Feb. 2, 2012: Authors of the best papers submitted to the workshop will be invited to submit their extended versions to Cluster Computing: Special Issue on Soft Computing Techniques in Cluster and Grid Computing Systems. Cluster Computing, The Journal of Networks, Software Tools and Applications (2010 Impact Factor: 0.679) is indexed on SCI, SCOPUS, INSPEC, Google Scholar, EBSCO, CSA, ACM Digital Library, CSI, DBLP, JCR/SE, and others.

May 11, 2012: Deadline extension, papers accepted until 31/05/2012.

May 28, 2012: Final deadline extension, papers accepted until 10/06/2012 using Easy Chair submission system.

July 02, 2012: New notification of acceptance on 07/07/2012.

July 7, 2012: Take note of the HPCLatam 2012 place: Salón de Actos (Meeting Room), second floor, Facultad de Ciencias Económicas (Business School), Universidad de Buenos Aires, Av. Córdoba 2122.

July 11, 2012: Special keynotes: Ian Foster(Argonne National Laboratory, University of Chicago), Mateo Valero (BSC, Spain) supported by RISC, Mauricio Marín (Yahoo! Research, Chile) supported by RISC and Adrián Cristal (BSC, Spain) supported by RISC; and one invited talk: Javier Príncipe (Universitat Politécnica de Catalunya, Spain).

August 26, 2012: New page with presentations and papers.

New complete proceedings avaliable: HPCLatAm 2012 proceedings (ISSN: 2422-5207).

The use and development of High Performance Computing in Latin America is steadily growing. New challenges come from the capabilities provided by clusters, grids, and distributed systems for HPC, promoting research and innovation in this area.

Building on the great success of the previous four editions, this year the Latin American Symposium on High Performance Computing is growing to include three major events: the High Performance Computing School (ECAR 2012), the V HPCLatAm2012 International Symposium itself (both to be held in Buenos Aires, from July 23 to August 3), and the HPC Day (August 30) within the 41st Argentine Conference of Informatics (41 JAIIO).

The main goal of HPCLatAM2012 is to provide a regional forum fostering the growth of the HPC community in Latin America through the exchange and dissemination of new ideas, techniques, and research in HPC. The symposium will feature invited talks from academy and industry, short- and full-paper sessions presenting both mature work and new ideas in research and industrial applications. Suggested topics of interest include, but are not restricted to:
  • Parallel Algorithms and Architectures
  • Distributed and Grid Computing
  • Cloud Computing
  • High Performance Applications
  • High Performance Software Tools
  • Visualization and Data Management
  • Tools and Environments for High Performance System Engineering
  • Component Technologies for High Performance Computing
  • Parallelism and Data Sharing on Multi-core Architectures
  • Virtualization in High Performance Computing
  • Graphics Processing Units in High Performance Computing
  • Country-wide Grid Initiatives
Paper submission deadline:: Deadline extension! June 10, 2012 (Easy Chair submission system)
Notification of acceptance: July 7, 2012
Camera-ready papers due: July 18, 2012
Conference Dates: July 23 to August 3, 2012

Short- and full-length papers must be written in English according to Springer LNCS style (guidelines available at: Papers must not have been previously published or submitted elsewhere. Submissions will be handled electronically using Easy chair system, please follow the link to submit.

The authors of accepted papers must guarantee that their paper will be presented at the symposium. At least one author of each accepted paper must be duly registered for the symposium in order for the paper to be scheduled in the papers session and to appear in the V HPCLatAm2012 proceedings.

Regular full-length papers
Full papers must not exceed 16 pages, including name, affiliation and address of the author(s), figures, tables, references, and an abstract of no more than 200 words. All full paper submissions will be carefully reviewed by at least two experts and returned to the author(s) with comments to ensure the high quality of accepted papers. Full papers accepted for the program will appear in the V HPCLatAm2012 proceedings.

