Abstract: A cell library is disclosed that includes soft error resistant logic cells. The soft error resistant logic cells can be used along with memory cells and conventional logic cells to form integrated circuit designs having increased soft error resistance. A method for forming an integrated circuit device is disclosed in which a first integrated circuit design is formed using conventional logic cells. An iterative process is then performed in which some of the conventional logic cells are replaced with high soft error resistant logic cells to obtain a soft error resistant design. Each soft error resistant logic cell that replaces a corresponding conventional logic cell will have the same cell size as the cell that is replaced, producing a soft error resistant design that does not take up additional surface area on the semiconductor substrate.

Abstract: An adaptive decision feedback equalizer includes a filter module, a compensation module, and a slicer module. The filter module generates a filtered signal by adaptively filtering an input serial data signal to reduce inter-symbol interference in the serial data signal. The compensation module generates a compensated signal by equalizing amplitudes of frequency components of the filtered signal in a compensation frequency range to reduce inter-symbol interference in the filtered signal. The slicer module determines logic states of serial data in the compensated signal and generates an output serial data signal including serial data having the determined logic states.

Abstract: A communication system that includes a packet switch having a buffered crossbar for routing data packets from input ports to output ports of the packet switch. The buffered crossbar stores a data packet received from an input port based on a clock signal of a clock domain and sends the data packet to an output port of the packet switch based on a clock signal of another clock domain. In this way, the buffered crossbar functions as a clock domain boundary between the input port and the output port. Moreover, the frequency of one or both of the clock signals may be selected to minimize power consumption in the packet switch or to select a tradeoff between power consumption and performance of the packet switch.

Abstract: A method and apparatus are disclosed for predicting the failure of a functional element of an integrated circuit during operation. The method includes determining whether the functional element of the integrated circuit device is in an idle cycle, performing a stress test of the functional element while the functional element is in the idle cycle, and indicating that the functional element, if it fails the stress test, is a potential future failing element. The stress test can include simultaneously providing a margining test voltage and a stress clock signal to the functional element. The stress test is performed in the background, during continuous operation of the integrated circuit device, such that normal operation of the integrated circuit device is not interrupted. Thereby, the method and apparatus of the present invention allows for failure prediction in a device before it happens, allowing for planned outages or workarounds and avoiding system downtime for unplanned repairs.

Abstract: The method of the present invention includes loading a selected set of preset parameters into a source device and a sink device of the DisplayPort device of an embedded system. Link training is then performed between the source device and the sink device utilizing the first set of preset parameter and the link status (bit lock, symbol lock and inter-lane alignment) of the DisplayPort device is then read. If the link status indicates that the link training is successful, a link is established between the source device and the sink device, or if the link status indicates that the link training is unsuccessful, a different set of preset parameters is loaded and link training is then performed again. The steps of loading, performing and reading are repeated with each of the plurality of sets of preset parameters until the link status indicates that the link training is successful.

Abstract: A packaged integrated circuit device and a circuit board assembly are disclosed that include a semiconductor die and a package substrate that includes a first grid array of contact pads that are electrically coupled to corresponding contact pads on the semiconductor die. The first grid array of contact pads includes a first set of adjacent rows or columns of contact pads that are coupled to a first channel that extends within a ground plane of the package substrate. The first grid array of contact pads includes a second set of adjacent rows or columns of contact pads that are electrically coupled to a second channel that extends within a power plane of the package substrate. The contact pads in the first set of adjacent rows or columns of contact pads directly overlie a portion of the first channel and the contact pads in the second set of adjacent rows or columns of contact pads directly overlie a portion of the second channel.

Abstract: A system and method for scheduling a thread identifies runnable threads based on precycle signals determined before the scheduling cycle. The thread indexes of the runnable threads are grouped according to the thread priorities of the runnable threads, and the thread indexes are ranked within each group. The runnable threads that will be runnable in the next scheduling cycle are identified based on same cycle signals determined during the scheduling cycle. The highest ranked thread index of the runnable threads that will also be runnable in the next scheduling cycle is selected as the scheduled thread. In another configuration, a round robin ranking and a priority ranking are determined for the thread indexes. The thread indexes are then ranked according to the round robin ranking and the priority ranking and the highest ranked thread index of a runnable thread is selected as the scheduled thread.

Abstract: A clock circuit generates a reference clock signal based on a resonant frequency of a crystal, generates thermometer-coded signals based on the reference clock signal, and generates a pulse train based on the thermometer-coded signals. The pulse train has a frequency that is a multiple of the frequency of the reference clock signal. Additionally, the clock circuit includes a phase-lock loop for generating an output clock signal based on the pulse train and aligning a phase of the output clock signal with pulses in the pulse train. In various embodiments, the frequency of the reference clock signal is the same as the resonant frequency of the crystal and the frequency of the output clock signal is a multiple of the resonant frequency of the crystal. Moreover, reference clock signal and the output clock signal each have a long-term jitter based on the precision of the resonant frequency of the crystal.

Abstract: A packet switch includes a pointer table for mapping locations in an input data buffer to locations in an output data buffer. The processor generates an output data packet based on data portions in the input data buffer and based on the pointer table. The output data buffer stores data portions of the output data packet successively in a sequential order and can output the data portions of the output data packet successively in a sequential order. The pointer table may be configured to reduce the latency or reduce the power consumption of the packet switch.

Abstract: A method for forming a semiconductor die and a flip-chip integrated circuit device are disclosed that include a power and ground mesh that is oriented diagonally. A layout of a semiconductor die is formed by generating a first integrated circuit design and copying and rotating the design so as to form three additional integrated circuit design blocks. The power and ground mesh layer includes four overlying sets of power and ground strips that are oriented diagonally and symmetric. Because the power and ground strips of the present invention are angled and correspond to the underlying integrated circuit design, they allow for powering both rotated and non-rotated logic while maintaining identical interconnection points and capacitive loading across all the repeated blocks. In addition, the angled power and ground strips allow for easily coupling power and ground to structures around the periphery of the power and ground strips.

Abstract: A device and method for protecting HDCP cryptographic keys are presented herein. The device and method include receiving a set of HDCP cryptographic keys, encoding the set of HDCP cryptographic keys such that the resultant encoded cryptographic data is enabled to be represented in rows and columns, and storing the set of keys in a storage device of an HDCP appliance in the rows and columns, wherein at least one of the rows does not include a complete cryptographic key and at least one of the columns does not include a complete cryptographic key. The method can use block interleaving or convolution interleaving encoding.

Abstract: A packet switch including input ports and output ports allocates an output bandwidth of each output port among virtual channels based on bandwidth allocations values corresponding to the virtual channels and a bandwidth precision value of the output port. The bandwidth precision value indicates a number of bandwidth precision bits, which may be outside a bandwidth reservation precision range specified in a serial RapidIO standard. The packet switch receives data packets compliant with the serial RapidIO standard at the input ports, identifies an output port for each data packet, and selects input ports based on the output ports of the data packets. Further, the packet switch routes a data packet from each selected input port to the output port of the data packet, and the output port outputs the data packet by using the output bandwidth of the output port allocated to the virtual channel identified by the data packet.

Abstract: A clock circuit includes a phase-lock loop for generating an output clock signal based on a data signal and a harmonic frequency detector for detecting whether the frequency of the output clock signal is a harmonic frequency of a frequency of a reference clock signal. The harmonic frequency detector includes a counter for generating a first divided clock signal by dividing the frequency of the output clock signal by a first divisor. Additionally, the harmonic frequency detector includes a counter for generating a second divided clock signal by dividing the frequency of the reference clock signal by a second divisor. The harmonic frequency detector also includes a frequency comparator for generating an output indicating whether the frequency of the output clock signal is a harmonic frequency of the frequency of the reference clock signal based on the first divided clock signal and the second divided clock signal.

