?
Исследование масштабируемости FlowVision на кластере с интерконнектом Ангара
Вычислительные методы и программирование: новые вычислительные технологии. 2017. Т. 18. С. 406-415.
Акимов В. С., Силаев Д. П., Симонов А. С., Semenov A.
The scalability of computations in FlowVision CFD software on the Angara-C1 cluster equipped with Angara interconnect is studied. Several test problems with 260 thousand, 5.5 million and 26.8 million computational cells are considered. Computations in FlowVision are performed using a new solver of linear systems based on the algebraic multigrid (AMG) method. It is shown that the special FlowVision’s technology named “Dynamic balancing” significantly improves the performance of computations if the peculiarities of the problem promote the non-uniform loading of CPUs. The Angara-C1 cluster demonstrates the excellent performance and scalability characteristics comparable with its analogues based on the 4х FDR Infiniband interconnect.
Челябинск : Издательский центр ЮУрГУ, 2021
Данный сборник содержит статьи, включенные в программу Международной научной конференции «Параллельные вычислительные технологии 2021». Конференция проходила 30 марта – 1 апреля 2021 года в Волгоградском государственном техническом университете (г. Волгоград).
Подробную информацию о конференции можно найти в сети Интернет по адресу http://agora.guru.ru/pavt
Отпечатано с авторских оригиналов. ...
Added: October 19, 2021
Челябинск : Издательский центр ЮУрГУ, 2015
Данный сборник содержит статьи, включенные в программу Международной научной конференции «Параллельные вычислительные технологии 2015». Конференция проходила с 31 марта по 2 апреля 2015 года в Уральском федеральном университете имени первого Президента России Б.Н. Ельцина и Институте математики и механики УрО РАН (г. Екатеринбург). Подробную информацию о конференции можно найти в сети Интернет по адресу http://agora.guru.ru/pavt. ...
Added: October 20, 2021
М. : Издательство МГУ, 2017
Данный сборник содержит работы, включенные в программу Международной конфе- ренции «Суперкомпьютерные дни в России» и сопутствующих мероприятий: конфе- ренции молодых ученых, семинаров «Суперкомпьютерное образование: проблемы и перспективы» и «Параллельная обработка больших графов». ...
Added: January 29, 2018
Khalilov M., Timofeev A., Lobachevskii Journal of Mathematics 2018 Vol. 39 No. 9 P. 1188-1198
An algorithm of MPI processes mapping optimization is adapted for supercomputers with interconnect Angara. The mapping algorithm is based on partitioning of parallel program communication pattern. It is performed in such a way that the processes between which the most intensive exchanges take place are tied to the nodes/processors with the highest bandwidth. The algorithm ...
Added: March 10, 2019
М. : МАКС Пресс, 2023
The book contains full papers in Russian, short papers and poster abstracts included in the agenda of the International Conference “Russian Supercomputing Days”. ...
Added: January 23, 2024
Замятина Е.Б., Миков А. И., Михеев Р. А., Вестник Пермского университета. Серия: Математика. Механика. Информатика 2013 № 4(23) С. 107-118
The problems of simulation of distributed information systems are discussed. There are a large number of specialized software systems dedicated to design a simulation model of distributed systems and to run a simulation experiment. The article deals with software and language tools of CAD Triad.Net, considers the main features of the simulation model and how ...
Added: March 10, 2015
С.Д. Кузнецов, Посконин А. В., Труды Института системного программирования РАН 2013 Т. 24 С. 327-258
Many modern applications (such as large-scale Web-sites, social networks, research projects, business analytics, etc.) have to deal with very large data volumes (also referred to as “big data”) and high read/write loads. These applications require underlying data management systems to scale well in order to accommodate data growth and increasing workloads. High throughput, low latencies ...
Added: January 30, 2018
Russkov A., Shchur L., Journal of Physics: Conference Series 2019 Vol. 1163 No. 012079 P. 1-5
Matrix multiplication is one of the core operations in many areas of scientific computing. We present the results of the experiments with the matrix multiplication of the big size comparable with the big size of the onboard memory, which is 1.5 terabyte in our case. We run experiments on the computing board with two sockets ...
Added: March 26, 2019
Ziganurova L., Shchur L., Physical Review E - Statistical, Nonlinear, and Soft Matter Physics 2018 Vol. 98 No. 022218 P. 1-15
We examine the question of the influence of sparse long-range communications on the synchronization in parallel discrete event simulations (PDES). We build a model of the evolution of local virtual times (LVT) in a conservative algorithm including several choices of local links. All network realizations belong to the small-world network class. We find that synchronization ...
Added: July 13, 2018
С.Д. Кузнецов, Посконин А. В., Программирование 2014 Т. 40 № 6 С. 34-47
In the last decade, a new class of data management systems collectively called NoSQL systems emerged and are now intensively developed. The main feature of these systems is that they abandon the relational data model and the SQL, do not fully support ACID transactions, and use distributed architecture (even though there are non-distributed NoSQL systems ...
Added: November 6, 2017
М. : Издательство МГУ, 2012
Данный сборник содержит доклады, включенные в программу Международной суперкомпьютерной конференции «Научный сервис в сети Интернет: поиск новых решений» и Всероссийской конференции молодых ученых «Теория и практика параллельного программирования». Конференции проводятся с 17 по 22 сентября 2012 года. Подробную информацию о конференциях можно найти в сети Интернет по адресу http://agora.guru.ru/abrau2012 ...
