Energy Transparency for Deeply Embedded Programs
- Submitting institution
-
University of Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 108550307
- Type
- D - Journal article
- DOI
-
10.1145/3046679
- Title of journal
- ACM Transactions on Architecture and Code Optimization
- Article number
- 8
- First page
- -
- Volume
- 14
- Issue
- 1
- ISSN
- 1544-3566
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2017
- 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)
-
D - Fundamentals of Computing
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Comprehensive article on making energy consumption of computing transparent from hardware to software. Based on a novel mapping technique first formalized in this paper, we demonstrate how energy consumption of deeply embedded programs can be estimated using advanced modelling techniques together with static resource analysis and a novel target-agnostic profiling-based technique. The energy estimation techniques are evaluated using a comprehensive set of benchmarks, including single- and, for the first time, multithreaded embedded programs. The EUR5.4M H2020 project TeamPlay (Action number: 779882) uses this fundamental approach and AbsInt GmbH (https://www.absint.com/) is developing a new tool, EnergyAnalyser, the first on the market.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -