TY - GEN
T1 - Energy effective data migration methodology with memory access awareness for IoT devices
AU - Han, Yeonjoon
AU - Park, Sangsoo
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea funded by the Korean Government (NRF-2017R1D1A1B03030393).
Publisher Copyright:
© 2018 IEEE.
PY - 2018/6/8
Y1 - 2018/6/8
N2 - The rapid development of Internet of Things (IoT) technology has led to the appearance of many IoT devices in various industries, such as the home appliance and healthcare device industries. Most IoT devices are becoming minimized and are battery-operated because of the mobility of these devices. Thus, reducing the execution time and energy consumption has become an important problem, as has the need to extend the battery life. In this paper, we propose a data migration methodology that transfers read-dominant data from SRAM to the flash memory with the aim of improving the performance of small-scale embedded systems. We trace the memory access in the hybrid memory and analyze the memory access patterns to separate the read-dominant data from among the read/write data. The read-dominant data are then relocated to the flash memory sector. These procedures enabled us to reduce the energy consumption for accessing the data in SRAM. Experiments showed that, compared with placing data in SRAM, the proposed methodology achieved an improvement in the execution time, energy consumption, and battery life.
AB - The rapid development of Internet of Things (IoT) technology has led to the appearance of many IoT devices in various industries, such as the home appliance and healthcare device industries. Most IoT devices are becoming minimized and are battery-operated because of the mobility of these devices. Thus, reducing the execution time and energy consumption has become an important problem, as has the need to extend the battery life. In this paper, we propose a data migration methodology that transfers read-dominant data from SRAM to the flash memory with the aim of improving the performance of small-scale embedded systems. We trace the memory access in the hybrid memory and analyze the memory access patterns to separate the read-dominant data from among the read/write data. The read-dominant data are then relocated to the flash memory sector. These procedures enabled us to reduce the energy consumption for accessing the data in SRAM. Experiments showed that, compared with placing data in SRAM, the proposed methodology achieved an improvement in the execution time, energy consumption, and battery life.
KW - Battery life
KW - Data migration
KW - Embedded system
KW - Energy efficiency
KW - Hybrid memory
KW - Internet of Things
UR - http://www.scopus.com/inward/record.url?scp=85050004224&partnerID=8YFLogxK
U2 - 10.1109/ECTI-NCON.2018.8378281
DO - 10.1109/ECTI-NCON.2018.8378281
M3 - Conference contribution
AN - SCOPUS:85050004224
T3 - 1st International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI-NCON 2018
SP - 54
EP - 59
BT - 1st International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI-NCON 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI-NCON 2018
Y2 - 25 February 2018 through 28 February 2018
ER -