Simulate DAG tasksets execution on multi-cores. This software package supports:
Supported scheduling algorithms:
Support response time analysis (RTA):
Supported execution models:
For random, two distribution functions can be chosen from:
(*) Note the normal distributed model is threshold by 3 delta.
Before run, install Python libraries using pip:
> sudo python3 -m pip install -r "requirements.txt"
Then, run the simulator with:
> python3 src/main.py >> results/result.log
and finally:
> python3 src/analysis.py
The results will be in the results
folder.
To reproduce the results in RTSS 2020 (notice there is a known issue; see below):
> python3 src/rtss_ae.py
data/
: contains all the input data (from the DAG generator).src/
: contains all source code in .py.
main.py
: the main file of the DAG simulatorrta_alphabeta_new.py
: the proposed priority ordering and (alpha, beta) response time analysisresults/
: save all the intermediate raw results.outputs/
: save all the produced diagrams.requirements.txt
: Python libraries that are required.README.md
: the repository readme document (this file).rtss2020-ae
by using $ git checkout rtss2020-ae
.Please cite the following paper if you use this code in your work:
Shuai Zhao, Xiaotian Dai, Iain Bate, Alan Burns and Wanli Chang. DAG Scheduling and Analysis on Multiprocessor Systems: Exploitation of Parallelism and Dependency. The IEEE Real-Time Systems Symposium. 2020.
BibTex entry:
@inproceedings{zhao2020dag,
title={DAG Scheduling and Analysis on Multiprocessor Systems: Exploitation of Parallelism and Dependency},
author={Zhao, Shuai and Dai, Xiaotian and Bate, Iain and Burns, Alan and Chang, Wanli},
booktitle={IEEE Real-Time Systems Symposium},
year={2020},
organization={IEEE}
}
MIT License