JPS63204923A - Compressed data buffer managing device - Google Patents

Abstract

PURPOSE:To easily secure the continuity of compressed image data by dividing one image data into plural blocks and administering a compressed data buffer where the compressed data obtained by processing the respective blocks in terms of compression in parallel in plural data compressing units is stored. CONSTITUTION:One image data 1 is divided into plural blocks and the respective divided blocks are processed in terms of compression in parallel in plural data compressor 2. The compressed data of every compressed block is stored in the compressed data buffer 3 and the compressed data buffer is managed by providing an managing table where the compressed data buffer 3 is made to correspond to the blocks of the image data 1. Even if the order of the numbers of the buffers 3 where the data is stored differs, the continuity of the data of original image data can be secured by managing the buffer numbers for the original image data 1 with the managing table.

Description

[Detailed Description of the Invention] [Summary] The present invention divides one image data into multiple blocks, and manages a compressed data buffer that stores compressed data obtained by compressing each block in parallel using multiple data compressors. Even if there are multiple compressed data buffers that store one block of image data,
Continuity of compressed image data can be easily ensured using the management table.

C. Industrial Application Field] The present invention relates to a compressed data buffer management device for managing compressed data in image data processing.

For image data processing, for example, when processing drawings,
Since a large amount of data is handled as a collection of drawings whose pixels are unit data, high-speed processing is required.

When image data is processed by one data compressor or data decompressor, there is a limit to the processing speed.

For this reason, methods are used to increase processing speed by dividing the processing among multiple data compressors or data decompressors and processing them in parallel. However, the divided image data is compressed or decompressed separately. , it has become necessary to manage compressed or expanded data in correspondence with the original image data.

[Conventional technology]

Conventionally, one image data was processed by one data compressor or data decompressor, so compressed or decompressed data that is input to and output from the data compressor or data decompressor is processed in series.

[Problem that the invention seeks to solve]

In this conventional method, image data is input to a data compressor, compressed, and stored in a compression buffer. A series of processes are performed in series.

Therefore, the continuity of the compressed data stored in the buffer is necessarily maintained, as is the decompression process by the data decompressor.

However, when image data is divided and processed in block units, one processed block is not necessarily stored in one buffer, but may be stored in multiple buffers depending on the amount of data in the processed block. When stored, it is difficult to maintain continuity of buffer numbers, and if continuity is not maintained, it will not be possible to restore the original image data.

Further, providing a buffer capacity sufficient to store data blocks to maintain continuity of data blocks to be processed will reduce memory usage efficiency.

The present invention was created in view of the above points, and an object of the present invention is to provide a device that manages compressed or expanded data obtained by dividing image data and performing parallel processing using a management table.

[Means for solving problems]

In order to achieve the above purpose, a plurality of data compressors that divide one image data into multiple blocks and compress each block, a compressed data buffer that stores the compressed data, and compressed data and images. A compressed data buffer is managed by providing a management table that corresponds to data blocks.

[Effect]

Even if one image data is processed and divided into multiple buffers and stored, and the order of the stored buffer numbers is different, the buffer numbers relative to the original image data are managed in a management table. By doing so, when restoring processed data, the management table can be referenced to ensure data continuity of the original image data.

〔Example〕

FIG. 1 is a diagram for explaining one embodiment of the compressed data buffer management method of the present invention, and FIG. 2 is a diagram for explaining another embodiment of the present invention.

As shown in Figure 1 (al), one image data 1 is divided into blocks A, B, C, etc., and each block is assigned to three data compressors 2a, 2b, 2c and processed. .

On the other hand, there are a plurality of compressed data buffers 3a, 3a, and 3b for storing compressed data output from the data compressors 2a, 2b, and 2C.
3b and 3c (there is one buffer, which is divided into a plurality of areas, and each of the plurality of areas is regarded as one buffer, and will be referred to as PRO 1, 2, and 3 below).

The outputs of data compressors 2a, 2b and 'lc are stored in corresponding compressed data buffer blocks 1, 2 and 3, respectively.

At this time, the compressed data buffer is managed using a management table as shown in FIG. 1(b), for example.

In other words, the management table contains the block number, used/unused,
Columns such as the next block number and effective length of stored data are provided to manage each block 1, 2, and 3 of the compressed data buffer.

Then, the management table is encoded together with the entered values and stored in the control memory of the control unit that controls each control.

Figure 1 (In the bl management table, block A of image data l is allocated to block 1 of the compressed data buffer and is in use, block B is allocated to block 2, and block C is allocated to block 3 and is in use. It is.

Further, the block 4 and subsequent blocks are shown to be unused.

The compressed data of image data 1 is block A-
The blocks of the compressed data buffer are managed as 1-2-3 so that they are continuous from B to C.

"-1" in the next block number column in Figure 1 fb) indicates that one image data has been stored in the block with the block number in this column (the image data is 3 A, B, C).
(This is an example of writing in the next block number field assuming that the block is composed of blocks.)

When image data is compressed in this way, the data length to which block data is compressed cannot be determined until after compression, so the compressed data of block B exceeds the memory capacity of block 2. If you have done so, block 2 is followed by block 4 (
Buffer 2 in the form of connecting compressed data buffer 3d)
Subsequent data that exceeds the limit is stored in block 4.

Then, the management table at this time is rewritten as shown in FIG. 2 (bl) to manage the compressed data buffer.

It goes without saying that the management table is also necessary when a plurality of data decompressors decompress and restore the contents of the compressed data buffer in units of blocks.

〔Effect of the invention〕

As described above, according to the present invention, when one image data is compressed using a plurality of data compressors, it is possible to ensure the continuity of the compressed data, and it is possible to There is no need to prepare a large buffer, which is extremely useful in practice.

[Brief explanation of the drawing]

FIG. 1 is a diagram for explaining one embodiment of the compressed data buffer management device of the present invention, and FIG. 2 is a diagram for explaining another embodiment of the compressed data buffer management device of the present invention. In the figure, 1 is image data, 2 is a data compressor, and 3 is a compressed data buffer. Figure 2

Claims (1)

[Claims] One image data (1) is divided into a plurality of blocks, each of the divided blocks is compressed in parallel by a plurality of data compressors (2), and the compressed data of each block is compressed. Compressed data buffer (
3) and manages the compressed data buffer by providing a management table that associates the compressed data buffer (3) with blocks of the image data (1).