Appendix: Facts about the GULSS Consortium
The GULSS Consortium will be set up jointly by:
- CNIC Chinese Academy of Sciences Beijing
- Huazhong University of Science and Technology, Wuhan,
- INRIA Lyon and INRIA Rennes,
- Université Sorbonne Paris Cité
In the research of high performance computing and data management in China, the CAS-CNIC Beijing has established a very good relationship with USPC and INRIA Lyon in France. The cooperation started in 2010 with visits in China by french delegates and under the supervision of the French consulate in Wuhan. Since then, many colleagues from Beijing, Hangzhou and Wuhan came in France as Professor fellowship invitations. French colleagues from INRIA Lyon and USPC spent 1-2 months in Beijing in 2015. The level of common publications is still good (see the references). Haiwu He (CAS) and Gilles Fedak (INRIA) have worked together in France for more than 6 years. The French partners also have strong links as they together participate to several projects in particular the ANR MapReduce project.
Shadi Ibrahim obtained his Ph.D from Huazhong University of Science and Technology of China, where he was supervised by Prof. Hai Jin. The title of Shadi's Ph.D thesis was "Performance-Aware Scheduling for Data-Intensive Cloud Computing”. After Shadi moved to Inria in November 2011, Prof. Jin and Shadi have continued working together on different ideas for improving the performance of Big Data application through reducing the impacts of disk interference which is introduced by virtualization technology.
The collaboration has generated fruitful results: more than 18 published joint papers (CCPE2015, TPDS 2014, FGCS 2013, PPNA 2013, Mascots 2013, CCGrid 2012, ICPP 2011, SCC 2011, CloudCom 2010, MapReduce 2010, CloudCom 2009 and HPDC 2009).
Academic visits in the 5 past years:
- Haiwu He: invited professor at INRIA (Lyon) by Gilles Fedak (2 months) in 11/2016
- Hai Jin (3 weeks in 2012) and Xuanhua Shi (3 weeks in 2015) from Wuhan were invited professors at Paris 13
- Gilles Fedak and Christophe Cerin: CAS Distinguished visiting Professor Fellowship Initiative (PIFI program) with CNIC, Beijing; (1 month + 2 months);
- Haiwu He: invited professor at INRIA (Lyon) by Gilles Fedak in 07/2015
- Christophe CERIN and Haiwu HE visited Congfeng Jiang (Hangzhou Dianzi University) in May, 2015
- Christophe CERIN and Haiwu He visited Huazhong University of Science and Technology in May, 2015
- Gilles Fedak visited CNIC / CAS in Beijing in September 2014.
- Lu Lu, PhD student from HUST, advised by Xuanhua Shi did a 6 months internship with G. Fedak in Lyon
- Shadi Ibrahim visited Huazhong University of Science and Technology in September, 2012
- Gilles Fedak, Haiwu He and Christophe Cérin visited Huazhong university of Science and Technology in 2010
Publications Co-authored in the past 5 years
- Anthony Simonet, Julio Anjos, Gilles Fedak, Haiwu He, Bing Tang, Lu Lu, Hai Jin, Xuanhua Shi, Mircea Moca, Gheorghe Silaghi, Asma Ben Cheich and Heithem Abbes. D3-MapReduce: Towards MapReduce for Distributed and Dynamic Data Sets, DataCom 2015, Chengdu, China
- Congfeng Jiang, Jian Wan, Christophe Cérin, Paolo Gianessi, Yanik Ngoko:Towards Energy Efficient Allocation for Applications in Volunteer Cloud. IPDPS Workshops 2014: 1516-1525
- Bing Tang, Haiwu He, Gilles Fedak, Parallel Data Processing in Dynamic Hybrid Computing Environment Using MapReduce, 14th International Conference, ICA3PP 2014, Dalian, China, August 24-27, 2014: 2014
- Gilles Fedak, Haiwu He and Franck Cappello, BitDew: A Data Management and Distribution Service with Multi-Protocol File Transfer and MetaData Abstraction, Journal of Network and Computer Applications: 2009 ,32(5),961--975
- Bing Tang, Mircea Moca, Stephane Chevalier, Haiwu He, Gilles Fedak.,Towards MapReduce for Desktop Grid Computing, In Fifth International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC): November 2010
- Lu Lu, Hai Jin, Xuanhua Shi, Gilles Fedak, "Assessing MapReduce for Internet Computing: A Comparison of Hadoop and BitDew-MapReduce", ACM/IEEE International Conference on Grid Computing(Grid 12), 2012
- Shadi Ibrahim, Hai Jin, Lu Lu, Bingsheng He, Gabriel Antoniu, Song Wu, “Handling Partitioning Skew in MapReduce using LEEN”, in Peer-to-Peer Networking and Applications Journal (PPNA), May. 2013.