Added: October 20, 2021
М. : МАКС Пресс, 2021
The book contains full papers in Russian, short papers, poster abstracts, and also abstracts of full papers in English included in the “Russian Supercomputing Days” conference agenda. ...
Added: October 20, 2021
Stegailov V., Dlinnova E., Ismagilov T. et al., International Journal of High Performance Computing Applications 2019 Vol. 33 No. 3 P. 507-521
In this paper, we describe the Desmos supercomputer that consists of 32 hybrid nodes connected by a low-latency highbandwidth Angara interconnect with torus topology. This supercomputer is aimed at cost-effective classical molecular dynamics calculations. Desmos serves as a test bed for the Angara interconnect that supports 3D and 4D torus network topologies, and verifies its ...
Added: November 11, 2018
Суперкомпьютерные дни в России: Труды международной конференции (24-25 сентября 2018 г., г. Москва).
М. : МГУ, 2018
Данный сборник содержит работы, включенные в программу Международной конференции «Суперкомпьютерные дни в России» и сопутствующих мероприятий: конференции молодых ученых, семинаров «Суперкомпьютерное образование: проблемы и перспективы» и «Грид-системы из персональных компьютеров». Конференция проводится с 24 по 25 сентября 2018 года в г. Москва. Подробную информацию о конференции можно найти в сети Интернет по адресу http://RussianSCDays.org ...
Added: October 31, 2018
Shchur L., Barash L., Weigel M. et al., , in : Supercomputing. RuSCDays 2018. Communications in Computer and Information Science, vol 965. Springer, Cham. : Springer, 2019. P. 354-366.
Population annealing is a novel Monte Carlo algorithm designed for simulations of systems of statistical mechanics with rugged free-energy landscapes. We discuss a realization of the algorithm for the use on a hybrid computing architecture combining CPUs and GPGPUs. The particular advantage of this approach is that it is fully scalable up to many thousands ...
Added: April 6, 2019
М. : Издательство Московского университета, 2012
The project “Supercomputer Education” of the presidential Commission for Modernization and Technological Development of Russian Economy has come to an end. Within this project the program of creation the integral system of supercomhuter education in Russia has been completed for the first time. ...
Added: March 25, 2014
Zlotnik A., Gavrilin undefined. V., Вестник Московского энергетического института 2016 № 1 С. 5-14
Изучается семейство трехточечных симметричных дискретизаций по пространству квазигидродинамической системы уравнений с общими уравнениями состояния газа. Выводится уравнение баланса энтропии. В нем вид сеточных дисбалансных слагаемых зависит от выбора усреднений плотности и внутренней энергии; для специальных усреднений недивергентные дисбалансные слагаемые равны 0. Выполняются расчеты известных тестов для системы уравнений Эйлера при различных уравнениях состояния. Их результаты ...
Added: October 9, 2015
S.D. Kuznetsov, Посконин А. В., Programming and Computer Software 2014 Vol. 40 No. 6 P. 323-332
In the last decade, a new class of data management systems collectively called NoSQL systems emerged and are now intensively developed. The main feature of these systems is that they abandon the relational data model and the SQL, do not fully support ACID transactions, and use distributed architecture (even though there are non-distributed NoSQL systems ...
Added: November 6, 2017
Овсянников А. П., Программные продукты и системы 2007 № 2 С. 17-19
Added: August 20, 2015
V.A. Gavrilin, A.A. Zlotnik, Computational Mathematics and Mathematical Physics 2015 Vol. 55 No. 2 P. 264-281
The one-dimensional quasi-gasdynamic system of equations in the form of mass, momentum, and total energy conservation laws with general gas equations of state is considered. A family of three-point symmetric spatial discretizations of this system is studied for which the internal energy equation has a suitable form (without imbalance terms). An entropy balance equation is ...
Added: February 21, 2015
Mirkin B., Optimization Letters 2014
A review of the book in two perspectives: engineering design and data analysis. ...
Added: March 11, 2015
С.Д. Кузнецов, Труды Института системного программирования РАН 2017 Т. 29 № 2 С. 117-160
In October 2013, the eighth meeting of researchers in the field of databases was held. The first such meeting took place in February 1988, so that 25 years passed between them. After each meeting, a report was published containing an overview of the current state of the field and a research program for the nearest ...
Added: February 12, 2018
Voevodin V. V., Chulkevich R., Kostenetskiy P. et al., Supercomputing Frontiers and Innovations 2021 Vol. 8 No. 3 P. 82-103
Supercomputer technologies are in demand for solving many important and computationallyintensive tasks in various fields of science and technology. Therefore, it is not surprising that there are several dozen supercomputer centers only in Russia. However, the goals of creating such centers, as well as the range of tasks solved in them, can vary greatly, therefore the structure of supercomputers ...
Added: October 20, 2021
Shchur L., Ziganurova L., Lobachevskii Journal of Mathematics 2017 Vol. 38 No. 5 P. 967-970
We simulate model for evolution of local virtual time profile in conservative parallel discrete event the simulation (PDES) algorithm with long-range communication links. The main findings of simulation are that i) growth exponent depends logarithmically on the concentration p of long-range links; ii) utilisation of processing elements time decreases slowly with p. Thismeans that the ...
Added: September 25, 2017