Approximating Outside the Processor

Energy usage in many contemporary computing systems is constrained by factors other than computation. The major components of energy use include transferring data onchip in high-performance systems, activating and accessing sensor and display interfaces in wearable and mobile systems, and accessing and refreshing memories in all system types. The relative proportion of energy usage due to factors outside computation will only grow in the future. This is because many of the factors in question are functions of system-level interconnects and packaging, which do not benefit directly from semiconductor technology scaling. There is an opportunity to improve the energy-efficiency of computing systems by exploiting their tolerance to inaccuracy, imprecision, and unreliability. But, seizing this opportunity requires approximating outside the processor, applying approximation to sensors and output devices, instead of only focusing on the operations in computations. This observation is particularly relevant for embedded, wearable, and mobile systems, which form the dominant (and growing) majority of the world’s computing devices.

[1]  Parthasarathy Ranganathan,et al.  Energy-aware user interfaces: an evaluation of user acceptance , 2004, CHI.

[2]  Martin C. Rinard,et al.  Verifying quantitative reliability for programs that execute on unreliable hardware , 2013, OOPSLA.

[3]  Henry Hoffmann,et al.  Managing performance vs. accuracy trade-offs with loop perforation , 2011, ESEC/FSE '11.

[4]  Naehyuck Chang,et al.  Dynamic voltage scaling of OLED displays , 2011, 2011 48th ACM/EDAC/IEEE Design Automation Conference (DAC).

[5]  Martin C. Rinard,et al.  Lax: Driver Interfaces for Approximate Sensor Device Access , 2015, HotOS.

[6]  Luis Ceze,et al.  Architecture support for disciplined approximate programming , 2012, ASPLOS XVII.

[7]  Daniel Weiskopf,et al.  Energy Aware Color Sets , 2009, Comput. Graph. Forum.

[8]  Lin Zhong,et al.  Power-saving color transformation of mobile graphical user interfaces on OLED-based displays , 2009, ISLPED.

[9]  Diana Marculescu,et al.  A Programming Model and Language Implementation for Concurrent Failure-Prone Hardware , 2006 .

[10]  Ding Li,et al.  Making web applications more energy efficient for OLED smartphones , 2014, ICSE.

[11]  Martin Rinard,et al.  Value-Deviation-Bounded Serial Data Encoding for Energy-Efficient Approximate Communication , 2015 .

[12]  Yiran Chen,et al.  Online OLED dynamic voltage scaling for video streaming applications on mobile devices , 2013, 2013 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS).

[13]  Archan Misra,et al.  FOCUS: a usable & effective approach to OLED display power management , 2013, UbiComp.

[14]  P. Stanley-Marbell,et al.  Encoding efficiency of digital number representations under deviation constraints , 2009, 2009 IEEE Information Theory Workshop.

[15]  Lin Zhong,et al.  Chameleon: A Color-Adaptive Web Browser for Mobile OLED Displays , 2012, IEEE Transactions on Mobile Computing.

[16]  Dan Grossman,et al.  EnerJ: approximate data types for safe and general low-power computation , 2011, PLDI '11.