- Xiao Ling, Shadi Ibrahim, Hai Jin, Song Wu, “Spatial Locality Aware Disk Scheduling in Virtualized Environment”, In the IEEE Transactions on Parallel and Distributed Systems (TPDS), 2015.
- Xiao Ling, Hai Jin, Shadi Ibrahim, Wenzhi Cao, Song Wu, Gabriel Antoniu, “Flubber: Two-level Disk Scheduling in Virtualized Environment”, in the Future Generation Computer Systems (FGCS) Journal, October 2013.
- Xiao Ling, Shadi Ibrahim, Hai Jin, Song Wu, Songqiao Tao “Exploiting Disk Spatial Locality in Virtualized Environments”, in Proceedings of the IEEE 21st International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems Mascots 2013, August 14-16, 2013 in San Francisco, CA.
- Shadi Ibrahim, Hai Jin, Lu Lu, Bingsheng He, Gabriel Antoniu, Song Wu, “Maestro: Replica-Aware Map Scheduling for MapReduce ”, in Proceedings of The 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing CCGrid 2012, May 13-16, 2012, Ottawa, Canada.
- Xiao Ling, Hai Jin, Shadi Ibrahim, Wenzhi Cao, Song Wu, “Efficient Disk I/O Scheduling with QoS guarantees for Xen-based Platforms”, in Proceedings of The 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing CCGrid 2012, May 13-16, 2012, Ottawa, Canada.
- Hai Jin, Shadi Ibrahim, Li Qi, Haijun Cao, Song Wu, Xuanhua Shi, “The MapReduce Programming Model and Implementations”, Book Chapter in Cloud Computing: Principles and Paradigms, Wiley Press, Mar. 2011.
- Shadi Ibrahim, Hai Jin, Lu Lu, Bingsheng He, Song Wu, “Adaptive Disk I/O Scheduling for MapReduce in Virtualized Environment”, in Proceedings of 40th annual International Conference on Parallel Processing ICPP 2011, Sep 13-16, Taiwan.
- Shadi Ibrahim, Bingsheng He, Hai Jin, “Towards Pay-As-You-Consume Cloud Computing”. in Proceedings of IEEE 8th International Conference on Services Computing SCC 2011, July 4-9, Washington, USA.
- Shadi Ibrahim, Hai Jin, Lu Lu, Bingsheng He,Li Qi, Song Wu, “LEEN: Locality/Fairness- aware Key Partitioning for MapReduce in the Cloud”, in the 2nd IEEE International Conference on Cloud Computing Technology and Science CloudCom 2010, Indiana, USA, Dec 2010.
- Dachuan Huang, Xuanhua Shi, Shadi Ibrahim, Lu Lu, Song Wu, Hai Jin, “MR-Scope: A Real Time Tracing Tool for MapReduce”,in The First International Workshop on MapReduce and its Applications MAPREDUCE’10 in conjunction with ACM HPDC 2010, Chicago, IL, USA, Jun 2010.
- Shadi Ibrahim, Hai Jin, Lu Lu, Li Qi, Song Wu, Xuanhua Shi, “Evaluating MapReduce on Virtual Machines : The Hadoop Case”, in 1st International conference on Cloud Computing CloudCom 2009, Beijing, China, Dec 2009.
- Shadi Ibrahim, Hai Jin, Cheng bin, HaiJun Cao, Song Wu, Li Qi, “CLOUDLET: Towards MapReduce Implementation on Virtual Machine”, Poster Session ,in 18th International Symposium on High Performance Distributed Computing HPDC 2009, Munich, Germany, June 2009.
- Christophe Cerin, Leila Abidi, Gilles Fedak and Haiwu He. Towards an Environment for doing Data Science that runs in Browsers, DataCom 2015, Chengdu, China
Detailed description of the partners:
INRIA, the French national institute for research in computer science and control, operating under the dual authority of the Ministry of Research and the Ministry of Industry, is dedicated to fundamental and applied research in information and communication science and technology (ICST). The Institute also plays a major role in technology transfer by fostering training through research, diffusion of scientific and technical information, development, as well as providing expert advice and participating in international programs. By playing a leading role in the scientific community in the field and being in close contact with industry, INRIA is a major participant in the development of ICST in France. Throughout its headquarter and its eight research centers in Rocquencourt, Rennes, Sophia Antipolis, Grenoble, Nancy, Bordeaux, Lille and Saclay, INRIA has a workforce of 4 100, 3 150 of whom are scientists from INRIA and INRIA's partner organizations such as CNRS universities and leading engineering schools. They work in 168 joint research project-teams.
