BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:High-Performance Processing with Field-Programmable Logic - George
  Constantinides\, Imperial College London
DTSTART:20080220T141500Z
DTEND:20080220T151500Z
UID:TALK10905@talks.cam.ac.uk
CONTACT:Prof Simon Moore
DESCRIPTION:Field-programmable logic devices\, such as Field-Programmable 
 Gate Arrays (FPGAs) are ‘programmable hardware’\, and may be configure
 d at startup or on-the-fly to implement a wide variety of digital electron
 ic designs. These devices are commonly used for rapid prototyping of compl
 ex computational systems. However\, I will discuss a different paradigm 
 – the use of FPG As as general purpose computers\, or as part of a gener
 al purpose computer system. In this approach\, conceived by multiple resea
 rchers over the last 10-15 years\, but only now coming of age\, the genera
 l purpose FPGA is configured to act as a special purpose computational mac
 hine for whatever computation is required at the present time\; the archit
 ecture is designed around the algorithm.\n\nI will briefly discuss the evo
 lution of FPGA architectures and draw comparisons with the evolution of ge
 neral purpose processors\, before discussing two main advantages of modern
  FPGA architectures\, the ability to design numerical representation aroun
 d the algorithm\, and the potential memory bandwidth available.\n\nAlthoug
 h companies such as Cray and SRC now incorporate FPG As in their new super
 computers\, one of the main challenges remains how to program such devices
 . We will touch on this question via an example providing food for thought
 . Finally\, I will present some numerical comparisons of performance achie
 ved using FPG As compared to traditional general purpose processors\, show
 ing 1-2 orders of magnitude improvements in speed for particular applicati
 ons.
LOCATION:Lecture Theatre 1\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR
