16,537 Hits in 6.0 sec

A Multi-GPU Programming Library for Real-Time Applications [chapter]

Sebastian Schaetz, Martin Uecker
2012 Lecture Notes in Computer Science  
We present MGPU, a C++ programming library targeted at single-node multi-GPU systems.  ...  These promising results lead us to conclude that multi-GPU systems are a viable solution for real-time MRI reconstruction as well as signal-processing applications in general.  ...  Conclusion We presented MGPU, a C++ template-based multi-GPU programming library for real-time applications.  ... 
doi:10.1007/978-3-642-33078-0_9 fatcat:kcur6mssxbg2pjmttin3d3kkaq

clOpenCL - Supporting Distributed Heterogeneous Computing in HPC Clusters [chapter]

Albano Alves, José Rufino, António Pina, Luís Paulo Santos
2013 Lecture Notes in Computer Science  
The former examples show that porting single-node-multi-GPU applications to a multi-node-multi-GPU execution environment is not straightforward.  ...  Thus, the benefits of a platform that would allow to efficiently run the same and unmodified program, whether in a single-node-multi-accelerator or a multi-nodemulti-accelerator scenario are obvious.  ...  An OpenCL application comprises a host program and a set of kernels intended to run on compute devices; the OpenCL specification defines a language for kernel programming, and an API for transferring data  ... 
doi:10.1007/978-3-642-36949-0_14 fatcat:uzhlp2oiofbtbchr632oik7jau

Real-world comparison of CPU and GPU implementations of SNPrank: a network analysis tool for GWAS

N. A. Davis, A. Pandey, B. A. McKinney
2010 Bioinformatics  
Our goal is to identify the best computational engine for the SNPrank web application and to provide a variety of well-tested implementations of SNPrank for Bioinformaticists to integrate into their research  ...  When compared with naïve, single-threaded CPU implementations, the GPU yields a large improvement in the execution time.  ...  ACKNOWLEDGEMENTS We would like to thank Chris Johnson for his programming contributions, and we would like to thank Nicholas Sinnott-Armstrong and Jason Moore for their helpful discussions.  ... 
doi:10.1093/bioinformatics/btq638 pmid:21115438 pmcid:PMC3018810 fatcat:mbseqsmgifgjxasxaypgpb2qau

Towards High-Level Programming of Multi-GPU Systems Using the SkelCL Library

Michel Steuwer, Philipp Kegel, Sergei Gorlatch
2012 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum  
for multi-GPU systems.  ...  In this paper, we focus on the specific support in SkelCL for systems with multiple GPUs and use a real-world application study from the area of medical imaging to demonstrate the reduced programming effort  ...  reconstruction software EMRECON [10] and the quadHIDAC PET data used in our application case study.  ... 
doi:10.1109/ipdpsw.2012.229 dblp:conf/ipps/SteuwerKG12 fatcat:iojevk44vbcyvas6x2c37zu27a

Towards A Multi-Device Version Of The Hyfmgpu Algorithm For Hyperspectral Scenes Registration

Jorge Fernández-Fabeiro, Álvaro Ordóñez, Arturo González-Escribano, Dora B. Heras
2018 Zenodo  
Hyperspectral image registration is a relevant task for real-time applications like environmental disasters management or search and rescue scenarios.  ...  Traditional algorithms were not devoted to real-time performance, the HYFMGPU algorithm having arisen as a solution to such a lack.  ...  Acknowledgements This work has been partially supported by Regional Government of Castilla y León (Spain) and ERDF program of European Union: PROPHET project (JCYL-VA082P17).  ... 
doi:10.5281/zenodo.1475157 fatcat:7jckloxyqzeljgynkz65y4bc7i

Cheetah: A Library for Parallel Ultrasound Beamforming in Multi-Core Systems

David Romero-Laorden, Carlos Julián Martín-Arguedas, Javier Villazón-Terrazas, Oscar Martinez-Graullera, Matilde Santos Peñas, César Gutierrez-Fernandez, Ana Jiménez Martín
2015 Journal of Applied Mathematics and Physics  
Taking this into account, a library for the fast generation of ultrasound images is presented.  ...  Developing new imaging methods needs to establish some proofs of concept before implementing them on real-time scenarios.  ...  The library is composed by several routines written in CUDA for fast execution, thus a NVIDIA© GPU is required at the present time.  ... 
doi:10.4236/jamp.2015.38131 fatcat:5pyl4djtlfhuzhlbz6uahrg2ka

Multi-device Controllers: A Library to Simplify Parallel Heterogeneous Programming

Ana Moreton-Fernandez, Arturo Gonzalez-Escribano, Diego R. Llanos
2017 International journal of parallel programming  
models (such as CUDA for NVIDIA's GPUs, or OpenMP for CPU-cores).  ...  In this work we introduce the Multi-Controler (MCtrl), an abstract entity implemented in a library, that coordinates the management of heterogeneous devices, including accelerators with different capabilities  ...  Acknowledgments This research has been partially supported by MICINN (Spain) and ERDF program of the European Union: HomProg-HetSys project (TIN2014-58876-P) and COST Program Action IC1305: Network for  ... 
doi:10.1007/s10766-017-0542-x fatcat:r4tlgwkz5jhojhfp4s5xdx666y