INRIA defined and implemented an ambitious policy on IT and communications equipment to the best international standards, with very high performance networks, computing and visualization resources, grids and now clouds allowing for far-reaching experiments to be run and technological developments implemented. The Institute now has also highly developed skills at its disposal as well as a high-level international visibility in the field of networks, computing grids and clouds. The Institute has set ambitious scientific goals for this field. Grids and clouds spread over several scientific priorities of the Strategic Plan for 2008-2012 (Modeling, Programming, Communicating, Interacting, Computational Engineering, Computational Sciences, Computational Medicine).
INRIA/AVALON, Lyon, France
Avalon (http://avalon.ens-lyon.fr), one of the LIP research teams located at ENS-Lyon. The long term goal of the Avalon team is to contribute to the design of programming models supporting a lot of architecture kinds, to implement them by mastering the various algorithmic issues involved, and to study the impact on application-level algorithms. To achieve such a goal, the team plans to contribute at different level including distributed algorithms, programming models, deployment of services, services discovery, service composition and orchestration, large scale data management, Cloud computing, etc. All the theoretical results are validated on software prototypes using applications from different fields of science such as bioinformatics, physics, cosmology, etc. The French experimental platform Grid'5000 is the platform of choice for experiments. Members of Avalon are leading the national projects for operating the platform and for conducting research on it (INRIA project Héméra, C. Perez). Avalon team was involved in the Nu@ge project aimed at building a federation of container-sized datacenter on the French territory . The Avalon team has solid collaborations with industrial companies (EDF, BULL, Alcatel-Lucent, etc.). Members of Avalon are involved in teaching activities at ENS Lyon and University Lyon I, in particular at Master level. Moreover, they contribute and organize to international level events (conferences, forum, tutorials, etc.). AERES rates the Avalon team (as part of the Graal project) with A, with A+ for its scientific quality and its production and A for all others items.
Gilles Fedak (co-Principal Investigator) has been a permanent Inria research scientist since 2004. After graduating from University Paris Sud in 2003, he has followed a postdoctoral fellowship at the University of California San Diego in 2003-2004. He received his Habilitation degree from ENS-Lyon in 2015. His research topics include designing and implementing an open-source Desktop Grid system called XtremWeb, an open-source platform for data-intensive applications on Cloud and Desktop Grid called BitDew. He is a member of the program committee of several conferences and workshops (HPDC, CloudCom, ScalCom, EuromicroPDP, eScience, ICCCN, IANA, CCGRID and more). He is co- editor of the Cluster Computing Journal. In 2012, he co-edited with C. Cérin the Desktop Grid Computing Book, (CRC publication). He has been the Principal Investigator of ANR JCJC DSLLAB project and ANR CloudPower project. He has also lead several bilateral cooperation programs with Japan, Tunisia and China. He was involved in FP6 CoreGrid Network of Excellence and FP6 Grid4All, as well as several national ACI and ANR projects including GP2PC, SPADES, Clouds@Home and more recently ANR MapReduce. G. Fedak was the Inria representative in the FP7 EDGeS and FP7 EDGI projects. He co-authored more than 90 scientific papers and won two best-paper awards.
- Active Data: A Programming Model to Manage Data Life Cycle Across Heterogeneous Systems and Infrastructures Anthony Simonet Gilles Fedak Matei Ripeanu. Future Generation Computing Systems, Elsevier, 2015
- Multi-Criteria and Satisfaction Oriented Scheduling for Hybrid Distributed Computing Infrastructures. M.Moca, C.Litan, G.C.Silaghi, and G.Fedak. Future Generation in Computer Systems, 2015.
- HybridMR: A New Approach for Hybrid MapReduce Combining Desktop Grid and Cloud Infrastructures Bing Tang, Haiwu He and Gilles Fedak, Concurrency and Computation: Practice and Experience, 2015.
- SpeQuloS: A QoS Service for BoT Applications Using Best Effort Distributed Computing Infrastructures Simon Delamare, Gilles Fedak, Derrick Kondo, Oleg Lodygensky. in International Symposium on High Performance Distributed Computing (HPDC’2012) , Delft, Nederlands, 2012
- BitDew: A Data Management and Distribution Service with Multi-Protocol and Reliable File Transfer. G. Fedak, H. He, and F. Cappello J journal of Network and Computer Applications, 32(5):961–975, 2009.
