<?xml version="1.0" encoding="UTF-8"?>
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en">
  <front>
    <journal-meta>
      <journal-id journal-id-type="issn">1561-5405</journal-id>
	    <journal-id journal-id-type="doi">10.24151/1561-5405</journal-id>	  
      <journal-id journal-id-type="publisher-id">Proceedings of Universities. Electronics</journal-id>
      <journal-title-group>
        <journal-title xml:lang="en">Scientifical and technical journal "Proceedings of Universities. Electronics"</journal-title>
        <trans-title-group xml:lang="ru">
          <trans-title>Научно-технический журнал «Известия высших учебных заведений. Электроника»</trans-title>
        </trans-title-group>        
      </journal-title-group>      
      <issn publication-format="print">1561-5405</issn>
      <issn publication-format="online">2587-9960</issn>
      <publisher>
        <publisher-name xml:lang="en">National Research University of Electronic Technology</publisher-name>
        <publisher-name xml:lang="ru">Национальный исследовательский университет "Московский институт электронной техники"</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>                                    
      
    <article-id pub-id-type="doi">10.24151/1561-5405-2018-23-2-161-172</article-id><article-id pub-id-type="udk">681.3</article-id><article-categories><subj-group><subject>Элементы интегральной электроники</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Main Trends in Development of Special-Purpose Manycore Processors</article-title><trans-title-group xml:lang="ru"><trans-title>Основные тенденции развития архитектур специализированных многоядерных процессоров</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><string-name xml:lang="ru">Елизаров Георгий Сергеевич </string-name><name-alternatives><name xml:lang="ru"><surname>Елизаров</surname><given-names>Георгий Сергеевич </given-names></name><name xml:lang="en"><surname>Sergeevich</surname><given-names>Elizarov Georgiy</given-names></name></name-alternatives><string-name xml:lang="en">Elizarov Georgiy Sergeevich</string-name><xref ref-type="aff" rid="AFF-1"/></contrib><contrib contrib-type="author"><string-name xml:lang="ru">Корнеев Виктор Владимирович </string-name><name-alternatives><name xml:lang="ru"><surname>Корнеев</surname><given-names>Виктор Владимирович </given-names></name><name xml:lang="en"><surname>Vladimirovich</surname><given-names>Korneev Viktor</given-names></name></name-alternatives><string-name xml:lang="en">Korneev Viktor Vladimirovich</string-name><xref ref-type="aff" rid="AFF-1"/></contrib><contrib contrib-type="author"><string-name xml:lang="ru">Тарасов Илья Евгеньевич </string-name><name-alternatives><name xml:lang="ru"><surname>Тарасов</surname><given-names>Илья Евгеньевич </given-names></name><name xml:lang="en"><surname>Evgenevich</surname><given-names>Tarasov Ilya</given-names></name></name-alternatives><string-name xml:lang="en">Tarasov Ilya Evgenevich</string-name><xref ref-type="aff" rid="AFF-1"/></contrib><contrib contrib-type="author"><string-name xml:lang="ru">Советов Петр Николаевич </string-name><name-alternatives><name xml:lang="ru"><surname>Советов</surname><given-names>Петр Николаевич </given-names></name><name xml:lang="en"><surname>Nikolaevich</surname><given-names>Sovetov Petr</given-names></name></name-alternatives><string-name xml:lang="en">Sovetov Petr Nikolaevich</string-name><xref ref-type="aff" rid="AFF-2"/></contrib><aff id="AFF-1" xml:lang="ru">ФГУП «НИИ «Квант», г. Москва, Россия</aff><aff id="AFF-2" xml:lang="ru">Московский государственный университет им. М.