?
Distance based prefetching algorithms for mining of the sporadic requests associations
Соколов А. П., Воеводкин В. С.
Modern storage systems intensively utilize data prefetching algorithms while processing sequencesof the read requests. Performance of the prefetching algorithm (for instance increase of the cache hitratio of the cache system – CHR) directly affects overall performance characteristics of the storagesystem (read latency, IOPS, etc.).There are widely known prefetching algorithms that are focused on the discovery of the sequential patterns in the stream of requests. This study examines a family of prefetching algorithms thatis focused on mining of the pseudo random (sporadic) patterns between read requests – sporadicprefetching algorithms. The key contribution of this paper is that it discovers a new, lightweightfamily of distance-based sporadic prefetching algorithms (DBSP) that outperforms the best previously known results on MSR traces collection. Another important contribution of this paper is athorough description of the procedure for comparing the performance of sporadic prefetchers.
Language:
English
Efremov A., Timofeev A., Ilyasov Y. et al., , in: ПАРАЛЛЕЛЬНЫЕ ВЫЧИСЛИТЕЛЬНЫЕ ТЕХНОЛОГИИ (ПаВТ’2025).: Издательский центр Южно-Уральского государственного университета, 2025. P. 56–81.
Accurate benchmarking is critical for selecting computing architectures optimized for machine learning (ML) tasks. Conventional benchmarks such as High-Performance Linpack (HPL) and High Performance Conjugate Gradients (HPCG) often fail to capture the diversity and complexity of modern ML workloads. This study investigates the correlation between hardware parameters (e.g., processor architecture, cache size, frequency) and ML ...
Added: April 4, 2026
Kostenetskiy P., Kozyrev V., Chulkevich R. et al., , in: Параллельные вычислительные технологии – XIX всероссийская научная конференция с международным участием, ПаВТ’2025, г. Москва, 8–10 апреля 2025 г. Короткие статьи и описания плакатов.: Челябинск: Издательский центр ЮУрГУ, 2025.
High-performance computing (HPC) has emerged as a critical tool for accelerating research across diverse scientific domains, enabling the efficient processing of large datasets and complex simulations. This article offers a comprehensive overview of the HPC resources available at HSE University in Moscow. We outline the university’s current HPC infrastructure, detailing its computational capabilities, software environments, ...
Added: May 28, 2025
Springer, 2025.
Added: February 21, 2025
Kostenetskiy P., Vyacheslav Kozyrev, Chulkevich R. et al., , in: 18th International Conference, PCT 2024, Chelyabinsk, Russia, April 2–4, 2024, Revised Selected Papers. Parallel Computational Technologies. Communications in Computer and Information Science (CCIS, volume 2241)Vol. 2241.: Springer, 2024. P. 49–64.
The detection of computational tasks that inefficiently utilize high-performance computing (HPC) resources is one of the major problems facing supercomputer centers. Such tasks can block valuable computational resources and slow down other supercomputer users’ computations. HPC TaskMaster, a task-performance monitoring system developed at the Higher School of Economics, addresses this issue by analyzing task metrics, ...
Added: December 20, 2024
Соколов А. П., Rumyantsev K., Yakovlev P. et al., Working papers by Cornell University. Series cond-mat.soft "arxiv.org" ( 2024
Handling vast amounts of data is crucial in today's world. The growth of high-performance computing has created a need for parallelization, particularly in the area of machine learning algorithms such as ANN (Approximate Nearest Neighbors). To improve the speed of these algorithms, it is important to optimize them for specific processor architectures. RISC-V (Reduced Instruction ...
Added: October 9, 2024
Gorshkov A., Rumyantsev K., Yakovlev P., Working papers by Cornell University. Series math "arxiv.org" 2024
Handling vast amounts of data is crucial in today's world. The growth of high-performance computing has created a need for parallelization, particularly in the area of machine learning algorithms such as ANN (Approximate Nearest Neighbors). To improve the speed of these algorithms, it is important to optimize them for specific processor architectures. RISC-V (Reduced Instruction ...
Added: October 8, 2024
Springer, 2023.
The two-volume set LNCS 14388 and 14389 constitutes the refereed proceedings of the 9th Russian Supercomputing Days International Conference (RuSCDays 2023) held in Moscow, Russia, during September 25-26, 2023.
The 44 full papers and 1 short paper presented in these proceedings were carefully reviewed and selected from 104 submissions. The papers have been organized in the ...
Added: January 26, 2024
Kolotinskii D., Alexei Timofeev, , in: Supercomputing: 8th Russian Supercomputing Days, RuSCDays 2022, Moscow, Russia, September 26–27, 2022, Revised Selected PapersVol. 13708.: Springer, 2022. P. 276–289.
According to the TOP-500 supercomputer ranking [27], since 2017, the share of supercomputers which have NVIDIA V100 and A100 graphics accelerators has been continuously growing, reaching 80% by November 2021 from the total number of supercomputers with accelerators and co-processors. This paper presents the results of an assessment of energy and economic efficiency, as well as ...
Added: May 16, 2023
Ferreira D., Joffrin E., Abduallev S. et al., Plasma Physics and Controlled Fusion 2021 Vol. 63 No. 8 Article 084006
In the fusion community, the use of high performance computing (HPC) has been mostly dominated by heavy-duty plasma simulations, such as those based on particle-in-cell and gyrokinetic codes. However, there has been a growing interest in applying machine learning for knowledge discovery on top of large amounts of experimental data collected from fusion devices. In ...
