Abstract: A content addressable memory (CAM) device with selective error logging. The CAM device includes a CAM array and an error detection circuit coupled to receive a data value from a selected storage location within the CAM array, the error detection circuit being adapted to generate an error indication according to whether the data value includes an error. An error storage circuit is coupled to receive the error indication from the error detection circuit and is adapted to store an error address that corresponds to the selected storage location if the error indication indicates that the data value includes an error and if the error address is not already stored within the error storage circuit.

Abstract: Methods and apparatus are described relating to a crossbar which is operable to route data from any of a first number of input channels to any of a second number of output channels according to routing control information. Each combination of an input channel and an output channel corresponds to one of a plurality of links. The crossbar circuitry is operable to route the data in a deterministic manner on each of the links thereby preserving a partial ordering represented by the routing control information. Events on different links are uncorrelated.

Abstract: Methods and systems consistent with certain aspects related to the present invention provide a process for aligning service containers in a system environment. In one aspect of the invention, the process may include receiving first event data from an application service container providing application services during runtime of a web service and receiving second event data from a system service container providing system services during runtime of the web service. The process may also dynamically align the system and application services such that a predetermined service level associated with the web service is met during runtime based on at least one of the first and second event data.

Abstract: A large multimaster I2C bus system is partitioned into smaller bus segments. The bus segments are connected by bridges that isolate the segments and direct selected transactions and commands between the segments. The bridge may handle bus segment error conditions and particularly a hang on the Port B bus by attempting to cause any device on the bus segment to respond after the bus bridge has attempted to acquire the segment for a first predetermined period of time. If the bus responds within the first predetermined period of time, the bus bridge resets the bus segment.

Abstract: Systems, methods, and computer program products for command line prediction are disclosed. Commands entered on a command line are saved to a command log. The command log is analyzed to generate a plurality of n-gram tables that reflect the entries in the command log. The n-gram tables may be stored in a suitable memory. Subsequent command sequences entered on the command line may be compared to the n-gram tables to assess the likelihood of a command.

Abstract: One embodiment of the present invention provides a system that facilitates offloading message segmentation from a central processing unit onto a network interface card. The system operates by first receiving a TSO-send message at the network interface card, wherein the TSO-send message contains information about the message to be sent. Next, the system uses a header address from the TSO-send message to access a message header from memory using remote direct memory access. The system then uses a payload address from the TSO-send message to access a payload from memory that contains message data using remote direct memory access. Finally, the network interface card segments the payload into a set of maximum segment size (mss) segments and transmits the set of mss segments on the network.

Abstract: Devices utilize elements carried by a fluid in a microchannel to switch, attenuate, shutter, filter, or phase shift optical signals. In certain embodiments, a microchannel carries a gaseous or liquid slug that interacts with at least a portion of the optical power of an optical signal traveling through a waveguide. The microchannel may form part of the cladding of the waveguide, part of the core and the cladding, or part of the core only. The microchannel may also have ends or may be configured as a loop or continuous channel. The fluid devices may be self-latching or may be semi-latching. The fluid in the microchannel is moved using e.g., e.g., electrocapillarity, differential-pressure electrocapillarity, electrowetting, continuous electrowetting, electrophoresis, electroosmosis, dielectrophoresis, electro-hydrodynamic electrohydrodynamic pumping, magneto-hydrodynamic magnetohydrodynamic pumping, thermocapillarity, thermal expansion, dielectric pumping, and/or variable dielectric pumping.

Abstract: An invention is provided for creating a test summary report. A test application is executed on a platform, where the test application is executed using a status utility having functions that generates XML code. The test results are generated in a XML enabled format using the status utility, and are output to a test execution log file. The test execution log file is processed to generate a well-formed XML test reports file, which is then logically arranged to create a logically arranged XML test reports file. The logically arranged XML test reports file is converted into a HTML test summary report.

Abstract: One embodiment of the present invention provides a system that optimizes support vector machine (SVM) kernel parameters. During operation, the system assigns sets of kernel parameter values to each node in a multiprocessor system. Next, the system performs a cross-validation operation at each node in the multiprocessor system based on a data set. This cross-validation operation computes an error cost value reflecting the number of misclassifications that arise while classifying the data set using the assigned set of kernel parameter values. The system then communicates the computed error cost values between nodes in the multiprocessor system, and eliminates nodes with relatively high error cost values. Next, the system performs a cross-over operation in which kernel parameter values are exchanged between remaining nodes to produce new sets of kernel parameter values. This process is repeated until a global winning set of kernel parameter values emerges.