В. Ломоносова</aff></contrib-group><fpage>161</fpage><lpage>172</lpage><self-uri>http://ivuz-e.ru/issues/2-_2018/osnovnye_tendentsii_razvitiya_arkhitektur_spetsializirovannykh_mnogoyadernykh_protsessorov/</self-uri><self-uri content-type="pdf">http://ivuz-e.ru/download/2_2018_2176.pdf</self-uri><abstract xml:lang="en"><p>The power consumption in the up-to-date integrated circuits is significantly determined by the length of conductors delivering the instructions and the data to functional devices. This peculiarity of the integrated circuits is taken into account when developing the architectures of power-efficient processor chips. The manycore processors with the special-purpose architecture, designed for building the computer complexes to solve the problems in various subject areas have been considered. The trends in the architectures of manycore processors for searching for the approaches to designing the special-purpose computing complexes based on the new ASICs with massive-parallel architecture at the chip level have been revealed. It has been shown that an important role in improvement of the effectiveness of manycore processors belongs to the specialization of functional abilities of cores, which makes possible to refuse from the support of the operations, which require using computers with large area. The tendency of using the hierarchy of processor cores on a chip in the form of the local groups, connected with the on-chip network has been revealed, which corresponds to the requirements of the technological processors with 28 nm norms and less with limiting the area of synchronous step network. The specialization while building the high-effectiveness of manycore processors permits to decrease the area of the computer unit and, thus, to increase the number of the cores on chip. The local memory of cores, multiplication units and support of the floating point calculations are the main units, determining the chip area. Therefore, the designing of the architecture at early stages of the development must be executed considering the requirements of the subject area for these devices and types of operation.</p></abstract><trans-abstract xml:lang="ru"><p>Энергопотребление в современных интегральных схемах существенно определяется суммарной длиной проводников, доставляющих команды и данные к функциональным устройствам. Эта особенность интегральных схем учитывается при разработке архитектур энергоэффективных процессорных кристаллов. Рассмотрены многоядерные процессоры со специализированной архитектурой, предназначенные для построения вычислительных комплексов для решения задач в различных предметных областях. Выявлены тенденции в архитектурах многоядерных процессоров для поиска подходов к проектированию специализированных вычислительных комплексов на базе вновь разрабатываемых СБИС с массовым параллелизмом на уровне кристалла. Показано, что важную роль в повышении эффективности многоядерных процессоров играет специализация функциональных возможностей ядер, которая позволяет отказаться от поддержки операций, требующих применения вычислительных устройств с большой площадью. Установлено, что использование иерархии процессорных ядер на кристалле в виде локальных групп, связанных накристальной сетью, отвечает требованиям технологических процессов с нормами 28 нм и менее по ограничению площади синхронной тактовой сети. Специализация при построении высокоэффективных многоядерных процессоров позволяет сократить площадь вычислительного узла и увеличить таким образом количество ядер на кристалле. Локальная память ядер, блоки умножения и поддержки вычислений плавающей точки являются основными узлами, определяющими площадь кристалла. Поэтому проектирование архитектуры на ранних стадиях разработки следует проводить с учетом требований предметной области к этим устройствам и типам операций. Характеристики рассмотренных многоядерных процессоров подтверждают вывод о предпочтительности применения многоуровневой иерархии вычислительных узлов с асинхронной работой узлов верхних уровней иерархии.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>процессор</kwd><kwd>вычислительная система</kwd><kwd>параллельное вычисление</kwd></kwd-group><funding-group/></article-meta>
  </front>
  <body/>
  <back>
    <ref-list><ref id="B1"><label>1.</label><mixed-citation xml:lang="ru">Safaa S. Omran, Laith F. Jumma. Design of multithreading SHA-1 &amp;amp; SHA-2 MIPS proces-sor using FPGA // 8th International Conference on Information Technology (ICIT), 2017. – P. 632–637.</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation xml:lang="ru">Beaucamps P.-E., Kalray F. Demo: MPPA® manycore processor towards future ADAS sys-tem solutions // Conference on Design and Architectures for Signal and Image Processing (DASIP), 2016. – P. 243–244.