English

Implementation-Oblivious Transparent Checkpoint-Restart for MPI

Distributed, Parallel, and Cluster Computing 2023-09-27 v1
Authors: Yao Xu , Leonid Belyaev , Twinkle Jain , Derek Schafer , Anthony Skjellum , Gene Cooperman
View on arXiv ↗ PDF ↗

Abstract

This work presents experience with traditional use cases of checkpointing on a novel platform. A single codebase (MANA) transparently checkpoints production workloads for major available MPI implementations: "develop once, run everywhere". The new platform enables application developers to compile their application against any of the available standards-compliant MPI implementations, and test each MPI implementation according to performance or other features.

Cite

@article{arxiv.2309.14996,
  title  = {Implementation-Oblivious Transparent Checkpoint-Restart for MPI},
  author = {Yao Xu and Leonid Belyaev and Twinkle Jain and Derek Schafer and Anthony Skjellum and Gene Cooperman},
  journal= {arXiv preprint arXiv:2309.14996},
  year   = {2023}
}

Comments

17 pages, 4 figures

Related papers

View all related →
Distributed, Parallel, and Cluster Computing · Computer Science
MANA for MPI: MPI-Agnostic Network-Agnostic Transparent Checkpointing
Rohan Garg, Gregory Price, Gene Cooperman
2019-04-30
Distributed, Parallel, and Cluster Computing · Computer Science
Improving scalability and reliability of MPI-agnostic transparent checkpointing for production workloads at NERSC
Prashant Singh Chouhan, Harsh Khetawat, Neil Resnik, Twinkle Jain +4
2021-03-17
Distributed, Parallel, and Cluster Computing · Computer Science
MANA-2.0: A Future-Proof Design for Transparent Checkpointing of MPI at Scale
Yao Xu, Zhengji Zhao, Rohan Garg, Harsh Khetawat +2
2021-12-14
Distributed, Parallel, and Cluster Computing · Computer Science
The Case for ABI Interoperability in a Fault Tolerant MPI
Yao Xu, Grace Nansamba, Anthony Skjellum, Gene Cooperman
2025-03-17
Distributed, Parallel, and Cluster Computing · Computer Science
Checkpoint/restart approaches for a thread-based MPI runtime
Julien Adam, Maxime Kermarquer, Jean-Baptiste Besnard, Leonardo Bautista-Gomez +5
2019-06-13
Distributed, Parallel, and Cluster Computing · Computer Science
Enabling Practical Transparent Checkpointing for MPI: A Topological Sort Approach
Yao Xu, Gene Cooperman
2024-08-06
Distributed, Parallel, and Cluster Computing · Computer Science
DMTCP Checkpoint/Restart of MPI Programs via Proxies
Gregory Michael Price
2018-03-28
Distributed, Parallel, and Cluster Computing · Computer Science
MPI Progress For All
Hui Zhou, Robert Latham, Ken Raffenetti, Yanfei Guo +1
2024-07-16
Operating Systems · Computer Science
Transparent Checkpoint-Restart over InfiniBand
Jiajun Cao, Gregory Kerr, Kapil Arya, Gene Cooperman
2014-02-03
Distributed, Parallel, and Cluster Computing · Computer Science
MPI Benchmarking Revisited: Experimental Design and Reproducibility
Sascha Hunold, Alexandra Carpen-Amarie
2016-05-30
Distributed, Parallel, and Cluster Computing · Computer Science
FTHP-MPI: Towards Providing Replication-based Fault Tolerance in a Fault-Intolerant Native MPI Library
Sarthak Joshi, Sathish Vadhiyar
2025-04-15
Distributed, Parallel, and Cluster Computing · Computer Science
Transparent Checkpointing for OpenGL Applications on GPUs
David Hou, Jun Gan, Yue Li, Younes El Idrissi Yazami +1
2021-08-03
Distributed, Parallel, and Cluster Computing · Computer Science
PartRePer-MPI: Combining Fault Tolerance and Performance for MPI Applications
Sarthak Joshi, Sathish Vadhiyar
2023-10-26
Distributed, Parallel, and Cluster Computing · Computer Science
Callback-based Completion Notification using MPI Continuations
Joseph Schuchart, Philipp Samfass, Christoph Niethammer, José Gracia +1
2021-12-23
Distributed, Parallel, and Cluster Computing · Computer Science
Collective Vector Clocks: Low-Overhead Transparent Checkpointing for MPI
Yao Xu, Gene Cooperman
2023-10-09
Distributed, Parallel, and Cluster Computing · Computer Science
Elastic execution of checkpointed MPI applications
Sumeet Gajjar, Saurabh Vaidya
2020-05-18
Distributed, Parallel, and Cluster Computing · Computer Science
PGMPI: Automatically Verifying Self-Consistent MPI Performance Guidelines
Sascha Hunold, Alexandra Carpen-Amarie, Felix Donatus Lübbe, Jesper Larsson Träff
2016-09-05
Distributed, Parallel, and Cluster Computing · Computer Science
Checkpoint-Restart Libraries Must Become More Fault Tolerant
Anthony Skjellum, Derek Schafer
2021-12-22
Distributed, Parallel, and Cluster Computing · Computer Science
Designing an Adaptive Application-Level Checkpoint Management System for Malleable MPI Applications
Jophin John, Michael Gerndt
2022-11-09
Software Engineering · Computer Science
Trustworthy Distributed Certification of Program Execution
Alex Wolf, Marco Edoardo Palma, Pasquale Salza, Harald C. Gall
2025-02-12
Distributed, Parallel, and Cluster Computing · Computer Science
Dependency-Aware Rollback and Checkpoint-Restart for Distributed Task-Based Runtimes
Kiril Dichev, Herbert Jordan, Konstantinos Tovletoglou, Thomas Heller +3
2017-05-30
Distributed, Parallel, and Cluster Computing · Computer Science
System-level Scalable Checkpoint-Restart for Petascale Computing
Jiajun Cao, Kapil Arya, Rohan Garg, Shawn Matott +4
2016-09-27
Distributed, Parallel, and Cluster Computing · Computer Science
MPI Advance : Open-Source Message Passing Optimizations
Amanda Bienz, Derek Schafer, Anthony Skjellum
2023-09-15
Distributed, Parallel, and Cluster Computing · Computer Science
MPI Application Binary Interface Standardization
Jeff R. Hammond, Lisandro Dalcin, Erik Schnetter, Marc Pérache +6
2023-08-23
Distributed, Parallel, and Cluster Computing · Computer Science
Quo Vadis MPI RMA? Towards a More Efficient Use of MPI One-Sided Communication
Joseph Schuchart, Christoph Niethammer, José Gracia, George Bosilca
2021-11-17
R2 v1 2026-06-28T12:32:50.916Z