Software & Systems

Journal articles №4 2014

1. Tracing and selfhealing in POSIX-systems [№4 за 2014 год]
Authors: Bombin A.A. (abombin@niisi.msk.ru) - Scientific Research Institute for System Studies of the Russian Academy of Sciences (SRISA RAS); Galatenko V.A. (galat@niisi.msk.ru) - Scientific Research Institute for System Studies of the Russian Academy of Sciences (SRISA RAS), Ph.D; Kostyukhin K.A. (kost@niisi.msk.ru) - Scientific Research Institute for System Studies of the Russian Academy of Sciences (SRISA RAS), Ph.D;
Abstract: This paper formulates a definition of the controlled execution original concept and motivates the importance of this concept when creating complex systems. Controlled execution is a specially organized process of hardware and software system functioning. This system is intended to perform its tasks despite errors, attacks and failures. The basics of controlled concept execution are: integration of information security, debugging and management tools; distribution of controlled execution for all phases of system life cycle; integrity of the controlled execution tools, differing in an impact degree on the target system, the possibility of interactions between these tools. Special cases of controlled execution are: information systems controlling; interactive debugging; system monitoring; system self-control; playback the previous sessions of the systems; modeling, collection and analysis of quantitative characteristics of systems; system selfhealing. Taking in the context of controlled execution, the authors propose a POSIX-systems selfhealing technique based on the POSIX trace mechanism. There is a brief review of a trace mechanism described in POSIX-2001. The paper proposes a technique of software systems selfhealing based on this mechanism and integrated into controlled execution concept. POSIX-2001 fixes the minimum functionality of tracing tools, which should be provided by a POSIX-compliant operating system. POSIX-2001 standard refers tracing as collection, accumulation and analysis of data on the events that took place in the user application operation. The work includes an example which can be useful in the practical application of selfhealing methods.
Keywords: controlled execution, debugging, tracing, selfhealing, posix
Visitors: 8832

2. The visual editor and calculation module of block diagrams for simulation and training complexes [№4 за 2014 год]
Authors: Mikhaylyuk M.V. (mix@niisi.ras.ru) - SRISA RAS, Ph.D; Torgashev M.A. (mtorg@mail.ru) - SRISA RAS, Ph.D;
Abstract: One of the most important components of simulation and training complexes is a control system for controlling motors, payload, actuators, etc. It can be presented as a diagram of functional elements which are called functional units or functional blocks. There are a lot of developments in this field. However, despite the abundance of existing software products, the task of creating simple and affordable systems based on block diagrams for simulation and training complexes is still urgent. The article describes a software package for creating, testing, editing and calculation of functional block diagrams designed for control systems of simulation and training complexes, including robots' and manipulators' simulation, virtual laboratories and training systems. The paper discusses in detail both functionality and technology of visual editor, the algorithm and the scheme of calculation module of block diagrams. The proposed editor has broad functionality and allows simulating rather complex schemes. A calculation module is implemented as a dynamic link library which can be connected to any software package. The developed technology allows enhancing functionality by connectin g additional software modules, which may include the implementation of special purpose computing blocks and blocks for data exchange, such as external consoles. The possibilities of applying the proposed system for process simulation and training systems are illustrated by simulation of anthropomorphic robot control in manual and copying mode. The advantages of the system are the ease of use, undemanding to resources and extensibility.
Keywords: virtual modeling, simulation and training complexes, functional diagrams, control systems
Visitors: 10758

