high performance computing on graphics processing units: hgpu.org

Nowadays, physics simulation is a relevant topic in several domains, from scientific areas like medicine to entertainment purposes such as movie’s effects, computer animation and games. To make easier the production of faster simulations, developers are using physics engines because they provide a variety of features like rigid and deformable body simulation, fluids dynamics and […]

The main goal of this project is to develop a computer program to model the rotation of a galaxy including dark matter. The computer program will be used to answer these questions: (1) How does dark matter affect rotational curves in galaxies; (2) how accurately can this be modeled; (3) what will happen when the […]

We present the GPUs computation acceleration for a very recurrent electromagnetic problem which is the calculation of the field radiated by electric dipoles in a multilayer structure (Green’s tensor in stratified background), based on the well-known Sommerfeld integrals. Using an optimized parallelization scheme, huge computation acceleration is obtained. Applications of such a work are very […]

Vergence ability is an important visual behavior observed on living creatures when they use vision to interact with the environment. The notion of active observer is equally useful for robotic vision systems on tasks like object tracking, fixation and 3D environment structure recovery. Humanoid robotics are a potential playground for such behaviors. This paper describes […]

Image segmentation is a key area of research in computer vision. Recent advances facilitated reformulation of the non-convex multi-phase segmentation problem as a convex optimization problem (see for example [2, 4, 9, 10, 13, 16]). Recently, [3] proposed a new convex relaxation approach for a class of vector-valued minimization problems, and this approach is directly […]

We describe a new approach to the processing of audio by way of transformations to and from the frequency domain. In previous papers we described the Sliding Discrete Fourier Transform (SDFT), comprising an extension to the classic phase vocoder algorithm to perform a frame update every sample. We proposed this as offering musical advantages over […]

The paper describes specific features of parallelization of collision integral computation algorithms, which are conditioned by the CUDA architecture of parallelization on graphic cards [1].

There are several possibilities to speed-up an iterative solver, e.g. by applying an efficient preconditioner to decrease the number of required iterations, or by parallelizing the given algorithm, etc. To acquire maximum performance from a massively parallelized environment, different parts of such a solver must be asynchronously parallelized to avoid expensive cooperation between threads. The […]

In this paper, we present a fast iterative magnetic resonance imaging (MRI) reconstruction algorithm taking advantage of the prevailing GPGPU programming paradigm. In clinical environment, MRI reconstruction is usually performed via fast Fourier transform (FFT). However, imaging artifacts (i.e. signal loss) resulting from susceptibility-induced magnetic field inhomogeneities degrade the quality of reconstructed images. These artifacts […]

In this work, we investigate the global memory access mechanism on recent GPUs. For the purpose of this study, we created specific benchmark programs, which allowed us to explore the scheduling of global memory transactions. Thus, we formulate a model capable of estimating the execution time for a large class of applications. Our main goal […]

Fourier domain optical coherence tomography (FD-OCT) provides faster line rates, better resolution, and higher sensitivity for noninvasive, in vivo biomedical imaging compared to traditional time domain OCT (TD-OCT). However, because the signal processing for FD-OCT is computationally intensive, real-time FD-OCT applications demand powerful computing platforms to deliver acceptable performance. Graphics processing units (GPUs) have been […]

Techniques used to implement an unstructured grid solver on modern graphics hardware are described. The three-dimensional Euler equations for inviscid, compressible flow are considered. Effective memory bandwidth is improved by reducing total global memory access and overlapping redundant computation, as well as using an appropriate numbering scheme and data layout. The applicability of per-block shared […]