TY - GEN
T1 - Towards Quality-Driven Approximate Software Generation for Accurate Hardware
T2 - 2020 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, CASES 2020
AU - Castro-Godinez, Jorge
AU - Shafique, Muhammad
AU - Henkel, Jorg
N1 - Funding Information:
ACKNOWLEDGMENT This work has been partially supported by the Costa Rica Institute of Technology and the OPRECOMP project through the 2019 Summer of Code initiative.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/20
Y1 - 2020/9/20
N2 - Many existing processor-based systems, especially using off-the-shelf components, cannot afford hardware modifications to embrace different approximate computing techniques proposed by the research community. In that case, it is mainly at the software level where error resiliency can be exploited efficiently. Although a multitude of approximate techniques can be applied at software level, they have been presented in isolation and little has been done to report their combined usage on different types of applications amenable to approximations. We present here AxSWGen, an automated quality-driven methodology to jointly explore and apply multiple approximate techniques to error-tolerant sections of applications. AxSWGen is implemented using LLVM compiler infrastructure. We present results of automated approximate software generated with AxSWGen and executed on a RISC-V processor (SiFive HiFive1 board), achieving up to 50% energy reduction for a 5% image degradation for an approximate Gaussian filter.
AB - Many existing processor-based systems, especially using off-the-shelf components, cannot afford hardware modifications to embrace different approximate computing techniques proposed by the research community. In that case, it is mainly at the software level where error resiliency can be exploited efficiently. Although a multitude of approximate techniques can be applied at software level, they have been presented in isolation and little has been done to report their combined usage on different types of applications amenable to approximations. We present here AxSWGen, an automated quality-driven methodology to jointly explore and apply multiple approximate techniques to error-tolerant sections of applications. AxSWGen is implemented using LLVM compiler infrastructure. We present results of automated approximate software generated with AxSWGen and executed on a RISC-V processor (SiFive HiFive1 board), achieving up to 50% energy reduction for a 5% image degradation for an approximate Gaussian filter.
KW - component
KW - formatting
KW - insert
KW - style
KW - styling
UR - http://www.scopus.com/inward/record.url?scp=85097299313&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097299313&partnerID=8YFLogxK
U2 - 10.1109/CASES51649.2020.9243814
DO - 10.1109/CASES51649.2020.9243814
M3 - Conference contribution
AN - SCOPUS:85097299313
T3 - Proceedings of the 2020 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, CASES 2020
SP - 12
EP - 14
BT - Proceedings of the 2020 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, CASES 2020
A2 - Mitra, Tulika
A2 - Gerstlauer, Andreas
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 20 September 2020 through 25 September 2020
ER -