Body Bias Domain Partitioning Size Exploration for a Coarse Grained Reconfigurable Accelerator

Yusuke MATSUSHITA; Hayate OKUHARA; Koichiro MASUYAMA; Yu FUJITA; Ryuta KAWANO; Hideharu AMANO

doi:10.1587/transinf.2017PAP0013

Body Bias Domain Partitioning Size Exploration for a Coarse Grained Reconfigurable Accelerator

Yusuke MATSUSHITA, Hayate OKUHARA, Koichiro MASUYAMA, Yu FUJITA, Ryuta KAWANO, Hideharu AMANO

Full Text Views

0

Share
Cite this

Summary :

Body biasing can be used to control the leakage power and performance by changing the threshold voltage of transistors after fabrication. Especially, a new process called Silicon-On-Thin Box (SOTB) CMOS can control their balance widely. When it is applied to a Coarse Grained Reconfigurable Array (CGRA), the leakage power can be much reduced by precise bias control with small domain size including a small number of PEs. On the other hand, the area overhead for separating power domain and delivering a lot of wires for body bias voltage supply increases. This paper explores the grain of domain size of an energy efficient CGRA called CMA (Cool Mega Array). By using Genetic Algorithm based body bias assignment method, the leakage reduction of various grain size was evaluated. As a result, a domain with 2x1 PEs achieved about 40% power reduction with a 6% area overhead. It has appeared that a combination of three body bias voltages; zero bias, weak reverse bias and strong reverse bias can achieve the optimal leakage reduction and area overhead balance in most cases.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.12 pp.2828-2836

Publication Date: 2017/12/01

Publicized: 2017/07/14

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017PAP0013

Type of Manuscript: Special Section PAPER (Special Section on Parallel and Distributed Computing and Networking)

Category: Architecture

Authors

Yusuke MATSUSHITA
  Keio University
Hayate OKUHARA
  Keio University
Koichiro MASUYAMA
  Keio University
Yu FUJITA
  Keio University
Ryuta KAWANO
  Keio University
Hideharu AMANO
  Keio University

Keyword

CGRA, body bias, power reduction, cool mega array

Cite this

Copy

Yusuke MATSUSHITA, Hayate OKUHARA, Koichiro MASUYAMA, Yu FUJITA, Ryuta KAWANO, Hideharu AMANO, "Body Bias Domain Partitioning Size Exploration for a Coarse Grained Reconfigurable Accelerator" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 12, pp. 2828-2836, December 2017, doi: 10.1587/transinf.2017PAP0013.
Abstract: Body biasing can be used to control the leakage power and performance by changing the threshold voltage of transistors after fabrication. Especially, a new process called Silicon-On-Thin Box (SOTB) CMOS can control their balance widely. When it is applied to a Coarse Grained Reconfigurable Array (CGRA), the leakage power can be much reduced by precise bias control with small domain size including a small number of PEs. On the other hand, the area overhead for separating power domain and delivering a lot of wires for body bias voltage supply increases. This paper explores the grain of domain size of an energy efficient CGRA called CMA (Cool Mega Array). By using Genetic Algorithm based body bias assignment method, the leakage reduction of various grain size was evaluated. As a result, a domain with 2x1 PEs achieved about 40% power reduction with a 6% area overhead. It has appeared that a combination of three body bias voltages; zero bias, weak reverse bias and strong reverse bias can achieve the optimal leakage reduction and area overhead balance in most cases.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2017PAP0013/_p

Copy

@ARTICLE{e100-d_12_2828,
author={Yusuke MATSUSHITA, Hayate OKUHARA, Koichiro MASUYAMA, Yu FUJITA, Ryuta KAWANO, Hideharu AMANO, },
journal={IEICE TRANSACTIONS on Information},
title={Body Bias Domain Partitioning Size Exploration for a Coarse Grained Reconfigurable Accelerator},
year={2017},
volume={E100-D},
number={12},
pages={2828-2836},
abstract={Body biasing can be used to control the leakage power and performance by changing the threshold voltage of transistors after fabrication. Especially, a new process called Silicon-On-Thin Box (SOTB) CMOS can control their balance widely. When it is applied to a Coarse Grained Reconfigurable Array (CGRA), the leakage power can be much reduced by precise bias control with small domain size including a small number of PEs. On the other hand, the area overhead for separating power domain and delivering a lot of wires for body bias voltage supply increases. This paper explores the grain of domain size of an energy efficient CGRA called CMA (Cool Mega Array). By using Genetic Algorithm based body bias assignment method, the leakage reduction of various grain size was evaluated. As a result, a domain with 2x1 PEs achieved about 40% power reduction with a 6% area overhead. It has appeared that a combination of three body bias voltages; zero bias, weak reverse bias and strong reverse bias can achieve the optimal leakage reduction and area overhead balance in most cases.},
keywords={},
doi={10.1587/transinf.2017PAP0013},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Body Bias Domain Partitioning Size Exploration for a Coarse Grained Reconfigurable Accelerator
T2 - IEICE TRANSACTIONS on Information
SP - 2828
EP - 2836
AU - Yusuke MATSUSHITA
AU - Hayate OKUHARA
AU - Koichiro MASUYAMA
AU - Yu FUJITA
AU - Ryuta KAWANO
AU - Hideharu AMANO
PY - 2017
DO - 10.1587/transinf.2017PAP0013
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2017
AB - Body biasing can be used to control the leakage power and performance by changing the threshold voltage of transistors after fabrication. Especially, a new process called Silicon-On-Thin Box (SOTB) CMOS can control their balance widely. When it is applied to a Coarse Grained Reconfigurable Array (CGRA), the leakage power can be much reduced by precise bias control with small domain size including a small number of PEs. On the other hand, the area overhead for separating power domain and delivering a lot of wires for body bias voltage supply increases. This paper explores the grain of domain size of an energy efficient CGRA called CMA (Cool Mega Array). By using Genetic Algorithm based body bias assignment method, the leakage reduction of various grain size was evaluated. As a result, a domain with 2x1 PEs achieved about 40% power reduction with a 6% area overhead. It has appeared that a combination of three body bias voltages; zero bias, weak reverse bias and strong reverse bias can achieve the optimal leakage reduction and area overhead balance in most cases.
ER -