Sophie Robert

FlowVR: A Middleware for Large Scale Virtual Reality Applications

This paper introduces FlowVR, a middleware dedicated to virtual reality applications distributed on clusters or grid environments. FlowVR supports coupling of heterogeneous parallel codes and is component oriented to favor code reuse. While classical communication paradigms focus on either a synchronous approach (FIFO channels) or an asynchronous one (sampling), FlowVR enables a large range of intermediate policies to better balance the application performance between levels of details, latencies and refresh rates.

GPU‐accelerated atom and dynamic bond visualization using hyperballs: A unified algorithm for balls, sticks, and hyperboloids

Ray casting on graphics processing units (GPUs) opens new possibilities for molecular visualization. We describe the implementation and calculation of diverse molecular representations such as licorice, ball‐and‐stick, space‐filling van der Waals spheres, and approximated solvent‐accessible surfaces using GPUs. We introduce HyperBalls, an improved ball‐and‐stick representation replacing tubes, linking the atom spheres by hyperboloids that can smoothly connect them. This type of depiction is particularly useful to represent dynamic phenomena, such as the evolution of noncovalent bonds. It is furthermore well suited to represent coarse‐grained models and spring networks. All these representations can be defined by a single general algebraic equation that is adapted for the ray‐casting technique and is well suited for execution on the GPU. Using GPU capabilities, this implementation can routinely, accurately, and interactively render molecules ranging from a few atoms up to huge macromolecular assemblies with more than 500,000 particles. In simple cases, based only on spheres, we have been able to display up to two million atoms smoothly.

Interactive Molecular Dynamics: Scaling up to Large Systems☆

Combining molecular dynamics simulations with user interaction would have various applications in both education and research. By enabling interactivity the scientist will be able to visualize the experiment in real time and drive the simulation to a desired state more easily. However, interacting with systems of interesting size requires significant computing resources due to the complexity of the simulation. In this paper, we propose an approach to combine a classical parallel molecular dynamics simulator, Gromacs, to a 3D virtual reality environment allowing to steer the simulation through external user forces applied with an haptic device to a selection of atoms. We specifically focused on minimizing the intrusion in the simulator code, on efficient parallel data extraction and filtering to transfer only the necessary data to the visualization environment, and on a controlled asynchronism between various components to improve interactivity. We managed to steer molecular systems of 1.7M atoms at about 25 Hz using 384 CPU cores. This framework allowed us to study a concrete scientific problem by testing one hypothesis of the transport of an iron complex from the exterior of the bacteria to the periplasmic space through the FepA membrane protein.

Experiments with Parallel One-Sided and Two-Sided Algorithms for SVD

A paper reports on testing parallel SVD algorithms for matrices arising from selected scientific and industrial applications. The codes for the SVD are based respectively on the one{sided and the two{ sided Jacobi approach. The matrices come from solving problems of the diffraction process in the crystallography, the diffusion equation in the reactor physics and from the aircraft industry. A parallelization of each of these approaches is described. Results from computational experiments performed on the Paragon machine with 56 processors are presented and discussed.

Automatic refinement of service compositions

We propose a method for the automatic refinement of web service compositions: given a composite web service specification over abstract modules, our method generates lower-level versions of this composition. The refinement process is based on query rewriting techniques extended to take into account not only functional and non-functional requirements but also semantic information. Experimental results illustrate the performance and scalability of the method.

Coherence and performance for interactive scientific visualization applications

This paper addresses the use of component-based development to build interactive scientific visualization applications. Our overall approach is to make this programming technique more accessible to non-computer-scientists. Therefore, we present a method to, out of constraints given by the user, automatically build and coordinate the dataflow of a real-time interactive scientific visualization application. This type of applications must run as fast as possible while preserving the accuracy of their results. These two aspects are often conflicting, for example when it comes to allowing message dropping or not. Our approach aims at automatically finding the best balance between these two requirements when building the application. An overview of a prototype implementation based on the FlowVR middleware is also given.

FlowVR-SciViz: a component-based framework for interactive scientific visualization

FlowVR is a component-based middleware providing the means to develop and run high performance VR or Scientific Visualization applications on PC cluster or grid architecture. In this paper, we present FvSciViz, a generic framework based on FlowVR, to build interactive scientific visualization from heterogeneous components. FvSciViz provides an API, called FVmoduleAPI, to build FlowVR components, a template of an interactive scientific visualization application and automatic tools to generate the application defined by the user. FVmoduleAPI encapsulates FlowVR technicalities in few simple functions inserted in the original code written in C, C++ or Fortran, to make it compatible with the programming model of the FlowVR middleware. The application template is based on generic components handling interaction, visualization and simulation. These components are set up in an XML file processed by FvSciVizs automatic tools in order to build the application. Some first experiments validate our approach.

FlowVR-VRPN: first experiments of a VRPN/FlowVR coupling

This paper describes a generic coupling between the middleware FlowVR designed to develop modular VR applications for distributed architectures like PC clusters and VRPN which is a library that manages a large number of physical devices. This generic coupling takes the advantages of the FlowVR programming model to provide all the services offered by VRPN in FlowVR applications.

Efficient Implicit Parallel Patterns for Geographic Information System

Abstract With the data growth, the need to parallelize treatments become crucial in numerous do-mains. But for non-specialists it is still difficult to tackle parallelism technicalities as data distribution, communications or load balancing. For the geoscience domain we propose a solution based on implicit parallel patterns. These patterns are abstract models for a class of algorithms which can be customized and automatically transformed in a parallel execution. In this paper, we describe a pattern for stencil computation and a novel pattern dealing with computation following a pre-defined order. They are particularly used in geosciences and we illustrate them with the flow direction and the flow accumulation computations.

Experiments on service composition refinement on the basis of preference-driven recommendation

The service oriented computing paradigm proposes the construction of applications by integrating pre-existent services. Since a large number of services may be available in the cloud, service recommendation and selection are key problems. The paper proposes the automation of the selection task that takes the abstract specification of a composition, the definition of concrete services and the preferences obtained from a recommendation routine to produce a list of refinements in preference order. This paper presents three versions of our approach. They differ in implementation options or in the methods used to combine preferences. Experiment results are provided as a benchmark for ensuring the efficiency of our proposal in practice.