Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.
About 2,532 papers for “GPU cluster”
Samek Jakub · Cvut DSpace (Czech Technical University) · 2016
Tato bakalářská práce se zabývá možnostmi clusteringu počítačů vybavených grafickou kartou pro obecné výpočty s ohledem na běh bezpečnostních nástrojů k prolamování hesel. Praktickou část práce představuje implementace GPU clusteru v prostředí FIT ČVUT s možností distribuovaného běhu vybraných programů a měření výkonnosti clusteru.
Cited by 0Open access
Philippe Helluy, Jonathan Jung · 2014
Cited by 0
Zhe Fan, Feng Qiu, Arie Kaufman et al. · 2005
Inspired by the attractive Flops/dollar ratio and the incredible growth in the speed of modern graphics processing units (GPUs), we propose to use a cluster of GPUs for high performance scientific computing. As an example application, we have developed a parallel flow simulation using the lattice Boltzmann model (LBM) on a GPU cluster and have simulated the dispersion of airborne contaminants in the Times Square area of New York City. Using 30 GPU nodes, our simulation can compute a 480x400x80 LBM in 0.31 second/step, a speed which is 4.6 times faster than that of our CPU cluster implementation. Besides the LBM, we also discuss other potential applications of the GPU cluster, such as cellular automata, PDE solvers, and FEM.
Cited by 436
Emanouil Atanassov, D. Georgiev, Nikolai L. Manev · 2012
The problem of integer factorization is of high practical importance because of the widespread use of public key cryptosystems for encryption and authentication of Internet connections. In this paper we describe our implementation of the elliptic curve method of integer factorization on an NVIDIA GPU-based cluster using the CUDA technology and report the results of our experiments. The performance of our implementation is compared with other known experiments and software.
Cited by 2
Michaël Krajecki, Julien Loiseau, François Alin et al. · 2016
The High Performance Computing field is striving for the next computational step: exascale (1018 floating point operations per second). The first machine at this scale is expected at horizon 2020 and some French companies such as Atos/Bull are already working on it. Their supercomputer, Sequana, will deliver the expected computational power using either Xeon Phi or GPU accelerators. However these machines are built to produce an exaFLOPS, they are exclusively based on computation. The question is how they will behave when confronted with highly irregular problems such as graph theory ones. Graph algorithms are considered to be highly irregular with intensive communication and require high memory resources (but also I/O). In this study our goal is to provide an optimized implementation of the Graph500 benchmark to rank the Kepler GPU based supercomputers (a specific class of HPC architectures) in the Graph500 list.
Cited by 3
Michaël Krajecki, Julien Loiseau, Francois Alin et al. · HAL (Le Centre pour la Communication Scientifique Directe) · 2016
Cited by 0
Keliang Zhang, Baifeng Wu · 2012
Modern GPUs are gradually used by more and more cluster computing systems as the high performance computing units due to their outstanding computational power, whereas bringing node-level architectural heterogeneity to cluster. In this paper, based on MPI and CUDA programming model, we aim to investigate task scheduling for GPU heterogeneous cluster by taking into account the node-level heterogeneous characteristics. At first, based on our GPU heterogeneous cluster, we classify executing tasks to six major classifications according to their parallelism degrees, input data sizes, and processing workloads. Then, aiming to realize optimal mapping between tasks and computing resources, a task scheduling strategy is presented. The strategy consists of two key algorithms. The first is packing task algorithm (PTA) used to pack multiple tasks into a single task, such packing provides us a way of task classification converting according to the characteristic of computing resources. The second is system-level scheduling algorithm(SLSA) used to distribute parallel and sequential tasks to corresponding nodes, to maintain the load balance.
Cited by 7
E. D’Azevedo, Judith Hill · Procedia Computer Science · 2012
This paper describes our progressindeveloping softwarefor performing parallelLUfactorizationofalarge dense matrix on a GPU cluster. Three approaches, with increasing software complexity, are considered: (i) a naive “thunking” approach that links the existing parallel ScaLAPACK software library with cuBLAS through a software emulation layer; (ii) a more intrusive magmaBLAS implementation integrated into the LU solver in the High-Performance Linpack software; and (iii) a left-looking out-of-core algorithm for solving problems that are larger than the available memory on GPUdevices. Comparisonof the performancegainsversus the current ScaLAPACK PZGETRF are provided.
Cited by 16Open access
Changaival, Boonyarit · CERN Document Server (European Organization for Nuclear Research) · 2014
ITS cluster finding algorithm is one of the data reduction algorithms at ALICE. It needs to be processed fast due to a high amount of data readout from the detector. A variety of platforms were studied for the system design. My work is to design, implement and benchmark this algorithm on a GPU platform. GPU is one of many platform that promote parallel computing. A high-end GPU can contain over 2000 processing cores comparing to the commodity CPUs which have only four cores. The program is written in C and CUDA library. The throughput (Number of events per second) is used as a metric to measure the performance. With the latest implementation, the throughput was increased by a factor of 5.
