Provably and Practically Efficient Granularity Control

Abstract : Over the past decade, many programming languages and systems for parallel-computing have been developed, e.g., Fork/Join and Habanero Java, Parallel Haskell, Parallel ML, and X10. Although these systems raise the level of abstraction for writing parallel codes, performance continues to require labor-intensive optimizations for coarsening the granularity of parallel executions. In this paper, we present provably and practically efficient techniques for controlling granularity within the run-time system of the language. Our starting point is "oracle-guided scheduling", a result from the functional-programming community that shows that granularity can be controlled by an "oracle" that can predict the execution time of parallel codes. We give an algorithm for implementing such an oracle and prove that it has the desired theoretical properties under the nested-parallel programming model. We implement the oracle in C++ by extending Cilk and evaluate its practical performance. The results show that our techniques can essentially eliminate hand tuning while closely matching the performance of hand tuned codes.
Document type :
Conference papers
Complete list of metadatas

Cited literature [44 references]  Display  Hide  Download

https://hal.inria.fr/hal-01973285
Contributor : Arthur Charguéraud <>
Submitted on : Monday, February 4, 2019 - 4:40:20 PM
Last modification on : Thursday, August 1, 2019 - 3:18:19 PM
Long-term archiving on : Sunday, May 5, 2019 - 4:49:20 PM

File

long_version.pdf
Files produced by the author(s)

Identifiers

Citation

Umut Acar, Vitaly Aksenov, Arthur Charguéraud, Mike Rainey. Provably and Practically Efficient Granularity Control. PPoPP 2019 - Principles and Practice of Parallel Programming, Feb 2019, Washington DC, United States. ⟨10.1145/3293883.3295725⟩. ⟨hal-01973285v2⟩

Share

Metrics

Record views

99

Files downloads

470