In high-performance computing (HPC), in situ analysis and visualization avoid costly I/O by extracting insight during the simulation run. When these tasks execute on the same GPUs that drive the simulation, resource contention can degrade performance. We propose an asynchronous framework that offloads visualization to idle CPU cores and overlaps in situ work with simulation execution. The framework uses ASCENT for efficient data movement and rendering and applies core pinning. Evaluated with NekRS on Polaris and JUWELS Booster, it reduced end-to-end runtime by 21-40% for slice-based visualizations compared to inline GPU instrumentation. Slice outputs incurred little overhead and overlapped cleanly with the simulation. Heavier filters like isovolumes, multilevel contours, and volume rendering were "free" (i.e., visualization time was encapsulated by simulation time) only at lower node counts, consistent with a CPU-budget model: filter cost and output cadence must fit the cores available per node.
Color blending is a widely used technique in mosaic or panorama image processing, particularly for seamlessly combining images with varying lighting or weather conditions. One key application is in aerial image mosaics, where seams often arise between images captured by aircraft. Blending large-scale mosaics, however, typically requires access to global image information, resulting in high memory demands. Prior work has addressed this challenge either through interactive local blending or by leveraging high-performance computing (HPC) systems with distributed memory.In this work, we present an out-of-core blending approach that processes large mosaics tile by tile using an iterative Poisson solver. Our method leverages a downsampled global mosaic to guide local blending, eliminating the need to load the full-resolution dataset into memory. We further introduce two adaptive execution strategies that vary the number of solver iterations per tile, improving both efficiency and quality. We demonstrate our approach using large orthomosaic datasets from the National Ecological Observatory Network (NEON), and implement the pipeline using the SYCL programming model for cross-platform portability.
We present a visual analytics system to increase proposal approval likelihood in Proof-of-Stake(PoS) blockchain governance. The proposed system introduces the Contextual Alliance Index(CAI), a similarity metric reflecting contextual information based on proposal voting data. Through heatmaps and bubble heap graphs, users can explore alliances among validators and support comparison and prioritization of persuadable validators. Furthermore, a case study illustrates an analytical process for understanding voting patterns for each proposal, and for identifying alliances and the prioritization of persuadable validators when drafting new proposals. This study is expected to contribute to the in-depth analysis of proposal patterns and the development of effective proposal strategies by identifying validator alliances in PoS blockchain governance.
We present two algorithms for building bricks over AMR cells on the GPU. Both algorithms focus on construction performance and produce output that allows for efficient cell location using NVIDIA ray tracing cores. In an effort to determine potential trade-offs between construction and sampling performance, we evaluate these algorithms on rendering methods common in scientific visualization.
We present a novel use of error-bounded lossy compression to accelerate distributed parallel volume rendering, which involves blending many semi-transparent images rendered by distributed processes, a procedure known as parallel image compositing. Specifically, we improve the widely adopted binary-swap algorithm by compressing intermediate images with strict pixel-wise error bounds. We propose a per-pixel error-bound model tailored to each communication request in the binary-swap algorithm to control the compositing error. We derive a per-round error bound based on the color and opacity of each intermediate pixel during compositing. Our algorithm also uses a dynamic strategy that balances compression and communication cost, deciding whether to compress based on network latency, bandwidth, and compressor performance. Our method significantly improves the frame rate for in situ rendering, demonstrating notable performance improvements in frame rate. We evaluate our algorithm through an end-to-end GPU-based parallel volume rendering pipeline using a GPU-accelerated renderer and compressor, integrated with CUDA-aware MPI. We demonstrate scalability with up to 512 GPUs on the Perlmutter supercomputer.
Contour trees offer an abstract representation of the level set topology in scalar fields and are widely used in topological data analysis and visualization. However, applying contour trees to large-scale scientific datasets remains challenging due to scalability limitations. Recent developments in distributed hierarchical contour trees have addressed these challenges by enabling scalable computation across distributed systems. Building on these structures, advanced analytical tasks—such as volumetric branch decomposition and contour extraction—have been introduced to facilitate large-scale scientific analysis. Despite these advancements, such analytical tasks substantially increase memory usage, which hampers scalability. In this paper, we propose a pre-simplification strategy to significantly reduce the memory overhead associated with analytical tasks on distributed hierarchical contour trees. We demonstrate enhanced scalability through strong scaling experiments, constructing the largest known contour tree—comprising over half a trillion nodes with complex topology—in under 15 minutes on a dataset containing 550 billion elements.
Implicit continuous models, such as functional models and implicit neural networks, are an increasingly popular method for replacing discrete data representations with continuous, high-order, and differentiable surrogates. These models offer new perspectives on the storage, transfer, and analysis of scientific data. In this paper, we introduce the first framework to directly extract complex topological features—contours, Jacobi sets, and ridge-valley graphs—from a type of continuous implicit model known as multivariate functional approximation (MFA). MFA replaces discrete data with continuous piecewise smooth functions. Given an MFA model as the input, our approach enables direct extraction of complex topological features from the model, without reverting to a discrete representation of the model. Our work is easily generalizable to any continuous implicit model that supports the queries of function values and high-order derivatives. Our work establishes the building blocks for performing topological data analysis and visualization on implicit continuous models.
Parallel event sequences, such as those collected in program execution traces and automated manufacturing pipelines, are typically visualized as interactive parallel timelines. As the dataset size grows, these charts frequently experience lag during common interactions such as zooming, panning, and filtering. Summarization approaches can improve interaction performance, but at the cost of accuracy in representation. To address this challenge, we introduce ESeMan (Event Sequence Manager), an event sequence management system designed to support interactive rendering of timeline visualizations with tunable accuracy. ESeMan employs hierarchical data structures and intelligent caching to provide visualizations with only the data necessary to generate accurate summarizations with significantly reduced data fetch time. We evaluate ESeMan's query times against summed area tables, M4 aggregation, and statistical sub-sampling on a variety of program execution traces. Our results demonstrate ESeMan provides better performance, achieving sub-100ms fetch times while maintaining visualization accuracy at the pixel level. We further present our benchmarking harness, enabling future performance evaluations for event sequence visualization.
Large language models (LLMs) are rapidly increasing in capability, but they still struggle with highly specialized programming tasks such as scientific visualization. We present an LLM agent, ChatVis, that aids the LLM to generate Python code for ParaView scientific visualization tasks, without the need for retraining or fine-tuning the LLM. ChatVis employs chain-of-thought prompt simplification, retrieval-augmented prompt generation using a vector database of documentation and code examples, and error checking with iterative prompt feedback to correct errors until a visualization is produced. An integral part of our approach is a benchmark suite of canonical visualization tasks, ParaView regression tests, and scientific use cases that includes comprehensive evaluation metrics. We evaluate our visualization agent by comparing results with a variety of top-performing unassisted LLMs. We find that all the metrics are significantly improved with ChatVis.
Join us for the 14th IEEE Symposium on Large Data Analysis and Visualization (IEEE LDAV) on Sunday, October 13th 2024 collocated with IEEE VIS 2024 in St. Pete Beach, Florida, USA.
The rise of heterogeneous resources in modern High Performance Computing (HPC) systems has propelled the scientific community beyond the exascale threshold. To maximize simulation performance on HPCs, applications increasingly rely on device resources, such as GPUs, leading to under-utilization of host resources, partic-ularly CPUs. In situ analysis and visualization techniques minimize data movement by operating on data in-memory, but this still in-volves blocking operations that incur a small penalty on simulation performance. We explore a novel instrumentation approach where GPU-based time step data is copied from device memory to host memory, enabling CPUs to concurrently perform visualization and analysis tasks. This strategy allows simulations to continue uninter-rupted by an in situ library's analysis and visualization processes.
