Generating performance portable code using rewrite rules: from high-level functional expressions to high-performance OpenCL code
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10593880
- Type
- E - Conference contribution
- DOI
-
10.1145/2784731.2784754
- Title of conference / published proceedings
- Proceedings of the 20th ACM SIGPLAN International Conference on Functional Programming
- First page
- 205
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- September
- 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
-
3
- Research group(s)
-
-
- Citation count
- 30
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Originality: Introduces a novel foundation for performance-portable code generation for GPUs based on functional programming, denotational semantics, dependent typing, and machine learning. Significance: Formal basis for broad research programme on performance-portable code generation. Follow-up work published at top tier conferences (e.g. CASES 2016, CG 2017 & 2018, ASPLOS 2018). Six PhD projects. Industrial funding from Google, Huawei, Facebook, and Microsoft. Most cited paper at ICFP 2015 (as of June 2020). Rigour: Formalism and optimisations proved correct. Empirical evaluation across 3 architectures. ICFP is the world-leading conference on functional languages. Acceptance rate (1996--2014): 31%.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -