Project proposal: If you would like to establish a new JLESC project, please use this template to describe your ideas. Then, submit the proposal to your local JLESC Executive Director as well as to the JLESC Director Franck Cappello via email. During the next conference call, your proposal will be discussed (and most likely accepted) and a project leader will be nominated (feel free to nominate someone yourself).

Your duties: To start your project officially, we ask you to submit a short description on this website, following the guidelines you can find here. At each JLESC workshop, one of your project members is expected to report on the progress of your work. Furthermore, each year we ask the project leaders to submit a written report on the status of the project. These reports are then assembled into an official JLESC report for the Steering Committee to evaluate.

Your benefits: Besides the obvious benefits you have from participating in a JLESC project (glory, honor, happiness), members of an active project have access to travel funds supporting visits, exchanges and further activities within the project. In particular, JLESC encourages PhD students to make use of these funds. Also, scientists participating actively in projects will receive preferred invitations to the JLESC workshops. For more information please contact your local JLESC Executive Director.

There are a total of 33 projects in JLESC with the following stages:

  • help wanted: 0
  • starting: 2
  • running: 21
  • suspended: 6
  • finished: 4

The convergence between HPC, Cloud and bigdata as well as the technology trends, in particular the end of the Moore’s law, call for research in new architecture at the large scale level and at the device level. The convergence between HPC, Cloud and bigdata is a central research topic in the community as shown by the BDEC meetings organized by the leaders of the community and by the orientation taken by vendors (HPC system providers). What type of resources are needed, what architecture, what system software, what programming models, what new applications are some of the questions this convergence raises. The end of the Moore's law is another factor of transformation in the HPC domain. It becomes clear that the CMOS integration progress will come to an end in the mid 2020's. It is also very unlikely that any new technology will provide four decades of progress that CMOS gave us. This opens a very exciting era of research for microarchitecture, system architecture and all the software stack: if performance progress does not come anymore from the technology then architecture and software will play a major role. The topic leaders are:

  • Kate Keahey (ANL)
  • Christine Morin (INRIA)
  • Rosa M. Badia (BSC)
  • Wen-Mei W. Hwu (UIUC)
  • Dirk Pleiter (JSC)

  • Evaluating high-level programming models for FPGA platforms

    • Kazutomo Yoshii (ANL)
    • Carlos Alvarez (BSC)
    • Daniel Jimenez-Gonzalez (BSC)
    • Xavier Martorell (BSC)
    • Kentaro Sano (RIKEN)
    • Zheming Jin (ANL)
    • Hal Finkel (ANL)
    • Franck Cappello (ANL)

    Elastic provisioning for data streams

    • Kate Keahey (ANL)
    • Gabriel Antoniu (INRIA)
    • Luis Pineda Morales (INRIA)
    • Balaji Subramaniam (ANL)
    • Alexandru Costan (INRIA)

    On-Demand Data Analytics and Storage for Extreme-Scale Simulations and Experiments

    • Franck Cappello (ANL)
    • Katrin Heitmann (ANL)
    • Gabrielle Allen (UIUC)
    • William Gropp (UIUC)
    • Salman Habib (ANL)
    • Ed Seidel (NCSA)
    • Brown Maxine D. (UIUC)
    • Rajkumar Kettimuthu (ANL)
    • Rob Sisneros (UIUC)
    • Corby B. Schmitz (ANL)
    • Sean R. Stevens (NCSA)
    • Matthew J. Turk (UIUC)
    • Thomas D. Uram (ANL)
    • David Wheeler (NCSA)
    • Michael J. Wilde (ANL)
    • Justin Wozniak (ANL)

    Advancing Chameleon and Grid'5000 testbeds

    • Kate Keahey (ANL)
    • David Loup (INRIA)
    • Simon Delamare (INRIA)
    • Lucas Nussbaum (INRIA)
    • Christian Perez (INRIA)

    Science needs and constraints in terms of simulation, analytics, communication and storage are the ultimate drivers of the research in the JLESC. Applications are the tangible instances of scientific problems on which the joint-lab can provide contributions. It is important in the joint-lab to understand trends and anticipate significant evolutions. How to model scientific problems and map them into efficient applications, what type of numerical methods these applications use and what are the attractive numerical methods for future extreme scale systems, what are the motifs (in the sense of Berkeley motifs) used in these applications, are there any new emerging motifs, how new constraints such as data reduction and in-situ data analytics change application design, how to map applications to mini-apps that are more tractable for computer science research purpose are among the questions that the JLESC address in this topic. The topic leaders are:

  • Tom Peterka (ANL)
  • Stéphane Lanteri (INRIA)
  • Mariano Vázquez (BSC)
  • Gabrielle Allen (UIUC)
  • Andreas Lintermann (JSC)
  • Naoya Maruyama (RIKEN)

  • Comparison of Meshing and CFD Methods for Accurate Flow Simulations on HPC systems

    • Andreas Lintermann (JSC)
    • Makoto Tsubokura (RIKEN)
    • Keiji Onishi (RIKEN)

    The ChASE library for large Hermitian eigenvalue problems

    • Edoardo Di Napoli (JSC)
    • Andre Schleife (UIUC)
    • Hiroya Suno (RIKEN)
    • Jan Winkelmann (EXT)

    Simplified Sustained System performance benchmark

    • Miwako Tsuji (RIKEN)
    • Bill Kramer (UIUC, NCSA)
    • Mitsuhisa Sato (RIKEN)

    Data communication and storage is becoming the main performance bottleneck for extreme scale systems. File system bandwidth for the largest systems seems plateauing around 1TB/s. This raises several new problems concerning the I/O infrastructure, the software of the storage system, visualization, how to perform analytics before storing the data produced by the simulation. New research domains have emerged in HPC system the past 2-5 years: Burst buffers, in-situ data analytics, workflows and new abstractions for storage. This topic of the JLESC oversees all these questions considering performance (I/O overheads and interference for example), scalability and reliability as critical. The topic leaders are:

  • Rob Ross (ANL)
  • Gabriel Antoniu (INRIA)
  • Toni Cortes (BSC)
  • Rob Sisneros (UIUC)
  • Wolfgang Frings (JSC)

  • Mitigating I/O Interference in Concurrent HPC Applications

    • Matthieu Dorier (ANL)
    • Gabriel Antoniu (INRIA)
    • Shadi Ibrahim (INRIA)
    • Orcun Yildiz (INRIA)
    • Rob Ross (ANL)

    Toward taming large and complex data flows in data-centric supercomputing

    • Emmanuel Jeannot (INRIA)
    • Venkatram Vishwanath (ANL)
    • Francois Tessier (ANL)

    Extreme-Scale Workflow Tools - Swift, Decaf, Damaris, FlowVR

    • Tom Peterka (ANL)
    • Justin Wozniak (ANL)
    • Matthieu Dreher (ANL)
    • Rob Ross (ANL)
    • Gabriel Antoniu (INRIA)
    • Matthieu Dorier (ANL)
    • Bruno Raffin (INRIA)

    Exploiting the Omnisc'IO prediction approach for Exascale systems

    • Matthieu Dorier (ANL)
    • Rob Ross (ANL)
    • Gabriel Antoniu (INRIA)
    • Shadi Ibrahim (INRIA)

    Resource Management, Scheduling, and Fault-Tolerance for HPC Workflows

    • Shadi Ibrahim (INRIA)
    • Nathanael Cheriere (INRIA)
    • Matthieu Dorier (ANL)
    • Rob Ross (ANL)
    • Gabriel Antoniu (INRIA)
    • Justin Wozniak (ANL)

    Smart In Situ Visualization

    • Gabriel Antoniu (INRIA)
    • Tom Peterka (ANL)
    • Rob Ross (ANL)
    • Matthieu Dorier (ANL)
    • Rob Sisneros (UIUC)
    • Lokman Rahmani (INRIA)
    • Leonardo Bautista Gomez (BSC)
    • Luc Bougé (INRIA)

    Elastic provisioning for data streams

    • Kate Keahey (ANL)
    • Gabriel Antoniu (INRIA)
    • Luis Pineda Morales (INRIA)
    • Balaji Subramaniam (ANL)
    • Alexandru Costan (INRIA)

    Modeling and avoiding execution interferences

    • Greg Bauer (NCSA)
    • Raphaël Bleuse (INRIA)
    • Franck Cappello (ANL)
    • Giorgo Lucarelli (INRIA)
    • Denis Trystram (INRIA)
    • Frederic Wagner (INRIA)

    Automatic I/O scheduling algorithm selection for parallel file systems

    • Toni Cortes (BSC)
    • Francieli Zanon Boito (INRIA)
    • Ramon Nou (BSC)
    • Jean-Francois Mehaut (INRIA)
    • Phillipe Navaux (UIUC)

    Network Simulations and Topology-aware Communications

    • Matthieu Dorier (ANL)
    • Nathanael Cheriere (INRIA)
    • Rob Ross (ANL)
    • Gabriel Antoniu (INRIA)
    • Shadi Ibrahim (INRIA)

    The efficient use of modern HPC systems has become one of the key challenges in computational science. Top HPC architectures already provide million-way concurrency, and current trends suggest that processor counts will continue to grow rapidly. There is a broad class of algorithms and methods that are common to several scientific or engineering problems. Ideally, the development of simulation programs follows a layered design in which generic methods are applied to create or extend domain-specific solutions. Such methods must therefore exploit the most efficient algorithms or parallel tools to avoid becoming computational bottlenecks themselves. Within JLESC, the following projects address critical issues in the field of numerical methods and algorithms. The topic leaders are:

  • Paul Hovland (ANL)
  • Luke Olson (UIUC)
  • Luc Giraud (INRIA)
  • Guillaume Houzeaux (BSC)
  • Robert Speck (JSC)
  • Toshiyuki Imamura (RIKEN)

  • Scalability Enhancements to FMM for Molecular Dynamics Simulations

    • Ivo Kabadshow (JSC)
    • Pavan Balaji (ANL)
    • David Haensel (JSC)
    • Abdelhalim Amer (ANL)

    Comparison of Meshing and CFD Methods for Accurate Flow Simulations on HPC systems

    • Andreas Lintermann (JSC)
    • Makoto Tsubokura (RIKEN)
    • Keiji Onishi (RIKEN)

    Fast Integrators for Scalable Quantum Molecular Dynamics

    • Emil Constantinescu (ANL)
    • Andre Schleife (UIUC)

    The ChASE library for large Hermitian eigenvalue problems

    • Edoardo Di Napoli (JSC)
    • Andre Schleife (UIUC)
    • Hiroya Suno (RIKEN)
    • Jan Winkelmann (EXT)

    Dynamic load balancing with Pampa in Alya

    • Guillaume Houzeaux (BSC)
    • Mariano Vázquez (BSC)
    • Vishal Mehta (BSC)
    • Emmanuel Jeannot (INRIA)
    • Cédric Lachat (INRIA)

    HPC libraries for solving dense symmetric eigenvalue problems

    • Toshiyuki Imamura (RIKEN)
    • Inge Gutheil (JSC)

    Reducing Communication in Sparse Iterative and Direct Solvers

    • Luke Olson (UIUC)
    • Amanda Bienz (UIUC)
    • Laura Grigori (INRIA)
    • William Gropp (UIUC)

    Iterative and direct parallel linear solvers in a hybrid MPI/OpenMP high performance computational engineering simulations

    • Pierre Ramet (INRIA)
    • Emmanuel Agullo (INRIA)
    • Antoni Artigues (BSC)
    • Guillaume Houzeaux (BSC)
    • Mariano Vázquez (BSC)

    Shared Infrastructure for Source Transformation Automatic Differentiation

    • Paul Hovland (ANL)
    • Laurent Hascoët (INRIA)
    • Sri Hari Krishna Narayanan (ANL)

    Resilience is a major roadblock for HPC executions on future exascale systems. Projections from current large systems and technology evolution predict errors will happen in exascale systems many times per day. These errors will propagate and generate various kinds of malfunctions, from simple process crashes to result corruptions. The past five years have seen extraordinary technical progress in many domains related to exascale resilience. Several technical options, initially considered inapplicable or unrealistic in the HPC context, have demonstrated surprising successes. Despite this progress, the exascale resilience problem is not solved, and the community is still facing the difficult challenge of ensuring that exascale applications complete and generate correct results while running on unstable systems. Within JLESC, the following projects address critical issues in the field of resilience and fault-tolerant HPC. The topic leaders are:

  • Franck Cappello (ANL)
  • Yves Robert (INRIA)
  • Bill Kramer (UIUC, NCSA)
  • Osman Unsal (BSC)
  • Robert Speck (JSC)
  • Atsushi Hori (RIKEN)

  • Exploiting Active Storage for Resilience

    • Dirk Pleiter (JSC)
    • Andrew A. Chien (ANL)
    • Nan Dun (ANL)
    • Nicholas Vandenbergen (JSC)

    Programming Model Extensions for Resilience

    • Abdelhalim Amer (ANL)
    • Pavan Balaji (ANL)
    • Vicenc Beltran (BSC)
    • Marc Casas (BSC)

