Disciplined Approximate Computing: From Language to Hardware, and Beyond
Prof. Luis Ceze,
University of Washington, USA –
Energy is increasingly a first-order concern in computer systems. Exploiting
energy-accuracy trade-offs is an attractive choice in applications that can
tolerate inaccuracies. A key challenge, though, is how to isolate parts of the
program that must be precise from those that can be approximated so that a
program functions correctly even as quality of service degrades. Addressing
that challenge leads to opportunities for approximate computing across the
entire system stack.
In this talk I will describe our effort on co-designing language, hardware and system support
to take advantage of approximate computing across the system stack in a safe and efficient way.
We use type qualifiers to declare data that may be subject to approximate
computation. Using these types, the system automatically maps approximate
variables to potentially imprecise and unreliable but much more efficient storage and
data operations, as well as more energy-efficient algorithms provided by the programmer.
In addition, the system can statically guarantee isolation of the precise program component
from the approximate component. This allows a programmer to control explicitly
how information flows from approximate data to precise data. Importantly,
employing static analysis eliminates the need for dynamic checks, further
improving energy savings. I will describe a micro-architecture that offers
explicit approximate storage and computation and a proposal on using
neural networks as approximate accelerators for general programs. I will
conclude with an overview of our current/future research directions, including
language extensions for quality-of-result specification, programming tools,
approximate persistent storage and approximate wireless communication.
This Distinguished Lecture Series is organized within a special partnership with the JEEC2014 (http://groups.ist.utl.pt/jeec/jeec14/)
Luis Ceze is an Associate Professor in the Computer Science and Engineering
Department at the University of Washington. His research focuses on computer
architecture, programming languages and OS to improve the programmability,
reliability and energy efficiency of multiprocessor systems. He has
co-authored over 60 papers in these areas, and had several papers selected as
IEEE Micro Top Picks and CACM research Highlights. He
is a recipient of an NSF CAREER Award, a Sloan Research Fellowship, a
Microsoft Research Faculty Fellowship and the 2013 IEEE TCCA Young Computer
Architect Award. He consults for Microsoft Research and co-founded Corensic
and Konyac, both UW-CSE spin-off companies. He was born and raised in Sao
Paulo, Brazil, where it drizzles all the time; he now (mostly) lives in the
similarly drizzly Seattle. When he is not working he is found either eating or
Leonel Augusto Pires Seabra de Sousa
Grande Auditório do Pavilhão de Civil no IST
EPIA’22: EPIA Conference on Artificial Intelligence
The EPIA Conference on Artificial Intelligence is a well-established European conference. The 21st edition of the EPIA conference will take place at Instituto Superior Técnico by 2022.
As in previous editions, this international conference is hosted with the patronage of the Portuguese Association for Artificial Intelligence (APPIA).
The purpose of this conference is to promote research in all areas of AI, covering both theoretical/foundational issues and applications, and the scientific exchange among researchers, engineers and practitioners in related disciplines.
For further details please visit the EPIA’22 website.