Cited by 0Open access
Philippe Helluy, Jonathan Jung · ESAIM Proceedings and Surveys · 2014
In this work we propose an efficient finite volume approximation of two-fluid flows. Our scheme is based on three ingredients. We first construct a conservative scheme that removes the pressure oscillations phenomenon at the interface. The construction relies on a random sampling at the interface [5, 6]. Secondly, we replace the exact Riemann solver by a faster relaxation Riemann solver with good stability properties [4]. Finally, we apply Strang directional splitting and optimized memory transpositions in order to achieve high performance on Graphics Processing Unit (GPU) or GPU cluster computations.
Cited by 5Open access
Haicheng Wu, Haicheng Wu, Jeffrey Young et al. · 2013
�On-line and off-line analysis �Retail analysis �Forecasting �Pricing �Etc… �Combination of relational data queries and computational kernels �Current applications process 1 to 50 TBs of data [1] �Not a traditional domain for GPU acceleration, but: �Parallel queries experience good speedup on GPUs [2] �GPU-related techniques can be applied to other “Big Data ” problems like irregular graphs, sorting
Cited by 0
M-Kusumgar · Zenodo (CERN European Organization for Nuclear Research) · 2026
Full Changelog: https://github.com/mrc-ide/gpu-cluster-showcase/commits/V0.1.0
Cited by 0Open access
Büchner, O. · JuSER (Forschungszentrum Jülich) · 2011
Cited by 0Open access
Benjamin Horowitz, Angela M. Bayer · ArXiv.org · 2025
We present jFoF, a fully GPU-native Friends-of-Friends (FoF) halo finder designed for both high-performance simulation analysis and differentiable modeling. Implemented in JAX, jFoF achieves end-to-end acceleration by performing all neighbor searches, label propagation, and group construction directly on GPUs, eliminating costly host--device transfers. We introduce two complementary neighbor-search strategies, a standard k-d tree and a novel linked-cell grid, and demonstrate that jFoF attains up to an order-of-magnitude speedup compared to optimized CPU implementations while maintaining consistent halo catalogs. Beyond performance, jFoF enables gradient propagation through discrete halo-finding operations via both frozen-assignment and topological optimization modes. Using a topological optimization approach via a REINFORCE-style estimator, our approach allows smooth optimization of halo connectivity and membership, bridging continuous simulation fields with discrete structure catalogs. These capabilities make jFoF a foundation for differentiable inference, enabling end-to-end, gradient-based optimization of structure formation models within GPU-accelerated astrophysical pipelines. We make our code publicly available at https://github.com/bhorowitz/jFOF/.
Cited by 0Open access
M-Kusumgar · Zenodo (CERN European Organization for Nuclear Research) · 2026
Full Changelog: https://github.com/mrc-ide/gpu-cluster-showcase/commits/V0.1.0
Cited by 0Open access
Karl Fürlinger, Nicholas J. Wright, David Skinner · 2011
Accelerating applications with GPUs has recently garnered a lot of interest from the scientific computing community. While tools for optimizing individual kernels are readily available, there is a lack of support for the specific needs of the HPC area. Most importantly, integration with existing parallel programming models (MPI and threading) and scalability to the full size of the machine are required. To address these issues we present our work on monitoring and performance evaluation of the CUDA runtime environment in the context of our scalable and efficient profiling tool IPM. We derive metrics for GPU utilization and identify missed opportunities for GPU-CPU overlap. We evaluate the monitoring accuracy and overheads of our approach and apply it to a full scientific application.
Cited by 7
遠藤 敏夫, Toshio Endo · Tokyo Tech Research Repository (Tokyo Institute of Technology) · 2010
Cited by 0
Puff, Jochen · Fachbereich Informatik (University of Stuttgart) · 2010
Cited by 0
Lokman Abbas-Turki, Stéphane Vialle · HAL (Le Centre pour la Communication Scientifique Directe) · 2009
Presentation given at 2nd JTE "GPGPU", University Paris-6, 4 décembre 2008, Paris, France.
Cited by 0Open access
Daniel M. Davis, Robert F. Lucas, Gene Wagenbreth et al. · 2007
The forces modeling and simulation (FMS) community has often been hampered by constraints in computing: not enough resolution, not enough entities, not enough behavioral variants. High performance computing can ameliorate those constraints. The use of Linux clusters is one path to higher performance; the use of graphics processing units (GPU) as accelerators is another. Merging the two paths holds even more promise. The high performance computing modernization program (HPCMP) accepted a successful proposal for a new 512 CPU (1,024 core), GPU-enhanced Linux cluster for the joint forces command's joint experimentation directorate (J9). The basic concepts underlying the use of GPUs as accelerators for intelligent agent, entity-level simulations are laid out. The simulation needs of J9, the direction from HPCMP and the careful analysis of the intersection of these are explicitly discussed. The configuration of the cluster is addressed and the assumptions that led to the conclusion that GPUs could increase performance by a factor of two are offered. Issues, problems and solutions will all be reported objectively, as guides to the FMS community and as confirmation or rejection of early assumptions. Early characterization runs of a single CPU with GPU-enhanced extensions are reported.
Cited by 4