Author:
Selivanova M V,Tyncherov K T,Ikhsanova F A,Kalmykov I A,Olenev A A
Abstract
Abstract
The paper studies the problem of determining the lower boundary of number correction speed in computing systems operating in the basis of non-positional arithmetic of residual classes. The topicality of the problem is necessitated by the search of methods allowing reducing the time for digital processing of signals in non-positional neuroprocessors. The study considers several variants of error correction with a single and multiple control bases of the residue system. The calculations were performed that allowed determining the time necessary for zeroing operation. The method of paired zeroing of numbers in a system of residual classes was modified. It was demonstrated that the suggested solutions allow appreciably reducing the time consumption by digital processing of signals in neuroprocessors destined for operations of summation and multiplication.
Subject
General Physics and Astronomy
Reference10 articles.
1. A method for increasing the reliability of verification of data represent-ed in a residue number system;Krasnobayev;Cybern. Syst. Anal+,2014
2. The use of redundant modular codes for improving the fault tolerance of special processors for digital signal processing;Makarova,2017
3. Method of increasing the reliability of telemetric well information transmitted by the wireless communication channel;Tyncherov;Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering,2018
4. Modular wavelet approach for reinforced plastic pipelines operation quality evaluation;Tyncherov,2017
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献