high performance computing on graphics processing units: hgpu.org

Today’s high performance embedded computing applications are posing significant challenges for processing throughout. Traditionally, such applications have been realized on application specific integrated circuits (ASICs) and/or digital signal processors (DSP). However, ASICs’ advantage in performance and power often could not justify the fast increasing fabrication cost, while current DSP offers a limited processing throughput that […]

Sorting is a kernel algorithm for a wide range of applications. In this paper, we present a new algorithm, GPU-Warpsort, to perform comparison-based parallel sort on Graphics Processing Units (GPUs). It mainly consists of a bitonic sort followed by a merge sort. Our algorithm achieves high performance by efficiently mapping the sorting tasks to GPU […]

This paper will describe how off-the-shelf 3D graphics cards can be used for scientific computation like SAR processing. In particular, a highly efficient one-dimensional FFT and a fast direct (global) backprojection implementation will be presented and analyzed.

A background model is constructed to detect moving objects in video sequences. Subsequent frames are stacked on top of each other using associated registration information that must be obtained in a preprocessing step. The change of the brightness value in each pixel over time might be caused by a moving object. Current graphics processing units […]

The Kernel Polynomial Method (KPM) is one of the fast diagonalization methods used for simulations of quantum systems in research fields of condensed matter physics and chemistry. The algorithm has a difficulty to be parallelized on a cluster computer or a supercomputer due to the fine-gain recursive calculations. This paper proposes an implementation of the […]

Analytic and iterative tomographic image reconstruction suffers from the time-consuming forward- and back-projection steps. We recently presented a set of acceleration techniques that improve the performance of forward- and backprojection on CPU (central processing unit) and CBE (cell broadband engine) -based platforms compared to straight-forward implementations by several orders of magnitude.

The Support Vector Machine (SVM) is a popular supervised learning method, providing high accuracy in many classification and regression tasks. However, its training phase is a computationally expensive task. In this work, we focus on the acceleration of this phase and a geometric approach to SVM training based on Gilbert’s Algorithm is targeted, due to […]

This paper presents a new algorithm for synthesising image texture. Texture synthesis is an important process in image post-production. Previous approaches can be classified as either parametric or nonparametric. Of these nonparametric approaches have achieved the most impressive results. Unfortunately, these methods generally suffer from high computational cost and difficulty in handling scale in the […]

When it comes to rendering models available as points, rather than meshes, splats are a common intermediate internal representation. In this paper we further the state of the art by ray tracing splats to produce expected effects such as reflections, refraction, and shadows. We render complex models at interactive frame rates allowing real time viewpoint, […]

In recent years the rate of development of Graphics Processor Units (GPUs) has been significantly faster than any other component in a PC or Workstation. This is clearly demonstrated by a continued six-month doubling in performance, to the extent that current GPU floating point horse-power is significantly beyond that of conventional micro-processors. In combination with […]

This paper presents an evaluation of the state of the art in Graphics Processing Unit (GPU) algorithmic techniques. Fast, portable methods for maintaining state between independent passes of an algorithm are compared and contrasted with similar techniques from the previous generation, which are still in widespread use in the graphical and non-graphical fields today. The […]

This paper introduces an IO bandwidth reduction technique for real-time moment invariant classifier systems running on both CPUs and GPUs. This system can run in real time on commodity general purpose graphics processor unit (GPGPU) systems. The output IO is reduced by calculating the locations of objects of interest using a projection of the 2D […]