ATF: A generic directive‐based auto‐tuning framework. (17th January 2018)

• Record Type: Journal Article
• Authors: Rasch, Ari; Gorlatch, Sergei
• Other Names: Garcia J. Daniel guestEditor.; Llanos Diego R. guestEditor.
• Is Part Of: Concurrency and computation. Volume 31:Number 5(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-01-17
• Subjects: auto‐tuning -- CLBlast -- CLTune -- CUDA -- dependent tuning parameters -- GEMM -- many‐core -- multi‐core -- multi‐objective auto‐tuning -- OpenCL -- OpenTuner -- tuning parameter constraints; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.4423
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: We describe the Auto‐Tuning Framework (ATF) — a simple‐to‐use, generic approach and its implementation, as a framework for automatic program optimization by choosing the most suitable values of program parameters such as the number of parallel threads, tile sizes, etc. ATF combines four major advantages over the state‐of‐the‐art auto‐tuning: i) it is generic regarding the programming language, application domain, tuning objective (eg, high performance and/or low energy consumption), and search technique; ii) it can auto‐tune a broader class of applications by allowing tuning parameters to be interdependent, eg, when one parameter is divisible by another parameter; iii) it allows tuning parameters to have substantially larger ranges by implementing an optimized search space generation process; and iv) it is arguably simpler to use, eg, the ATF user prepares an application for auto‐tuning by annotating its source code with simple tuning directives. We demonstrate ATF's efficacy by comparing it to the state‐of‐the‐art auto‐tuning approaches, OpenTuner and CLTune; ATF shows better tuning results with less programmer's effort.