BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Disciplined Approximate Computing: From Language to Hardware\, and
  Beyond - Luis Ceze\, University of Washington
DTSTART:20130918T090000Z
DTEND:20130918T100000Z
UID:TALK46646@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Energy is increasingly a first-order concern in computer syste
 ms. Exploiting energy-accuracy trade-offs is an attractive choice in appli
 cations 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 s
 ervice degrades. Addressing that challenge leads to opportunities for appr
 oximate computing across the entire system stack. \n\nIn 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 s
 afe and efficient way. We use type qualifiers to declare data that may be 
 subject to approximate computation. Using these types\, the system automat
 ically maps approximate variables to potentially imprecise and unreliable 
 but much more efficient storage and data operations\, as well as more ener
 gy-efficient algorithms provided by the programmer. In addition\, the syst
 em can statically guarantee isolation of the precise program component fro
 m the approximate component. This allows a programmer to control explicitl
 y how information flows from approximate data to precise data. Importantly
 \, employing static analysis eliminates the need for dynamic checks\, furt
 her improving energy savings. I will describe a micro-architecture that of
 fers explicit approximate storage and computation and a proposal on using 
 neural networks as approximate accelerators for general programs. I will c
 onclude with an overview of our current/future research directions\, inclu
 ding language extensions for quality-of-result specification\, programming
  tools\, approximate persistent storage and approximate wireless communica
 tion.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR