Accurately measuring overhead, communication time and progression of blocking and nonblocking collective operations at massive scale

@article{Hoefler2010AccuratelyMO,
  title={Accurately measuring overhead, communication time and progression of blocking and nonblocking collective operations at massive scale},
  author={Torsten Hoefler and Timo Schneider and Andrew Lumsdaine},
  journal={IJPEDS},
  year={2010},
  volume={25},
  pages={241-258}
}
Accurate, reproducible and comparable measurement of the overheads, communication times and progression behaviour of blocking and nonblocking collective operations is a complicated task. Although different measurement schemes for blocking collective operations are implemented in well-known benchmarks, many of these schemes introduce different systematic errors in their measurements. We characterise these errors and select a window-based approach as the most accurate method. However, this… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 19 CITATIONS

MPI Benchmarking Revisited: Experimental Design and Reproducibility

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Hierarchical Clock Synchronization in MPI

  • 2018 IEEE International Conference on Cluster Computing (CLUSTER)
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

MPI Overlap: Benchmark and Analysis

  • 2016 45th International Conference on Parallel Processing (ICPP)
  • 2016
VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 28 REFERENCES

Implementation and performance analysis of non-blocking collective operations for MPI

  • Proceedings of the 2007 ACM/IEEE Conference on Supercomputing (SC '07)
  • 2007
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Optimizing non-blocking collective operations for infiniband

  • 2008 IEEE International Symposium on Parallel and Distributed Processing
  • 2008
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Message progression in parallel computing - to thread or not to thread?

  • 2008 IEEE International Conference on Cluster Computing
  • 2008
VIEW 1 EXCERPT

Low-Overhead LogGP Parameter Assessment for Modern Interconnection Networks

  • 2007 IEEE International Parallel and Distributed Processing Symposium
  • 2007
VIEW 1 EXCERPT

Open MPI Collective Operation Performance on Thunderbird

J. Pjesivac-Grbovic
  • Technical report, The University of Tennessee,
  • 2007
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…