- author = "Jason Ansel and Shoaib Kamil and Kalyan Veeramachaneni and Jonathan Ragan-Kelley and Jeffrey Bosboom and Una-May O'Reilly and Saman P. Amarasinghe",
- title = "{OpenTuner}: an extensible framework for program autotuning",
- booktitle = "International Conference on Parallel Architectures and Compilation, PACT '14",
- year = "2014",
- editor = "Jose Nelson Amaral and Josep Torrellas",
- pages = "303--316",
- address = "Edmonton, Canada",
- month = aug # " 24-27",
- publisher = "ACM",
- keywords = "genetic algorithms, genetic programming, genetic improvement, program autotuning, multi-armed bandit problem",
- timestamp = "Thu, 24 Nov 2022 09:18:38 +0100",
-
biburl = "
https://dblp.org/rec/conf/IEEEpact/AnselKVRBOA14.bib",
- bibsource = "dblp computer science bibliography, https://dblp.org",
-
URL = "https://doi.org/10.1145/2628071.2628092",
-
DOI = "
doi:10.1145/2628071.2628092",
-
code_url = "http://opentuner.org/",
- size = "13 pages",
-
abstract = "Program autotuning has been shown to achieve better or
more portable performance in a number of domains.
However, autotuners themselves are rarely portable
between projects, for a number of reasons: using a
domain-informed search space representation is critical
to achieving good results; search spaces can be
intractably large and require advanced machine learning
techniques; and the landscape of search spaces can vary
greatly between different problems, sometimes requiring
domain specific search techniques to explore
efficiently.
This paper introduces OpenTuner, a new open source framework for building domain-specific multi-objective program autotuners. OpenTuner supports fully-customizable configuration representations, an extensible technique representation to allow for domain-specific techniques, and an easy to use interface for communicating with the program to be autotuned. A key capability inside OpenTuner is the use of ensembles of disparate search techniques simultaneously; techniques that perform well will dynamically be allocated a larger proportion of tests. We demonstrate the efficacy and generality of OpenTuner by building auto-tuners for 7 distinct projects and 16 total benchmarks, showing speedups over prior techniques of these projects of up to 2.8 fold with little programmer effort.",
-
notes = "Not GP?
GCC_FLAGS GCC_PARAMS. AUC Bandit
Multiple simultaneous search.
time, accuracy, energy, size, confidence. GCC/G++ Flags: fft.c, matrixmultiply.cpp, raytracer.cpp, tsp_ga.cpp Halide: Blur, Wavelet, Bilateral. Linpack PetaBricks: Poisson, Sort, Strassen, Tridiagonal Solver. Stencil, Laplacian, Stencil, Unitary Matrix, Mario",