Abstract: One embodiment of the present invention provides a system that tests the quality and/or the reliability of a component. During operation, the system applies test conditions to a plurality of specimens of the component. While applying the test conditions, the system measures the same variable from each of the plurality of specimens. Next, the system computes a running average of the measured variable across the plurality of specimens. The system then computes residuals between the measured variable for each specimen and the running average. The system next determines from the residuals whether the associated specimens are degraded.

Abstract: A system in a package (SIP) or multi-chip module (200, 300, 400) (MCM) uses an electron beam (235, 335, 435) for electrically coupling between microcircuits (230, 330, 430) and (232, 332, 432). In one embodiment, the micro-circuits (230, 430) and (232, 432) can be configured in a side-by-side configuration. In another embodiment, the micro-circuits (330) and (332) can be configured in a chip-on-chip configuration. In yet another embodiment, the electron beam (435) can include a plurality of electron beams (436) and appear as ribbon shaped between two micro-circuits (430, 432). Further, the fabrication to form the electron source (234, 334, 434) and the deflector (261, 356, 461) can be at the final metallization step of the process.

Abstract: A component device carrier system includes a component device frame, a component device collar, and a clocked gear assembly providing motion in at least two directions. The component device collar is disposed around a component device. The component device collar is received in the component device frame to guide and position the component device. Gears on the component device frame mesh with the clocked gear assembly to enable motion in the at least two directions for positioning and securing the component device and for connecting and disconnecting the component device. A component carrier blade supports and arranges a plurality of component devices in at least one linear array.

Abstract: Techniques for modeling a circuit cell of a microprocessor or other integrated circuit for hierarchical powergrid analysis are disclosed herein. Distribution coefficients, used to distribute node voltages and capacitances to respective parts of the cell, are determined for each internal node of the cell. Current distribution coefficients may also be determined for each resistor in the cell. Using the distribution coefficients, internal cell capacitances are modeled as port capacitors. Resistive elements are modeled as a resistor network having no internal nodes. Transistor elements are modeled as port current sources. Such a model permits back calculation of internal node voltages and currents.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for performing a transaction across one or more resources. A connection is established to one or more resources that are required by a transaction. Each connected resource is registered with a transaction manager. One of the resources is designated as an anchor resource. The one or more resources are updated in accordance with the transaction; and a two-phase commit with each resource involved in the transaction is performed, wherein the anchor resource is committed to after every other resource has been committed to. Methods and apparatus, including computer program products, implementing and using techniques for recovering one or more interrupted transactions across one or more resources are also described.

Abstract: An input/output interface is used to transmit data between a transmitting circuit and a receiving circuit. Selectively during both system startup and system operation, a known bit pattern transmitted by the transmitting circuit is compared to a received bit pattern. The received bit pattern may be seen at the receiving circuit or a voltage regulator that is used to control the power supply level of the input/output interface. Dependent on the comparison of the known bit pattern and the received bit pattern, a bit error rate across the input/output interface is determined, in response to which the voltage regulator adjusts the power supply level of the input/output interface.

Abstract: A technique for improving multiple critical timing paths that exhibit similar characteristics has been discovered. The technique efficiently improves multiple critical timing paths by reducing the number of unique critical timing path patterns for analysis. In some embodiments of the present invention a method for use in connection with an integrated circuit design includes identifying distinct timing paths of the integrated circuit design. The distinct timing paths have timing violations. The method includes associating a first plurality of the distinct timing paths with a first set of timing paths. Individual ones of the first plurality belonging to a second set of timing paths and include a first common characteristic. The method includes improving the first set of timing paths based at least in part on an improvement to an individual timing path of the first set of timing paths.

Abstract: An electronic receiver for decoding data encoded into light is described. The light is received at an ultra-small resonant structure. The resonant structure generates an electric field in response to the incident light. An electron beam passing near the resonant structure is altered on at least one characteristic as a result of the electric field. Data is encoded into the light by a characteristic that is seen in the electric field during resonance and therefore in the electron beam as it passes the electric field. Alterations in the electron beam are thus correlated to data values encoded into the light.

Abstract: Access to external service providers is provided through portlets, where each portlet accessible by a user is represented on the display of the user device. Through use of a dynamic content channel, e.g., a portlet, a highly customizable content page may be produced for any individual client system. When a portlet is selected on a user device, the content associated with the portlet is retrieved and automatically transformed into data that can be displayed by that user device. Thus, a particular user device is not limited to accessing content in a format identical to that associated with the user interface in use on the user device. Consequently, the user's ability to access a wide variety of content sources independent of the characteristics of the particular user device is further enhanced.

Abstract: Committing data loaded on a device includes computing a program unit storage commitment fingerprint over a program unit if the program unit is finally loaded in a non-volatile memory on the device, associating the program unit storage commitment fingerprint with the program unit and storing the program unit storage commitment fingerprint.