A Coprocessor for Fast Searching in LargeDatabases: Associative Computing EngineDISSERTATIONsubmitted in partial fulfillment ofthe requirements for the degree ofDoktor-Ingenieur (Dr.-Ing.)to the Faculty of Engineering Scienceand Informatics of the University of UlmbyChristophe Layerfrom DijonFirst Examiner: Prof. Dr.-Ing. H.-J. PfleidererSecond Examiner: Prof. Dr.-Ing. T. G. NollActing Dean: Prof. Dr. rer. nat. H. PartschExamination Date: June 12, 2007c Copyright 2002-2007by Christophe Layer— All Rights Reserved —AbstractAs a matter of fact, information retrieval has changed considerably in recent years withthe expansion of the Internet and the advent of always more modern and inexpensivemass storage devices. Due to the enormous increase in stored digital contents, multi-media devices must provide effective and intelligent search functionalities. However,in order to retrieve a few relevant kilobytes from a large digital store, one moves upto hundreds of gigabytes of data between memory and processor over a bandwidth-restrictedbus. Theonlylong-termsolutionistodelegatethistasktothestoragemediumitself.For that purpose, this thesis describes the development and prototyping of an as-sociative search coprocessor called ACE: an Associative Computing Engine dedicatedto the retrieval of digital information by means of approximate matching procedures.