Abstract: Methods for image characterization image search are provided in the invention. An input image comprising a plurality of pixels is provided. The image is converted into Hue Saturation Value (HSV) model, each pixel comprises a hue level, a saturation level and a brightness level. Characteristics of the input image are then calculated based on the hue level, saturation level and the brightness level.

Abstract: Included are embodiments for processing video data. At least one embodiment includes receive logic configured to receive the video data chosen from a plurality of formats and filter logic configured to filter the video data according to the instruction. Similarly, some embodiments include transform logic configured to transform the video data according to the instruction, where the instruction contains a mode indication in which the filter logic and the transform logic execute based on the format of the video data.

Abstract: A control method for a memory is provided. The memory includes a plurality of storage units, each storing a plurality of bits. In a read mode, a read command is provided to the memory. The value of a most significant bit (MSB) of each storage unit is obtained and recorded. The value of the most significant bits is output. The value of a neighboring bit of each storage unit is obtained and recorded. The neighboring bit neighbors the most significant bit. The value of the neighboring bits is output.

Abstract: Systems and methods for thread group kickoff and thread synchronization are described. One method is directed to synchronizing a plurality of threads in a general purpose shader in a graphics processor. The method comprises determining an entry point for execution of the threads in the general purpose shader, performing a fork operation at the entry point, whereby the plurality of threads are dispatched, wherein the plurality of threads comprise a main thread and one or more sub-threads. The method further comprises performing a join operation whereby the plurality of threads are synchronized upon the main thread reaching a synchronization point. Upon completion of the join operation, a second fork operation is performed to resume parallel execution of the plurality of threads.

Abstract: A scenario simulation system for a multimedia device is disclosed. An outline detection device separates a plurality of images from an image source to a plurality of foreground and background images which are stored in a foreground storage medium and a background storage medium respectively. A foreground selector selects a foreground image, and a background selector selects a background image. An image mixer mixes the foreground image with the background image as an output image. An image output module transmits the output image for replacing a real image to a remote multimedia device.

Abstract: Resuming from a sleep state. A request may received to resume operation of a computer system from a sleep state to an executing state. A restoring process may be initiated to restore the computer system to an executing state. The restoring process may include loading information from a nonvolatile memory medium to a computer system memory medium. A request may be received from a processor of the computer system to access the computer system memory medium. The request may require access to a portion of the computer system memory medium in the executing state, and may be received prior to completion of the restoring process. It may be determined if the portion of the computer system memory medium has been restored. If the portion of the computer system memory medium has not been restored, the portion of the computer system memory medium may be restored from the nonvolatile memory medium ahead of other portions in the restoring process.

Abstract: A clock generator is provided. The clock generator includes a crystal oscillator, an inverter coupled to the crystal oscillator in parallel, a first circuit and a second circuit. The crystal oscillator has a first terminal and a second terminal. The inverter generates a first signal and a second signal at the first and second terminals of the crystal oscillator, respectively. The first circuit coupled to the first terminal of the crystal oscillator generates a first clock signal with a constant frequency according to the first signal. The second circuit coupled to the second terminal of the crystal oscillator generates a second clock signal with a variable frequency according to the second signal.

Abstract: A microprocessor includes a plurality of execution units configured to receive instructions and operands thereof and to execute the instructions. An instruction scheduler issues the instructions to the execution units and selects sources of the instruction operands. At least one of the execution units detects one of the operands of one of the instructions is a denormal operand, generates an indication that the instruction needs to be replayed in response to detecting the denormal operand, and provides the denormal operand to the instruction scheduler in response to detecting the denormal operand, rather than normalizing the denormal operand. The instruction scheduler normalizes the denormal operand, in response to the indication, and causes the normalized operand, rather than the denormal operand, to be provided to the execution unit when the instruction is replayed.

Abstract: A multi-core microprocessor includes first and second processing cores and a bus coupling the first and second processing cores. The bus conveys messages between the first and second processing cores. The cores are configured such that: the first core stops executing user instructions and interrupts the second core via the bus, in response to detecting a predetermined event; the second core stops executing user instructions, in response to being interrupted by the first core; each core outputs its state after it stops executing user instructions; and each core waits to begin fetching and executing user instructions until it receives a notification from the other core via the bus that the other core is ready to begin fetching and executing user instructions. In one embodiment, the predetermined event comprises detecting that the first core has retired a predetermined number of instructions. In one embodiment, microcode waits for the notification.

Abstract: A microprocessor configured to access an external memory includes a first-level cache, a second-level cache, and a bus interface unit (BIU) configured to interface the first-level and second-level caches to a bus used to access the external memory. The BIU is configured to prioritize requests from the first-level cache above requests from the second-level cache. The second-level cache is configured to generate a first request to the BIU to fetch a cache line from the external memory. The second-level cache is also configured to detect that the first-level cache has subsequently generated a second request to the second-level cache for the same cache line. The second-level cache is also configured to request the BIU to refrain from performing a transaction on the bus to fulfill the first request if the BIU has not yet been granted ownership of the bus to fulfill the first request.

Abstract: A leadframe for a leadframe type package includes a chip base, and leads constituting lead lanes. One lead lane includes a pair of first differential signal leads, a pair of second differential signal leads, a pair of third differential signal leads between which and the pair of first differential signal leads is arranged the pair of second differential signal leads and a first power lead arranged between the pair of first and second differential signal leads. One of the pairs of differential signal leads has half-duplex transmission mode and two of the other pairs of differential signal leads have full-duplex transmission mode.

