Mian Dong

Power modeling of graphical user interfaces on OLED displays

Emerging organic light-emitting diode (OLED)-based displays obviate external lighting; and consume drastically different power when displaying different colors, due to their emissive nature. This creates a pressing need for OLED display power models for system energy management, optimization as well as energy-efficient GUI design, given the display content or even the graphical user interface (GUI) code. In this work, we present a comprehensive treatment of power modeling of OLED displays, providing models that estimate power consumption based on pixel, image, and code, respectively. These models feature various tradeoffs between computation efficiency and accuracy so that they can be employed in different layers of a mobile system. We validate the proposed models using a commercial QVGA OLED module. For example, our statistical learning-based image-level model reduces computation by 1600 times while keeping the error below 10%, compared to the more accurate pixel-level model.

Power Modeling and Optimization for OLED Displays

Emerging organic light-emitting diode (OLED)-based displays obviate external lighting, and consume drastically different power when displaying different colors, due to their emissive nature. This creates a pressing need for OLED display power models for system energy management, optimization as well as energy-efficient GUI design, given the display content or even the graphical-user interface (GUI) code. In this work, we study this opportunity using commercial QVGA OLED displays and user studies. We first present a comprehensive treatment of power modeling of OLED displays, providing models that estimate power consumption based on pixel, image, and code, respectively. These models feature various tradeoffs between computation efficiency and accuracy so that they can be employed in different layers of a mobile system. We validate the proposed models using a commercial QVGA OLED module and a mobile device with a QVGA OLED display. Then, based on the models, we propose techniques that adapt GUIs based on existing mechanisms as well as arbitrarily under usability constraints. Our measurement and user studies show that more than 75 percent display power reduction can be achieved with user acceptance.

Power-saving color transformation of mobile graphical user interfaces on OLED-based displays

Emerging organic light-emitting diode (OLED)-based displays have drastically different power consumption when displaying different colors, due to their emissive nature. They bring a new opportunity for power saving by transforming GUI colors. In this work, we study this opportunity using a commercial-off-the-shelf QVGA OLED module and user studies. We present techniques that adapt GUIs based on existing mechanisms as well as arbitrarily under usability constraints. Our measurement and user studies show that more than 75% display power reduction can be achieved with user acceptance.

Characterizing the Performance and Power Consumption of 3D Mobile Games

A preliminary study using the Quake 3 and XRace games as benchmarks on three mainstream mobile system-on-chip architectures reveals that the geometry stage is the main bottleneck in 3D mobile games and confirms that game logic significantly affects power consumption.

Rethink energy accounting with cooperative game theory

Energy accounting determines how much a software principal contributes to the total system energy consumption. It is the foundation for evaluating software and for operating system based energy management. While various energy accounting policies have been tried, there is no known way to evaluate them directly simply because it is hard to track all hardware usage by software in a heterogeneous multicore system like modern smartphones and tablets. In this work, we argue that energy accounting should be formulated as a cooperative game and that the Shapley value provides the ultimate ground truth for energy accounting policies. We reveal the important flaws of existing energy accounting policies based on the Shapley value theory and provide Shapley value-based energy accounting, a practical approximation of the Shapley value, for battery-powered mobile systems. We evaluate this approximation against existing energy accounting policies in two ways: (i) how well they identify the top energy consuming applications, and (ii) how effective they are in system energy management. Using a prototype based on Texas Instruments Pandaboard and smartphone workload, we experimentally demonstrate existing energy accounting policies can deviate by 400% in attributing energy consumption to running applications and can be up to 25% less effective in system energy management when compared to Shapley value-based energy accounting.

Nanowire Crossbar Logic and Standard Cell-Based Integration

Nanowire crossbar is one of the most promising circuit solutions for nanoelectronics. However, it is still unclear whether or how they can be competitive in implementing logic circuits, as compared to their MOSFET counterparts. We analyze nanowire crossbars in area, speed, and power, in comparison with their MOSFET counterparts. We show nanowire crossbars do not scale well in terms of logic density and speed. To achieve performance close to their MOSFET counterparts, crossbar circuits need faster field-effect transistors (FETs) to compensate the high resistance of nanowires. Motivated by the analysis and comparative study, we propose a crossbar cells design based on judicious use of silicon nanowires. The crossbar cell is compatible with the conventional MOSFET fabrication and design methodologies, in particular, standard cell-based integrated circuit design. We evaluate logic circuits synthesized with crossbar cells and MOSFET cells based on the MCNC91 benchmark. The results show that crossbar cells can provide a density advantage of more than four times over the traditional MOSFET circuits with the same process technology, while achieving close performance and consuming less than one third power.

Challenges to Crossbar Integration of Nanoscale Two-Terminal Symmetric Memory Devices

Crossbar is the most efficient architecture to organize memory devices into dense, large-scale arrays. Emerging nanotechnology promises two-terminal, symmetric memory devices of superior electrical properties. In this work, however, we show that these two-terminal, symmetric devices impose grave challenges to the crossbar-based memory organization. First, we prove that conventional crossbar organization will not work for such symmetric devices. Second, we propose a revised crossbar organization that does work for such devices. However, diodes or switches must be employed to convert such devices into asymmetrical devices in order to avoid considerable energy cost, which can significantly discount their advantage over conventional asymmetrical devices. Third, we demonstrate that there is significant difference in delay and power consumption for accessing a memory device of different contents, i.e., 0 or 1. Such difference constitutes a performance bottleneck of crossbar- based integration of resistive memory devices.

Logic synthesis with nanowire crossbar: reality check and standard cell-based integration

Nanowire crossbar is one of the most promising circuit solutions for nanoelectronics. We show nanowire crossbars do not scale well in terms of logic density and speed. We consequently propose a crossbar cell design based on judicious use of silicon nanowire crossbars with microscale pitches and small dimensions. The crossbar cell is compatible with the conventional MOSFET fabrication and standard cell-based integration. We evaluate logic circuits using crossbar cells and show that they can improve density by more than fourfold over the traditional MOSFET circuits with the same process technology, while achieving close performance and over threefold power reduction.

System energy consumption is a multi-player game

Our key insight is that per-process energy accounting can be formulated as a problem that has been extensively studied in game theory: when multiple players participate in a game and the game produces a surplus, how to divide the surplus among the players? Shapley value is a well-known single value solution to this problem. For any coalition of players S ⊆ N = {1, 2, ... , n}, we denote v(S) as the game surplus if played by coalition S. Shapley value defines the only way to distribute the the grand coalition surplus v(N) among the n players that satisfies four simple axioms: Efficiency, Symmetry, Dummy, and Additivity.