Abstract:
A method of designing a clock tree in an integrated circuit combines steps of making a list of all clock sinks (110); positioning a temporary reference insertion point (TIP) (120); grouping the sinks together with structured clock buffers (SCBs) in a set of levels (140); and moving the SCBs to improve symmetry of the tree (150). The SCBs may be of several sizes and may be positioned horizontally (42) or vertically (45) and moved within limits (46) to permit the program to calculate a complete tree.
Abstract:
A method (and structure) for automatically configuring a network including a plurality of interconnected computers, includes configuring more than one of the plurality of computers to assume a role as a designated router (202) which determines a current network configuration (204) by determining which computers are currently on-line, using this determined current network configuration (204) to determine a current network topology (205) that defines a neighborhood relationship among the interconnected computers currently on-line, and communicating the current network topology to the network. The method also includes defining a priority criterion (203) and automatically selecting one of the computers according to the priority criterion to serve the role as designated router.
Abstract:
A method and apparatus for issuing and executing memory instructions so as to maximize the number of requests issued to a highly pipelined memory and avoid reading data from memory (10) before a corresponding write to memory (10). The memory is divided into a number of regions, each of which is associated with a fence counter (18) that is incremented each time a memory instruction that is targeted to the memory region is issued and decremented each time there is a write to the memory region. After a fence instruction is issued, no further memory instructions (23) are issued if the counter for the memory region specified in the fence instruction is above a threshold. When a sufficient number of the outstanding issued instructions are executed, the counter will be decremented below the threshold and further memory instructions are then issued.
Abstract:
A stressed film applied across a boundary defined by a structure or a body (e.g. substrate or layer ) of semiconductor material provides a change from tensile to compressive stress in the semiconductor material proximate to the boundary and is used to modify boron diffusion rate during annealing and thus modify final boron concentrations and/or profiles/gradients. In the case of a field effect transistor, the gate structure may be formed with or without sidewalls to regulate the location of the boundary relative to source/drain, extension and/or halo implants. Different boron diffusion rates can be produced in the lateral and vertical directions and diffusion rates comparable to arsenic can be achieved. Reduction of junction capacitance of both nFETs and pFETs can be achieved simultaneously with the same process steps.
Abstract:
A method, apparatus, and computer instructions for providing identification and monitoring of entities. A distributed data processing system (100) includes one or more distributed publishing entities (400, 402, 404), which publish computer readable announcements (800) in a standard language. These announcements (800) may contain a description of a monitoring method (802) that may be used to monitor the behavior of one or more distributed monitored entities (400, 402, 404). These announcements also may include information used to identify a monitoring method (802) that may be used by the distributed monitored entity (400) to monitor its own behavior or by a distributed consumer entity to monitor the behavior of the distributed monitored entity (400). The monitoring also may be performed by a third-party distributed monitoring entity (400).
Abstract:
A network switching 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 (12) and a suite of peripheral elements formed on a semiconductor substrate (10). The interface processors (12) and peripherals together form a network processor capable of cooperating with other elements including an optional switch fabric device in executing instructions directing the flow of data in the network.
Abstract:
A fan module including: two or more individual fans, each fan having an air movement means and a motor engaged with the air movement means for accelerating air entering each of the two or more individual fans; a temperature sensor for sensing a temperature associated with the two or more fans and for outputting a first signal corresponding to the temperature; rotational speed sensor for outputting a second signal corresponding to a rotational speed of each of the two or more fans; and a processor for receiving the first and second signals and controlling the two or more individual fans based on the first and second signals.
Abstract:
An access control function (440) for an integrated system (400) is provided which determines data access based on the master id of a requesting master (410) within the system (400) and the address of the data. The access control function (440) can be inserted, for example, into the data transfer path between bus control logic (430) and one or more slaves (420). In addition to determining whether to grant access to the data, the access control function (440) can further qualify the access by selectively implementing encryption and decryption (470) of data, again dependent on the data authorization level for the particular functional master (410) initiating the request for data.
Abstract:
A voltage island system including a hot-switchable voltage bus for IDDQ current measurements. The voltage island system includes a plurality of voltage islands (V1, V2, ..., Vn), a global power system (102), and a quiescent power system (104). The global power system (102) includes a plurality of on-chip global header devices (H1, H2, ..., Hn) for selectively providing a voltage VDDg to the plurality of voltage islands in response to global header control signals (xl, x2, ..., xn), respectively. A global VDDg power supply (106) provides power to the global header devices (H1, H2, ..., Hn) via a VDDg power distribution grid/bus (108). The quiescent power system (104) includes a plurality of on-chip quiescent header devices (Hlq, H2q, ..., Hnq) for selectively providing a quiescent voltage VDDq to the plurality of voltage islands in response to quiescent header control signals xlq, x2q, ..., xnq, respectively. A quiescent VDDq power supply (110) provides power to the quiescent header devices via a VDDq power distribution grid/bus (112).
Abstract:
A system and method of electronic check processing at an existing point-of-sale (POS) system (10). A customer presents a check to pay for a transaction at the POS. A checker runs the check through an MICR scanner (22) and captures the MICR information from the check. The MICR information is forwarded to a verification system (12) for approval. Once the check is approved, the purchaser's contact information is scanned and digitized from the face of the check by an optical scanner (23) to create an ECC Agreement slip (150), which is printed on a high speed printer (24). Once the purchaser signs the agreement slip (150), he returns the slip (150) to the checker. The slip (150) is retained by the retailer and handled for cash balancing similarly to a charge card slip. The point-of-sale terminal (10) automatically voids the negotiable instrument (162) prior to the instrument (162) being returned to the purchaser to complete the transaction.