Short papers/Extended abstracts
Authors are invited to submit short papers (extended abstracts) for results that are too late to be submitted as regular full-length papers. Short papers must not exceed 4 pages. Short papers accepted for the program will appear in the proceedings (not expanded to full papers, and with Extended Abstract in the title) and be presented orally during the symposium (in suitably shorter speaking slots) as a regular part of the program.

Special Issues
Authors of the best papers submitted to the workshop will be invited to submit their extended versions to Cluster Computing: Special Issue on Soft Computing Techniques in Cluster and Grid Computing Systems. Cluster Computing, The Journal of Networks, Software Tools and Applications (2010 Impact Factor: 0.679) is indexed on SCI, SCOPUS, INSPEC, Google Scholar, EBSCO, CSA, ACM Digital Library, CSI, DBLP, JCR/SE, and others.
Monday, July 23
08:00 to 09:00 Registration (coffee available)
09:00 to 09:30 Opening session: Prof. Barañao (Science, Technology and Productive Innovation Minister, Argentina)
09:30 to 10:15 Keynote speaker: Prof. Mateo Valero (Barcelona Supercomputing Center, Spain)
10:15 to 11:00 Invited Talk: Presentation of National System of High Performance Computing Large Scientific Equipment, Prof Pablo Mininni (CONICET/UBA)
11:00 to 11:30 Coffee break
11:30 to 13:00 Full Papers I: High performance scientific computing
11:30-11:50 Parallel Adaptive Simulation of Coupled Incompressible Viscous Flow and Advective-Diffusive Transport Using Stabilized FEM Formulation
11:50-12:10 A Numerical Algorithm for the Solution of Viscous Incompressible Flow on GPU's
12:10-12:40 Parallel Computing Applied to Satellite Images Processing for Solar Resource Estimates
12:40-13:00 Parallel conversion of satellite image information for a wind energy generation forecasting model
13:00 to 14:30 Lunch (students unpack posters)
14:30 to 15:00 Featured talk: Meeting Exascale Challenges with File System Building Blocks, Andy McNeill (IBM)
15:00 to 15:45 Keynote speaker: Mauricio Marín (Universidad de Santiago de Chile and Yahoo! Research Chile)
15:45 to 16:00 Coffee break
16:00 to 18:00 Full Papers II: GPU computing
16:20-16:40 Facial Recognition Using Neural Networks over GPGPU
16:40-17:00 Parallel implementations of the MinMin heterogeneous computing scheduler in GPU
17:20-17:40 A parallel online GPU scheduler for large heterogeneous computing systems
17:40-18:00 Biclustering of very large datasets with GPU tecnology using CUDA
18:00 to 18:30 Invited talk: RISC project Initial Results, Prof. Ulises Cortés (Barcelona Supercomputer Center, Spain)
18:30 to 19:45 Poster evaluation (snacks available)

21:00 Symposium dinner (Parrilla típica "El Desnivel", Defensa 855, San Telmo), transportation available.

