摘要:
The present invention discloses a speculative execution processor including a plurality of executing units for processing in parallel a plurality of instructions in an instruction sequence stored in its memory. The processor comprises an instruction type distinguishing device for distinguishing a type of a conditional branch instruction included in the unexecuted instruction sequence, the condition of the conditional branch instruction depending on another instruction, an instruction parallel-issuing device for issuing in parallel instructions included in a succeeding instruction sequence to be executed following the conditional branch instruction and/or instructions included in an instruction sequence to be executed after the branching to the executing units while whether or not to branch is not determined, a branching determining device for determining whether to branch when the another instruction is executed, and an execution result managing device for identifying whether the execution results of the instruction sequences are effective based on the determining results of the branching determining device.
摘要:
In a cache memory simultaneously conducting updating for a miss and a decision on a miss for the subsequent address, a write flag generated by a control unit is written in a valid flag field. Based on this operation, during an access to an external memory at an occurrence of a miss, a tag field and the valid flag field are simultaneously updated. When updating a data field, a read operation is achieved on the tag and valid flag fields to decide occurrence of miss. Thus, an external memory access for a miss at a next address can be executed at an earlier point of time. Moreover, by the provision of a data latch disposed for an output from the data field, and by reading data at a next address and keeping it in the data latch during a memory read cycle, succeeding hit data can be outputted immediately after a miss processing is completed. Furthermore, also in a cache memory having a plurality of tag fields and a plurality of valid flag fields, the updating for a miss and the decision on a miss for a next address can be attained at the same time.
摘要:
A two-dimensional filter arithmetic device comprises a picture memory, a line memory, a vertical filtering unit which includes nine first filter modules installed in parallel, a buffer for timing adjustments, and a horizontal filtering unit which includes four second filter modules installed in parallel. From the line memory, the pixel values of nine full pels per line are inputted in parallel to the vertical filtering unit, nine vertically-filtered values of half pels are generated and inputted to the horizontal filtering unit; thereby, four two-dimensionally-filtered values of half pels are generated.
摘要:
The present invention provides a processor that cyclically executes a plurality of threads in accordance with an execution time allocated to each of the threads, comprising a reconfigurable integrated circuit. The processor stores circuit configuration information sets respectively corresponding to the plurality of threads, reconfigures a part of the integrated circuit based on the circuit configuration information sets, and sequentially executes each thread using the integrated circuit that has been reconfigured based on one of the configuration information sets that corresponds to the thread. While executing a given thread, the processor selects a thread to be executed next, and reconfigures a part of the integrated circuit where is not currently used for execution of the given thread, based on a circuit configuration information set corresponding to the selected thread.
摘要:
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.
摘要:
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. The processor includes a plurality of register groups; a select/switch unit operable to select one of the plurality of register groups as an execution target register group on which a program execution is based, and to switch the selection target every time a first predetermined period elapses; a restoring unit operable to restore, every time the switching is performed, one of the register value groups into one of the register groups that is not selected as the execution target register group; a saving unit operable to save, prior to the restoring, register values in the register group targeted for restoring, by overwriting a register value group in the memory that corresponds to the register values; and a program execution unit operable to execute, every time the switching is performed, a program corresponding to a register value group in the execution target register group.
摘要:
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.
摘要:
The present invention provides an integrated circuit for video/audio processing in which the design resources obtained by the development of video/audio devices can be used also for other types of video/audio devices. The integrated circuit comprises a microcomputer block 2 including a CPU, a stream I/O block 4 for inputting/outputting video and audio streams to and from an external device, a media processing block 3 for executing the media processing including at least one of the compression and decompression of the video and audio streams, etc. inputted to the stream I/O block 4, an AV IO block 5 for converting the video and audio streams subjected to the media processing in the media processing block 3 into video and audio signals and outputting these signals to the external device, etc, and a memory IF block 6 for controlling the data transfer between the microcomputer block 2, the stream I/C block 4, the media processing block 3 and the AV IO block 5 and an external memory 9.
摘要:
A cache memory of the present invention includes: for each cache entry, way 0 to way 3 which hold use flags U indicating whether or not the use flags U have been accessed; and a control unit which: updates, when a cache entry is hit, a use flag U corresponding to the hit cache entry so that the use flag U indicates that the cache entry has been accessed; and reset, in the case where all other use flags in the same set indicates that the cache entries have been accessed herein, the all other use flags so that the use flags indicate that the cache entries have not been accessed; and select a cache entry to be replaced from among the cache entries corresponding to the use flags indicating that the cache entries have not been accessed.
摘要:
A transcoder for resizing video data and outputting the resized video data to a reproduction apparatus. The reproduction apparatus reproduces the resized video data by repeating a display period and a non-display period alternately. The transcoder includes: a resizing unit that resizes the video data; and a control unit that causes the resizing unit to resize the video data to first video data having a first resolution so that the reproduction apparatus displays one image during each display period, and causes the resizing unit to resize, during each period between the resizing of the video data to the first video data, the video data to second video data having a second resolution that is lower than the first resolution.