Systems and Means of Informatics
2021, Volume 31, Issue 3, pp 113-122
RECURRENT SIGNAL PROCESSOR HARDWARE IMPLEMENTATION
- Yu. A. Stepchenkov
- N. V. Morozov
- Yu. G. Diachenko
- D. V. Khilko
Abstract
The paper presents the results of hybrid architecture of recurrent multicore signal processor (HARMSP) hardware implementation as register transfer level VHDL-model and its prototype approbation on a development board with Intel Arria10 field-programmable gate array (FPGA). HARMSP consists of von-Neumann master processor at control architecture level and data-flow recurrent processor with four computing sections at operational level. Hardware HARMSP model is a complex of software or hardware control processor (CP) implementation and operational level VHDL-model. CAD Quartus (Intel) provides the software CP implementation on FPGA, whereas SoC FPGA on the development board contains the hardware CP implementation as dual-core Cortex-A9 processor.
[+] References (3)
- Shikunov, Yu., Yu. Stepchenkov, and D. Khilko. 2018. Recurrent mechanism developments in the data-flow computer architecture. IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering Proceedings. Piscataway, NJ: IEEE. 1413-1418. doi: 10.1109/EIConRus.2018.8317362.
- HAN Pilot Platform. Specifications. Available at: https://www.terasic.com.tw/cgi- bin/page/archive.pl?Language=English&CategoryNo=216&No=1133&PartNo=2 (accessed August 31, 2021). см русский вариант, он другой
- Intel Quartus Prime Software. Available at: https://www.intel.ru/content/www/ru/ ru/software/programmable/quartus-prime/download.html (accessed August 31, 2021).
[+] About this article
Title
RECURRENT SIGNAL PROCESSOR HARDWARE IMPLEMENTATION
Journal
Systems and Means of Informatics
Volume 31, Issue 3, pp 113-122
Cover Date
2021-11-10
DOI
10.14357/08696527210310
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
recurrent signal processor; multicore hybrid architecture; VHDL- model; FPGA
Authors
Yu. A. Stepchenkov , N. V. Morozov , Yu. G. Diachenko , and D. V. Khilko
Author Affiliations
Federal Research Center "Computer Science and Control", Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|