23,100 Hits in 5.1 sec

Performance Portability for ECP Data Analytics (SIAM CSE21) [article]

William Hart
A talk presented at the SIAM CSE21 conference, MS162/192: Exascale Computing Project Performance Portability Analysis  ...  in CUDA, and HIP translations appear satisfactory -The team is considering the use of Kokkos for performance portability • Performance bottlenecks -Resource orchestration is a key challenge for  ...  DAO applications represent new challenges for HPC systems • Large-scale data-driven computations • Kernels for sparse, irregular computations, etc.  ... 
doi:10.6084/m9.figshare.14153816.v1 fatcat:273nr7j26zazld4xz5furwnpiq

Sesame: A User-Transparent Optimizing Framework for Many-Core Processors

Jianbin Fang, A. L. Varbanescu, H. Sips
2013 2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing  
As an answer, I propose an optimizing framework for parallel applications running on many-core processors (Sesame).  ...  With the integration of more computational cores and deeper memory hierarchies on modern processors, the performance gap between naively parallelized code and optimized code becomes much larger than ever  ...  In the thesis, I propose a generic optimizing framework for many-core processors (Sesame), ensuring high productivity by letting naive code stay portable and high performance by performing code specializations  ... 
doi:10.1109/ccgrid.2013.79 dblp:conf/ccgrid/FangVS13 fatcat:dds6wlwv3jhsni7sps3wcfhhsy

MapReduce: Simplified Data Analysis of Big Data

Seema Maitrey, C.K. Jha
2015 Procedia Computer Science  
But there was a tremendous increase in the amount of data, their computation and analyses in recent years.  ...  With the development of computer technology, there is a tremendous increase in the growth of data.  ...  The portability in Hadoop support users by making the development simper and reduce installation complexity. This results in the widespread of this parallel computing paradigm.  ... 
doi:10.1016/j.procs.2015.07.392 fatcat:whtpro3grzbpphvfzbptlun744


Michael Gerndt, Barton P. Miller
2016 Concurrency and Computation  
CPPC (ComPiler for Portable Checkpointing) is a checkpointing tool designed to feature both portability and transparency. It is made up of a library and a compiler.  ...  With the evolution of high-performance computing towards heterogeneous, massively parallel systems, parallel applications have developed new checkpoint and restart necessities.  ...  CONCLUDING REMARKS CPPC is a portable and transparent checkpointing infrastructure for parallel applications.  ... 
doi:10.1002/cpe.v22:6 fatcat:mdtctljdjrfljjxnpanwz54s5e


2014 American Journal of Applied Sciences  
Rapid growth in the field of "cloud computing" also increases severe security concerns, because security has a constant issue. This study reviews security models of cloud computing.  ...  These requirements are very common in an organization while dealing with current technological data and requirements.  ...  Zhang and Zhang (2009) analyzed the security issues in the cloud computing, briefed about the Open Cloud Computing Federation (OCCF).  ... 
doi:10.3844/ajassp.2014.1224.1228 fatcat:a735kermjrbspd4hupkx3zpebu

Special Issue: Current Trends in Compilers for Parallel Computers

Juan Touriño, Basilio B. Fraguela, Ramón Doallo, Manuel Arenaz
2007 Concurrency and Computation  
The first representative of this research line in this issue is the paper by Kessler et al., who identify and analyze the different classes of schedules for VLIW processors.  ...  The first paper in this special issue, authored by Liao et al., presents OpenUH, a portable OpenMP compiler built on top of the Open64 open source infrastructure that is paired with the portable Tsinghua  ... 
doi:10.1002/cpe.1172 fatcat:yf6odxbk5rfjhflnm2siiq4wpu


Muhammad Usman Ashraf
2019 International Journal of Advanced Research in Computer Science  
The next breakthrough in the computing revolution is the Exascale level of performance that is 10 18 calculations per second-a remarkable achievement in computing that will have a fathomless influence  ...  Leading to objectives, the current study presents a comprehensive analysis of existing strategies that can be considered to enhance performance and reducing power for emerging Exascale computing system  ...  The hybrid of MPI + OpenACC programming model was proposed to resolve the portability and scalability issues for heterogeneous frameworks.  ... 
doi:10.26483/ijarcs.v10i2.6397 fatcat:k3l3lk5kuzhnldn5b2qzkh4eia

An Overview of Portable Distributed Techniques [article]

Sanjay Bansal, Nirved Pandey
2011 arXiv   pre-print
In this paper, we reviewed of several portable parallel programming paradigms for use in a distributed programming environment. The Techniques reviewed here are portable.  ...  We have identified the various factors and issues for improving these four important characteristics.  ...  It supports certain forms of error detection and recovery. The PVM (Parallel Virtual Machine) provides a unified framework .Large systems can be developed in a straightforward and efficient manner.  ... 
arXiv:1101.2573v1 fatcat:6uxydjnykraalbfemjzxq4asgy

