high performance computing on graphics processing units: hgpu.org

This paper describes the parallel SIFT-detector implementation on the basis of the NVIDIA CUDA technology for the images matching. The SIFT-detector implementation was applied for the images matching in the stereo-system mounted on the moving car and for images from the onboard UAV-camera.

The PageRank algorithm for determining the "importance" of Web pages forms the core component of Google’s search technology. As the Web graph is very large, containing over a billion nodes, PageRank is generally computed offline, during the preprocessing of the Web crawl, before any queries have been issued. Viewed mathematically, PageRank is nothing but the […]

Image inpainting refers to the process of reconstructing the original image from a damaged one in a visually plausible way. We propose a new gradientbased algorithm for exemplar-based inpainting by making use of L1 norm. We implement the most time consuming step of the algorithm on the GPU and compare the serial execution timings against […]

We present recent results of prototyping general-purpose particle tracking on GPUs and discuss our CUDA implementation of transfer maps for single-particle dynamics and collective effects. The objective of this work being incorporation of the GPU-accelerated tracking into ANL’s accelerator code ELEGANT [1], we used the code’s quadrupole and drift-with-LSC elements as test cases, achieving 80x […]

In this paper, we present what we believe to be the first GPU-based implementation (using CUDA) for solving the gene regulatory network model inference problem. Our implementation uses differential evolution as its search engine, and adopts a power law system of differential equations (an S-System) for modelling the dynamics of the gene regulatory networks of […]

We report on a GPU implementation of the condensation method designed by Abdelmalek Salem and Kouachi Said for computing the determinant of a matrix. We consider two types of coefficients: modular integers and floating point numbers. We evaluate the performance of our code by measuring its effective bandwidth and argue that it is numerical stable […]

Similarity search in a large collection of stored objects in a metric database has become a most interesting problem. The Spaghettis is an efficient metric data structure to index metric spaces. However, for real applications processing large volumes of generated data, query response times can be high enough. In these cases, it is necessary to […]

The interactions between the components of many natural and artificial systems can be described using a graph. These graphs often have an irregular structure with non-trivial topological features. Complex system behaviour emerges on the macroscopic scale from a large number of relatively simple interactions on the microscopic scale. To better understand the observed behaviour of […]

The objective of this Bachelor Thesis is to explore the possibilities of using NVIDIA CUDA enabled GPU Processors within the HDPC framework. The HDPC framework is one of the heterogeneous MP-SoC architectures programmed with the Daedalus framework. This paper will focus on the transfer overhead introduced by using the GPU and how to best cope […]

This paper presents the evaluation of the use of a graphics processor for realtime radio astronomy DSP (Digital Signal Processing) within VLBI (Very Long Baseline Interferometry). A polyphase filter bank (pfb) was implemented in a prototype application to convert external ADC input into channelized frequency streams. This system was tested with a 32 channel pfb, […]

In this paper we propose a method for computing convolution of large 3D images. The convolution is performed in a frequency domain using a convolution theorem. The algorithm is accelerated on a graphic card by means of the CUDA parallel computing model. Convolution is decomposed in a frequency domain using the DIF (decimation in frequency) […]

In this paper, we propose and implement the object oriented framework for the CUDA based pyramidal image blending. This algorithm is an essential part of an image stitching process for a seamless panoramic mosaic. The CUDA framework is a novel GPU programming framework from NVIDIA. It offers a complex integration framework and require more than […]