Abstract: The present invention is directed to a universal serial bus (USB) transaction translator and an associated IN isochronous transaction method. A device interface is coupled to a device via a device bus, and a host interface is coupled to a host via a host bus, wherein the host USB version is higher than the device USB version. At least two buffers configured to store data are disposed between the device interface and the host interface. A controller stores the data in the buffers alternately. A register is used to record device bus information. Before the host sends an IN packet, the controller pre-fetches data from the device according to the device bus information and then stores the data in the buffers; the controller responds with the pre-fetched data to the host after the host sends the IN packet.

Abstract: A reconstructable geometry mapping method is provided. The reconstructable geometry mapping method includes: extracting geometry information of a plurality of occluding geometry shapes of an object's front-face with respect to a light source's point of view; performing a consistency test on a testing pixel so as to determine an occluding geometry shape corresponding to the testing pixel from the object's front-face among the plurality of occluding geometry shapes, in which the occluding geometry shape includes an occluding point, and the testing pixel overlaps with the occluding point when viewing from the light's point of view; reconstructing a depth value of an occluding point corresponding to the testing pixel; and performing a shadow determination of the testing pixel.

Abstract: An apparatus for extracting instructions from a stream of undifferentiated instruction bytes in a microprocessor having an instruction set architecture in which the instructions are variable length. Decode logic decodes the instruction bytes of the stream to generate for each a corresponding opcode byte indictor and end byte indicator and receives a corresponding taken indicator for each of the instruction bytes. The taken indicator is true if a branch predictor predicted the instruction byte is the opcode byte of a taken branch instruction. The decode logic generates a corresponding bad prediction indicator for each of the instruction bytes. The bad prediction indicator is true if the corresponding taken indicator is true and the corresponding opcode byte indicator is false. The decode logic sets to true the bad prediction indicator for each remaining byte of an instruction whose opcode byte has a true bad prediction indicator.

Abstract: A microprocessor integrated circuit includes first and second processors. The first processor is configured to detect that the second processor has not retired an instruction for a predetermined amount of clock cycles and to responsively reset the second processor. The microprocessor integrated circuit also includes microcode. The second processor is configured to execute the microcode in response to a reset of the second processor. The microcode is configured to read debug information within the microprocessor integrated circuit and to output the debug information external to the microprocessor integrated circuit in response to determining that the reset was performed by the first processor.

Abstract: An out-of-order execution microprocessor for reducing load instruction replay likelihood due to store collisions. A register alias table (RAT) is coupled to first and second queues of entries and generates dependencies used to determine when instructions may execute out of order. The RAT allocates an entry of the first queue and populates the allocated entry with an instruction pointer of a load instruction, when it determines that the load instruction must be replayed. The RAT allocates an entry of the second queue when it encounters a store instruction and populates the allocated entry with a dependency that identifies an instruction upon which the store instruction depends for its data. The RAT causes a subsequent instance of the load instruction to share the dependency when it encounters the subsequent instance of the load instruction and determines that its instruction pointer matches the instruction pointer of an entry of the first queue.

Abstract: Determining and simultaneously using a circuit for a mobile device couple to a base station, the circuit may comprise an identification signal detector for receiving a first identification signal corresponding to a first module and a second identification signal corresponding to a second module in the mobile device. The circuit may comprise a receiver for receiving a plurality of signals from the base station; said plurality of signals is configured to set up communication between the mobile device and the base station. The circuit may comprise a calculator for calculating a plurality of parameters in response to the first identification signal, second identification signal and said plurality of signals received from said base station. The circuit may also comprise a processor for attaching the first and second module to the base station simultaneously in response to a plurality of slots by time multiplexing and the plurality of parameters.

Abstract: A Dynamic Random Access Memory (DRAM) controller for controlling read and write operations of a DRAM includes a storage unit and a control unit. The storage unit stores a first predetermined size of data including data written into the DRAM in response to a previous partial write request, and stores the corresponding store addresses of the first predetermined size of data in the DRAM. The control unit, in response to a read request, determines whether there exists any address in the store addresses equal to a read address of the read request, and read data corresponding to the read address from the storage unit when there exists same address in the store addresses equal to the read address.

Abstract: The present invention is directed to a universal serial bus (USB) transaction translator and a micro-frame synchronization method. A device interface is coupled to a device via a device bus, and a host interface is coupled to a host via a host bus, wherein the host USB version is higher than the device USB version. At least two buffers configured to store data are disposed between the device interface and the host interface. A controller stores the data in the buffers alternately. A start-of-frame (SOF) counter is used to count the SOF packets, wherein the counting value of the SOF counter is compared to a predefined value. Specifically, the controller resets a SOF timer for sending the SOF packet when the counting value achieves the predefined value or is greater than the predefined value, such that the SOF packet and an isochronous timestamp packet (ITP) from the host are sent at the same time.

Abstract: A serial bus device for transmitting a packet to a link partner is provided. The serial bus device includes a processing unit and a clock difference compensation unit coupled to the processing unit. The processing unit generates the packet. The clock difference compensation unit determines whether to transmit at least one skip ordered set to the link partner prior to the packet according to a type of the packet, so as to compensate for a clock difference for the link partner.