Ten Years of Building Broken Chips
Ten Years of Building Broken Chips
Inexact Design for Ultra Energy Efficient Platform Architectures and Embedded Systems
Well over a decade ago, many believed that an engine of growth driving the semiconductor and computing industries, captured nicely by Gordon Moore’s remarkable prophecy (Moore’s law), was speeding towards a dangerous cliff-edge. When faced with this issue, I decided to consider a different approach back in 2002—one which suggested falling off the metaphorical cliff as a design choice, but in a controlled manner. This resulted in devices, circuits and architectures that switch and produce bits of information that deviate from the intended correct specification—the results would be approximate or inexact. Despite being inexact by trading accuracy away, these hardware designs have been shown to be significantly more efficient in the energy they consume, their speed of execution, and physical area needs.
This in turn makes them attractive for a range of large-scale data-centric applications such as analytics, search, learning and climate modeling, as well as embedded applications involving video and audio. In this talk, I will start with our beginnings with inexactness from 2002—one that Technology Review labeled as being heretical in their TR10 citation—and give an overview of a range of ideas that our group as well as other groups around the world have been developing since. I will also outline opportunities for applying inexact design in the context of realizing extremely energy-efficient platform architectures including memory systems, for computing with big data at one extreme, and battery-constrained embedded systems with strong ties to neural processing at the other. We intend to use this talk as a basis for developing partnerships to collaboratively help grow this exciting frontier in inexact hardware, and eventually software systems.
Krishna V. Palem is the Ken and Audrey Kennedy Professor at Rice University with appointments in Computer Science, in Electrical and Computer Engineering and in Statistics. In the past, he founded and directed the NTU-Rice Institute on Sustainable and Applied Infodynamics (ISAID), and is a scholar in the Baker Institute for Public Policy. He was a Moore Distinguished Faculty Fellow at Caltech in 2006-2007, and a Schonbrunn Fellow at the Hebrew University of Jerusalem in 1999, where he was recognized for excellence in teaching. His advisee Suren Talla was awarded the Janet Fabri Prize for outstanding dissertation in 2001, and his related work on the foundations of architecture assembly for designing reconfigurable embedded SoC architectures, developed at Proceler Inc. which he co-founded as a CTO, was a nominee on 2002 for the Analysts choice awards as one of the four outstanding technologies.
A decade ago, he pioneered a novel technology entitled Probabilistic CMOS (PCMOS) for enabling ultra low-energy computing, with his students. In this area, his student Lakshmi Chakrapani's research was recognized through an outstanding dissertation award by Sigma Xi in 2008. PCMOS has also been recognized by a best-paper award at the IEEE-ACM CASES 2006 conference in Seoul, as one of the ten technologies 'likely to change the way we live' by MIT's Technology Review in 2008, and as one of the seven 'emerging world changing technologies' by IEEE as part of its 125th anniversary celebrations in 2009.
Broadly, he has led efforts internationally in the area of embedded systems and their compiler optimizations, for which he has been named a Fellow of the IEEE, the ACM and AAAS. In 2012, Forbes (India) ranked him second on the list of eighteen scientists who are "..some of the finest minds of Indian origin." He is the recipient of the 2008 W. Wallace McDowell Award, IEEE Computer Society's highest technical award and one of computing's most prestigious individual honors.