Method and apparatus for anti-aliasing using floating point subpixel color values and compression of same

1. A method of data compression comprising:

representing each sub-pixel of each pixel of a display with a pointer corresponding to an attribute of the sub-pixel, the attribute being a floating point binary number; and

determining an overall attribute of each pixel by any one of:

assigning the attribute of the sub-pixels of the pixel to the attribute of the pixel when the sub-pixels of the pixel are represented by an identical pointer; and

resolving the attribute of the pixel by the attributes of the sub-pixels of the pixel when the sub-pixels of the pixel are represented by non-identical pointers.

2. The method of claim 1 , wherein each attribute represents color information and further comprising storing the overall attributes of each pixel as pointer information in memory.

3. The method of claim 1 , wherein the pointer represents at least two different floating point binary colors.

4. The method of claim 1 , wherein the resolving comprises:

converting the attribute corresponding to each non-identical pointer to a binary fixed point attribute;

combining the binary fixed point attributes to determine a combined fixed point attribute;

converting the combined fixed point attribute to a combined binary floating point attribute; and

representing the overall attribute of the pixel by the combined binary floating point attribute.

5. The method of claim 4 , wherein the combining comprises averaging the binary fixed point attributes based on the number of non-identical pointers of the pixel.

6. An apparatus comprising:

logic operative to:

represent each sub-pixel of each pixel of a plurality of pixels of a display with a pointer corresponding to an attribute of the sub-pixel, the attribute being a floating point binary number; and

determine an overall attribute of each pixel by any one of:

assigning the attribute of the sub-pixels to the overall attribute of the pixel when the sub-pixels are represented by an identical pointer; and

resolving the overall attribute of the pixel by the attributes of the sub-pixels when the sub-pixels are represented by non-identical pointers of the pixel.

7. The apparatus of claim 6 , wherein each attribute represents color information and further comprising the logic operative to store the overall attributes of each pixel as pointer information in memory.

8. The apparatus of claim 6 , wherein the pointer represents at least two different floating point binary colors.

9. The apparatus of claim 6 , wherein the resolving comprises the logic operative to:

convert the attribute corresponding to each non-identical pointer to a binary fixed point attribute;

combine the binary fixed point attributes to determine a combined fixed point attribute;

convert the combined fixed point attribute to a combined binary floating point attribute; and

represent the overall attribute of the pixel by the combined binary floating point attribute.

10. The apparatus of claim 9 , wherein to combine comprises averaging the binary fixed point attributes based on the number of non-identical pointers of the pixel.

11. An apparatus comprising logic operative to:

receive pointers corresponding to sub-pixels of each pixels of a display, each pointer representing an attribute of the corresponding sub-pixel;

assign the attribute of the sub-pixels to an overall attribute of the pixel when the sub-pixels are represented by an identical pointer;

resolve the overall attribute of the pixel by the attributes of the sub-pixels when the sub-pixels are represented by non-identical pointers of the pixel.

12. The apparatus of claim 11 , wherein to resolve the overall attribute of the pixel comprises:

converting the attribute corresponding to each non-identical pointer to a binary fixed point attribute;

combining the binary fixed point attributes to determine a combined fixed point attribute;

converting the combined fixed point attribute to a combined binary floating point attribute; and

representing the overall attribute of the pixel by the combined binary floating point attribute.

13. The apparatus of claim 12 , wherein the combining comprises averaging the binary fixed point attributes based on the number of non-identical pointers of the pixel.

14. A method of data compression comprising:

storing sub-pixels values for a plurality of pixels in a tile; and

selecting from one of at least the following compression levels:

a clear state that utilizes a single floating point color value per tile;

an uncompressed state that utilizes a floating point color value stored for each sub-pixel of each pixel in a tile;

a partial compression state that utilize a pointer for each sub-pixel in a tile that selects a floating point color value for each sub-pixel;

full compression that utilizes a single floating point color value for each pixel, to compress the plurality of sub-pixel values; and

producing compression encoding data for each tile indicating the compression level selected for the tile.