Safe parallel programming using dynamic dependence hints
Proceedings of the 2011 ACM international conference on Object oriented programming systems languages and applications
Hi-index | 0.00 |
The key to performance improvements in the multi-core era is for software to utilize the available concurrency. This paper presents a lightweight programming framework called Gossamer that is easy to use, enables the solution of a broad range of parallel programming problems, and produces efficient code. Gossamer contains (1) a set of high-level annotations that one adds to a sequential program to specify concurrency and synchronization, (2) a source-to-source translator that produces an optimized program that uses our threading library, and (3) a run-time system that provides efficient threads and synchronization. Gossamer supports iterative and recursive parallelism, pipelined computations, domain decomposition, and MapReduce computations.