EGPGV17: Eurographics Symposium on Parallel Graphics and Visualization

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2631432

Browse

Now showing 1 - 9 of 9

Achieving Portable Performance For Wavelet Compression Using Data Parallel Primitives
(The Eurographics Association, 2017) Li, Shaomeng; Marsaglia, Nicole; Chen, Vincent; Sewell, Christopher; Clyne, John; Childs, Hank; Alexandru Telea and Janine Bennett
We consider the problem of wavelet compression in the context of portable performance over multiple architectures. We contribute a new implementation of the wavelet transform algorithm that uses data parallel primitives from the VTK-m library. Because of the data parallel primitives approach, our algorithm is hardware-agnostic and yet can run on many-core architectures. We also study the efficacy of this implementation over multiple architectures against hardware-specific comparators. Results show that our performance is portable, scales well, and is comparable to native implementations. Finally, we argue that compression times for large data sets are likely fast enough to fit within in situ constraints, adding to the evidence that wavelet transformation could be an effective in situ compression operator.
EG PGV 2017: Frontmatter
(Eurographics Association, 2017) Telea, Alexandru; Bennett, Janine;
Interactive Exploration of Dissipation Element Geometry
(The Eurographics Association, 2017) Vierjahn, Tom; Schnorr, Andrea; Weyers, Benjamin; Denker, Dominik; Wald, Ingo; Garth, Christoph; Kuhlen, Torsten W.; Hentschel, Bernd; Alexandru Telea and Janine Bennett
Dissipation elements (DE) define a geometrical structure for the analysis of small-scale turbulence. Existing analyses based on DEs focus on a statistical treatment of large populations of DEs. In this paper, we propose a method for the interactive visualization of the geometrical shape of DE populations. We follow a two-step approach: in a pre-processing step, we approximate individual DEs by tube-like, implicit shapes with elliptical cross sections of varying radii; we then render these approximations by direct ray-casting thereby avoiding the need for costly generation of detailed, explicit geometry for rasterization. Our results demonstrate that the approximation gives a reasonable representation of DE geometries and the rendering performance is suitable for interactive use.
PaViz: A Power-Adaptive Framework for Optimizing Visualization Performance
(The Eurographics Association, 2017) Labasan, Stephanie; Larsen, Matthew; Childs, Hank; Rountree, Barry; Alexandru Telea and Janine Bennett
Power consumption is widely regarded as one of the biggest challenges to reaching the next generation of high-performance computing. One strategy for achieving an exaflop given limited power is hardware overprovisioning. In this model, the theoretical peak power usage of the system is greater than the maximum allowable power usage, and a central manager keeps the aggregate power usage at the maximum by enforcing power caps on each node in the system. For this model to be effective, the central manager must be able to make informed trade-offs between power usage and performance. With this work, we introduce PaViz, a software framework designed to optimize the distribution of power for visualization algorithms, which have different characteristics than simulation codes. In this study, we focus specifically on rendering. Our strategy uses a performance model, where nodes predicted to have a small amount of work are allocated less power, and nodes predicted to have a large amount of work are allocated more power. This approach increases the likelihood of all nodes finishing at the same time, which is optimal for power efficiency. At best, our adaptive strategy achieves up to 33% speedup over the traditional strategy, while using the same total power.
Photo-Guided Exploration of Volume Data Features
(The Eurographics Association, 2017) Raji, Mohammad; Hota, Alok; Sisneros, Robert; Messmer, Peter; Huang, Jian; Alexandru Telea and Janine Bennett
In this work, we pose the question of whether, by considering qualitative information such as a sample target image as input, one can produce a rendered image of scientific data that is similar to the target. The algorithm resulting from our research allows one to ask the question of whether features like those in the target image exists in a given dataset. In that way, our method is one of imagery query or reverse engineering, as opposed to manual parameter tweaking of the full visualization pipeline. For target images, we can use real-world photographs of physical phenomena. Our method leverages deep neural networks and evolutionary optimization. Using a trained similarity function that measures the difference between renderings of a phenomenon and real-world photographs, our method optimizes rendering parameters. We demonstrate the efficacy of our method using a superstorm simulation dataset and images found online. We also discuss a parallel implementation of our method, which was run on NCSA's Blue Waters.
Prediction of Distributed Volume Visualization Performance to Support Render Hardware Acquisition
