RUS  ENG
Full version
JOURNALS // Numerical methods and programming // Archive

Num. Meth. Prog., 2023 Volume 24, Issue 1, Pages 89–114 (Mi vmp1076)

This article is cited in 2 papers

Parallel software tools and technologies

Ontological analysis of the subject area of the Algo500 digital platform

Alexander S. Antonov, Rostislav V. Maier

Lomonosov Moscow State University, Research Computing Center, Moscow, Russia

Abstract: The Algo500 digital platform project is aimed at solving the problem of joint analysis of the properties of algorithms and features of supercomputer architectures. In this paper, based on the methodology of ontological analysis, concepts, models and metamodels of data are considered and proposed, approaches to the description of some concepts from the world of high-performance computing (HPC) are substantiated, new requirements for data models are established, which should ensure the fulfillment of the tasks set when creating the Algo500 platform.

Keywords: ontological analysis, Algo500, AlgoWiki, CompZoo, PerfData, problem, method, algorithm, implementation, supercomputer, rating, supercomputer experiment.

UDC: 517.968; 517.444; 519.642; 519.642.3

Received: 25.11.2022
Accepted: 13.02.2023

DOI: 10.26089/NumMet.v24r107



© Steklov Math. Inst. of RAS, 2024