ログイン 新規登録
言語:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

  1. シンポジウム
  2. シンポジウムシリーズ
  3. Asia Pacific Conference on Robot IoT System Development and Platform (APRIS)
  4. 2021

Performance Estimation for Embedded Many-core Processor with Software/Hardware Performance Description

https://ipsj.ixsq.nii.ac.jp/records/216180
https://ipsj.ixsq.nii.ac.jp/records/216180
596bc7a1-ba97-4dd3-b4e5-09a36261b6d0
名前 / ファイル ライセンス アクション
IPSJ-APRIS2021004.pdf IPSJ-APRIS2021004.pdf (1.9 MB)
Copyright (c) 2022 by the Information Processing Society of Japan
オープンアクセス
Item type Symposium(1)
公開日 2022-01-28
タイトル
タイトル Performance Estimation for Embedded Many-core Processor with Software/Hardware Performance Description
タイトル
言語 en
タイトル Performance Estimation for Embedded Many-core Processor with Software/Hardware Performance Description
言語
言語 eng
資源タイプ
資源タイプ識別子 http://purl.org/coar/resource_type/c_5794
資源タイプ conference paper
著者所属
Graduate School of Science and Engineering, Saitama University
著者所属
Technology Headquarters eSOL Co., Ltd
著者所属
Graduate School of Science and Engineering, Saitama University
著者所属(英)
en
Graduate School of Science and Engineering, Saitama University
著者所属(英)
en
Technology Headquarters eSOL Co., Ltd
著者所属(英)
en
Graduate School of Science and Engineering, Saitama University
著者名 Yutaro, Kobayashi

× Yutaro, Kobayashi

Yutaro, Kobayashi

Search repository
Hiroshi, Fujimoto

× Hiroshi, Fujimoto

Hiroshi, Fujimoto

Search repository
Takuya, Azumi

× Takuya, Azumi

Takuya, Azumi

Search repository
著者名(英) Yutaro, Kobayashi

× Yutaro, Kobayashi

en Yutaro, Kobayashi

Search repository
Hiroshi, Fujimoto

× Hiroshi, Fujimoto

en Hiroshi, Fujimoto

Search repository
Takuya, Azumi

× Takuya, Azumi

en Takuya, Azumi

Search repository
論文抄録
内容記述タイプ Other
内容記述 Embedded systems, such as automotive systems, are becoming larger and more complex, requiring high computing power and low power consumption. To meet these requirements, multi-/many-core processors and MATLAB/Simulink are increasingly used. Moreover, to support multi-/many-core processors, model-based parallelization tools have been developed. However, the problem of model-based parallelization tools estimated time for each Simulink block has a large error compared to the execution time. Moreover, it is that only hardware information is used to estimate the execution time of parallelized C code. Therefore, the estimation method is proposed to improve the execution time of each Simulink block in comparison with existing methods. Also, a new estimation method is proposed that uses both software and hardware information to estimate the overall execution time. The execution time of the Simulink model is estimated by the conventional method, and the proposed method is measured and compared with the actual execution time to evaluate the proposed method. The experimental results show that the execution time of the parallelized model can be reduced by improving the estimation execution time of each block. It was also found that the use of hardware and software information improved the estimation of the execution time of the parallelized model.
論文抄録(英)
内容記述タイプ Other
内容記述 Embedded systems, such as automotive systems, are becoming larger and more complex, requiring high computing power and low power consumption. To meet these requirements, multi-/many-core processors and MATLAB/Simulink are increasingly used. Moreover, to support multi-/many-core processors, model-based parallelization tools have been developed. However, the problem of model-based parallelization tools estimated time for each Simulink block has a large error compared to the execution time. Moreover, it is that only hardware information is used to estimate the execution time of parallelized C code. Therefore, the estimation method is proposed to improve the execution time of each Simulink block in comparison with existing methods. Also, a new estimation method is proposed that uses both software and hardware information to estimate the overall execution time. The execution time of the Simulink model is estimated by the conventional method, and the proposed method is measured and compared with the actual execution time to evaluate the proposed method. The experimental results show that the execution time of the parallelized model can be reduced by improving the estimation execution time of each block. It was also found that the use of hardware and software information improved the estimation of the execution time of the parallelized model.
書誌情報 Proceedings of Asia Pacific Conference on Robot IoT System Development and Platform

巻 2021, p. 21-28, 発行日 2022-01-28
出版者
言語 ja
出版者 情報処理学会
戻る
0
views
See details
Views

Versions

Ver.1 2025-01-19 15:54:02.591546
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Cite as

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3


Powered by WEKO3