    Optimization of Fault-Tolerance Strategies for Workflow Applications

    • Anne Benoit (INRIA)
    • Franck Cappello (ANL)
    • Yves Robert (INRIA)
    • Aurélien Cavelan (INRIA)

    Hybrid resilience for MPI + tasks codes

    • Omer Subasi (BSC)
    • Tatiana V. Martsinkevich (INRIA)
    • Jesus Labarta (BSC)
    • Franck Cappello (ANL)
    • Osman Unsal (BSC)

    Checkpoint/Restart of/from lossy state

    • Franck Cappello (ANL)
    • Luke Olson (UIUC)
    • Jon Calhoun (UIUC)
    • Marc Snir (ANL)

    New Techniques to Design Silent Data Corruption Detectors

    • Leonardo Bautista Gomez (BSC)
    • Prasanna Balaprakash (ANL)
    • Anne Benoit (INRIA)
    • Franck Cappello (ANL)
    • Aurélien Cavelan (INRIA)
    • Yves Robert (INRIA)
    • Omer Subasi (BSC)
    • Hongyang Sun (INRIA)
    • Osman Unsal (BSC)
    • Sheng Di (ANL)

    Parallel architectures enable to target more complex and ambitious problems each year. But in many cases, the achieved performance is far away from what the theoretical values promised us. Performance analysis tools allow application developers to identify and characterize the inefficiencies that caused a poor performance. We consider that this analysis must be the first step towards the optimization of an application. Optimizing without a previous analysis could be like driving without directions as it could mean wasting efforts improving parts of the code that were not the real performance bottlenecks. Within JLESC, the following projects address critical issues in the performance tools and analysis. The topic leaders are:

  • Arnaud Legrand (INRIA)
  • Judit Gimenez (BSC)
  • Bernd Mohr (JSC)
  • Sanjay Kale (UIUC)

  • Use of the Folding profiler to assist on data distribution for heterogeneous memory systems

    • Antonio J. Peña (BSC)
    • Harald Servat (BSC)
    • Lena Oden (JSC)
    • Judit Gimenez (BSC)
    • Jesus Labarta (BSC)
    • Pavan Balaji (ANL)

    Developer tools for porting and tuning parallel applications on extreme-scale parallel systems

    • Brian J.N. Wylie (JSC)
    • Miwako Tsuji (RIKEN)
    • Hitoshi Murai (RIKEN)
    • Christian Feld (JSC)
    • Judit Gimenez (BSC)

    The community has converged since more than a decade towards the model of MPI+OpenMP. While other programming models have been proposed, ultimately the relevant new features proposed by these models were integrated into MPI (RMA for example) and OpenMP (accelerator directives for example). So it is remarkable that MPI and OpenMP are continuously evolving to adapt to changes in architectures. The next generation of systems and the future Exascale systems pose new problems with the non-volatile memory, many cores CPUs and the needs to manage power, to better load balance the execution and to handle a variety of accelerators. In particular, tasks based programming models and runtimes are attractive and need to be refined for these new systems. The topic leaders are:

  • Pavan Balaji (ANL)
  • Jean-Francois Mehaut (INRIA)
  • Marc Snir (ANL)
  • Jesus Labarta (BSC)
  • Ivo Kabadshow (JSC)
  • Mitsuhisa Sato (RIKEN)

  • Scalability Enhancements to FMM for Molecular Dynamics Simulations

    • Ivo Kabadshow (JSC)
    • Pavan Balaji (ANL)
    • David Haensel (JSC)
    • Abdelhalim Amer (ANL)

    Energy Efficiency and Load Balancing

    • Raphael Keller Tesser (INRIA)
    • Edson Luiz Padoin (INRIA)
    • Phillipe Navaux (UIUC)
    • Celsco Mendes (NCSA)
    • Sanjay Kale (UIUC)
    • Jean-Francois Mehaut (INRIA)

    Enhancing Asynchronous Parallelism in OmpSs with Argobots

    • Pavan Balaji (ANL)
    • Sangmin Seo (ANL)
    • Abdelhalim Amer (ANL)
    • Rosa M. Badia (BSC)
    • Jesus Labarta (BSC)
    • Xavier Teruel (BSC)
    • Vicenc Beltran (BSC)

    Dynamic load balancing with Pampa in Alya

    • Guillaume Houzeaux (BSC)
    • Mariano Vázquez (BSC)
    • Vishal Mehta (BSC)
    • Emmanuel Jeannot (INRIA)
    • Cédric Lachat (INRIA)