Abstract: An arbiter generates an availability signal indicating whether pseudo-ports are available for receiving data. Each pseudo-port identifies one or more output ports of a packet switch. The availability signal also indicates whether each pseudo-port has a hold. A hold on a pseudo-port indicates that the pseudo-port is being held for an input port of the packet switch. Although the packet switch may complete routing of a data packet in progress to an output port of the pseudo-port that has the hold, the packet switch will not initiate routing of a data packet to an output port of the pseudo-port until each output port of the pseudo-port is available. When all the output ports of the pseudo-port are available, the packet switch can route data of a data packet from the input port for which the pseudo-port is being held to each output port of the pseudo-port.

Abstract: A device and method are disclosed for performing a limit address check validation in a switching device. The device includes a data selector circuit that is enabled to select the content of an address register in an array of address registers, and a comparator electrically coupled to the data selector circuit and enabled to take a first input from the data selector circuit and target address as a second input from a communication packet. The method includes receiving the target address, seeking and locating a matching address in an array of base address registers, directing the packet to the port associated with the matching address, determining the target address to be a valid address by comparing the target address with a limit address associated with the matching base address, and nullifying the match if the target address is greater than the limit address.

Abstract: A method and device for handling catastrophic switch routing errors. Upon receiving a communication packet in a packet switching device, a port in the switching device is matched with the destination address of the communication packet and a routing code is generated to direct routing of the communication packet internally to the packet switching device. The routing code is analyzed to determine whether a catastrophic routing condition exists in the routing code. If no catastrophic routing condition exists, the routing is executed. However, when there is a catastrophic routing condition, execution of the routing of the communication packet is prevented.

Abstract: A test circuit determines whether a frequency of an output clock signal of a clock circuit is above an output threshold frequency. An input clock signal of the clock circuit is set to an elevated frequency that is higher than a specified frequency. A first counter counts the number of clock cycles of the input clock signal in a test interval to within a tolerance of the elevated frequency. The tolerance of the elevated frequency is higher than a tolerance of the specified frequency. A second counter counts the number of clock cycles of a feedback clock signal in the test interval. A comparator determines whether the frequency of the output clock signal is above the output threshold frequency based on the number of clock cycles of the input clock signal and the number of clock cycles of the feedback clock signal.

Abstract: A packet switch includes an error management module in addition to various components that facilitate routing of data packets through the packet switch. The components generate error codes indicating errors occurring in the packet switch and provide the error codes to the error management module. The error management module select error codes generated by the components and generates an error log based on the selected error codes. Each component is inhibited from providing the same error code to the error management module more than once until the component receives an acknowledgement for that error code from the error management module. A user can access the error log during operation of the packet switch to monitor performance of the packet switch.

Abstract: An integrated circuit includes a phase step generator and a clock circuit. The phase step generator generates an input clock signal based on a reference clock and the clock circuit generates an output clock signal based on the input clock signal. Additionally, the clock circuit generates a feedback clock signal based on the output clock signal and locks a phase of the feedback clock signal with a phase of the input clock signal. In response to an assertion of a trigger signal, the phase step generator extends a phase of the input clock signal by inserting a phase step into the reference clock signal. A bandwidth of the clock circuit is determined based on the output clock signal after assertion of the trigger signal.

Abstract: A comparator generates lower and upper reference voltages to establish an amplitude hysteresis. A first comparator circuit generates a first comparison signal indicating whether an input signal is above the upper reference voltage. A second comparator circuit generates a second comparison signal indicating whether the input signal is below the lower reference voltage. Further, the first and second comparison signals may be low-pass filtered to establish a time hysteresis. A latch is set to a first state if the first control signal indicates the input signal is above the upper reference voltage. The latch is set to a second state if the second control signal indicates the input signal is below the lower reference voltage. In some embodiments, the comparator has a rail-to-rail common mode input voltage range, a low-power mode of operation, and is self-biased to compensate for temperature, voltage, and process characteristics.