Laurent Lefevre is a permanent researcher in computer science at Inria and member of the Avalon team. He got his “Habilitation à Diriger des Recherches” in Computer Science from the ENS de Lyon in 2013. He has co-authored more than 100 peer-reviewed papers published in journals and conference proceedings.
- M. Diouri, O. Glück, L. Lefèvre, JC. Mignot. “Providing Green Services in HPC Data Centers: A Methodology based on Energy Estimation”, Khan, Samee U. and Zomaya, Albert. Handbook on Data Centers, Springer, 2015.
- M. Bagein et al. “Energy Efficiency for Ultrascale Systems: Challenges and Trends from Nesus Project”, Supercomputing Frontiers and Innovation Journal, Special issue on Sustainable Ultrascale Computing Systems, Volume 2, Number 2, pages 105-131, September 2015.
- AC.Orgerie ,M.Assunção and L.Lefèvre “A Survey on Techniques for Improving the Energy Efficiency of Large Scale Distributed Systems”, ACM Computing Surveys, Volume 46, Issue 4, December 2014.
Marcos Dias de Assunção is a starting researcher at Inria. He obtained a Ph.D. in Computer Science and Software Engineering (2009) from The University of Melbourne, Australia. Marcos has published research papers in several conferences and journals on distributed systems, including FGCS, CCPE, HPDC, Mascots, IEEE Cloud, NOMS, and IM.
- M. Netto, C. Cardonha, R. Cunha, M. Assunção, Evaluating Auto-scaling Strategies for Cloud Computing Environments, 22nd IEEE International Symposium Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS 2014), pp. 187–196, Paris, Sep. 2014.
- M. Assunção, R.N. Calheiros, S. Bianchi, M. Netto, R. Buyya, BigData Computing and Clouds: Trends and Future Directions, Journal of Parallel and Distributed Computing, Vol. 79-80, pp. 3-15, 2015.
- M. Assunção , Carlos Cardonha, Marco A.S. Netto, Renato L. F .Cunha , Impact of User Patience on Auto-Scaling Resource Capacity for Cloud Services, Future Generation Computer Systems (FGCS), Vol. 55, pp. 41–50, 2016.
INRIA/Kerdata - Rennes, France
KerData (https://team.inria.fr/kerdata/) is a joint research team of Inria Rennes - Bretagne Atlantique, ENS Rennes and INSA Rennes. Kerdata’s main research activities address the area of distributed data management at challenging scales, with a particular focus on clouds and petascale HPC architectures. Shadi Ibrahim (Research Scientist, Inria, partner coordinator) and Gabriel Antoniu (Senior Research Scientist, Inria, leader of the KerData project-team) will be the main participants of KerData in this project.
Shadi Ibrahim (INRIA/Kerdata scientific representative) is a permanent Inria Research Scientist within the KerData team. He obtained his Ph.D. in Computer Science from Huazhong University of Science and Technology in Wuhan of China in 2011. He has published several research papers in recognized Big Data and Cloud Computing research conferences and journals including TPDS, FGCS, PPNA, SC, IPDPS, Mascots, CCGrid, ICPP, SCC, Cluster, and Cloudcom.
- Orcin Yildiz, Matthieu Dorier, Shadi Ibrahim, Rob Ross, Gabriel Antoniu. On the Root Causes of Cross-Application I/O Interference in HPC Storage Systems. IPDPS - International Parallel and Distributed Processing Symposium, May 2016.
- Orçun Yildiz, Shadi Ibrahim, Gabriel Antoniu, Enabling fast failure recovery in shared Hadoop clusters: Towards failure-aware scheduling, Future Generation Computer Systems, 2016.
- Matthieu Dorier, Orçun Yildiz, Shadi Ibrahim,Anne-Cécile Orgerie, and Gabriel Antoniu, "On the Energy Footprint of I/O Management in Exascale HPC Systems", Future Generation Computer Systems, 2016.
- Shadi Ibrahim, Tien-Dat Phan, Alexandra Carpen-Amarie, Houssem-Eddine Chihoub, Diana Moise, and Gabriel Antoniu, “Governing Energy Con- sumption in Hadoop through CPU Frequency Scaling: an Analysis”, In the Future Generation Computer Systems (FGCS) Journal, 2015.
- Shadi Ibrahim, Hai Jin, Lu Lu, Bingsheng He, Song Wu, “Adaptive disk i/o scheduling for map reduce in virtualized environment”, in the 2011 International Conference on Parallel Processing (ICPP 2011).
