A failure detector for HPC platforms

George Bosilca, Aurelien Bouteiller, Amina Guermouche, Thomas Hérault, Yves Robert, Pierre Sens, Jack J. Dongarra. A failure detector for HPC platforms. IJHPCA, 32(1):139-158, 2018. [doi]

@article{BosilcaBGHRSD18,
  title = {A failure detector for HPC platforms},
  author = {George Bosilca and Aurelien Bouteiller and Amina Guermouche and Thomas Hérault and Yves Robert and Pierre Sens and Jack J. Dongarra},
  year = {2018},
  doi = {10.1177/1094342017711505},
  url = {https://doi.org/10.1177/1094342017711505},
  researchr = {https://researchr.org/publication/BosilcaBGHRSD18},
  cites = {0},
  citedby = {0},
  journal = {IJHPCA},
  volume = {32},
  number = {1},
  pages = {139-158},
}