BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:What if Computers Understood Physics? - Dr Phillip Stanley-Marbell
  - University of Cambridge\, Dept Engineering.
DTSTART:20171025T151500Z
DTEND:20171025T163000Z
UID:TALK85321@talks.cam.ac.uk
CONTACT:David Greaves
DESCRIPTION:  Embedded systems measure noisy phenomena from the physical w
 orld and often generate outputs for control of noise-tolerant systems such
  as the human visual system. The algorithms that consume sensed data (e.g.
 \, pedometer algorithms) are often robust to limited input data errors. Wh
 en the outputs of these algorithms are for human consumption\, we can expl
 oit both the robustness of algorithms to input errors as well as the flexi
 bility of human perception\, for more efficient sensor-driven interactive 
 computing systems. And across both inputs and outputs\, there is a missed 
 opportunity to exploit the constraints imposed by the laws of nature and p
 hysical design of systems\, to improve time-\, energy-\, and error-efficie
 ncy.\n\nLax\, Rake\, and Crayon are three recent systems that build on the
 se observations to improve the energy efficiency of sensor activation\, se
 nsor data acquisition\, and displays. Lax [SMR15a] reduces sensor operatio
 n power dissipation by over 40%\, in exchange for infrequent sensor access
  failures that are easily masked by existing sensor applications. The Rake
  project [SMR15b\, SMR16a\, SMR16c]] trades data transfer power dissipatio
 n for data accuracy\, minimally affecting the algorithms that consume this
  data. Crayon [SMR16b] reduces power dissipation of OLED displays\, by exp
 loiting the flexibility of human shape and color perception. Lax\, Rake\, 
 and Crayon are a break from the conventional approach of focusing program 
 optimizations in embedded systems on the programs themselves. By turning t
 he focus of program transformations outward\, to the hardware subsystems t
 hat provide program inputs (sensors) and the hardware that is the destinat
 ion for program outputs (displays)\, our results show that it is viable an
 d profitable to exploit the physics of signals in nature and the flexibili
 ty of human perception to make computing systems more efficient.\n\nIn thi
 s talk\, I will overview the Lax\, Rake\, and Crayon systems and will brie
 fly outline new ongoing work on a custom-designed hardware platform that b
 uilds on these ideas (Warp) and new description languages for describing t
 he physical constrains of systems (Newton) and sensor access constraints (
 Sail).
LOCATION:Lecture Theatre 1\, Computer Laboratory
END:VEVENT
END:VCALENDAR