Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Main Topics

Schedule

            Speaker

Affiliation

Type of presentation

Title (tentative)

Download

 

 

 

 

 

 

 

Dinner Before the Workshop

7:30 PM

Only people registered for the dinner

 

 

Valpré hotel

 

 

 

 

 

 

 

 

Workshop Day 1

Wednesday June 12th

 

 

 

 

 

 

 

 

 

 

TITLES ARE TEMPORARY (except if in bold font)

 

Registration

08:00

 

 

 

 

 

Welcome and Introduction

Amphitheatre

08:30

Marc Snir + Franck Cappello

INRIA&UIUC&ANL

Background

Welcome, Workshop objectives and organization

 

 

08:45

Bill Kramer

UIUC

Background

NCSA updates and vision of the collaboration

 

 

09:00

Marc Snir

ANL

Background

ANL updates vision of the collaboration

 

 

09:15

Frederic Desprez

Inria

Background

INRIA updates and vision of the collaboration

 

Big systems
Chair: Christian Perez

9:30

Bill Kramer

UIUC

Background

Update on BlueWaters

 

 

10:00

Break

 

 

 

 

 

10:30

Mitsuhisa Sato

U. Tsukuba & AICS

Background

AICS and the K computer

aics-130612.pptx

CANCELED

11:00

Paul Gibbon

Juelich

Background

Meeting the Exascale Challenge at the Juelich Supercomputing Centre.

 

Resilience&fault tolerance  and simulation
Chair: Franck Cappello

11:00

Marc Snir

ANL&UIUC

Report

ICIS report on Resilience

 

 11:30Vincent BaudouiTotal & ANLJoint-ResultsRound-off error and silent soft error propagation in exascale applications 

 

12:00

Lunch

 

 

 

 

Numerical Algorithms
Chair: Frederic Desprez

13:30

Bill Gropp

UIUC

Background

Topics for Collaboration in Numerical Libraries

 


14:00

Paul Hoveland

ANL

Background

Argonne strategic plan in applied math

 

 

14:30

Marc Baboulin

INRIA

Background

Using condition numbers to assess numerical quality in high-performance computing applications

 

 

15:00

Luke Olson

UIUC 

Background

Opportunities in developing a more robust and scalable multigrid solver

 

 15:30Break    

 

16:00

Frederic Nataf

INRIA&P6

Background

Toward black-box adaptive domain decomposition methods

 

Resilience&fault tolerance  and simulation

Chair: Franck Cappello

16:30Bogdan NicolaeIBMJoint Result

AI-Ckpt: Leveraging Memory Access Patterns for Adaptive Asynchronous Incremental Checkpointing

 
 17:00Martin QuisonINRIAResultImproving Simulations of MPI Applications Using A Hybrid Network Model with Topology and Contention Support 

 

17:30

Adjourn

 

 

 

 

 

18:45

Bus for Diner

 

 

 

 

 

 

 

 

 

 

 

Workshop Day 2

Thursday June 13th

 

 

 

 

 

 

 

 

 

 

 

 

Programming Models (cont.)
Chair: Frederic Desprez

08:30

Jean-François Mehaut 

INRIA

Result

Progresses in the European FP7 Mont-Blanc 1 project and objectives of its follow up: Mont-Blanc 2

 

 

09:00

Rajeev Thakur

ANL

Background

Update on MPI and OS/R Activities at Argonne

 

 

09:30

Andra Ecaterina Hugo

INRIA

Results 

Composing multiple StarPU applications over heterogeneous machines: a supervised approach

 

 

10:00

Celso Mendes

UIUC

Background

Dynamic Load Balancing for Weather Models via AMPI

 

 

10:30

Break

 

 

 

 

Big Data, I/O, Visualization
Chair: Kate Keahey

11:00

Dries Kimpe

ANL

Results

Triton: Exascale Storage

 

 

11:30

Gilles Fedak

INRIA

Result

Active Data: A Programming Model to Manage Data Life Cycle Across Heterogeneous Systems and Infrastructures

 

 

12:00

Matthieu Dorrier

INRIA

Joint Result

Data Analysis of Ensemble Simulations: an In Situ Approach using Damaris

 

 

12:30

Ian Foster

ANL

Background

TBA

 

 

13:00

Lunch

 

 

 

 

 

 

 

 

 

 

 

Mini Workshop1

 

 

 

 

 

 

Resilience
Chair: Marc Snir 

14:00

Ana Gainaru

UIUC

Results

Challenges in predicting failures on the Blue Waters system.

 

 

14:30

Xiang Ni

UIUC 

Results

ACR: Automatic Checkpoint/Restart for Soft and Hard Error Protection.

