TY - JOUR
T1 - X-CGRA
T2 - An Energy-Efficient Approximate Coarse-Grained Reconfigurable Architecture
AU - Akbari, Omid
AU - Kamal, Mehdi
AU - Afzali-Kusha, Ali
AU - Pedram, Massoud
AU - Shafique, Muhammad
N1 - Funding Information:
Manuscript received January 17, 2019; revised April 10, 2019 and June 26, 2019; accepted August 14, 2019. Date of publication August 27, 2019; date of current version September 18, 2020. This work was supported in part by the German Research Foundation (DFG) as part of the priority program “Dependable Embedded Systems” (SPP 1500 - http://spp1500.itec.kit.edu). This article was recommended by Associate Editor X. Jiao. (Corresponding author: Mehdi Kamal.) O. Akbari was with the School of Electrical and Computer Engineering, University of Tehran, Tehran 14395-515, Iran. He is now with the School of Electrical and Computer Engineering, Tarbiat Modares University, Tehran 14115-111, Iran (e-mail: o.akbari@modares.ac.ir).
Publisher Copyright:
© 1982-2012 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/10
Y1 - 2020/10
N2 - In this article, we present an energy-efficient approximate CGRA (X-CGRA). Instead of conventional exact arithmetic units, it employs configurable approximate adders and multipliers in the so-called quality-scalable processing elements (QSPEs). Furthermore, the structure and functionality of the other architectural components, like context memory, are modified based on the quality-scalable operating modes of the QSPEs. The quality reconfigurability of the X-CGRA makes it amenable for both error-resilient and nonresilient applications. To map the applications on the X-CGRA, a mapping technique is proposed that efficiently utilizes the QSPEs and selects appropriate approximation modes in order to lower the energy consumption while satisfying a user-defined quality constraint. We evaluate the efficacy of our X-CGRA for several benchmark applications from different domains, including image/video processing, signal processing, and scientific computations. Different sizes of X-CGRA are synthesized using a 15-nm FinFET technology. For these benchmarks, the results indicate energy consumption reduction of up to 3.21× compared to those of a typical exact CGRA, at the cost of 4% quality loss.
AB - In this article, we present an energy-efficient approximate CGRA (X-CGRA). Instead of conventional exact arithmetic units, it employs configurable approximate adders and multipliers in the so-called quality-scalable processing elements (QSPEs). Furthermore, the structure and functionality of the other architectural components, like context memory, are modified based on the quality-scalable operating modes of the QSPEs. The quality reconfigurability of the X-CGRA makes it amenable for both error-resilient and nonresilient applications. To map the applications on the X-CGRA, a mapping technique is proposed that efficiently utilizes the QSPEs and selects appropriate approximation modes in order to lower the energy consumption while satisfying a user-defined quality constraint. We evaluate the efficacy of our X-CGRA for several benchmark applications from different domains, including image/video processing, signal processing, and scientific computations. Different sizes of X-CGRA are synthesized using a 15-nm FinFET technology. For these benchmarks, the results indicate energy consumption reduction of up to 3.21× compared to those of a typical exact CGRA, at the cost of 4% quality loss.
KW - Adaptivity
KW - approximate computing
KW - coarsegrained reconfigurable architecture (CGRA)
KW - energy efficiency
KW - error resilience
KW - mapping
KW - quality of service (QoS)
UR - http://www.scopus.com/inward/record.url?scp=85071662897&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071662897&partnerID=8YFLogxK
U2 - 10.1109/TCAD.2019.2937738
DO - 10.1109/TCAD.2019.2937738
M3 - Article
AN - SCOPUS:85071662897
SN - 0278-0070
VL - 39
SP - 2558
EP - 2571
JO - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
JF - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
IS - 10
M1 - 8815818
ER -