As Moore's Law and Dennard scaling trends have slowed, the challenges of building high-performance computer architectures while maintaining acceptable power efficiency levels have heightened. Over the past ten years, architecture techniques for power efficiency have shifted from primarily focusing on module-level efficiencies, toward more holistic design styles based on parallelism and heterogeneity. This work highlights and synthesizes recent techniques and trends in power-efficient computer architecture. Table of Contents: Introduction / Voltage and Frequency Management / Heterogeneity and Specialization / Communication and Memory Systems / Conclusions / Bibliography / Authors' Biographies

Autorentext

Magnus Sjalander is a Research Associate at Uppsala University. He received both his Ph.D. degree (2008) and Lic.Eng. degree (2006) in Computer Engineering from Chalmers University of Technology, Sweden. He has been a visiting researcher at NXP Semiconductors, worked at Aeroflex Gaisler, been a post-doctoral researcher at Chalmers University of Technology, and a research scientist at Florida State University. Sjalander's research interests include energy-efficient computing, high-performance and low-power digital circuits, micro-architecture and memory-system design, and hardware-software interaction.Margaret Martonosi is the Hugh Trumbull Adams '35 Professor of Computer Science at Princeton University, where she has been on the faculty since 1994. She also holds an affiliated faculty appointment in Princeton EE. Martonosi's research interests are in computer architecture and mobile computing, with particular focus on power-efficient systems. Her work has included the developmentof the Wattch power modeling tool and the Princeton ZebraNet mobile sensor network project for the design and real-world deployment of zebra tracking collars in Kenya. Her current research focuses on hardware-software interface approaches to manage heterogeneous parallelism and power-performance tradeoffs in systems ranging from smartphones to chip multiprocessors to large-scale data centers. Martonosi is a Fellow of both IEEE and ACM. She was the 2013 recipient of the Anita Borg Institute Technical Leadership Award. She has also received the 2013 NCWIT Undergraduate Research Mentoring Award and the 2010 Princeton University Graduate Mentoring Award. In addition to many archival publications, Martonosi is an inventor on six granted US patents, and has co-authored a technical reference book on power-aware computer architecture. She serves on the Board of Directors of the Computing Research Association (CRA). Martonosi completed her Ph.D. at Stanford University, and also holds a Master'sdegree from Stanford and a bachelor's degree from Cornell University, all in Electrical Engineering.Stefanos Kaxiras is a full professor at Uppsala University, Sweden. He holds a Ph.D. degree in Computer Science from the University of Wisconsin. In 1998, he joined the Computing Sciences Center at Bell Labs (Lucent) and later Agere Systems. In 2003 he joined the faculty of the ECE Department of the University of Patras, Greece and in 2010 became a full professor at Uppsala University, Sweden. Kaxiras' research interests are in the areas of memory systems, and multiprocessor/multicore systems, with a focus on power efficiency. He has co-authored more than 100 research papers and 13 US patents, participated in five major European research projects, and currently receives funding from SwedenâEUR(TM)s business incubator and innovation agency VINNOVA. Kaxiras is a Distinguished ACM Scientist and IEEE member.