3. Simulation of potential distribution in the operation area of the [№4 за 2014 год]
Authors: Masalsky N.V. (volkov@niisi.ras.ru) - SRISA RAS, Ph.D;
Abstract: The article discusses the simulation questions of transistor structures characteristics that are created according to a new generation technology "germanium on an insulator". It also considers one of the possible approaches to the analytical solution of a 2D Poisson equation for a potential in the operation area of a field double gate nanotransistor with "germanium on an insulator" structure and architecture "without overlapping of gate regions and a drain/source". The authors have received an analytical solution of a Poisson equation for a potential using superposition principle. The paper considers physical restrictions of technological parameters of researched transistor structures for their electro-physical characteristics optimization. In particular, for effective suppression of short-channel effects. These effects are shown more in devices under study than in similar "silicon on an insulator" structures. Based on numerical solutions of a Poisson equation the paper analyzes dependences of the main electro-physical characteristics on technological parameters. These characteristics include potential distribution in operation area, threshold voltage and a subthreshold characteristic slope. Non-linear nature of the received dependences is caused by the exponential growth of a volume charge in the transistor operation area. For selected topological norms an optimization of parameters defining drain and source regions provides an additional degree of freedom control of key characteristics along with operation area and frontal gate oxide. This is important for an applicability analysis of transistor structures "germanium on an insulator".
Keywords: subthreshold slope, threshold voltage, potential distribution, analytical model, double gate field nanotransistor, structure "germanium on an insulator"
Visitors: 10041

4. Synthesis of burst-mode asynchronous schemes using Synopsys Design Compiler [№4 за 2014 год]
Author: Surkov A.V. (surkov@cs.niisi.ras.ru) - SRISA RAS;
Abstract: The industrial needs in a robust computing systems increase the interest in asynchronous logic. The major reasons to use asynchronous design are the high robustness and wide operating temperature range of such schemes. The most significant counter argument is the long developing time as а result of the lack of asynchronous design automation tools (EDA). The burst mode schemes are the asynchronous schemes sub-class which is the easiest to build. The cross-coupled dual rail expansion method is the most popular to design the burst mode schemes and can use the synchronous schemes as an interim step of designing process. The synchronous scheme must perform the same function and can be obtained by a common synthesis way. The conversion from synchronous prototype to burst-mode scheme may use the templates, so it is easy to automate this process. We chose the Synopsys Design Compiler as one of EDA tools, which may provide synchronous synthesis and also use Tcl language for scripting. The whole burst mode synthesis workflow process consists of three major steps: synchronous synthesis from Verilog description, dual rail expansion and construction of complete detection sub-scheme. The last step is to optimize the load capability of the elements of the final scheme through the static timing analysis algorithms built into the DC tool. All the steps are processed by the one tcl script working in the DC shell, so overall process is fully automated. At this time the script has a limited functionality, an d can handle only one pipeline stage per run.
Keywords: synopsys dc, CAD system, burst mode schemes, asynchronous schemes
Visitors: 10636

5. Rear-projection method in visualization subsystem of training simulation system [№4 за 2014 год]
Authors: Giatsintov A.M. (algts@inbox.ru) - SRISA RAS; Mamrosenko K.A. (kirillam@ya.ru) - SRISA RAS, Ph.D;
Abstract: Nowadays in many industry sectors (for example, in aerospace industry) there is a shortage of qualified specialists, capable of controlling complex technical systems. There is a need of a massive increase of training centers efficiency, particularly with adaption of new training methods and developing of more effective training complexes. Using multimedia technologies in training-simulation systems development allows creating training materials data banks that include images, texts accompanied by audio, video and visual effects, interactive interface; provide an effective way of using collected information for distant and distributed training. One way of using multimedia data in training simulation systems is to insert a graphical representation of instructor into virtual environment. In order to correctly visualize an image of instructor in a 3D virtual scene a method of rear-projection has been developed. It is based on 3D keying. Its main function is to separate an object from a uniform background. This process can be described as a process of creating a mask that contains information about image translucency that separates an object from other parts of an image. Any keying method is resource-intensive, so processing of large images on CPU can lead to performance problems of visualization subsystem, while one of the requirements for visualization subsystem is real-time operation. Considering this requirement, a realization of keying algorithm uses resources of the video card to process images.
Keywords: render, rendering, training simulation systems, keying, rear-projection
Visitors: 9923

