Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load Tasks
Recent developments in autonomous driving systems highlight the significance of response time analysis. In autonomous driving systems, the complexities of response time analysis stem from different periods of tasks, tasks with high computational demands (high-load tasks), and Directed Acyclic Graph...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10857337/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832088105074556928 |
|---|---|
| author | Tomoya Kobayashi Ryo Okamura Takuya Azumi |
| author_facet | Tomoya Kobayashi Ryo Okamura Takuya Azumi |
| author_sort | Tomoya Kobayashi |
| collection | DOAJ |
| description | Recent developments in autonomous driving systems highlight the significance of response time analysis. In autonomous driving systems, the complexities of response time analysis stem from different periods of tasks, tasks with high computational demands (high-load tasks), and Directed Acyclic Graph (DAG) structures. Although Cause-Effect Chain can consider tasks that are activated at different periods, there is no method that can handle high-load tasks. This paper proposes an allocation algorithm that assigns multiple processor cores to a single task and response time analysis using the Cause-Effect Chain in systems that include high-load tasks is realized. In addition, this paper extends a response time bound of Cause-Effect Chain, and proposes a response time bound of systems with DAG structures. The proposed algorithm and the proposed response time bound are evaluated by task sets generated from measured autonomous driving data. The evaluation results show that the proposed algorithm consistently indicates higher acceptance rates than existing algorithms. Furthermore, the proposed response time bound for the DAG can estimate response times that are shorter than existing bounds. |
| format | Article |
| id | doaj-art-eab5b8adcd2549a8b13b200198d909a8 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-eab5b8adcd2549a8b13b200198d909a82025-02-06T00:00:32ZengIEEEIEEE Access2169-35362025-01-0113215572156810.1109/ACCESS.2025.353601310857337Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load TasksTomoya Kobayashi0https://orcid.org/0009-0000-4937-9697Ryo Okamura1Takuya Azumi2Graduate School of Science and Engineering, Saitama University, Saitama, JapanGraduate School of Science and Engineering, Saitama University, Saitama, JapanGraduate School of Science and Engineering, Saitama University, Saitama, JapanRecent developments in autonomous driving systems highlight the significance of response time analysis. In autonomous driving systems, the complexities of response time analysis stem from different periods of tasks, tasks with high computational demands (high-load tasks), and Directed Acyclic Graph (DAG) structures. Although Cause-Effect Chain can consider tasks that are activated at different periods, there is no method that can handle high-load tasks. This paper proposes an allocation algorithm that assigns multiple processor cores to a single task and response time analysis using the Cause-Effect Chain in systems that include high-load tasks is realized. In addition, this paper extends a response time bound of Cause-Effect Chain, and proposes a response time bound of systems with DAG structures. The proposed algorithm and the proposed response time bound are evaluated by task sets generated from measured autonomous driving data. The evaluation results show that the proposed algorithm consistently indicates higher acceptance rates than existing algorithms. Furthermore, the proposed response time bound for the DAG can estimate response times that are shorter than existing bounds.https://ieeexplore.ieee.org/document/10857337/Cause-effect chainDAGmany-core processorsparallelization |
| spellingShingle | Tomoya Kobayashi Ryo Okamura Takuya Azumi Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load Tasks IEEE Access Cause-effect chain DAG many-core processors parallelization |
| title | Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load Tasks |
| title_full | Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load Tasks |
| title_fullStr | Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load Tasks |
| title_full_unstemmed | Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load Tasks |
| title_short | Response Time Analysis With Cause-Effect Chain Considering DAG Structure and High-Load Tasks |
| title_sort | response time analysis with cause effect chain considering dag structure and high load tasks |
| topic | Cause-effect chain DAG many-core processors parallelization |
| url | https://ieeexplore.ieee.org/document/10857337/ |
| work_keys_str_mv | AT tomoyakobayashi responsetimeanalysiswithcauseeffectchainconsideringdagstructureandhighloadtasks AT ryookamura responsetimeanalysiswithcauseeffectchainconsideringdagstructureandhighloadtasks AT takuyaazumi responsetimeanalysiswithcauseeffectchainconsideringdagstructureandhighloadtasks |