@Article{Dhillon,
title = {A Data-Clustering Algorithm on Distributed Memory Multiprocessors},
author = {Inderjit S. Dhillon and Dharmendra S. Modha},
journal = {Large-scale Parallel KDD Systems Workshop, ACM SIGKDD},
year = {1999},
month = {August},
note* = {document "fondateur" du KMeans distribué via MPI}
}

@Article{MapReduceForMachineLearning,
title = {MapReduce For Machine Learning on Multicore},
author = {Cheng-Tao Chu, Sang Kyun Kim, Yi-An Lin, YuanYuan Yu, Gary Bradski, Andrew Y. Ng, Kunle Olukotun},
journal = {-},
year = {1996},
month = {-},
note* = {document intéressant pour se donner une idée des perfs de scaling sur du 64 processeurs}
}

@Article{KMeansOnNOWs,
title = {Parallel K-Means Clustering Algorithm on NOWs},
author = {Sanpawat Kantabutra and Alva L. Couch},
journal = {NecTec Technical Journal},
year = {2000},
month = {January},
note* = {Only article I read where parallelisation is 1 worker per cluster instead of 1 worker for N/P points}
}

@Article{Pollard,
title = {Strong consistency of K-Means clustering},
author = {David Pollard},
journal = {The Annals of Statistics},
year = {1981},
month = {January},
note* = {Historical article on the consistency of Online K-Means algorithm}
}

@Article{BiauKMeans,
title = {On the performance of clustering in Hilbert spaces},
author = {Gérard Biau, Luc Devroye, Gábor Lugosi},
journal = {?},
year = {-},
month = {-},
note* = {K-Means theoretical performances}
}

@Article{KMeansIsNPhard,
title = {The Planar k-means Problem is NP-hard},
author = {Meena Mahajan, Prajakta Nimbhorkar, Kasturi Varadarajan},
journal = {?},
year = {-},
month = {-},
note* = {2D K-Means is NP-Hard}
}

@Article{KMeansJoshi,
title = {Parallel K-means Algorithm on Distributed Memory Multiprocessors},
author = {Manasi N.Joshi},
journal = {?},
year = {2003},
month = {spring},
note* = {un papier sur un K-Means distribué}
}

@Article{ParaKMeans,
title = {ParaKMeans : implementation of a parallelised K-Means algorithm suitable for laboratory use},
author = {Piotr Kraj, Ashok Sharma, Nikhil Garge, Robert Podolsky, Richard A McIndoe},
journal = {BMC BioInformatics},
year = {2008},
month = {april},
note* = {ParaKMeans en C#}
}

@Article{KMeansParallelInC,
title = {Parallel K-Means Data Clustering},
author = {Liao W},
journal = {},
year = {2005},
month = {},
note* = {Code en C}
}

@MISC{HPS_1,
    author = {On Ibm Sp (draft and Gang Cheng and Marek Podgorny},
    title = {The High Performance Switch and Programming Interfaces on IBM SP2},
    year = {1995}
}

@Article{HPS_2,
    author = {Vasilios Georgitsis, John Sobolewski},
    title = {Performance of MPL and MPICH on the SP2 System},
}

@misc{SortBenchmark,
title = {Sort Benchmark Home Page},
author = {},
note = {\url{http://sortbenchmark.org/}},
}

@misc{TeraSortWinnerYahoo,
title = {TeraByte Sort on Apache Hadoop},
author = {Owen O Malley},
note = {\url{http://www.hpl.hp.com/hosted/sortbenchmark/YahooHadoop.pdf}}
}

@misc{AzureStorageResources,
title = {Azure Storage Resources},
author = {},
note = {\url{http://blogs.msdn.com/b/windowsazurestorage/archive/2010/03/28/windows-azure-storage-resources.aspx}}
}

@misc{AzureScope,
title = {Azure Scope},
author = {},
note = {\url{http://azurescope.cloudapp.net/}}
}

@techreport{Commodity_Grid_With_Amazon,
title = {Commodity grid computing with Amazon S3 and EC2},
author = {Simson Garfinkel},
institution = {Harvard University}
}

@techreport{The_Impact_Of_Virtualization,
title = {The Impact of Virtualization on Network Performance of Amazon EC2 Data Center},
author = {Guohui Wang, T. S. Eugene Ng},
institution = {Dept. of Computer Science, Rice University},
note* = {technical paper about benchmarking UDP and TCP layers performance in communication, and evaluating of Virtualization is impacting theses layers.}
}

@INPROCEEDINGS{Lin09bruteforce,
    author = {Jimmy Lin},
    title = {Brute force and indexed approaches to pairwise document similarity comparisons with mapreduce},
    booktitle = {In Proceedings of the 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2009},
    year = {2009},
    pages = {155--162},
    note* = { Bio-Statistics research article, on queries run on a 240 machines cluster using Hadoop}
}

@TECHREPORT{Saini96nasparallel,
    author = {Subhash Saini and David H. Bailey and Sgi Origin},
    title = {NAS Parallel Benchmark (Version 1.0) Results 11-96},
    institution = {},
    year = {1996}
}

@Article {BridgingtheGap,
title = {Bridging the Gap between the Cloud and an eScience Application Platform},
author = {Yogesh Simmhan, Catharine van Ingen, Girish Subramanian, Jie Li},
note* = {Investigates different issues of porting an app into the cloud. Mostly Azure oriented.}
}

