Coding Ants: Optimization of GPU code using ant colony optimization. (December 2018)

• Record Type: Journal Article
• Authors: Papenhausen, Eric; Mueller, Klaus
• Is Part Of: Computer languages, systems & structures. Volume 54(2018)
• Page Start: 119
• Page End: 138
• Publication Date: 2018-12
• Subjects: Automatic optimization -- GPU optimization -- Autotuning -- CUDA -- Ant colony optimization -- Polyhedral model; Programming languages (Electronic computers) -- Periodicals; Computer networks -- Periodicals; Computer architecture -- Periodicals; Computer systems -- Periodicals; Langage de programmation; Réseau d'ordinateurs; Architecture d'ordinateur; Périodique électronique (Descripteur de forme); Ressource Internet (Descripteur de forme); 005.13
• DOI: 10.1016/j.cl.2018.05.003
• Languages: English
• ISSNs: 1477-8424

Abstract

Highlights: Devised an optimization framework for parallel programs using ant colony optimization. Several optimizations not typically considered with GPU auto-tuners. Achieved speed-ups of about 3 for GPU platforms coded in CUDA. Use of regression trees and performance metrics led to better performing solutions. Abstract: This article proposes the Coding Ants framework, an approach for auto-tuning which uses ant colony optimization to find a sequence of code optimizations for GPU architectures. The proposed framework is built as an extension to the PPCG compiler, a source-to-source code generator based on the polyhedral model and specializing in the generation of CUDA code. As such, the Coding Ants framework is able to use the polyhedral abstraction to represent a large space of possible transformations. Several optimizations are also presented which have not been included in any previous GPU auto-tuning system. The proposed framework also extends the traditional ant colony optimization algorithm to include performance metrics as well as a regression tree analysis to segment the search space. We evaluate the framework on the PolyBench suite and compare the performance of three levels of optimization that transfer increasing control to the Coding Ants framework from the PPCG cost model.