Gabriel Antoniu is a Senior Research Scientist at Inria, Rennes. He leads the KerData research team, focusing on storage and I/O management for Big Data processing on scalable infrastructures (clouds, HPC systems). He has acted as advisor for 15 PhD theses and has co-authored over 100 international publications.
- Matthieu Dorier et al. Using Formal Grammars to Predict I/O Behaviors in HPC: the Omnisc’IO Approach. IEEE Transactions on Parallel and Distributed Systems (TPDS), 2016.
- Benoit Da Motaetal., IMAGEN Consortium. Machine learning patterns for neuroimaging-genetic studies in the cloud. Recent Advances and the Future Generation of Neuroinformatics Infrastructure. 2014.
- Radu Tudoran et al. 2014 JetStream: enabling high performance event streaming across cloud data-centers. In Proceedings of the 8th ACM International Conference on Distributed Event-Based Systems (DEBS ’14).
University Paris 13
Université Paris 13 is a multidisciplinary university based in the north of Paris, in the towns of Villetaneuse, Saint Denis, La Plaine Saint-Denis and Bobigny (Seine-Saint-Denis department) and at Argenteuil (Val-d’Oise department). It has 24,000 students spread over five campuses, in initial or continuing training. The Paris 13 University is a member of the COMUE Sorbonne Paris Cité (SPC) and Campus Condorcet. The Computer Science laboratory of Paris-North University (LIPN) has been associated with CNRS (UMR 7030) since January 1992. Most of the LIPN professors hold a permanent position at Paris 13 University, at Institut Galilée or IUT de Villetaneuse. Research at LIPN is carried out in its major areas of expertise, in particular Combinatorics, Algorithmics, Logic, Software, Natural Language Processing, Machine Learning, Combinatorial Optimization. LIPN develops fundamental researches and has a cooperation policy with large organisations and companies. This policy leads to participating in European or international projects, ANR, etc. The collaboration with companies also includes CIFRE fellowships. Additional information is available on the laboratory website. The LIPN team will contribute in data management, orchestration of grid and cloud middleware and also on machine learning algorithms seen as applications for validating the project.
Christophe Cérin is professor of computer science since 2005, at the University of Paris 13, France. He has initiated an infrastructure project related to big data and high performance computing for e-sciences for USPC (Université Sorbonne Paris Cité) federating the universities of Paris 3, Paris 5, Paris 7, Paris 13, INALCO, Sciences Po, Institut de Physique du Globe de Paris and Ecoles des hautes études en santé publique. At Paris 13, he chairs the board for the cluster computing facility available to all campus scientists and also chairs the ’Expert Committee’ in charge of recruiting and mentoring full time junior and senior professors in computer science. His industrial experience is currently as local chair for the Wendelin project (Gaz de France, Mitsubishi, Inria, Telecom ParisTech, Paris 13) related to Big Data.
- Walid Saad, Hither Abbes, Mohamed Jemni, Christophe Cérin: Designing and Implementing a Cloud-hosted SaaS for data movement and sharing with SlapOS. IJBDI 1(1/2): 18-35 (2014)
- Congfeng Jiang, Jian Wan, Christophe Cérin, Paolo Gianessi, Yanik Ngoko: Towards Energy Efficient Allocation for Applications in Volunteer Cloud. IPDPS Workshops 2014: 1516-1525
- Walid Saad,Leila Abidi, Heithem Abbes, Christophe Cérin, Mohamed Jemni: Wide Area BonjourGrid as a Data Desktop Grid: Modeling and Implementation on Top of Redis. SBAC-PAD 2014: 286-293
- Walid Saad, Heithem Abbes, Christophe Cérin, Mohamed Jemni: A Data Prefetching Model for Desktop Grids and the Condor Use Case. Trust- Com/ISPA/IUCC 2013: 1065-1072
- Christophe Cérin and Gilles Fedak: Desktop Grid Computing, Chapman&Hall/CRC Numerical Analysis and Scientific Computing Series,2012
Computer Network Information Center of the Chinese Academy of Sciences CNIC/CAS
The Computer Network Information Center (CNIC) of the Chinese Academy of Sciences (CAS) is an institution involved in constructing and operating IT infrastructure and providing IT-related services. In addition, it serves as an R\&D and demonstration base for e-technology applications.
CNIC was founded in 1995 in connection with the establishment of the National Computing and Networking Facility of China (NCFC). Within the framework of the NCFC, CNIC participated in every step of the early development of China’s Internet, including China’s fully functional access to the international Internet (as the 77th country) in April 1994. One month later, China’s national-level domain ".cn" came into use with the installation of China’s first domain server.
