RT Conference Proceedings
T1 Resilience of Parallel Applications
A1 Losada, Nuria
A1 Martín, María J.
A1 González, Patricia
A2 Carretero Pérez, Jesús
A2 García Blas, Javier
A2 Petcu, Dana
AB Future exascale systems are predicted to be formed by millions of cores. This is a great opportunity for HPCapplications, however, it is also a hazard for the completion of their execution. Even if one computation nodepresents a failure every one century, a machine with 100.000 nodes will encounter a failure every 9 hours. Thus,HPC applications need to make use of fault tolerance techniques to ensure they successfully finish their execution.This PhD thesis is focused on fault tolerance solutions for generic parallel applications, more specifically in checkpointingsolutions. We have extended CPPC, an MPI application-level portable checkpointing tool developed inour research group, to work with OpenMP applications, and hybrid MPI-OpenMP applications. Currently, weare working on transparently obtaining resilient MPI applications, that is, applications that are able to recoverthemselves from failures without stopping their execution.
SN 978-84-608-6309-0
YR 2016
FD 2016-02
LK https://hdl.handle.net/10016/22885
UL https://hdl.handle.net/10016/22885
LA eng
NO Proceedings of the First PhD Symposium on Sustainable UltrascaleComputing Systems (NESUS PhD 2016) Timisoara, Romania. February 8-11, 2016.
NO European Cooperation in Science and Technology. COST
NO This research was supported by the Ministry of Economy and Competitiveness of Spain and FEDER fundsof the EU (Project TIN2013-42148-P, and the predoctoral grant of Nuria Losada ref. BES-2014-068066) andby EU under the COST Program Action IC1305: Network for Sustainable Ultrascale Computing (NESUS).
DS e-Archivo
RD 17 jul. 2024