high performance computing on graphics processing units: hgpu.org

We develop cache efficient, multicore, and GPU algorithms for RNA folding using Nussinov’s equations. Our cache efficient algorithm provides a speedup between 1.6 and 3.0 relative to a naive straightforward single core code. The multicore version of the cache efficient single core algorithm provides a speedup, relative to the naive single core algorithm, between 7.5 […]

We develop novel single-GPU parallelizations of the Smith-Waterman algorithm for pairwise sequence alignment. Our algorithms, which are suitable for the alignment of a single pair of very long sequences, can be used to determine the alignment score as well as the actual alignment. Experimental results demonstrate an order of magnitude reduction in run time relative […]

Diagrammatic Determinantal Quantum Monte Carlo (DDQMC) algorithms are used to solve quantum impurity models such as the Anderson model. The calculation of acceptance rates and observables during the Monte Carlo walk involves linear algebra operations whose computational expense increases with decreasing temperature. Thus, the lower boundary of the treatable temperature range is limited by the […]

A mathematical morphology is used as a tool for extracting image components that are useful in the representation and description of region shape. The mathematical morphology operations of dilation, erosion, opening, and closing are important building blocks of many other image processing algorithms. The data parallel programming provides an opportunity for performance acceleration using highly […]

2014-09-20 Accepted papers will be published in the one of the following Journals with ISSN. International Journal of Computer and Communication Engineering (IJCCE, ISSN: 2010-3743) Journal of Advances in Computer Networks (JACN, ISSN: 1793-8244) Journal of Communications (ISSN: 1796-2021) 3G & 4G Mobile Communication Services Agents and Multi-Agents systems for ICT Integrated Circuits for Communications […]

We consider the performance acceleration of the conventional Time Domain Backprojection and Kirchhoff Migration algorithms for imaging concealed targets. The Compute Unified Device Architecture (CUDA) and Open Computing Language (OpenCL) are used here for accelerating these algorithms on Graphics Processing Units (GPUs). Data generated by means of analytical methods, simulation and experiment are used for […]

Parallel performance for GPUs today surpasses the traditional multi-core CPUs. Currently, many AI algorithms started to be tested on GPUs rather than CPUs, especially after the release of libraries such as Cuda and OpenCL that allows the implementation of general algorithms on the GPU. One of the most famous game tree search algorithms is Negamax, […]

The success of Android is based on its unified Java programming model that allows to write platform-independent programs for a variety of different target platforms. However, this comes at the cost of performance. As a consequence, Google introduced APIs that allow to write native applications and to exploit multiple cores as well as embedded GPUs […]

Distributed sources of voluminous data have raised the need of distributed data mining. Conventional data mining techniques works well on structured data which is clean, pre-processed and properly arranged either in the form of structured files, databases or data warehouse. These techniques are based upon centralised data store however they have several limitations in distributed […]

The IEEE Symposium on Field Programmable Custom Computing Machines is the original and premier forum for presenting and discussing new research related to computing that exploits the unique features and capabilities of FPGAs and other reconfigurable hardware. Over the past two decades, FCCM has been the place to present papers on architectures, tools, and programming […]

his paper presents a simulation of the casting solidification process performed on graphics processors compatible with nVidia CUDA architecture. The new approach shown in this paper allows the process of matrix building to be divided into two independent phases. The first is independent from the nodal temperature values computed in successive time–steps. The second is […]

SIMD Parallelization is one of the most useful ways of decreasing the computation time and increases the performance of computation intensive algorithms. To do such process, we could execute some processes on several machines by using different platforms like MPI, OpenMP and distribute the workload by using message passing and shared memory. One of the […]