GPU Concurrency: Weak Behaviours and Programming Assumptions
- Submitting institution
-
The University of Kent
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 9685
- Type
- E - Conference contribution
- DOI
-
10.1145/2694344.2694391
- Title of conference / published proceedings
- Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS '15
- First page
- 577
- Volume
- -
- Issue
- -
- ISSN
- 0362-1340
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2015
- URL
-
https://kar.kent.ac.uk/50272/
- 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
-
7
- Research group(s)
-
-
- Citation count
- 25
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- GPUs are an essential hardware component in commercial electronics. This paper is significant because, until this work, GPU behaviour was considered to be well understood (including by manufacturers). This paper however revealed a class of unexpected behaviours and manufacturer specifications were shown to be incorrect. Subsequently the authors were hired by NVIDIA to incorporate this understanding into their working practices, and their validation toolchain now uses this work. This led to further ongoing collaborations with NVIDIA and AMD.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
