Abstract: A memory circuit for use in a data processing circuit is described, in which memory cells have at least two states, each state being determined by both a first voltage level corresponding to a first supply line and a second voltage level corresponding to a second supply line. The memory circuit comprises a readable state in which information stored in a memory cell is readable and an unreadable state in which information stored in said memory cell is reliably retained but unreadable. Changing the first voltage level but keeping the second voltage level substantially constant effects a transition between the readable state and the unreadable state. In use, the static power consumption of the memory cell in the unreadable state is less than static power consumption of the memory cell in the readable state.

Abstract: A system and method is provided that improves the propagation characteristics of an electrical conducting signal wire on an integrated circuit. The system includes a pair of parallel shielding wires positioned on opposite longitudinal sides of the signal wire. A shielding signal is applied to the shielding wires. The shielding signal is out of phase with the signal of interest propagated on the signal wire.

Abstract: The present invention relates generally methods and apparatus for controlling current demand in an integrated circuit. One embodiment relates to a method that includes detecting if a supply voltage overshoot or a undershoot is present or anticipated, and if detected, controlling current consumed by a power consumption circuitry to ensure that the power supply voltage remains within acceptable levels. Other embodiments relate to an integrated circuit having a capacitive decoupling structure, power consumption circuitry, and power consumption control circuitry for controlling current consumed by at least a portion of the power consumption circuitry. Therefore, embodiments of the invention relate to monitoring and controlling power consumption (i.e. current demand) of a power consumption circuit (such as an integrated circuit) in order to prevent devastating supply voltage undershoots, overshoots, and oscillations.

Abstract: A memory circuit for use in a data processing circuit is described, in which memory cells have at least two states, each state being determined by both a first voltage level corresponding to a first supply line and a second voltage level corresponding to a second supply line. The memory circuit comprises a readable state in which information stored in a memory cell is readable and an unreadable state in which information stored in said memory cell is reliably retained but unreadable. Changing the first voltage level but keeping the second voltage level substantially constant effects a transition between the readable state and the unreadable state. In use, the static power consumption of the memory cell in the unreadable state is less than static power consumption of the memory cell in the readable state.

Abstract: A solution to perform cross coupling delay characterization for integrated circuits and other microprocessor applications. The invention properly models the integrated circuit in various configurations at various times to accommodate the non-linearities associated with driver circuitry and the undesirable capacitive coupling between nets within the integrated circuit, specifically those that are located within close proximity to one another and that generate deleterious effects of the transitions of the drivers from low to high, and from high to low. The invention provides for a computationally efficient solution to perform the delay characterization of the speeding up and slowing down of individual transition operations within the microprocessor.

Abstract: A system and method is provided that improves the propagation characteristics of an electrical conducting signal wire on an integrated circuit. The system includes a pair of parallel shielding wires positioned on opposite longitudinal sides of the signal wire. A shielding signal is applied to the shielding wires. The shielding signal is out of phase with the signal of interest propagated on the signal wire.

Abstract: A method for designing and routing circuitry having reduced cross talk. Early noise analysis (22) is performed after global routing (12) but before detailed routing (28) in order to repair problems (24) before detailed routing (28) is performed. In one embodiment, the early noise analysis (22) is preceded by probabilistic extraction (16). In one embodiment, probabilistic extraction (16) includes determining a probability of occurrence for each configuration in a predetermined set of configurations (54). Probabilistic capacitance extraction is then performed (56). A probabilistic distributed coupled RC network is constructed using the extracted capacitances (60). In one embodiment, probabilistic extraction (16) includes estimating aggressor strength (20) using the probabilistic distributed coupled RC network.

Abstract: Method for generating a set of switching vectors where each vector S1-Si causes the output X to transition in the predetermined way provided that the input A transitions in the selected way. This method may be used for any electrical circuit cluster, including the simple one illustrated in FIG. 3. This method handles any number of side inputs, gate clusters which have feedback within the gate cluster, and gate clusters which have internal nodes that may be in a third state other than a logic level one or a logic level zero (e.g. a high impedance state).

Abstract: The present invention relates generally methods and apparatus for controlling current demand in an integrated circuit. One embodiment relates to a method that includes detecting if a supply voltage overshoot or a undershoot is present or anticipated, and if detected, controlling current consumed by a power consumption circuitry to ensure that the power supply voltage remains within acceptable levels. Other embodiments relate to an integrated circuit having a capacitive decoupling structure, power consumption circuitry, and power consumption control circuitry for controlling current consumed by at least a portion of the power consumption circuitry. Therefore, embodiments of the invention relate to monitoring and controlling power consumption (i.e. current demand) of a power consumption circuit (such as an integrated circuit) in order to prevent devastating supply voltage undershoots, overshoots, and oscillations.

Abstract: The invention relates to a new method of guidance for routing of nets in an integrated circuit model wherein all nets are first approximately routed, as with Steiner routing, and victim nets with functional delay noise above predetermined thresholds are identified. Each victim net is then detail routed. For each victim net detail routed, a set of least noise aggressive neighboring nets is selected. Segments of those neighboring nets are assigned tracks adjacent to the victim net in such a way as to maximize utilization of the victim net's neighboring tracks, thereby reducing noise induced on the victim net and maximizing use of available space on the semiconductor. The process is then repeated until there are no additional victim nets, at which point the remaining nets are detail routed.

