TY - JOUR
T1 - ECAX
T2 - Balancing error correction costs in approximate accelerators
AU - Castro-Godínez, Jorge
AU - Shafique, Muhammad
AU - Henkel, Jörg
N1 - Funding Information:
The authors thank Michael Käser for his support in exploring error correction at different granularity levels. This work was partially supported by the Costa Rica Institute of Technology.
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/10
Y1 - 2019/10
N2 - Approximate computing has emerged as a design paradigm amenable to error-tolerant applications. It enables trading the quality of results for efficiency improvement in terms of delay, power, and energy consumption under user-provided tolerable quality degradation. Approximate accelerators have been proposed to expedite frequently executing code sections of error-resilient applications while meeting a defined quality level. However, these accelerators may produce unacceptable errors at run time if the input data changes or dynamic adjustments are made for a defined output quality constraint. State-of-the-art approaches in approximate computing address this issue by correctly re-computing those accelerator invocations that produce unacceptable errors; this is achieved by using the host processor or an alternate exact accelerator, which is activated on-demand. Nevertheless, such approaches can nullify the benefits of approximate computing, especially when input data variations are high at run time and errors due to approximations are above a tolerable threshold. As a robust and general solution to this problem, we propose ECAx, a novel methodology to explore low-overhead error correction in approximate accelerators by selectively correcting most significant errors, in terms of their magnitude, without losing the gains of approximations. We particularly consider the case of approximate accelerators built with approximate functional units such as approximate adders. Our novel methodology reduces the required exact re-computations on the host processor, achieving up to 20% performance gain compared to state-of-the-art approaches.
AB - Approximate computing has emerged as a design paradigm amenable to error-tolerant applications. It enables trading the quality of results for efficiency improvement in terms of delay, power, and energy consumption under user-provided tolerable quality degradation. Approximate accelerators have been proposed to expedite frequently executing code sections of error-resilient applications while meeting a defined quality level. However, these accelerators may produce unacceptable errors at run time if the input data changes or dynamic adjustments are made for a defined output quality constraint. State-of-the-art approaches in approximate computing address this issue by correctly re-computing those accelerator invocations that produce unacceptable errors; this is achieved by using the host processor or an alternate exact accelerator, which is activated on-demand. Nevertheless, such approaches can nullify the benefits of approximate computing, especially when input data variations are high at run time and errors due to approximations are above a tolerable threshold. As a robust and general solution to this problem, we propose ECAx, a novel methodology to explore low-overhead error correction in approximate accelerators by selectively correcting most significant errors, in terms of their magnitude, without losing the gains of approximations. We particularly consider the case of approximate accelerators built with approximate functional units such as approximate adders. Our novel methodology reduces the required exact re-computations on the host processor, achieving up to 20% performance gain compared to state-of-the-art approaches.
KW - Approximate computing
UR - http://www.scopus.com/inward/record.url?scp=85073162455&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073162455&partnerID=8YFLogxK
U2 - 10.1145/3358179
DO - 10.1145/3358179
M3 - Article
AN - SCOPUS:85073162455
SN - 1539-9087
VL - 18
JO - ACM Transactions on Embedded Computing Systems
JF - ACM Transactions on Embedded Computing Systems
IS - 5s
M1 - a48
ER -