作者: J. Wingstrom , H. Casanova
DOI:
关键词:
摘要: Desktop grids are compute platforms that aggregate and harvest the idle CPU cycles of individually owned personal computers workstations. A challenge for using these is resources volatile. Due to this volatility vast majority desktop grid applications embarrassingly parallel high-throughput. Deeper understanding nature resource availability needed enable use a broader class applications. In document we further thanks statistical analysis traces collected on real-world platforms.