high performance computing on graphics processing units: hgpu.org

Generalized Hough Transform (GHT) is a well known but seldom used algorithm for object detection. The merit of this algorithm is its ability to detect object location and its pose accurately. However, this algorithm has a huge drawback of high memory and extensive computational requirement. As a result, usage of this algorithm for object detection […]

We propose an implementation for quad-tree based solid object coloring using Compute Unified Device Architecture (CUDA). There are numerous different techniques in use for solid object coloring. One commonly used technique is the quad-tree, which has evolved from work in different fields. A quad-tree is a tree data structure in which each internal node has […]

We present MGPU, a C++ programming library targeted at single-node multi-GPU systems. Such systems combine disproportionate floating point performance with high data locality and are thus well suited to implement real-time algorithms. We describe the library design, programming interface and implementation details in light of this specific problem domain. The core concepts of this work […]

This research paper explores an OpenCL-based algorithm to aid heat load modelling for district heating plants. Previous studies have proven that heat loads mostly depend on the external temperatures (temperature dependency component) and the time of the day (time dependency component). In this research we have used the sum of two truncated exponential functions to […]

This paper proposes a novel Vehicle to Vehicle (V2V) communication system for collision avoidance which merges four different wireless devices (GPS, Wi-Fi, ZigBee and 3G) with a low power embedded Single Board Computer (SBC) in order to increase processing speed while maintaining a low cost. The three major technical challenges with such combinations are the […]

This experiment explores the performance of GPUs in genetic algorithms using binary data. The experiment executes a genetic algorithm which works with binary sequences that are processed on the GPU. The hypothesis is that an optimal number of maximum threads (likely larger than small) is required to have an optiomal runtime. The results show that […]

General purpose GPU based systems are highly attractive as they give potentially massive performance at little cost. Realizing such potential is challenging due to the complexity of programming. This paper presents a compiler based approach to automatically generate optimized OpenCL code from data-parallel OpenMP programs for GPUs. Such an approach brings together the benefits of […]

Frequency domain analysis is one of the most common analysis techniques in signal and image processing. Fast Fourier Transform (FFT) is a well know tool used to perform such analysis by obtaining the frequency spectrum for time- or spatial-domain signals and vice versa. FFT-Shift is a subsequent operation used to handle the resulting arrays from […]

This paper presents an implementation of the FDTD-compatible Green’s function on a heterogeneous parallel processing system. The developed implementation simultaneously utilizes computational power of the central processing unit (CPU) and the graphics processing unit (GPU) to the computational tasks best suited to each architecture. Recently, closed-form expression for this discrete Green’s function (DGF) was derived, […]

The histogram is a fundamental statistical tool that has been extensively used in various domains. In data mining and machine learning applications, weighted histogram calculation often serves as a key component in the processing of their massive data sets. However, the atomic operation, which is introduced to resolve the collisions in GPU-based parallel histogramming with […]

Graphics models are getting increasingly bulkier with detailed geometry, textures, normal maps, etc. There is a lot of interest to model and navigate through detailed models of large monuments. Many monuments of interest have both rich detail and large spatial extent. Rendering them for navigation on a single workstation is practically impossible, even given the […]

Molecular dynamics (MD) simulations provide a molecular-resolution physical description of the folding and assembly processes, but the size and the timescales of simulations are limited because the underlying algorithm is computationally demanding. We recently introduced a parallel neighbor list algorithm that was specifically optimized for MD simulations on GPUs. In our present study, we analyze […]