Salishan 2015 Program
Keynote Address
Failure, Resilience, Opportunity and Innovation | John Daly, Department of Defense
Session 1: The Fault Environment
Building Reliable Chips in the Future: Fact, Fiction or an Oxymoron? | Vikas Chandra, ARM
The Fault Environment Unveiled | Sudhavan Gurumurthi, AMD/University of Virginia
Resiliency for Reliability - Myths and Truths | Shekhar Borkar, Intel Corporation
New Resilience Capabilities with Micron's HCM | David Resnick, Sandia National Laboratories
The Fault Environment Unveiled | Sudhavan Gurumurthi, AMD/University of Virginia
Resiliency for Reliability - Myths and Truths | Shekhar Borkar, Intel Corporation
New Resilience Capabilities with Micron's HCM | David Resnick, Sandia National Laboratories
Session 2: Resilient Numerical Methods
Bend But Don't Break: Prospects for Resilience Without Recovery in Algorithms for Hyperbolic Systems | Jeffrey Hittinger, Lawrence Livermore National Laboratory
Fault Tolerance in Number Library Routines | Jack Dongarra, University of Tennessee
On Numerical Resiliency in Numerical Linear Algebra Solvers | Luc Giraud, INRIA
Application Structure Aware Resilience and Cost Model for Differentiated Recovery | Anshu Dubey, Lawrence Berkeley National Laboratory
Fault Tolerance in Number Library Routines | Jack Dongarra, University of Tennessee
On Numerical Resiliency in Numerical Linear Algebra Solvers | Luc Giraud, INRIA
Application Structure Aware Resilience and Cost Model for Differentiated Recovery | Anshu Dubey, Lawrence Berkeley National Laboratory
Working Dinner
Why HPC Matters | Eng Lim Goh, Silicon Graphics International Corporation
Session 3: System Software and APIs
Data-Driven Decision Making in Resilience | Nathan DeBardeleben, Los Alamos National Laboratory
Revisiting Checkpointing for Exascale-Class Systems | Kurt Ferreira, Sandia National Laboratories
Scalable Program Analyses to Improve Software Reliability | Cindy Rubio-Gonzalez, University of California at Davis
Fault Tolerant Programming Abstractions and Failure Recovery Models for MPI Applications | Ignacio Laguna Peralta, Lawrence Livermore National Laboratory
Revisiting Checkpointing for Exascale-Class Systems | Kurt Ferreira, Sandia National Laboratories
Scalable Program Analyses to Improve Software Reliability | Cindy Rubio-Gonzalez, University of California at Davis
Fault Tolerant Programming Abstractions and Failure Recovery Models for MPI Applications | Ignacio Laguna Peralta, Lawrence Livermore National Laboratory
Random Access
|
So What Is This OCR Thing? | Tim Mattson, Intel Corporation
Metric For System Reliability | Laxmikant Kale, University of Illinois How Google (And the Internet) Do It | Philip Levis, Stanford University LIbfabric: Your New BFF | Sung-Eun Choi, Cray, Inc. IEEE Rebooting Computing | Dave Mountain, Department of Defense What's Easier To Program | John Levesque, Cray, Inc. Correctness Field Testing of LANL HPC Platforms | Sarah Michalak, Los Alamos National Laboratory |
The Impact of ECI | Jim Ang, Sandia National Laboratories
Error Models | Mattan Erez, University of Texas at Austin AMT RTS WG | Robert Clay/Ron Brightwell, Sandia National Laboratories Application I/O Kernels | Ilene Carpenter, National Renewable Energy Lab Scalable Memory Patterns | Si Hammond, Sandia National Laboratories Scalable Network Simulations | Nalini Kumar, University of Florida Reproducibility and ACM | Mike Heroux, Sandia National Laboratories Open-System Adiabatic Quantum Annealing Update | Bob Lucas, Information Sciences Institute |
Session 4: Data Analysis on Uncertain Data
Relaxing Resilience Data Quality Requirements Due to Visualization and Analysis Needs | James Ahrens, Los Alamos National Laboratory
Living With "Dirty" Data While Avoiding Exascale "Garbage In, Garbage Out" | Michael McKerns, California Institute of Technology
Approximate Computing for Approximate Data | Martin Rinard, Massachusetts Institute of Technology
Towards Interactive Analysis and Exploration of the HPC Performance Landscape | Yarden Livnat, University of Utah
Living With "Dirty" Data While Avoiding Exascale "Garbage In, Garbage Out" | Michael McKerns, California Institute of Technology
Approximate Computing for Approximate Data | Martin Rinard, Massachusetts Institute of Technology
Towards Interactive Analysis and Exploration of the HPC Performance Landscape | Yarden Livnat, University of Utah
Session 5: Future Application Development Environment
Three Crazy Ways to Cope With Failure That Will Change Your Apps Forever | Sung-Eun Choi, Cray, Inc.
Quantitatively Modeling Applications Resilience With the Data Vulnerability Factor | Jeffrey Vettter, Georgia Institute of Technology
Global View Resilience: Flexible, Portable, Scalable Application Recovery for Fail-Stop and "Silent" Errors | Andrew Chien, University of Chicago
Exploiting the User's Knowledge of Resilience | Bob Lucas, Information Sciences Instittute
Quantitatively Modeling Applications Resilience With the Data Vulnerability Factor | Jeffrey Vettter, Georgia Institute of Technology
Global View Resilience: Flexible, Portable, Scalable Application Recovery for Fail-Stop and "Silent" Errors | Andrew Chien, University of Chicago
Exploiting the User's Knowledge of Resilience | Bob Lucas, Information Sciences Instittute