Checkpointing workflows for fail-stop errors
L Han, LC Canon, H Casanova… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
We consider the problem of orchestrating the execution of workflow applications structured
as Directed Acyclic Graphs (DAGs) on parallel computing platforms that are subject to fail …
as Directed Acyclic Graphs (DAGs) on parallel computing platforms that are subject to fail …
LADR: Low-cost application-level detector for reducing silent output corruptions
Applications running on future high performance computing (HPC) systems are more likely
to experience transient faults due to technology scaling trends with respect to higher circuit …
to experience transient faults due to technology scaling trends with respect to higher circuit …
Optimal resilience patterns to cope with fail-stop and silent errors
This work focuses on resilience techniques at extreme scale. Many papers deal with fail-stop
errors. Many others deal with silent errors (or silent data corruptions). But very few papers …
errors. Many others deal with silent errors (or silent data corruptions). But very few papers …
Spatial support vector regression to detect silent errors in the exascale era
As the exascale era approaches, the increasing capacity of high-performance computing
(HPC) systems with targeted power and energy budget goals introduces significant …
(HPC) systems with targeted power and energy budget goals introduces significant …
Exploiting spatial smoothness in HPC applications to detect silent data corruption
L Bautista-Gomez, F Cappello - 2015 IEEE 17th International …, 2015 - ieeexplore.ieee.org
Next-generation supercomputers are expected to have more components and, at the same
time, consume several times less energy per operation. This situation is pushing …
time, consume several times less energy per operation. This situation is pushing …
Exploring the capabilities of support vector machines in detecting silent data corruptions
As the exascale era approaches, the increasing capacity of high-performance computing
(HPC) systems with targeted power and energy budget goals introduces significant …
(HPC) systems with targeted power and energy budget goals introduces significant …
Coping with silent and fail-stop errors at scale by combining replication and checkpointing
This paper provides a model and an analytical study of replication as a technique to cope
with silent errors, as well as a mixture of both silent and fail-stop errors on large-scale …
with silent errors, as well as a mixture of both silent and fail-stop errors on large-scale …
A generic approach to scheduling and checkpointing workflows
This work deals with scheduling and checkpointing strategies to execute scientific workflows
on failure-prone large-scale platforms. To the best of our knowledge, this work is the first to …
on failure-prone large-scale platforms. To the best of our knowledge, this work is the first to …
A visual comparison of silent error propagation
High-performance computing (HPC) systems play a critical role in facilitating scientific
discoveries. Their scale and complexity (eg, the number of computational units and software …
discoveries. Their scale and complexity (eg, the number of computational units and software …
Anomaly detection in scientific datasets using sparse representation
A Moon, M Kim, J Chen, SW Son - Proceedings of the First Workshop on …, 2023 - dl.acm.org
As the size and complexity of high-performance computing (HPC) systems keep growing,
scientists' ability to trust the data produced is paramount due to potential data corruption for …
scientists' ability to trust the data produced is paramount due to potential data corruption for …