Assessing the benefits of fine-grain parallelism in dataflow programs

@inproceedings{Culler1988AssessingTB,
  title={Assessing the benefits of fine-grain parallelism in dataflow programs},
  author={David E. Culler and G. K. Maa},
  booktitle={SC},
  year={1988}
}
A method for assessing the benefits of fine-grain parallelism in “real” programs is presented. The method is based on parallelism profiles and speedup curves derived by executing dataflow graphs on an interpreter under progressively more realistic assumptions about processor resources and communication costs. It is shown that programs, even using traditional algorithms, exhibit ample parallelism when parallelism is exposed at all levels, i.e., within expressions, across nested loops and… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS