Efficient data-parallel tree-traversal for BlobTrees

The hierarchical implicit modelling paradigm, as exemplified by the BlobTree, makes it possible to support not only Boolean operations and affine transformations, but also various forms of blending and space warping. Typically, the resulting solid is converted to a boundary representation, a triangle mesh approximation, for rendering. These triangles are obtained by evaluating the corresponding implicit function (field) at the samples of a dense regular three-dimensional grid and by performing a local iso-surface extraction at each voxel. The performance bottleneck of this rendering process lies in the cost of the tree traversal (which typically must be executed hundreds of millions of times) and in the cost of applying the inverses of the space transformations associated with some of the nodes of the tree to the grid samples.