Computing’s Energy Problem (and what we can do about it) Mark Horowitz

📋 论文概要

该论文分析了技术缩放带来的计算能源问题，指出功耗成为进一步发展的主要瓶颈，并探讨了通过架构创新和电压缩放等手段降低能耗的可能方向。

💡 主要创新点

• 指出了计算能源问题的重要性，强调能源是未来计算发展的核心限制因素。
• 提出了通过架构创新和电压缩放等技术路径来应对能耗挑战。

🏷 关键词

📄 原文摘要

1. Introduction Technology scaling has decreased the cost of computing to the point where it can be included in almost anything. As a result, we now live in a world surrounded by computing devices. They power our searches on Google, connect to our friends on Facebook, answer our questions to Siri, and serve us our entertainment on Youtube; they are in our homes everywhere, in all our appliances (I recently had to reboot my refrigerator), cars, workplaces, and even in the cards we send to each other. We have become so accustomed to computing becoming faster, cheaper, and lower power, we simply assume it will continue. Already, smartphone capabilities are being embedded in eye glasses [1] and smart watches [2]. While scaling computing performance has never been easy, a number of factors have made scaling increasingly difficult this past decade, and have caused power to become the principal constraint on performance. Section 2 quickly

👥 作者与机构

Departments of Electrical Engineering and Computer Science,

Stanford University, Stanford, CA