March 2005
Intermediate to advanced
880 pages
18h 59m
English
Daniel HornStanford University
Many GPGPU-based applications rely on the fragment processor, which operates across a large set of output memory locations, consuming a fixed number of input elements per location and operating a small program on those elements to produce a single output element in that location. Because the fragment program must write its results to a preordained memory location, it is not able to vary the amount of data that it outputs according to the input data it processes. (See Chapter 30 in this book, “The GeForce 6 Series GPU Architecture,” for more details on the capabilities and limits of the fragment processor.)
Many algorithms are difficult to implement under ...
Read now
Unlock full access