6. Methods of multiprocessor system initializations [№4 за 2014 год]
Author: Lavrinov G.A. (lavrinov@cs.niisi.ras.ru) - SRISA RAS;
Abstract: Any multiprocessor system must be initialized on power. This article considers RapidIO systems. Correct RapidIO routers configuration influences on proper work of the whole system. There are two initialization algorithms: dynamic and static. RapidIO dynamic initialization algorithm indicated in the specification has a number of faulties including a lack of information about physical structure after initialization. For example, it is unacceptable for some tasks on testing of a multiprocessor system. Therefore, static initialization should be used as it already envisages a set of commands for settin g up routes between devices. It is proposed to apply the configurator that uses basic RapidIO switch ports in order to create a set of commands performing initialization effectively. The system is considered as a set of basic blocks with unique numbers of RapidIO switch ports. A configurator takes the input of the structure from a module geographical address, module models and connections between other modules. Output it creates a set of service packages to initialize RapidIO communicative interface. The effectiveness of this method appears mostly during the creating of various multiprocessor system modifications. This article also describes the current hardware support for initialization interface and its application in the testing system.
Keywords: RapidIO, multiprocessor systems, initialization, configurator, testing, routing, algorithm
Visitors: 11767

7. The analysis of interval stochastic temperature fields of technical systems [№4 за 2014 год]
Authors: Madera A.G. (alexmadera@mail.ru) - SRISA RAS, Ph.D; Kandalov P.I. (petrki87@gmail.com) - SRISA RAS;
Abstract: Experience has shown that the actual temperature fields of technical systems have uncertainty interval nature. This is due to the interval factors determining the thermal regime of the technical system. These factors include: the design parameters of technical systems with statistical techno logical manufacture spread; factors arising in the operation of technical systems ( power consumption, heat flows, internal environment parameters); environmental factors (temperature, medium, refrigerant, flows velocity, etc.). However, now modeling of temperature fields of technical systems is being conducted under the assumption of determinac y. This means that all thermal condition parameters are considered accurately known. The paper presents the method and algorithm of mathematical modeling and simulation of stochastic interval temperature fields for technical systems. The method and algorithm are based on the author's developments according to a matrix-topological method, the software complex three-dimensional deterministic modeling of temperature fields of technical systems (STF-ElectronMod), as well as Monte-Carlo method. The application of the method and algorithm for modeling interval stochastic temperature fields is considered on the example of an electronic system.
Keywords: a tempering, uncertainty, interval, stochastic, mathematical expectation, variance, standard deviation
Visitors: 8478

8. On one method of blood cell classification and its software implementation [№4 за 2014 год]
Authors: Belyakov V.K. (bel.vk@yandex.ru) - LLC “WESTTRADE LTD”, Ph.D; Sukhenko E.P. (evs@westtrade.ru ) - LLC “WESTTRADE LTD”, Ph.D; Zakharov A.V. (zaharov@niisi.msk.ru) - SRISA RAS; Koltsov P.P. (koltsov@niisi.msk.ru) - SRISA RAS, Ph.D; Kotovich N.V. (kotovich@niisi.msk.ru) - SRISA RAS; Kravchenko A.A. (alexk@genebee.msu.su) - SRISA RAS, Ph.D; Kutsaev A.S. (koutsaev@niisi.msk.ru) - SRISA RAS, Ph.D; Osipov A.S. (osipa68@yahoo.com) - SRISA RAS, Ph.D; Kuznetsov A.B. (shuricnet@mail.ru) - Pirogov Russian National Research Medical University, Ph.D;
Abstract: A method is offered to classify the leukocytes, erythrocytes and thrombocytes. This method is based upon a comprehensive study of various segmentation methods of microscopic images and algorithms for calculation of blood cell feature sets. Our approach assumes the application of an improved combined segmentation method for microscopic images, the use of an optimized feature vector of an object and a neural network classifier. The important role in the design of our segmentation method belongs to the EDEM method for a comparative study of image processing algorithms developed in SRISA RAS. The segmentation method includes such steps as edge detection, contour closing and over-segmentation elimi-nation (based upon a set of features calculated for each initial segment). For the edge detection we use a combination of the classical Canny detector and the Ritter-Cooper method designed for blood cell segmentation. This combination comprises the advantages of both algorithms. For the boundary enhancement and contour closing steps we use an approach based upon the graph theory which develops the adaptive contour closure algorithm proposed by Jiang. The over-segmentation elimination is an iterative procedure. Our segmentation method is suitable for both red and white blood cell segmentation. To solve the blood cell classification task by a feature set we use a neural network of a multilayer perceptron type (three-layer feedforward neural network with a sigmoid function in the hidden layer). The neural network classifier allows one to effectively separate the cells into different types used in practical hematology. The program library, where the proposed classification method was implemented, is created. Our tests with various blood smear images have shown a high potential of our method for prac-tical application.
Keywords: automated microscopic systems, blood cells, image segmentation, edge detectors, comparative study, image classification, neural network
Visitors: 15726

