Work-first and help-first scheduling policies for async-finish task parallelism

Multiple programming models are emerging to address an increased need for dynamic task parallelism in applications for multicore processors and shared-address-space parallel computing. Examples include OpenMP 3.0, Java Concurrency Utilities, Microsoft Task Parallel Library, Intel Thread Building Blocks, Cilk, X10, Chapel, and Fortress. Scheduling algorithms based on work stealing, as embodied in Cilk’s implementation of dynamic spawnsync parallelism, are gaining in popularity but also have inherent limitations. In this paper, we address the problem of efficient and scalable implementation of X10’s asyncfinish task parallelism, which is more general than Cilk’s spawn-sync parallelism. We introduce a new work-stealing scheduler with compiler support for async-finish task parallelism that can accommodate both work-first and help-first scheduling policies. Performance results on two different multicore SMP platforms show significant improvements due to our new work-stealing al...

• Type: Conference
• Year: 2009
• Where: IPPS
• Authors: Yi Guo, Rajkishore Barik, Raghavan Raman, Vivek Sarkar
• Keywords: Cilk’s Spawn-sync Parallelism, Distributed And Parallel Computing, Dynamic Task Parallelism, IPPS 2009, Task Parallelism