Automatic adaptive approximation for stencil computations

Abstract : Approximate computing is necessary to meet deadlines in some compute-intensive applications like simulation. Building them requires a high level of expertise from the application designers as well as a significant development effort. Some application programming interfaces greatly facilitate their conception but they still heavily rely on the developer's domain-specific knowledge and require many modifications to successfully generate an approximate version of the program. In this paper we present new techniques to semi-automatically discover relevant approximate computing parameters. We believe that superior compiler-user interaction is the key to improved productivity. After pinpointing the region of interest to optimize, the developer is guided by the compiler in making the best implementation choices. Static analysis and runtime monitoring are used to infer approximation parameter values for the application. We evaluated these techniques on multiple application kernels that support approximation and show that with the help of our method, we achieve similar performance as non-assisted, hand-tuned version while requiring minimal intervention from the user.
Liste complète des métadonnées

https://hal.inria.fr/hal-02072737
Contributor : Maxime Schmitt <>
Submitted on : Tuesday, March 19, 2019 - 2:07:26 PM
Last modification on : Friday, April 5, 2019 - 10:12:53 AM

File

paper.pdf
Files produced by the author(s)

Identifiers

Citation

Maxime Schmitt, Philippe Helluy, Cédric Bastoul. Automatic adaptive approximation for stencil computations. CC 2019 - 28th International Conference on Compiler Construction, Feb 2019, Washington, United States. pp.170-181, ⟨10.1145/3302516.3307348⟩. ⟨hal-02072737⟩

Share

Metrics

Record views

74

Files downloads

171