A Logic Programming Approach to Predict Effective Compiler Settings for Embedded Software
- Submitting institution
-
University of Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96438115
- Type
- E - Conference contribution
- DOI
-
10.1017/S1471068415000174
- Title of conference / published proceedings
- Proceedings of the 31st International Conference on Logic Programming, 4-5 July 2015
- First page
- 481
- Volume
- 15
- Issue
- 4-5
- ISSN
- 1471-0684
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
A - Artificial Intelligence and Autonomy
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- One of the first papers to propose the idea of applying relational data mining to the task of compiler tuning. The approach has the potential to significantly increase software performance and reduce energy consumption while imposing no additional burden on software programmers or compiler developers. Unlike previous work, which selects compiler flags based on a small predetermined set of simple features extracted from the source program, we use a lossless representation of the code from which arbitrarily complex features can be automatically constructed. Demonstrated the benefits of a prototype system on an embedded architecture in relation to the state-of-the-art method.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -