D. V. Lulyava

D. V. Lulyava

Auto-generated profile, based on publicly available information

D. V. Lulyava

MIREA – Russian Technological University

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 May 2024 in Russian Technological Journal
Verified
Journal Article
Open access
PDF file
ITIlya Tarasov
Ilya Tarasov
PSPeter N. Sovietov
Peter N. Sovietov
DLD. V. Lulyava
D. V. Lulyava
DMD. I. Mirzoyan
D. I. Mirzoyan
Objectives. Following the completion of development stages due to transistor scaling (Dennard’s law) and an increased number of general-purpose processor cores (limited by Amdahl’s law), further improvements in the performance of computing systems naturally proceeds to the stage of developing specialized computing subsystems for performing specific tasks within a limited computational subclass. The development of such systems requires both the selection of the relevant high-demand tasks and the application of design techniques for achieving desired indicators within the developed specializations at very large scales of integration. The purpose of the present work is to develop a methodology for designing specialized computing systems based on the joint optimization of hardware and software in relation to a selected subclass of problems.Methods. The research is based on various methods for designing digital systems.Results. Approaches to the analysis of computational problems involving the construction of a computational graph abstracted from the computing platform, but limited by a set of architectural solutions, are considered. The proposed design methodology based on a register transfer level (RTL) representation synthesizer of a computing device is limited to individual computing architectures for which the relevant circuit is synthesized and optimized based on a high-level input description of the algorithm. Among computing node architectures, a synchronous pipeline and a processor core with a tree-like arithmetic-logical unit are considered. The efficiency of a computing system can be increased by balancing the pipeline based on estimates of the technological basis, and for the processor—based on optimizing the set of operations, which is performed based on the analysis of the abstract syntax tree graph with its optimal coverage by subgraphs corresponding to the structure of the arithmetic logic unit.Conclusions. The considered development approaches are suitable for accelerating the process of designing specialized computing systems with a massively parallel architecture based on pipeline or processor computing nodes.

5 June 2025 in Russian Technological Journal
Verified
Journal Article
Open access
PDF file
ITIlya Tarasov
Ilya Tarasov
PSPeter N. Sovietov
Peter N. Sovietov
DLD. V. Lulyava
D. V. Lulyava
NDN. A. Duksin
N. A. Duksin
Objectives. Pipelining is an effective method for increasing the clock frequency of digital circuits. At the same time, balancing the pipeline stages during circuit synthesis at the register transfer level does not yet guarantee a balanced topological implementation of such a pipeline in terms of signal propagation delays according to the selected technological basis. This is due to the specifics of the algorithms for placing and routing components of digital devices, which are not capable of optimizing solutions in a strict mathematical sense in an acceptable time. In practice, approaches for developing digital devices combine manual control of topological constraints that set general rules for placing components with automatic optimization for localized fragments of the circuit are used to obtain results close to optimal. Pipeline circuits are based on a simple connection diagram of individual stages to demonstrate the effect of using topological design constraints on their example. On the basis of pipeline structures, a number of algorithms can be implemented to effectively complement programmable processor devices and provide hardware acceleration of some tasks. The present work develops methodological recommendations for managing topological design constraints in the implementation of pipeline computing structures based on programmable logic devices (PLD) with field-programmable gate array (FPGA) architecture.Methods. The work is based on accepted methods for designing and modeling digital systems.Results. Based on the analysis, modifications to a 32-bit CORDIC transcendental function computation pipeline were developed. By adding design constraints on the placement of register groups corresponding to the pipeline stages a significant increase in the clock frequency can be achieved as compared to automatic placement to reduce the running time of the tracing algorithms. The resulting effect is systematically reproduced in several implemented versions of the pipeline. Conclusions. The presented recommendations can be used to control the clock frequency and number of stages of pipeline computing structures while simultaneously reducing the time of one iteration and routing of a module based on PLD with FPGA architecture.