Dr. Toni Cortes


  1. 1.dataClay: the integration of persistent data, parallel programming models, and true sharing
    Keynote at International Symposium on Parallel and Distributed Computing (ISPDC 2015), Limassol, Cyprus, 30 June, 2015

  2. Since the beginning, persistent data and non persistent data have been treated as two separate abstractions. A clear example is that the model used to store data into volatile memory (mainly objects an their relations) is completely different from the model used to store the same data into a persistent storage (mainly tables or files). This differentiation between data has many negative side effects because persistent data cannot be integrated into the programming model. This lack of integration causes, among others, the following problems  i) moving computation to the data becomes a complex task (deployment can become an arduous task) , ii) the extraction of potential data parallelism by the programming model is very difficult (the programming model is unaware of where the data really is), and iii) offering a mechanisms to really share data without taking the control from the data owner becomes nearly impossible (we will show that today data is not really shared).

  3. In this talk, we will present dataClay, a new-generation object storage and its integration with the COMPSs programming model. This new way to handle data (and code), and its perfect fit with a parallel programming model will eliminate all the afore-mentioned problems easing the task of implementing data-centric programs while full advantage of the available parallelism.

  4.    Slides

  5. 2.Data Sharing in the Big-data era
    Keynote at BigDataCloud 2014, Porto, Portugal, 25 August, 2014

  6. In this talk, Toni will focus on the value of big data, which comes from the possibility of extracting information from large amounts of raw data. And, as in real life, the most valuable information comes from the merging of shared information from different sources. Unfortunately, current sharing mechanisms are either too restrictive and thus not flexible enough, or the data provider losses control over its asset (its data). This limitation prevents data owners and potential service designers from taking advantage of the available data. In this talk we will introduce the idea of self-contained objects and how 3rd-party enrichment of such objects can offer an environment where the data providers keep full control over its data while service designers get the maximum flexibility.

  7.     Slides

  8. 3.Why bother humans? They do not care!
    Keynote at Euro-Par 2011, Bordeaux, France, September 2, 2011

  9. Traditionally, HPC has been obtained at a high cost for the users. How many times have you heard, or read, from HPC managers that user training was key to achieve high performance on a HPC system? But think it from the user perspective; did any of the recommendations make any sense to them? How much pain did this training mean to them? How many things did they have to worry about besides their real problem? They cared about a business or science problem that, unfortunately, involved large amounts of data and computation. They did not care about all these other things they had to learn to get their problem solved. Can HPC systems be designed and implemented in a different way where high-performance is achieved by the system and not the user?

  10. Just a couple of thoughts: i) if current systems are complex to use, can you imagine using an exaflop machine? and ii) the iPad2 would have been in the top500 till 1994, could we have though back in 1994 that a machine in the top500 could be as easily used as an iPad2?

  11.     Slides

  12. 4.Adapting RAID technology to large heterogeneous clusters
    Keynote at HeteroPar 2007, Austin, Texas, September 20, 2007

  13. Current clusters tend to have heterogeneous resources and storage devices a no exception. Current high performance solutions to access data such a RAID technology are not able to handle this heterogeneity in a nice way. Thus new distribution algorithms have to be devised to use these heterogeneous storage devices taking the most of their potential. In addition, these distribution algorithms have to be easy to use and also need to be scalable, meaning that the addition of more storage resources to the cluster does not imply a redistribution of all data as would happen in mostRAID technologies.

  14.     Slides

Mass media

  1. 1.Interview on BigData
    Ciencia Optimista, RAC1
    June 19, 2013

         Audio (in Catalan)

Invited talks

  1. 1.Parallel File System – Quo Vadis? ISC 2016, Frankfurt; Germany, June 19-23, 2016  (Panel Talk)
        Panelists: Eric Barton, Intel, Volker Lindenstruth, University of Frankfurt, Franz-Josef Pfreundt, ITWM, and Toni Cortes BSC

  2. 2.Integrating the access to persistent data with parallel programming. Ioannina University, Greece, May 24, 2016

  3. 3.Task based programming models and its integration with data. BigStorage initial school, Barcelona, Spain, March 3-9, 2016

  4. 4.Integration of Parallel Programming Models and Persistent Data. NESUS winter school, Timișoara, Romania, February 8-11, 2016

  5. 5.BSC and integrating persistent data and parallel programming models. HPC Advisory Council Conference. Barcelona, Spain, September  22, 2015

  6. 6.DataClay: Towards Usable and Shareable Storage. Big Data and Extreme-scale Computing (BDEC), January 28-30, 2015, Barcelona, Spain

  7. 7.dataClay: the future of data sharing. 2nd workshop of the JLESC, Chicago, IL, USA, November 23-26, 2014

  8. 8.Infrastructures for BigData. Big Data in Biomedicine: Challenges and Opportunities, Barcelona, Spain November 11-12, 2014
        Panelists: Toni Cortes - BSC, Blak Fitch - IBM, Teresa Przytycka - NCBI/NLM/NIH

  9. 9.Sharing data: the real challenge to use BigData. Universidad de Granada, Granda, Spain, July 18, 2014.