</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation xml:lang="ru">Fang Gao, Zhangqin Huang, Zheng Wang, Shulong Wang. An object detection acceleration framework based on low-power heterogeneous manycore architecture // IEEE 3rd World Forum on Internet of Things (WF-IoT). – 2016. – P. 597–602.</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation xml:lang="ru">Faber L., Boryczko K. Efficient parallel execution of genetic algorithms on Epiphany manycore processor // Federated Conference on Computer Science and Information Systems (FedCSIS). – 2016. – P. 865–872.</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation xml:lang="ru">Andrews D., Platzner M. Programming models for reconfigurable manycore systems // 11th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC). – 2016. – P. 1–8.</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation xml:lang="ru">A 101.4 GOPS/W Reconfigurable and Scalable Control-Centric Embedded Processor for Do-main-Specific Applications / Yuxiang Huan, Ning Ma, Jia Mao et al. // IEEE Transactions on Circuits and Systems-I: Regular papers. – December 2016. – Vol. 63. – No. 12. – P. 2245–2256.</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation xml:lang="ru">Compiler Optimizations for Manycore Processors / Linhai Song, Min Feng, Nishkam Ravi et al. // 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). – 2014. – P. 659–671.</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation xml:lang="ru">Nan Ye, Ziyu Hao, Xianghui Xie. The Speedup Model for Manycore Processor // International Conference on Information Science and Cloud Computing Companion (ISCC-C). – 2013. – P. 469–474.</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation xml:lang="ru">Kirchhoff M., Kaptsova N., Streitpferdt D., Fengler W. Optimizing compiler for a specialized real-time floating point softcore processor // 8th Annual Industrial Automation and Electrome-chanical Engineering Conference (IEMECON). – 2017. – P. 181–188.</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation xml:lang="ru">A heterogeneous multicore crypto-processor with flexible long-word-length computation / Jun Han, Renfeng Dou, Lingyun Zeng et al. // IEEE Transactions on Circuits and Systems I: Regular Papers. – May 2015. – Vol. 62, Iss. 5. – P. 1372–1381.</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation xml:lang="ru">Chia-Hsiang Yang, Chun-Wei Chou, Chia-Shen Hsu, Chiao-En Chen. A systolic array based gtd processor with a parallel algorithm // IEEE Transactions on Circuits and Systems I: Regular Papers. – April 2015. – Vol. 62. – Iss. 4. – P. 1099–1108.</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation xml:lang="ru">Tony Nowatzki, Vinay Gangadhar, Karthikeyan Sankaralingam. A heterogeneous von neumann/explicit dataflow processor // IEEE Micro. – May-June 2016. – Vol. 36. – Iss. 3. – P. 20–30.</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation xml:lang="ru">Aashiha Priyadarshni L. Heterogeneous Multi core processors for improving the efficiency of Market basket analysis algorithm in data mining // International Journal of Computer Trends and Technology (IJCTT). – Sep. 2014. – Vol. 15(1). – P. 16–19.</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation xml:lang="ru">Vahid Lari, Alexandru Tanase, Frank Hannig, Jürgen Teich. Massively parallel processor architectures for resource-aware computing // 1st Workshop on Resource Awareness and Adaptivity in Multi-Core Computing (Racing 2014). – 2014. – URL: https://arxiv.org/abs/1405.2907 (дата обращения 20.07.2017).</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation xml:lang="ru">Exploiting heterogeneity for energy efficiency in chip multiprocessors /V. Saripalli, G. Sun, A. Mishra et al. // IEEE Journal on Emerging and Selected Topics in Circuits and Systems. – Jun. 2011. – Vol. 1. – No. 2. – P. 109–119.</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation xml:lang="ru">A framework for open tiled manycore system-on-chip / S. Wallentowitz, A. Lankes, A. Zaib et al. // In Field Programmable Logic and Applications (FPL), 2012 22nd International Confer-ence on. – 2012. – P. 535–538.</mixed-citation></ref><ref id="B17"><label>17.</label><mixed-citation xml:lang="ru">Mitsuishi T., Kaneda T., Torii S., Amano H. Implementing breadth-first search on a compact supercomputer suiren // Computing and Networking (CANDAR), 2016 Fourth International Symposium on: IEEE. – 2016. – С. 395–401.