high performance computing on graphics processing units: hgpu.org

In this paper we present a GPU implementation to accurately select 3D objects based on their silhouettes by a pointing device with six degrees of freedom (6DOF) in a virtual environment (VE). We adapt a 2D picking metaphor to 3D selection in VE’s by changing the projection and view matrices according to the position and […]

In this paper, an improved Poisson matting method is proposed to segment participants in real-time at a tele-presence session from their background. In order to improve the matting process, we introduce the concept of color distance and extend the standard Poisson matting using patch matching. The idea of patch based matching algorithm, which is widely […]

We present an extension of the model checker PRISM for (general purpose) graphics processing units (GPUs). The extension is based on parallel algorithms for probabilistic model checking which are tuned for GPUs. In particular, we parallelize the parts of the algorithms that boil down to linear algebraic operations, like solving systems of linear equations and […]

Maximal frequent itemsets are one of several condensed representations of frequent itemsets, which store most of the information contained in frequent itemsets using less space, thus being more suitable for stream mining. This paper considers a problem that to the best of our knowledge has not been addressed, namely, how to use GPU to mine […]

Volume rendering techniques have been used widely for high quality visualization of 3D data sets, especially in the fields of biomedical image processing. However, when rendering very large (out-of-core) volume data sets, the conventional in-core volume rendering algorithms cannot run efficiently due to the impossibility of fitting the entire input data in the internal memory […]

The introduction of programmability into commodity graphics hardware (GPUs) has enabled their use much beyond their native domain of computer graphics, in many areas of high performance computing. We have shown in previous work that many types of CT algorithms, both iterative and non-iterative, can also greatly benefit from the high degree of SIMD (same […]

We present a design and implementation of a high-throughput deep packet inspection performing both stream categorization and intrusion detection on GPU platform using CUDA. This implementation is capable of matching 64 ethernet packet streams against 25 given regular expressions at 524 Mb/s rate on a computer system with GeForce GTX 295 graphic card.

A CUDA implementation of the existing software FIRST (Fast Iterative Reconstruction Software for (PET) Tomography) is presented. This implementation uses consumer graphics processing units (GPUs) to accelerate the compute-intensive parts of the reconstruction: forward and backward projection. FIRST was originally developed in FORTRAN, and it has been migrated to C language to be used with […]

We present our new parallel GPU clusters in Beijing and Heidelberg and demonstrate the nearly optimal speedup and performance for parallel direct astrophysical N-body simulations with up to six million bodies. We reach about 1/3 of the peak performance for a real application code. The clusters are used to simulate dense star clusters with many […]

We propose a conceptual extension of the standard triangle-based graphics pipeline by an additional intersection stage. The corresponding intersection program performs ray-object intersection tests for each fragment of an object’s bounding volume. The resulting hit fragments are transferred to the fragment shading stage for computing the illumination and performing further fragment operations. Our approach combines […]

The finite-difference time-domain (FDTD) algorithm has become a tool of choice in many areas of RF and microwave engineering and optics. However, FDTD runs too slow for some simulations to be practical, even when carried out on supercomputers. The development of dedicated hardware to accelerate FDTD computations has been investigated. In this paper, we demonstrate […]

This paper describes the fast point-based 2-D/3-D registration that will increase the registration speed of intraoperative two-dimensional (2-D) fluoroscopy and preoperative three-dimensional (3-D) CT images using GPU (graphics processing unit)-based DRR’s preprocessing. Rigid 2-D/3-D registration of 2-D fluoroscopy images with 3-D CT images can be used for image-guided surgery or intraoperative navigation. X-ray fluoroscopy images […]