high performance computing on graphics processing units: hgpu.org

We report on the development of a new code for long-term simulation of beam-beam effects in particle colliders. The underlying physical model relies on a matrix-based arbitrary-order symplectic particle tracking for beam transport and the Bassetti-Erskine approximation for the beam-beam interaction. The computations are accelerated through a parallel implementation on a hybrid GPU/CPU platform. With […]

The need to speed-up computing has introduced the interest to explore parallelism in algorithms and parallel programming. Technology is evolving fast but computing power in sequential execution is not increasing as much as earlier but CPUs contain more and more parallel computing resources. However, parallel algorithms may not be able to exploit all the parallelism […]

Large scale beam dynamics simulations can derive significant benefit from efficient implementation of general-purpose particle tracking on GPUs. We present the latest results of our work on accelerating Argonne National Lab’s accelerator simulation code ELEGANT, using CUDA-enabled GPUs. We summarize the performance of beamline elements ported to GPU, and discuss optimization techniques for some core […]

The “Simple Accelerator Modelling in Matlab” (SAMM) code is a set of Matlab routines for modelling beam dynamics in high energy particle accelerators. It includes a set of CUDA codes that can be run on a graphics processing unit. These can be called from SAMM and can potentially give a significant increase in tracking speed. […]

This thesis conducts a number of numerical experiments using massively parallel GPU computations to study a new continuous data assimilation algorithm. We test the algorithm on two-dimensional incompressible fluid flows given by the Navier-Stokes equations. In this context, observations of the Eulerian velocity field given at a finite resolution of nodal points in space may […]

Evolutionary Computation techniques and other metaheuristics have been increasingly used in the last years for solving many real-world tasks that can be formulated as optimization problems. Among their numerous strengths, a major one is their natural predisposition to parallelization. In this paper, we introduce libCudaOptimize, an open source library which implements some metaheuristics for continuous […]

BACKGROUND: Multidimensional scaling (MDS) is a widely used approach to dimensionality reduction. It has been applied to feature selection and visualization in various areas. Among diverse MDS methods, the classical MDS is a simple and theoretically sound solution for projecting data objects onto a low dimensional space while preserving the original distances among them as […]

The advent of low cost GPU hardware and user friendly parallel programming APIs, such as NVIDIA CUDA means that affordable, programmable, high-performance computing environments for simulation are now attainable for development of scientific simulations. In this paper the authors present the MineHunter program, a parallel simulation of neural networks on NVIDIA CUDA. The simulation consists […]

In this paper, we implement ACO algorithms on a PC which has 4 GTX 480 GPUs. We implement two types of ACO models; the island model, and the other is the master/slave model. When we compare the island model and the master/slave model, the island model shows promising speedup values on class (iv) QAP instances. […]

For the visual analysis of multidimensional data, dimension reduction methods are commonly used to project to a lower-dimensional visual space. In the context of multifields, i.e., volume data with a multidimensional attribute space, the spatial arrangement of the samples in the volumetric domain can be exploited to generate a Continuous Representation of the Projected Attribute […]

Optimising the use of all the cores of a hybrid multi-core CPU and its accelerating GPUs is becoming increasingly important as such combined systems become widely available. We show how a complex interplay of cross-calling kernels and host components can be used to support good throughput performance on hybrid simulation tasks that have inherently serial […]

Scaling up deep learning algorithms has been shown to lead to increased performance in benchmark tasks and to enable discovery of complex high-level features. Recent efforts to train extremely large networks (with over 1 billion parameters) have relied on cloud-like computing infrastructure and thousands of CPU cores. In this paper, we present technical details and […]