Advanced Micro Devices Corporation

Dunti Corporation

Other

Rupaka Mahalingaiah

Thang M Tran

Paul K Miller

James K Pickett

Rammohan Narayan

Gerald David Zuraski, Jr

Viren H Kapadia

Douglas D Gephardt

David B Witt

William M Johnson

James R MacDonald

Brian D McMinn

Rodney W Schmidt

Andrew McBride

Thomas S Green

Terry Hulett

A mechanism that enables multiple Mobile Devices to operate in clusters is provided. Using the mobile cluster mechanism framework provided in this invention, Mobile Devices can execute compute intensive tasks in the field by sharing the task between various devices. The invention also contemplates various options of implementing the cluster mechanism on Mobile Devices. The invention further contemplates solutions for the roaming of Mobile Devices.

Method and apparatus for enabling mobile cluster computing

A mechanism to generate clocks when there is no security breach is contemplated. Using the conditional generation of clocks for synchronous digital designs, the invention enables mechanisms to secure Mobile Devices. When a potential security breach is detected, clock generation to at least a portion of the Mobile Device is disabled. The invention also contemplates mechanisms to re-enable the Mobile Device when the security risk is resolved.

Method and apparatus for securing digital devices while reducing power consumption

A system and method of authenticating a user of a data network which inserts control information into certain data packets being sent over the network. The control information is user-specific, including such items as user identity, password, originating CPU, or biometric information. Inserting the control information into data packets transmitted during the entire session permits continuous authentication.

Method and apparatus for providing continuous user verification in a packet-based network

A system and method of providing secure communications between two or more hosts connected to a public network, where a secure virtual network (SVN) is established among the two or more hosts.

Method and apparatus for securing communication over public network

An architecture, system, and method are provided for transparently mapping a network identification number of a host to an access point of an internet. The host can be moved from a first point to a second point on the internet without having to reconfigure routing tables or to update routing protocols. The network identification number of the host does not change as it is moved from the first point to the second point. Thus, the network identification number of the host does not perform routing. Instead, routing occurs by targeting the exit end module onto which the host is connected, i.e., at the second point. The exit end module thereby contains configuration registers which store mapping tables that note the new destination address of any data being sent to the new host location, and properties such as security and priority codes.

Apparatus, system, and method for routing data to and from a host that is moved from one location on a communication system to another location on the communication system

An architecture, system and method are provided for efficiently transferring packets of data across a communication network. Portions of the communication network is structured such that there are hierarchical levels of high speed Routing Switches existing throughout the network. Distributed routing of packets is achieved by comparing identification numbers of Routing Switches with the destination address of a data packet. Once routing is achieved within the transport ID based network, transfer to a destination termination device occurs through a single look-up table only when departing the network. The routing operation between termination devices can therefore be achieved using a single mapping operation and is backward compatible with devices external to the network and protocols used by those devices. Each Routing Switch thereby serves as a traffic manager, having registers that are configured so as to allow the traffic manager to direct packets of data from an input port to an output port in the quickest, most efficient manner without having to decode the entire destination address or requiring time-consumptive routing tables.

Network packet transmission mechanism

A packet architecture, communication system, and method are provided for determining the location at which a network is disrupted, disabled, and/or severed. The packet can contain control bits and error identification bits which note the location at which disturbance exists, and informs the originating module to take alternative path if necessary. The alternative path can be applied to either re-sending the existing packet or sending future packets between certain modules connected to the network, wherein the network preferably includes one or more ring topologies interconnected with one another between termination devices. The termination devices allow communication across subnets which form an intranet or across a global system, or internet. Although redundant transmission channels are used, each transmission channel preferably does not send redundant packets, nor are the transmission channels dedicated as uni-directional. Instead, each of the redundant transmission channels can send dissimilar packets in a bi-directional fashion.

Communication network and protocol which can efficiently maintain transmission across a disrupted network

An architecture, system and method are provided for transparently mapping addresses across multiple addressing domains and/or protocols. A destination of a packet can therefore be transferred from a first addressing domain within one network to a second addressing domain within another network, without inserting knowledge into the packet of the relationship between the two separate and independent domains. Transmission modules within one network can be identified with unique identification numbers or addresses assigned during configuration of those modules. The identification numbers assigned internal to the network can be mapped and placed upon the packet as the packet enters the network. Mapping, however, is minimal, knowing that relatively few external devices are connected to select internal devices and/or modules. The packet can then be mapped into the network, where it is then transferred across the network whereupon it is mapped to another network or termination device external to the network. The downstream network or termination device may have an addressing domain entirely separate and independent from the addressing domain used within the network, the benefit of which is to free up external addressing space that would normally be used if the external addressing domain were used internally.

Address mapping mechanism enabling multi-domain addressing in communication networks

An architecture, system and method are provided for efficiently transferring packets of data across a communication network. The communication network is structured such that there are hierarchical levels of high speed switches existing throughout the network. Distributed routing of packets is achieved by comparing identification numbers of only select switches with the destination address on a field-by-field basis. Not all fields need be compared at all switches. Once routing is achieved within the structured network, transfer to a destination termination device occurs through a single look-up table only when departing the network if multiple termination devices are present at that exit node. The routing operation between termination devices can therefore be achieved using a single mapping operation (if more than one termination device must be selected) and is backward compatible with devices external to the network and protocols used by those devices. An additional protocol layer specific to the structure is wrapped onto the incoming packet protocol using a series of read cycles to a memory which temporarily receives the incoming protocol. The sequence of reads can be quickly achieved without using conventional packet processors and the delayed access times normally attributed to those processors. Each switch thereby serves as a traffic manager, having registers that are configured so as to allow the traffic manager to direct packets of data from an input port to an output port in the quickest, most efficient manner without having to decode the entire destination address or requiring time-consumptive routing tables.

Communication network having modular switches that enhance data throughput

Architectures, systems, and methods are provided for securing and prioritizing packets of data sent through a communication network. Each packet is assigned a security code and priority code as it enters the network. The security code or priority code may remain the same or change as it travels from node-to-node across the network. By assigning security and priority codes to each packet, maximum bandwidth allocation can be achieved among the nodes in a packet-switched environment. The assigned security and priority codes enter and travel through the network according to modules which have a hierarchical class or grouping. Thus, the security and priority information may be sent solely within one class or among classes depending on where, within the classes the data path exists. In this manner, a specified quality of service can be achieved to ensure the data path is secured dynamically as it travels from node to node, and also to determine which packet among several is to be forwarded across a shared resource of that network.

Communication network having packetized security codes and a system for detecting security breach locations within the network

Communication network across which packets of data are transmitted according to a priority scheme

Modular switches interconnected across a communication network to achieve minimal address mapping or translation between termination devices

A microprocessor configured to rapidly decode variable-length instructions is disclosed. The microprocessor is configured with a predecoder and an instruction cache. The predecoder is configured to expand variable-length instructions to create fixed-length instructions by padding instruction fields within each variable-length instruction with constants until each field reaches a predetermined maximum width. The fixed-width instructions are then stored within the instruction cache and output for execution when a corresponding requested address is received. The instruction cache may store both variable- and fixed-width instructions, or just fixed-width instructions. An array of pointers may be used to access particular fixed-length instructions. The fixed-length instructions may be configured to all have the same fields and the same lengths, or they may be divided into groups, wherein instructions within each group have the same fields and the same lengths. A software program configured to generate fixed-length instructions from variable-length instructions is also disclosed. A method for decoding variable-length instructions is also disclosed.

Growing community of inventors

Austin, TX, United States of America

Rupaka Mahalingaiah