A Comparison of Parallel Compositing Techniques on Shared Memory Architectures

Parallel compositing techniques have traditionally focused on distributed memory architectures with communication of pixel values usually being the main bottleneck. On shared memory architectures, communication is handled through memory accesses, obviating the need for explicit communication steps. Shared memory architectures with multiple graphics accelerators provide the capability for parallel rendering while combining the partial results from multiple graphics adaptors requires compositing. For this reason, in this paper shared memory architectures are considered for compositing operations. A number of previously introduced parallel compositing algorithms are compared on a shared memory machine, including the binary swap and parallel pipeline techniques.