</mixed-citation></ref><ref id="B18"><label>18.</label><mixed-citation xml:lang="ru">Olofsson A. Epiphany-V: a 1024 processor 64-bit RISC system-on-chip //arXiv preprint arXiv:1610.01832. – 2016. – URL: https://arxiv.org/abs/1610.01832 (дата обращения: 20.07.2017).</mixed-citation></ref><ref id="B19"><label>19.</label><mixed-citation xml:lang="ru">KiloCore: A 32 nm 1000-processor array / B. Bohnenstiehl et al. // Proc. HotChips Symp. High-Perform. Chips. – 2016. – P. 63–69.</mixed-citation></ref><ref id="B20"><label>20.</label><mixed-citation xml:lang="ru">de Dinechin B.D. Kalray MPPA®: Massively parallel processor array: Revisiting DSP ac-celeration with the Kalray MPPA Manycore processor // Hot Chips 27 Symposium (HCS), 2015 IEEE: IEEE. – 2015. – P. 1–27.</mixed-citation></ref><ref id="B21"><label>21.</label><mixed-citation xml:lang="ru">An Energy-efficient processor architecture for embedded systems / James Balfour, William J. Dally, David Black-Schaffer et al. // IEEE Computer Architecture Letters. – January-June 2008. – Vol. 7. – No. 1. – Р. 29–32.</mixed-citation></ref><ref id="B22"><label>22.</label><mixed-citation xml:lang="ru">Dongarra J.J. Report on the Sunway TaihuLight System 24, 2016. – University of Tennessee Department of Electrical Engineering and Computer Science Tech Report UT-EECS-16-742. – URL: http://www.netlib.org/utk/people/JackDongarra/PAPERS/sunway-report-2016.pdf (дата обращения 20.07.2017).</mixed-citation></ref><ref id="B23"><label>23.</label><mixed-citation xml:lang="ru">TILE-Gx72 Product Brief: TILE-Gx72, PB041-Rel. 4.0 (14 February 2015) // Ezchip. – URL: http://www.tilera.com/files/drim__TILE-Gx8072_PB041-04_WEB_7666.pdf (дата об-ращения 20.07.2017).</mixed-citation></ref><ref id="B24"><label>24.</label><mixed-citation xml:lang="ru">Sodani A. Knights landing (KNL): 2nd Generation Intel® Xeon Phi processor // Hot Chips 27 Symposium (HCS), 2015 IEEE: IEEE. – 2015. – P. 1–24.</mixed-citation></ref><ref id="B25"><label>25.</label><mixed-citation xml:lang="ru">Dark silicon and the end of multicore scaling / H. Esmaeilzadeh, E. Blem, R.St. Amant et al. // ACM SIGARCH Computer Architecture News. – 2011. – Vol. 39. – No. 3. – P. 365–376.</mixed-citation></ref><ref id="B26"><label>26.</label><mixed-citation xml:lang="ru">Survey on Real-Time Networks-on-Chip / S. Hesham, J. Rettkowski, D. Gochringer et al. // IEEE Transactions on Parallel and Distributed Systems. – 2017. – Vol. 28. – No. 5. – P. 1500–1517.</mixed-citation></ref><ref id="B27"><label>27.</label><mixed-citation xml:lang="ru">Chung E.S., Milder P.A., Hoe J.C., Mai K. Single-chip heterogeneous computing: Does the future include custom logic, fpgas, and gpgpus? // Proc. of the 2010 43rd Annual IEE: ACM In-ternational Symposium on Microarchitecture. IEEE Computer Society. – 2010. – Р. 225–236.</mixed-citation></ref><ref id="B28"><label>28.</label><mixed-citation xml:lang="ru">Understanding sources of inefficiency in general-purpose chips / R. Hameed et al. //ACM SIGARCH Computer Architecture News. – 2010. – Vol. 38. – No. 3. – P. 37–47.</mixed-citation></ref><ref id="B29"><label>29.</label><mixed-citation xml:lang="ru">Bathen L.A. D., Dutt N.D. Software controlled memories for scalable many-core architec-tures // Embedded and Real-Time Computing Systems and Applications (RTCSA), 2012 IEEE 18th International Conference on. – 2012. – P. 1–10.</mixed-citation></ref><ref id="B30"><label>30.</label><mixed-citation xml:lang="ru">Паттерсон Д., Хеннесси Дж. Архитектура компьютера и проектирование компьютерных систем. – 4-е изд. – СПб.: Питер, 2012. – 784 c.</mixed-citation></ref><ref id="B31"><label>31.</label><mixed-citation xml:lang="ru">Гергель В.П. Высокопроизводительные вычисления для многопроцессорных много-ядерных систем: учебник. – М.: Изд-во Московского университета, 2010. – 544 с.</mixed-citation></ref><ref id="B32"><label>32.</label><mixed-citation xml:lang="ru">Каляев И.А., Левин И.И., Семерников Е.А., Шмойлов В.И. Реконфигурируемые мультиконвейерные вычислительные структуры / под общ. ред. И.А. Каляева. – Ростов н/Д: Изд-во ЮНЦ РАН, 2008. – 320 с.</mixed-citation></ref></ref-list>    
  </back>
</article>
