CRAFT: A library for easier application-level Checkpoint/Restart and Automatic Fault Tolerance

Faisal Shahzad; Jonas Thies; Moritz Kreutzer; Thomas Zeiser; Georg Hager; Gerhard Wellein

doi:10.1109/TPDS.2018.2866794

CRAFT: A library for easier application-level Checkpoint/Restart and Automatic Fault Tolerance

Faisal Shahzad, Jonas Thies, Moritz Kreutzer, Thomas Zeiser, Georg Hager, Gerhard Wellein

Research output: Contribution to journal › Article › Scientific › peer-review

30 Citations (Scopus)

Abstract

In order to efficiently use the future generations of supercomputers, fault tolerance and power consumption are two of the prime challenges anticipated by the High Performance Computing (HPC) community. Checkpoint/Restart (CR) has been and still is the most widely used technique to deal with hard failures. Application-level CR is the most effective CR technique in terms of overhead efficiency but it takes a lot of implementation effort.

Original language	English
Journal	IEEE Transactions on Parallel and Distributed Systems
DOIs	https://doi.org/10.1109/TPDS.2018.2866794
Publication status	Published - 2018
Externally published	Yes

Keywords

Application-level checkpoint/restart
automatic fault tolerance
Checkpointing
Fault tolerance
Fault tolerant systems
Hardware
Kernel
Libraries
User-Level Failure Mitigation (ULFM

Access to Document

10.1109/TPDS.2018.2866794

Cite this

@article{7caf20618d6343e391b4f98b5b80ef9a,

title = "CRAFT: A library for easier application-level Checkpoint/Restart and Automatic Fault Tolerance",

abstract = "In order to efficiently use the future generations of supercomputers, fault tolerance and power consumption are two of the prime challenges anticipated by the High Performance Computing (HPC) community. Checkpoint/Restart (CR) has been and still is the most widely used technique to deal with hard failures. Application-level CR is the most effective CR technique in terms of overhead efficiency but it takes a lot of implementation effort.",

keywords = "Application-level checkpoint/restart, automatic fault tolerance, Checkpointing, Fault tolerance, Fault tolerant systems, Hardware, Kernel, Libraries, User-Level Failure Mitigation (ULFM",

author = "Faisal Shahzad and Jonas Thies and Moritz Kreutzer and Thomas Zeiser and Georg Hager and Gerhard Wellein",

year = "2018",

doi = "10.1109/TPDS.2018.2866794",

language = "English",

journal = "IEEE Transactions on Parallel and Distributed Systems",

issn = "1045-9219",

publisher = "IEEE",

}

TY - JOUR

T1 - CRAFT

T2 - A library for easier application-level Checkpoint/Restart and Automatic Fault Tolerance

AU - Shahzad, Faisal

AU - Thies, Jonas

AU - Kreutzer, Moritz

AU - Zeiser, Thomas

AU - Hager, Georg

AU - Wellein, Gerhard

PY - 2018

Y1 - 2018

N2 - In order to efficiently use the future generations of supercomputers, fault tolerance and power consumption are two of the prime challenges anticipated by the High Performance Computing (HPC) community. Checkpoint/Restart (CR) has been and still is the most widely used technique to deal with hard failures. Application-level CR is the most effective CR technique in terms of overhead efficiency but it takes a lot of implementation effort.

AB - In order to efficiently use the future generations of supercomputers, fault tolerance and power consumption are two of the prime challenges anticipated by the High Performance Computing (HPC) community. Checkpoint/Restart (CR) has been and still is the most widely used technique to deal with hard failures. Application-level CR is the most effective CR technique in terms of overhead efficiency but it takes a lot of implementation effort.

KW - Application-level checkpoint/restart

KW - automatic fault tolerance

KW - Checkpointing

KW - Fault tolerance

KW - Fault tolerant systems

KW - Hardware

KW - Kernel

KW - Libraries

KW - User-Level Failure Mitigation (ULFM

UR - http://www.scopus.com/inward/record.url?scp=85052702633&partnerID=8YFLogxK

U2 - 10.1109/TPDS.2018.2866794

DO - 10.1109/TPDS.2018.2866794

M3 - Article

AN - SCOPUS:85052702633

SN - 1045-9219

JO - IEEE Transactions on Parallel and Distributed Systems

JF - IEEE Transactions on Parallel and Distributed Systems

ER -

CRAFT: A library for easier application-level Checkpoint/Restart and Automatic Fault Tolerance

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this