...
Main Topics | Schedule | Speakers | Types of presentation | Topic | Download |
| Sunday 18th: |
| From Argonne Guest House | The Bus will leave at 6:30PM. Since a bus is available, no taxi will be covered. |
|
Sunday Nov. 18th | Dinner | Giordano's | http://www.giordanos.com/ |
| |
Workshop Day 1 (Room 1416, TCS conference center) | Monday Nov. 19th |
|
|
| |
| 07:30-8:30 | Transportation: Guest House to TCS (building 240) |
| (Entrance of the conference center) |
|
| 08:00 | Contiental Breakfast and Registration |
| Food available in Room 1407, Lunch seating in room 1416 (second half) |
|
Welcome and Introduction | 08:30 | Franck Cappello, INRIA & UIUC, Marc Snir ANL | Opening | Welcome, formal opening and workshop details |
|
| 08:40 | Marc Snir | Opening | ANL presentation and vision of the collaboration |
|
| 08:50 | Bill Gropp | Opening | UIUC/NCSA update and vision of the collaboation |
|
| 09:00 | Frederic Desprez | Opening | INRIA update on HPC strategy and vision of the collaboration |
|
Big Apps, Big DATA - Big I/O | 09:15 | Robert Jacob | Trends in HPC | Climate simulation at extreme scale | |
| 09:45 | Rob Ross, ANL | Trends in HPC | Trends in HPC I/O and File systems |
|
| 10:15 | Break |
|
|
|
| 10:45 | Rob Pennington, NCSA | Trends in HPC | Scientific Data Generators – Plague or a Panacea? | |
| 11:15 | Andrew Chien, ANL | Potential collaboration | Presto/Blockus: Towards a Scalable R Programming System | |
| 11:45 | Matthieu Dorier, INRIA | Joint Results | I/O and in-situ visualization: recent results with the Damaris approach | |
| 12:15 | Lunch |
|
|
|
Programming Models/Runtime chair: Sanjay Kale | 13:30 | Wen-Mei Hwu, UIUC | TBA | Scalability, Performance, and Numerical Stability of Many-core GPU Algorithms - A Case Study of Tri-diagonal Solvers | |
| 14:00 | Pavan Balaji, ANL | Potential collaboration | MPI3 and Unified Runtime | |
| 14:30 | Andra Hugo, Raymond Namyst, INRIA | Potential collaboration | Composing multiple StarPU applications over heterogeneous machines: a supervised approach | |
| 15:00 Jean-François Mehaut | E. Francesquini, INRIA | Potential collaboration |
| |
| 15:30 | Break |
|
|
|
Numerical algorithms and Methods | 16:00 | Stefan Wild, ANL | Potential collaboration | Numerical optimization for "automatic" tuning of codes | |
16:30 | Laura Grigori | Results | Iterative methods, preconditioning, and their application to CMB data analysis | ||
| 17:00 | TBA, ANL | Potiential collaboration | TBA | |
| 17:30 | Laurent Hascoet, INRIA | Early Results | The Data-Dependence graph of Adjoint Codes | |
18:00 | Adjourn |
| |||
19:00 | Dinner | Jameson's |
| ||
|
|
|
|
|
|
Workshop Day 2 (Main room) | Tuesday Nov. 20th |
|
|
|
|
|
|
|
|
|
|
Big Systems | 08:30 | Pete Beckman, ANL | Trends | New Directions in Extreme-Scale Operating Systems and Runtime Software |
|
| 09:00 | Bill Kramer, UIUC/NCSA | Trends | Blue Waters update |
|
Cloud | 09:30 | Ian Foster, ANL | Potential collaboration | Big Process for Big Data | |
| 10:00 | Christine Morin, INRIA | Potential collaboration | Work in Progress on Cloud Computing in Myriads Team and Contrail European Project | |
| 10:30 | Break |
|
|
|
11:00 | Frederic Desprez, INRIA | Potential collaboration | Workflow Allocations and Scheduling on IaaS Platforms, from Theory to Practice | ||
Resilience: | 11:30 | Yves Robert | Early Result | Performance modeling of checkpointing under failure prediction | |
| 12:00 | Rinku Gupta, ANL | Potential collaboration | CIFTS: An infrastructure for coordinated and comprehensive system-wide fault tolerance. |
|
| 12:30 | Ana Gainaru, UIUC | Early Results | Coupling failure prediction, proactive and preventive checkpoint for current production HPC systems. |
|
| 13:00 | Lunch |
| Food buffet in Room 1407, Lunch seating in room 1416 (second half) |
|
|
|
|
| Parallel Session |
|
Mini workshop on Numerical libraries | 8:30 | ||||
| 09:00 | Bill Gropp, UIUC | Potential collaboration | TBA | |
| 09:30 | Laura Grigori, INRIA | Potential collaboration | TBA | |
| 10:00 | Break | TBA | ||
| 10:30 | Anshu Dubey, ANL | Potential collaboration | Optimizing Scientific Codes While Retaining Portability |
|
| 11:00 | Discussion |
|
|
|
| 12:00 | Adjourn |
|
|
|
| 13:00 | Lunch |
|
|
|
|
|
|
| Parallel Sessions |
|
Mini workshop on Performance Modeling and simulation | 14:30 | Sanjay Kale, UIUC | Early Results | BIG SIM |
|
| 15:00 | Arnaud Legrand, INRIA |
| SimGrid for HPC |
|
| 15:30 | Torsten Hoefler, ETH | Early Results | Performance Modeling for Parallel Software Development and Tuning |
|
| 16:00 | Break |
|
|
|
