We present a scalable parallel solver for the pressure Poisson equation in fluids simulation which can accommodate complex irregular domains in the order of a billion degrees of freedom, using a single server or workstation fitted with GPU or Many-Core accelerators. The design of our numerical technique is attuned to the subtleties of heterogeneous computing, and allows us to benefit from the high memory and compute bandwidth of GPU accelerators even for problems that are too large to fit entirely on GPU memory. This is achieved via algebraic formulations that adequately increase the density of the GPU-hosted computation as to hide the overhead of offloading from the CPU, in exchange for accelerated convergence. Our solver follows the principles of Domain Decomposition techniques, and is based on the Schur complement method for elliptic partial differential equations. A large uniform grid is partitioned in non-overlapping subdomains, and bandwidth-optimized (GPU or Many-Core) accelerator cards are used to efficiently and concurrently solve independent Poisson problems on each resulting subdomain. Our novel contributions are centered on the careful steps necessary to assemble an accurate global solver from these constituent blocks, while avoiding excessive communication or dense linear algebra. We ultimately produce a highly effective Conjugate Gradients preconditioner, and demonstrate scalable and accurate performance on high-resolution simulations of water and smoke flow.

Level sets have been established as highly versatile implicit surface representations, with widespread use in graphics applications including modeling and dynamic simulation. Nevertheless, level sets are often presumed to be limited, compared to explicit meshes, in their ability to represent domains with thin topological features (e.g. narrow slits and gaps) or, even worse, material overlap. Geometries with such features may arise from modeling tools that tolerate occasional self-intersections, fracture modeling algorithms that create narrow or zero-width cuts by design, or as transient states in collision processing pipelines for deformable objects. Converting such models to level sets can alter their topology if thin features are not resolved by the grid size. We argue that this ostensible limitation is not an inherent defect of the implicit surface concept, but a collateral consequence of the standard Cartesian lattice used to store the level set values. We propose storing signed distance values on a regular hexahedral mesh which can have multiple collocated cubic elements and non-manifold bifurcation to accommodate non-trivial topology. We show how such non-manifold level sets can be systematically generated from convenient alternative geometric representations. Finally we demonstrate how this representation can facilitate fast and robust treatment of self-collision in simulations of volumetric elastic deformable bodies.

We present an interactive simulation framework for authoring surgical procedures of soft tissue manipulation using physics-based simulation to animate the flesh. This interactive authoring tool can be used by clinical educators to craft three-dimensional illustrations of the intricate maneuvers involved in craniofacial repairs, in contrast to two-dimensional sketches and still photographs which are the medium used to describe these procedures in the traditional surgical curriculum. Our virtual environment also allows surgeons-intraining to develop cognitive skills for craniofacial surgery by experimenting with different approaches to reconstructive challenges, adapting stock techniques to flesh regions with nonstandard shape, and reach preliminary predictions about the feasibility of a given repair plan. We use a Cartesian grid-based embedded discretization of nonlinear elasticity to maximize regularity, and expose opportunities for aggressive multithreading and SIMD accelerations. Using a grid-based approach facilitates performance and scalability, but constrains our ability to capture the topology of thin surgical incisions. We circumvent this restriction by hybridizing the grid-based discretization with an explicit hexahedral mesh representation in regions where the embedding mesh necessitates overlap or nonmanifold connectivity. Finally, we detail how the front-end of our system can run on lightweight clients, while the core simulation capability can be hosted on a dedicated server and delivered as a network service.

Lattice deformers are a popular option for modeling the behavior of elastic bodies as they avoid the need for conforming mesh generation, and their regular structure offers significant opportunities for performance optimizations. Our work expands the scope of current lattice-based elastic deformers, adding support for a number of important simulation features. We accommodate complex nonlinear, optionally anisotropic materials while using an economical one-point quadrature scheme. Our formulation fully accommodates near-incompressibility by enforcing accurate nonlinear constraints, supports implicit integration for large time steps, and is not susceptible to locking or poor conditioning of the discrete equations. Additionally, we increase the accuracy of our solver by employing a novel high-order quadrature scheme on lattice cells overlapping with the model boundary, which are treated at sub-cell precision. Finally, we detail how this accurate boundary treatment can be implemented at a minimal computational premium over the cost of a voxel-accurate discretization. We demonstrate our method in the simulation of complex musculoskeletal human models.