Tuesday, July 24
08:45 to 09:15 Reception (coffee available)
09:15 to 10:00 Keynote speaker: Adrián Cristal (Barcelona Supercomputing Center, Spain)
10:00 to 10:30 Invited talk: Javier Príncipe (Universidad Politécnica de Catalunya, Spain)
10:30 to 11:15 Presentations I
10:30-10:45 Parallel Simulations of Coupled Multiphysics Problems in Bio-physics
10:45-11:00 Scaled Real-Time Parallelization for DEVS Simulation of Hybrid Systems
11:00-11:15 Accessing files using transactional memory
11:15 to 11:30 Coffee break
11:30 to 12:15 Keynote speaker: Ian Foster (Argonne National Laboratory, University of Chicago, USA)
12:15 to 13:00 Presentations II
12:15-12:30 Parallel execution of a parameter sweep for molecular dynamics simulations in a mixed GPU/CPU environment
12:30-12:45 Improve an efficient simulation of multidimensional Gaussian random fields in GPU
12:45-13:00 Applying List Scheduling Algorithms In A Multithreaded Execution Environment
13:00 to 14:00 Lunch
14:00 to 15:00 Full Papers III: Applications
14:00-14:20 Optimizing Latency in Beowulf Clusters
14:20-14:40 SMCV: a Methodology for Detecting Transient Faults in Multicore Clusters
14:40-15:00 Evolutionary Statistical System for applying in Forest Fire Spread Prediction
15:00 to 16:00 Presentations III
15:00-15:15 Parallelizing NEC's Equation Solver Algorithm with OpenMP
15:15-15:30 Parallelizing Lattice Boltzmann Methods with OpenMP
15:30-15:45 Power Characterisation of Shared-Memory HPC Systems
15:45-16:00 Using distributed local information to improve global performance in Grids
16:00 to 16:15 Coffee break
16:15 to 16:45 Final Poster Round (in SUM)
16:45 to 17:00 Poster and Paper Awards – Closing
17:00 to 19:00 Face-to-face meeting RISC Project (only project members)
This event is coordinated with the HPC-Day to be held on 30 August in JAIIO conference. The inscription fee allows assisting both events: HPCLatAm Symposium and HPC-Day. With the inscription to this event, you can assist both:
  • SADIO non-members: $430 (Argentinian Pesos).
  • SADIO members: $215 (Argentinian Pesos).
  • Professors and education staff: $260 (Argentinian Pesos).
  • SADIO non-members students: $120 (Argentinian Pesos).
  • SADIO members students: $120 (Argentinian Pesos).

The student discount is only for undergraduate students.

  • Cash: SADIO - Uruguay 252 2º "D"- Capital Federal - Buenos Aires. Monday-Friday 12:00 to 18:00.
  • Bank Transfer (only for residents in Argentina). BBVA -Bco. Francés, Sucursal 330 Tribunales, Cta. Cte. Pesos: 502/7, CBU: 01703304 20000000050276, CUIT: 30-64931218-0
  • Credit card: VISA o MASTERCARD.
    • The registration is closed

  • Esteban Mocskos, Universidad de Buenos Aires, Argentina
  • Sergio Nesmachnow, Universidad de la República, Uruguay
  • Adrián Cristal, Barcelona Supercomputing Center, Spain
  • Andrés More, Intel, Argentina
  • Alvaro Coutinho, Universidade Federal do Rio de Janeiro, Brasil
  • Carlos Garcia Garino, Universidad Nacional de Cuyo, Argentina
  • Cristian Perfumo, University of Newcastle, Australia
  • Diego Crupnicoff, Mellanox Technologies, USA
  • Eduardo Bringa, Universidad Nacional de Cuyo, Argentina
  • Gerson Geraldo Cavalheiro, Universidade Federal de Pelotas, Brasil
  • Gonzalo Hernández Oliva, Universidad de Valparaíso, Chile
  • Francisco Brasileiro, Universidade Federal de Campina Grande, Brasil
  • Marcela Printista, Universidad Nacional de San Luis, Argentina
  • Mariano Camilo González Lebrero, Universidad de Buenos Aires, Argentina
  • Mariano Vázquez, Barcelona Supercomputing Center, Spain
  • Mario Storti, Universidad Nacional del Litoral, Argentina
  • Miguel Angel Cavaliere, Tenaris Siderca and Universidad de Buenos Aires, Argentina
  • Nicolás Wolovick, Universidad Nacional de Córdoba, Argentina
  • Pablo Mininni, Universidad de Buenos Aires, Argentina
  • Alejandro Soba, CNEA-CONICET, Argentina
  • Patricia Tissera, IAFE, Universidad de Buenos Aires, Argentina
  • Ricardo Medel, Intel, Argentina
  • Roberto Bevilacqua, Comisión Nacional de Energía Atómica, Universidad de Buenos Aires, Universidad Nacional de San Martin, Argentina

"A network for supporting the coordination of Supercomputing Research between Europe and Latin America"
Contact e-mail: hpc2012 (at)