9. Real-time particle system realization on GPU [№4 за 2014 год]
Authors: Maltsev A.V. (avmaltcev@mail.ru) - SRISA RAS, Ph.D;
Abstract: Particle systems are commonly used in virtual three-dimensional scenes for realistic simulation and visualization of important (in terms of the correct environment perception) natural phenomena and objects that have no clear geometry boundaries, e.g. smoke, fire, water jets, rain, snow, etc. The work proposes the technology for distributed simulation and visualization of such systems using modern multi-core graphic processors. This technology includes two stages. The first stage includes calculation of particle system condition at specified time moment as particles data array. The second assumes a visualization of obtained array with «on the fly» synthesis of necessary particle geometry, their lighting calculation and texture mapping. Both stages are performed on videocard's graphics pipeline that allows achieving high degree of parallelism. For this purpose the shader rendering mechanism is employed including vertex, geometry and fragment shaders. The second stage uses a geometr y shader for synthesis of particle's polygonal model. As an example, particle construction is considered as a “sprite”. It has a square form with its front face is always looking at virtual camera. Developed technology supports using of particle systems with number of elements about 10 6 in three-dimensional scenes. It saves a possibility of real-time rendering that is particularly important for such application fields as simulation-training complexes and virtual environment systems. Furthermore, the article also describes practical results of proposed decisions that are oriented for using in real -time visualization systems.
Keywords: render, particle system, shaders, graphic processor, simulation-training complexes
Visitors: 12802

10. Using driver for Ethernet 1 Gbps controller’s prototype testing [№4 за 2014 год]
Author: Slinkin D.I. (slin@nm.ru) - SRISA RAS;
Abstract: The article describes a family of Ethernet controllers created the SRISA RAS. Currently a prototype of a new perspective processor with embedded Gigabit Ethernet controller is being designed. Testing is an integral part of microcircuits design process and is a time-consuming task. This article introduces an approach to testing of an embedded network controller model during its design. The prototype in question is implemented as a field-programmable gate array (FPGA) based on technological card. There are several different ways of microcircuits projects verification. The article offers the network controllers testing method based on author’s practical experience. This testing method has become the main stage of the network controller’s prototype verification. The system software – drivers are suggested as a basis for the testing software. The article also considers the following subjects: the tasks which can be solved using software based tests, such as: smoke tests, suitability, compatibility with different hardware and operation systems, program compatibility with previous version of microcircuit, stability and reliability testing. Special attention is paid to performance testing and to surveying of a network controller’s behavior beyond the limits of normal operation; factors tha t affect the system’s performance; an issue of CPU loading during intensive network activity and the ways of its reduction; situations which can appear during controller’s stress loading. In conclusion the paper discusses a range of functional tests application, as well as their advantages and disadvantages in comparison with other testing methods. Drivers and ready-made tests are presented as means of reducing labor-intensity. The plan of future works is suggested.
Keywords: network controller, ethernet, vlsi functional testing, performance testing, baget, linux
Visitors: 10008

| 1 | 2 | 3 | 4 | 5 | Next → ►