摘要:
The present invention relates to a video processing device for processing data corresponding to a sequence of pictures according to a predictive block-based encoding technique. Said device comprises a processing unit (20) including a reconstruction circuit (16) for reconstructing pictures from decoded data and an external memory (1) for storing reference pictures delivered by the reconstruction circuit. The processing unit further comprises a memory controller (11) for controlling data exchange between the processing unit and the external memory, a cache memory (17) for temporarily storing data corresponding to a prediction area, said data being read out from the external memory via the memory controller, and a motion compensation circuit (14) for delivering motion compensated data to the reconstruction circuit on the basis of the prediction area read out from the cache memory.
摘要:
The invention relates to a functional system comprising a set of functions (F, F′) which are to access a collective resource (RSRC), the system including an interface (INT) arranged to implement an access scheme (AS) including at least one state (I) defined by an order of priority for an arbitration according to which the functions (F, F′) can access the collective resource (RSRC), the state (I) being characterized in that, for at least one set of at least two functions (F), the access possibilities in read mode (F_R) and the access possibilities in write mode (F_W) have different priority levels, the access possibilities in read mode having consecutive priority levels higher than the priority levels of the access possibilities in write mode.
摘要:
A data processing arrangement comprises a plurality of processors and a memory interface via which the processors can access a collective memory. The memory interface comprises an interface memory (SRAM) for temporarily storing data belonging to different processors. The memory interface also comprises a control circuit for controlling the interface memory in such a manner that it forms a FIFO memory for each of the different processors. This makes to possible to realize implementations at a comparatively low cost in comparison with a memory interface comprising a separate FIFO memory for each processor.
摘要:
A data processing arrangement comprises a plurality of processors. These processors share a collective memory. The arrangement comprises private buses. A private bus enables data communication exclusively between a processor and the collective memory. A memory interface provides access to the collective memory in data bursts while it produces substantially steady data streams on the private buses.
摘要:
The present invention relates to a video processing device for processing data corresponding to a sequence of pictures according to a predictive block-based encoding technique. Said device comprises a processing unit (20) including a reconstruction circuit (16) for reconstructing pictures from decoded data and an external memory (1) for storing reference pictures delivered by the reconstruction circuit. The processing unit further comprises a memory controller (11) for controlling data exchange between the processing unit and the external memory, a cache memory (17) for temporarily storing data corresponding to a prediction area, said data being read out from the external memory via the memory controller, and a motion compensation circuit (14) for delivering motion compensated data to the reconstruction circuit on the basis of the prediction area read out from the cache memory.
摘要:
The invention relates to a method of detecting a watermark W, formed by a set of coefficients, in an information signal S, said watermark W and said information signal S being configured in the form of matrices SM M*M. The coefficients of the Fourier transform matrix of the matrix of the signal TSM and the coefficients of the Fourier transform matrix of the watermark matrix TWM are used in a calculation step CAL of the inverse transform matrix of the multiplication ITM of the transform matrix of the signal TSM and of the transform matrix of the watermark TWM, said calculation CAL being produced in sequences which each result in obtaining I columns of the inverse transform matrix of the multiplication, where M is a multiple of I and different from I. Said I columns are stored in a memory called internal memory and the detection step DET of the watermark is achieved with each sequence by detection of peaks of each set of the I columns while said I columns are present in the internal memory. The invention permits the use of a small-size internal memory.
摘要:
Access by a function to a collective resource is controlled by requiring that the function waits for a minimum number of clock cycles CLK called latency [LAT] between two successive accesses of the function. The function is further required to wait a number of cycles called penalty [PEN] which is higher than the latency between two successive accesses when a given number of successive accesses separated in time by at least the value of the latency has taken place beforehand. Registers [REG1, REG2] are decremented (or incremented) with each clock cycle and incremented (or decremented) with each access of the function to the collective resource. Tests [T1, T3, T4] are made with the contents of the registers to authorize [GRT] the access to the collective resource.
摘要:
A functional unit of a device is associated with a secret. Data stored in a memory location of the device is encrypted using the secret. The memory location of the device is accessible to other functional units; but without knowledge of the secret, the stored encrypted data is useless. The sharing of the secret creates a secure path between memory locations and functional units of the device while maintaining a unitary memory architecture. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.
摘要:
A functional unit of a device is associated with a secret. Data stored in a memory location of the device is encrypted using the secret. The memory location of the device is accessible to other functional units; but without knowledge of the secret, the stored encrypted data is useless. The sharing of the secret creates a secure path between memory locations and functional units of the device while maintaining a unitary memory architecture. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.
摘要:
A processing of data in cooperation with a memory (MEM), for example an MPEG decoding, has the following characteristic features. A processor (P) generates a logic request (LRQ). The logic request (LRQ) defines at least one characteristic (CAR) common to a group of data (GRP). An addressing circuit (AGA) generates a physical request (PRQ) on the basis of the logic request (LRQ). The physical request (PRQ) defines memory (MEM) addresses (A) relating to the group of data (GRP). A memory interface (INT) effects a transfer (TRNSFR) of the group of data (GRP) between the memory (MEM) and the processor (P) on the basis of the physical request (PRQ). Thus, the processor need not know how and where the data to be processed or having been processed are stored in the memory. This facilitates the design of a data processing device and, particularly, a family of such devices.