Software

Oracle Scheduling: Controlling Granularity in Implicitly Parallel Languages

Download Now Free registration required

Executive Summary

A classic problem in parallel computing is determining whether to execute a task in parallel or sequentially. If small tasks are executed in parallel, the task-creation overheads can be overwhelming. If large tasks are executed sequentially, processors may spin idle. This granularity problem, however well known, is not well understood: broadly applicable solutions remain elusive. The authors propose techniques for controlling granularity in implicitly parallel programming languages. Using a cost semantics for a general-purpose language in the style of the lambda calculus with support for parallelism, they show that task-creation overheads can indeed slow down parallel execution by a multiplicative factor.

  • Format: PDF
  • Size: 456.9 KB