Abstract: A system and method is disclosed for providing a redistribution metal layer in an integrated circuit. The redistribution metal layer is formed from the last metal layer in the integrated circuit during manufacture of the integrated circuit before final passivation is applied. The last metal layer provides sites for solder bump pads used in flip chip interconnection. The redistribution metal layer can be (1) a flat layer deposited over the next to last metal layer through an opening in a dielectric layer, or (2) deposited over an array of vias connected to the next to last metal layer. Space between the solder bump pads is deposited with narrower traces for connecting active circuit areas below. A final passivation layer is deposited to ensure product reliability.

Abstract: A multi-bit trie network search engine is implemented by a number of pipeline logic units corresponding to the number of longest-prefix strides and a set of memory blocks for holding prefix tables. Each pipeline logic unit is limited to one memory access, and the termination point within the pipeline logic unit chain is variable to handle different length prefixes. The memory blocks are coupled to the pipeline logic units with a meshed crossbar and form a set of virtual memory banks, where memory blocks within any given physical memory bank may be allocated to a virtual memory bank for any particular pipeline logic unit. An embedded programmable processor manages route insertion and deletion in the prefix tables, together with configuration of the virtual memory banks.

Abstract: An electronic system, an integrated circuit and a method for display are disclosed. The electronic system contains a first device, a memory and a video/audio compression/decompression device such as a decoder/encoder. The electronic system is configured to allow the first device and the video/audio compression/decompression device to share the memory. The electronic system may be included in a computer in which case the memory is a main memory. Memory access is accomplished by one or more memory interfaces, direct coupling of the memory to a bus, or direct coupling of the first device and decoder/encoder to a bus. An arbiter selectively provides access for the first device and/or the decoder/encoder to the memory based on priority. The arbiter may be monolithically integrated into a memory interface. The decoder may be a video decoder configured to comply with the MPEG-2 standard. The memory may store predicted images obtained from a preceding image.

Abstract: An apparatus is provided that includes a light source, an array of light-reflecting devices, and a processor for positioning the light-reflecting devices so as to display an image on the display screen. Each of the light-reflecting devices selectively reflects the light from the light source onto a corresponding pixel of a display screen. The processor positions a first of the light-reflecting devices such that light from the light source is reflected by the first light-reflecting device onto a first pixel of the display screen, which is different than the pixel of the display screen that corresponds to the first light-reflecting device.

Abstract: There is disclosed a data processor having a clustered architecture that comprises at least one branching cluster, at least one non-branching cluster and remote conditional branching control circuitry. Each of the clusters is capable of computing branch conditions, though only the branching cluster is operable to perform branch address computations. The remote conditional branching control circuitry, which is associated with each of the clusters, is operable in response to sensing a conditional branch instruction in a non-branching cluster to (i) cause the branching cluster to compute a branch address and a next program counter address, (ii) cause the non-branching cluster to compute a branch condition, and (iii) communicate the computed branch condition from the non-branching cluster to the branching cluster. The data processor then uses the computed branch condition to select one of the branch address or the next program counter address.

Abstract: The invention provides a method and system for operating a pipelined microprocessor more quickly, by detecting instructions that load from identical memory locations as were recently stored to, without having to actually compute the referenced external memory addresses. The microprocessor examines the symbolic structure of instructions as they are encountered, so as to be able to detect identical memory locations by examination of their symbolic structure. For example, in a preferred embodiment, instructions that store to and load from an identical offset from an identical register are determined to be referencing the identical memory location, without having to actually compute the complete physical target address.

Abstract: An apparatus and method for transmitting and recovering encoded data streams across Physical Medium Attachments (PMA) are provided. The data stream includes a plurality of data blocks. The method of transmitting includes tagging at least some of the plurality of data blocks in the data stream. The method also includes splitting the data stream into first and second lanes of data blocks. The method further includes transmitting the first lane of data blocks to a first PMA and the second lane of data blocks to a second PMA.

Abstract: A method includes extracting at least one object file from a library of object files. The method also includes identifying an interprocedural optimization associated with a plurality of object files. The plurality of object files includes the at least one extracted object file. The method further includes invoking recompilation of at least one of the plurality of object files to implement the identified interprocedural optimization. In addition, the method includes generating at least one executable file using the at least one recompiled object file. The plurality of object files could include interprocedural summary information generated by a compiler during a compilation of at least one source file and a compiler internal representation associated with the compiler during the compilation. The interprocedural optimization could be identified using the interprocedural summary information, and the at least one recompiled object file could be generated using the compiler internal representation.

Abstract: A phase-acquisition (PA) loop for a read channel comprises an accumulator, a comparator, and a filter. The accumulator holds an acquired phase-correction value corresponding to a difference between a phase of a sample clock and a phase of data carried by a read signal, and provides the acquired phase-correction value to a circuit that modifies the read signal to compensate for the phase difference. The comparator receives a reference phase-correction value that also corresponds to the difference between the phases of the sample clock and the data, and generates an error signal that is related to a difference between the reference and acquired phase-correction values. And the filter causes the acquired phase-correction value to have a predetermined relationship to the reference phase-correction value.

