Memory access system and method for efficiently utilizing memory bandwidth
View Patent ↗A memory access system and method for efficiently utilizing memory bandwidth is disclosed. A data arrangement unit arranges video data into at least a primary block and a supplemental block, which are then stored in a memory device. The video data are arranged such that the video data of the primary block stored in the memory device can be sequentially read by a device, thereby increasing efficiency in memory bandwidth usage and memory data access.
1. A memory access system for efficiently utilizing memory bandwidth, comprising:
a data arrangement unit for arranging video data into at least a primary block and a supplemental block such that the primary block includes luma components of all pixels and only chrominance components of non-even number pixels, and the supplemental block includes only chrominance components of even number pixels; and
a memory device in which the arranged video data of the primary block and the supplemental block are respectively and separately stored;
wherein the video data are specifically arranged such that the arranged video data stored in the memory device are sequentially and continuously read by a device in an order of the pixels.
2. The system of claim 1 , wherein the video data are provided by a video data source.
3. The system of claim 1 , wherein the video data have YUV color-space format, wherein Y stands for luma component, and U and V stand for chrominance components.
4. The system of claim 3 , wherein the data arrangement unit removes at least one chrominance component of an adjacent two pixels represented by the video data, while maintaining luma components of the pixels.
5. The system of claim 3 , wherein the components U and V of even-number pixels are removed, resulting in the primary block.
6. The system of claim 5 , wherein the removed components U and V compose the supplemental block.
7. The system of claim 4 , wherein a missing chrominance component caused by the removal is recovered by interpolation between a preceding pixel and a succeeding pixel.
8. The system of claim 1 , wherein, the primary block and the supplemental block are read from the memory device in turn.
9. The system of claim 1 , wherein the primary block and the supplemental block are read at the same time.
10. The system of claim 1 , wherein the data arrangement unit comprises:
a demultiplexer from which the video data of the primary block are outputted via a first output port of the demultiplexer, and the video data of the supplemental block are outputted via a second output port of the demultiplexer;
a first buffer and a second buffer for respectively storing the video data from the first output port and the second output port; and
a multiplexer which receives the video data of the first buffer and the video data of the second buffer in turn, which are then stored into the memory device.
11. A memory access method for efficiently utilizing memory bandwidth, comprising:
arranging video data into at least a primary block and a supplemental block such that the primary block includes luma components of all pixels and only chrominance components of non-even number pixels, and the supplemental block includes only chrominance components of even number pixels; and
storing the arranged video data of the primary block and the supplemental block respectively and separately in a memory device;
wherein the video data are specifically arranged such that the arranged video data stored in the memory device are sequentially and continuously read by a device in an order of the pixels.
12. The method of claim 11 , wherein the video data are provided by a video data source.
13. The method of claim 11 , wherein the video data have a YUV color-space format, wherein Y stands for luma component, and U and V stand for chrominance components.
14. The method of claim 13 , wherein the step of arranging the video data comprises:
removing at least one chrominance component of an adjacent two pixels represented by the video data., while maintaining luma components of the pixels.
15. The method of claim 13 , wherein the components U and V of even-number pixels are removed, resulting in the primary block.
16. The method of claim 15 , wherein the removed components U and V compose the supplemental block.
17. The method of claim 14 , wherein missing a chrominance component caused by the removal is recovered by interpolation between a preceding pixel and a succeeding pixel.
18. The method of claim 11 , wherein the primary block and the supplemental block are read from the memory device in turn.
19. The method of claim 11 , wherein the primary block and the supplemental block are read at the same time.
20. The method of claim 11 , wherein the step of arranging the video data comprises:
demultiplexing the video data to generate the primary block and the supplemental block;
respectively buffering the video data of the primary block and the video data of the supplemental block;
multiplexing the buffered video data of the primary block and the buffered video data of the supplemental block in turn; and
storing the multiplexed video data of the primary block and the multiplexed video data of the supplemental block into the memory device.