Architecture and performance of Devito, a system for automated stencil computation
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 4723
- Type
- D - Journal article
- DOI
-
10.1145/3374916
- Title of journal
- ACM Transactions on Mathematical Software
- Article number
- ARTN 6
- First page
- 1
- Volume
- 46
- Issue
- 1
- ISSN
- 0098-3500
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2020
- 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
- Yes
- Number of additional authors
-
9
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Devito automates the finite difference method, inspired by Firedrake, which automates finite element, and is Numfocus-affiliated (https://numfocus.org/sponsored-projects/affiliated-projects). Tutorials given at Intel HPC Conference 2017, Rice Oil and Gas HPC Conference (https://rice2020oghpc.rice.edu/program-2/) and Transform 2020 (https://transform2020.sched.com). Devito supports a large network of industrial and academic users across the world (https://www.devitoproject.org/). Continuing development is funded by Intel, Microsoft, NVIDIA, Shell and DownUnder Geosolutions, who use it in production at scale. Devito Codes Ltd. was spun out (Spring 2020) by Gorman and Luporini (CTO) to provide industrial support for this open-source project.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