This work presents a graphical user interface (GUI) designed to allow users to interactively create scientific visualizations and workflows with the in situ visualization software, Ascent [5]. Traditionally, in situ pipelines are configured through a YAML file, which can be cumbersome. Our GUI offers an alternative by automating the conversion of user inputs into a format that Ascent can process, eliminating the need for manual file editing. This interactive capability increases the potential for a more diverse group of users to leverage Ascent's powerful visualization tools.
This study analyzes the impact of validator behavior on investor rewards in proof-of-stake (PoS) based blockchain networks and proposes a visualization system to assist investors in selecting appropriate validators. This system enables personalized evaluations through five adjustable indicators tailored to the investor's preferences. By utilizing similarity-based circular visualizations and radar charts, it facilitates the selection and comparison of validators. Additionally, it provides time-series data-based line graphs and raw data-based table views to support detailed comparative analysis among validators. The introduction of such a multifaceted evaluation methodology in staking investments is expected to contribute to the formation of user-customized portfolios and the establishment of optimized investment strategies.
The conventional method of data exploration primarily relies on 2D and 3D visualization tools. However, with the advent of lower-cost virtual reality (VR) hardware, a transformation is underway. This study presents a novel data pipeline developed from ParaView (Open source Scientific visualization software) to the Unity Game Engine (Cross platform used to develop interactive contents such as games, animations and in this case VR) to investigate this transition. Specifically, we apply VR technology to the exploration of particle-based scientific datasets, focusing on data generated by a Hardware/Hybrid Accelerated Cosmology Code (HACC) simulation. This project applies VR to the identification of patterns and clusters within HACC particle-based datasets. We enable effective user interaction by integrating VR into the broader field of large data exploration, which includes features like data interaction, manipulation, and in-depth analysis. We implement custom interactions to enable interrogation of underlying data streams to provide deeper insight.
This work explores the application of recent advancements in radi-ance field rendering, specifically 3D Gaussian splatting, to generate high-quality approximations of scientific data. In this technique, a 3D Gaussian splatting model is built from a 3D point cloud gen-erated using structure-from-motion, or a randomly initialized one when using a NeRF as input. This point cloud serves as the basis for initializing a set of Gaussian primitives, which are then refined through machine learning to minimize differences between ground truth and rendered images. We modified this pipeline to train Gaus-sian models directly from scientific data, eliminating the need for structure-from-motion. We test exporting an isosurface as a point cloud, which is then used to train a Gaussian model representing the dataset's isosurface. We also experimented with using a cinema database to produce a 3D Gaussian model; however, this approach yielded less promising results due to sub-optimal point cloud ini-tialization. Our findings highlight the potential of this technique for scientific datasets, suggesting it could enable efficient post-hoc visualization with reduced computational resources.
Cuneiform is the earliest known system of writing, first developed for the Sumerian language of southern Mesopotamia in the second half of the 4th millennium BC. Cuneiform signs are obtained by impressing a stylus on fresh clay tablets. For certain purposes, e.g. authentication by seal imprint, some cuneiform tablets were enclosed in clay envelopes, which cannot be opened without destroying them. The aim of our interdisciplinary project is the non-invasive study of clay tablets. A portable X-ray micro-CT scanner is developed to acquire density data of such artifacts on a high-resolution, regular 3D grid at collection sites. The resulting volume data is processed through feature-preserving denoising, extraction of high-accuracy surfaces using a manifold dual marching cubes algorithm and extraction of local features by enhanced curvature rendering and ambient occlusion. For the non-invasive study of cuneiform inscriptions, the tablet is virtually separated from its envelope by curvature-based segmentation. The computational- and data-intensive algorithms are optimized for near-real-time offline usage with limited resources at collection sites. To visualize the complexity-reduced and octree-based compressed representation of surfaces, we develop and implement an interactive application. To facilitate the analysis of such clay tablets, we implement shape-based feature extraction algorithms to enhance cuneiform recognition. Our workflow supports innovative 3D display and interaction techniques such as autostereoscopic displays and gesture control.
