摘要:
An object of the present invention is to detect a failure of a camera input in a system including a camera or a video transmission path (camera input). An image processor includes a hash derivation circuit having a computing unit that calculates hash values on an input screen and a storage circuit that stores the hash values. The image processor compares the hash values between multiple frames so as to decide whether the screens have changed or stopped. A failure is detected when the screens are stopped.
摘要:
A plurality of transfer modules (402-0 to 402-M) that transfer data between processing units are provided so as to respectively correspond to a plurality of processing units (401-0 to 401-M). First ring buses (403-0 to 403-M) connect, for each of the processing units (401-0 to 401-M), subunits within a corresponding processing unit and the transfer module corresponding to the processing unit so that they form a ring shape. The plurality of transfer modules (402-0 to 402-M) are connected so that they form a ring shape by a second ring bus (404).
摘要:
In a data processing device comprising a memory controller controlling writing/reading of data to/from the memory, a processor requesting writing/reading of data, and an error detection module requesting writing/reading of data to/from the memory controller in accordance with a request from the processor, an error detection module calculates a first error detection code of the first data having a write request from the processor, reads the second data having a read request from the processor from the memory, calculates a second error detection code from the read data, compares the first error detection code and the second error detection code, and transmits the result of the comparison to the external module.
摘要:
To provide a semiconductor device which suppresses a delay in processing. The semiconductor device is equipped with a plurality of read units which read data stored across a plurality of banks in a memory having the banks, and an access method managing section which, when one of the read units reads the data, determines a read start bank number being a bank number to start reading according to operation situations of the read units excepting the one read unit, and instructs the determined read start bank number to the one read unit.
摘要:
In an image processing device, a motion image decoding processing unit extracts a feature amount of a target image to be decoded from an input stream, and changes a read size of a cache fill from an external memory to a cache memory, based on the feature amount. The feature amount represents an intra macro block ratio in, for example, one picture (frames or fields), or a motion vector variation. When the intra macro block ratio is high, the read size of the cache fill is decreased.
摘要:
Provided is a data processing device that reduces the amount of memory access in a case where data and an error control code are to be stored in a memory. The processing device includes a data compression section, a code generation section, a binding section, and a transfer section. The data compression section generates second data by performing a predetermined compression process on first data that is to be stored in a memory and of a predetermined data length. The code generation section generates an error control code for the first data or the second data. The binding section generates third data by binding the second data generated by the data compression section to the error control code generated by the code generation section. The transfer section transfers the third data generated by the binding section to the memory in units of the predetermined data length.
摘要:
Regarding association between an area where compressed data is stored and an area where auxiliary information required to access the compressed data is stored, it is necessary to manage the association by software for each processing unit, so that the processing becomes complicated. A management unit memory area including a compressed data storage area and an auxiliary information storage area including auxiliary information are defined on a memory space. By calculating an auxiliary information address from an address indicating a location on a memory where a management unit memory space is set, an address of the auxiliary information storage area, and an address of the compressed data, the compressed data and the auxiliary information are associated with each other and the auxiliary information is read.
摘要:
There is a problem that memory protection against access to a shared memory by a sub-arithmetic unit used by a program executed in a main-arithmetic unit cannot be performed in a related-art semiconductor device. According to one embodiment, a semiconductor device includes a sub-arithmetic unit configured to execute a process of a part of a program executed by a main-arithmetic unit, and a shared memory shared by the main-arithmetic unit and the sub-arithmetic unit, in which the sub-arithmetic unit includes a memory protection unit configured to permit or prohibit access to the shared memory based on an access permission range address value provided from the main-arithmetic unit, the access to the shared memory being access that arises from a process executed by the sub-arithmetic unit.
摘要:
In a semiconductor device, a load of CPU required for arbitration when using a shared resource is reduced. The semiconductor device includes a CPU section and a hardware IP. In the CPU section, software modules are executed. The hardware IP includes a storage unit, an arbitration unit, and a calculation unit. The storage unit includes control receiving units that receive operation requests transmitted by the software modules, respectively. The calculation unit performs processing based on an operation request transmitted from the control receiving units. The arbitration unit controls information transmission between the control receiving units and the calculation unit so that the calculation unit receives only an operation request from any one of the control receiving units.