 

 

15:00

Tatiana Martsinkevich

INRIA & ANL

Result

On the feasibility of message logging in hybrid hierarchical FT protocols

 

 

15:30

Mohamed Slim Bouguerra

INRIA & ANL

Result

Investigating the probability distribution of false negative failure alerts in HPC systems

 

 

16:00

Break

 

 

 

 

 

16:30

Amina Guermouche

UVSQ

Result 

Multi-criteria Checkpointing Strategies: Response-time versus Resource Utilization

 

 

17:00

Thomas Ropars

EPFL

Result

Towards efficient replication of HPC applications to deal with crash failures

 

 

17h30

Mehdi Diouri

INRIA 

Result

ECOFIT: A Framework to Estimate Energy Consumption of Fault Tolerance Protocols for HPC Applications

 

 

18:00

Adjourn

 

 

 

 

 

 

 

 

 

 

 

Mini Workshop2

 

 

 

 

 

 

Numerical Algorithms and Libraries
Chair:  Bill Gropp 

14:00

Jean Utke

ANL

Result

Designing and implementing a tool-indedendent, adjoinable MPI wrapper library

 

 

14:30

Laurent Hascoet

INRIA

Result

The adjoint of MPI one-sided communications

 

 

15:00

Stefan Wild,

ANL

Result

Loud computations? Noise in iterative solvers

 

 

15:30

Jed Brown

ANL

Result

Vectorization, communication aggregation, and reuse in stochastic and temporal dimensions

 

 

16:00

Break

 

 

 

 

 

16:30

Yushan Wang

INRIA P11

Result

TBA

 

 

17:00

Frederic Hecht

INRIA/P6

Result

TBA

 

 

18:00

Adjourn

 

 

 

 

 

 

 

 

 

 

 

 

18:45

Bus for diner

 

 

Lyon

 

 

 

 

 

 

 

 

Workshop Day 3

Friday June 14th

 

 

 

 

 

 

 

 

 

 

 

 

Mini Workshop1 (cont.)

 

 

 

 

 

 

Resilience
Chair:  Franck Cappello.

08:30

Di Sheng

INRIA

ResultTBA 

Optimization of Google Cloud Task Processing with Checkpoint-Restart Mechanism 

 

 

09:00

Guillaume Aupy

INRIA

Result

On the Combination of Silent Error Detection and Checkpointing

 

 

09:30

Discussion

 

 

 

 

 

10:00

Break

 

 

 

 

Mini Workshop3 

10:30

Guillaume Mercier

INRIA

Result

TBA

 

Programming and Scheduling 
Chair:  Rajeev Thakur

11:00

Vincent Lanore

INRIA

Result

Static 2D FFT adaptation through a component model based on Charm++

 

 

11:30

Anne Benoit

INRIA

Result

Energy-efficient scheduling

 

 

12:00

François Tessier

INRIA

Result

TBA

 

 

12:30

Discussions

 

 

 

 

 

13:00

Closing and Lunch

 

 

 

 

 

 

 

 

 

 

 

Mini Workshop2 (cont.)

 

 

 

 

 

 

Numerical Algorithms and Libraries 
Chair:  Paul Hovland

08:30

François Pellegrini

INRIA

Result

Shared memory parallel algorithms in Scotch 6

 

 

09:00

Luc Giraud

INRIA 

Result

TBA

 

 

09:30

Discussions

 

 

 

 

 

10:00

Break

 

 

 

 

Mini Workshop4 

10:30

Kate Keahey

ANL 

Result

TBA

 

Clouds 
Chair:  Frederic desprez

11:00

Gabriel Antoniu

INRIA

Result

TBA

 

 

11:30

Christian Perez

INRIA

Result

TBA

 

 

12:00

Eddy Caron

INRIA

Result

TBA

 

 

12:30

Discussions

 

 

 

 

 

13:00

Closing and Lunch

 

 

 

 

...

abstract: Hybrid hierarchical fault tolerance protocols are a promising solution for providing fault tolerance on large scale. A hybrid hierarchical protocol combines coordinated checkpointing and message logging. A lot of work has been done on more efficient implementation of checkpointing protocols, however there are some questions that stay not fully studied with regards to message logging. Message logging requires some portion of the process memory and logged data is flushed to a safe storage together with the checkpoint. There are several possible strategies to take in case where there is not enough memory to log messages between two checkpoints. Each of the strategies will be discussed.

Di Sheng

Optimization of Google Cloud Task Processing with Checkpoint-Restart Mechanism

 

In this paper, we aim at optimizing fault-tolerance techniques based on a checkpointing/restart mechanism, in the context of cloud computing. Our contribution is three-fold. (1) We derive a fresh formula to compute the optimal number of checkpoints for cloud jobs with varied distributions of failure events. Our analysis is not only generic with no assumption on failure probability distribution, but attractively simple to apply in practice. (2) We design an adaptive algorithm to optimize the checkpointing effect regarding various costs like checkpointing/restart overhead. (3) We evaluate our optimized solution in a real cluster environment with hundreds of virtual machines and Berkeley Lab Checkpoint/Restart tool. Task failure events are emulated via a production trace produced on a large-scale Google data center. Experiments confirm that our solution is fairly suitable for Google systems. Our optimized formula outperforms Young’s formula by 3-10 percent, reducing wall-clock lengths by 50-200 seconds per job on average