high performance computing on graphics processing units: hgpu.org

We provide efficient single-precision and integer GPU implementations of Strassen’s algorithm as well as of Winograd’s variant. On an NVIDIA C1060 GPU, a speedup of 32% (35%) is obtained for Strassen’s 4-level implementation and 33% (36%) for Winograd’s variant relative to the sgemm (integer version of sgemm) code in CUBLAS 3.0 when multiplying 16384×16384 matrices. […]

Determining upper body poses using computer vision can have long execution times when using traditional linear methods on the CPU. This paper shows how parallel processing methods, and in particular the usage of a GPU API called CUDA, can increase system performance.

The Partial Differential Equations (PDEs) play major role in mathematical modeling of problems in engineering and science. The engineering disciplines such as electro-magnetics and fluid dynamics use PDEs heavily and development of products in these engineering fields employs computational intensive numerical methods. These computational intensive methods takes reasonable amount of time on state of the […]

We present a novel certified and complete algorithm to compute arrangements of real planar algebraic curves. It provides a geometric-topological analysis of the decomposition of the plane induced by a finite number of algebraic curves in terms of a cylindrical algebraic decomposition. From a high-level perspective, the overall method splits into two main subroutines, namely […]

ATLAS is one of two general purpose collision detectors within the Large Hadron Collider, detecting millions of events per second. One tool for the eventual analysis of this data is TMVA, the Toolkit for Multi-Variate Analysis. Comprising of a number of machine learning techniques, it supports physicists in classifying events. This project forms a feasibility […]

Compressive sensing (CS) has been shown to enable dramatic acceleration of MRI acquisition in some applications. Being an iterative reconstruction technique, CS MRI reconstructions can be more time consuming than traditional inverse Fourier reconstruction. We have accelerated our CS MRI reconstruction by factors of up to 27 by using a split Bregman solver combined with […]

In this paper we propose a first step towards a general and open source approach for using GPGPU (General-Purpose Computation on GPUs) features within virtual machines (VMs). In particular, we describe the use of rCUDA, a GPGPU virtualization framework, to permit the execution of GPU-accelerated applications within VMs, thus enabling GPGPU capabilities on any virtualized […]

During my internship, I was in charge of implementing a GPU version of the optical flow algorithm. The optical flow algorithm is based on the total variation features described in my bibliography. The internship takes place in VITRONIC (Wiesbaden, Germany), a pioneer and one of the leading organizations worldwide in the field of machine vision. […]

Actual trend set by CPU manufacturers and recent developement in the field of graphical processing units (GPUs) offered us the computational power of multi-core and many-core architectures. Database applications can benefit greatly from parallelism; however, many algorithms need to be redesigned and many technical issues need to be solved. In this paper, we have focused […]

With the rapid development of the graphics processing unit (GPU), a recent GPU offers incredible resources for general purpose computing. We apply this technology to Monte Carlo simulations of the 2D and 3D lattice Ising models. By implementing the checkerboard algorithm, results are obtained up to 54, 62 and 68 times faster on the GPU […]

Recent advances in GPUs (graphics processing units) lead to massively parallel hardware that is easily programmable and widely applied in areas which require intensive computation besides graphics acceleration. The appearance of GPU clusters gains popularity in the scientific computing community, and the study on GPU clusters becomes an increasingly hot issue. While extending a singleGPU […]

Computational processors NVIDIA Tesla GPU based on the new Fermi generation of CUDA architecture are intended to perform massively parallel calculations applicable to various parts of the scientific and technical research, including the area of fluid dynamics modeling, in particular the simulation of real gas flow. In this paper we show that a significant acceleration […]