Lessons Learned Implementing User-Level Failure Mitigation in MPICH

  title={Lessons Learned Implementing User-Level Failure Mitigation in MPICH},
  author={Wesley Bland and Huiwei Lu and Sangmin Seo and Pavan Balaji},
  journal={2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing},
User-level failure mitigation (ULFM) is becoming the front-running solution for process fault tolerance in MPI. While not yet adopted into the MPI standard, it is being used by applications and libraries and is being considered by the MPI Forum for future inclusion into MPI itself. In this paper, we introduce an implementation of ULFM in MPICH, a high-performance and widely portable implementation of the MPI standard. We demonstrate that while still a reference implementation, the runtime cost… CONTINUE READING