Anisotropic Filtering - Performance and Optimization

Performance and Optimization

The sample count required can make anisotropic filtering extremely bandwidth-intensive. Multiple textures are common; each texture sample could be four bytes or more, so each anisotropic pixel could require 512 bytes from texture memory, although texture compression is commonly used to reduce this.

As a video display device can easily contain over two million pixels, and as the desired frame rate can be as high as 30–60 frames per second (or more) the texture memory bandwidth can become very high very quickly. Ranges of hundreds of gigabytes per second of pipeline bandwidth for texture rendering operations is not unusual where anisotropic filtering operations are involved.

Fortunately, several factors mitigate in favor of better performance:

• The probes themselves share cached texture samples, both inter-pixel and intra-pixel.
• Even with 16-tap anisotropic filtering, not all 16 taps are always needed because only distant highly oblique pixel fills tend to be highly anisotropic.
• Highly Anisotropic pixel fill tends to cover small regions of the screen (i.e. generally under 10%)
• Texture magnification filters (as a general rule) require no anisotropic filtering.