Method and apparatus for high density storage and handling of bit-plane data
View Patent ↗In an image processing system, high density storage of bit-plane data is provided in a secondary or page memory as well as high bandwidth access to the data by an image processor. The page memory provides storage of data not currently being processed. The page memory may also be part of a system that provides input and output of image data to and from the image processor. The image data may be handled outside the image processor in a packed pixel form and be converted between that form and bit-line form which the page memory stores during input and output. The bit-line data may be gathered into bit-planes for use by the image processor during movement of data from the page memory to the processing logic.
1. A digital data processing system comprising:
an array of processing elements having first data storage means, adapted to process bit-plane data, wherein the array of processing elements comprises M rows and N columns of processing elements;
second data storage means, coupled to the first data storage means, said second storage means adapted to store bit-plane data not needed for immediate processing, wherein the second data storage means are distributed amongst m units each providing bit-plane data storage for a M/m-row segment of the array, and wherein each unit inputs and outputs bit-plane data to and from the array in N-bit wide bit-lines; and
a data path between the first data storage means and the second data storage means, said data path being wider than one bit-line and narrower than one bit-plane.
2. The system of claim 1 , further including third data storage means, coupled to said second data storage means and having higher density than the first storage means and the second data storage means.
3. The system of claim 2 , wherein the third data storage means are adapted to store one of image pixel data and packed image pixel data.
4. The system of claim 1 wherein each of said m units further comprises a line buffer configured to store a single raster order pixel grouping of data in bit-line form, said raster order pixel grouping representing a pixel line comprising N pixels.
5. The system of claim 4 , wherein the line buffer comprises a first FIFO storage for input of bit-line data and a second FIFO storage for output of bit-line data.
6. The system of claim 4 , wherein the line buffer comprises a bi-directional FIFO storage configured for input and output of bit-line data.
7. The system of claim 4 , wherein the line buffer comprises a dual port storage device configured for input and output of bit-line data.
8. The system of claim 4 , adapted to conform pixel data input to a pattern whereby each of the m unit line buffers are written in turn until each unit line buffer contains a pixel line, and to simultaneously transfer pixel lines from the line buffers to the second storage means within each unit, and wherein the transfer is timed to allow uninterrupted input of pixel data to the unit, and whereby the pattern of pixel data input implies that pixels are selected in steps of m pixel lines.
9. The system of claim 4 , adapted to conform pixel data output to a pattern whereby pixel lines are transferred to the line buffers from the second storage means within each unit simultaneously, and wherein each of the m unit line buffers are read in turn until all unit line buffers are empty, and wherein the transfer is timed to allow uninterrupted output of pixel data from the units, whereby pixels are written to the output frame in steps of m pixel lines.
10. The system of claim 1 , wherein the array of processing elements comprises a register plane adapted to move bit-plane data between the processor array and the units, said register plane being partitioned at M/m-row intervals such that each M/m-row array segment provides an independent access point for input and output of bit-plane data via the register plane, the access point providing for transfer of bit-line data between the M/m-row array segment and the corresponding unit.
11. The system of claim 10 , wherein the input and output of bit-plane data is done as a background task without interfering with computational processing by the array of processing elements.
12. The system of claim 10 , further including a single program sequencer adapted to control the array of processing elements, and to provide control of computational processing simultaneously with control of bit-plane input and output.
13. The system of claim 12 , wherein the program sequencer is further adapted to send commands to the units to provide read and write controls for the second data storage means for the purpose of controlling bit-plane input and output.
14. The system of claim 12 , wherein the program sequencer is adapted to receive a page inhibit logical discrete and to inhibit generation of bit-plane input and output commands in response to active page inhibit discrete.