17th INTERNATIONAL FORUM ON MPSoC
for software-defined hardware
For further information, please send email to Frédéric Pétrot
Accuracy-energy trade-off with dynamic adequate operators using run-time back bias
Adequate computing is an emerging paradigm in which the accuracy of computation results can be traded against, e.g., savings in energy, improvement in performance, at run-time. This work presents the impact of adequate operators on several applications, e.g., graphics, image processing. These operators are constructed in an automatic way by designing their data-path with the threshold voltage scaling as a knob to dynamically control the power/accuracy tradeoff. Results indicate significant energy saving potential when employing these operators.
Anca Molnos received her M.Sc. degree in computer science from the "Politehnica" University of Bucharest, Romania and the Ph.D. degree in computer engineering from the Delft University of Technology, The Netherlands, in 2001 and 2009, respectively. Between 2006 and 2009 she was senior scientist at NXP Semiconductors, The Netherlands, working on low-power multi-processors and distributed real-time systems. From 2009 to 2012 she was a researcher with the Delft University of Technology, working on embedded multi-core resource management for low-power and quality of service. In 2013 she joined CEA LETI, where her research focuses on developing adaptive, energy-aware software, variability management frameworks, and adequate computing methods.