Abstract: A pixel calculating device that performs vertical filtering on pixel data in order to reduce frame data in a vertical direction. The pixel calculating device includes a decoding unit 401 for decoding compressed video data to produce frame data, frame memory 402 for storing the frame data, a filtering unit 403 for reducing the frame data in a vertical direction by the vertical filtering to produce a reduced image, buffer memory 404 for storing the reduced image outputted from filtering unit 403, and a control unit 406 for controlling filtering unit 403 based on a decoding state of the video data by decoding unit 401 and a filtering state of the frame data by filtering unit 403, so that overrun and underrun do not occur in filtering unit 403.

Abstract: A pixel calculating device for performing vertical filtering that includes 16 pixel processing units 1 to 16 and an input buffer group 22 storing 16 pieces of pixel data and filter coefficients. Each of the pixel processing units performs operations using the pixel data and a filter coefficient supplied from input buffer group 22, and then acquires pixel data from an adjacent pixel processing unit. Further operations are performed by each of the pixel processing units using the acquired pixel data and operation results are accumulated. Filtering is carried out through a repetition of this acquiring and accumulation process, the number of taps being determined by the number of repetitions.

Abstract: The parallel execution processor 100 fetches a piece of instruction data. When the piece of instruction data includes only one instruction, the instruction decoding unit 120 assigns the one instruction to all the PEs. When the piece of instruction data includes two instructions, the instruction decoding unit 120 forms all the PEs into two groups, so as to assign one instruction to each group. By making it possible to execute, in parallel, not only one type of instruction but also instructions that are different from each other, it is possible to improve the utilization efficiency of the parallel execution processor 100.

Abstract: A processor according to the present invention includes a decoding unit 20, an operation unit 40 and others. When the decoding unit 20 decodes an instruction “vxaddh Rc, Ra, Rb”, an arithmetic and logic/comparison operation unit 41 and others (i) adds the higher 16 bits of a register Ra to the lower 16 bits of the register Rb, stores the result in the higher 16 bits of a register Rc, and in parallel with this, (ii) adds the lower 16 bits of the register Ra to the higher 16 bits of the register Rb, and stores the result in the lower 16 bits of the register Rc.

Abstract: A processor according to the present invention includes a decoding unit 20, an operation unit 40 and others. When the decoding unit 20 decodes Instruction vcchk, the operation unit 40 and the like judges whether vector condition flags VC0˜VC3 (110) of a condition flag register (CFR) 32 are all zero or not, and (i) sets condition flags C4 and C5 of the condition flag register (CFR) 32 to 1 and 0, respectively, when all of the vector condition flags VC0˜VC3 are zero, and (ii) sets the condition flags C4 and C5 to 0 and 1, respectively, when not all the vector condition flags are zero. Then, the vector condition flags VC0˜VC3 are stored in the condition flags C0˜C3.

Abstract: A data processor has sixteen processing elements that each include a register file and an arithmetic logic unit. A network unit connects between the register files of the processing elements and the arithmetic logic units of the processing elements. The network unit has a selector for simultaneously performing a plurality of data transfers which are each made from a register file of one processing element to an operation unit of another processing element. With the provision of this selector that can perform such simultaneous data transfers, the processing efficiency of the processing elements can be maintained even if a change occurs in operand assignments and the like.

Abstract: A processor for sequentially executing a plurality of programs using a plurality of register value groups stored in a memory that correspond one-to-one with the programs.

Abstract: A microprocessor comprises a calculation unit that (i) includes partial calculation units each operable to perform partial data calculation, and (ii) is operable to perform data calculation on N or less bits, where N is a total number of bits on which the partial calculation units are to perform data calculation. The microprocessor, when having the calculation unit perform data calculation according to an instruction fetched from a memory, controls the partial calculation units depending on a bit width mode selected in terms of a number of bits on which data calculation is to be performed, so as to either (i) have all the partial calculation units operate, or (ii) suspend operation of a predetermined number of the partial calculation units, and have the rest of the partial calculation units operate.

Abstract: A circuit group control system which receives from a master processor a first command sequence and a second command sequence each of which is composed of a plurality of commands, each command being to be executed by one of a plurality of circuits, and causes any available circuits to execute the commands one by one in order of arrangement in each command sequence. The circuit group control system achieves concurrent execution of a plurality of command sequences by causing a circuit (a second circuit) to execute a command in the second command sequence while another circuit (a first circuit) is executing another command in the first command sequence.

