high performance computing on graphics processing units: hgpu.org

Graphics processing units (GPUs) for years have been dedicated mostly to real time rendering. Recently leading GPU manufactures have extended their research area and decided to support also graphics computing. In this paper, we describe an impact of new GPU features on development process of an efficient finite difference time domain (FDTD) implementation.

This Paper proposes an interactive point clouds fairing algorithm running on many-core system. The algorithm is composed of four steps. Firstly, a k nearest neighbor searching method was designed which could fully utilize the computing ability of GPU. Secondly, a parallel Gaussian weighted normal estimation was put forward. Thirdly, a weighted fairing method was proposed […]

We present the I3DC system prototype, which constructs the cube for tens of millions of data items within milliseconds, and provides high-quality cube visualization as well as highly-interactive OLAP operations. Our approach is based on a novel blending-as-aggregation (BAA) algorithm that maps distributive OLAP aggregations to the intrinsic rendering mechanisms of the GPU. Our system […]

The computational power of modern graphics processing units (GPUs) has become an interesting alternative in high performance computing. The specialized hardware of GPUs delivers a high degree of parallelism and performance. Various applications in scientific computing have been implemented such that computationally intensive parts are executed on GPUs. In this article, we present a GPU […]

The purpose of this paper is to implement association rule mining algorithm using Nvidia CUDA framework for general purpose computing on GPU. The major objective is to perform performance comparison of association rule mining algorithm using C based implementation on Intel Quad Core/Core2 Duo CPU with CUDA based implementation on Nvidia G80 and GTX 200 […]

This paper discusses the three-dimension visualization of the geological data using the ray-casting algorithm which can display the internal structure of geological body in details. An improved scheme transforming lots of matrix multiplications to a few of vector additions is developed to accelerate the ray-casting algorithm for the imaging of huge amount of three-dimensional geological […]

The Embarrassingly Parallel (EP) is one kernel benchmark of NAS Parallel Benchmarks (NPB) which are a set of programs designed to help evaluate the performance of parallel supercomputers. In the EP benchmark, two-dimensional statistics are accumulated from a large number of Gaussian pseudo-random numbers, which produced by Linear Congruential Generator (LCG). In this paper, we […]

This report presents steps towards accelerating Fluidity, a general-purpose computational fluid dynamics package. One portion of the code, an iterative solver, is targeted for optimisation by using Graphics Processing Units (GPUs) to perform computations. A literature survey which examines the performance issues of iterative solvers and optimisations which may overcome these issues on classical and […]

We present a performance analysis and benchmarking study of the OP2 "active" library, which provides an abstraction framework for the solution of parallel unstructured mesh applications. OP2 aims to decouple the scientific specification of the application from its parallel implementation, achieving code longevity and near-optimal performance through re-targeting the back-end to different hardware. Runtime performance […]

PDEs are important in a whole variety of applications. Want a suitable level of abstraction to separate the user’s specification of the app from the details of the parallel implementation. Aim to achieve code longevity and near-optimal performance through re-targeting the back-end to different hardware.

One of the major trends in the design of exascale architectures is the use of multicore nodes enhanced with GPU accelerators. Exploiting all resources of a hybrid accelerators- based node at their maximum potential is thus a fundamental step towards exascale computing. In this article, we present the design of a highly efficient QR factorization […]

Implementations of the Basic Linear Algebra Subprograms (BLAS) interface are major building block of dense linear algebra (DLA) libraries, and therefore have to be highly optimized. We present some techniques and implementations that significantly accelerate the corresponding routines from currently available libraries for GPUs. In particular, Pointer Redirecting – a set of GPU specific optimization […]