This paper describes the adaptation to a distributed computational setting of a well-scaling parallel algorithm for computing Morse-Smale segmentations based on path compression. Additionally, we extend the algorithm to efficiently compute connected components in distributed structured and unstructured grids, based either on the connectivity of the underlying mesh or a feature mask. Our implementation is seamlessly integrated with the distributed extension of the Topology ToolKit (TTK), ensuring robust performance and scalability. To demonstrate the practicality and efficiency of our algorithms, we conducted a series of scaling experiments on large-scale datasets, with sizes of up to 40963 vertices on up to 64 nodes and 768 cores.
Functional approximation as a high-order continuous representation provides a more accurate value and gradient query compared to the traditional discrete volume representation. Volume visualization directly rendered from functional approximation generates high-quality rendering results without high-order artifacts caused by trilinear interpolations. However, querying an encoded functional approximation is computationally expensive, especially when the input dataset is large, making functional approximation impractical for interactive visualization. In this paper, we proposed a novel functional approximation multi-resolution representation, Adaptive-FAM, which is lightweight and fast to query. We also design a GPU-accelerated out-of-core multi-resolution volume visualization framework that directly utilizes the Adaptive-FAM representation to generate high-quality rendering with interactive responsiveness. Our method can not only dramatically decrease the caching time, one of the main contributors to input latency, but also effectively improve the cache hit rate through prefetching. Our approach significantly outperforms the traditional function approximation method in terms of input latency while maintaining comparable rendering quality.
This work presents an approach for the automatic detection of locally turbulent vortices within turbulent 2D flows such as instabilites. First, given a time step of the flow, methods from Topological Data Analysis (TDA) are leveraged to extract the geometry of the vortices. Specifically, the enstrophy of the flow is simplified by topological persistence, and the vortices are extracted by collecting the basins of the simplified enstrophy's Morse complex. Next, the local kinetic energy power spectrum is computed for each vortex. We introduce a set of indicators based on the kinetic energy power spectrum to estimate the correlation between the vortex's behavior and that of an idealized turbulent vortex. Our preliminary experiments show the relevance of these indicators for distinguishing vortices which are turbulent from those which have not yet reached a turbulent state and thus known as laminar.
Scientists generate petabytes of data daily to help uncover environmental trends or behaviors that are hard to predict. For example, understanding climate simulations based on the long-term average of temperature, precipitation, and other environmental variables is essential to predicting and establishing root causes of future undesirable scenarios and assessing possible mitigation strategies. While supercomputer centers provide a powerful infrastructure for generating petabytes of simulation output, accessing and analyzing these datasets interactively remains challenging on multiple fronts. This paper presents an approach to managing, visualizing, and analyzing petabytes of data within a browser on equipment ranging from the top NASA supercomputer to commodity hardware like a laptop. Our novel data fabric abstraction layer allows user-friendly querying of scientific information while hiding the complexities of dealing with file systems or cloud services. We also optimize network utilization while streaming from petas-cale repositories through state-of-the-art progressive compression algorithms. Based on this abstraction, we provide customizable dashboards that can be accessed from any device with any internet connection, enabling interactive visual analysis of vast amounts of data to a wide range of users - from top scientists with access to leadership-class computing environments to undergraduate students of disadvantaged backgrounds from minority-serving institutions. We focus on NASA's use of petascale climate datasets as an example of particular societal impact and, therefore, a case where achieving equity in science participation is critical. We validate our approach by improving the ability of climate scientists to visually explore their data via two fully interactive dashboards. We further validate our approach by deploying the dashboards and simplified training materials in the classroom at a minority-serving institution. These dashboards, released in simplified form to the general public, contribute significantly to a broader push to democratize the access and use of climate data.
