Waldemar Celes

The evolution of Lua

We report on the birth and evolution of Lua and discuss how it moved from a simple configuration language to a versatile, widely used language that supports extensible semantics, anonymous functions, full lexical scoping, proper tail calls, and coroutines.

A general topology-based framework for adaptive insertion of cohesive elements in finite element meshes

Large-scale simulation of separation phenomena in solids such as fracture, branching, and fragmentation requires a scalable data structure representation of the evolving model. Modeling of such phenomena can be successfully accomplished by means of cohesive models of fracture, which are versatile and effective tools for computational analysis. A common approach to insert cohesive elements in finite element meshes consists of adding discrete special interfaces (cohesive elements) between bulk elements. The insertion of cohesive elements along bulk element interfaces for fragmentation simulation imposes changes in the topology of the mesh. This paper presents a unified topology-based framework for supporting adaptive fragmentation simulations, being able to handle two- and three-dimensional models, with finite elements of any order. We represent the finite element model using a compact and “complete” topological data structure, which is capable of retrieving all adjacency relationships needed for the simulation. Moreover, we introduce a new topology-based algorithm that systematically classifies fractured facets (i.e., facets along which fracture has occurred). The algorithm follows a set of procedures that consistently perform all the topological changes needed to update the model. The proposed topology-based framework is general and ensures that the model representation remains always valid during fragmentation, even when very complex crack patterns are involved. The framework correctness and efficiency are illustrated by arbitrary insertion of cohesive elements in various finite element meshes of self-similar geometries, including both two- and three-dimensional models. These computational tests clearly show linear scaling in time, which is a key feature of the present data-structure representation. The effectiveness of the proposed approach is also demonstrated by dynamic fracture analysis through finite element simulations of actual engineering problems.

A load-balancing strategy for sort-first distributed rendering

In this paper we present a multi-threaded sort-first distributed rendering system. In order to achieve load balance among the rendering nodes, we propose a new partitioning scheme based on the rendering time of the previous frame. The proposed load-balancing algorithm is very simple to be implemented and works well for both geometry and rasterization-bound models. We also propose a strategy to assign tiles to rendering nodes that effectively uses the available graphics resources, thus improving rendering performance.

Passing a language through the eye of a needle

How the embeddability of Lua impacted its design.

High-Quality Hardware-Based Ray-Casting Volume Rendering Using Partial Pre-Integration

In this paper, we address the problem of the interactive volume rendering of unstructured meshes and propose a new hardware-based ray-casting algorithm using partial pre-integration. The proposed algorithm makes use of modern programmable graphics card and achieves rendering rates competitive with full pre-integration approaches (up to 2M tet/sec). This algorithm allows the interactive modification of the transfer function and results in high-quality images, since no artifact due to under-sampling the full numerical pre-integration exists. We also compare our approach with implementations of cell-projection algorithm and demonstrate that ray-casting can perform better than cell projection, because it eliminates the high costs involved in ordering and transferring data.

Accelerated Corner-Detector Algorithms

Fast corner-detector algorithms are important for achieving real time in different computer vision applications. In this paper, we present new algorithm implementations for corner detection that make use of graphics processing units (GPU) provided by commodity hardware. The programmable capabilities of modern GPUs allow speeding up counterpart CPU algorithms. In the case of corner-detector algorithms, most steps are easily translated from CPU to GPU. However, there are challenges for mapping the feature selection step to the GPU parallel computational model. This paper presents a template for implementing corner-detector algorithms that run entirely on GPU, resulting in significant speed-ups. The proposed template is used to implement the KLT corner detector and the Harris corner detector, and numerical results are presented to demonstrate the algorithms efficiency.

Efficient Handling of Implicit Entities in Reduced Mesh Representations

State-of-the-art numerical analyses require mesh representation with a data structure that provides topological information. Due to the increasing size of the meshes currently used for simulating complex behaviors with finite elements or boundary elements (e.g., adaptive and/or coupled analyses), several researchers have proposed the use of reduced mesh representations. In a reduced representation, only a few types of the defined topological entities are explicitly represented; all the others are implicit and retrieved “on-the-fly,” as required. Despite being very effective in reducing the memory space needed to represent large models, reduced representations face the challenge of ensuring the consistency of all implicit entities when the mesh undergoes modifications. As implicit entities are usually described by references to explicit ones, modifying the mesh may change the way implicit entities (which are not directly modified) are represented, e.g., the referenced explicit entities may no longer exist. We propose a new and effective strategy to treat implicit entities in reduced representations, which is capable of handling transient nonmanifold configurations. Our strategy allows, from the application point of view, explicit and implicit entities to be interchangeably handled in a uniform and transparent way. As a result, the application can list, access, attach properties to, and hold references to implicit entities, and the underlying data structure ensures that all such information remains valid even if the mesh is modified. The validity of the proposed approach is demonstrated by running a set of computational experiments on different models subjected to dynamic remeshing operations.

GPU-accelerated Adaptively Sampled Distance Fields

Adaptively Sampled Distance Fields (ADFs) are volumetric shape representations that support a broad range of applications in the areas of computer graphics, computer vision and physics. ADFs are especially beneficial for representing shapes with features at very diverse scales. In this paper, we propose a strategy to represent and reconstruct ADFs on modern graphics hardware (GPUs). We employ a 3D hashing scheme to store the underlying data structure and try to balance the tradeoff between memory requirements and reconstruction efficiency. To render ADFs on GPU, we use a general-purpose ray-casting technique based on sphere tracing, which guarantees the reconstruction of fine details. We also present a way to overcome the Cl discontinuities inherent to ADFs and efficiently reconstruct smooth surface normals across cell boundaries. The effectiveness of our proposal is demonstrated for isosurface rendering and morphing.

Multiple display viewing architecture for virtual environments over heterogeneous networks

Visualization systems that support multiple-display viewing can greatly enhance user perception. The common approach to provide multiple synchronized views uses a powerful centralized processing unit to support the rendering process on all screens. As an alternative approach, we propose a distributed architecture that supports a flexible and reliable visualization system that, while giving the users a sensation of immersion, uses a heterogeneous network of low-end graphics workstations. The proposed system ensures portability and synchronization of all displayed views.

ParTopS: compact topological framework for parallel fragmentation simulations

Cohesive models are used for simulation of fracture, branching and fragmentation phenomena at various scales. Those models require high levels of mesh refinement at the crack tip region so that nonlinear behavior can be captured and physical results obtained. This imposes the use of large meshes that usually result in computational and memory costs prohibitively expensive for a single traditional workstation. If an extrinsic cohesive model is to be used, support for dynamic insertion of cohesive elements is also required. This paper proposes a topological framework for supporting parallel adaptive fragmentation simulations that provides operations for dynamic insertion of cohesive elements, in a uniform way, for both two- and three-dimensional unstructured meshes. Cohesive elements are truly represented and are treated like any other regular element. The framework is built as an extension of a compact adjacency-based serial topological data structure, which can natively handle the representation of cohesive elements. Symmetrical modifications of duplicated entities are used to reduce the communication of topological changes among mesh partitions and also to avoid the use of locks. The correctness and efficiency of the proposed framework are demonstrated by a series of arbitrary insertions of cohesive elements into some sample meshes.