The goal of CNIC is to lead the way in establishing and supporting "e-science" in China. By "e-science" we mean the use of IT resources in all aspects of scientific research to improve efficiency and enhance scientific achievement. CNIC is also committed to serving the management of CAS by supporting its IT needs. CNIC aims to rank among the world’s top supercomputing centers, data centers and science research networks. Realization of our goal relies on more than 700 employees and over 160 graduate students, all of whom work diligently together in an interdisciplinary manner.
CNIC has already basically established a secure and reliable cyber-infrastructure that includes a science and technology network, supercomputing environment, data resource platform, public outreach platform and CAS’s Academia Resource Planning system. Below are key data about CNIC (current as of November 2013):
CSTNET (China Science \& Technology Network) has a nationwide network connecting 12 regional subcenters and 20 independent institutes via high-speed links, covering more than 30 provinces, autonomous regions and municipalities. The supercomputing environment of CAS, consists of one main center in Beijing, nine subcenters, 18 CAS institute centers and 11 GPU centers across China. The Supercomputing Center supports research on computational physics, computational chemistry, materials science, life science, drug design, geophysics, fluid dynamics, climate modeling, astronomy and agriculture. The scientific data center maintains a 24-PB storage environment. The scientific database has been accessed by more than 58 million visitors with more than 610 TB of downloaded data. The NSC (Network-based Science Communication) platform currently consists of four regional service centers in China with average daily page views of more than 1.88 million. Virtual Science Museums of China, a portal of the NSC platform, currently has over 230,000 page views per day. The CAS ARP (Academia Resource Planning) system supports 133 on-line ARP modules and the academic website group platform sustains 688 independent websites.
Haiwu He (CNIC/CAS scientific representative) is a 100 Talents Professor at the CNIC, CAS. He is also a “Chunhui Scholar” of Ministry of Education of China since 2013. Prof. Haiwu HE received his M. Sc. and Ph. D. degrees in computing from the University of Sciences and Technologies of Lille, France, respectively in 2002 and 2005. He was a postdoctoral researcher at Inria Saclay, France in 2007. He was a research engineer expert at Inria Rhone-Alpes in Lyon, France from 2008 to 2014. He has published about 30 refereed journal and conference papers. His research interest covers BigData, Cloud computing and HPC. Now, he is also a research team leader of a joint GPU research center of CNIC/CAS.
- DSMC3: Fast Direct Simulation Monte Carlo Solver for the Boltzmann Equation by Multi-Chain Markov Chain and Multicore Programming. Di Zhao, Haiwu He, International Journal of Modeling, Simulation, and Scientific Computing, 2016
- HybridMR: A New Approach for Hybrid MapReduce Combining Desktop Grid and Cloud Infrastructures. Bing Tang, Haiwu He and Gilles Fedak, Concurrency and Computation: Practice and Experience, 2015.
- Availability and Network-aware Map Reduce Task Scheduling over theIn tenet. Bing Tang, Qi Xie, Haiwu He and Gilles Fedak, ICAPP 2015
- BitDew: A Data Management and Distribution Service with Multi-Protocol and Reliable File Transfer. G. Fedak, H. He, and F. Cappello Journal of Network and Computer Applications, 32(5):961–975, 2009.
- A hybrid GMRES/LS-Arnoldi method to accelerate the parallel solution of linear systems. Haiwu HE, G. BERGERE, and S. Petiton. Computers and Mathematics with Applications, 51(11):1647-1662, 2006.
Di Zhao is a 100 Talents Associate Professor at the CNIC, CAS. Zhao Di obtained his Ph.D. in Computer and Applied Mathematics from Louisiana Tech University in 2010. From 2010 to 2014, He is the head of Chinese Academy of Sciences –NVIDIA Joint Research Centre (GPU Research Center) and the Joint Education Center (GPU Education Center).
- DSMC3: Fast Direct Simulation Monte Carlo Solver for the Boltzmann Equation by Multi-Chain Markov Chain and Multicore Programming. Di Zhao, Haiwu He, International Journal of Modeling, Simulation, and Scientific Computing, 2016
- GPU Acceleration of Convolutional Neural Network for Brain Carcinoma MRI Image Segmentation by cuDNN. Di Zhao, Jianbo Lei ,GPU Technology Conference 2015 (GTC 2015)
- Fast Filter Bank Convolution for Three-dimensional Wavelet Transform by Shared Memory on Mobile GPU Computing. Di Zhao, Journal of Super- computing, 2015,71(9):3440-3455
Beefing Niu is a 100 Talents Professor at the CNIC, CAS. He got his Ph.D. in computer software in CNIC (Computer Network Information Center), CAS (Chinese Academy of Sciences). He published high impact articles in Nature and Cell in the field of health care.
