| Item type |
SIG Technical Reports(1) |
| 公開日 |
2017-05-09 |
| タイトル |
|
|
タイトル |
A low overhead trace and compression system for Automotive RTOS |
| タイトル |
|
|
言語 |
en |
|
タイトル |
A low overhead trace and compression system for Automotive RTOS |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
IoT，組込み |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
Hitachi, Ltd. Research and Development |
| 著者所属 |
|
|
|
Hitachi, Ltd. Research and Development |
| 著者所属 |
|
|
|
Hitachi Automotive Systems, Ltd. |
| 著者所属 |
|
|
|
Hitachi Automotive Systems, Ltd. |
| 著者所属 |
|
|
|
Hitachi, Ltd. Research and Development |
| 著者所属(英) |
|
|
|
en |
|
|
Hitachi, Ltd. Research and Development |
| 著者所属(英) |
|
|
|
en |
|
|
Hitachi, Ltd. Research and Development |
| 著者所属(英) |
|
|
|
en |
|
|
Hitachi Automotive Systems, Ltd. |
| 著者所属(英) |
|
|
|
en |
|
|
Hitachi Automotive Systems, Ltd. |
| 著者所属(英) |
|
|
|
en |
|
|
Hitachi, Ltd. Research and Development |
| 著者名 |
Jairo, Lopez
Taku, Shimosawa
Kazuyoshi, Serizawa
Tomohito, Ebina
Hiroshi, Mine
|
| 著者名(英) |
Jairo, Lopez
Taku, Shimosawa
Kazuyoshi, Serizawa
Tomohito, Ebina
Hiroshi, Mine
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In the realm of automotive operating systems, there is a strong need to be able to detect, handle and store ECU executions for the automobile to work under stricter functional safety standards. However automotive ECUs run real time operating systems (RTOS) under hard real time constraints with the absolutely bare minimum of computational resources. In order to detect and store ECU executions we designed and implemented a tracer for AUTOSAR compatible RTOS which has a low overhead, saving the start and end of task / ISR and the relative time of execution. On top of this tracer we then built a pattern identification based algorithm that also offers us a lossless compression ratio of 1.27 : 1. Our implementation gives us a worst case overhead of 500 nanoseconds for the tracer and 4600 nanoseconds for the tracer running with the pattern identification method, demonstrating the feasibility of introducing this design into hard real time constrained automotive ECUs. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In the realm of automotive operating systems, there is a strong need to be able to detect, handle and store ECU executions for the automobile to work under stricter functional safety standards. However automotive ECUs run real time operating systems (RTOS) under hard real time constraints with the absolutely bare minimum of computational resources. In order to detect and store ECU executions we designed and implemented a tracer for AUTOSAR compatible RTOS which has a low overhead, saving the start and end of task / ISR and the relative time of execution. On top of this tracer we then built a pattern identification based algorithm that also offers us a lossless compression ratio of 1.27 : 1. Our implementation gives us a worst case overhead of 500 nanoseconds for the tracer and 4600 nanoseconds for the tracer running with the pattern identification method, demonstrating the feasibility of introducing this design into hard real time constrained automotive ECUs. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AN10444176 |
| 書誌情報 |
研究報告システムソフトウェアとオペレーティング・システム（OS）
巻 2017-OS-140,
号 8,
p. 1-7,
発行日 2017-05-09
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8795 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-OS17140008.pdf (747.1 kB)
