high performance computing on graphics processing units: hgpu.org

For solving large instances of the Travelling Salesman Problem (TSP), the use of a candidate set (or candidate list) is essential to limit the search space and reduce the overall execution time when using heuristic search methods such as Ant Colony Optimisation (ACO). Recent contributions have implemented ACO in parallel on the Graphics Processing Unit […]

In this paper we present three-dimensional numerical simulations of electromagnetic waves. The Maxwell equations are solved by the Discontinuous Galerkin (DG) method. For achieving high performance, we exploit two levels of parallelism. The coarse grain parallelism is managed through MPI and a classical domain decomposition. The fine grain parallelism is managed with OpenCL in order […]

This thesis deals with manipulating huge geometric data in the field of computer graphics. The proposed approach uses a data stream technique to allow processing gigantic datasets that by far exceed the size of the main memory. The amount of data is hierarchically reduced by clustering and replacing each cluster by a representative. The input […]

Graphics Processing Unit (GPU) programming techniques have been applied to a range of scientific and engineering computations. In computational electromagnetics, uses of the GPU technique have dramatically increased since the release of NVIDIA’s Compute Unified Device Architecture (CUDA), a powerful and simple-to-use programmer environment that renders GPU computing easy accessibility to developers not specialized in […]

Mathematicians and computational scientists are often limited in their ability to model complex phenomena by the time it takes to run simulations. This thesis will inform interested researchers on how the development of highly parallel computer graphics hardware and the compiler frameworks to exploit it are expanding the range of algorithms that can be explored […]

Neural networks and machine learning algorithms in general require a flexible environment where new algorithm prototypes and experiments can be set up as quickly as possible with best possible computational performance. To that end, we provide a new framework called Torch7, that is especially suited to achieve both of these competing goals. Torch7 is a […]

This book follows an example-driven, simplified, and practical approach to using OpenCL for general purpose GPU programming. If you are a beginner in parallel programming and would like to quickly accelerate your algorithms using OpenCL, this book is perfect for you! You will find the diverse topics and case studies in this book interesting and […]

BACKGROUND AND OBJECTIVE: Short-read sequencing is becoming the standard of practice for the study of structural variants associated with disease. However, with the growth of sequence data largely surpassing reasonable storage capability, the biomedical community is challenged with the management, transfer, archiving, and storage of sequence data. METHODS: We developed Hierarchical mUlti-reference Genome cOmpression (HUGO), […]

During brachytherapy and biopsy, significant prostate motion (including deformation) can occur, causing the target lesion to move during the procedures. One method to improve the accuracy of needle tip placement during these percutaneous procedures is to use a 3D Finite Element (FE) model to estimate the amount of needle deflection. This model is based on […]

The problem of scheduling sports leagues has received considerable attention in recent years, especially since mathematically optimized schedules often have a large impact both economically and environmentally. The Mirrored Traveling Tournament Problem (mTTP) is an optimization problem that represents certain types of sports scheduling where the main objective is to minimize the total distance traveled […]

Multiple-GPU systems have become ubiquitously available due to their support of massive parallel computing and more device memory for large scale problems. Such systems are ideal for In-Situ visualization applications, which require significant computational power for concurrent execution of simulation and visualization. While pipelining based parallel computing scheme overlaps the execution of simulation and rendering […]

This paper describes recent work on the BIDMach toolkit for large-scale machine learning. BIDMach has demonstrated single-node performance that exceeds that of published cluster systems for many common machine-learning task. BIDMach makes full use of both CPU and GPU acceleration (through a sister library BIDMat), and requires only modest hardware (commodity GPUs). One of the […]