- Mutational landscape and significance across 12 major cancer types. CyriacKandoth, metal. Nature 502 (7471), 333-339, 2013
- Pan-cancer network analysis identifies combinations of rare somatic mutations across pathways and protein complexes. Mark DM Leiserson et al.. Nature genetics. 47(2) 106-144, 2015
- Multiplatform analysis of 12 cancer types reveals molecular classification within and across tissues of origin. Katherine A Hoadley et al., Cancer
Genome Atlas Research Network. Cell. 158(4) 929-944, 2014
Xiaoyu Yang is a 100 Talents Professor at the CNIC, CAS. He got his Ph.D from De Montfort University, UK. His main research interests include e-Science, SOA, cloud computing, collaborative computing, grid computing, Java enterprise software architecture, etc.
- Cloud Computing in eScience: Research Challenges and Opportunities .Xiaoyu Yang et al.,Journal of Supercomputing, 2014
- A business-oriented Cloud federation model for real-time applications. Yang, X., Nasser B., et al., Future Generation Computer Systems, Elsevier, Volume 28, Issue 8, October 2012, Pages 1158–1167
- Service-Oriented Methodology and Technologies for Cloud Computing. Xiaoyu Yang, Lu Lu, IGI Global, 2012, (Book)
Huazhong University of Science and Technology (HUST) SCTS/CGCL/BDTS
Huazhong University of Science and Technology (HUST) is a national key university under the direct leadership of the Ministry of Education of P. R. China and is among the first Universities joining the national “211 Project” and “985 Project”. It was founded on May 26, 2000 as a result of the merger of the former Huazhong University of Science and Technology, Tongji Medical University and Wuhan Urban Construction Institute. At present, the University has eleven disciplines : engineering, medicine, management, science, philosophy, economics, law, education, literature, history and agriculture, offering a variety of degree programs, including 86 undergraduate programs, 256 graduate programs, 181 PhD programs. There are 32 post-doctoral research centers, 7 national key disciplines, 15 national key sub disciplines.
The Key Laboratory of Services Computing Technology and System (SCTS), Ministry of Education (MOE), the Key Laboratory of Cluster and Grid Computing (CGCL), Hubei Province, and concurrently the Engineering Lab of Big Data Technology and System (BDTS) is part of the national key discipline of computer system architecture and the key discipline of computer software and theory in Hubei Province, enjoying academic freedom and advanced research capabilities of international standards. The research areas that SCTS/CGCL/BDTS is engaged in Computing System Virtualization, Grid Computing, Peer to Peer Computing, Image Processing, System Security and etc. SCTS/CGCL/BDTS is gifted with research talents, initiative re- search members and excellent hardware environments. Currently 6 professors, 11 associate professors, and over 10 PhD staff members are working there, among them there are altogether 1 chief scientist from National 973 Basic Research Project, 1 awarded with National Outstanding Youth, 1 selected as National Class Talent of "New Century Hundred- Thousand-Myriad Talents Plan", 1 awarded with "Plan of Supporting New Century Talent". Besides the 130 full-time PhD candidates and graduate students, the lab has graduated more than 200 masters and 30 Ph.D students over the years.
SCTS/CGCL/BDTS is the main node of ChinaGrid, CNGrid Wuhan node, 985 Innovation and Technology Platform ; with a 2,000m2 test site, and the total value of its research instrument adds up to over RMB 90 million yuan. The development will directly provide a much better infrastructure and external environment for talent training in the future. SCTS/CGCL/BDTS has been undertaking about 40 significant research projects, including projects from 973 basic research project scheme, key projects from MOE, National Outstanding Youth Foundation, National Natural Science Foundation of China (NSFC), National 863 Hi-Tech R&D Program and some international cooperation, and CNGI projects supported by National Development and Reform Commission. Now SCTS/CGCL/BDTS is playing a leading role in the "Changjiang Scholar and Innovative Team Development Plan" from MOE, and Hubei Natural Science Fund Innovative Team.
SCTS/CGCL/BDTS has composed more than 20 monographs and teaching materials, and contributed over 900 papers to domestic and international periodicals and conferences which have been indexed more than 200 times by SCI and EI. SCTS/CGCL/BDTS has obtained 158 national invention patents and 131 national software copyrights, and filed in more than 100 national invention patents.
