Phoenix rebirth: Scalable MapReduce on a large-scale shared-memory system

@article{Yoo2009PhoenixRS,
  title={Phoenix rebirth: Scalable MapReduce on a large-scale shared-memory system},
  author={R. M. Yoo and A. Romano and C. Kozyrakis},
  journal={2009 IEEE International Symposium on Workload Characterization (IISWC)},
  year={2009},
  pages={198-207}
}
  • R. M. Yoo, A. Romano, C. Kozyrakis
  • Published 2009
  • Computer Science
  • 2009 IEEE International Symposium on Workload Characterization (IISWC)
  • Dynamic runtimes can simplify parallel programming by automatically managing concurrency and locality without further burdening the programmer. Nevertheless, implementing such runtime systems for large-scale, shared-memory systems can be challenging. This work optimizes Phoenix, a MapReduce runtime for shared-memory multi-cores and multiprocessors, on a quad-chip, 32-core, 256-thread UltraSPARC T2+ system with NUMA characteristics. We show how a multi-layered approach that comprises… CONTINUE READING
    Decoupled MapReduce for Shared-Memory Multi-Core Architectures
    Resource-Aware MapReduce Runtime for Multi/Many-core Architectures
    A scalable and composable map-reduce system
    1
    SMR: Scalable MapReduce for Multicore Systems
    1
    Rearchitecting MapReduce for Heterogeneous Multicore Processors with Explicitly Managed Memories
    14
    Improved Programming-Language Independent MapReduce on Shared-Memory Systems
    Optimizing mapreduce with low memory requirements for shared-memory systems
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES
    Evaluating MapReduce for Multi-core and Multiprocessor Systems
    1030
    MapReduce for the Cell B.E. Architecture
    66
    Hoard: a scalable memory allocator for multithreaded applications
    486
    Cilk: An Efficient Multithreaded Runtime System
    1699
    MapReduce: simplified data processing on large clusters
    20335
    Corey: An Operating System for Many Cores
    375
    Embracing diversity in the Barrelfish manycore operating system
    127