|
|
 |
• Содержание выпуска •
• Software and Hardware for Distributed Systems and Supercomputers •
• Mathematical Modelling •
• Artificial Intelligence, Intelligence Systems, Neural Networks •
• Mathematical Foundations of Programming •
• Methods for Optimal Control and Control Theory •
• Supercomputing Software and Hardware •
Software and Hardware for Distributed Systems and Supercomputers
Responsible for the Section: Sergei Abramov, Dr. Phys.-Math.Sci.,
corresponding member of RAS
On the left: assigned number of the paper, submission date, the number
of A5 pages contained in the paper, and the reference to the full-text
PDF
/r1/pdf.jpg) .
|
Article # 26_2014
15
p.
/r1/pdf.jpg)
PDF |
submitted on 20th
Nov 2014 displayed on
website on
09th Dec
2014 Serdyuk Yu.
Programming the graphics processors (GPU) in MC# language
MC# is an extension of the object-oriented language
C#. It intended for developing applications running on multicore
processors and on clusters with distributed memory. Given paper
presents the basic principles and tools for programming the graphics
processors (GPUs) in MC# language. The sample program in MC#
intended to run on GPU is presented. Further we describe the tools
for establishing the parameters of GPU configuration and for using
of shared memory in MC# programs. In the final section we outline
the current problems under investigation and the directions for
further improvement of MC# programming system for GPU. (in Russian).
Key words: parallel programming, graphics processors (GPU,
shared memory. |
|
article citation |
http://psta.psiras.ru/read/psta2014_4_3-17.pdf |
|
Article # 23_2014
21
p.
PDF |
submitted on 14th
Nov 2014 displayed on
website on
15th
Dec
2014 Shevchuk Yu., Ponomarev A.,
Elistratov A.
BotikSwitch the Ethernet switch family
The article presents a family of compact managed
Ethernet switches for Internet providing using FTTx network
architecture. The family comprises 5 switch models: from switches
with as much as 9 SFP ports for fiber optics connection to small
client-end switches with a single SFP port. The switches work in
industrial temperature range, accept wide range of DC power supply
voltages, feature an interface for external sensor connection. The
control protocol is designed for automated control and monitoring of
a large number (thousands) of switches. Control features include
ping, IEEE 802.1Q VLANS, fine grained per-port bandwidth control and
MAC address based packet filtering. The switch family facilitates
cost-effective modern networks. (In Russian).
Key words: internet, managed Ethernet switch, VLAN, fiber
optics, SFP, FTTB, FTTH, FTTx. |
|
article citation |
http://psta.psiras.ru/read/psta2014_4_83-103.pdf |
|
Article # 26_2014
12
p.
PDF |
submitted on 05th
Dec 2014 displayed on
website on 25th Dec
2014 Mayboroda Yu., Syntsov M.,
Ozerin A., Kuzin A., Varlamov O.
Automatic tagging system based on mivar technologies
This article considers the problem of development of
an automatic tagging system. The review of the existing problems and
software products in the sphere of image recognition is presented.
For solving the problem of classification of all objects which exist
in an image it is proposed to develop the modul of context ambiguity
elimination and the control modul which controls intelligent
launching of the other system moduls. These moduls use mivar
technologies: mivar knowledge base and mivar method of logical
inference. The article presents the modul scheme of the system and
also the description of how the moduls of the system work. (in
Russian)
Key words: artificial intelligence, image recognition,
automatic tagging, mivar, mivar technologies. |
|
article citation |
http://psta.psiras.ru/read/psta2014_4_159-170.pdf |
|
Article # 27_2014
12
p.
PDF |
submitted on 04th
Dec 2014 displayed on
website on
15th
Dec
2014 Sukhoroslov O.
Integration of distributed computing applications and resources
on the base of cloud platform
Everest is a cloud platform for researchers
supporting publication, execution and composition of applications
running across distributed computing r esources. The paper describes
the platform’s architecture, application development, integration
with external computing resources and application composition using
the platform’s API. (In Russian).
Key words: distributed computing, cloud platform, web
services, REST, integration of computing resources, application
composition. |
|
article citation |
http://psta.psiras.ru/read/psta2014_4_171-182.pdf |
|
Article # 28_2014
12
p.
PDF |
submitted on 04th
Dec 2014 displayed on
website on 25th Dec
2014 Volkov S., Sukhoroslov O.
Implementation of parameter sweep computations on Everest
platform
Parameter sweep applications are a
very important class of applications, which are typically defined as
a set of computational experiments over a set of input parameters,
each of which is executed with its own parameter combination. These
co mputations arise in many scientific contexts. This article
introduces the Parameter Sweep web service that runs such
applications in distributed computing environment. Also discussed is
the Everest cloud platform, on which this service is
built. (in Russian).
Key words: grid technologies, parameter sweep computations,
computational web services. |
|
article citation |
http://psta.psiras.ru/read/psta2014_4_183-194.pdf |
|
Article # 29_2014
11
p.
PDF |
submitted on 04th
Dec 2014 displayed on
website on
29th
Dec
2014 Demidov A.
About the features of DBMS architecture in MPP-system
Today a lot of effort is worldwide put into
development exaplops computers, which will be able to perform 1018
floating-point operations per second. Effective performance of the
cluster on real tasks is considerably less of that value due to
synchronisation costs of concurrent processes. This paper introduces
a concept of passive cache, which eliminates any need for process
synchronization in some tasks, and proposes a system architecture of
high performance distributed DBMS, based on the passive cache. (in
Russian).
Key words: parallel and distributed computing, very large
databases. |
|
article citation |
http://psta.psiras.ru/read/psta2014_4_195-205.pdf |
• Содержание выпуска •
• Software and Hardware for Distributed Systems and Supercomputers •
• Mathematical Modelling •
• Artificial Intelligence, Intelligence Systems, Neural Networks •
• Mathematical Foundations of Programming •
• Methods for Optimal Control and Control Theory •
• Supercomputing Software and Hardware •
|
/r5/_derived/content-01(019).en.html_cmp_strtedge110_vbtn.gif){kind=small}
/_derived/content-02(020).en.html_cmp_strtedge110_vbtn.gif){kind=small}
/_derived/content-03(021).en.html_cmp_strtedge110_vbtn.gif){kind=small}
.en.html_cmp_strtedge110_vbtn.gif){kind=small}
/_derived/content-05(023).en.html_cmp_strtedge110_vbtn.gif){kind=small}