Xuanhua Shi (co-Principal Investigator) is a full professor in Service Computing Technology and System Lab/Cluster and Grid Computing Lab/ Big Data Technology and System Lab (SCTS/CGCL/BDTS), Huazhong University of Science and Technology (China). He received his Ph.D. degree in Computer Engineering from Huazhong University of Science and Technol- ogy (China) in 2005. From 2006, he worked as an Inria Post-Doc in the PARIS team at Rennes for one year. He currently leads the Big Data team in SCTS/CGCL/BDTS and works on big data systems, such as in-memory data processing, graph computing, etc. The in-memory computing system (called Mammoth) developed by his team has been recommended as Spotlight on Transactions by IEEE Computer. He published over 80 peer-reviewed publications, received research support from a variety of governmental and industrial organizations, such as National Science Foundation of China, Ministry of Science and Technology, Ministry of Education, and European Union. He has chaired several conferences and workshops and served on technical program committees of numerous international conferences. He is a member of IEEE and ACM, and a senior member of CCF (China Computer Federation).
- Xuanhua Shi, Ming Chen, Ligang He, Xu Xie, Lu Lu, Hai Jin, Yong Chen, and Song Wu, "Mammoth: Gearing Hadoop Towards Memory-Intensive MapReduce Applications", IEEE Transactions on Parallel and Distributed Systems, 26(8):2300-2315, 2015. Spotlight paper on Transactions
- Xuanhua Shi, Haohong Lin, Hai Jin, Bing Bing Zhou, Zuoning Yin, Sheng Diand Song Wu,"GIRAFFE: A Scalable Distributed Coordination Service for Large-scale Systems". IEEE Cluster, Madrid, Spain, 2014. Nominated for Best Paper
- Xuanhua Shi, Junling Liang, Sheng Di, Bingsheng He, Hai Jin, Lu Lu, Zhixiang Wang, Xuan Luo, Jianlong Zhong, "Optimization of Asynchronous Graph Processing on GPU with Hybrid Coloring Model". ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP’15), San Francisco, USA, 2015
- Zhixiang Wang, Xuanhua Shi, Hai Jin, Song Wu, Yong Chen, "Iteration Based Collective I/O Strategy for Parallel I/O Systems", CCGrid, 2014
- Lu Lu, Xuanhua Shi, Qiuyue Wang, Daxing Yuan, Song Wu, "Morpho: a Decoupled MapReduce Framework for Elastic Cloud Computing" ,Future Generation Computer Systems, 36:80-90, 2014
Qiangsheng Hua is an associate professor at SCTS/CGCL/BDTS, Huazhong University of Science and Technology (China). He published over 40 peer-reviewed papers in networking and distributed algorithms.
- Qiang-Sheng Hua, Haoqiang Fan, Ming Ai, Lixiang Qian, Yangyang Li, Xuanhua Shi, Hai Jin. Nearly Optimal Distributed Algorithm for Computing Betweenness Centrality. ICDCS 2016, Nara, Japan, June 27-30, 2016.
- Dongxiao Yu, Qiang-Sheng Hua*, Yuexuan Wang, Haisheng Tan, Francis C. M. Lau. Distributed multiple-message broadcast in wireless ad hoc networks under the SINR model. Theoretical Computer Science 610: 182-191, 2016.
- Dongxiao Yu, Yuexuan Wang, Qiang-Sheng Hua*, Francis C. M. Lau. Distributed (Delta+1)-coloring in the physical model. Theoretical Computer Science 553: 37-56, 2014.
Haikun Liu is an associate professor at SCTS/CGCL/BDTS, Huazhong University of Science and Technology (China). He received his Ph.D degree in Computer Science and Technology from HUST in 2012. From Jan. 2013 to Jan. He has published over 20 papers in peer-reviewed conferences and journals.
- Haikun Liu, Bingsheng He, F2C: Enabling Fair and Fine-grained Resource Sharing in Multi-tenant IaaS Clouds, IEEE Transaction on Parallel and Distribute Systems, 2015, DOI:10.1109/TPDS.2015.2499769
- Haikun Liu, Hai Jin,Xiamfei Liao, Wei Deng, Bingsheng Heand Cheng-Zhong Xu, Hotplug or Ballooning : A Comparative Study on Dynamic Memory Management Techniques for Virtual Machines, IEEE Transaction on Parallel and Distribute System, Vol. 26, No. 5, May 2015, pp. 1350-1363
- Haikun Liu and Bingsheng He, VMbuddies: Coordinating Live Migration of Multi-tier Applications in Cloud Environments, IEEE Transaction on Parallel and Distribute System, Vol.26, No.4, April 2015, pp. 1192-1205