2687-0517 17 4 2024 1-89

RAR RUS 7-15 57225127284 0000-0001-9325-0356 ITMO University Tomilov Nikita programmer174@icloud.com

St. Petersburg, Russian Federation

58910796700 0009-0009-1470-7633 ITMO University Turov Vladimir firemoon@icloud.com

St. Petersburg, Russian Federation

Evaluating the performance of Java Vector API in vector embedding operations Hardware vector instructions are widely used to improve the performance of computations. The Java Vector API introduced in Java 16 allows using them portably on any platform supported by the Java Virtual Machine (JVM). In this paper, we evaluate performance benefits from rewriting typical vector search operations, such as computing distance between two vector embeddings, using the Java Vector API. We compare the performance of these vectorized implementations with semantically equivalent scalar code. Furthermore, we compare the Java Vector API with native C++ implementations, called from Java code via different Java-to-native interfaces, namely Java JNI, Project Panama (Foreign Function and Memory API), and manipulating Java JIT compiler via JVM CI and Nalim library. Benchmarking results suggest that in certain situations using Vector API can produce a measurable increase in performance of low-level operations, which can be translated into speedup of high-level algorithms such as Product Quantization. However, under certain scenarios, using Vector API is slower than relying on automatic vectorization provided by JVM, and most benchmarks suggest that invoking calculations implemented in C++ is faster even with all performance penalties incurred by native code invocations. Using techniques to lower these penalties, for example, by avoiding memory copy operations, can decrease the execution time by five times compared to Vector API and by ten times compared to plain Java code. However, in cases where using native code is prohibited, Vector API can still demonstrate a noticeable performance uplift, which can be beneficial for vector-related calculations in Java applications. 10.18721/JCSTCS.17401 004.422 vector representations Java JVM Java JNI Java JVM CI Project Panama native code invocation https://infocom.spbstu.ru/article/2024.83.1/

RAR RUS 16-34 Skiba Vladimir bauman@bmstu.ru 0000-0003-0644-1731 Petrenko Sergei petrenko.sa@talantiuspeh.ru Murzina Anastasiya myrzina.aa@talantiuspeh.ru Popova Kristina popova.kr@talantiuspeh.ru New types of threats and assessment of quantum stability of information systems in the field of foreign trade activity The introduction of technologies for performing customs operations through information systems without the direct participation of customs officials, as well as the evolving political situation and the adoption of sanctions against the Russian Federation by the United Stated and its allied states, significantly increase the importance of ensuring information security of customs authorities. The results obtained in the field of quantum informatics clearly demonstrate the high technological potential of quantum technologies. A cryptanalytically relevant or significant quantum computer can threaten civil and military communication systems, including information systems of customs authorities and individual participants in foreign trade activity. In this situation, there is a growing need to prepare in advance for possible collisions and take all necessary measures to protect against the mentioned quantum threat, including developing a plan for relevant priority measures. 10.18721/JCSTCS.17402 004.03 foreign trade activity information security quantum security threat quantum stability critical information infrastructure https://infocom.spbstu.ru/article/2024.83.2/

RAR RUS 35-45 Russian-Armenian University Avetisyan Vaan avahan@mail.ru

Yerevan, Republic of Armenia

On the possibilities of human emission and reception of high-frequency ultrasound This article suggests the possibility of the existence of an ultrasonic channel of information exchange in humans, similar to bats, dolphins, whales, etc. The possible frequency band of such a channel is estimated, resulting in frequencies from several hundred kilohertz to several hundred megahertz. In order to verify the assumption made and to minimize the efforts to find the frequency band of the supposed communication channel in such a wide frequency range, the corresponding experiment is considered and the results of previously performed scientific researches are discussed. The consequences of the presence of such a possibility in humans are considered and, on their basis, an attempt is made to explain some unusual phenomena inherent in humans. 10.18721/JCSTCS.17403 621 frequency band human unusual phenomena information exchange channel ultrasound emission https://infocom.spbstu.ru/article/2024.83.3/

RAR RUS 46-55 Peter the Great St. Petersburg Polytechnic University Tran Thanh Dat thanhdat140495@gmail.com

