RUS  ENG
Full version
JOURNALS // Program Systems: Theory and Applications // Archive

Program Systems: Theory and Applications, 2025 Volume 16, Issue 3, Pages 41–68 (Mi ps473)

Hardware, software and distributed supercomputer systems

Performance and fault tolerance of the ideal system network via additional parallelity

V. S. Podlazov

V.A. Trapeznikov Institute of Control Sciences of RAS, Moscow, Russia

Abstract: The article considers methods for increasing the performance of system networks by increasing their parallelism in two ways: using their copies and parallel channels in each copy. The article considers methods for constructing non-blocking system networks with direct channels of arbitrary size. The article considers methods for constructing non-blocking networks with a given number of parallel channels as networks with the structure of quasi-complete graphs. The article considers a method for constructing system networks of any size with a given number of parallel channels by using the corresponding number of their copies.

Key words and phrases: complete switch, direct channels, multiplexers and demultiplexers, multi-stage switch, conflictfree routing, non-blocking switch, static self-routing, quasi-complete graph with a given number of parallel channels, isomorphism of a quasi-complete graph and a symmetric block-design.

UDC: 004.724.2 + 004.272.43
BBK: 32.971.321.1

MSC: Primary 65Y05; Secondary 68Q10

Received: 24.03.2025
Accepted: 17.04.2025

DOI: 10.25209/2079-3316-2025-16-3-41-68



© Steklov Math. Inst. of RAS, 2026