Running applications on a hybrid cluster
Запуск приложений на гибридном кластере

A. V. Bogdanov, I. G. Gankevich, V. Yu. Gayduchok, N. V. Yuzhanin
2015 Компьютерные исследования и моделирование  
Some statistics from tests programs and applications runs will be demonstrated. The main focus of interest is open source applications (e. g.  ...  We also put emphasis on multi-GPU systems that are often used to build hybrid clusters. Calculations were performed on a hybrid cluster of SPbU computing center.  ...  But programming such systems requires more accuracy from a programmer. Multi-GPU systems introduce new questions.  ... 
doi:10.20537/2076-7633-2015-7-3-475-483 fatcat:utdivofnxvetrlqnoeu5c7ewnm

Multi-CPU/Multi-GPU Based Framework for Multimedia Processing [chapter]

Sidi Ahmed Mahmoudi, Pierre Manneback
2015 IFIP Advances in Information and Communication Technology  
Image and video processing algorithms present a necessary tool for various domains related to computer vision such as medical applications, pattern recognition and real time video processing methods.  ...  In this paper, we propose a new framework for multimedia (single image, multiple images, multiple videos, video in real time) processing that exploits the full computing power of heterogeneous machines  ...  Multi-GPU based Event detection and localization in real time This application is used for event detection and localization in real time.  ... 
doi:10.1007/978-3-319-19578-0_5 fatcat:p7wgwy2hyvabfdtf4gefnndcku

Automatic Multi-GPU Code Generation applied to Simulation of Electrical Machines [article]

Antonio Wendell De Oliveira Rodrigues , Frédéric Guyomarc'H, Jean-Luc Dekeyser (INRIA Lille - Nord Europe), Yvonnick Le Menach
2011 arXiv   pre-print
CPU + GPU) using OpenCL, an open standard for parallel programming of heterogeneous systems.  ...  Consequently, this approach helps industries to achieve their time-to-market constraints and confirms by experimental tests, performance improvements using multi-GPU environments.  ...  This allows for adding, modifying, transforming model elements in order to achieve a final model closer to the real program application.  ... 
arXiv:1107.0538v1 fatcat:z56bffz3mzh2ffhzaxt5exsphu

On the Use of Small 2D Convolutions on GPUs [chapter]

Shams A. H. Al Umairy, Alexander S. van Amesfoort, Irwan D. Setija, Martijn C. van Beurden, Henk J. Sips
2011 Lecture Notes in Computer Science  
The GPU architecture seems to be a suitable architecture to accelerate these convolutions, but reaching high application performance requires substantial development time and non-portable optimizations  ...  Computing many small 2D convolutions using FFTs is a basis for a large number of applications in many domains in science and engineering, among them electromagnetic diffraction modeling in physics.  ...  CUFFT provides a FFTW library-like interface for computing FFTs in parallel on CUDA GPUs.  ... 
doi:10.1007/978-3-642-24322-6_6 fatcat:b7u2jr3ap5clzpvjixhbxo36ca

Image processing on mobile devices: An overview

Rafika Thabet, Ramzi Mahmoudi, Mohamed Hedi Bedoui
2014 International Image Processing, Applications and Systems Conference  
With the emergence of general-purpose computing on embedded GPUs and their programming models like OpenGL ES 2.0 and OpenCL, mobile processors are gaining a more parallel computing capability.  ...  Its application on low-power mobile devices has been the interest of a wide research group related to newly emerging contexts such as augmented reality, visual search, object recognition, and so on.  ...  Their special investigation has focused on the role of mobile GPUs for energy or/and time optimization in real-time applications.  ... 
doi:10.1109/ipas.2014.7043267 fatcat:6dp4onkpzncwbbw7jdpv3v4pgi

High-level Programming for Medical Imaging on Multi-GPU Systems Using the SkelCL Library

Michel Steuwer, Sergei Gorlatch
2013 Procedia Computer Science  
In this paper, we present SkelCL -a high-level programming model for systems with multiple GPUs and its implementation as a library on top of OpenCL.  ...  scalability when using multi-GPU systems.  ...  Acknowledgements We would like to thank the anonymous reviewers for their valuable comments.  ... 
doi:10.1016/j.procs.2013.05.239 fatcat:l3yes2jwfnhclfjnxurqiqx5je

Automatic Parallelization of Python Programs for Distributed Heterogeneous Computing [article]

Jun Shirako, Akihiro Hayashi, Sri Raj Paul, Alexey Tumanov, Vivek Sarkar
2022 arXiv   pre-print
24 nodes and 144 GPUs in the OLCF Summit supercomputer for the Space-Time Adaptive Processing (STAP) radar application.  ...  This paper introduces a novel approach to automatic ahead-of-time (AOT) parallelization and optimization of sequential Python programs for execution on distributed heterogeneous platforms.  ...  Shirako, Hayashi, Paul, Tumanov, Sarkar hybrid Python/C++ code generation, fine-grained NumPy-to-CuPy conversion, and profile-based CPU/GPU runtime selection.  ... 
arXiv:2203.06233v1 fatcat:4e7sa6j3szgfri5pajrgccuvuu

Automatic Multi-GPU Code Generation Applied to Simulation of Electrical Machines

A. Wendell O. Rodrigues, Frédéric Guyomarc'h, Jean-Luc Dekeyser, Yvonnick Le Menach
2012 IEEE transactions on magnetics  
CPU + GPU) using OpenCL, an open standard for parallel programming of heterogeneous systems.  ...  Consequently, this approach helps industries to achieve their time-to-market constraints and confirms by experimental tests, performance improvements using multi-GPU environments.  ...  This allows for adding, modifying, transforming model elements in order to achieve a final model closer to the real program application.  ... 
doi:10.1109/tmag.2011.2179527 fatcat:hh7ikiinjrghhabgcxxpcfdpe4
« Previous Showing results 1 — 15 out of 16,537 results