Added: January 31, 2023
Springer, 2022.
Added: December 19, 2022
IOP Publishing, 2021.
International Conference on Computer Simulation in Physics and beyond (CSP 2020) 12-16 October 2020, Moscow, Russia
Accepted papers received: 14 December 2020
Published online: 22 January 2021 ...
Added: January 20, 2022
IEEE, 2021.
2021 Workshop on Exascale MPI (ExaMPI)
DOI: 10.1109/ExaMPI54564.2021
14-14 Nov. 2021 ...
Added: January 20, 2022
Kostenetskiy P., Chulkevich R., Kozyrev V., Journal of Physics: Conference Series 2021 Vol. 1740 Article 012050
The National Research University Higher School of Economics launched its HPC cluster and created a new division named the Supercomputer Simulation Unit. Now the university HPC cluster occupies seventh place in rating the most powerful computers of the CIS TOP50. The HPC cluster uses to solve machine learning problems, population genomics, hydrodynamics, atomistic and continuous ...
Added: February 25, 2021
Starykh V., Mukhamedzyanov G., В кн.: Actual Problems of System and Software Engineering. Proceedings of the 6th International Conference Actual Problems of System and Software Engineering. Moscow, Russia, 12-14 November, 2019Vol. 2514.: CEUR Workshop Proceedings, 2019. С. 193–199.
The article deals with the solution of the problems of the formation and use of applied ontologies as a
Abstract: The purpose of this article - the forming of theoretical foundations, analysis of working tools and technologies for the construction of an information system that allows to optimize the scanning of IS for compliance with information ...
Added: February 2, 2021
Zelenkov Y., , in: Supercomputing. RuSCDays 2020. Communications in Computer and Information ScienceVol. 1331: 6th Russian Supercomputing Days, RuSCDays 2020, Moscow, Russia, September 21–22, 2020, Revised Selected Papers.: Switzerland: Springer, 2020. P. 401–412.
The intellectual structure of scientific discipline consists of a set of interacting topics. The evolution of these topics is the subject of special attention because it reflects the actual interest of researchers and stakeholders. This paper analyzes issues of High-Performance Computing (HPC) on the base of the formal topic modeling technique. Analyzing the abstracts of ...
Added: December 10, 2020
Springer, 2020.
This volume comprises the proceedings of the 13th International Conference on Parallel Processing and Applied Mathematics (PPAM 2019), which was held inBiałystok, Poland, September 8–11, 2019. It was organized by the Department of Computer and Information Science of the Częstochowa University of Technology together with Białystok University of Technology, under the patronage of the Committee ...
Added: October 14, 2020
Kostenetskiy P., В кн.: Суперкомпьютерные дни в России: Труды международной конференции (25-26 сентября 2017 г., г. Москва).: М.: Издательство МГУ, 2017. С. 876–881.
Платформа «Персональный виртуальный компьютер» (ПВК) - универсальное средство доступа для студентов и преподавателей в облако образовательных сервисов ВУЗа, построенная на базе вычислительного кластера «СКИФ Урал» и виртуальных машин. В качестве следующего этапа развития платформы (ПВК) в ЮУрГУ была выбрана тесная интеграция с приложениями суперкомпьютерного моделирования и высокопроизводительного вычислителя. В глазах пользователей произошло слияние системы ПВК ...
Added: March 27, 2020
Nolde D., Krylov N., Телегин П. Н. et al., Труды НИИСИ РАН 2018 Т. 7 № 4 С. 157–161
The performance of molecular dynamics software package Gromacs was measured on various
hardware: desktop computers, clusters based on x84_64 processors or many integrated core processors, and
heterogeneous system with gaming graphic cards or general purpose GPU systems. The optimal choice of hardware
for molecular dynamics simulations is discussed. ...
Added: February 10, 2020
Krylov N., Nolde D., Телегин П. Н. et al., Труды НИИСИ РАН 2018 Т. 8 № 6 С. 74–78
We studied the performance of two algorithms for processing results of molecular dynamics (MD)
simulation on modern computing platforms: calculations of radial distribution function (RDF) and energies. We found
that both algorithms effectively parallelize both on systems with shared memory and on clusters with distributed
memory. For processing the results of medium-sized MD systems, the parallelization efficiency of ...
Added: February 10, 2020
Chelyabinsk: IEEE, 2018.
The 2018 Global Smart Industry Conference is organized in order to exchange experience, promote discussion and presentation of research papers, and summarize results in development of innovative models, methods and technologies for the digital industry in universities, scientific and industrial associations of the Russian Federation as well as in foreign companies, and the experience of ...
Added: November 25, 2019
Nikolskiy V., Stegailov V., В кн.: Суперкомпьютерные дни в России: Труды международной конференции (25-26 сентября 2017 г., г. Москва).: М.: Издательство МГУ, 2017. С. 595–606.
В данной работе мы сравниваем возможности компиляторов по построению век-торизованного кода для современных процессоров ARMv8 и x86_64 и обсуждаемассемблерный алгоритм достижения максимальной производительности на обеихархитектурах. Представлен высокооптимизированный микротест, достигающиймаксимальную долю от пиковой производительности на процессоре ARMv8, в товремя как аналогичные программы для архитектуры x86_64 уже разработаны.Тесты были проведены на системе-на-чипе Nvidia Tegra X1 с четырьмя ...
Added: October 30, 2019