AENAO: high-performance, power-aware and reliable processors and computer systems

点击翻译按钮获取中文摘要

At the core of virtually all modern electronic devices such as computers, cell phones, and network routers there is at least one processor that is the "brains" of the device. Processors manipulate information represented as numbers. Processors are extremely useful because they can interact with the environment - via sensors (e.g., a microphone) and actuators (e.g., a speaker) - following a prespecified, yet complex, set of actions. Processors are also extremely useful in scientific exploration as they can evaluate complex models of physical phenomena such as chemical, biological and inter-planetary interactions that are too expensive or impractical to study otherwise. Today many everyday activities and much of scientific exploration rely on the availability of optimized, inexpensive processors. Historically, it was possible to continuously improve the performance and other characteristics of processors (e.g., energy consumption) while reducing cost. A typical computer in the early 80's cost several tens of thousands, while today just a few hundred dollars while being 1000 times as powerful. Much of the communications and computing industry relies on this trend. A key mechanism for improving processors is computer architecture, which studies how to build processors given the available manufacturing technologies while taking into consideration the applications that these processors will be used for. Computer architecture faces continuous challenges for two reasons: (1) the properties of the underlying technology change significantly over time, and (2) so do the applications. This research is targeted at improving processors by addressing new challenges that stem from the continuous shrinking of the underlying manufacturing technology and the new applications that have emerged as processor-based devices have become ubiquitous. The challenges addressed include performance, design complexity, and energy consumption. Such techniques must be developed if the historical trends of advance in processor performance and cost are to be maintained. A variety of processor-based devices ranging from smart-phones to supercomputers will benefit from this research.