high performance computing on graphics processing units: hgpu.org

We propose a parallel Mean Shift (MS) tracking algorithm on Graphics Processing Unit (GPU) using Compute Unified Device Architecture (CUDA). Traditional MS algorithm uses a large number of color histogram, say typically 16x16x16, which makes parallel implementation infeasible. We thus employ K-Means clustering to partition the object color space that enables us to represent color […]

The shader in the GPU are widely used to model coastal terrain, but the created terrain are of great similarity and unable to embody the differences of coastal features. To overcome the above disadvantage, we present a new modeling method for created terrain based on sketch map. Through specifying the coastal features type, the proposed […]

This study is devoted to exploring possible applications of GPU technology for acceleration of the database access. We use the n-gram based approximate text search engine as a test bed for GPU based acceleration algorithms. Two solutions – hybrid CPU/GPU and pure GPU algorithms for query processing are studied and compared with the baseline CPU […]

Interactive isosurface extraction has recently become possible through successful efforts to map algorithms such as Marching Cubes (MC) and Marching Tetrahedra (MT) to modern Graphics Processing Unit (GPU) architectures. Other isosurfacing algorithms, however, are not so easily portable to GPUs, either because they involve more complex operations or because they are not based on discrete […]

Parallel codes are written primarily for the purpose of performance. It is highly desirable that parallel codes be portable between parallel architectures without significant performance degradation or code rewrites. While performance portability and its limits have been studied thoroughly on single processor systems, this goal has been less extensively studied and is more difficult to […]

We present a unique and elegant graphics hardware realization of multi agent simulation. Specifically, we adapted Velocity Obstacles that suits well parallel computation on single instruction, multiple thread, SIMT, type architecture. We explore hash based nearest neighbors search to considerably optimize the algorithm when mapped on to the GPU. Moreover, to alleviate inefficiencies of agent […]

Driven by the insatiable demand of real-time graphics, especially from the market of computer games, Graphics Processing Unit (GPU) is becoming a major computing horsepower during recent years since the performance of GPU is surpassing that of the contemporary CPU. This paper presents our study on how to efficiently recover the passwords for encrypted RAR […]

Protecting data by passwords in documents such as DOC, PDF or RAR, ZIP archives has been demonstrated to be weak under dictionary attacks. Time for recovering the passwords of such documents mainly depends on two factors: the size of the password search space and the computing power of the underline system. In this paper, we […]

Graphics processing unit GPU supports data parallel computation through single instruction multi-data, and provides powerful logic computation ability. We have testified that RAR password decryption rate is greatly improved utilizing parallel computation ability of GPU.

Dealing with high-resolution imagery with billions or trillions of samples is an enormous challenge that oftenoverwhelms the graphics subsystem of any computer. Silicon Graphics, Inc. addressed this issue by providing explicit hardwaresupport for offset registers and texture sub-loads in their InfiniteReality machine. The clipmap algorithm uses sub-textures andincremental updates based on a toroidal mapping to […]

We present benchmark results of optimized dense matrix multiplication kernels for Cypress GPU. We write general matrix multiply (GEMM) kernels for single (SP), double (DP) and double-double (DDP) precision. Our SGEMM and DGEMM kernels show ~2 Tflop/s and ~470 Gflop/s, respectively. These results for SP and DP correspond to 73% and 87% of the theoretical […]

Original bump mapping is only defined for surfaces with a known surface parametrization. In this paper a new method, for the GPU, is proposed which does not use such a given parametrization. To compute the perturbed normal the only inputs used are the surface position, the height value and the original normal. The method decouples […]