Filters








14 Hits in 5.6 sec

ExaGeoStat: A High Performance Unified Software for Geostatistics on Manycore Systems [article]

Sameh Abdulah, Hatem Ltaief, Ying Sun, Marc G. Genton, David E. Keyes
2018 arXiv   pre-print
Using state-of-the-art high performance dense linear algebra libraries associated with various leading edge parallel architectures (Intel KNLs, NVIDIA GPUs, and distributed-memory systems), ExaGeoStat  ...  The framework takes a first step in the merger of large-scale data analytics and extreme computing for geospatial statistical applications, to be followed by additional complexity reducing improvements  ...  This research made use of the resources of the KAUST Supercomputing Laboratory.  ... 
arXiv:1708.02835v3 fatcat:uzh6ygjcgjc4xdctdukuet532i

ExaGeoStat: A High Performance Unified Software for Geostatistics on Manycore Systems

Sameh Abdulah, Hatem Ltaief, Ying Sun, Marc G. Genton, David Keyes
2018 IEEE Transactions on Parallel and Distributed Systems  
Using state-of-the-art high performance dense linear algebra libraries associated with various leading edge parallel architectures (Intel KNLs, NVIDIA GPUs, and distributed-memory systems), ExaGeoStat  ...  The software takes a first step in the merger of large-scale data analytics and extreme computing for geospatial statistical applications, to be followed by additional complexity reducing improvements  ...  parallel architectures, e.g., Intel Xeon, Intel manycore Xeon Phi Knights Landing chip (KNL), NVIDIA GPU accelerators, and distributed-memory homogeneous systems.  ... 
doi:10.1109/tpds.2018.2850749 fatcat:6ycaixc2l5gp7pf3g4jfge2ije

High Performance Multivariate Geospatial Statistics on Manycore Systems

Mary Salvana, Sameh Abdulah, Huang Huang, Hatem Ltaief, Ying Sun, Marc M. Genton, David Keyes
2021 IEEE Transactions on Parallel and Distributed Systems  
match the growth in environmental data coming from the widespread use of different data collection technologies.  ...  Modeling and inferring spatial relationships and predicting missing values of environmental data are some of the main tasks of geospatial statisticians.  ...  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.  ... 
doi:10.1109/tpds.2021.3071423 fatcat:ypss4jk7uvgc7klbjh72m33kt4

Large-scale Environmental Data Science with ExaGeoStatR [article]

Sameh Abdulah, Yuxiao Li, Jian Cao, Hatem Ltaief, David E. Keyes, Marc G. Genton, Ying Sun
2022 arXiv   pre-print
In this paper, we advocate the use of ExaGeoStatR, a package for exascale Geostatistics in R that supports a parallel computation of the exact maximum likelihood function on a wide variety of parallel  ...  Here, we demonstrate ExaGeoStatR by illustrating its implementation details, analyzing its performance on various parallel architectures, and assessing its accuracy using synthetic datasets with up to  ...  Here, ncores and ngpus are the numbers of CPU cores and GPU accelerators to deploy, ts denotes the tile size used for parallelized matrix operations, pgrid and qgrid are the cluster topology parameters  ... 
arXiv:1908.06936v2 fatcat:ysqhmmzulfgezm7gghwhdluhli

Accelerating a Geometrical Approximated PCA Algorithm Using AVX2 and CUDA

Alina L. Machidon, Octavian M. Machidon, Cătălin B. Ciobanu, Petre L. Ogrutan
2020 Remote Sensing  
benefits in implementing it on the multi-core CPU using AVX2 intrinsics.  ...  Device Architecture (CUDA).  ...  In [33] , Josth et al. presented two implementations of the PCA algorithm, first using the Streaming SIMD Extensions (SSE) instructions set of the CPU, and secondly using the CUDA technique on GPU architectures  ... 
doi:10.3390/rs12121918 fatcat:sgr42gu7qfapnkxs55sqjsqeya

Parallel Approximation of the Maximum Likelihood Estimation for the Prediction of Large-Scale Geostatistics Simulations

Sameh Abdulah, Hatem Ltaief, Ying Sun, Marc G. Genton, David E. Keyes
2018 2018 IEEE International Conference on Cluster Computing (CLUSTER)  
Performance results of TLR-based computations on shared and distributed-memory systems attain up to 13X and 5X speedups, respectively, compared to full accuracy simulations using synthetic and real datasets  ...  In this paper, we extend the Exascale GeoStatistics software framework (i.e., ExaGeoStat 1 ) to support the Tile Low-Rank (TLR) approximation technique, which exploits the data sparsity of the dense covariance  ...  This research made use of the resources of the KAUST Supercomputing Laboratory.  ... 
doi:10.1109/cluster.2018.00089 dblp:conf/cluster/AbdulahL0GK18 fatcat:lsjryhqezvgt5dxhchxlsp5t4q

Modeling and Multiple Perceptions [chapter]

