International Business Machines Corporation

Santosh Prasad Gaur

Harsaran S Bhatia

Narasipur G Anantha

Fabrice Jean Verplanken

Jean Louis Calvignac

Michael Steven Siegel

Marco C Heddes

Brian Mitchell Bass

William Eric Hall

James Johnson Allen, Jr

John S Lechaton

John L Mauer, Iv

Gurumakonda R Srinivasan

Joseph M Mosley

Paul J Tsang

Jack A Dorler

James L Walsh

David B Eardley

Hans B Pogge

Yi-Shiou Huang

A system and method are described for secure data transfer over a network. According to an exemplary embodiment a system for secure data transfer over a network includes memory and a memory controller configured to transfer data received from the network to the memory. The system includes a processor, having logic configured to retrieve a portion of the data from the memory using the memory controller. The processor also includes logic configured to perform security operations on the retrieved portion of the data, and logic configured to store the operated-on portion of the data in the memory using the memory controller. The memory controller is further configured to transfer the operated-on portion of the data from the memory to the network.

Secure data transfer over a network

A system and method are described for performing security operations on network data. According to an exemplary embodiment, a system for performing security operations on network data includes memory and a data coprocessor configured to transfer data into and out of the memory. A plurality of processors are coupled to the memory and to the data coprocessor. Each processor is configured to perform, in parallel to one another, security operations on a portion of the data. The system includes a plurality of security coprocessors coupled to the memory. Each security coprocessor is coupled to a respective one of the processors and configured to assist the respective processor in performing security operations on the portion of the data.

System and method for performing security operations on network data

Aspects for optimizing leaf comparisons from a tree search of data stored in external memory of an embedded processing system are described. The aspects include providing a control structure for leaf data comparisons as a control vector and a match key, and utilizing the control vector to direct types of comparison tests performed with the match key.

Method and system for optimizing leaf comparisons from a tree search

Aspects for optimizing data searches in tree structures are described. The aspects include organizing multiple search levels of data into sub-trees contained in fixed size blocks of shared external memory of an embedded processing system, and requiring each reference to the data to proceed from one-half of a sub-tree during a descent of the search tree based on a search pattern.

Method and system for optimizing data searches in tree structures

A network apparatus comprising storage units storing configuration information about the network apparatus, an input network interface to at least one network physical line, at least one processor receiving network data from said network interface, processing said data, storing information about said network data in said storage units, storing said data as formatted data units in said storage units, a first bus interface to two bus connections, a first hardware component reading said configuration information and said information about data stored in said storing units and steering said formatted data units stored in said storage units to at least one of the two bus connections of said first bus interface, a second bus interface to two bus connections, an output network interface to at least one network physical line, a second hardware component reading formatted data units arriving on at least one of the two bus connections of said second bus interface and storing said formatted data units in said storage units, said at least one processor reading said formatted data units from said storage units, processing them and sending them as network data to at least one network physical line through said output network interface. On the basis of this network processor, it is possible to build switching systems by adding one network processor and at least one switch; it is also possible to build double density blades attached to two redundant switch fabrics which can also be accessed concurrently.

Network processor interface for building scalable switching systems

A network switch apparatus, components for such an apparatus, and methods of operating such an apparatus in which data flow handling and flexibility is enhanced by the cooperation among a plurality of interface processors and a suite of peripheral elements formed on a semiconductor substrate. The interface processors and peripherals together form a network processor capable of cooperating with other elements including an optional switching fabric device in executing instructions directing the flow of data in a network.

Network switch using network processor and methods

A method is disclosed for fabricating a small area, self aligned guard ring in a Schottky barrier diode. A vertically-walled hole is anisotropically etched completely through a dielectric layer on a silicon substrate. A layer of doped polycrystalline silicon is deposited over the apertured dielectric layer. The polycrystalline silicon is reactively ion etched away to leave only a lining about the perimeter of the hole in the dielectric layer. The structure is heated to diffuse the dopant from the lining into the substrate. Schottky diode metal is deposited on the substrate exposed through the lined aperture in the dielectric layer.

Schottky diode having limited area self-aligned guard ring and method

Method for making Schottky diode having limited area self-aligned guard

A process is described which permits the fabrication of very narrow base width bipolar transistors in selected areas of an integrated circuit chip and bipolar transistors of wider base width on other selected areas of the same integrated circuit chip. The ability to selectively vary the transistor characteristics from one region of an integrated circuit chip to another provides a degree of freedom for design of integrated circuits which is valuable. The bipolar transistors on an integrated circuit chip are processed up to the point of emitter formation using conventional techniques. But, prior to the emitter formation, the base area which is to be the emitters of the selected region having the very narrow base transistors is dry etched using reactive ion etching. The existing silicon nitride/silicon dioxide layers with the emitter opening therein are used as the etching mask for this reactive ion etching procedure. Once the etching is completed to the desired depth, the normal processing is resumed to form the emitter and rest of the metallization.

Method and resulting structure for selective multiple base width

A method for making a lateral PNP transistor simultaneously with an NPN transistor and the resultant device wherein a first mask defines a base-width by the resistor implant for a P-type resistor and a second mask is overlaid asymmetrically on said first mask to partially cover the collector. At the same time that the NPN extrinsic base contact is made, P-type dopants are introduced in the areas exposed by the first and second masks to provide an emitter and a collector contact for the PNP transistor.

Method of fabricating a lateral PNP transistor

A process is described which permits the fabrication of very narrow base width bipolar transistors. The ability to selectively vary the transistor characteristics provides a degree of freedom for design of integrated circuits. The bipolar transistor is processed up to the point of emitter formation using conventional techniques. But, prior to the emitter formation, the base area which is to be the emitter is dry etched using reactive ion etching. The existing silicon nitride/silicon dioxide layers with the emitter opening therein are used as the etching mask for this reactive ion etching procedure. Once the etching is completed to the desired depth, the normal processing is resumed to form the emitter and rest of the metallization. Since the intrinsic base under the emitter is etched. and the normal emitter is formed afterwards, the etching reduces the base width by an amount approximately equal to the etched depth. The transistor characteristics depend strongly upon the base width so the etching is controlled to very tight dimensions.

Method for making a base etched transistor integrated circuit

A dynamic memory cell has a P+ injector region surrounded by an N+ region in an N- layer on an N+ layer. The injector region is placed between N+ source and drain regions. Holes injected into the N-layer are trapped by the high-low junctions at the N+, N- interfaces and are detected by sensing the source-drain current. Current levels are used to establish binary one and zero levels in the cell. Four masks in an aligned procedure simplify fabrication.

High density memory cell

A dynamic memory cell uses a low barrier Schottky contact at a drain region to eliminate the need for an external gating diode. The drain is separated from source and injector regions by a heavily doped N+ reach through region extending to a heavily doped N+ blanket semiconductor. Holes injected into one of the separated regions are trapped by high-low junctions and are detected by sensing the source-drain current.

Growing community of inventors

Raleigh, NC, United States of America

Santosh Prasad Gaur