high performance computing on graphics processing units: hgpu.org

Heterogeneous parallel system with multiprocessors and accelerators are becoming ubiquitous due to better cost-performance and energy-efficiency. These heterogeneous processor architectures have different instruction sets and are optimized for either task latency or throughput purposes. Challenges occur in regard to programmability and performance when executing SPMD computations on heterogeneous architectures simultaneously. In order to meet these […]

We develop an optimized FFT based Poisson solver on a CPU-GPU heterogeneous platform for the case when the input is too large to fit on the GPU global memory. The solver involves memory bound computations such as 3D FFT in which the large 3D data may have to be transferred over the PCIe bus several […]

Numerical calculations based on finite-difference timedomain (FDTD) simulations for metallic nanostructures in a broad optical spectrum require an accurate modeling of the permittivity of dispersive materials. In this paper, we present the algorithms behind BCALM (Belgium-CAlifornia Light Machine), an open-source 3D-FDTD solver simultaneously operating on multiple Graphical Processing Units (GPUs) and efficiently utilizing multi-pole dispersion […]

The paper is devoted to creating effective and flexible Tsunami Modeling Environment based on a Service-Oriented Architecture (SOA) allowing high-level of operability and reusability of system components. Accordingly, we use the original Virtual MVC-design pattern (VMVC-pattern) approach that is demarcating a Functional (View) and an Implementation (Model) task by inducing an Integrator (Controller). This allows […]

Advances in computational methods and hardware platforms provide efficient processing of medical imaging data sets for surgical planning. In the case of neurosurgical interventions that are performed via a straight access path, planning entails selecting a pathway, from the scalp surface to the targeted area, that is of minimal risk to the patient. We propose […]

Sort-last parallel rendering is widely used. Recent GPU developments mean that a PC equipped with multiple GPUs is a viable alternative to a high-cost supercomputer: the Fermi architecture of s single GPU supports uniform virtual addressing, providing a foundation for non-uniform memory access (NUMA) on multi-GPU platforms. Such hardware changes require the user to reconsider […]

The article deals with the development of software and algorithmic techniques for multidimensional modeling and inversion of electromagnetic logs. With many new oil and gas fields being developed in difficult geological conditions, the requirements tend to be higher for reliability and efficiency of log data interpretation. Within this research various programs and algorithms were created […]

This paper studies the name lookup issue with longest prefix matching, which is widely used in URL filtering, content routing/switching, etc. Recently Content-Centric Networking (CCN) has been proposed as a clean slate future Internet architecture to naturally fit the contentcentric property of today’s Internet usage: instead of addressing end hosts, the Internet should operate based […]

We present a real-time subsurface scattering simulation to perform real-time rendering of translucent particle-based fluids. After particle-based fluid simulation, we immediately build voxelized fluids, calledVoronoi fluids, with particle locations and neighbour lists using GPUs. And then, we perform a multiple subsurface scattering simulation over the Voronoi fluids with the diffusion equation (DE). We employ Finite […]

We describe an interface and an implementation for performing Kronecker product actions on NVIDIA GPUs for multiple small 2-D matrices and 3-D arrays processed in parallel as a batch. This method is suited to cases where the Kronecker product component matrices are identical but the operands in a matrix-free application vary in the batch. Any […]

BACKGROUND: The maximal sensitivity for local alignments makes the Smith-Waterman algorithm a popular choice for protein sequence database search based on pairwise alignment. However, the algorithm is compute-intensive due to a quadratic time complexity. Corresponding runtimes are further compounded by the rapid growth of sequence databases. RESULTS: We present CUDASW++ 3.0, a fast Smith-Waterman protein […]

In order to harness the power of multicore CPUs and GPUs, HPC (High Performance Computing) programmers and even end-users need new tools and techniques to express their core problem, divide that core problem into sub problems, allocate computational resources for the sub-problems, execute the resources, and collect results. HPC users focus more on the problem […]