Scalable failure masking for stencil computations using ghost region expansion and cell to rank remapping

DOI10.1137/16M1081610MaRDI QIDQ5372633zbMATH OpenOpenAlexFDO

Authors Marc Gamell, Keita Teranishi, H. Kolla, Jackson R. Mayo, Michael A. Heroux, J. H. Chen, Manish Parashar

Publication date 27 October 2017

Published in SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/16m1081610

zbMATH Keywords

parallel computingfault tolerancestencil computation

Mathematics Subject Classification ID

Parallel numerical computation (65Y05) Reliability, testing and fault tolerance of networks and computer systems (68M15) Distributed systems (68M14)

Recommendations

• A minimally intrusive low-memory approach to resilience for existing transient solvers
• Resilience for massively parallel multigrid solvers
• Fault tolerant algorithms for heat transfer problems
• Towards local-failure local-recovery in PDE frameworks: the case of linear solvers
• scientific article; zbMATH DE number 5503714

Cites work

• Algorithm-based fault tolerance for FFT networks
• Scalable failure masking for stencil computations using ghost region expansion and cell to rank remapping

Cited in

(2)

• Erasure coding for fault-oblivious linear system solvers
• Scalable failure masking for stencil computations using ghost region expansion and cell to rank remapping

This page was built for publication: Scalable failure masking for stencil computations using ghost region expansion and cell to rank remapping

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5372633)