LACIO: A New Collective I/O Strategy for Parallel I/O Systems

@article{Chen2011LACIOAN,
  title={LACIO: A New Collective I/O Strategy for Parallel I/O Systems},
  author={Y. Chen and X. Sun and Rajeev Thakur and P. C. Roth and W. Gropp},
  journal={2011 IEEE International Parallel & Distributed Processing Symposium},
  year={2011},
  pages={794-804}
}
  • Y. Chen, X. Sun, +2 authors W. Gropp
  • Published 2011
  • Computer Science
  • 2011 IEEE International Parallel & Distributed Processing Symposium
  • Parallel applications benefit considerably from the rapid advance of processor architectures and the available massive computational capability, but their performance suffers from large latency of I/O accesses. The poor I/O performance has been attributed as a critical cause of the low sustained performance of parallel systems. Collective I/O is widely considered a critical solution that exploits the correlation among I/O accesses from multiple processes of a parallel application and optimizes… CONTINUE READING
    Iteration Based Collective I/O Strategy for Parallel I/O Systems
    • 14
    • PDF
    Revealing applications' access pattern in collective I/O for cache management
    • 17
    • PDF
    Improving Collective I/O Performance Using Non-volatile Memory Devices
    • 11
    • Highly Influenced
    Heterogeneity-Aware Collective I/O for Parallel I/O Systems with Hybrid HDD/SSD Servers
    • 9
    • PDF
    Pre-execution Data Prefetching with Inter-thread I/O Scheduling
    • 4
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 50 REFERENCES
    Data sieving and collective I/O in ROMIO
    • 525
    • PDF
    Improved parallel I/O via a two-phase run-time access strategy
    • 276
    • PDF
    Hiding I/O latency with pre-execution prefetching for parallel applications
    • 59
    • PDF
    Collective buffering: Improving parallel I/O performance
    • 30
    Server-Directed Collective I/O in Panda
    • 206
    Design and evaluation of primitives for parallel I/O
    • 87
    Lightweight I/O for Scientific Applications
    • 79
    • PDF
    Noncontiguous I/O through PVFS
    • 80
    • PDF