Abstract: A system and method for manipulating waveforms, including transaction cancellation, in parallel time-warp simulation of circuits, such as those modeled in VHDL. Events waveforms for each output of a processor are organized by the simulation time (ST) of the events which created them and by the simulation time (RT) at which they are to be effective. A phantom buffer provides a linked list of events and associated transactions cancelled as a result of insertion of a new event in said chain of events. Rollback of a cancelled event waveform is done by restoring to the linked lists selected events and transactions from the phantom buffer.

Abstract: System and method for calculating global virtual time for use in memory management, termination detection, snapshots, crash recovery, input and output handling, and so forth, and in parallel simulation of digital circuits. Processes executing on parallel processors communicate messages through channels having output trail buffers on each process communicating to the channel, and one input trail buffer for all processes receiving messages from the channel. A channel is the union of all wires or communication paths connecting two processors. Input trail buffers store the time stamp of the most recently received message, and output trail buffers store valley messages. Global virtual time is calculated with reference to the least time stamp of the output trail buffers, where the least time stamp is calculated with respect to the time stamp of the input trail buffer.

Abstract: A process and implementing computer system (13) for optimally sizing elements of an integrated circuit includes determining actual arrival times and required arrival times (403) for processed signals at all nodes within the integrated circuit and determining the slack or difference (405) between arrival and required times for each node. If the actual arrival time for a particular node is after the time required to meet a predetermined design constraint of the node (407), a determination (411) is made regarding the effect of that element on the nodal slack for an incremental increase in the size of that element. Thereafter an element is selected (413) for sizing increase (415) in accordance with a weighting function and the process is repeated until all of the nodes in the integrated circuit have positive slack times (407, 409).

Abstract: A process and implementing computer system (13) for optimally sizing elements of an integrated circuit includes determining actual arrival times and required arrival times (403) for processed signals at all nodes within the integrated circuit and determining the slack or difference (405) between arrival and required times for each node. If the actual arrival time for a particular node is after the time required to meet a predetermined design constraint of the node (407), a determination (411) is made regarding the effect of that element on the nodal slack for an incremental increase in the size of that element. Thereafter an element is selected (413) for sizing increase (415) in accordance with a weighting function and the process is repeated until all of the nodes in the integrated circuit have positive slack times (407, 409).

Abstract: A process and implementing computer system (13) for optimally sizing elements of an integrated circuit includes determining actual arrival times and required arrival times (403) for processed signals at all nodes within the integrated circuit and determining the slack or difference (405) between arrival and required times for each node. If the actual arrival time for a particular node is after the time required to meet a predetermined design constraint of the node (407), a determination (411) is made regarding the effect of that element on the nodal slack for an incremental increase in the size of that element. Thereafter an element is selected (413) for sizing increase (415) in accordance with a weighting function and the process is repeated until all of the nodes in the integrated circuit have positive slack times (407,409).

Abstract: A method for designing an integrated circuit involves a four step process. First, a behavioral circuit model (BCM) is read which contains assignment statements which identify the logical operation of an integrated circuit (IC). The BCM is translated to a data file which described a plurality of interconnected logic gate functions to duplicate the operation of the BCM. The gates in the data file are then assigned a specific Vdd and ground rail size, a specific drive strength for speed considerations, and a cell pitch or height to optimize physical layout, in any order. The result in a physical design file which may be used to form masks and integrated circuits having optimized speed and optimized circuit area in a short design cycle.

Abstract: A method and apparatus for designing and manufacturing integrated circuits (ICs) involves providing an initial library of IC cells (106) and a behavioral circuit model (100) in order to create a gate schematic netlist (102). The gate schematic netlist (102) is optimized by changing individual transistor sizes, power rail sizes, cell pitch, and the like in a step (103). Once the optimization has occurred, the initial library can no longer be used to place and route the IC. Therefore, a hybrid logic cell library is created from the gate schematic netlist (102) via a step (105). This hybrid library and the above optimizations provides a placed and routed IC via a step (126) in a short design cycle while optimizing performance of the IC.

Abstract: An integrated circuit, when designed, must adhere to timing constraints while attempting to minimize circuit area. In order to adhere to timing specifications while arriving at a near-optimal circuit surface area, an iterative process is used which selectively increases logic gates sizes by accessing logic gates from a memory stored logic gate library. A circuit representation is read along with timing constraints for circuit paths. Each circuit path in the circuit is processed to find it's actual circuit path delay. A most out-of-specification circuit path (in terms of speed) is chosen in the circuit and a sensitivity calculation is performed for each logic gate in the most out-of-specification circuit path. The logic gate in the circuit path with the maximized sensitivity (sensitivity=.DELTA.speed/.DELTA.area) is increased in size by accessing a larger gate in the library in order to improve speed at the expense of area.

Abstract: In a virtual time system employing parallel processing nodes, processor nodes communicate with each other by sending messages. Each message between any pair of processing nodes is labeled with a sequence number, which allows the system to determine which messages are "in-transit" at any point in time. In the invention, sequence numbers are drawn in a sending processing node from a finite range according to a method that permits them to be reused through time while providing unique sequence numbers with respect to other messages sent since a last received sequence number provided by a receiving processing node. The last received sequence number is the message sequence number in a last message sent by the sending processing node to the receiving processing node.