Christine Parent, Stefano Spaccapietra, Esteban Zimányi
2017 Encyclopedia of GIS  
Cross-References Computer Environments for GIS and CAD Movement Patterns in Spatio-Temporal Data Cross-References Geospatial Semantic Web, Interoperability Metadata and Interoperability, Geospatial  ...  Modeling with Pictogrammic Languages OGC's Open Standards for Geospatial Interoperability Vector Data Cross-References Indexing, Query and Velocity-Constrained Privacy Threats in Location-Based Services  ...  Some approaches employ the k-means algorithm to cluster the input point set, using distance measures (e.g., Euclidean distance) and possibly also vehicle direction, as a condition to introduce seeds at  ... 
doi:10.1007/978-3-319-17885-1_805 fatcat:d4t4ossygvcutpfabqn6f3hjcm

Optimization of hybrid parallel application execution in heterogeneous high performance computing systems considering execution time and power consumption [article]

Paweł Rościszewski
2018 arXiv   pre-print
Utilizing full power of such systems requires programming parallel applications that are hybrid in two meanings: they can utilize parallelism on multiple levels at the same time and combine together programming  ...  Both meanings of the application hybridity result in multiplicity of execution parameters of nontrivial interdependences and influence on the considered optimization criteria.  ...  while loops, executed on single-node heterogeneous manycore architectures using StarPU [80] for execution on CPUs and GPUs.  ... 
arXiv:1809.07611v1 fatcat:f2vl3kmgznckroj6h3uwt2zwf4

Big data and extreme-scale computing

M Asch, T Moore, R Badia, M Beck, P Beckman, T Bidot, F Bodin, F Cappello, A Choudhary, B de Supinski, E Deelman, J Dongarra (+27 others)
2018 The international journal of high performance computing applications  
methods for analyzing and using that data are radically reshaping the landscape of scientific computing.  ...  Based on those meetings, we argue that the rapid proliferation of digital data generators, the unprecedented growth in the volume and diversity of the data they generate, and the intense evolution of the  ...  They would also gratefully acknowledge all the following sponsors who supported the big data and exascale computing workshop series: Government Sponsors: US Department of Energy, the National Science Foundation  ... 
doi:10.1177/1094342018778123 fatcat:vwrrxmad4rhtppq6ioaz4h5q7a

GPU Data Structures and Code Generation for Modeling, Simulation, and Visualization

Johannes Sebastian Mueller-Roemer
2020
However, specialized algorithms and data structures are required to make efficient use of the processing power of GPUs.  ...  Modern GPUs are fully programmable massively parallel manycore processors that are characterized by their high energy efficiency and good price-performance ratio.  ...  Therefore, using either would mean using two different versions of LLVM for CPU and GPU code, or not having the full range of CPU optimizations, such as vectorization in the presence of potential aliasing  ... 
doi:10.25534/tuprints-00011291 fatcat:ng3ikjwvkbdgbm2ugqyvnfzl4y

ENVIROPORTS: Análisis y predicción de series temporales de parámetros ambientales y su interrelación con tráfico marítimo en entornos portuarios

Mª Ángeles García, Paula Gómez, Ivan Felis, Eduardo Madrid, Rosa Martínez
2021 Zenodo  
These include increasing core counts but stagnant clock frequencies; the high cost of data movement; use of accelerators (GPUs, FPGAs, coprocessors), making architectures increasingly heterogeneous; and  ...  of geospatial data, but current approaches may not be optimal when system behaviour is dominated by spatial or temporal context.  ... 
doi:10.5281/zenodo.5776422 fatcat:pesxgujowfftrdfegvik26n2vi

Exploiting Data Sparsity In Covariance Matrix Computations on Heterogeneous Systems

Ali Charara
2018
Covariance matrices are ubiquitous in computational sciences, typically describing the correlation of elements of large multivariate spatial data sets.  ...  However, dealing with large data sets (i.e., covariance matrices of billions in size) can rapidly become prohibitive in memory footprint and algorithmic complexity.  ...  on various CPU architectures.  ... 
doi:10.25781/kaust-5m8z4 fatcat:ldejra7mqzdvtfxzwjtnvgft6i

Report of the 2014 NSF CyberBridges Workshop on Developing the Next Generation of Cyberinfrastructure Faculty for Computational and Data-enabled Science and Engineering

Figshare Admin Nsf
2018
Five keynote presentations were given by nationally- and internationally-recognized leaders in fields relevant to the use and development of cyberinfrastructure in science and engineering research.  ...  Sixteen of the attendees from the 2012 workshop returned for this year's workshop.  ...  Acknowledgements Our efforts in planning and conducting the CyberBridges workshop and the development of this report were supported by Natasha Nikolaidis (  ... 
doi:10.25391/nsf.6815009.v1 fatcat:hkojirjxrrfljmwsv55j7hmn34

ICAS 2013 Committee ICAS Advisory Chairs ICAS 2013 Technical Program Committee

Lisbon, Michael Bauer, Michael Grottke, Bruno Dillenseger, Michael Bauer, Michael Grottke, Bruno Dillenseger, Jemal Abawajy, Javier Alonso, Richard Anthony, Tsz-Chiu Au, Mark Balas (+72 others)
unpublished
Commonly, there is a set of general user interface guidelines; the challenge is due to a need for cross-team expertise.  ...  Small-scale and large-scale virtualization and model-driven architecture, as well as management challenges in such architectures are considered.  ...  Using D as the set of clusterheads, a partition of G into clusters, each of radius k, follows.  ... 
fatcat:ke3eyz375zejhezaowd63bksqu