Abstract: A gain controller for a gain loop of a read channel includes a comparator circuit, an accumulator circuit, and a function circuit. The comparator circuit determines an error between an actual sample of a read signal and a corresponding ideal sample of the read signal, and the accumulator circuit holds a gain-correction value and adjusts the gain-correction value in response to the error. The function circuit generates a gain-correction signal by performing a predetermined mathematical operation involving the gain-correction value, and provides the gain-correction signal to a variable-gain amplifier that is operable to amplify actual samples of the read signal. Because such a gain controller allows one to locate the variable-gain amplifier (VGA) after the analog-to-digital converter (ADC) in a read channel, the gain controller may significantly reduce the latency of the gain-acquisition (GA) loop or the gain-tracking (GT) loop of the read channel.

Abstract: Counter-clockwise and clockwise quadrant transitions are detected and accumulated with respect to a received complex signal over a certain time period. These transitions may then be compared in order to obtain information indicative of both a magnitude and phase of a carrier frequency error for the received signal. Additionally, zero-crossings of the received complex signal over the same certain time period are detected and accumulated. The accumulated crossings provide information indicative of frequency offset magnitude. The determined magnitude and phase of the frequency error may then be used to adjust a local oscillator frequency to provide for improved receiver performance.

Abstract: Mutual capacitances between regions of a MOS device become substantial factors that limit the speed and performance of the device as the device dimensions are reduced in size. A MOS transistor with a shielding structure formed above the gate is described. The shielding structure is connected to ground and is configured to reduce at least some of these mutual capacitances.

Abstract: A packet based display interface configured to operate in a multimedia device in a network and methods to train the packet based display interface is disclosed. The packet based display interface includes a media transport block to communicate video packets across a first unidirectional link, a dual data transport block to communicate packet messages to and from client service blocks across a bidirectional link using multiple transport protocols, and a detection block to determine the addition or deletion of a network device using a second unidirectional link. Each transport protocol uses a different message format on the bidirectional link. The training methods include exchanging messages to determine transport protocol capabilities, training the bidirectional link and setting the transport protocols used.

Abstract: The addition of high throughput capability elements to beacon frames and peer link action frames in wireless mesh networks enable the utilization of desirable features without further modifications to the network. Rules can be established for high throughput mesh point protection in a mesh network, Space-time Block Code (STBC) operations and 20/40 MHz operation selections. However, features such as PSMP (power save multi-poll) and PCO (phased coexistence operations) are barred from implementation to prevent collisions.

Abstract: First and second integer transform matrices can be used to approximate the discrete cosine transform. An input matrix of data is multiplied by a first transform matrix of integers to produce an intermediate matrix of data. The intermediate matrix is multiplied by a second transform matrix of integers to produce a transform result matrix of data. The multiplications by the first and second transform matrices can be pipelined to increase throughput. A plurality of transform data paths can also be provided in parallel to increase throughput.

Abstract: There is disclosed a data processor that executes variable latency load operations using bypass circuitry that allows load word operations to avoid stalls caused by shifting circuitry.

Abstract: A system and method for correcting errors in an ECC block using soft-decision data. In an embodiment, a soft-decision ECC decoding method, uses “soft” data indicative of how reliable bits of data are when read out. Such a method may use an update module for receiving and manipulating the soft-decision data and iteratively change bits or groups of bits based upon an ordering of the reliability factors. Then a calculator module may determine the total number of errors still remaining after each iteration. Determining just the total number of errors instead of the actual locations is far less computationally intensive, and therefore, many combination of potential flip-bit combination may be analyzed quickly to determine if any combination might reduce the total number of errors enough to be handled by the conventional hard-decision ECC decoding method.

Abstract: A dielectric layer overlies a semiconductor substrate. The substrate has components and appropriate contacts formed therein. The dielectric layer electrically insulates the substrate and components from overlying conductive interconnect layers. A barrier layer is arranged over the dielectric layer to isolate the interconnect layers from other structures. A copper layer is then deposited over the barrier layer and thick interconnect lines having a first width and a first height are realized. Then, the barrier layer is etched using one of many alternative techniques. The barrier layer has a second width and a second height wherein the second width of the barrier liner is selected to be greater than the first width of the thick copper interconnect.

Abstract: A system and method for correcting errors in an ECC block using erasure-identification data when generating an error-locator polynomial. In an embodiment, a ECC decoding method, uses “erasure” data indicative of bits of data that are unable to be deciphered by a decoder. Such a method may use an Berlekamp-Massey algorithm that receives two polynomials as inputs; a first polynomial indicative of erasure location in the stream of bits and a syndrome polynomial indicative of all bits as initially determined. The Berlekamp-Massey algorithm may use the erasure identification information to more easily decipher the overall codeword when faced with a error-filled codeword.

Abstract: A 4-T SRAM cell in which two layers of permanent SOG (with an intermediate oxide layer) are used to provide planarization between the first and topmost poly layers.