Abstract: The present invention provides an image decoding apparatus that realizes speed-up processing of taking out an MR (macroblock remainder) from a fixed length unit that consists of a first DCT block and the MR, without increasing cost. A Setup processor 3 outputs one out of a plurality of fixed length units that constitute an SB (synchronized block). First, calculation is performed for a length from a beginning of the fixed length unit to a EOB (end of block) that is included in the fixed length unit. The calculated length is then used as an offset in taking out the MR. Then an end portion of a second DCT block that is included in the MR is combined with a corresponding beginning portion of the second DCT block, in order to obtain the complete second DCT block. The complete second DCT block is outputted to a variable length code decoder 13.

Abstract: A pixel calculating device that performs vertical filtering on pixel data in order to reduce frame data in a vertical direction. The pixel calculating device includes a decoding unit 401 for decoding compressed video data to produce frame data, frame memory 402 for storing the frame data, a filtering unit 403 for reducing the frame data in a vertical direction by means of the vertical filtering to produce a reduced image, buffer memory 404 for storing the reduced image outputted from filtering unit 403, and a control unit 406 for controlling filtering unit 403 based on a decoding state of the video data by decoding unit 401 and a filtering state of the frame data by filtering unit 403, so that overrun and underrun do not occur in filtering unit 403.

Abstract: When an OSD data storage area for storing OSD data needs to be reserved, an area of a frame storage apparatus that should store macroblocks corresponding to an invisible area on a screen is allocated as the OSD data storage area. There is no degradation in picture quality. When doing so, the data reduction control unit 64 receives an instruction to reserve the OSD data storage area and discards the corresponding macroblocks. The OSD data access unit 63 writes the OSD data into an area of the frame storage apparatus that was assigned to store the discarded macroblocks.

Abstract: The speed of decoding processing for variable-length coded image data is improved.

Abstract: A pixel calculating device for performing vertical filtering that includes 16 pixel processing units 1 to 16 and an input buffer group 22 storing 16 pieces of pixel data and filter coefficients. Each of the pixel processing units performs operations using the pixel data and a filter coefficient supplied from input buffer group 22, and then acquires pixel data from an adjacent pixel processing unit. Further operations are performed by each of the pixel processing units using the acquired pixel data and operation results are accumulated. Filtering is carried out through a repetition of this acquiring and accumulation process, the number of taps being determined by the number of repetitions.

Abstract: A first bit string extracting unit extracts a first bit string. A first bit length judging unit detects a first codeword from the first bit string. A first decoding unit generates a first run-level pair from the first codeword. A second bit string extracting unit extracts a second bit string. A second bit length judging unit detects a second codeword from the second bit string. A second decoding unit generates a second run-level pair from the second codeword. A first inverse quantizing unit inverse quantizes the first level to obtain a DCT coefficient. A second inverse quantizing unit inverse quantizes the second level to obtain a DCT coefficient. A second buffer controller writes the DCT coefficients and their first buffer addresses into a second buffer. A first buffer controller reads the DCT coefficients and the first buffer addresses from the second buffer and writes the DCT coefficients into a first buffer at the respective first buffer addresses.

Abstract: A transfer-target unit outputs commands for data reading and data writing. An address generator generates control signals in accordance with the commands, and outputs the number of bytes of data first transferred by read access. A command generator generates control commands in accordance with the control signals to control an SDRAM. At this time the command generator judges the number of transferred bytes to control so that the SDRAM executes instructions in order from an instruction which is the most efficient in data transfer. That is, in the case where data is read across a bank boundary, the command generator judges which is to be executed first between read processing in a bank 0 and active processing in a bank1, to control the SDRAM. A data processor mediates data transfer between the transfer-target unit and the SDRAM in accordance with the control commands.

Abstract: Bitstream analyzing unit 111 fetches a coded block pattern and a coded quantized DCT coefficient from each block in a bitstream. Entropy decoding unit 112 decodes the coded block pattern into a block pattern and decodes the coded quantized DCT coefficient into pairs of a run length and an effectiveness factor. Dequantization unit 115 generates orthogonal transformation coefficients from the pairs of a run length and an effectiveness factor. Inverse Discrete Cosine Transform (IDCT) unit 110 generates a difference image from the orthogonal transformation coefficients. Decode controlling unit 110 instructs first selecting unit 118 to select constants “0”output from first constant generating unit 117 when the image is a “skipped” block. Image storage unit 120 stores a plurality of reference frame pictures having been decoded.