@Article {Eucalyptus,
title = {The Eucalyptus Open-source Cloud-computing System},
author = {Daniel Nurmi, Rich Wolski, Chris Grzegorczyk
Graziano Obertelli, Sunil Soman, Lamia Youseff, Dmitrii Zagorodnov},
note* = {The Eucalyptus Open-Source Cloud-Computing System is an opensource
software framework for cloud computing that implements Infrastructure as a Service (IaaS). Describes the basic
principles of the EUCALYPTUS design, and discuss architectural
trade-offs they made},
}

@Article = {StragglerIssuesInMapReduce,
title = {The Curse of Zipf and Limits to Parallelization: A Look at the Stragglers Problem in MapReduce},
author = {Jimmy Lin},
note* = {Discussion on the straggler issue, good description of why is there an issue, etc... Very naive solution but the interest is explaining rather than proposing a solution}
}

@techreport = {BenchmarkingAmazonEC2,
title = {Benchmarking Amazon EC2 for high-performance scientific computing},
author = {Edward Walker},
note* = {EC2 agains a HPC cluster : Abe. Performance in term of runtime, bandwidth, latency etc...}
}

@Article = {Early_Observations_On_Azure,
title = {Early Observations on the Performance of Windows Azure},
author = {Zach Hill, Jie Li, Ming Mao, Arkaitz Ruiz-Alvarez, and Marty Humphrey},
note* = {benchmark on Azure performances. Good graphics about bandwidth limitations, good explanations of VM boot latencies, etc...}
}

@misc = {Azure_Pricing,
title = {Azure Pricing},
author = {},
note = {\url{http://www.microsoft.com/windowsazure/pricing/}}
}

@misc = {Azure SLA,
title = {Azure Service Level Agreement},
note = {\url{http://www.microsoft.com/windowsazure/sla/}}
}

@Article{CAP_Theorem,
 author = {Gilbert, Seth and Lynch, Nancy},
 title = {Brewer's conjecture and the feasibility of consistent, available, partition-tolerant web services},
 journal = {SIGACT News},
 volume = {33},
 number = {2},
 year = {2002},
 issn = {0163-5700},
 pages = {51--59},
 doi = {http://doi.acm.org/10.1145/564585.564601},
 publisher = {ACM},
 address = {New York, NY, USA},
 note*={Demonstration of the CAP Theorem}
 }

@Article {BenchmarkingCloudServices,
title = {Benchmarking Cloud Serving Systems with YCSB},
author = {Brian F. Cooper, Adam Silberstein, Erwin Tam, Raghu Ramakrishnan, Russell Sears},
note*={excellent description of different tradeoffs in storage design}
}

@misc={CLAP_Presentation,
author = {Daniel Abadi},
title = {Problems with CAP, and Yahoo's little known NoSQL System },
journal = {http://dbmsmusings.blogspot.com/2010/04/problems-with-cap-and-yahoos-little.html},
note* = {excellent analyse of what's missing in CAP theorem},
}

@Article = {BASE,
title = {BASE : an ACID alternative},
author = {Dan Pritchett}
}

@misc = {NoSQL,
title = {http://nosql-database.org/},
note = {\url{http://nosql-database.org/ censored NoSQL databases}}
}

@Article = {Eventually_Consistent,
title = {Eventually Consistent},
author = {Werner Wogels}
}

@misc = {Slaying_Relational_Dragons,
title = {Slaying Relational Dragons},
author = {Ayende},
journal = {http://ayende.com/Blog/archive/2010/02/22/slaying-relational-dragons.aspx}
}

@Misc = {AzureQueuesConnotBeLarger,
title = {Azure queues cannot be larger than 8192 bytes},
author = {Rinat Abdullin}
}

@Article = {AboveTheCloud,
title = {Above the Clouds: A Berkeley View of Cloud Computing},
author = {Michael Armbrust, Armando Fox, Rean Griffith, Anthony D. Joseph, Randy Katz,
Andy Konwinski, Gunho Lee, David Patterson, Ariel Rabkin, Ion Stoica, and Matei Zaharia}
}

@Article = {HighPerformanceComputingWithClouds,
title = {High Performance Computing with Clouds},
author = {Raihan Masud}
}

@inproceedings{TOP500,
 author = {Napper, Jeffrey and Bientinesi, Paolo},
 title = {Can cloud computing reach the top500?},
 booktitle = {UCHPC-MAW \'09: Proceedings of the combined workshops on UnConventional high performance computing workshop plus memory access workshop},
 year = {2009},
 isbn = {978-1-60558-557-4},
 pages = {17--20},
 location = {Ischia, Italy},
 doi = {http://doi.acm.org/10.1145/1531666.1531671},
 publisher = {ACM},
 address = {New York, NY, USA},
 }


@Inproceedings{lenk2009witcaamotcl,
  author = {Alexander Lenk and Markus Klems and Jens Nimis and Stefan Tai and Thomas Sandholm},
  booktitle = {ICSE Workshop on Software Engineering Challenges of Cloud Computing, 2009. CLOUD 09.},
  month = {Mai},
  publisher = {IEEE Press},
  title = {What's inside the Cloud? An Architectural Map of the Cloud Landscape},
  year = {2009},
}