Parallel processing of the shear-warp factorization with the binary-swap method on a distributed-memory multiprocessor system

Volume rendering is an efficient tool for analyzing and understanding volumetric data in many scientific applications such as medical imaging and computational fluid dynamics. The paper presents a data-parallel volume rendering algorithm for shear-warp factorization of the viewing transformation with the binary-swap compositing method to achieve real-time rendering. This algorithm is suited to distributed-memory multiprocessor systems with a message-passing mechanism. Volume is subdivided into subvolumes to be allocated to PEs. Each PE shears an allocated subvolume and generates a subvolume image from the sheared subvolume in parallel. In order to carry out fast compositing of subvolume images, the binary-swap method is employed, which can keep the overheads due to compositing low. The authors implement the parallel shear-warp factorization algorithm with binary-swap compositing on the IBM SP2 with 32 PEs, and show volume rendering of 256²×128 to 256³ voxels for a screen of 256² pixels at 15 to 22 frames/sec. As a result, message-passing multiprocessor systems using the algorithm are also suitable for achieving real-time volume rendering