Distributed and Parallel Big Textual Data Parsing for Social Sensor Network

Jung-Ho Um, Chang-Hoo Jeong, Sung-Pil Choi, Seungwoo Lee, Hwan-Min Kim, Hanmin Jung
2013 International Journal of Distributed Sensor Networks  
As a result, we prove that the proposed system is useful for parsing text data in social sensor network.  ...  Also, to reduce communication overheads, the statistical model used by the parser is resided on local cache in each mapper.  ...  Acknowledgments This work utilized scientific and technical contents constructed through "Establishment of the Sharing System for Electronic Information with Core Science and Technology" Project (K-13-  ... 
doi:10.1155/2013/525687 fatcat:b7kor6awcje3lo6kcloyq42rfi

Navigation System Volume Simulation based on DPSSF

Chao Wang, Xiaoshuang Wang, Qun Li, Weiping Wang
2011 Procedia Engineering  
To resolve the model integration problem in Navigation System Volume Simulation (SVS), A distributed & parallelized simulation framework based on Simulation Model Portability (SMP2) and Service-Oriented  ...  The SVS and its main criterions are introduced and then a simulation SVS model framework is propounded. The distributed & parallelized SMP2 simulation framework based on SOA (DPSSF) is detailed.  ...  in view for each node on a latitude and longitude grid over the simulation time period.  ... 
doi:10.1016/j.proeng.2011.08.1079 fatcat:t2tkc2q3bfdvvb7csyxhawloky

A unified wireless sensor network framework

Joshua Kiepert, Sin Ming Loo
2012 2012 IEEE International Systems Conference SysCon 2012  
This paper outlines the traditional approaches to WSN system design, and in contrast, proposes the necessary components of a unified WSN framework that would support the majority of present applications  ...  as well as providing the foundation for further advancements in the field.  ...  However, other issues need to be considered. In the following sections we will briefly analyze each data management system and identify issues involved with each methodology. A.  ... 
doi:10.1109/syscon.2012.6189450 fatcat:gbj4g7cwqvdaljhugs7mbnog4i

An auto-tuning framework for parallel multicore stencil computations

Shoaib Kamil, Cy Chan, Leonid Oliker, John Shalf, Samuel Williams
2010 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)  
parallel implementations in Fortran, C, or CUDA, thus allowing performance portability across diverse computer architectures, including the AMD Barcelona, Intel Nehalem, Sun Victoria Falls, and the latest  ...  of stencil kernels used in practice makes this computation pattern difficult to assemble into a library.  ...  Acknowledgments We would like to express our gratitude to Sun and NVIDIA for their hardware donations.  ... 
doi:10.1109/ipdps.2010.5470421 dblp:conf/ipps/KamilCOSW10 fatcat:endkmhvhjjfuvmnpmuxp7elpm4

SWARM: A Parallel Programming Framework for Multicore Processors

David A. Bader, Varun Kanade, Kamesh Madduri
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
In this paper, we identify key issues in algorithm design for multicore processors and propose a computational model for these systems.  ...  We introduce SWARM (SoftWare and Algorithms for Running on Multi-core), a portable open-source parallel library of basic primitives that fully exploit multicore processors.  ...  SWARM: Programming Framework for Multicore Systems SWARM [3] is a portable open-source portable library that provides a programming framework for designing algorithms on multicore systems.  ... 
doi:10.1109/ipdps.2007.370681 dblp:conf/ipps/BaderKM07 fatcat:oqtbqmbzuzbrfihus5b4e47qgu

An Analysis of Computation Offloading Mechanisms for Computationally Intensive Mobile Applications

C Anuradha
Computational offloading is a ground-breaking system utilized in versatile distributed computing for improving reaction time and battery productivity of the cell phones which are considered as two basic  ...  the makers and working framework merchants in the most recent decade.  ...  It utilizes a static analyzer for recognizing the lawful parcels of the application.  ... 
doi:10.26782/jmcms.spl.2019.08.00005 fatcat:4266nkzmkbdafmq2gwf5yy3day

Generalizing mapreduce as a unified cloud and HPC runtime

Judy Qiu
2011 Proceedings of the 2nd international workshop on Petascal data analytics: challenges and opportunities - PDAC '11  
Further, one must meet these challenges for both computation and storage.  ...  This requires attractive powerful programming models that address issues of portability with scaling performance and fault tolerance.  ...  Data locality can be implicitly integrated into the runtime platform as the same set of nodes are used for both computation and storage, which instantiates the paradigm of "moving the computation to data  ... 
doi:10.1145/2110205.2110213 fatcat:y7v2q76bprhqreh4f32waz4o5y
« Previous Showing results 1 — 15 out of 23,100 results