. Efficient distribution of high performance computing resources according to actual application needs has been a major research topic since high-performance computing (HPC) technologies became widely introduced. At the same time, comfortable and transparent access to these resources was a key user requirement. In this paper we discuss approaches to build a virtual private supercomputer available at user’s desktop: a virtual computing environment tailored specifically for a target user with a particular target application. We describe and evaluate possibilities to create the virtual supercomputer based on light-weight virtualization technologies, and analyze the efficiency of our approach compared to traditional methods of HPC resource management.