- author = "Zheng Wang2 and Michael F. P. O'Boyle",
- title = "Machine Learning in Compiler Optimization",
- journal = "Proceedings of the IEEE",
- year = "2018",
- volume = "106",
- number = "11",
- pages = "1879--1901",
- month = nov,
- keywords = "genetic algorithms, genetic programming, SBSE, Compiler, Machine Learning, Code Optimisation, Program Tuning, GPU, OpenCL",
-
URL = "
https://eprints.lancs.ac.uk/id/eprint/89859/1/main.pdf",
-
URL = "
https://doi.org/10.1109/JPROC.2018.2817118",
-
DOI = "
doi:10.1109/JPROC.2018.2817118",
- timestamp = "Fri, 02 Oct 2020 14:42:27 +0200",
-
biburl = "https://dblp.org/rec/journals/pieee/WangO18.bib",
- bibsource = "dblp computer science bibliography, https://dblp.org",
- size = "21 pages",
- abstract = "In the last decade, machine-learning-based compilation has moved from an obscure research niche to a mainstream activity. In this paper, we describe the relationship between machine learning and compiler optimization and introduce the main concepts of features, models, training, and deployment. We then provide a comprehensive survey and provide a road map for the wide variety of different research areas. We conclude with a discussion on open issues in the area and potential research directions. This paper provides both an accessible introduction to the fast moving area of machine-learning-based compilation and a detailed bibliography of its main achievements.",
-
notes = "3) Energy Consumption, especially GPU, OpenMP and
NUMA.
predicting the best compiler flags, eg GPUs CUDA, OpenMP, OpenCL.
loop unroll factor. Petabricks. fast Fourier transformation (FFT) FFTW3. avoid overfitting.Feature Engineering. complied using different compiler passes with different orders. Hardware performance counter values, such as executed instruction counts and cache miss rate. task co-location.
The core issue is that systems are so complex that it is impossible to know for sure when to use such an optimization.
opens up the possibility of much greater creativity and new research areas.",
