2017

Conference proceedings

• J. Jang and H. Yang (corresponding author), “Executable Dataflow Benchmark Generation Technique for Multi-Core Embedded Systems,” in Proc. of Rapid System Prototyping (RSP), pp. 50-56 2017. [link] [bibtex]

  @inproceedings{Jang:2017:EDB:3130265.3130323,
   author = {Jang, Jeonggyu and Yang, Hoeseok},
   title = {Executable Dataflow Benchmark Generation Technique for Multi-core Embedded Systems},
   booktitle = {Proceedings of the 28th International Symposium on Rapid System Prototyping: Shortening the Path from Specification to Prototype},
   series = {RSP '17},
   year = {2017},
   isbn = {978-1-4503-5418-9},
   location = {Seoul, South Korea},
   pages = {50--56},
   numpages = {7},
   url = {http://doi.acm.org/10.1145/3130265.3130323},
   doi = {10.1145/3130265.3130323},
   acmid = {3130323},
   publisher = {ACM},
   address = {New York, NY, USA},
   keywords = {benchmark, dataflow, multi-core},
  } 

Journal articles

• S. Kim and H. Yang (corresponding author), “Dual-Port SDRAM Architecture for Low-Power Communication of Internet-of-Things Devices,” vol. 17, no. 6, pp 893-903, December 2017. [PDF][bibtex]

  @article{kim2017dual,
    title={Dual-port SDRAM Architecture for Low-power Communication of Internet-of-things Devices},
    author={Kim, Sungchan and Yang, Hoeseok},
    journal={JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE},
    volume={17},
    number={6},
    pages={893--903},
    year={2017}
  }

• S. Kim and H. Yang (corresponding author), “An Energy-Aware Runtime Management of Multi-Core Sensory Swarms,” Sensors, 17(9), August 2017. [link][bibtex]

  @Article{s17091955,
  AUTHOR = {Kim , Sungchan and Yang, Hoeseok},
  TITLE = {An Energy-Aware Runtime Management of Multi-Core Sensory Swarms},
  JOURNAL = {Sensors},
  VOLUME = {17},
  YEAR = {2017},
  NUMBER = {9},
  ARTICLE NUMBER = {1955},
  URL = {http://www.mdpi.com/1424-8220/17/9/1955},
  ISSN = {1424-8220},
  ABSTRACT = {In sensory swarms, minimizing energy consumption under performance constraint is one of the key objectives. One possible approach to this problem is to monitor application workload that is subject to change at runtime, and to adjust system configuration adaptively to satisfy the performance goal. As today’s sensory swarms are usually implemented using multi-core processors with adjustable clock frequency, we propose to monitor the CPU workload periodically and adjust the task-to-core allocation or clock frequency in an energy-efficient way in response to the workload variations. In doing so, we present an online heuristic that determines the most energy-efficient adjustment that satisfies the performance requirement. The proposed method is based on a simple yet effective energy model that is built upon performance prediction using IPC (instructions per cycle) measured online and power equation derived empirically. The use of IPC accounts for memory intensities of a given workload, enabling the accurate prediction of execution time. Hence, the model allows us to rapidly and accurately estimate the effect of the two control knobs, clock frequency adjustment and core allocation. The experiments show that the proposed technique delivers considerable energy saving of up to 45%compared to the state-of-the-art multi-core energy management technique.},
  DOI = {10.3390/s17091955}
  }