St. Petersburg, Russian Federation

Channel selection at input of narrowband direct-conversion receiver based on current-driven passive mixer Some issues when applying a Miller N-path filter to narrowband direct-conversion receiver (DCR) based on current-driven passive mixer and solutions to mitigate those issues are presented. The small impedances of the parallel LC circuit of low noise amplifier (LNA) at high frequencies cause undesirable effects: conversion gain reduction, noise figure increase and non-linear effects of the switches. A commutated network with the addition of resistors RFB1 and RFB2 is proposed to reduce the influence of those undesirable effects. The receiver is designed in the frequency range from 2.4 GHz to 2.6 GHz with 0.18 µm CMOS UMC technology. When applying the Miller N-path filter, although the conversion gain decreased by 3 dB and the noise figure increased by 1 dB, the in-band linearity (P1dB and IIP3) of the DRC increased by 6–9 dB compared to the DRC without the Miller N-path filter. 10.18721/JCSTCS.17404 621.3.049.774.2 narrowband direct-conversion receiver current-driven passive mixer Miller N-path filter channel selection low noise amplifier commutated network https://infocom.spbstu.ru/article/2024.83.4/

RAR RUS 56-63 Sazanov Arseniy arseny.sazanov@gmail.com Development of an algorithm for synchronization of traffic light controller programs This article develops an algorithm for synchronizing traffic light controller programs on one route in accordance with the general plan from the core. The relevance of the problem under consideration is described within the framework of improving the quality of functioning of adaptive and intelligent traffic control systems. An analysis of domestic and foreign modern solutions is carried out that ensure synchronization of traffic light modes in both local and distributed control systems of traffic light objects. Based on the necessary initial data and entered conditions that provide the required performance indicators of traffic control systems, an algorithm for synchronizing traffic controller programs is developed. For clarification, a general diagram of the synchronization algorithm is given. Conclusions are made on the results of testing the algorithm in real conditions and the prospects for further development of this study are described, including integration with existing control systems and the possibility of adaptation to various urban infrastructures. 10.18721/JCSTCS.17405 004.021 traffic light controller synchronization algorithm traffic light control control traffic management https://infocom.spbstu.ru/article/2024.83.5/

RAR RUS 64-77 Ustinova Valeria ustlera@list.ru Lutsenko Anton anton.lutsenko.03@mail.ru Shpak Adelina adelina.shpak@yandex.ru Mironenkov Grigorii mironenkov97@gmail.com Ivlev Vladislav nevidd@yandex.ru A method for finding the correspondence between a railway station model and its visual representation based on graphs The paper proposes a method for searching and comparing objects of the railway station model in the database format to the corresponding objects of the station visual representation in the SVG file format. The method is based on reducing the structure of a railway station to a directed asymmetric graph and using comparison algorithms to find correspondences between topological and actual characteristics of objects. The method includes comparing nodes and connections of the model graph with structural elements of the station visual representation. The paper also proposes a software tool that implements the proposed method. The software tool was tested in an experiment involving three employees, which revealed the average number of inconsistencies found, as well as the average time of the inconsistency search process before and after automation. The result of the research is that the method increases the accuracy of the process by two times and accelerates it by five times. 10.18721/JCSTCS.17406 004.052.42 graph model representation comparison of representations railway station visualization https://infocom.spbstu.ru/article/2024.83.6/

RAR RUS 78-89 Concern CSRI Elektropribor, JSC Kozlov Alexey kas573@yandex.ru

St. Petersburg, Russian Federation

Pilipko M.M. m_m_pilipko@rambler.ru Concern CSRI Elektropribor, JSC Tulaev Artyom artulaev@gmail.com

St. Petersburg, Russian Federation

Belyaev Yakov designcenter.spb@mail.ru Design process of the MASH 2-2 sigma-delta modulator This paper presents the design process of the cascaded (MASH) 2-2 sigma-delta modulator. For this purpose, several sigma-delta modulator topologies were studied at the system and schematic levels. Simulation at the system level was used to define the requirements for the operational transconductance amplifier (OTA), which is a part of the integrator. Sigma-delta modulators were designed using a 0.18 µm CMOS technology library. The influence of temperature swing, process variations and noise on the characteristics of second-order sigma-delta modulators was taken into account during simulation. As a result of the simulation, the optimal second-order topology was selected. This topology was used to design the cascaded (MASH) 2-2 sigma-delta modulator. The developed modulator has a resolution of 15.97 effective bits, a working frequency band of 20 kHz, consumes 12 mW of power at a supply voltage of 3.3 V. The occupied area of the circuit on the chip is 0.22 mm2. A device with such characteristics can be used in interfaces of micromechanical sensors. 10.18721/JCSTCS.17407 621.3.049.774.2 ADC sigma-delta OTA comparator topology https://infocom.spbstu.ru/article/2024.83.7/