Fast Search & Transfer Asa

Overture Services, Inc.

Arne Halaas

B&oslash;rge Svingen

Geirr Ivarsson Leistad

Knut Magne Risvik

Tor Egge

Børge Svingen

Olaf Birkeland

In a search engine with two-dimensional scalable architecture for searching of a collection of documents, the search engine comprises data processing units which forms set of nodes connected in a network, a first set of nodes comprising dispatch nodes, a second set of nodes search nodes and a third set of nodes indexing nodes. The search nodes are grouped in columns, which via the network are connected in parallel between the dispatch nodes and an indexing node. The dispatch nodes are adapted for processing search queries and search answers, the search nodes are adapted to contain search software, at least some of the search nodes additionally including at least one search processor module and the indexing nodes are adapted for generally generating indexes for the search software. Optionally, acquisition nodes provided in a fourth set of nodes and adapted for processing the search answers, thus relieving the dispatch nodes of this task. The two-dimensional scaling takes place respectively through a scaling of the data volume and a scaling of the search engine performance through a respective adaptation of the architecture.

Search engine with two-dimensional linearly scalable parallel architecture

A digital processing system P, configured as a regular tree with n&plus;1 levels S , S , S . . . S and degree k, provided in the form of a circuit P on the level S and forms the root node of the tree, an underlying level S , q&equals;1,2, . . . n&minus;1, in the circuit P provided nested in the K circuits P on the overlying level S , each circuit P on this level including k circuits P . A q&equals;n defined zeroth level in the circuit P includes from K &plus;1 to K circuits P which form kernel processors in the processing device P and on the level S and constitute the leaf nodes of the tree, the kernel processor P being provided nested in each of the circuits p on the level S . Each of the circuits P , P , . . . P , includes a logic unit E which generally is connected with circuits P , P , . . . P . Each of the circuits P , P , . . . P has additionally identical interfaces I, such that I &minus;I &minus; . . . I .

Digital processing system

A non-numeric coprocessor for fuzzy information retrieval and pattern recognition has means for information processing and is connectable to a host computer and a data source. A plurality of internal processing elements are organized in a number of simultaneously operable window modules (W , W , . . . ) a arranged for inspecting data streams from said source. The processing elements compare data stream bytes with predetermined upper and lower bounds, to decide whether a byte is within said bounds, and, if so, to produce a hit signal. Each window module has a window match logic for correlating hit signals from its different processing elements, and to produce a window match signal, by the occurrence of a predefined match. By structuring the coprocessor in this manner, a parallel processing potential is attained, which can be utilized by data routing means ( ) to allow for separate data streams to be routed to individual or chained window modules selectably configured as groups of windows or super-windows according to application needs.

Processing circuit and a search processor circuit

Growing community of inventors

Trondheim, Norway

Arne Halaas