  10. 10.Sharing data: the real challenge to use BigData. Big-data seminar at INRIA, Renns, France, December 9, 2013

  11. 11.Supercomputación y big data. Instituto Menéndez y Pelayo, Barcelona, Spain, November 19, 2013

  12. 12.Vivir en un Mar de Datos. Hacia una sociedad inteligente, Madrid, Spain, November 13, 2013 - Panel on big data

        Video (in Spanish)

  1. 13.A new paradigm to enable flexible and efficient data sharing without loss of control. CloudScapeV, Brussels, Belgium, February 27-28, 2013 (Panel Talk)
        Panelists: Jean-Pierre Laisne - Bull, Stuart Coleman - EUDAT, Rob Baxter - EPCC
    Toni Cortes - BSC

  2. 14.EOFS Exascale IO workgroup status 11th HLRS/hww Workshop on Scalable Global Parallel File Systems - Total Cost of Dataship, Stuttgart, Germany, May 7-9, 2012

  3. 15.Deterministic storage in heterogeneous environments SCALUS winter school, Barcelona, Spain, February 22, 2011

  4. 16.Implications of Exascale Computing for Storage Systems Research. IEEE Conference on Cluster Computing (Cluster 2010), Heraklion, Crete, September 20-24, 2010 (Panel talk)
        Panelists: Toni Cortes - UPC / BSC, Garth Gibson - CMU / Panasas, Peter Haas - HLRS Stuttgart, Rob Ross - ANL

  5. 17.Advantages and challenges of application execution management. 1st XtreemOS summer school, Oxford, UK, September 9, 2009

  6. 18.Autonomic Storage System based on Automatic Learning. Microsoft Research, Cambridge, UK, February 21, 2008

  7. 19.XtreemFS: a global file system targeted to data sharing among organizations. Universidad de Murcia, Murcia, February 11, 2008

  8. 20.Autonomic Storage System based on Automatic Learning . Heinz Nixdorf Institut, University of Paderborn, Germany, October 2006

  9. 21.Cooperation with IBM designing issues for the BG/L. Universidad de Castilla la Mancha, Albacete, February 28, 2005

  10. 22.Cooperation with IBM designing issues for the BG/L. Universidad de Murcia, Murcia, October 2004

  11. 23.Approaches to Autonomic Computing at CIRI. IBM TJW Research lab, New York, NY, March 2004

  12. 24.I have resources! Can I used them to improve parallel I/O?. Universidad Politécnica de Madrid, Madrid, March 2003

  13. 25.Software for Cluster Computing: Potential and Limitations . Universidad de A Coruña, A Coruña, November 2002

  14. 26.Panel titled "Teaching Operating Systems". XIII Jornadas de Paralelismo, LLeida, September 2002

  15. 27.Cluster Computing: Potential and Limitations. Universidad de Castilla la Mancha, Albacete, May 10, 2001

  16. 28.A Case for Heterogeneous Disk Arrays. Universidad de Murcia, Murcia, March 2000

  17. 29.Panel titled "Teaching Distributed Systems". X Jornadas de Paralelismo, La manga del mar menor, September 1999

  18. 30.Swap Compression. Arizona State University, June 1999

  19. 31.Cooperative Caching and Prefetching for Parallel/Distributed File Systems Storage System Laboratory. HP Labs, Palo Alto, June 1999

  20. 32.Seguridad en Unix
    Entornos Unix: Actualidad y Futuro, Barcelona, Spain, September 1992

  21. 33.Seminars and tutorials

  22. 1.Storage I/O in Modern Servers and Data-centric Applications: Efficiency and Scalability Challenges
    in cooperation with Angelos Bilas, Ricardo-Jimenez Peris, and Bilha Mendelson. HiPEAC, Paris, Jan 24, 2012

  23. 2.Easing Application Execution in Grids with XtreemOS Operating System. Open Grid Forum (OGF-28), Munich, Germany, March 15, 2010 (1/2-day tutorial)

  24. 3.Parallel I/O: Problems and solutions. Universidad de Granada, Granada, May 12-13, 2009 (2-day tutorial)

  25. 4.Parallel I/O: Problems and solutions. Universidad de Granada, Granada, May 15-16, 2008 (2-day tutorial)

  26. 5.Handling Heterogeneous Storage Devices in Clusters
    in cooperation with André Brinkmann,. IEEE Conference on Cluster Computing (Cluster 2007), Austin, Texas, September 17, 2007  (1/2-day tutorial)

  27. 6.Parallel I/O: Problems and solutions. Universidad de Granada, Granada, May 2007 (1-day tutorial)

  28. 7.Parallel I/O: Lessons learnt in the last 20 years. IEEE Conference on Cluster Computing (Cluster 2004), San Diego, CA, September 20-23, 2004 (1/2-day tutorial)

  29. 8.Parallel I/O: Problems and solutions. XIV Jornadas de Paralelismo, Leganés, Madrid, September 2003 (1/2-day tutorial)

  30. 9.Parallel I/O: Lessons learnt in the last 20 years. Universidad Carlos III, Madrid, March 2003 (3-day tutorial)

  31. 10.BCluster Computing: Potential and Limitations. XI Jornadas de Paralelismo, Granada, September 12, 2000  (1/2-day tutorial)

  32. 11.Windows NT: Concepts and Utilization. Grupo Viajes Iberia, Palma de Mallorca, June 1996 (5-day tutorial)

  33. 12.Operating System: Management and Tuning. Universidad de la Palmas, Las Palmas de Gran Canaria, February 1996 (5-day tutorial)