Author name: By Chetan Arvind Patil

Modern multiprocessor systems-on-chip (MpSoCs) offer tremendous power and performance optimization opportunities by tuning thousands of potential voltage, frequency and core configurations. As the workload phases change at runtime, different configurations may become optimal with respect to power, performance or other metrics. Identifying the optimal configuration at runtime is infeasible due to the large number of workloads and configurations. This paper proposes a novel methodology that can find the Pareto-optimal configurations at runtime as a function of the workload. To achieve this, we perform an extensive offline characterization to find classifiers that map performance counters to optimal configurations. Then, we use these classifiers and performance counters at runtime to choose Pareto-optimal configurations. We evaluate the proposed methodology by maximizing the performance per watt for 18 single- and multi-threaded applications. Our experiments

One of the great strengths of the modern technology is how better today one make use of each pixel of screen to display useful and colorful contents. This strength can be further enhanced through the appropriate use of technology. We propose to develop and deploy a platform/module for Television. Such a platform/module should simplify the headache of using different screen for different purpose and put everything or most of the thing on Television screen which is now days just used for watching channels or at the most channels plus internet. This will promote more informed screen of television and will surely save cost by not investing in different display devices. Overall, it should provide the user with a better in house/office experience and should enhance out-of-class interactions. We are proposing to develop and deploy a platform/module. This will consist of any

Touch based smart phones and tablets have increased rapidly and have become primary mode of computing and communication. Users have to perform various types of touch inputs on these devices to interact with applications and manufacturers are always looking to improve the response time to satisfy users. However, performing touch gestures and making it more responsive has significant effect both on device battery and the microarchitecture. It is therefore important for computer architects and system designers to take into consideration the underlying effects of these touch gestures and user interactions at architectural level. Also, it’s important to understand how efficient the touch architecture in today’s smartphones are, and if there is any possibility to improve their efficiency. Therefore, there is a need to put forward ways to study these effects, and this technical report takes a look at touch interactions, their underlying architecture, and