DonNTU   Masters' portal

Content

Introduction

To date, there are more than 130 million computers and over 80% of them are combined in a variety of information and computer networks from small local area networks in offices to global networks such as Internet. Global trend towards unification of computers in the network due to a number of important reasons, such as the acceleration of information transmission, the possibility of rapid exchange of information between users, receiving and sending messages (fax, E - Mail letters and other things) without departing from the workplace, the ability to instantly obtain any information from anywhere in the world, as well as the exchange of information between computers of different manufacturers running different software.

It is therefore necessary to develop a fundamental solution to the problem of organizing INC (Information Network Computing) on the basis of an existing local area network and the software system meets modern scientific and technical requirements, taking into account the growing needs and the possibility of further gradual development of the network due to the emergence of new hardware and software solutions [1].

1. Theme urgency

Dynamic queue management applications for the maintenance of the network by adapting its structure to the state of the input and output streams is an important task in the local area sensor systems operating in real time. Managing the distribution of flows can be achieved both by controlling the structure of the network by changing the capacity of wireless channels in bundles of telecommunications systems, or redistribution of channels when changing network of information interactions between individual pairs of switching nodes, and by controlling the routes of streams without changing the structure of the network.

2. Goal and tasks of the research

The purpose of master's work is to study the existing algorithms for sorting and processing of data queue for service, as well as creating the most profitable of the algorithm. The basis for the development of a new method of sorting and processing of data are the modern FPGA.

3. Abstract

The analysis of principles of a design and operation of modern systems of verification of reconfigurable PLD-based devices of such known corporations, as Virtual Computer Corporation (H.O.T), Nallatech (FUSE), Aptix (System Explorer), Xilinx (XtremeDSP Development Kit) is made. This system, realizing integration of configurable plate and tools of designing, are means for an evaluation, adjustment and prototyping of the projects using PLD chips and other elements as a computing element of a system [2].

Development of a hardware module with a parallel sorting data entry

The work of this module is carried out in two stages.
Stage 1.

There is an accumulation of information. Sensors remove evidence and pass them on to the inputs of register data (A – D), where it is converted into binary sequences. These sequences come from the pairs of registers in the comparison circuit. Then we have two maximum values of the 4 registers. These two values are the same comparator and multiplexer circuit whose output is a single maximum value. This is the feedback circuit is fed to the second input of the multiplexer, which is set at the beginning of our scheme.

Select the highest value in the scheme

Figure 1 – Select the highest value in the scheme
(animation: 8 frames, 250 kb)

Stage 2.

Turning to the operation of the flag (trigger) occurs after a time interval equal to the passage of the input data from sensors, through multiplexers to the registers + transit time ordering scheme. Its main task – to allow for transfer of information from the register with the critical value of the diagnostic parameter in a register, the contents of which will be the first in the queue for processing applications.

Conclusion

In this paper the current master of scientific and technical challenge, which is devoted to the study and modification of modern methods of sorting.

This master's work is not completed yet. Final completion: December 2012. The full text of the work and materials on the topic can be obtained from the author or his head after this date.

References

  1. Компьютерные сети [Электронный ресурс]. http://www.radioland.net.ua.
  2. Палагин А.В., Опанасенко В.Н., Сахарин В.Г. Системы верификации на основе реконфигурируемых устройств. – ISSN 1028-9763. Математические машины и системы, 2004, № 2.
  3. Сортировка вставкой. http://borlpasc.narod.ru/inzik/glava1/sortivs.htm.
  4. Сортировка пузырьком. http://algolist.manual.ru/sort/bubble_sort.php.
  5. Гриценко А. А., Сероштан С.Ю., Зинченко Ю.Е. Разработка аппаратного модуля сортировки с последовательным вводом данных и минимальным временем обработки. / Наукові праці ДонНТУ ISSN 1996-1588, Серія "Інформатика, кібернетика та обчислювальна техніка" випуск 13(185), 2011.
  6. Поляков А. К. Языки VHDL и VERILOG в проектировании цифровой аппаратуры / А.К. Поляков. – М.: СОЛОН-Пресс, 2003. – 320 с.
  7. Максфилд К. Проектирование на ПЛИС. Курс молодого бойца / К. Максфилд. – М.: Издательский дом «Додэка-XXI», 2007. – 408 с.
  8. Палагин А. В. Реконфигурируемые вычислительные системы: Основы и приложения / А. В. Палагин, В. Н Опанасенко. – К.: Просвіта, 2006. – 280 с.: ил.
  9. Grout I. Digital systems design with FPGAs / I. Grout. – Elsevier, 2008. – 724 pp.
  10. Batcher K. E. Sorting networks and their applications / K. E. Batcher. – "Goodyear Aerospace Corporation", 1968. – 8 pp.
  11. Жабин В.И. Исследование методов построения вычислительных устройств на основе FPGA / В.И. Жабин, Н.А. Ковалев // Технология и конструирование в электронной аппаратуре. – 2002. – № 2. – С. 35-39.