|
|
|
Papers are accepted in the form of a PDF file
To view the PDF files, you will need Adobe Acrobat Reader
 |
|
 |
• Содержание выпуска
Supercomputing Software and Hardware
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 #
1_2021
17 с.
/r1/pdf.jpg)
PDF |
submitted on
14th
Dec 2020 displayed on
website on 02th
March
2021 Anatolii D. Panferov, Nikolai A.
Novikov, Alexandr A. Trunov
Simulate the behavior of graphene in external electric fields
The paper presents the results obtained in developing
a complex for calculating the parameters of monolayer graphene under
an external electric field’s action. The used physical model allows
detailed reproduction of such parameters but requires an extensive
computation for exact values. The model is based on the system of
kinetic equations that provide the calculation of the time-dependent
distribution function of charge carriers in two-dimensional momentum
space. The computational resource requirements are proportional to
the number of the computational grid nodes that cover the momentum
space. The model’s behavior allows local grids that cover only a
relatively small part of the computed function domain.
We model the results of the action of short high-frequency pulses of
an electric field and analyze the behavior of the model at the
maximum level of the external field to search and localize regions
in momentum space, the determination of the distribution function in
which is sufficient to obtain the values of the observables. Such
localization of distribution functions from calculations on
relatively sparse grids works even for weak external electric
fields.
Obtaining the observed parameters requires calculating the integral
characteristics of the distribution function in the two-dimensional
momentum space. Its implementation in parallel with the simultaneous
calculation of the distribution function’s values on the optimized
grid makes it unnecessary to preserve the values of the distribution
function and possible to obtain only one-dimensional time series.
Such representing data on the dynamics of the observed parameters is
useful for analyzing the behavior of the model under consideration.
(In Russian).
Key words: numerical simulation, graphene, distribution
function of charge carriers, optimal choice of the computational
grid, calculation of the observed parameters. |
|
article citation |
http://psta.psiras.ru/read/psta2021_1_3-19.pdf |
|
DOI |
https://doi.org/10.25209/2079-3316-2021-12-1-3-19 |
|
Article #
2_2021
93 с.
PDF |
submitted on
19th
Sep 2020 displayed on
website on 02th
March
2021 Boris Ya. Steinberg, Oleg B.
Steinberg
Program transformations as the base for
optimizing parallelizing compilers
The paper deals with program transformations leading
to acceleration and summarize the
publications on various parallel computing architectures and
tools for developing effective programs for them. The
discussion focuses on a combination of
parallelization and optimization of access to memory modules of
different levels. It highlights that the lag of automatic
program optimization from the needs of new
architectures restrains the development of new promising
computing systems.
The development of the theory of program transformation and
optimizing (parallelizing) compilers could
lead to a significant increase in the productivity of
programmers. The article substantiates the call for the
modernization of the optimizing compilation
and presents new problem statements.
(In Russian).
Key words: optimizing compiler, parallel computations,
program transformations, data locality,
memory access optimization, tile. |
|
article citation |
http://psta.psiras.ru/read/psta2021_1_21-113.pdf |
|
DOI |
https://doi.org/10.25209/2079-3316-2021-12-1-21-113 |
|
Article #
3_2021
14 с.
PDF |
submitted on
18th
Dec 2029 displayed on
website on 23th
March
2021 Alexey V. Makhankov, Maksim O.
Kuznetsov, Anatolii D. Panferov
Efficiency of using NVIDIA coprocessors in
modeling the behavior of charge carriers in graphene
Specialized hardware solutions play an important role
in the development of supercomputer
technologies. Currently, most computing systems
of maximum performance use mathematical coprocessors of
various types. So the development of applied
software solutions designed to realize the potential of
modern computing platforms requires ensuring the efficient
use of hardware accelerators. The course of
work on a software system for simulating the behavior
of charge carriers in graphene needs to solve the problem of
supporting such accelerators and to
investigate the efficiency of the solution obtained. The
current situation and the prospects for the next few years
suggest the NVIDIA accelerators and CUDA
software technology, but the hardware architecture of
NVIDIA accelerators is fundamentally different from the CPU
architecture, and therefore the mathematical
libraries adapted for CUDA do not support the entire
range of algorithms used in the original version of the
program. The paper presents the features of
an implementation of CUDA support and the results of
comparative testing of the obtained solution using the
example of a problem with realistic
characteristics. (In Russian).
Key words: high performance computing, hybrid architectures,
CUDA, graphene, quantum kinetic equation. |
|
article citation |
http://psta.psiras.ru/read/psta2021_1_115-128.pdf |
|
DOI |
https://doi.org/10.25209/2079-3316-2021-12-1-115-128 |
|
|
|
• Содержание выпуска
|
 |
|
Adress: Ailamazyan Program Systems Institute of the Russian
Academy of Sciences, PSTA Online Journal, 4 a Peter the First Street,
Veskovo village, Pereslavl area, Yaroslavl region, 152021 Russia
Phone: +7-4852-695-228. E-mail:
info@psta.psiras.ru.
Website:
http://psta.psiras.ru
©
Electronic Scientific Journal "Program Systems: Theory and
Applications" 2010-2017
© Ailamazyan Program System Institute of RAS 2010-2018
 |
|
