In the last decades cosmological N-body dark matter simulations have enabled ab initio studies of the formation of structure in the Universe. Gravity amplified small density fluctuations generated shortly after the Big Bang, leading to the formation of galaxies in the cosmic web. These calculations have led to a growing demand for methods to analyze time-dependent particle based simulations. Rendering methods for such N-body simulation data usually employ some kind of splatting approach via point based rendering primitives and approximate the spatial distributions of physical quantities using kernel interpolation techniques, common in SPH (Smoothed Particle Hydrodynamics)-codes. This paper proposes three GPU-assisted rendering approaches, based on a new, more accurate method to compute the physical densities of dark matter simulation data. It uses full phase-space information to generate a tetrahedral tessellation of the computational domain, with mesh vertices defined by the simulation's dark matter particle positions. Over time the mesh is deformed by gravitational forces, causing the tetrahedral cells to warp and overlap. The new methods are well suited to visualize the cosmic web. In particular they preserve caustics, regions of high density that emerge, when several streams of dark matter particles share the same location in space, indicating the formation of structures like sheets, filaments and halos. We demonstrate the superior image quality of the new approaches in a comparison with three standard rendering techniques for N-body simulation data.

Analysis of phenomena that simultaneously occur on different spatial and temporal scales requires adaptive, hierarchical schemes to reduce computational and storage demands. Adaptive mesh refinement (AMR) schemes support both refinement in space that results in a time-dependent grid topology, as well as refinement in time that results in updates at higher rates for refined levels. Visualization of AMR data requires generating data for absent refinement levels at specific time steps. We describe a solution starting from a given set of "key frames" with potentially different grid topologies. The presented work was developed in a project involving several research institutes that collaborate in the field of cosmology and numerical relativity. AMR data results from simulations that are run on dedicated compute machines and is thus stored centrally, whereas the analysis of the data is performed on the local computers of the scientists. We built a distributed solution using remote procedure calls (RPC). To keep the application responsive, we split the bulk data transfer from the RPC response and deliver it asynchronously as a binary stream. The number of network round-trips is minimized by using high level operations. In summary, we provide an application for exploratory visualization of remotely stored AMR data.

Datasets of tens of gigabytes are becoming common in computational and experimental science. This development is driven by advances in imaging technology, producing detectors with growing resolutions, as well as availability of cheap processing power and memory capacity in commodity-based computing clusters. We describe the design of a visualization system that allows scientists to interactively explore large remote data sets in an efficient and flexible way. The system is broadly applicable and currently used by medical scientists conducting an osteoporosis research project. Human vertebral bodies are scanned using a high resolution microCT scanner producing scans of roughly 8 GB size each. All participating research groups require access to the centrally stored data. Due to the rich internal bone structure, scientists need to interactively explore the full dataset at coarse levels, as well as visualize subvolumes of interest at the highest resolution. Our solution is based on HDF5 and GridFTP. When accessing data remotely, the HDF5 data processing pipeline is modified to support efficient retrieval of subvolumes. We reduce the overall latency and optimize throughput by executing high-level operations on the remote side. The GridFTP protocol is used to pass the HDF5 requests to a customized server. The approach takes full advantage of local graphics hardware for rendering. Interactive visualization is accomplished using a background thread to access the datasets stored in a multiresolution format. A hierarchical volume tenderer provides seamless integration of high resolution details with low resolution overviews.

In this paper, we present an algorithm that accelerates 3D texture-based volume rendering of large, sparse data sets, i.e., data sets where only a traction of the voxels contain relevant information. In texture-based approaches, the rendering performance is affected by the fill-rate, the size of texture memory, and the texture I/O bandwidth. For sparse data, these limitations can be circumvented by restricting most of the rendering work to the relevant parts of the volume. In order to efficiently enclose the corresponding regions with axis-aligned boxes, we employ a hierarchical data structure, known as an AMR (adaptive mesh refinement) tree. The hierarchy is generated utilizing a clustering algorithm. A good balance is thereby achieved between the size of the enclosed volume, i.e., the amount to render in graphics hardware and the number of axis-aligned regions, i.e., the number of texture coordinates to compute in software. The waste of texture memory by the power-of-two restriction is minimized by a 3D packing algorithm which arranges texture bricks economically in memory. Compared to an octree approach, the rendering performance is significantly increased and less parameter tuning is necessary.

For quantitative examination of phenomena that simultaneously occur on very different spatial and temporal scales, adaptive hierarchical schemes are required. A special numerical multilevel technique, associated with a particular hierarchical data structure, is so-called adaptive mesh refinement (AMR). It allows one to bridge a wide range of spatial and temporal resolutions and therefore gains increasing popularity. We describe the interplay of several visualization and VR software packages for rendering time dependent AMR simulations of the evolution of the first star in the universe. The work was done in the framework of a television production for Discovery Channel television, "The Unfolding Universe.". Parts of the data were taken from one of the most complex AMR simulation ever carried out: It contained up to 27 levels of resolution, requiring modifications to the texture based AMR volume rendering algorithm that was used to depict the density distribution of the gaseous interstellar matter. A voice and gesture controlled CAVE application was utilized to define camera paths following the interesting features deep inside the computational domains. Background images created from cosmological computational data were combined with the final renderings.