(The Eurographics Association, 2017) Tkachev, Gleb; Frey, Steffen; Müller, Christoph; Bruder, Valentin; Ertl, Thomas; Alexandru Telea and Janine Bennett
We present our data-driven, neural network-based approach to predicting the performance of a distributed GPU volume renderer for supporting cluster equipment acquisition. On the basis of timing measurements from a single cluster as well as from individual GPUs, we are able to predict the performance gain of upgrading an existing cluster with additional or faster GPUs, or even purchasing of a new cluster with a comparable network configuration. To achieve this, we employ neural networks to capture complex performance characteristics. However, merely relying on them for the prediction would require the collection of training data on multiple clusters with different hardware, which is impractical in most cases. Therefore, we propose a two-level approach to prediction, distinguishing between node and cluster level. On the node level, we generate performance histograms on individual nodes to capture local rendering performance. These performance histograms are then used to emulate the performance of different rendering hardware for cluster-level measurement runs. Crucially, this variety allows the neural network to capture the compositing performance of a cluster separately from the rendering performance on individual nodes. Therefore, we just need a performance histogram of the GPU of interest to generate a prediction. We demonstrate the utility of our approach using different cluster configurations as well as a range of image and volume resolutions.
Progressive CPU Volume Rendering with Sample Accumulation
(The Eurographics Association, 2017) Usher, Will; Amstutz, Jefferson; Brownlee, Carson; Knoll, Aaron; Wald, Ingo; Alexandru Telea and Janine Bennett
We present a new method for progressive volume rendering by accumulating object-space samples over successively rendered frames. Existing methods for progressive refinement either use image space methods or average pixels over frames, which can blur features or integrate incorrectly with respect to depth. Our approach stores samples along each ray, accumulates new samples each frame into a buffer, and progressively interleaves and integrates these samples. Though this process requires additional memory, it ensures interactivity and is well suited for CPU architectures with large memory and cache. This approach also extends well to distributed rendering in cluster environments. We implement this technique in Intel's open source OSPRay CPU ray tracing framework and demonstrate that it is particularly useful for rendering volumetric data with costly sampling functions.
A Space-Efficient Method for Navigable Ensemble Analysis and Visualization
(The Eurographics Association, 2017) Hota, Alok; Raji, Mohammad; Hobson, Tanner; Huang, Jian; Alexandru Telea and Janine Bennett
Scientists increasingly rely on simulation runs of complex models in lieu of cost-prohibitive or infeasible experimentation. The data output of many controlled simulation runs, the ensemble, is used to verify correctness and quantify uncertainty. However, due to their size and complexity, ensembles are difficult to visually analyze because the working set often exceeds strict memory limitations.We present a navigable ensemble analysis tool, NEA, for interactive exploration of ensembles. NEA's pre-processing component takes advantage of the data similarity characteristics of ensembles to represent the data in a new, spatially-efficient data structure which does not require fully reconstructing the original data at visualization time. This data structure allows a fine degree of control in working set management, which enables interactive ensemble exploration while fitting within memory limitations. Scientists can also gain new insights from the data-similarity analysis in the pre-processing component.
A Task-Based Parallel Rendering Component For Large-Scale Visualization Applications
(The Eurographics Association, 2017) Biedert, Tim; Werner, Kilian; Hentschel, Bernd; Garth, Christoph; Alexandru Telea and Janine Bennett
An increasingly heterogeneous system landscape in modern high performance computing requires the efficient and portable adaption of performant algorithms to diverse architectures. However, classic hybrid shared-memory/distributed systems are designed and tuned towards specific platforms, thus impeding development, usage and optimization of these approaches with respect to portability. We demonstrate a flexible parallel rendering framework built upon a task-based dynamic runtime environment enabling adaptable performance-oriented deployment on various platform configurations. Our task definition represents an effective and easy-to-control trade-off between sort-first and sort-last image compositing, enabling good scalability in combination with inherent dynamic load balancing. We conduct comprehensive benchmarks to verify the characteristics and potential of our novel task-based system design for high-performance visualization.

Browse

Browsing EGPGV17: Eurographics Symposium on Parallel Graphics and Visualization by Title

Results Per Page

Sort Options