| 16:30 | Timo Schneider, ETH | Early Results | Optimization Principles for Collective Neighborhood Communications |
|
| 17:00 | Discussion |
|
|
|
| 18:00 | Adjourn |
|
|
|
| 19:00 | Dinner | Meggaiano's | [http://www.maggianos.com/EN/Oak-Brook_Oak-Brook_IL/Pages/LocationLanding.aspx?AspxAutoDetectCookieSupport=1 |
|
|
|
|
|
|
|
Mini workshop on Cloud | 14:30 | Kate Keahey, ANL | Potential collaboration | Infrastructure Outsourcing in Multi-Cloud Environment |
|
| 15:00 | Narayan Deai, ANL | Potential collaboration | Building Clouds for Technical Computing |
|
| 15:30 | Jonathan Rouzaud, INRIA | Potential collaboration | Provisioning Virtual Machines in Federated Clouds |
|
| 16:00 | Break |
|
|
|
| 16:30 | Michael Wilde | Potential collaboration | Swift: simpler parallel programming for cloud and HPC domains http://www.ci.uchicago.edu/swift (Swift for clouds and clusters) |
|
| 17:00 | Discussion |
|
|
|
| 18:00 | Adjourn |
|
|
|
| 19:00 | Dinner | Meggaiano's | [http://www.maggianos.com/EN/Oak-Brook_Oak-Brook_IL/Pages/LocationLanding.aspx?AspxAutoDetectCookieSupport=1 |
|
|
|
|
|
|
|
Workshop Day 3 (Main room) | Wednesday Nov 21st |
|
|
|
|
|
|
|
| Parallel Sessions |
|
Mini workshop on Programming models/runtime | 08:30 | Emmanuel Jeannot, INRIA | Results | TBA |
|
09:00 | Sanjay Kale, UIUC | Charm++ update |
| ||
09:30 | Christian Klein, INRIA |
| Cooperative Resource Management for Parallel and Distributed Systems |
| |
10:00 | Break |
|
| ||
10:30 | Jim Dinan |
| A One-Sided View of HPC: Global-View Models and Portable Runtime Systems |
| |
11:00 | Sebastien Fourestier | Potential collaboration | Parallel repartitioning and re-mapping in Scotch |
| |
| 11:30 | Discussion |
|
|
|
| 12:30 | Closing |
|
|
|
| 13:00 | Lunch |
|
|
|
|
|
|
|
|
|
Mini workshop on Resilience | 08:30 | Mohamed Slim Bouguerra | Result | TBA |
|
| 09:00 | Amina Guermouche, INRIA | Result | Unified Model for Assessing Checkpointing Protocols at Extreme-Scale |
|
| 09:30 | Bogdan Nicolae, IBM | Result | I-Ckpt: Leveraging memory access patterns and inline collective deduplication to improve scalability of CR |
|
| 10:00 | Break |
|
|
|
| 10:30 | Tatiana Martsinkevich, INRIA | Result | Fully distributed recovery for send-determinism applications |
|
| 11:00 | Peter Brune, ANL | Trends | Multilevel Resiliency for PDE Simulations |
|
| 11:30 | Xiang Ni, Estaban Menese | Results | Scalable in-memory checkpoint with automatic restart on failure |
|
| 12:00 | Discussion |
|
| |
| 12:30 | Closing |
|
|
|
| 13:00 | Lunch |
| Boxe Lunches |
|
...
In this talk we will review recent advances in minizing communication for linear algebra operations. Communication avoiding algorithms refer to a new class of algorithms that provably minimize communication, in terms of both volume of communication and number of messages transferred on the critical path of the algorithms. After a brief introduction of communication avoiding algorithms for dense operations that have been introduced in the recent years, this talk will focus mainly on iterative methods, incomplete LU factorizations, two level preconditioners, and their impact on a challenging
application in astrophysics, the CMB data analysis.
E. Francesquini (USP Sao Paulo, Université de Grenoble)
The Actor Model and Multi-core ArchitecturesAdvisors: A. Goldman (USP Sao Paulo), J-F. Méhaut (UJF-CEA, Grenoble)
Newest multi-core machines have a hierarchical memory structure, meaning that the time need to send a message from one actor to the other changes significantly depending on their location. This difference is specially noticeable if the machine in question is a NUMA machine. Applications developed using the actor model trust the runtime environment to do an efficient actor-to-core mapping. In this presentation we will show some of our ongoing work that aims at the creation of an efficient actor runtime system for these machine architectures. We will show the importance of taking into account not only the machine architecture but also the application characteristics during the scheduling decisions. In order to validate our findings we will use an actual virtual machine, specifically the Erlang VM, exercised using synthetic benchmarks and real applications such as Sim-Diasca, an open source discrete simulation engine developed in Erlang by EDF Wiki Markup The Actor model for parallel and concurrent programming has been in use for at least two decades \[1\]. However, it was not until recently that the interest in this model has been rekindled due, in part, to the emergence of multi and many-core architectures. In this model, there is no shared memory and the communication is entirely based on message passing.