PARMA: Parallelization-Aware Run-time Management for Energy-Efficient Many-Core Systems
- Submitting institution
-
University of Newcastle upon Tyne
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 263822-73169-1292
- Type
- D - Journal article
- DOI
-
10.1109/TC.2020.2975787
- Title of journal
- IEEE Transactions on Computers
- Article number
- -
- First page
- 1507
- Volume
- 69
- Issue
- 10
- ISSN
- 0018-9340
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2020
- URL
-
https://doi.org/10.1109/TC.2020.2975787
- 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
-
5
- Research group(s)
-
E - Secure and Resilient Systems
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper is one of the key outputs from the PRIME EP/K034448/1 programme and STRATA EP/N023641/1 platform grants. It proposes a significant extension of the well-established Amdahl's model for adapting to heterogeneity, culminating in two parallelisation and energy/performance benchmarking tools for many-core systems. This work answers a key research question whether it is possible to achieve an efficient parallelisation without instrumenting the applications. It was crucial for two research proposals on heterogeneous many-core systems modelling. The outputs of this paper led to an industrial grant on runtime methods for tackling the energy/performance trade-offs in highly parallel and heterogeneous systems.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -